diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..593f2ba684df00ce4efa25956ef2e580614a7b59 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,23 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1875/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b5f93b35a31b76a196c1bc096642d1348bfeb7ae
--- /dev/null
+++ b/README.md
@@ -0,0 +1,56 @@
+---
+library_name: peft
+license: other
+base_model: meta-llama/Llama-3.2-1B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: llama3.2-1b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama3.2-1b
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the mathinstruct dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.4.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/adapter_model.safetensors b/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8dccbd00f8b654b41b87d53e00ede0c2d39d4943
--- /dev/null
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6ca1a286feb5f305d1377fb4b2b4ba22d9b9fc3346cd70c7a0b6f26c723ab9
+size 22573704
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..9aecdedbe38ee7488418ffeffde0ced048359694
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1764404625814323e+17,
+    "train_loss": 0.6465437274932861,
+    "train_runtime": 2365.2475,
+    "train_samples_per_second": 12.684,
+    "train_steps_per_second": 0.793
+}
\ No newline at end of file
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-100/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-100/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c7254c9a587970bc6dd97f4e636cbcc2707d1ffd
--- /dev/null
+++ b/checkpoint-100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ebfa8c8446a8383d729ac24bfa650392fd3ecd4c58d2efeff0073419e84fcb
+size 22573704
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0174857f21c9816e4c3c5c9cd66c444515e6a58c
--- /dev/null
+++ b/checkpoint-100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea1c039fc83872211ec8ea68aa68159022783f3ccb33efdc3d0469417df1b70
+size 45276986
diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..60b5ff8f5384a684a269526e7c23e03a984fbb77
--- /dev/null
+++ b/checkpoint-100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeaf5f81794f7e3eff407ed147d07602da6499cdf39f79193d6603bdbaef56b0
+size 1064
diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-100/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-100/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8e9bf9d78d729f9c3ed94741ba2a0f189d35251
--- /dev/null
+++ b/checkpoint-100/trainer_state.json
@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.16,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6310561256570880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1000/adapter_config.json b/checkpoint-1000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1000/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1000/adapter_model.safetensors b/checkpoint-1000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ac8872cd81a2df0d6790354915714d02c920d561
--- /dev/null
+++ b/checkpoint-1000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801dbf65e3cf855f18cf1685dd560a12a0a65a509250b38b2e2a4ae2a0e77ff3
+size 22573704
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..58f043f851e3d6b4618384b5ead113ecd2a34bc5
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b5765022122d78d8449c5e2f67f8459c8fc4f1a037a31b98ef1047a77ab921
+size 45276986
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e0c21f26fbe9826bba53e91743146a6f18a4468
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aed3fde651f04e541c7e2da7b8b58e5b8fc9fcf1dacfc8254146682f84077c9
+size 1064
diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1000/tokenizer.json b/checkpoint-1000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec34e10aa8c78ece2c0047bcf0a6da02ef47841c
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.240126522831667e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1100/README.md b/checkpoint-1100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1100/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1100/adapter_config.json b/checkpoint-1100/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1100/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1100/adapter_model.safetensors b/checkpoint-1100/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..18a0bd786dcf3fe3b7918b35e6c922d60d1604a2
--- /dev/null
+++ b/checkpoint-1100/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7abf739a40d37ed12434376746bcae636af9a92af6732ea3a553e7b927276e
+size 22573704
diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1d9d0968720d4d5723fc5b064e771bad09742d7a
--- /dev/null
+++ b/checkpoint-1100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df773dc0557d5ee1d30af4e55c93d47161b20f473a41917585beceb57158f450
+size 45276986
diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-1100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f04a32d1baf907c9157b76bef34cfa7539944284
--- /dev/null
+++ b/checkpoint-1100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf616674b42264e305610180821eb0e8f03cfbba013a34bdcde2f8537d5f3c69
+size 1064
diff --git a/checkpoint-1100/special_tokens_map.json b/checkpoint-1100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1100/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1100/tokenizer.json b/checkpoint-1100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1100/tokenizer_config.json b/checkpoint-1100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1100/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff9a783c5895f232d29b35fc63ca00f618b680c5
--- /dev/null
+++ b/checkpoint-1100/trainer_state.json
@@ -0,0 +1,1573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.76,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.87313708080169e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1200/README.md b/checkpoint-1200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1200/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1200/adapter_config.json b/checkpoint-1200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1200/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1200/adapter_model.safetensors b/checkpoint-1200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0c5424ea4f404d1f587c659753f411ba6e884791
--- /dev/null
+++ b/checkpoint-1200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf0cd1315fb42578fcd6e8894dbb7b7851f625319b7773d9e8c97703287791c
+size 22573704
diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cc281997201ac57468eac0315ef7fc9085adfa84
--- /dev/null
+++ b/checkpoint-1200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b44bd95bf1c5cee85797d2b39182fe602837c2698bbf04ae60a4ff443d11813
+size 45276986
diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-1200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..55eeeda0e29bcfad8be82da4ee94785a3f5563a5
--- /dev/null
+++ b/checkpoint-1200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce8836fce4037aad29e963cdec7ec8c16775fff070b0745d426b1929aeb3b03
+size 1064
diff --git a/checkpoint-1200/special_tokens_map.json b/checkpoint-1200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1200/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1200/tokenizer.json b/checkpoint-1200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1200/tokenizer_config.json b/checkpoint-1200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1200/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c0516de9b3540575661a92b8e1efc7c46c8ab65
--- /dev/null
+++ b/checkpoint-1200/trainer_state.json
@@ -0,0 +1,1713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.92,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.518625937385062e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1300/README.md b/checkpoint-1300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1300/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1300/adapter_config.json b/checkpoint-1300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1300/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1300/adapter_model.safetensors b/checkpoint-1300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..38b0b8b048ac8e4a9b3a6033d72aac96349e1c08
--- /dev/null
+++ b/checkpoint-1300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b919733590839c4a71aea19cae3ae9f1ca80b08382c3a68f63fd4066635c5f
+size 22573704
diff --git a/checkpoint-1300/optimizer.pt b/checkpoint-1300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2dc3d0117cc8c51cf4c7aaec019ce6c770808ddc
--- /dev/null
+++ b/checkpoint-1300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f085efe076d51c87f26edef8d9014f5b7a9b01d62e5e96d0a8f826026de0f57
+size 45276986
diff --git a/checkpoint-1300/rng_state.pth b/checkpoint-1300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1300/scheduler.pt b/checkpoint-1300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7a2fb85da7968e8f3d7f3fa43e1b905068c3327e
--- /dev/null
+++ b/checkpoint-1300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9f1578475de7fa30a036952f213791083f9d440f2f723c27ee6b3278e154f
+size 1064
diff --git a/checkpoint-1300/special_tokens_map.json b/checkpoint-1300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1300/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1300/tokenizer.json b/checkpoint-1300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1300/tokenizer_config.json b/checkpoint-1300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1300/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1300/trainer_state.json b/checkpoint-1300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d2bb18d62a2a0956d2a44748fa9d558806a28340
--- /dev/null
+++ b/checkpoint-1300/trainer_state.json
@@ -0,0 +1,1853 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.08,
+  "eval_steps": 500,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.139909901477478e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1300/training_args.bin b/checkpoint-1300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1400/README.md b/checkpoint-1400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1400/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1400/adapter_config.json b/checkpoint-1400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1400/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1400/adapter_model.safetensors b/checkpoint-1400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..09ee73a00ccf5f999739c7257680bd7059e89957
--- /dev/null
+++ b/checkpoint-1400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec089fc34ad501b8c0a8378fe4ca6660a53358dec7456aa53982d7f00d8b485
+size 22573704
diff --git a/checkpoint-1400/optimizer.pt b/checkpoint-1400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..856e66a742660c7c1b6447ff1be0ac1a8cb2e435
--- /dev/null
+++ b/checkpoint-1400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0675dc87578168e92eca0ecde8e13b71f0bf6bdf4d0e1822fe7676291aca7b30
+size 45276986
diff --git a/checkpoint-1400/rng_state.pth b/checkpoint-1400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1400/scheduler.pt b/checkpoint-1400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b7f5fe8c664d2455e487cd7b7ae5713c678ee84c
--- /dev/null
+++ b/checkpoint-1400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965f92ef1c492826aab0266c7f7bca9df480dd00d8819c66c4840910e2350eea
+size 1064
diff --git a/checkpoint-1400/special_tokens_map.json b/checkpoint-1400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1400/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1400/tokenizer.json b/checkpoint-1400/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1400/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1400/tokenizer_config.json b/checkpoint-1400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1400/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1400/trainer_state.json b/checkpoint-1400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..da9eb074c7291c69643034eb32beb2315261f13b
--- /dev/null
+++ b/checkpoint-1400/trainer_state.json
@@ -0,0 +1,1993 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.24,
+  "eval_steps": 500,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.74112334912553e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1400/training_args.bin b/checkpoint-1400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1500/README.md b/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_config.json b/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1500/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_model.safetensors b/checkpoint-1500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d58acfd6befadedd49a95b3ebdceaee9572b76d8
--- /dev/null
+++ b/checkpoint-1500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a764b1b5a93f26da53bdde530ccb8d6167f1799dcf51951ca9dc12cd2fcd8f
+size 22573704
diff --git a/checkpoint-1500/optimizer.pt b/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0320707e16c4c9fb2036393cdc86e0b73094ca01
--- /dev/null
+++ b/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3abbbdfba8d1eb7b323e1e2860db19ff637ca11982a771a79720dbee2fa270
+size 45276986
diff --git a/checkpoint-1500/rng_state.pth b/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1500/scheduler.pt b/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e1b0a614624460fe0d30918ccff590ebd952a443
--- /dev/null
+++ b/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afbb99b66193191c6fbfaa45808387495264b7d5ddd90b54fccbc0033a9c95b6
+size 1064
diff --git a/checkpoint-1500/special_tokens_map.json b/checkpoint-1500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1500/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1500/tokenizer.json b/checkpoint-1500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1500/tokenizer_config.json b/checkpoint-1500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1500/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1500/trainer_state.json b/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..12e4b77dd7334ea238097c242e3ca6da6c69deaa
--- /dev/null
+++ b/checkpoint-1500/trainer_state.json
@@ -0,0 +1,2133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.380974420190822e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1500/training_args.bin b/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1600/README.md b/checkpoint-1600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1600/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1600/adapter_config.json b/checkpoint-1600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1600/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1600/adapter_model.safetensors b/checkpoint-1600/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..abdf7f3146e8c6b8481994f15fd32b28dc33b373
--- /dev/null
+++ b/checkpoint-1600/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337145b61a5001c8b09d6896c4e7f224022d6fa1fd18637ba924032c11327a41
+size 22573704
diff --git a/checkpoint-1600/optimizer.pt b/checkpoint-1600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..53acd7f31fb3a79d2e10bb085a2453169fbd3534
--- /dev/null
+++ b/checkpoint-1600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caea1c237acd1c97587f3784f6b230128367e5a3b6cdea722de3d9b47ab66008
+size 45276986
diff --git a/checkpoint-1600/rng_state.pth b/checkpoint-1600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1600/scheduler.pt b/checkpoint-1600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..55abad80d146bbe0e01861c5346970fd406d6e3a
--- /dev/null
+++ b/checkpoint-1600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ac804f61ed769803ac44a524dacfd9d31977b3b034955eebeef825bec16b3a
+size 1064
diff --git a/checkpoint-1600/special_tokens_map.json b/checkpoint-1600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1600/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1600/tokenizer.json b/checkpoint-1600/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1600/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1600/tokenizer_config.json b/checkpoint-1600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1600/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1600/trainer_state.json b/checkpoint-1600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d85bcecfe762d5eb166535c2bd66ef3210212c81
--- /dev/null
+++ b/checkpoint-1600/trainer_state.json
@@ -0,0 +1,2273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.56,
+  "eval_steps": 500,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.6262741684913635,
+      "learning_rate": 1.8608723480938206e-05,
+      "loss": 0.5715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.8025808334350586,
+      "learning_rate": 1.812485871939056e-05,
+      "loss": 0.5266,
+      "step": 1510
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.8753231167793274,
+      "learning_rate": 1.7646740237157256e-05,
+      "loss": 0.5422,
+      "step": 1515
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6459301710128784,
+      "learning_rate": 1.7174401590239587e-05,
+      "loss": 0.5553,
+      "step": 1520
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.6917416453361511,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 0.5765,
+      "step": 1525
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.7890029549598694,
+      "learning_rate": 1.6247195995785837e-05,
+      "loss": 0.549,
+      "step": 1530
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.9913660883903503,
+      "learning_rate": 1.579239412273078e-05,
+      "loss": 0.4876,
+      "step": 1535
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.9030985832214355,
+      "learning_rate": 1.5343502229386207e-05,
+      "loss": 0.5546,
+      "step": 1540
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.9133403301239014,
+      "learning_rate": 1.4900551820530828e-05,
+      "loss": 0.5356,
+      "step": 1545
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7083793878555298,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 0.5142,
+      "step": 1550
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 1.095435619354248,
+      "learning_rate": 1.40325993882509e-05,
+      "loss": 0.6054,
+      "step": 1555
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8825190663337708,
+      "learning_rate": 1.3607658280716473e-05,
+      "loss": 0.5294,
+      "step": 1560
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.9436343908309937,
+      "learning_rate": 1.3188780485176088e-05,
+      "loss": 0.5294,
+      "step": 1565
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.0125439167022705,
+      "learning_rate": 1.2775995399915631e-05,
+      "loss": 0.4905,
+      "step": 1570
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8476350903511047,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5186,
+      "step": 1575
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.9092681407928467,
+      "learning_rate": 1.196881881330798e-05,
+      "loss": 0.4909,
+      "step": 1580
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.7970360517501831,
+      "learning_rate": 1.1574483962392767e-05,
+      "loss": 0.5303,
+      "step": 1585
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.8575041890144348,
+      "learning_rate": 1.1186355118645554e-05,
+      "loss": 0.5169,
+      "step": 1590
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.7397408485412598,
+      "learning_rate": 1.0804459522284926e-05,
+      "loss": 0.5339,
+      "step": 1595
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7415968179702759,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 0.5283,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.97940656031662e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1600/training_args.bin b/checkpoint-1600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1700/README.md b/checkpoint-1700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1700/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1700/adapter_config.json b/checkpoint-1700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1700/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1700/adapter_model.safetensors b/checkpoint-1700/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d055100aa17299c05a0077273e9be7f1393e1e35
--- /dev/null
+++ b/checkpoint-1700/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270ec35d767b39a3b93e3419f81244f050a2770e9d1c9736aefcb0d7f50e0c3a
+size 22573704
diff --git a/checkpoint-1700/optimizer.pt b/checkpoint-1700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c0c51497804067168da2cc30ebb8bd4f7aff01ad
--- /dev/null
+++ b/checkpoint-1700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3868031bb03724af6642cdb7cac87eca1b9fbb14c5c57acb56307bb79465c50d
+size 45276986
diff --git a/checkpoint-1700/rng_state.pth b/checkpoint-1700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1700/scheduler.pt b/checkpoint-1700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f8624eebc36c0010107fd6b864b21b7c1865182a
--- /dev/null
+++ b/checkpoint-1700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3eec6f9e7ec8904e865b68e83b407d99aebb49c71b712ac6c8770848a2d2ed
+size 1064
diff --git a/checkpoint-1700/special_tokens_map.json b/checkpoint-1700/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1700/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1700/tokenizer.json b/checkpoint-1700/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1700/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1700/tokenizer_config.json b/checkpoint-1700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1700/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1700/trainer_state.json b/checkpoint-1700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..62643c7719b60a79838e4353842b8c7280142f17
--- /dev/null
+++ b/checkpoint-1700/trainer_state.json
@@ -0,0 +1,2413 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7199999999999998,
+  "eval_steps": 500,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.6262741684913635,
+      "learning_rate": 1.8608723480938206e-05,
+      "loss": 0.5715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.8025808334350586,
+      "learning_rate": 1.812485871939056e-05,
+      "loss": 0.5266,
+      "step": 1510
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.8753231167793274,
+      "learning_rate": 1.7646740237157256e-05,
+      "loss": 0.5422,
+      "step": 1515
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6459301710128784,
+      "learning_rate": 1.7174401590239587e-05,
+      "loss": 0.5553,
+      "step": 1520
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.6917416453361511,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 0.5765,
+      "step": 1525
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.7890029549598694,
+      "learning_rate": 1.6247195995785837e-05,
+      "loss": 0.549,
+      "step": 1530
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.9913660883903503,
+      "learning_rate": 1.579239412273078e-05,
+      "loss": 0.4876,
+      "step": 1535
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.9030985832214355,
+      "learning_rate": 1.5343502229386207e-05,
+      "loss": 0.5546,
+      "step": 1540
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.9133403301239014,
+      "learning_rate": 1.4900551820530828e-05,
+      "loss": 0.5356,
+      "step": 1545
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7083793878555298,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 0.5142,
+      "step": 1550
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 1.095435619354248,
+      "learning_rate": 1.40325993882509e-05,
+      "loss": 0.6054,
+      "step": 1555
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8825190663337708,
+      "learning_rate": 1.3607658280716473e-05,
+      "loss": 0.5294,
+      "step": 1560
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.9436343908309937,
+      "learning_rate": 1.3188780485176088e-05,
+      "loss": 0.5294,
+      "step": 1565
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.0125439167022705,
+      "learning_rate": 1.2775995399915631e-05,
+      "loss": 0.4905,
+      "step": 1570
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8476350903511047,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5186,
+      "step": 1575
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.9092681407928467,
+      "learning_rate": 1.196881881330798e-05,
+      "loss": 0.4909,
+      "step": 1580
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.7970360517501831,
+      "learning_rate": 1.1574483962392767e-05,
+      "loss": 0.5303,
+      "step": 1585
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.8575041890144348,
+      "learning_rate": 1.1186355118645554e-05,
+      "loss": 0.5169,
+      "step": 1590
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.7397408485412598,
+      "learning_rate": 1.0804459522284926e-05,
+      "loss": 0.5339,
+      "step": 1595
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7415968179702759,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 0.5283,
+      "step": 1600
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 0.7035180926322937,
+      "learning_rate": 1.0059474843362892e-05,
+      "loss": 0.5576,
+      "step": 1605
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.9805112481117249,
+      "learning_rate": 9.696438046391288e-06,
+      "loss": 0.5136,
+      "step": 1610
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 0.6661838889122009,
+      "learning_rate": 9.339739064316233e-06,
+      "loss": 0.5885,
+      "step": 1615
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.8581559062004089,
+      "learning_rate": 8.989402931500434e-06,
+      "loss": 0.5,
+      "step": 1620
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7146279811859131,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5325,
+      "step": 1625
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.9474234580993652,
+      "learning_rate": 8.307917116538378e-06,
+      "loss": 0.5772,
+      "step": 1630
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 0.9583209753036499,
+      "learning_rate": 7.976815263412963e-06,
+      "loss": 0.5736,
+      "step": 1635
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.7156705260276794,
+      "learning_rate": 7.652171914231776e-06,
+      "loss": 0.5199,
+      "step": 1640
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 0.8224849700927734,
+      "learning_rate": 7.3340098535827905e-06,
+      "loss": 0.5753,
+      "step": 1645
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.8689257502555847,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5424,
+      "step": 1650
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 0.6636053323745728,
+      "learning_rate": 6.717218460270536e-06,
+      "loss": 0.5555,
+      "step": 1655
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.8688860535621643,
+      "learning_rate": 6.418632416150927e-06,
+      "loss": 0.4936,
+      "step": 1660
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 0.6272854208946228,
+      "learning_rate": 6.126614234612593e-06,
+      "loss": 0.6291,
+      "step": 1665
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 1.2240337133407593,
+      "learning_rate": 5.8411844104969916e-06,
+      "loss": 0.5197,
+      "step": 1670
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9820936918258667,
+      "learning_rate": 5.562362976251901e-06,
+      "loss": 0.5398,
+      "step": 1675
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 1.1582359075546265,
+      "learning_rate": 5.290169500525577e-06,
+      "loss": 0.6059,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 0.5501114726066589,
+      "learning_rate": 5.024623086793323e-06,
+      "loss": 0.531,
+      "step": 1685
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.8848717212677002,
+      "learning_rate": 4.765742372016735e-06,
+      "loss": 0.6054,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 0.7358693480491638,
+      "learning_rate": 4.513545525335705e-06,
+      "loss": 0.5173,
+      "step": 1695
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.9218215942382812,
+      "learning_rate": 4.268050246793276e-06,
+      "loss": 0.4944,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0611966095445197e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1700/training_args.bin b/checkpoint-1700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1800/README.md b/checkpoint-1800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1800/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1800/adapter_config.json b/checkpoint-1800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1800/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1800/adapter_model.safetensors b/checkpoint-1800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b4aecf3346bcecbacc7e12e4fe42fa76d1dd530
--- /dev/null
+++ b/checkpoint-1800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0aa6caaaa835f73a08a0f38672aff5ecdffd345851e6ee438b1aae475f7fb4
+size 22573704
diff --git a/checkpoint-1800/optimizer.pt b/checkpoint-1800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b835c159985636ae511870047ef1df567a1856ea
--- /dev/null
+++ b/checkpoint-1800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad02be800eb66fb7021bc5f65353218dc64b0a30d138c00e3f59085a7f0057dc
+size 45276986
diff --git a/checkpoint-1800/rng_state.pth b/checkpoint-1800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1800/scheduler.pt b/checkpoint-1800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7700a21f899d862b51aa9922a23a28f63fc9f25f
--- /dev/null
+++ b/checkpoint-1800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5dc0a991543597746accf379f280ebfcdf588edf4bc55d548208c58399ab795
+size 1064
diff --git a/checkpoint-1800/special_tokens_map.json b/checkpoint-1800/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1800/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1800/tokenizer.json b/checkpoint-1800/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1800/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1800/tokenizer_config.json b/checkpoint-1800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1800/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1800/trainer_state.json b/checkpoint-1800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..efe3e34287a39756ec5f51363aa42c9980d43882
--- /dev/null
+++ b/checkpoint-1800/trainer_state.json
@@ -0,0 +1,2553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.88,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.6262741684913635,
+      "learning_rate": 1.8608723480938206e-05,
+      "loss": 0.5715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.8025808334350586,
+      "learning_rate": 1.812485871939056e-05,
+      "loss": 0.5266,
+      "step": 1510
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.8753231167793274,
+      "learning_rate": 1.7646740237157256e-05,
+      "loss": 0.5422,
+      "step": 1515
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6459301710128784,
+      "learning_rate": 1.7174401590239587e-05,
+      "loss": 0.5553,
+      "step": 1520
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.6917416453361511,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 0.5765,
+      "step": 1525
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.7890029549598694,
+      "learning_rate": 1.6247195995785837e-05,
+      "loss": 0.549,
+      "step": 1530
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.9913660883903503,
+      "learning_rate": 1.579239412273078e-05,
+      "loss": 0.4876,
+      "step": 1535
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.9030985832214355,
+      "learning_rate": 1.5343502229386207e-05,
+      "loss": 0.5546,
+      "step": 1540
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.9133403301239014,
+      "learning_rate": 1.4900551820530828e-05,
+      "loss": 0.5356,
+      "step": 1545
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7083793878555298,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 0.5142,
+      "step": 1550
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 1.095435619354248,
+      "learning_rate": 1.40325993882509e-05,
+      "loss": 0.6054,
+      "step": 1555
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8825190663337708,
+      "learning_rate": 1.3607658280716473e-05,
+      "loss": 0.5294,
+      "step": 1560
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.9436343908309937,
+      "learning_rate": 1.3188780485176088e-05,
+      "loss": 0.5294,
+      "step": 1565
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.0125439167022705,
+      "learning_rate": 1.2775995399915631e-05,
+      "loss": 0.4905,
+      "step": 1570
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8476350903511047,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5186,
+      "step": 1575
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.9092681407928467,
+      "learning_rate": 1.196881881330798e-05,
+      "loss": 0.4909,
+      "step": 1580
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.7970360517501831,
+      "learning_rate": 1.1574483962392767e-05,
+      "loss": 0.5303,
+      "step": 1585
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.8575041890144348,
+      "learning_rate": 1.1186355118645554e-05,
+      "loss": 0.5169,
+      "step": 1590
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.7397408485412598,
+      "learning_rate": 1.0804459522284926e-05,
+      "loss": 0.5339,
+      "step": 1595
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7415968179702759,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 0.5283,
+      "step": 1600
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 0.7035180926322937,
+      "learning_rate": 1.0059474843362892e-05,
+      "loss": 0.5576,
+      "step": 1605
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.9805112481117249,
+      "learning_rate": 9.696438046391288e-06,
+      "loss": 0.5136,
+      "step": 1610
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 0.6661838889122009,
+      "learning_rate": 9.339739064316233e-06,
+      "loss": 0.5885,
+      "step": 1615
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.8581559062004089,
+      "learning_rate": 8.989402931500434e-06,
+      "loss": 0.5,
+      "step": 1620
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7146279811859131,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5325,
+      "step": 1625
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.9474234580993652,
+      "learning_rate": 8.307917116538378e-06,
+      "loss": 0.5772,
+      "step": 1630
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 0.9583209753036499,
+      "learning_rate": 7.976815263412963e-06,
+      "loss": 0.5736,
+      "step": 1635
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.7156705260276794,
+      "learning_rate": 7.652171914231776e-06,
+      "loss": 0.5199,
+      "step": 1640
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 0.8224849700927734,
+      "learning_rate": 7.3340098535827905e-06,
+      "loss": 0.5753,
+      "step": 1645
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.8689257502555847,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5424,
+      "step": 1650
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 0.6636053323745728,
+      "learning_rate": 6.717218460270536e-06,
+      "loss": 0.5555,
+      "step": 1655
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.8688860535621643,
+      "learning_rate": 6.418632416150927e-06,
+      "loss": 0.4936,
+      "step": 1660
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 0.6272854208946228,
+      "learning_rate": 6.126614234612593e-06,
+      "loss": 0.6291,
+      "step": 1665
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 1.2240337133407593,
+      "learning_rate": 5.8411844104969916e-06,
+      "loss": 0.5197,
+      "step": 1670
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9820936918258667,
+      "learning_rate": 5.562362976251901e-06,
+      "loss": 0.5398,
+      "step": 1675
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 1.1582359075546265,
+      "learning_rate": 5.290169500525577e-06,
+      "loss": 0.6059,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 0.5501114726066589,
+      "learning_rate": 5.024623086793323e-06,
+      "loss": 0.531,
+      "step": 1685
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.8848717212677002,
+      "learning_rate": 4.765742372016735e-06,
+      "loss": 0.6054,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 0.7358693480491638,
+      "learning_rate": 4.513545525335705e-06,
+      "loss": 0.5173,
+      "step": 1695
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.9218215942382812,
+      "learning_rate": 4.268050246793276e-06,
+      "loss": 0.4944,
+      "step": 1700
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 0.6374716758728027,
+      "learning_rate": 4.029273766093333e-06,
+      "loss": 0.5183,
+      "step": 1705
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.583243191242218,
+      "learning_rate": 3.797232841391407e-06,
+      "loss": 0.668,
+      "step": 1710
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 0.8384690284729004,
+      "learning_rate": 3.5719437581185454e-06,
+      "loss": 0.5068,
+      "step": 1715
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.8034130334854126,
+      "learning_rate": 3.3534223278382405e-06,
+      "loss": 0.5823,
+      "step": 1720
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.8146041631698608,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 0.6111,
+      "step": 1725
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.8122982382774353,
+      "learning_rate": 2.936743296547273e-06,
+      "loss": 0.5231,
+      "step": 1730
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 0.7326982021331787,
+      "learning_rate": 2.738614939505646e-06,
+      "loss": 0.5236,
+      "step": 1735
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.7472147345542908,
+      "learning_rate": 2.5473127213422763e-06,
+      "loss": 0.5657,
+      "step": 1740
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 0.8197700381278992,
+      "learning_rate": 2.3628500683055222e-06,
+      "loss": 0.5518,
+      "step": 1745
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.8733732104301453,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4908,
+      "step": 1750
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 0.8913092017173767,
+      "learning_rate": 2.014494761575314e-06,
+      "loss": 0.5459,
+      "step": 1755
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 1.1259772777557373,
+      "learning_rate": 1.8506265566567094e-06,
+      "loss": 0.5208,
+      "step": 1760
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 0.7692184448242188,
+      "learning_rate": 1.6936468126984572e-06,
+      "loss": 0.5824,
+      "step": 1765
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.588602602481842,
+      "learning_rate": 1.543566547079467e-06,
+      "loss": 0.5512,
+      "step": 1770
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.6324055790901184,
+      "learning_rate": 1.400396292949513e-06,
+      "loss": 0.6327,
+      "step": 1775
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.7608378529548645,
+      "learning_rate": 1.26414609848996e-06,
+      "loss": 0.5292,
+      "step": 1780
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 0.7972851395606995,
+      "learning_rate": 1.134825526208605e-06,
+      "loss": 0.5692,
+      "step": 1785
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.9705446362495422,
+      "learning_rate": 1.0124436522684243e-06,
+      "loss": 0.5532,
+      "step": 1790
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 0.6317399144172668,
+      "learning_rate": 8.970090658507291e-07,
+      "loss": 0.5314,
+      "step": 1795
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6457757949829102,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 0.524,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.127865302557655e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1800/training_args.bin b/checkpoint-1800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-1875/README.md b/checkpoint-1875/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-1875/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-1875/adapter_config.json b/checkpoint-1875/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-1875/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1875/adapter_model.safetensors b/checkpoint-1875/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8dccbd00f8b654b41b87d53e00ede0c2d39d4943
--- /dev/null
+++ b/checkpoint-1875/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6ca1a286feb5f305d1377fb4b2b4ba22d9b9fc3346cd70c7a0b6f26c723ab9
+size 22573704
diff --git a/checkpoint-1875/optimizer.pt b/checkpoint-1875/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..efd03d94ee8db9b6cf67feff572e90f6452fb2f4
--- /dev/null
+++ b/checkpoint-1875/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaec017289341958e66903a06d4981ed9ffd65aac4d4dfdebf20554f1ecdb0c
+size 45276986
diff --git a/checkpoint-1875/rng_state.pth b/checkpoint-1875/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..323d589b0258d085c7a07b0c4f97b26796e865c5
--- /dev/null
+++ b/checkpoint-1875/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244
diff --git a/checkpoint-1875/scheduler.pt b/checkpoint-1875/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7bcc83046254482bec5329a31b22453caa9506df
--- /dev/null
+++ b/checkpoint-1875/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293fbb7e5ee488097b1b02e80a5587b368df9f7e036db0596e2bbfbbec8e7f45
+size 1064
diff --git a/checkpoint-1875/special_tokens_map.json b/checkpoint-1875/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-1875/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-1875/tokenizer.json b/checkpoint-1875/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1875/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1875/tokenizer_config.json b/checkpoint-1875/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-1875/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-1875/trainer_state.json b/checkpoint-1875/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..20ac21ed0b8e3cd78f09abbc93a7d7b40822a71d
--- /dev/null
+++ b/checkpoint-1875/trainer_state.json
@@ -0,0 +1,2658 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.6262741684913635,
+      "learning_rate": 1.8608723480938206e-05,
+      "loss": 0.5715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.8025808334350586,
+      "learning_rate": 1.812485871939056e-05,
+      "loss": 0.5266,
+      "step": 1510
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.8753231167793274,
+      "learning_rate": 1.7646740237157256e-05,
+      "loss": 0.5422,
+      "step": 1515
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6459301710128784,
+      "learning_rate": 1.7174401590239587e-05,
+      "loss": 0.5553,
+      "step": 1520
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.6917416453361511,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 0.5765,
+      "step": 1525
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.7890029549598694,
+      "learning_rate": 1.6247195995785837e-05,
+      "loss": 0.549,
+      "step": 1530
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.9913660883903503,
+      "learning_rate": 1.579239412273078e-05,
+      "loss": 0.4876,
+      "step": 1535
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.9030985832214355,
+      "learning_rate": 1.5343502229386207e-05,
+      "loss": 0.5546,
+      "step": 1540
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.9133403301239014,
+      "learning_rate": 1.4900551820530828e-05,
+      "loss": 0.5356,
+      "step": 1545
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7083793878555298,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 0.5142,
+      "step": 1550
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 1.095435619354248,
+      "learning_rate": 1.40325993882509e-05,
+      "loss": 0.6054,
+      "step": 1555
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8825190663337708,
+      "learning_rate": 1.3607658280716473e-05,
+      "loss": 0.5294,
+      "step": 1560
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.9436343908309937,
+      "learning_rate": 1.3188780485176088e-05,
+      "loss": 0.5294,
+      "step": 1565
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.0125439167022705,
+      "learning_rate": 1.2775995399915631e-05,
+      "loss": 0.4905,
+      "step": 1570
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8476350903511047,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5186,
+      "step": 1575
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.9092681407928467,
+      "learning_rate": 1.196881881330798e-05,
+      "loss": 0.4909,
+      "step": 1580
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.7970360517501831,
+      "learning_rate": 1.1574483962392767e-05,
+      "loss": 0.5303,
+      "step": 1585
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.8575041890144348,
+      "learning_rate": 1.1186355118645554e-05,
+      "loss": 0.5169,
+      "step": 1590
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.7397408485412598,
+      "learning_rate": 1.0804459522284926e-05,
+      "loss": 0.5339,
+      "step": 1595
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7415968179702759,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 0.5283,
+      "step": 1600
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 0.7035180926322937,
+      "learning_rate": 1.0059474843362892e-05,
+      "loss": 0.5576,
+      "step": 1605
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.9805112481117249,
+      "learning_rate": 9.696438046391288e-06,
+      "loss": 0.5136,
+      "step": 1610
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 0.6661838889122009,
+      "learning_rate": 9.339739064316233e-06,
+      "loss": 0.5885,
+      "step": 1615
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.8581559062004089,
+      "learning_rate": 8.989402931500434e-06,
+      "loss": 0.5,
+      "step": 1620
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7146279811859131,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5325,
+      "step": 1625
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.9474234580993652,
+      "learning_rate": 8.307917116538378e-06,
+      "loss": 0.5772,
+      "step": 1630
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 0.9583209753036499,
+      "learning_rate": 7.976815263412963e-06,
+      "loss": 0.5736,
+      "step": 1635
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.7156705260276794,
+      "learning_rate": 7.652171914231776e-06,
+      "loss": 0.5199,
+      "step": 1640
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 0.8224849700927734,
+      "learning_rate": 7.3340098535827905e-06,
+      "loss": 0.5753,
+      "step": 1645
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.8689257502555847,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5424,
+      "step": 1650
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 0.6636053323745728,
+      "learning_rate": 6.717218460270536e-06,
+      "loss": 0.5555,
+      "step": 1655
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.8688860535621643,
+      "learning_rate": 6.418632416150927e-06,
+      "loss": 0.4936,
+      "step": 1660
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 0.6272854208946228,
+      "learning_rate": 6.126614234612593e-06,
+      "loss": 0.6291,
+      "step": 1665
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 1.2240337133407593,
+      "learning_rate": 5.8411844104969916e-06,
+      "loss": 0.5197,
+      "step": 1670
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9820936918258667,
+      "learning_rate": 5.562362976251901e-06,
+      "loss": 0.5398,
+      "step": 1675
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 1.1582359075546265,
+      "learning_rate": 5.290169500525577e-06,
+      "loss": 0.6059,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 0.5501114726066589,
+      "learning_rate": 5.024623086793323e-06,
+      "loss": 0.531,
+      "step": 1685
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.8848717212677002,
+      "learning_rate": 4.765742372016735e-06,
+      "loss": 0.6054,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 0.7358693480491638,
+      "learning_rate": 4.513545525335705e-06,
+      "loss": 0.5173,
+      "step": 1695
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.9218215942382812,
+      "learning_rate": 4.268050246793276e-06,
+      "loss": 0.4944,
+      "step": 1700
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 0.6374716758728027,
+      "learning_rate": 4.029273766093333e-06,
+      "loss": 0.5183,
+      "step": 1705
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.583243191242218,
+      "learning_rate": 3.797232841391407e-06,
+      "loss": 0.668,
+      "step": 1710
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 0.8384690284729004,
+      "learning_rate": 3.5719437581185454e-06,
+      "loss": 0.5068,
+      "step": 1715
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.8034130334854126,
+      "learning_rate": 3.3534223278382405e-06,
+      "loss": 0.5823,
+      "step": 1720
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.8146041631698608,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 0.6111,
+      "step": 1725
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.8122982382774353,
+      "learning_rate": 2.936743296547273e-06,
+      "loss": 0.5231,
+      "step": 1730
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 0.7326982021331787,
+      "learning_rate": 2.738614939505646e-06,
+      "loss": 0.5236,
+      "step": 1735
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.7472147345542908,
+      "learning_rate": 2.5473127213422763e-06,
+      "loss": 0.5657,
+      "step": 1740
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 0.8197700381278992,
+      "learning_rate": 2.3628500683055222e-06,
+      "loss": 0.5518,
+      "step": 1745
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.8733732104301453,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4908,
+      "step": 1750
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 0.8913092017173767,
+      "learning_rate": 2.014494761575314e-06,
+      "loss": 0.5459,
+      "step": 1755
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 1.1259772777557373,
+      "learning_rate": 1.8506265566567094e-06,
+      "loss": 0.5208,
+      "step": 1760
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 0.7692184448242188,
+      "learning_rate": 1.6936468126984572e-06,
+      "loss": 0.5824,
+      "step": 1765
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.588602602481842,
+      "learning_rate": 1.543566547079467e-06,
+      "loss": 0.5512,
+      "step": 1770
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.6324055790901184,
+      "learning_rate": 1.400396292949513e-06,
+      "loss": 0.6327,
+      "step": 1775
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.7608378529548645,
+      "learning_rate": 1.26414609848996e-06,
+      "loss": 0.5292,
+      "step": 1780
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 0.7972851395606995,
+      "learning_rate": 1.134825526208605e-06,
+      "loss": 0.5692,
+      "step": 1785
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.9705446362495422,
+      "learning_rate": 1.0124436522684243e-06,
+      "loss": 0.5532,
+      "step": 1790
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 0.6317399144172668,
+      "learning_rate": 8.970090658507291e-07,
+      "loss": 0.5314,
+      "step": 1795
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6457757949829102,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 0.524,
+      "step": 1800
+    },
+    {
+      "epoch": 2.888,
+      "grad_norm": 0.8593656420707703,
+      "learning_rate": 6.870136738164612e-07,
+      "loss": 0.5227,
+      "step": 1805
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 1.0187020301818848,
+      "learning_rate": 5.924676063995382e-07,
+      "loss": 0.5993,
+      "step": 1810
+    },
+    {
+      "epoch": 2.904,
+      "grad_norm": 0.7082214951515198,
+      "learning_rate": 5.048983018699827e-07,
+      "loss": 0.5618,
+      "step": 1815
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.6521438956260681,
+      "learning_rate": 4.2431190614309335e-07,
+      "loss": 0.5504,
+      "step": 1820
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.8906036615371704,
+      "learning_rate": 3.50714075049563e-07,
+      "loss": 0.5147,
+      "step": 1825
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 1.0908008813858032,
+      "learning_rate": 2.841099739386066e-07,
+      "loss": 0.5564,
+      "step": 1830
+    },
+    {
+      "epoch": 2.936,
+      "grad_norm": 0.6374122500419617,
+      "learning_rate": 2.2450427731534053e-07,
+      "loss": 0.5188,
+      "step": 1835
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.9616740345954895,
+      "learning_rate": 1.7190116851280026e-07,
+      "loss": 0.5438,
+      "step": 1840
+    },
+    {
+      "epoch": 2.952,
+      "grad_norm": 1.0712924003601074,
+      "learning_rate": 1.2630433939825327e-07,
+      "loss": 0.4962,
+      "step": 1845
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.8226613998413086,
+      "learning_rate": 8.771699011416168e-08,
+      "loss": 0.5021,
+      "step": 1850
+    },
+    {
+      "epoch": 2.968,
+      "grad_norm": 0.9519492983818054,
+      "learning_rate": 5.6141828853573106e-08,
+      "loss": 0.5277,
+      "step": 1855
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.9817518591880798,
+      "learning_rate": 3.1581071670006015e-08,
+      "loss": 0.5764,
+      "step": 1860
+    },
+    {
+      "epoch": 2.984,
+      "grad_norm": 0.7039242386817932,
+      "learning_rate": 1.4036442321962995e-08,
+      "loss": 0.5408,
+      "step": 1865
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 0.591012179851532,
+      "learning_rate": 3.509172151938689e-09,
+      "loss": 0.5014,
+      "step": 1870
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7672661542892456,
+      "learning_rate": 0.0,
+      "loss": 0.6182,
+      "step": 1875
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1764404625814323e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1875/training_args.bin b/checkpoint-1875/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-1875/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-200/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-200/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0f1c797611eceae0cd2fcdbab57546689d78f9bf
--- /dev/null
+++ b/checkpoint-200/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539600392265b6d89a8d665d509d929b2600a637fbeb02dea86f50d822af90eb
+size 22573704
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c8fff132dcd511dc14f780fb1cc6753bd90319a7
--- /dev/null
+++ b/checkpoint-200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e70a973497780780e3ea4b355121e910128937b09a5ab6b36c75b0c413bdc3
+size 45276986
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e01e9dad217e7c9f2c3104afe13d3b3a9d02e67
--- /dev/null
+++ b/checkpoint-200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad6c3134999faf80423953251450284daa031eb6b358fb44f5b77a376ba8c7c
+size 1064
diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-200/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-200/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..877104e06ebe9ccdd53c4fe2a6d2f17918614b72
--- /dev/null
+++ b/checkpoint-200/trainer_state.json
@@ -0,0 +1,313 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2337729827766272e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-300/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-300/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3a9e164f7848d3ceeb7a8574e9a4d2fc97a42956
--- /dev/null
+++ b/checkpoint-300/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66546909729f19b1ecbfea54e9dc990d8916c4593340728298ae3728eb682778
+size 22573704
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7e112dc3094acfea288118f82c040800b913758b
--- /dev/null
+++ b/checkpoint-300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6129d7cf76fdba16b64d9efe52e484780cd067c6e5bbd81d8611e34f61be3c12
+size 45276986
diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fcf445dfe81ee88a19395f4d600f06654fb4dbef
--- /dev/null
+++ b/checkpoint-300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efc5b9509020acd538e103b4c206b5094c7f6f88bb022a2dc967282f3f504a5
+size 1064
diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-300/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-300/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..569f9e85fe079eeacf7ad864906c3e04372799c3
--- /dev/null
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,453 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.48,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8927173541298176e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-400/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-400/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..429fb11aa31bd07de848e9f56e0ef20123fd6663
--- /dev/null
+++ b/checkpoint-400/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ce1932001edf4fdf8680f1b1c8dda73ede7836d4da6e2c42588a1c71654b5e
+size 22573704
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1909aaece302d808d0538ec72239d5c19321d0cc
--- /dev/null
+++ b/checkpoint-400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea5efe7c2cb9b18b562567f4c377b7bed9112b47294674d824efb5cca688a27
+size 45276986
diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..802339c5d72d86401d83baffba15c3e88fddcca4
--- /dev/null
+++ b/checkpoint-400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb37142613edd3d55d2b3a28992c79903ad20ad05e9a18470c93ae5fb7cbcd9
+size 1064
diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-400/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-400/tokenizer.json b/checkpoint-400/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-400/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-400/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..28971800b645de7eeb668153e09a5f361834e40c
--- /dev/null
+++ b/checkpoint-400/trainer_state.json
@@ -0,0 +1,593 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.64,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4987417120866304e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-500/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7d7fa67eb8b7f773aa75d91026ab6928cf6001d3
--- /dev/null
+++ b/checkpoint-500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f602b09099fd49d502876cfed4e02ede39b72ee4dce9a08c723b8062b67a9aec
+size 22573704
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e188800bf8d4996650ca682fcad8ebe413d91b03
--- /dev/null
+++ b/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8167a3ab334ee07b914bbeafe099227d0698c8f0ecbd6e547ffa66ae10d3e8
+size 45276986
diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..630cc0c742bc0d197c96187fb383a7c65d4a16af
--- /dev/null
+++ b/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d1ce3e9d1290a7de2c506ddfff436767e5820ac449f30914f4d4a7a64a91a4
+size 1064
diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-500/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-500/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..61683404ae3d84bd58b27966f6d6588be4e3f53d
--- /dev/null
+++ b/checkpoint-500/trainer_state.json
@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1643762555879424e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-600/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-600/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..68bf7e3144656bf29d1756f047afa29aa5fa540b
--- /dev/null
+++ b/checkpoint-600/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90ad3fd3f6d9166b75049f2923dec2d7a41c604fc09d7dbc458ce454c0ae6a3
+size 22573704
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7ecc89149e6cf98f565294d2e942e8fce44d74fc
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35113237cc4f677cce4d3e7035cd488cb659b7941c9e437ec4cf6188004a734a
+size 45276986
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93a52228ea16468eaab41b66555ced3eaaea002c
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6667fdfb7a029b2c5ae465c109530e3a6d5434c7
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd83495c5da896776fc4a926c71c29ac7d3e1a4836a52655fefe41adedeec40d
+size 1064
diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-600/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-600/tokenizer.json b/checkpoint-600/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-600/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-600/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..804935ed7f99e2b5e04e87c78796a1b6242fbd9a
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,873 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.749352880943923e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-700/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-700/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-700/adapter_model.safetensors b/checkpoint-700/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1dc151de11ef5bfdbb526f0f2bc350bd676cc053
--- /dev/null
+++ b/checkpoint-700/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23aa58d1133b56f2343cecfc1fdc4f51accb88c723c309d15db0158d28d7870
+size 22573704
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad543edf6892ffe3572f3918079d7b69b63ac72f
--- /dev/null
+++ b/checkpoint-700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c50450bc8ab09626757372688e7328d081b7614cc5dc54149bad94fe84d1e
+size 45276986
diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cb8beef15c9e90c10dc2d8c3a573ec157ff9b93f
--- /dev/null
+++ b/checkpoint-700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0efae093702a8aec8960e4abc7014cf4c16fd4059e4e2f122e7a528ba18078
+size 1064
diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-700/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-700/tokenizer.json b/checkpoint-700/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-700/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-700/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b3a03812acbdeecf2f214bc34cc8d8c4b127da72
--- /dev/null
+++ b/checkpoint-700/trainer_state.json
@@ -0,0 +1,1013 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.12,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.320122286794342e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-800/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-800/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..852ebb0b1304796b430cc548f7d1159a0c9ff3a4
--- /dev/null
+++ b/checkpoint-800/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8600ec44a0efc32cf5c719075638ea8ff944a881acdedabdf6ddb6f04160f517
+size 22573704
diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..571ba4eb6c1a04b58b4ae1f3038553d043162d02
--- /dev/null
+++ b/checkpoint-800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3cf72a3adc57837cbe4c2b468f6c4339eb1c93554a66c3b1ff5c745f293174
+size 45276986
diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1de02cc10c419098078f64682645763ad1054bbd
--- /dev/null
+++ b/checkpoint-800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57aea9202da80532acfcd9243ff68caac5326250cc2e03647d8eee08cca191c9
+size 1064
diff --git a/checkpoint-800/special_tokens_map.json b/checkpoint-800/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-800/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-800/tokenizer.json b/checkpoint-800/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-800/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-800/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8f150ace31f5ff7823fe80694faa04a8bca0c9a
--- /dev/null
+++ b/checkpoint-800/trainer_state.json
@@ -0,0 +1,1153 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.28,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.969068985162138e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..31d07dbe00996b0568fd0eb91d05ac9a95722459
--- /dev/null
+++ b/checkpoint-900/README.md
@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.2-1B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0
\ No newline at end of file
diff --git a/checkpoint-900/adapter_config.json b/checkpoint-900/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..73202e5c7ba7132c890e52da7442b36a9efff4dd
--- /dev/null
+++ b/checkpoint-900/adapter_config.json
@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-900/adapter_model.safetensors b/checkpoint-900/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bc454c3b10c17b2e5a9e746185cf223f98c0a05f
--- /dev/null
+++ b/checkpoint-900/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245e5b414a2b1168e45b8b832a3a851bc0ffd4f8bbf6717d77afa76a2e563449
+size 22573704
diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..db68ad93dd1fe6a6a8a0d74734e10725911657f4
--- /dev/null
+++ b/checkpoint-900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f18de82d5d8207f45c8c2c55e1cb81b90b7a17d998dd87c091cf410579097b
+size 45276986
diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..33cefe6919222ddfa3c3946df69b8e5c5a17a0fc
--- /dev/null
+++ b/checkpoint-900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244
diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ddf64790e3baf171fba9c07fc38b3192828bff7d
--- /dev/null
+++ b/checkpoint-900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac0ce7603ccc0b8731e0616e37e36d0ee140ae326f3ed4de11624a836b9b56b
+size 1064
diff --git a/checkpoint-900/special_tokens_map.json b/checkpoint-900/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/checkpoint-900/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/checkpoint-900/tokenizer.json b/checkpoint-900/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-900/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-900/tokenizer_config.json b/checkpoint-900/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/checkpoint-900/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..59a009d30200dcd643f507f42437d3093b09b51a
--- /dev/null
+++ b/checkpoint-900/trainer_state.json
@@ -0,0 +1,1293 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.44,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.645753588278886e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/checkpoint-900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/llamaboard_config.yaml b/llamaboard_config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..0bf5a4170417056674de5ecab1cdc8de81f0d4ee
--- /dev/null
+++ b/llamaboard_config.yaml
@@ -0,0 +1,72 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Llama-3.2-1B
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: linear
+top.template: default
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 16
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 1024
+train.dataset:
+- mathinstruct
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 1
+train.learning_rate: 2e-4
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '10000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.swanlab_api_key: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0
diff --git a/running_log.txt b/running_log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..a7e928a9f8adc460388591ee147d12bbdd4f933d
--- /dev/null
+++ b/running_log.txt
@@ -0,0 +1,1874 @@
+[INFO|2024-12-28 20:32:56] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
+
+[INFO|2024-12-28 20:32:56] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:32:56] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:32:56] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/tokenizer.json
+
+[INFO|2024-12-28 20:32:56] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2024-12-28 20:32:56] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-12-28 20:32:56] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/special_tokens_map.json
+
+[INFO|2024-12-28 20:32:56] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/tokenizer_config.json
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2024-12-28 20:32:57] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:32:57] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/tokenizer.json
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/special_tokens_map.json
+
+[INFO|2024-12-28 20:32:57] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/tokenizer_config.json
+
+[INFO|2024-12-28 20:32:58] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2024-12-28 20:32:58] logging.py:157 >> Add pad token: <|end_of_text|>
+
+[INFO|2024-12-28 20:32:58] logging.py:157 >> Loading dataset TIGER-Lab/MathInstruct...
+
+[INFO|2024-12-28 20:33:03] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:33:03] configuration_utils.py:746 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[WARNING|2024-12-28 20:33:03] logging.py:162 >> Input length is smaller than max length. Consider increase input length.
+
+[INFO|2024-12-28 20:33:03] logging.py:157 >> Using linear scaling strategy and setting scaling factor to 1.0
+
+[INFO|2024-12-28 20:33:03] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/model.safetensors
+
+[INFO|2024-12-28 20:33:03] modeling_utils.py:1670 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2024-12-28 20:33:03] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "eos_token_id": 128001
+}
+
+
+[INFO|2024-12-28 20:33:04] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|2024-12-28 20:33:04] modeling_utils.py:4808 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Llama-3.2-1B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
+
+[INFO|2024-12-28 20:33:04] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/generation_config.json
+
+[INFO|2024-12-28 20:33:04] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9
+}
+
+
+[INFO|2024-12-28 20:33:04] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2024-12-28 20:33:04] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2024-12-28 20:33:04] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2024-12-28 20:33:04] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2024-12-28 20:33:04] logging.py:157 >> Found linear modules: o_proj,down_proj,k_proj,gate_proj,up_proj,v_proj,q_proj
+
+[INFO|2024-12-28 20:33:05] logging.py:157 >> trainable params: 5,636,096 || all params: 1,241,450,496 || trainable%: 0.4540
+
+[INFO|2024-12-28 20:33:05] trainer.py:698 >> Using auto half precision backend
+
+[INFO|2024-12-28 20:33:05] trainer.py:2313 >> ***** Running training *****
+
+[INFO|2024-12-28 20:33:05] trainer.py:2314 >>   Num examples = 10,000
+
+[INFO|2024-12-28 20:33:05] trainer.py:2315 >>   Num Epochs = 3
+
+[INFO|2024-12-28 20:33:05] trainer.py:2316 >>   Instantaneous batch size per device = 16
+
+[INFO|2024-12-28 20:33:05] trainer.py:2319 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+[INFO|2024-12-28 20:33:05] trainer.py:2320 >>   Gradient Accumulation steps = 1
+
+[INFO|2024-12-28 20:33:05] trainer.py:2321 >>   Total optimization steps = 1,875
+
+[INFO|2024-12-28 20:33:05] trainer.py:2322 >>   Number of trainable parameters = 5,636,096
+
+[INFO|2024-12-28 20:33:11] logging.py:157 >> {'loss': 1.2049, 'learning_rate': 2.0000e-04, 'epoch': 0.01}
+
+[INFO|2024-12-28 20:33:18] logging.py:157 >> {'loss': 0.9333, 'learning_rate': 1.9999e-04, 'epoch': 0.02}
+
+[INFO|2024-12-28 20:33:25] logging.py:157 >> {'loss': 0.8671, 'learning_rate': 1.9997e-04, 'epoch': 0.02}
+
+[INFO|2024-12-28 20:33:31] logging.py:157 >> {'loss': 0.7979, 'learning_rate': 1.9994e-04, 'epoch': 0.03}
+
+[INFO|2024-12-28 20:33:36] logging.py:157 >> {'loss': 0.7662, 'learning_rate': 1.9991e-04, 'epoch': 0.04}
+
+[INFO|2024-12-28 20:33:43] logging.py:157 >> {'loss': 0.7929, 'learning_rate': 1.9987e-04, 'epoch': 0.05}
+
+[INFO|2024-12-28 20:33:49] logging.py:157 >> {'loss': 0.7683, 'learning_rate': 1.9983e-04, 'epoch': 0.06}
+
+[INFO|2024-12-28 20:33:56] logging.py:157 >> {'loss': 0.8667, 'learning_rate': 1.9978e-04, 'epoch': 0.06}
+
+[INFO|2024-12-28 20:34:04] logging.py:157 >> {'loss': 0.8446, 'learning_rate': 1.9972e-04, 'epoch': 0.07}
+
+[INFO|2024-12-28 20:34:09] logging.py:157 >> {'loss': 0.9051, 'learning_rate': 1.9965e-04, 'epoch': 0.08}
+
+[INFO|2024-12-28 20:34:14] logging.py:157 >> {'loss': 0.7235, 'learning_rate': 1.9958e-04, 'epoch': 0.09}
+
+[INFO|2024-12-28 20:34:18] logging.py:157 >> {'loss': 0.8169, 'learning_rate': 1.9950e-04, 'epoch': 0.10}
+
+[INFO|2024-12-28 20:34:24] logging.py:157 >> {'loss': 0.8266, 'learning_rate': 1.9941e-04, 'epoch': 0.10}
+
+[INFO|2024-12-28 20:34:29] logging.py:157 >> {'loss': 0.7580, 'learning_rate': 1.9931e-04, 'epoch': 0.11}
+
+[INFO|2024-12-28 20:34:36] logging.py:157 >> {'loss': 0.7759, 'learning_rate': 1.9921e-04, 'epoch': 0.12}
+
+[INFO|2024-12-28 20:34:42] logging.py:157 >> {'loss': 0.7797, 'learning_rate': 1.9910e-04, 'epoch': 0.13}
+
+[INFO|2024-12-28 20:34:49] logging.py:157 >> {'loss': 0.7437, 'learning_rate': 1.9899e-04, 'epoch': 0.14}
+
+[INFO|2024-12-28 20:34:56] logging.py:157 >> {'loss': 0.8043, 'learning_rate': 1.9887e-04, 'epoch': 0.14}
+
+[INFO|2024-12-28 20:35:02] logging.py:157 >> {'loss': 0.7701, 'learning_rate': 1.9874e-04, 'epoch': 0.15}
+
+[INFO|2024-12-28 20:35:10] logging.py:157 >> {'loss': 0.7090, 'learning_rate': 1.9860e-04, 'epoch': 0.16}
+
+[INFO|2024-12-28 20:35:10] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-100
+
+[INFO|2024-12-28 20:35:10] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:35:10] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:35:10] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-100/tokenizer_config.json
+
+[INFO|2024-12-28 20:35:10] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-100/special_tokens_map.json
+
+[INFO|2024-12-28 20:35:17] logging.py:157 >> {'loss': 0.7377, 'learning_rate': 1.9846e-04, 'epoch': 0.17}
+
+[INFO|2024-12-28 20:35:23] logging.py:157 >> {'loss': 0.8352, 'learning_rate': 1.9831e-04, 'epoch': 0.18}
+
+[INFO|2024-12-28 20:35:30] logging.py:157 >> {'loss': 0.7738, 'learning_rate': 1.9815e-04, 'epoch': 0.18}
+
+[INFO|2024-12-28 20:35:35] logging.py:157 >> {'loss': 0.8067, 'learning_rate': 1.9799e-04, 'epoch': 0.19}
+
+[INFO|2024-12-28 20:35:41] logging.py:157 >> {'loss': 0.7456, 'learning_rate': 1.9781e-04, 'epoch': 0.20}
+
+[INFO|2024-12-28 20:35:48] logging.py:157 >> {'loss': 0.7580, 'learning_rate': 1.9764e-04, 'epoch': 0.21}
+
+[INFO|2024-12-28 20:35:54] logging.py:157 >> {'loss': 0.7895, 'learning_rate': 1.9745e-04, 'epoch': 0.22}
+
+[INFO|2024-12-28 20:36:02] logging.py:157 >> {'loss': 0.7302, 'learning_rate': 1.9726e-04, 'epoch': 0.22}
+
+[INFO|2024-12-28 20:36:07] logging.py:157 >> {'loss': 0.8152, 'learning_rate': 1.9706e-04, 'epoch': 0.23}
+
+[INFO|2024-12-28 20:36:12] logging.py:157 >> {'loss': 0.8461, 'learning_rate': 1.9686e-04, 'epoch': 0.24}
+
+[INFO|2024-12-28 20:36:18] logging.py:157 >> {'loss': 0.7787, 'learning_rate': 1.9665e-04, 'epoch': 0.25}
+
+[INFO|2024-12-28 20:36:24] logging.py:157 >> {'loss': 0.7574, 'learning_rate': 1.9643e-04, 'epoch': 0.26}
+
+[INFO|2024-12-28 20:36:28] logging.py:157 >> {'loss': 0.8487, 'learning_rate': 1.9620e-04, 'epoch': 0.26}
+
+[INFO|2024-12-28 20:36:34] logging.py:157 >> {'loss': 0.6611, 'learning_rate': 1.9597e-04, 'epoch': 0.27}
+
+[INFO|2024-12-28 20:36:41] logging.py:157 >> {'loss': 0.7802, 'learning_rate': 1.9573e-04, 'epoch': 0.28}
+
+[INFO|2024-12-28 20:36:48] logging.py:157 >> {'loss': 0.6727, 'learning_rate': 1.9549e-04, 'epoch': 0.29}
+
+[INFO|2024-12-28 20:36:53] logging.py:157 >> {'loss': 0.7502, 'learning_rate': 1.9523e-04, 'epoch': 0.30}
+
+[INFO|2024-12-28 20:36:59] logging.py:157 >> {'loss': 0.8401, 'learning_rate': 1.9498e-04, 'epoch': 0.30}
+
+[INFO|2024-12-28 20:37:04] logging.py:157 >> {'loss': 0.7494, 'learning_rate': 1.9471e-04, 'epoch': 0.31}
+
+[INFO|2024-12-28 20:37:10] logging.py:157 >> {'loss': 0.7842, 'learning_rate': 1.9444e-04, 'epoch': 0.32}
+
+[INFO|2024-12-28 20:37:10] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-200
+
+[INFO|2024-12-28 20:37:11] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:37:11] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:37:11] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-200/tokenizer_config.json
+
+[INFO|2024-12-28 20:37:11] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-200/special_tokens_map.json
+
+[INFO|2024-12-28 20:37:18] logging.py:157 >> {'loss': 0.8082, 'learning_rate': 1.9416e-04, 'epoch': 0.33}
+
+[INFO|2024-12-28 20:37:23] logging.py:157 >> {'loss': 0.7883, 'learning_rate': 1.9387e-04, 'epoch': 0.34}
+
+[INFO|2024-12-28 20:37:31] logging.py:157 >> {'loss': 0.7356, 'learning_rate': 1.9358e-04, 'epoch': 0.34}
+
+[INFO|2024-12-28 20:37:37] logging.py:157 >> {'loss': 0.7891, 'learning_rate': 1.9328e-04, 'epoch': 0.35}
+
+[INFO|2024-12-28 20:37:44] logging.py:157 >> {'loss': 0.7671, 'learning_rate': 1.9298e-04, 'epoch': 0.36}
+
+[INFO|2024-12-28 20:37:51] logging.py:157 >> {'loss': 0.6608, 'learning_rate': 1.9267e-04, 'epoch': 0.37}
+
+[INFO|2024-12-28 20:38:00] logging.py:157 >> {'loss': 0.6470, 'learning_rate': 1.9235e-04, 'epoch': 0.38}
+
+[INFO|2024-12-28 20:38:08] logging.py:157 >> {'loss': 0.7290, 'learning_rate': 1.9202e-04, 'epoch': 0.38}
+
+[INFO|2024-12-28 20:38:13] logging.py:157 >> {'loss': 0.6713, 'learning_rate': 1.9169e-04, 'epoch': 0.39}
+
+[INFO|2024-12-28 20:38:22] logging.py:157 >> {'loss': 0.7049, 'learning_rate': 1.9135e-04, 'epoch': 0.40}
+
+[INFO|2024-12-28 20:38:30] logging.py:157 >> {'loss': 0.7419, 'learning_rate': 1.9101e-04, 'epoch': 0.41}
+
+[INFO|2024-12-28 20:38:35] logging.py:157 >> {'loss': 0.7148, 'learning_rate': 1.9066e-04, 'epoch': 0.42}
+
+[INFO|2024-12-28 20:38:43] logging.py:157 >> {'loss': 0.7493, 'learning_rate': 1.9030e-04, 'epoch': 0.42}
+
+[INFO|2024-12-28 20:38:49] logging.py:157 >> {'loss': 0.7652, 'learning_rate': 1.8994e-04, 'epoch': 0.43}
+
+[INFO|2024-12-28 20:38:56] logging.py:157 >> {'loss': 0.7438, 'learning_rate': 1.8957e-04, 'epoch': 0.44}
+
+[INFO|2024-12-28 20:39:01] logging.py:157 >> {'loss': 0.7683, 'learning_rate': 1.8920e-04, 'epoch': 0.45}
+
+[INFO|2024-12-28 20:39:06] logging.py:157 >> {'loss': 0.8115, 'learning_rate': 1.8881e-04, 'epoch': 0.46}
+
+[INFO|2024-12-28 20:39:12] logging.py:157 >> {'loss': 0.8335, 'learning_rate': 1.8843e-04, 'epoch': 0.46}
+
+[INFO|2024-12-28 20:39:19] logging.py:157 >> {'loss': 0.6933, 'learning_rate': 1.8803e-04, 'epoch': 0.47}
+
+[INFO|2024-12-28 20:39:23] logging.py:157 >> {'loss': 0.7515, 'learning_rate': 1.8763e-04, 'epoch': 0.48}
+
+[INFO|2024-12-28 20:39:23] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-300
+
+[INFO|2024-12-28 20:39:23] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:39:23] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:39:24] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-300/tokenizer_config.json
+
+[INFO|2024-12-28 20:39:24] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-300/special_tokens_map.json
+
+[INFO|2024-12-28 20:39:31] logging.py:157 >> {'loss': 0.6931, 'learning_rate': 1.8722e-04, 'epoch': 0.49}
+
+[INFO|2024-12-28 20:39:37] logging.py:157 >> {'loss': 0.7820, 'learning_rate': 1.8681e-04, 'epoch': 0.50}
+
+[INFO|2024-12-28 20:39:44] logging.py:157 >> {'loss': 0.7361, 'learning_rate': 1.8639e-04, 'epoch': 0.50}
+
+[INFO|2024-12-28 20:39:49] logging.py:157 >> {'loss': 0.7443, 'learning_rate': 1.8597e-04, 'epoch': 0.51}
+
+[INFO|2024-12-28 20:39:57] logging.py:157 >> {'loss': 0.7221, 'learning_rate': 1.8554e-04, 'epoch': 0.52}
+
+[INFO|2024-12-28 20:40:02] logging.py:157 >> {'loss': 0.7622, 'learning_rate': 1.8510e-04, 'epoch': 0.53}
+
+[INFO|2024-12-28 20:40:08] logging.py:157 >> {'loss': 0.8556, 'learning_rate': 1.8466e-04, 'epoch': 0.54}
+
+[INFO|2024-12-28 20:40:15] logging.py:157 >> {'loss': 0.7814, 'learning_rate': 1.8421e-04, 'epoch': 0.54}
+
+[INFO|2024-12-28 20:40:24] logging.py:157 >> {'loss': 0.7220, 'learning_rate': 1.8375e-04, 'epoch': 0.55}
+
+[INFO|2024-12-28 20:40:28] logging.py:157 >> {'loss': 0.7903, 'learning_rate': 1.8329e-04, 'epoch': 0.56}
+
+[INFO|2024-12-28 20:40:33] logging.py:157 >> {'loss': 0.6996, 'learning_rate': 1.8283e-04, 'epoch': 0.57}
+
+[INFO|2024-12-28 20:40:39] logging.py:157 >> {'loss': 0.7730, 'learning_rate': 1.8235e-04, 'epoch': 0.58}
+
+[INFO|2024-12-28 20:40:45] logging.py:157 >> {'loss': 0.7280, 'learning_rate': 1.8188e-04, 'epoch': 0.58}
+
+[INFO|2024-12-28 20:40:51] logging.py:157 >> {'loss': 0.7659, 'learning_rate': 1.8139e-04, 'epoch': 0.59}
+
+[INFO|2024-12-28 20:40:56] logging.py:157 >> {'loss': 0.7039, 'learning_rate': 1.8090e-04, 'epoch': 0.60}
+
+[INFO|2024-12-28 20:41:02] logging.py:157 >> {'loss': 0.7125, 'learning_rate': 1.8041e-04, 'epoch': 0.61}
+
+[INFO|2024-12-28 20:41:09] logging.py:157 >> {'loss': 0.6980, 'learning_rate': 1.7991e-04, 'epoch': 0.62}
+
+[INFO|2024-12-28 20:41:14] logging.py:157 >> {'loss': 0.8255, 'learning_rate': 1.7940e-04, 'epoch': 0.62}
+
+[INFO|2024-12-28 20:41:19] logging.py:157 >> {'loss': 0.6616, 'learning_rate': 1.7889e-04, 'epoch': 0.63}
+
+[INFO|2024-12-28 20:41:24] logging.py:157 >> {'loss': 0.7452, 'learning_rate': 1.7837e-04, 'epoch': 0.64}
+
+[INFO|2024-12-28 20:41:24] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-400
+
+[INFO|2024-12-28 20:41:24] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:41:24] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:41:25] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-400/tokenizer_config.json
+
+[INFO|2024-12-28 20:41:25] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-400/special_tokens_map.json
+
+[INFO|2024-12-28 20:41:32] logging.py:157 >> {'loss': 0.7652, 'learning_rate': 1.7785e-04, 'epoch': 0.65}
+
+[INFO|2024-12-28 20:41:40] logging.py:157 >> {'loss': 0.7793, 'learning_rate': 1.7732e-04, 'epoch': 0.66}
+
+[INFO|2024-12-28 20:41:45] logging.py:157 >> {'loss': 0.6875, 'learning_rate': 1.7678e-04, 'epoch': 0.66}
+
+[INFO|2024-12-28 20:41:54] logging.py:157 >> {'loss': 0.7465, 'learning_rate': 1.7624e-04, 'epoch': 0.67}
+
+[INFO|2024-12-28 20:42:01] logging.py:157 >> {'loss': 0.7205, 'learning_rate': 1.7570e-04, 'epoch': 0.68}
+
+[INFO|2024-12-28 20:42:08] logging.py:157 >> {'loss': 0.6589, 'learning_rate': 1.7515e-04, 'epoch': 0.69}
+
+[INFO|2024-12-28 20:42:13] logging.py:157 >> {'loss': 0.7035, 'learning_rate': 1.7459e-04, 'epoch': 0.70}
+
+[INFO|2024-12-28 20:42:20] logging.py:157 >> {'loss': 0.7870, 'learning_rate': 1.7403e-04, 'epoch': 0.70}
+
+[INFO|2024-12-28 20:42:29] logging.py:157 >> {'loss': 0.7515, 'learning_rate': 1.7347e-04, 'epoch': 0.71}
+
+[INFO|2024-12-28 20:42:34] logging.py:157 >> {'loss': 0.7199, 'learning_rate': 1.7290e-04, 'epoch': 0.72}
+
+[INFO|2024-12-28 20:42:41] logging.py:157 >> {'loss': 0.8037, 'learning_rate': 1.7232e-04, 'epoch': 0.73}
+
+[INFO|2024-12-28 20:42:46] logging.py:157 >> {'loss': 0.7502, 'learning_rate': 1.7174e-04, 'epoch': 0.74}
+
+[INFO|2024-12-28 20:42:53] logging.py:157 >> {'loss': 0.7446, 'learning_rate': 1.7115e-04, 'epoch': 0.74}
+
+[INFO|2024-12-28 20:43:00] logging.py:157 >> {'loss': 0.6507, 'learning_rate': 1.7056e-04, 'epoch': 0.75}
+
+[INFO|2024-12-28 20:43:06] logging.py:157 >> {'loss': 0.7164, 'learning_rate': 1.6997e-04, 'epoch': 0.76}
+
+[INFO|2024-12-28 20:43:12] logging.py:157 >> {'loss': 0.7621, 'learning_rate': 1.6937e-04, 'epoch': 0.77}
+
+[INFO|2024-12-28 20:43:18] logging.py:157 >> {'loss': 0.7623, 'learning_rate': 1.6876e-04, 'epoch': 0.78}
+
+[INFO|2024-12-28 20:43:26] logging.py:157 >> {'loss': 0.6606, 'learning_rate': 1.6815e-04, 'epoch': 0.78}
+
+[INFO|2024-12-28 20:43:34] logging.py:157 >> {'loss': 0.6941, 'learning_rate': 1.6753e-04, 'epoch': 0.79}
+
+[INFO|2024-12-28 20:43:39] logging.py:157 >> {'loss': 0.6841, 'learning_rate': 1.6691e-04, 'epoch': 0.80}
+
+[INFO|2024-12-28 20:43:39] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-500
+
+[INFO|2024-12-28 20:43:39] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:43:39] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:43:40] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-500/tokenizer_config.json
+
+[INFO|2024-12-28 20:43:40] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-500/special_tokens_map.json
+
+[INFO|2024-12-28 20:43:47] logging.py:157 >> {'loss': 0.6996, 'learning_rate': 1.6629e-04, 'epoch': 0.81}
+
+[INFO|2024-12-28 20:43:54] logging.py:157 >> {'loss': 0.7542, 'learning_rate': 1.6566e-04, 'epoch': 0.82}
+
+[INFO|2024-12-28 20:44:00] logging.py:157 >> {'loss': 0.7175, 'learning_rate': 1.6502e-04, 'epoch': 0.82}
+
+[INFO|2024-12-28 20:44:05] logging.py:157 >> {'loss': 0.7565, 'learning_rate': 1.6439e-04, 'epoch': 0.83}
+
+[INFO|2024-12-28 20:44:10] logging.py:157 >> {'loss': 0.7339, 'learning_rate': 1.6374e-04, 'epoch': 0.84}
+
+[INFO|2024-12-28 20:44:16] logging.py:157 >> {'loss': 0.5690, 'learning_rate': 1.6309e-04, 'epoch': 0.85}
+
+[INFO|2024-12-28 20:44:20] logging.py:157 >> {'loss': 0.7556, 'learning_rate': 1.6244e-04, 'epoch': 0.86}
+
+[INFO|2024-12-28 20:44:25] logging.py:157 >> {'loss': 0.7084, 'learning_rate': 1.6179e-04, 'epoch': 0.86}
+
+[INFO|2024-12-28 20:44:31] logging.py:157 >> {'loss': 0.6935, 'learning_rate': 1.6113e-04, 'epoch': 0.87}
+
+[INFO|2024-12-28 20:44:36] logging.py:157 >> {'loss': 0.7076, 'learning_rate': 1.6046e-04, 'epoch': 0.88}
+
+[INFO|2024-12-28 20:44:42] logging.py:157 >> {'loss': 0.7151, 'learning_rate': 1.5979e-04, 'epoch': 0.89}
+
+[INFO|2024-12-28 20:44:48] logging.py:157 >> {'loss': 0.7001, 'learning_rate': 1.5912e-04, 'epoch': 0.90}
+
+[INFO|2024-12-28 20:44:53] logging.py:157 >> {'loss': 0.7285, 'learning_rate': 1.5844e-04, 'epoch': 0.90}
+
+[INFO|2024-12-28 20:44:59] logging.py:157 >> {'loss': 0.8041, 'learning_rate': 1.5776e-04, 'epoch': 0.91}
+
+[INFO|2024-12-28 20:45:05] logging.py:157 >> {'loss': 0.7353, 'learning_rate': 1.5707e-04, 'epoch': 0.92}
+
+[INFO|2024-12-28 20:45:11] logging.py:157 >> {'loss': 0.7792, 'learning_rate': 1.5638e-04, 'epoch': 0.93}
+
+[INFO|2024-12-28 20:45:18] logging.py:157 >> {'loss': 1.0121, 'learning_rate': 1.5569e-04, 'epoch': 0.94}
+
+[INFO|2024-12-28 20:45:24] logging.py:157 >> {'loss': 0.7727, 'learning_rate': 1.5499e-04, 'epoch': 0.94}
+
+[INFO|2024-12-28 20:45:30] logging.py:157 >> {'loss': 0.7410, 'learning_rate': 1.5429e-04, 'epoch': 0.95}
+
+[INFO|2024-12-28 20:45:36] logging.py:157 >> {'loss': 0.6919, 'learning_rate': 1.5358e-04, 'epoch': 0.96}
+
+[INFO|2024-12-28 20:45:36] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-600
+
+[INFO|2024-12-28 20:45:36] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:45:36] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:45:36] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-600/tokenizer_config.json
+
+[INFO|2024-12-28 20:45:36] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-600/special_tokens_map.json
+
+[INFO|2024-12-28 20:45:44] logging.py:157 >> {'loss': 0.7163, 'learning_rate': 1.5287e-04, 'epoch': 0.97}
+
+[INFO|2024-12-28 20:45:48] logging.py:157 >> {'loss': 0.8152, 'learning_rate': 1.5216e-04, 'epoch': 0.98}
+
+[INFO|2024-12-28 20:45:54] logging.py:157 >> {'loss': 0.6709, 'learning_rate': 1.5144e-04, 'epoch': 0.98}
+
+[INFO|2024-12-28 20:46:00] logging.py:157 >> {'loss': 0.6527, 'learning_rate': 1.5072e-04, 'epoch': 0.99}
+
+[INFO|2024-12-28 20:46:05] logging.py:157 >> {'loss': 0.8194, 'learning_rate': 1.5000e-04, 'epoch': 1.00}
+
+[INFO|2024-12-28 20:46:10] logging.py:157 >> {'loss': 0.6627, 'learning_rate': 1.4927e-04, 'epoch': 1.01}
+
+[INFO|2024-12-28 20:46:16] logging.py:157 >> {'loss': 0.6366, 'learning_rate': 1.4854e-04, 'epoch': 1.02}
+
+[INFO|2024-12-28 20:46:21] logging.py:157 >> {'loss': 0.6717, 'learning_rate': 1.4781e-04, 'epoch': 1.02}
+
+[INFO|2024-12-28 20:46:26] logging.py:157 >> {'loss': 0.6483, 'learning_rate': 1.4707e-04, 'epoch': 1.03}
+
+[INFO|2024-12-28 20:46:31] logging.py:157 >> {'loss': 0.6151, 'learning_rate': 1.4633e-04, 'epoch': 1.04}
+
+[INFO|2024-12-28 20:46:38] logging.py:157 >> {'loss': 0.6707, 'learning_rate': 1.4559e-04, 'epoch': 1.05}
+
+[INFO|2024-12-28 20:46:42] logging.py:157 >> {'loss': 0.6125, 'learning_rate': 1.4484e-04, 'epoch': 1.06}
+
+[INFO|2024-12-28 20:46:48] logging.py:157 >> {'loss': 0.6206, 'learning_rate': 1.4409e-04, 'epoch': 1.06}
+
+[INFO|2024-12-28 20:46:54] logging.py:157 >> {'loss': 0.6161, 'learning_rate': 1.4333e-04, 'epoch': 1.07}
+
+[INFO|2024-12-28 20:47:00] logging.py:157 >> {'loss': 0.6583, 'learning_rate': 1.4258e-04, 'epoch': 1.08}
+
+[INFO|2024-12-28 20:47:05] logging.py:157 >> {'loss': 0.6222, 'learning_rate': 1.4182e-04, 'epoch': 1.09}
+
+[INFO|2024-12-28 20:47:10] logging.py:157 >> {'loss': 0.7160, 'learning_rate': 1.4106e-04, 'epoch': 1.10}
+
+[INFO|2024-12-28 20:47:16] logging.py:157 >> {'loss': 0.6198, 'learning_rate': 1.4029e-04, 'epoch': 1.10}
+
+[INFO|2024-12-28 20:47:24] logging.py:157 >> {'loss': 0.6389, 'learning_rate': 1.3952e-04, 'epoch': 1.11}
+
+[INFO|2024-12-28 20:47:30] logging.py:157 >> {'loss': 0.6842, 'learning_rate': 1.3875e-04, 'epoch': 1.12}
+
+[INFO|2024-12-28 20:47:30] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-700
+
+[INFO|2024-12-28 20:47:30] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:47:30] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:47:30] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-700/tokenizer_config.json
+
+[INFO|2024-12-28 20:47:30] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-700/special_tokens_map.json
+
+[INFO|2024-12-28 20:47:38] logging.py:157 >> {'loss': 0.6071, 'learning_rate': 1.3798e-04, 'epoch': 1.13}
+
+[INFO|2024-12-28 20:47:46] logging.py:157 >> {'loss': 0.5915, 'learning_rate': 1.3720e-04, 'epoch': 1.14}
+
+[INFO|2024-12-28 20:47:51] logging.py:157 >> {'loss': 0.6794, 'learning_rate': 1.3642e-04, 'epoch': 1.14}
+
+[INFO|2024-12-28 20:47:57] logging.py:157 >> {'loss': 0.6773, 'learning_rate': 1.3564e-04, 'epoch': 1.15}
+
+[INFO|2024-12-28 20:48:04] logging.py:157 >> {'loss': 0.6680, 'learning_rate': 1.3486e-04, 'epoch': 1.16}
+
+[INFO|2024-12-28 20:48:12] logging.py:157 >> {'loss': 0.6997, 'learning_rate': 1.3407e-04, 'epoch': 1.17}
+
+[INFO|2024-12-28 20:48:20] logging.py:157 >> {'loss': 0.8310, 'learning_rate': 1.3328e-04, 'epoch': 1.18}
+
+[INFO|2024-12-28 20:48:27] logging.py:157 >> {'loss': 0.6378, 'learning_rate': 1.3249e-04, 'epoch': 1.18}
+
+[INFO|2024-12-28 20:48:32] logging.py:157 >> {'loss': 0.6547, 'learning_rate': 1.3170e-04, 'epoch': 1.19}
+
+[INFO|2024-12-28 20:48:37] logging.py:157 >> {'loss': 0.5808, 'learning_rate': 1.3090e-04, 'epoch': 1.20}
+
+[INFO|2024-12-28 20:48:43] logging.py:157 >> {'loss': 0.5582, 'learning_rate': 1.3010e-04, 'epoch': 1.21}
+
+[INFO|2024-12-28 20:48:50] logging.py:157 >> {'loss': 0.5801, 'learning_rate': 1.2930e-04, 'epoch': 1.22}
+
+[INFO|2024-12-28 20:48:56] logging.py:157 >> {'loss': 0.6500, 'learning_rate': 1.2850e-04, 'epoch': 1.22}
+
+[INFO|2024-12-28 20:49:03] logging.py:157 >> {'loss': 0.6627, 'learning_rate': 1.2770e-04, 'epoch': 1.23}
+
+[INFO|2024-12-28 20:49:08] logging.py:157 >> {'loss': 0.5603, 'learning_rate': 1.2689e-04, 'epoch': 1.24}
+
+[INFO|2024-12-28 20:49:13] logging.py:157 >> {'loss': 0.6525, 'learning_rate': 1.2608e-04, 'epoch': 1.25}
+
+[INFO|2024-12-28 20:49:20] logging.py:157 >> {'loss': 0.6731, 'learning_rate': 1.2527e-04, 'epoch': 1.26}
+
+[INFO|2024-12-28 20:49:27] logging.py:157 >> {'loss': 0.6255, 'learning_rate': 1.2446e-04, 'epoch': 1.26}
+
+[INFO|2024-12-28 20:49:33] logging.py:157 >> {'loss': 0.6585, 'learning_rate': 1.2365e-04, 'epoch': 1.27}
+
+[INFO|2024-12-28 20:49:41] logging.py:157 >> {'loss': 0.5996, 'learning_rate': 1.2284e-04, 'epoch': 1.28}
+
+[INFO|2024-12-28 20:49:41] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-800
+
+[INFO|2024-12-28 20:49:41] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:49:41] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:49:41] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-800/tokenizer_config.json
+
+[INFO|2024-12-28 20:49:41] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-800/special_tokens_map.json
+
+[INFO|2024-12-28 20:49:50] logging.py:157 >> {'loss': 0.6355, 'learning_rate': 1.2202e-04, 'epoch': 1.29}
+
+[INFO|2024-12-28 20:49:56] logging.py:157 >> {'loss': 0.6615, 'learning_rate': 1.2120e-04, 'epoch': 1.30}
+
+[INFO|2024-12-28 20:50:04] logging.py:157 >> {'loss': 0.6096, 'learning_rate': 1.2038e-04, 'epoch': 1.30}
+
+[INFO|2024-12-28 20:50:11] logging.py:157 >> {'loss': 0.5984, 'learning_rate': 1.1956e-04, 'epoch': 1.31}
+
+[INFO|2024-12-28 20:50:19] logging.py:157 >> {'loss': 0.5569, 'learning_rate': 1.1874e-04, 'epoch': 1.32}
+
+[INFO|2024-12-28 20:50:26] logging.py:157 >> {'loss': 0.7088, 'learning_rate': 1.1791e-04, 'epoch': 1.33}
+
+[INFO|2024-12-28 20:50:32] logging.py:157 >> {'loss': 0.6731, 'learning_rate': 1.1709e-04, 'epoch': 1.34}
+
+[INFO|2024-12-28 20:50:38] logging.py:157 >> {'loss': 0.6188, 'learning_rate': 1.1626e-04, 'epoch': 1.34}
+
+[INFO|2024-12-28 20:50:43] logging.py:157 >> {'loss': 0.7004, 'learning_rate': 1.1544e-04, 'epoch': 1.35}
+
+[INFO|2024-12-28 20:50:51] logging.py:157 >> {'loss': 0.5884, 'learning_rate': 1.1461e-04, 'epoch': 1.36}
+
+[INFO|2024-12-28 20:51:00] logging.py:157 >> {'loss': 0.5739, 'learning_rate': 1.1378e-04, 'epoch': 1.37}
+
+[INFO|2024-12-28 20:51:05] logging.py:157 >> {'loss': 0.6435, 'learning_rate': 1.1295e-04, 'epoch': 1.38}
+
+[INFO|2024-12-28 20:51:12] logging.py:157 >> {'loss': 0.6897, 'learning_rate': 1.1212e-04, 'epoch': 1.38}
+
+[INFO|2024-12-28 20:51:16] logging.py:157 >> {'loss': 0.6641, 'learning_rate': 1.1129e-04, 'epoch': 1.39}
+
+[INFO|2024-12-28 20:51:22] logging.py:157 >> {'loss': 0.6273, 'learning_rate': 1.1045e-04, 'epoch': 1.40}
+
+[INFO|2024-12-28 20:51:30] logging.py:157 >> {'loss': 0.6437, 'learning_rate': 1.0962e-04, 'epoch': 1.41}
+
+[INFO|2024-12-28 20:51:37] logging.py:157 >> {'loss': 0.6345, 'learning_rate': 1.0879e-04, 'epoch': 1.42}
+
+[INFO|2024-12-28 20:51:45] logging.py:157 >> {'loss': 0.5913, 'learning_rate': 1.0795e-04, 'epoch': 1.42}
+
+[INFO|2024-12-28 20:51:51] logging.py:157 >> {'loss': 0.6482, 'learning_rate': 1.0711e-04, 'epoch': 1.43}
+
+[INFO|2024-12-28 20:51:58] logging.py:157 >> {'loss': 0.6165, 'learning_rate': 1.0628e-04, 'epoch': 1.44}
+
+[INFO|2024-12-28 20:51:58] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-900
+
+[INFO|2024-12-28 20:51:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:51:58] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:51:58] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-900/tokenizer_config.json
+
+[INFO|2024-12-28 20:51:58] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-900/special_tokens_map.json
+
+[INFO|2024-12-28 20:52:05] logging.py:157 >> {'loss': 0.6340, 'learning_rate': 1.0544e-04, 'epoch': 1.45}
+
+[INFO|2024-12-28 20:52:09] logging.py:157 >> {'loss': 0.6509, 'learning_rate': 1.0461e-04, 'epoch': 1.46}
+
+[INFO|2024-12-28 20:52:17] logging.py:157 >> {'loss': 0.6212, 'learning_rate': 1.0377e-04, 'epoch': 1.46}
+
+[INFO|2024-12-28 20:52:23] logging.py:157 >> {'loss': 0.7305, 'learning_rate': 1.0293e-04, 'epoch': 1.47}
+
+[INFO|2024-12-28 20:52:29] logging.py:157 >> {'loss': 0.6685, 'learning_rate': 1.0209e-04, 'epoch': 1.48}
+
+[INFO|2024-12-28 20:52:35] logging.py:157 >> {'loss': 0.6214, 'learning_rate': 1.0126e-04, 'epoch': 1.49}
+
+[INFO|2024-12-28 20:52:43] logging.py:157 >> {'loss': 0.6035, 'learning_rate': 1.0042e-04, 'epoch': 1.50}
+
+[INFO|2024-12-28 20:52:49] logging.py:157 >> {'loss': 0.5868, 'learning_rate': 9.9581e-05, 'epoch': 1.50}
+
+[INFO|2024-12-28 20:52:55] logging.py:157 >> {'loss': 0.6003, 'learning_rate': 9.8743e-05, 'epoch': 1.51}
+
+[INFO|2024-12-28 20:53:01] logging.py:157 >> {'loss': 0.5854, 'learning_rate': 9.7906e-05, 'epoch': 1.52}
+
+[INFO|2024-12-28 20:53:09] logging.py:157 >> {'loss': 0.5882, 'learning_rate': 9.7068e-05, 'epoch': 1.53}
+
+[INFO|2024-12-28 20:53:14] logging.py:157 >> {'loss': 0.7187, 'learning_rate': 9.6231e-05, 'epoch': 1.54}
+
+[INFO|2024-12-28 20:53:19] logging.py:157 >> {'loss': 0.6156, 'learning_rate': 9.5394e-05, 'epoch': 1.54}
+
+[INFO|2024-12-28 20:53:23] logging.py:157 >> {'loss': 0.6488, 'learning_rate': 9.4557e-05, 'epoch': 1.55}
+
+[INFO|2024-12-28 20:53:30] logging.py:157 >> {'loss': 0.6601, 'learning_rate': 9.3721e-05, 'epoch': 1.56}
+
+[INFO|2024-12-28 20:53:37] logging.py:157 >> {'loss': 0.5968, 'learning_rate': 9.2885e-05, 'epoch': 1.57}
+
+[INFO|2024-12-28 20:53:42] logging.py:157 >> {'loss': 0.7034, 'learning_rate': 9.2050e-05, 'epoch': 1.58}
+
+[INFO|2024-12-28 20:53:46] logging.py:157 >> {'loss': 0.5973, 'learning_rate': 9.1215e-05, 'epoch': 1.58}
+
+[INFO|2024-12-28 20:53:50] logging.py:157 >> {'loss': 0.7877, 'learning_rate': 9.0381e-05, 'epoch': 1.59}
+
+[INFO|2024-12-28 20:53:57] logging.py:157 >> {'loss': 0.6440, 'learning_rate': 8.9547e-05, 'epoch': 1.60}
+
+[INFO|2024-12-28 20:53:57] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1000
+
+[INFO|2024-12-28 20:53:57] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:53:57] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:53:57] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1000/tokenizer_config.json
+
+[INFO|2024-12-28 20:53:57] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1000/special_tokens_map.json
+
+[INFO|2024-12-28 20:54:04] logging.py:157 >> {'loss': 0.6678, 'learning_rate': 8.8714e-05, 'epoch': 1.61}
+
+[INFO|2024-12-28 20:54:09] logging.py:157 >> {'loss': 0.6088, 'learning_rate': 8.7882e-05, 'epoch': 1.62}
+
+[INFO|2024-12-28 20:54:16] logging.py:157 >> {'loss': 0.6219, 'learning_rate': 8.7051e-05, 'epoch': 1.62}
+
+[INFO|2024-12-28 20:54:21] logging.py:157 >> {'loss': 0.6698, 'learning_rate': 8.6221e-05, 'epoch': 1.63}
+
+[INFO|2024-12-28 20:54:29] logging.py:157 >> {'loss': 0.6207, 'learning_rate': 8.5392e-05, 'epoch': 1.64}
+
+[INFO|2024-12-28 20:54:36] logging.py:157 >> {'loss': 0.6260, 'learning_rate': 8.4563e-05, 'epoch': 1.65}
+
+[INFO|2024-12-28 20:54:42] logging.py:157 >> {'loss': 0.6972, 'learning_rate': 8.3736e-05, 'epoch': 1.66}
+
+[INFO|2024-12-28 20:54:47] logging.py:157 >> {'loss': 0.6282, 'learning_rate': 8.2910e-05, 'epoch': 1.66}
+
+[INFO|2024-12-28 20:54:53] logging.py:157 >> {'loss': 0.6219, 'learning_rate': 8.2085e-05, 'epoch': 1.67}
+
+[INFO|2024-12-28 20:55:00] logging.py:157 >> {'loss': 0.6220, 'learning_rate': 8.1262e-05, 'epoch': 1.68}
+
+[INFO|2024-12-28 20:55:06] logging.py:157 >> {'loss': 0.5801, 'learning_rate': 8.0440e-05, 'epoch': 1.69}
+
+[INFO|2024-12-28 20:55:13] logging.py:157 >> {'loss': 0.5980, 'learning_rate': 7.9619e-05, 'epoch': 1.70}
+
+[INFO|2024-12-28 20:55:18] logging.py:157 >> {'loss': 0.6990, 'learning_rate': 7.8799e-05, 'epoch': 1.70}
+
+[INFO|2024-12-28 20:55:23] logging.py:157 >> {'loss': 0.5882, 'learning_rate': 7.7981e-05, 'epoch': 1.71}
+
+[INFO|2024-12-28 20:55:31] logging.py:157 >> {'loss': 0.5321, 'learning_rate': 7.7165e-05, 'epoch': 1.72}
+
+[INFO|2024-12-28 20:55:39] logging.py:157 >> {'loss': 0.6647, 'learning_rate': 7.6350e-05, 'epoch': 1.73}
+
+[INFO|2024-12-28 20:55:45] logging.py:157 >> {'loss': 0.6280, 'learning_rate': 7.5537e-05, 'epoch': 1.74}
+
+[INFO|2024-12-28 20:55:52] logging.py:157 >> {'loss': 0.6262, 'learning_rate': 7.4726e-05, 'epoch': 1.74}
+
+[INFO|2024-12-28 20:55:58] logging.py:157 >> {'loss': 0.6131, 'learning_rate': 7.3916e-05, 'epoch': 1.75}
+
+[INFO|2024-12-28 20:56:04] logging.py:157 >> {'loss': 0.6494, 'learning_rate': 7.3108e-05, 'epoch': 1.76}
+
+[INFO|2024-12-28 20:56:04] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1100
+
+[INFO|2024-12-28 20:56:05] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:56:05] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:56:05] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1100/tokenizer_config.json
+
+[INFO|2024-12-28 20:56:05] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1100/special_tokens_map.json
+
+[INFO|2024-12-28 20:56:12] logging.py:157 >> {'loss': 0.5514, 'learning_rate': 7.2302e-05, 'epoch': 1.77}
+
+[INFO|2024-12-28 20:56:20] logging.py:157 >> {'loss': 0.5823, 'learning_rate': 7.1498e-05, 'epoch': 1.78}
+
+[INFO|2024-12-28 20:56:25] logging.py:157 >> {'loss': 0.7207, 'learning_rate': 7.0696e-05, 'epoch': 1.78}
+
+[INFO|2024-12-28 20:56:32] logging.py:157 >> {'loss': 0.7006, 'learning_rate': 6.9896e-05, 'epoch': 1.79}
+
+[INFO|2024-12-28 20:56:37] logging.py:157 >> {'loss': 0.6222, 'learning_rate': 6.9098e-05, 'epoch': 1.80}
+
+[INFO|2024-12-28 20:56:43] logging.py:157 >> {'loss': 0.6569, 'learning_rate': 6.8303e-05, 'epoch': 1.81}
+
+[INFO|2024-12-28 20:56:51] logging.py:157 >> {'loss': 0.5430, 'learning_rate': 6.7509e-05, 'epoch': 1.82}
+
+[INFO|2024-12-28 20:56:57] logging.py:157 >> {'loss': 0.6334, 'learning_rate': 6.6718e-05, 'epoch': 1.82}
+
+[INFO|2024-12-28 20:57:05] logging.py:157 >> {'loss': 0.6701, 'learning_rate': 6.5929e-05, 'epoch': 1.83}
+
+[INFO|2024-12-28 20:57:12] logging.py:157 >> {'loss': 0.6216, 'learning_rate': 6.5143e-05, 'epoch': 1.84}
+
+[INFO|2024-12-28 20:57:20] logging.py:157 >> {'loss': 0.5877, 'learning_rate': 6.4359e-05, 'epoch': 1.85}
+
+[INFO|2024-12-28 20:57:27] logging.py:157 >> {'loss': 0.6256, 'learning_rate': 6.3577e-05, 'epoch': 1.86}
+
+[INFO|2024-12-28 20:57:31] logging.py:157 >> {'loss': 0.7062, 'learning_rate': 6.2798e-05, 'epoch': 1.86}
+
+[INFO|2024-12-28 20:57:38] logging.py:157 >> {'loss': 0.6304, 'learning_rate': 6.2022e-05, 'epoch': 1.87}
+
+[INFO|2024-12-28 20:57:42] logging.py:157 >> {'loss': 0.7695, 'learning_rate': 6.1248e-05, 'epoch': 1.88}
+
+[INFO|2024-12-28 20:57:49] logging.py:157 >> {'loss': 0.5723, 'learning_rate': 6.0478e-05, 'epoch': 1.89}
+
+[INFO|2024-12-28 20:57:54] logging.py:157 >> {'loss': 0.6847, 'learning_rate': 5.9709e-05, 'epoch': 1.90}
+
+[INFO|2024-12-28 20:58:01] logging.py:157 >> {'loss': 0.6618, 'learning_rate': 5.8944e-05, 'epoch': 1.90}
+
+[INFO|2024-12-28 20:58:07] logging.py:157 >> {'loss': 0.6275, 'learning_rate': 5.8182e-05, 'epoch': 1.91}
+
+[INFO|2024-12-28 20:58:14] logging.py:157 >> {'loss': 0.5617, 'learning_rate': 5.7422e-05, 'epoch': 1.92}
+
+[INFO|2024-12-28 20:58:14] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1200
+
+[INFO|2024-12-28 20:58:15] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 20:58:15] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 20:58:15] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1200/tokenizer_config.json
+
+[INFO|2024-12-28 20:58:15] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1200/special_tokens_map.json
+
+[INFO|2024-12-28 20:58:21] logging.py:157 >> {'loss': 0.6278, 'learning_rate': 5.6666e-05, 'epoch': 1.93}
+
+[INFO|2024-12-28 20:58:26] logging.py:157 >> {'loss': 0.6713, 'learning_rate': 5.5912e-05, 'epoch': 1.94}
+
+[INFO|2024-12-28 20:58:30] logging.py:157 >> {'loss': 0.6113, 'learning_rate': 5.5162e-05, 'epoch': 1.94}
+
+[INFO|2024-12-28 20:58:37] logging.py:157 >> {'loss': 0.5587, 'learning_rate': 5.4414e-05, 'epoch': 1.95}
+
+[INFO|2024-12-28 20:58:44] logging.py:157 >> {'loss': 0.5601, 'learning_rate': 5.3670e-05, 'epoch': 1.96}
+
+[INFO|2024-12-28 20:58:49] logging.py:157 >> {'loss': 0.5941, 'learning_rate': 5.2930e-05, 'epoch': 1.97}
+
+[INFO|2024-12-28 20:58:55] logging.py:157 >> {'loss': 0.6285, 'learning_rate': 5.2192e-05, 'epoch': 1.98}
+
+[INFO|2024-12-28 20:59:01] logging.py:157 >> {'loss': 0.6516, 'learning_rate': 5.1458e-05, 'epoch': 1.98}
+
+[INFO|2024-12-28 20:59:10] logging.py:157 >> {'loss': 0.5904, 'learning_rate': 5.0727e-05, 'epoch': 1.99}
+
+[INFO|2024-12-28 20:59:17] logging.py:157 >> {'loss': 0.6190, 'learning_rate': 5.0000e-05, 'epoch': 2.00}
+
+[INFO|2024-12-28 20:59:21] logging.py:157 >> {'loss': 0.6058, 'learning_rate': 4.9276e-05, 'epoch': 2.01}
+
+[INFO|2024-12-28 20:59:26] logging.py:157 >> {'loss': 0.6248, 'learning_rate': 4.8556e-05, 'epoch': 2.02}
+
+[INFO|2024-12-28 20:59:32] logging.py:157 >> {'loss': 0.5247, 'learning_rate': 4.7839e-05, 'epoch': 2.02}
+
+[INFO|2024-12-28 20:59:40] logging.py:157 >> {'loss': 0.5439, 'learning_rate': 4.7127e-05, 'epoch': 2.03}
+
+[INFO|2024-12-28 20:59:46] logging.py:157 >> {'loss': 0.4491, 'learning_rate': 4.6417e-05, 'epoch': 2.04}
+
+[INFO|2024-12-28 20:59:54] logging.py:157 >> {'loss': 0.5200, 'learning_rate': 4.5712e-05, 'epoch': 2.05}
+
+[INFO|2024-12-28 21:00:01] logging.py:157 >> {'loss': 0.5259, 'learning_rate': 4.5010e-05, 'epoch': 2.06}
+
+[INFO|2024-12-28 21:00:08] logging.py:157 >> {'loss': 0.5025, 'learning_rate': 4.4312e-05, 'epoch': 2.06}
+
+[INFO|2024-12-28 21:00:14] logging.py:157 >> {'loss': 0.4772, 'learning_rate': 4.3619e-05, 'epoch': 2.07}
+
+[INFO|2024-12-28 21:00:19] logging.py:157 >> {'loss': 0.5945, 'learning_rate': 4.2929e-05, 'epoch': 2.08}
+
+[INFO|2024-12-28 21:00:19] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1300
+
+[INFO|2024-12-28 21:00:20] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:00:20] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:00:20] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1300/tokenizer_config.json
+
+[INFO|2024-12-28 21:00:20] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1300/special_tokens_map.json
+
+[INFO|2024-12-28 21:00:28] logging.py:157 >> {'loss': 0.4813, 'learning_rate': 4.2243e-05, 'epoch': 2.09}
+
+[INFO|2024-12-28 21:00:34] logging.py:157 >> {'loss': 0.5315, 'learning_rate': 4.1561e-05, 'epoch': 2.10}
+
+[INFO|2024-12-28 21:00:39] logging.py:157 >> {'loss': 0.5591, 'learning_rate': 4.0883e-05, 'epoch': 2.10}
+
+[INFO|2024-12-28 21:00:45] logging.py:157 >> {'loss': 0.6050, 'learning_rate': 4.0210e-05, 'epoch': 2.11}
+
+[INFO|2024-12-28 21:00:53] logging.py:157 >> {'loss': 0.4955, 'learning_rate': 3.9540e-05, 'epoch': 2.12}
+
+[INFO|2024-12-28 21:00:58] logging.py:157 >> {'loss': 0.5757, 'learning_rate': 3.8875e-05, 'epoch': 2.13}
+
+[INFO|2024-12-28 21:01:05] logging.py:157 >> {'loss': 0.5313, 'learning_rate': 3.8214e-05, 'epoch': 2.14}
+
+[INFO|2024-12-28 21:01:11] logging.py:157 >> {'loss': 0.5904, 'learning_rate': 3.7557e-05, 'epoch': 2.14}
+
+[INFO|2024-12-28 21:01:18] logging.py:157 >> {'loss': 0.4679, 'learning_rate': 3.6905e-05, 'epoch': 2.15}
+
+[INFO|2024-12-28 21:01:22] logging.py:157 >> {'loss': 0.5235, 'learning_rate': 3.6258e-05, 'epoch': 2.16}
+
+[INFO|2024-12-28 21:01:27] logging.py:157 >> {'loss': 0.5797, 'learning_rate': 3.5614e-05, 'epoch': 2.17}
+
+[INFO|2024-12-28 21:01:32] logging.py:157 >> {'loss': 0.5772, 'learning_rate': 3.4976e-05, 'epoch': 2.18}
+
+[INFO|2024-12-28 21:01:38] logging.py:157 >> {'loss': 0.5316, 'learning_rate': 3.4341e-05, 'epoch': 2.18}
+
+[INFO|2024-12-28 21:01:44] logging.py:157 >> {'loss': 0.5646, 'learning_rate': 3.3712e-05, 'epoch': 2.19}
+
+[INFO|2024-12-28 21:01:49] logging.py:157 >> {'loss': 0.5431, 'learning_rate': 3.3087e-05, 'epoch': 2.20}
+
+[INFO|2024-12-28 21:01:54] logging.py:157 >> {'loss': 0.5403, 'learning_rate': 3.2467e-05, 'epoch': 2.21}
+
+[INFO|2024-12-28 21:01:59] logging.py:157 >> {'loss': 0.5329, 'learning_rate': 3.1851e-05, 'epoch': 2.22}
+
+[INFO|2024-12-28 21:02:07] logging.py:157 >> {'loss': 0.5696, 'learning_rate': 3.1241e-05, 'epoch': 2.22}
+
+[INFO|2024-12-28 21:02:12] logging.py:157 >> {'loss': 0.5900, 'learning_rate': 3.0635e-05, 'epoch': 2.23}
+
+[INFO|2024-12-28 21:02:20] logging.py:157 >> {'loss': 0.5116, 'learning_rate': 3.0034e-05, 'epoch': 2.24}
+
+[INFO|2024-12-28 21:02:20] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1400
+
+[INFO|2024-12-28 21:02:20] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:02:20] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:02:20] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1400/tokenizer_config.json
+
+[INFO|2024-12-28 21:02:20] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1400/special_tokens_map.json
+
+[INFO|2024-12-28 21:02:27] logging.py:157 >> {'loss': 0.5783, 'learning_rate': 2.9438e-05, 'epoch': 2.25}
+
+[INFO|2024-12-28 21:02:33] logging.py:157 >> {'loss': 0.6259, 'learning_rate': 2.8846e-05, 'epoch': 2.26}
+
+[INFO|2024-12-28 21:02:41] logging.py:157 >> {'loss': 0.5759, 'learning_rate': 2.8260e-05, 'epoch': 2.26}
+
+[INFO|2024-12-28 21:02:47] logging.py:157 >> {'loss': 0.4970, 'learning_rate': 2.7679e-05, 'epoch': 2.27}
+
+[INFO|2024-12-28 21:02:53] logging.py:157 >> {'loss': 0.6190, 'learning_rate': 2.7103e-05, 'epoch': 2.28}
+
+[INFO|2024-12-28 21:02:57] logging.py:157 >> {'loss': 0.5858, 'learning_rate': 2.6532e-05, 'epoch': 2.29}
+
+[INFO|2024-12-28 21:03:04] logging.py:157 >> {'loss': 0.6291, 'learning_rate': 2.5966e-05, 'epoch': 2.30}
+
+[INFO|2024-12-28 21:03:10] logging.py:157 >> {'loss': 0.6418, 'learning_rate': 2.5406e-05, 'epoch': 2.30}
+
+[INFO|2024-12-28 21:03:17] logging.py:157 >> {'loss': 0.5483, 'learning_rate': 2.4851e-05, 'epoch': 2.31}
+
+[INFO|2024-12-28 21:03:24] logging.py:157 >> {'loss': 0.6071, 'learning_rate': 2.4300e-05, 'epoch': 2.32}
+
+[INFO|2024-12-28 21:03:31] logging.py:157 >> {'loss': 0.5099, 'learning_rate': 2.3756e-05, 'epoch': 2.33}
+
+[INFO|2024-12-28 21:03:35] logging.py:157 >> {'loss': 0.5186, 'learning_rate': 2.3216e-05, 'epoch': 2.34}
+
+[INFO|2024-12-28 21:03:42] logging.py:157 >> {'loss': 0.5043, 'learning_rate': 2.2682e-05, 'epoch': 2.34}
+
+[INFO|2024-12-28 21:03:48] logging.py:157 >> {'loss': 0.6100, 'learning_rate': 2.2154e-05, 'epoch': 2.35}
+
+[INFO|2024-12-28 21:03:55] logging.py:157 >> {'loss': 0.5987, 'learning_rate': 2.1631e-05, 'epoch': 2.36}
+
+[INFO|2024-12-28 21:04:02] logging.py:157 >> {'loss': 0.5212, 'learning_rate': 2.1113e-05, 'epoch': 2.37}
+
+[INFO|2024-12-28 21:04:10] logging.py:157 >> {'loss': 0.4796, 'learning_rate': 2.0601e-05, 'epoch': 2.38}
+
+[INFO|2024-12-28 21:04:17] logging.py:157 >> {'loss': 0.4844, 'learning_rate': 2.0094e-05, 'epoch': 2.38}
+
+[INFO|2024-12-28 21:04:22] logging.py:157 >> {'loss': 0.5085, 'learning_rate': 1.9594e-05, 'epoch': 2.39}
+
+[INFO|2024-12-28 21:04:29] logging.py:157 >> {'loss': 0.4839, 'learning_rate': 1.9098e-05, 'epoch': 2.40}
+
+[INFO|2024-12-28 21:04:29] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1500
+
+[INFO|2024-12-28 21:04:29] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:04:29] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:04:29] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1500/tokenizer_config.json
+
+[INFO|2024-12-28 21:04:29] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1500/special_tokens_map.json
+
+[INFO|2024-12-28 21:04:38] logging.py:157 >> {'loss': 0.5715, 'learning_rate': 1.8609e-05, 'epoch': 2.41}
+
+[INFO|2024-12-28 21:04:42] logging.py:157 >> {'loss': 0.5266, 'learning_rate': 1.8125e-05, 'epoch': 2.42}
+
+[INFO|2024-12-28 21:04:49] logging.py:157 >> {'loss': 0.5422, 'learning_rate': 1.7647e-05, 'epoch': 2.42}
+
+[INFO|2024-12-28 21:04:55] logging.py:157 >> {'loss': 0.5553, 'learning_rate': 1.7174e-05, 'epoch': 2.43}
+
+[INFO|2024-12-28 21:05:03] logging.py:157 >> {'loss': 0.5765, 'learning_rate': 1.6708e-05, 'epoch': 2.44}
+
+[INFO|2024-12-28 21:05:08] logging.py:157 >> {'loss': 0.5490, 'learning_rate': 1.6247e-05, 'epoch': 2.45}
+
+[INFO|2024-12-28 21:05:13] logging.py:157 >> {'loss': 0.4876, 'learning_rate': 1.5792e-05, 'epoch': 2.46}
+
+[INFO|2024-12-28 21:05:19] logging.py:157 >> {'loss': 0.5546, 'learning_rate': 1.5344e-05, 'epoch': 2.46}
+
+[INFO|2024-12-28 21:05:24] logging.py:157 >> {'loss': 0.5356, 'learning_rate': 1.4901e-05, 'epoch': 2.47}
+
+[INFO|2024-12-28 21:05:30] logging.py:157 >> {'loss': 0.5142, 'learning_rate': 1.4464e-05, 'epoch': 2.48}
+
+[INFO|2024-12-28 21:05:35] logging.py:157 >> {'loss': 0.6054, 'learning_rate': 1.4033e-05, 'epoch': 2.49}
+
+[INFO|2024-12-28 21:05:41] logging.py:157 >> {'loss': 0.5294, 'learning_rate': 1.3608e-05, 'epoch': 2.50}
+
+[INFO|2024-12-28 21:05:45] logging.py:157 >> {'loss': 0.5294, 'learning_rate': 1.3189e-05, 'epoch': 2.50}
+
+[INFO|2024-12-28 21:05:53] logging.py:157 >> {'loss': 0.4905, 'learning_rate': 1.2776e-05, 'epoch': 2.51}
+
+[INFO|2024-12-28 21:06:00] logging.py:157 >> {'loss': 0.5186, 'learning_rate': 1.2369e-05, 'epoch': 2.52}
+
+[INFO|2024-12-28 21:06:06] logging.py:157 >> {'loss': 0.4909, 'learning_rate': 1.1969e-05, 'epoch': 2.53}
+
+[INFO|2024-12-28 21:06:11] logging.py:157 >> {'loss': 0.5303, 'learning_rate': 1.1574e-05, 'epoch': 2.54}
+
+[INFO|2024-12-28 21:06:17] logging.py:157 >> {'loss': 0.5169, 'learning_rate': 1.1186e-05, 'epoch': 2.54}
+
+[INFO|2024-12-28 21:06:24] logging.py:157 >> {'loss': 0.5339, 'learning_rate': 1.0804e-05, 'epoch': 2.55}
+
+[INFO|2024-12-28 21:06:29] logging.py:157 >> {'loss': 0.5283, 'learning_rate': 1.0429e-05, 'epoch': 2.56}
+
+[INFO|2024-12-28 21:06:29] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1600
+
+[INFO|2024-12-28 21:06:29] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:06:29] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:06:29] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1600/tokenizer_config.json
+
+[INFO|2024-12-28 21:06:29] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1600/special_tokens_map.json
+
+[INFO|2024-12-28 21:06:36] logging.py:157 >> {'loss': 0.5576, 'learning_rate': 1.0059e-05, 'epoch': 2.57}
+
+[INFO|2024-12-28 21:06:42] logging.py:157 >> {'loss': 0.5136, 'learning_rate': 9.6964e-06, 'epoch': 2.58}
+
+[INFO|2024-12-28 21:06:49] logging.py:157 >> {'loss': 0.5885, 'learning_rate': 9.3397e-06, 'epoch': 2.58}
+
+[INFO|2024-12-28 21:06:57] logging.py:157 >> {'loss': 0.5000, 'learning_rate': 8.9894e-06, 'epoch': 2.59}
+
+[INFO|2024-12-28 21:07:04] logging.py:157 >> {'loss': 0.5325, 'learning_rate': 8.6455e-06, 'epoch': 2.60}
+
+[INFO|2024-12-28 21:07:10] logging.py:157 >> {'loss': 0.5772, 'learning_rate': 8.3079e-06, 'epoch': 2.61}
+
+[INFO|2024-12-28 21:07:17] logging.py:157 >> {'loss': 0.5736, 'learning_rate': 7.9768e-06, 'epoch': 2.62}
+
+[INFO|2024-12-28 21:07:23] logging.py:157 >> {'loss': 0.5199, 'learning_rate': 7.6522e-06, 'epoch': 2.62}
+
+[INFO|2024-12-28 21:07:30] logging.py:157 >> {'loss': 0.5753, 'learning_rate': 7.3340e-06, 'epoch': 2.63}
+
+[INFO|2024-12-28 21:07:35] logging.py:157 >> {'loss': 0.5424, 'learning_rate': 7.0224e-06, 'epoch': 2.64}
+
+[INFO|2024-12-28 21:07:42] logging.py:157 >> {'loss': 0.5555, 'learning_rate': 6.7172e-06, 'epoch': 2.65}
+
+[INFO|2024-12-28 21:07:50] logging.py:157 >> {'loss': 0.4936, 'learning_rate': 6.4186e-06, 'epoch': 2.66}
+
+[INFO|2024-12-28 21:07:56] logging.py:157 >> {'loss': 0.6291, 'learning_rate': 6.1266e-06, 'epoch': 2.66}
+
+[INFO|2024-12-28 21:08:01] logging.py:157 >> {'loss': 0.5197, 'learning_rate': 5.8412e-06, 'epoch': 2.67}
+
+[INFO|2024-12-28 21:08:08] logging.py:157 >> {'loss': 0.5398, 'learning_rate': 5.5624e-06, 'epoch': 2.68}
+
+[INFO|2024-12-28 21:08:13] logging.py:157 >> {'loss': 0.6059, 'learning_rate': 5.2902e-06, 'epoch': 2.69}
+
+[INFO|2024-12-28 21:08:20] logging.py:157 >> {'loss': 0.5310, 'learning_rate': 5.0246e-06, 'epoch': 2.70}
+
+[INFO|2024-12-28 21:08:24] logging.py:157 >> {'loss': 0.6054, 'learning_rate': 4.7657e-06, 'epoch': 2.70}
+
+[INFO|2024-12-28 21:08:31] logging.py:157 >> {'loss': 0.5173, 'learning_rate': 4.5135e-06, 'epoch': 2.71}
+
+[INFO|2024-12-28 21:08:36] logging.py:157 >> {'loss': 0.4944, 'learning_rate': 4.2681e-06, 'epoch': 2.72}
+
+[INFO|2024-12-28 21:08:36] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1700
+
+[INFO|2024-12-28 21:08:37] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:08:37] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:08:37] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1700/tokenizer_config.json
+
+[INFO|2024-12-28 21:08:37] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1700/special_tokens_map.json
+
+[INFO|2024-12-28 21:08:44] logging.py:157 >> {'loss': 0.5183, 'learning_rate': 4.0293e-06, 'epoch': 2.73}
+
+[INFO|2024-12-28 21:08:50] logging.py:157 >> {'loss': 0.6680, 'learning_rate': 3.7972e-06, 'epoch': 2.74}
+
+[INFO|2024-12-28 21:08:56] logging.py:157 >> {'loss': 0.5068, 'learning_rate': 3.5719e-06, 'epoch': 2.74}
+
+[INFO|2024-12-28 21:09:02] logging.py:157 >> {'loss': 0.5823, 'learning_rate': 3.3534e-06, 'epoch': 2.75}
+
+[INFO|2024-12-28 21:09:07] logging.py:157 >> {'loss': 0.6111, 'learning_rate': 3.1417e-06, 'epoch': 2.76}
+
+[INFO|2024-12-28 21:09:13] logging.py:157 >> {'loss': 0.5231, 'learning_rate': 2.9367e-06, 'epoch': 2.77}
+
+[INFO|2024-12-28 21:09:20] logging.py:157 >> {'loss': 0.5236, 'learning_rate': 2.7386e-06, 'epoch': 2.78}
+
+[INFO|2024-12-28 21:09:29] logging.py:157 >> {'loss': 0.5657, 'learning_rate': 2.5473e-06, 'epoch': 2.78}
+
+[INFO|2024-12-28 21:09:34] logging.py:157 >> {'loss': 0.5518, 'learning_rate': 2.3629e-06, 'epoch': 2.79}
+
+[INFO|2024-12-28 21:09:40] logging.py:157 >> {'loss': 0.4908, 'learning_rate': 2.1852e-06, 'epoch': 2.80}
+
+[INFO|2024-12-28 21:09:49] logging.py:157 >> {'loss': 0.5459, 'learning_rate': 2.0145e-06, 'epoch': 2.81}
+
+[INFO|2024-12-28 21:09:56] logging.py:157 >> {'loss': 0.5208, 'learning_rate': 1.8506e-06, 'epoch': 2.82}
+
+[INFO|2024-12-28 21:10:02] logging.py:157 >> {'loss': 0.5824, 'learning_rate': 1.6936e-06, 'epoch': 2.82}
+
+[INFO|2024-12-28 21:10:11] logging.py:157 >> {'loss': 0.5512, 'learning_rate': 1.5436e-06, 'epoch': 2.83}
+
+[INFO|2024-12-28 21:10:18] logging.py:157 >> {'loss': 0.6327, 'learning_rate': 1.4004e-06, 'epoch': 2.84}
+
+[INFO|2024-12-28 21:10:26] logging.py:157 >> {'loss': 0.5292, 'learning_rate': 1.2641e-06, 'epoch': 2.85}
+
+[INFO|2024-12-28 21:10:32] logging.py:157 >> {'loss': 0.5692, 'learning_rate': 1.1348e-06, 'epoch': 2.86}
+
+[INFO|2024-12-28 21:10:39] logging.py:157 >> {'loss': 0.5532, 'learning_rate': 1.0124e-06, 'epoch': 2.86}
+
+[INFO|2024-12-28 21:10:44] logging.py:157 >> {'loss': 0.5314, 'learning_rate': 8.9701e-07, 'epoch': 2.87}
+
+[INFO|2024-12-28 21:10:51] logging.py:157 >> {'loss': 0.5240, 'learning_rate': 7.8853e-07, 'epoch': 2.88}
+
+[INFO|2024-12-28 21:10:51] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1800
+
+[INFO|2024-12-28 21:10:51] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:10:51] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:10:52] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1800/tokenizer_config.json
+
+[INFO|2024-12-28 21:10:52] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1800/special_tokens_map.json
+
+[INFO|2024-12-28 21:10:58] logging.py:157 >> {'loss': 0.5227, 'learning_rate': 6.8701e-07, 'epoch': 2.89}
+
+[INFO|2024-12-28 21:11:04] logging.py:157 >> {'loss': 0.5993, 'learning_rate': 5.9247e-07, 'epoch': 2.90}
+
+[INFO|2024-12-28 21:11:12] logging.py:157 >> {'loss': 0.5618, 'learning_rate': 5.0490e-07, 'epoch': 2.90}
+
+[INFO|2024-12-28 21:11:18] logging.py:157 >> {'loss': 0.5504, 'learning_rate': 4.2431e-07, 'epoch': 2.91}
+
+[INFO|2024-12-28 21:11:24] logging.py:157 >> {'loss': 0.5147, 'learning_rate': 3.5071e-07, 'epoch': 2.92}
+
+[INFO|2024-12-28 21:11:32] logging.py:157 >> {'loss': 0.5564, 'learning_rate': 2.8411e-07, 'epoch': 2.93}
+
+[INFO|2024-12-28 21:11:40] logging.py:157 >> {'loss': 0.5188, 'learning_rate': 2.2450e-07, 'epoch': 2.94}
+
+[INFO|2024-12-28 21:11:45] logging.py:157 >> {'loss': 0.5438, 'learning_rate': 1.7190e-07, 'epoch': 2.94}
+
+[INFO|2024-12-28 21:11:51] logging.py:157 >> {'loss': 0.4962, 'learning_rate': 1.2630e-07, 'epoch': 2.95}
+
+[INFO|2024-12-28 21:11:58] logging.py:157 >> {'loss': 0.5021, 'learning_rate': 8.7717e-08, 'epoch': 2.96}
+
+[INFO|2024-12-28 21:12:03] logging.py:157 >> {'loss': 0.5277, 'learning_rate': 5.6142e-08, 'epoch': 2.97}
+
+[INFO|2024-12-28 21:12:06] logging.py:157 >> {'loss': 0.5764, 'learning_rate': 3.1581e-08, 'epoch': 2.98}
+
+[INFO|2024-12-28 21:12:14] logging.py:157 >> {'loss': 0.5408, 'learning_rate': 1.4036e-08, 'epoch': 2.98}
+
+[INFO|2024-12-28 21:12:23] logging.py:157 >> {'loss': 0.5014, 'learning_rate': 3.5092e-09, 'epoch': 2.99}
+
+[INFO|2024-12-28 21:12:29] logging.py:157 >> {'loss': 0.6182, 'learning_rate': 0.0000e+00, 'epoch': 3.00}
+
+[INFO|2024-12-28 21:12:29] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1875
+
+[INFO|2024-12-28 21:12:29] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:12:29] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:12:30] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1875/tokenizer_config.json
+
+[INFO|2024-12-28 21:12:30] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/checkpoint-1875/special_tokens_map.json
+
+[INFO|2024-12-28 21:12:31] trainer.py:2584 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2024-12-28 21:12:31] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3.2-1B/lora/llama3.2-1b
+
+[INFO|2024-12-28 21:12:31] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Llama-3.2-1B/snapshots/4e20de362430cd3b72f300e6b0f18e50e7166e08/config.json
+
+[INFO|2024-12-28 21:12:31] configuration_utils.py:746 >> Model config LlamaConfig {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2024-12-28 21:12:31] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/tokenizer_config.json
+
+[INFO|2024-12-28 21:12:31] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3.2-1B/lora/llama3.2-1b/special_tokens_map.json
+
+[WARNING|2024-12-28 21:12:32] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2024-12-28 21:12:32] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2024-12-28 21:12:32] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..04829afa78a2d2df203ac846968db37269b01f7f
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..61c03bf2b5e0c03056cebf7a58c8c096dafc1ffc
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..9aecdedbe38ee7488418ffeffde0ced048359694
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1764404625814323e+17,
+    "train_loss": 0.6465437274932861,
+    "train_runtime": 2365.2475,
+    "train_samples_per_second": 12.684,
+    "train_steps_per_second": 0.793
+}
\ No newline at end of file
diff --git a/trainer_log.jsonl b/trainer_log.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..5fc4e9b9654af7b0ddfbc4bebc46009ed280028d
--- /dev/null
+++ b/trainer_log.jsonl
@@ -0,0 +1,377 @@
+{"current_steps": 5, "total_steps": 234, "loss": 1.0617, "lr": 1.9977477585156252e-05, "epoch": 0.064, "percentage": 2.14, "elapsed_time": "0:00:51", "remaining_time": "0:39:31"}
+{"current_steps": 5, "total_steps": 1875, "loss": 1.2049, "lr": 0.0001999964908278481, "epoch": 0.008, "percentage": 0.27, "elapsed_time": "0:00:05", "remaining_time": "0:34:31"}
+{"current_steps": 10, "total_steps": 1875, "loss": 0.9333, "lr": 0.00019998596355767805, "epoch": 0.016, "percentage": 0.53, "elapsed_time": "0:00:13", "remaining_time": "0:40:38"}
+{"current_steps": 15, "total_steps": 1875, "loss": 0.8671, "lr": 0.00019996841892833, "epoch": 0.024, "percentage": 0.8, "elapsed_time": "0:00:19", "remaining_time": "0:41:10"}
+{"current_steps": 20, "total_steps": 1875, "loss": 0.7979, "lr": 0.00019994385817114646, "epoch": 0.032, "percentage": 1.07, "elapsed_time": "0:00:25", "remaining_time": "0:39:02"}
+{"current_steps": 25, "total_steps": 1875, "loss": 0.7662, "lr": 0.00019991228300988585, "epoch": 0.04, "percentage": 1.33, "elapsed_time": "0:00:31", "remaining_time": "0:38:18"}
+{"current_steps": 30, "total_steps": 1875, "loss": 0.7929, "lr": 0.00019987369566060176, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:00:37", "remaining_time": "0:38:54"}
+{"current_steps": 35, "total_steps": 1875, "loss": 0.7683, "lr": 0.00019982809883148722, "epoch": 0.056, "percentage": 1.87, "elapsed_time": "0:00:44", "remaining_time": "0:38:41"}
+{"current_steps": 40, "total_steps": 1875, "loss": 0.8667, "lr": 0.00019977549572268468, "epoch": 0.064, "percentage": 2.13, "elapsed_time": "0:00:50", "remaining_time": "0:38:42"}
+{"current_steps": 45, "total_steps": 1875, "loss": 0.8446, "lr": 0.0001997158900260614, "epoch": 0.072, "percentage": 2.4, "elapsed_time": "0:00:58", "remaining_time": "0:39:46"}
+{"current_steps": 50, "total_steps": 1875, "loss": 0.9051, "lr": 0.00019964928592495045, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:01:03", "remaining_time": "0:38:40"}
+{"current_steps": 55, "total_steps": 1875, "loss": 0.7235, "lr": 0.00019957568809385694, "epoch": 0.088, "percentage": 2.93, "elapsed_time": "0:01:08", "remaining_time": "0:37:45"}
+{"current_steps": 60, "total_steps": 1875, "loss": 0.8169, "lr": 0.00019949510169813003, "epoch": 0.096, "percentage": 3.2, "elapsed_time": "0:01:12", "remaining_time": "0:36:28"}
+{"current_steps": 65, "total_steps": 1875, "loss": 0.8266, "lr": 0.00019940753239360047, "epoch": 0.104, "percentage": 3.47, "elapsed_time": "0:01:18", "remaining_time": "0:36:17"}
+{"current_steps": 70, "total_steps": 1875, "loss": 0.758, "lr": 0.00019931298632618356, "epoch": 0.112, "percentage": 3.73, "elapsed_time": "0:01:23", "remaining_time": "0:35:52"}
+{"current_steps": 75, "total_steps": 1875, "loss": 0.7759, "lr": 0.0001992114701314478, "epoch": 0.12, "percentage": 4.0, "elapsed_time": "0:01:30", "remaining_time": "0:36:07"}
+{"current_steps": 80, "total_steps": 1875, "loss": 0.7797, "lr": 0.0001991029909341493, "epoch": 0.128, "percentage": 4.27, "elapsed_time": "0:01:37", "remaining_time": "0:36:20"}
+{"current_steps": 85, "total_steps": 1875, "loss": 0.7437, "lr": 0.00019898755634773158, "epoch": 0.136, "percentage": 4.53, "elapsed_time": "0:01:43", "remaining_time": "0:36:21"}
+{"current_steps": 90, "total_steps": 1875, "loss": 0.8043, "lr": 0.0001988651744737914, "epoch": 0.144, "percentage": 4.8, "elapsed_time": "0:01:50", "remaining_time": "0:36:26"}
+{"current_steps": 95, "total_steps": 1875, "loss": 0.7701, "lr": 0.00019873585390151003, "epoch": 0.152, "percentage": 5.07, "elapsed_time": "0:01:57", "remaining_time": "0:36:34"}
+{"current_steps": 100, "total_steps": 1875, "loss": 0.709, "lr": 0.0001985996037070505, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:02:04", "remaining_time": "0:36:46"}
+{"current_steps": 105, "total_steps": 1875, "loss": 0.7377, "lr": 0.00019845643345292054, "epoch": 0.168, "percentage": 5.6, "elapsed_time": "0:02:11", "remaining_time": "0:36:57"}
+{"current_steps": 110, "total_steps": 1875, "loss": 0.8352, "lr": 0.00019830635318730154, "epoch": 0.176, "percentage": 5.87, "elapsed_time": "0:02:17", "remaining_time": "0:36:45"}
+{"current_steps": 115, "total_steps": 1875, "loss": 0.7738, "lr": 0.0001981493734433433, "epoch": 0.184, "percentage": 6.13, "elapsed_time": "0:02:24", "remaining_time": "0:36:55"}
+{"current_steps": 120, "total_steps": 1875, "loss": 0.8067, "lr": 0.0001979855052384247, "epoch": 0.192, "percentage": 6.4, "elapsed_time": "0:02:29", "remaining_time": "0:36:32"}
+{"current_steps": 125, "total_steps": 1875, "loss": 0.7456, "lr": 0.00019781476007338058, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:02:35", "remaining_time": "0:36:13"}
+{"current_steps": 130, "total_steps": 1875, "loss": 0.758, "lr": 0.00019763714993169452, "epoch": 0.208, "percentage": 6.93, "elapsed_time": "0:02:42", "remaining_time": "0:36:20"}
+{"current_steps": 135, "total_steps": 1875, "loss": 0.7895, "lr": 0.00019745268727865774, "epoch": 0.216, "percentage": 7.2, "elapsed_time": "0:02:48", "remaining_time": "0:36:10"}
+{"current_steps": 140, "total_steps": 1875, "loss": 0.7302, "lr": 0.00019726138506049438, "epoch": 0.224, "percentage": 7.47, "elapsed_time": "0:02:56", "remaining_time": "0:36:26"}
+{"current_steps": 145, "total_steps": 1875, "loss": 0.8152, "lr": 0.00019706325670345275, "epoch": 0.232, "percentage": 7.73, "elapsed_time": "0:03:01", "remaining_time": "0:36:11"}
+{"current_steps": 150, "total_steps": 1875, "loss": 0.8461, "lr": 0.0001968583161128631, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:03:06", "remaining_time": "0:35:45"}
+{"current_steps": 155, "total_steps": 1875, "loss": 0.7787, "lr": 0.00019664657767216176, "epoch": 0.248, "percentage": 8.27, "elapsed_time": "0:03:12", "remaining_time": "0:35:34"}
+{"current_steps": 160, "total_steps": 1875, "loss": 0.7574, "lr": 0.00019642805624188147, "epoch": 0.256, "percentage": 8.53, "elapsed_time": "0:03:18", "remaining_time": "0:35:27"}
+{"current_steps": 165, "total_steps": 1875, "loss": 0.8487, "lr": 0.0001962027671586086, "epoch": 0.264, "percentage": 8.8, "elapsed_time": "0:03:22", "remaining_time": "0:35:00"}
+{"current_steps": 170, "total_steps": 1875, "loss": 0.6611, "lr": 0.00019597072623390668, "epoch": 0.272, "percentage": 9.07, "elapsed_time": "0:03:29", "remaining_time": "0:34:56"}
+{"current_steps": 175, "total_steps": 1875, "loss": 0.7802, "lr": 0.00019573194975320673, "epoch": 0.28, "percentage": 9.33, "elapsed_time": "0:03:35", "remaining_time": "0:34:55"}
+{"current_steps": 180, "total_steps": 1875, "loss": 0.6727, "lr": 0.00019548645447466431, "epoch": 0.288, "percentage": 9.6, "elapsed_time": "0:03:42", "remaining_time": "0:34:56"}
+{"current_steps": 185, "total_steps": 1875, "loss": 0.7502, "lr": 0.00019523425762798329, "epoch": 0.296, "percentage": 9.87, "elapsed_time": "0:03:47", "remaining_time": "0:34:38"}
+{"current_steps": 190, "total_steps": 1875, "loss": 0.8401, "lr": 0.00019497537691320668, "epoch": 0.304, "percentage": 10.13, "elapsed_time": "0:03:53", "remaining_time": "0:34:30"}
+{"current_steps": 195, "total_steps": 1875, "loss": 0.7494, "lr": 0.00019470983049947444, "epoch": 0.312, "percentage": 10.4, "elapsed_time": "0:03:58", "remaining_time": "0:34:16"}
+{"current_steps": 200, "total_steps": 1875, "loss": 0.7842, "lr": 0.00019443763702374812, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "0:04:04", "remaining_time": "0:34:11"}
+{"current_steps": 205, "total_steps": 1875, "loss": 0.8082, "lr": 0.00019415881558950302, "epoch": 0.328, "percentage": 10.93, "elapsed_time": "0:04:12", "remaining_time": "0:34:15"}
+{"current_steps": 210, "total_steps": 1875, "loss": 0.7883, "lr": 0.00019387338576538744, "epoch": 0.336, "percentage": 11.2, "elapsed_time": "0:04:17", "remaining_time": "0:34:01"}
+{"current_steps": 215, "total_steps": 1875, "loss": 0.7356, "lr": 0.00019358136758384912, "epoch": 0.344, "percentage": 11.47, "elapsed_time": "0:04:25", "remaining_time": "0:34:13"}
+{"current_steps": 220, "total_steps": 1875, "loss": 0.7891, "lr": 0.00019328278153972947, "epoch": 0.352, "percentage": 11.73, "elapsed_time": "0:04:31", "remaining_time": "0:34:04"}
+{"current_steps": 225, "total_steps": 1875, "loss": 0.7671, "lr": 0.00019297764858882514, "epoch": 0.36, "percentage": 12.0, "elapsed_time": "0:04:39", "remaining_time": "0:34:06"}
+{"current_steps": 230, "total_steps": 1875, "loss": 0.6608, "lr": 0.0001926659901464172, "epoch": 0.368, "percentage": 12.27, "elapsed_time": "0:04:45", "remaining_time": "0:34:04"}
+{"current_steps": 235, "total_steps": 1875, "loss": 0.647, "lr": 0.00019234782808576824, "epoch": 0.376, "percentage": 12.53, "elapsed_time": "0:04:54", "remaining_time": "0:34:17"}
+{"current_steps": 240, "total_steps": 1875, "loss": 0.729, "lr": 0.00019202318473658705, "epoch": 0.384, "percentage": 12.8, "elapsed_time": "0:05:02", "remaining_time": "0:34:18"}
+{"current_steps": 245, "total_steps": 1875, "loss": 0.6713, "lr": 0.00019169208288346166, "epoch": 0.392, "percentage": 13.07, "elapsed_time": "0:05:08", "remaining_time": "0:34:09"}
+{"current_steps": 250, "total_steps": 1875, "loss": 0.7049, "lr": 0.0001913545457642601, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:05:16", "remaining_time": "0:34:19"}
+{"current_steps": 255, "total_steps": 1875, "loss": 0.7419, "lr": 0.00019101059706849957, "epoch": 0.408, "percentage": 13.6, "elapsed_time": "0:05:24", "remaining_time": "0:34:20"}
+{"current_steps": 260, "total_steps": 1875, "loss": 0.7148, "lr": 0.00019066026093568378, "epoch": 0.416, "percentage": 13.87, "elapsed_time": "0:05:29", "remaining_time": "0:34:08"}
+{"current_steps": 265, "total_steps": 1875, "loss": 0.7493, "lr": 0.00019030356195360874, "epoch": 0.424, "percentage": 14.13, "elapsed_time": "0:05:37", "remaining_time": "0:34:10"}
+{"current_steps": 270, "total_steps": 1875, "loss": 0.7652, "lr": 0.0001899405251566371, "epoch": 0.432, "percentage": 14.4, "elapsed_time": "0:05:43", "remaining_time": "0:34:01"}
+{"current_steps": 275, "total_steps": 1875, "loss": 0.7438, "lr": 0.0001895711760239413, "epoch": 0.44, "percentage": 14.67, "elapsed_time": "0:05:50", "remaining_time": "0:33:59"}
+{"current_steps": 280, "total_steps": 1875, "loss": 0.7683, "lr": 0.0001891955404777151, "epoch": 0.448, "percentage": 14.93, "elapsed_time": "0:05:55", "remaining_time": "0:33:44"}
+{"current_steps": 285, "total_steps": 1875, "loss": 0.8115, "lr": 0.00018881364488135448, "epoch": 0.456, "percentage": 15.2, "elapsed_time": "0:06:00", "remaining_time": "0:33:30"}
+{"current_steps": 290, "total_steps": 1875, "loss": 0.8335, "lr": 0.00018842551603760724, "epoch": 0.464, "percentage": 15.47, "elapsed_time": "0:06:06", "remaining_time": "0:33:25"}
+{"current_steps": 295, "total_steps": 1875, "loss": 0.6933, "lr": 0.00018803118118669202, "epoch": 0.472, "percentage": 15.73, "elapsed_time": "0:06:13", "remaining_time": "0:33:20"}
+{"current_steps": 300, "total_steps": 1875, "loss": 0.7515, "lr": 0.00018763066800438636, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "0:06:17", "remaining_time": "0:33:04"}
+{"current_steps": 305, "total_steps": 1875, "loss": 0.6931, "lr": 0.0001872240046000844, "epoch": 0.488, "percentage": 16.27, "elapsed_time": "0:06:25", "remaining_time": "0:33:05"}
+{"current_steps": 310, "total_steps": 1875, "loss": 0.782, "lr": 0.00018681121951482393, "epoch": 0.496, "percentage": 16.53, "elapsed_time": "0:06:31", "remaining_time": "0:32:58"}
+{"current_steps": 315, "total_steps": 1875, "loss": 0.7361, "lr": 0.00018639234171928353, "epoch": 0.504, "percentage": 16.8, "elapsed_time": "0:06:38", "remaining_time": "0:32:52"}
+{"current_steps": 320, "total_steps": 1875, "loss": 0.7443, "lr": 0.0001859674006117491, "epoch": 0.512, "percentage": 17.07, "elapsed_time": "0:06:44", "remaining_time": "0:32:43"}
+{"current_steps": 325, "total_steps": 1875, "loss": 0.7221, "lr": 0.00018553642601605068, "epoch": 0.52, "percentage": 17.33, "elapsed_time": "0:06:51", "remaining_time": "0:32:41"}
+{"current_steps": 330, "total_steps": 1875, "loss": 0.7622, "lr": 0.00018509944817946922, "epoch": 0.528, "percentage": 17.6, "elapsed_time": "0:06:57", "remaining_time": "0:32:33"}
+{"current_steps": 335, "total_steps": 1875, "loss": 0.8556, "lr": 0.0001846564977706138, "epoch": 0.536, "percentage": 17.87, "elapsed_time": "0:07:03", "remaining_time": "0:32:25"}
+{"current_steps": 340, "total_steps": 1875, "loss": 0.7814, "lr": 0.00018420760587726923, "epoch": 0.544, "percentage": 18.13, "elapsed_time": "0:07:09", "remaining_time": "0:32:17"}
+{"current_steps": 345, "total_steps": 1875, "loss": 0.722, "lr": 0.0001837528040042142, "epoch": 0.552, "percentage": 18.4, "elapsed_time": "0:07:18", "remaining_time": "0:32:24"}
+{"current_steps": 350, "total_steps": 1875, "loss": 0.7903, "lr": 0.00018329212407100994, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "0:07:22", "remaining_time": "0:32:09"}
+{"current_steps": 355, "total_steps": 1875, "loss": 0.6996, "lr": 0.00018282559840976042, "epoch": 0.568, "percentage": 18.93, "elapsed_time": "0:07:28", "remaining_time": "0:31:58"}
+{"current_steps": 360, "total_steps": 1875, "loss": 0.773, "lr": 0.00018235325976284275, "epoch": 0.576, "percentage": 19.2, "elapsed_time": "0:07:33", "remaining_time": "0:31:49"}
+{"current_steps": 365, "total_steps": 1875, "loss": 0.728, "lr": 0.00018187514128060946, "epoch": 0.584, "percentage": 19.47, "elapsed_time": "0:07:40", "remaining_time": "0:31:43"}
+{"current_steps": 370, "total_steps": 1875, "loss": 0.7659, "lr": 0.00018139127651906184, "epoch": 0.592, "percentage": 19.73, "elapsed_time": "0:07:45", "remaining_time": "0:31:33"}
+{"current_steps": 375, "total_steps": 1875, "loss": 0.7039, "lr": 0.00018090169943749476, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "0:07:50", "remaining_time": "0:31:21"}
+{"current_steps": 380, "total_steps": 1875, "loss": 0.7125, "lr": 0.00018040644439611348, "epoch": 0.608, "percentage": 20.27, "elapsed_time": "0:07:56", "remaining_time": "0:31:14"}
+{"current_steps": 385, "total_steps": 1875, "loss": 0.698, "lr": 0.00017990554615362198, "epoch": 0.616, "percentage": 20.53, "elapsed_time": "0:08:03", "remaining_time": "0:31:11"}
+{"current_steps": 390, "total_steps": 1875, "loss": 0.8255, "lr": 0.00017939903986478355, "epoch": 0.624, "percentage": 20.8, "elapsed_time": "0:08:08", "remaining_time": "0:30:59"}
+{"current_steps": 395, "total_steps": 1875, "loss": 0.6616, "lr": 0.00017888696107795342, "epoch": 0.632, "percentage": 21.07, "elapsed_time": "0:08:13", "remaining_time": "0:30:50"}
+{"current_steps": 400, "total_steps": 1875, "loss": 0.7452, "lr": 0.000178369345732584, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "0:08:18", "remaining_time": "0:30:39"}
+{"current_steps": 405, "total_steps": 1875, "loss": 0.7652, "lr": 0.00017784623015670238, "epoch": 0.648, "percentage": 21.6, "elapsed_time": "0:08:27", "remaining_time": "0:30:40"}
+{"current_steps": 410, "total_steps": 1875, "loss": 0.7793, "lr": 0.00017731765106436073, "epoch": 0.656, "percentage": 21.87, "elapsed_time": "0:08:34", "remaining_time": "0:30:39"}
+{"current_steps": 415, "total_steps": 1875, "loss": 0.6875, "lr": 0.00017678364555305978, "epoch": 0.664, "percentage": 22.13, "elapsed_time": "0:08:40", "remaining_time": "0:30:29"}
+{"current_steps": 420, "total_steps": 1875, "loss": 0.7465, "lr": 0.0001762442511011448, "epoch": 0.672, "percentage": 22.4, "elapsed_time": "0:08:48", "remaining_time": "0:30:30"}
+{"current_steps": 425, "total_steps": 1875, "loss": 0.7205, "lr": 0.00017569950556517566, "epoch": 0.68, "percentage": 22.67, "elapsed_time": "0:08:55", "remaining_time": "0:30:27"}
+{"current_steps": 430, "total_steps": 1875, "loss": 0.6589, "lr": 0.00017514944717726962, "epoch": 0.688, "percentage": 22.93, "elapsed_time": "0:09:02", "remaining_time": "0:30:22"}
+{"current_steps": 435, "total_steps": 1875, "loss": 0.7035, "lr": 0.00017459411454241822, "epoch": 0.696, "percentage": 23.2, "elapsed_time": "0:09:08", "remaining_time": "0:30:14"}
+{"current_steps": 440, "total_steps": 1875, "loss": 0.787, "lr": 0.00017403354663577783, "epoch": 0.704, "percentage": 23.47, "elapsed_time": "0:09:15", "remaining_time": "0:30:10"}
+{"current_steps": 445, "total_steps": 1875, "loss": 0.7515, "lr": 0.00017346778279993415, "epoch": 0.712, "percentage": 23.73, "elapsed_time": "0:09:23", "remaining_time": "0:30:09"}
+{"current_steps": 450, "total_steps": 1875, "loss": 0.7199, "lr": 0.00017289686274214118, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "0:09:28", "remaining_time": "0:30:01"}
+{"current_steps": 455, "total_steps": 1875, "loss": 0.8037, "lr": 0.00017232082653153422, "epoch": 0.728, "percentage": 24.27, "elapsed_time": "0:09:35", "remaining_time": "0:29:55"}
+{"current_steps": 460, "total_steps": 1875, "loss": 0.7502, "lr": 0.00017173971459631787, "epoch": 0.736, "percentage": 24.53, "elapsed_time": "0:09:40", "remaining_time": "0:29:46"}
+{"current_steps": 465, "total_steps": 1875, "loss": 0.7446, "lr": 0.00017115356772092857, "epoch": 0.744, "percentage": 24.8, "elapsed_time": "0:09:47", "remaining_time": "0:29:42"}
+{"current_steps": 470, "total_steps": 1875, "loss": 0.6507, "lr": 0.0001705624270431721, "epoch": 0.752, "percentage": 25.07, "elapsed_time": "0:09:54", "remaining_time": "0:29:36"}
+{"current_steps": 475, "total_steps": 1875, "loss": 0.7164, "lr": 0.00016996633405133655, "epoch": 0.76, "percentage": 25.33, "elapsed_time": "0:10:00", "remaining_time": "0:29:29"}
+{"current_steps": 480, "total_steps": 1875, "loss": 0.7621, "lr": 0.0001693653305812805, "epoch": 0.768, "percentage": 25.6, "elapsed_time": "0:10:06", "remaining_time": "0:29:23"}
+{"current_steps": 485, "total_steps": 1875, "loss": 0.7623, "lr": 0.00016875945881349676, "epoch": 0.776, "percentage": 25.87, "elapsed_time": "0:10:12", "remaining_time": "0:29:16"}
+{"current_steps": 490, "total_steps": 1875, "loss": 0.6606, "lr": 0.000168148761270152, "epoch": 0.784, "percentage": 26.13, "elapsed_time": "0:10:20", "remaining_time": "0:29:14"}
+{"current_steps": 495, "total_steps": 1875, "loss": 0.6941, "lr": 0.00016753328081210245, "epoch": 0.792, "percentage": 26.4, "elapsed_time": "0:10:28", "remaining_time": "0:29:13"}
+{"current_steps": 500, "total_steps": 1875, "loss": 0.6841, "lr": 0.00016691306063588583, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:10:33", "remaining_time": "0:29:02"}
+{"current_steps": 505, "total_steps": 1875, "loss": 0.6996, "lr": 0.00016628814427068953, "epoch": 0.808, "percentage": 26.93, "elapsed_time": "0:10:41", "remaining_time": "0:28:59"}
+{"current_steps": 510, "total_steps": 1875, "loss": 0.7542, "lr": 0.00016565857557529566, "epoch": 0.816, "percentage": 27.2, "elapsed_time": "0:10:48", "remaining_time": "0:28:55"}
+{"current_steps": 515, "total_steps": 1875, "loss": 0.7175, "lr": 0.00016502439873500289, "epoch": 0.824, "percentage": 27.47, "elapsed_time": "0:10:54", "remaining_time": "0:28:47"}
+{"current_steps": 520, "total_steps": 1875, "loss": 0.7565, "lr": 0.0001643856582585254, "epoch": 0.832, "percentage": 27.73, "elapsed_time": "0:10:59", "remaining_time": "0:28:37"}
+{"current_steps": 525, "total_steps": 1875, "loss": 0.7339, "lr": 0.000163742398974869, "epoch": 0.84, "percentage": 28.0, "elapsed_time": "0:11:04", "remaining_time": "0:28:29"}
+{"current_steps": 530, "total_steps": 1875, "loss": 0.569, "lr": 0.00016309466603018496, "epoch": 0.848, "percentage": 28.27, "elapsed_time": "0:11:10", "remaining_time": "0:28:22"}
+{"current_steps": 535, "total_steps": 1875, "loss": 0.7556, "lr": 0.00016244250488460158, "epoch": 0.856, "percentage": 28.53, "elapsed_time": "0:11:15", "remaining_time": "0:28:11"}
+{"current_steps": 540, "total_steps": 1875, "loss": 0.7084, "lr": 0.00016178596130903344, "epoch": 0.864, "percentage": 28.8, "elapsed_time": "0:11:19", "remaining_time": "0:28:00"}
+{"current_steps": 545, "total_steps": 1875, "loss": 0.6935, "lr": 0.00016112508138196917, "epoch": 0.872, "percentage": 29.07, "elapsed_time": "0:11:25", "remaining_time": "0:27:53"}
+{"current_steps": 550, "total_steps": 1875, "loss": 0.7076, "lr": 0.0001604599114862375, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "0:11:31", "remaining_time": "0:27:44"}
+{"current_steps": 555, "total_steps": 1875, "loss": 0.7151, "lr": 0.0001597904983057519, "epoch": 0.888, "percentage": 29.6, "elapsed_time": "0:11:36", "remaining_time": "0:27:37"}
+{"current_steps": 560, "total_steps": 1875, "loss": 0.7001, "lr": 0.0001591168888222342, "epoch": 0.896, "percentage": 29.87, "elapsed_time": "0:11:42", "remaining_time": "0:27:29"}
+{"current_steps": 565, "total_steps": 1875, "loss": 0.7285, "lr": 0.00015843913031191723, "epoch": 0.904, "percentage": 30.13, "elapsed_time": "0:11:47", "remaining_time": "0:27:19"}
+{"current_steps": 570, "total_steps": 1875, "loss": 0.8041, "lr": 0.00015775727034222675, "epoch": 0.912, "percentage": 30.4, "elapsed_time": "0:11:53", "remaining_time": "0:27:13"}
+{"current_steps": 575, "total_steps": 1875, "loss": 0.7353, "lr": 0.0001570713567684432, "epoch": 0.92, "percentage": 30.67, "elapsed_time": "0:12:00", "remaining_time": "0:27:08"}
+{"current_steps": 580, "total_steps": 1875, "loss": 0.7792, "lr": 0.00015638143773034267, "epoch": 0.928, "percentage": 30.93, "elapsed_time": "0:12:05", "remaining_time": "0:27:00"}
+{"current_steps": 585, "total_steps": 1875, "loss": 1.0121, "lr": 0.00015568756164881882, "epoch": 0.936, "percentage": 31.2, "elapsed_time": "0:12:12", "remaining_time": "0:26:55"}
+{"current_steps": 590, "total_steps": 1875, "loss": 0.7727, "lr": 0.000154989777222484, "epoch": 0.944, "percentage": 31.47, "elapsed_time": "0:12:18", "remaining_time": "0:26:48"}
+{"current_steps": 595, "total_steps": 1875, "loss": 0.741, "lr": 0.00015428813342425177, "epoch": 0.952, "percentage": 31.73, "elapsed_time": "0:12:24", "remaining_time": "0:26:41"}
+{"current_steps": 600, "total_steps": 1875, "loss": 0.6919, "lr": 0.00015358267949789966, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "0:12:30", "remaining_time": "0:26:34"}
+{"current_steps": 605, "total_steps": 1875, "loss": 0.7163, "lr": 0.00015287346495461315, "epoch": 0.968, "percentage": 32.27, "elapsed_time": "0:12:38", "remaining_time": "0:26:31"}
+{"current_steps": 610, "total_steps": 1875, "loss": 0.8152, "lr": 0.0001521605395695108, "epoch": 0.976, "percentage": 32.53, "elapsed_time": "0:12:42", "remaining_time": "0:26:21"}
+{"current_steps": 615, "total_steps": 1875, "loss": 0.6709, "lr": 0.00015144395337815064, "epoch": 0.984, "percentage": 32.8, "elapsed_time": "0:12:48", "remaining_time": "0:26:15"}
+{"current_steps": 620, "total_steps": 1875, "loss": 0.6527, "lr": 0.00015072375667301893, "epoch": 0.992, "percentage": 33.07, "elapsed_time": "0:12:54", "remaining_time": "0:26:07"}
+{"current_steps": 625, "total_steps": 1875, "loss": 0.8194, "lr": 0.00015000000000000001, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:12:59", "remaining_time": "0:25:58"}
+{"current_steps": 630, "total_steps": 1875, "loss": 0.6627, "lr": 0.00014927273415482915, "epoch": 1.008, "percentage": 33.6, "elapsed_time": "0:13:04", "remaining_time": "0:25:51"}
+{"current_steps": 635, "total_steps": 1875, "loss": 0.6366, "lr": 0.0001485420101795274, "epoch": 1.016, "percentage": 33.87, "elapsed_time": "0:13:10", "remaining_time": "0:25:44"}
+{"current_steps": 640, "total_steps": 1875, "loss": 0.6717, "lr": 0.00014780787935881923, "epoch": 1.024, "percentage": 34.13, "elapsed_time": "0:13:15", "remaining_time": "0:25:35"}
+{"current_steps": 645, "total_steps": 1875, "loss": 0.6483, "lr": 0.0001470703932165333, "epoch": 1.032, "percentage": 34.4, "elapsed_time": "0:13:20", "remaining_time": "0:25:26"}
+{"current_steps": 650, "total_steps": 1875, "loss": 0.6151, "lr": 0.00014632960351198618, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "0:13:25", "remaining_time": "0:25:18"}
+{"current_steps": 655, "total_steps": 1875, "loss": 0.6707, "lr": 0.00014558556223635003, "epoch": 1.048, "percentage": 34.93, "elapsed_time": "0:13:32", "remaining_time": "0:25:13"}
+{"current_steps": 660, "total_steps": 1875, "loss": 0.6125, "lr": 0.00014483832160900326, "epoch": 1.056, "percentage": 35.2, "elapsed_time": "0:13:37", "remaining_time": "0:25:04"}
+{"current_steps": 665, "total_steps": 1875, "loss": 0.6206, "lr": 0.00014408793407386588, "epoch": 1.064, "percentage": 35.47, "elapsed_time": "0:13:42", "remaining_time": "0:24:56"}
+{"current_steps": 670, "total_steps": 1875, "loss": 0.6161, "lr": 0.00014333445229571873, "epoch": 1.072, "percentage": 35.73, "elapsed_time": "0:13:49", "remaining_time": "0:24:50"}
+{"current_steps": 675, "total_steps": 1875, "loss": 0.6583, "lr": 0.00014257792915650728, "epoch": 1.08, "percentage": 36.0, "elapsed_time": "0:13:54", "remaining_time": "0:24:43"}
+{"current_steps": 680, "total_steps": 1875, "loss": 0.6222, "lr": 0.00014181841775163013, "epoch": 1.088, "percentage": 36.27, "elapsed_time": "0:13:59", "remaining_time": "0:24:34"}
+{"current_steps": 685, "total_steps": 1875, "loss": 0.716, "lr": 0.0001410559713862128, "epoch": 1.096, "percentage": 36.53, "elapsed_time": "0:14:04", "remaining_time": "0:24:26"}
+{"current_steps": 690, "total_steps": 1875, "loss": 0.6198, "lr": 0.00014029064357136628, "epoch": 1.104, "percentage": 36.8, "elapsed_time": "0:14:10", "remaining_time": "0:24:21"}
+{"current_steps": 695, "total_steps": 1875, "loss": 0.6389, "lr": 0.00013952248802043165, "epoch": 1.112, "percentage": 37.07, "elapsed_time": "0:14:18", "remaining_time": "0:24:17"}
+{"current_steps": 700, "total_steps": 1875, "loss": 0.6842, "lr": 0.0001387515586452103, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "0:14:24", "remaining_time": "0:24:10"}
+{"current_steps": 705, "total_steps": 1875, "loss": 0.6071, "lr": 0.00013797790955218014, "epoch": 1.1280000000000001, "percentage": 37.6, "elapsed_time": "0:14:32", "remaining_time": "0:24:08"}
+{"current_steps": 710, "total_steps": 1875, "loss": 0.5915, "lr": 0.00013720159503869815, "epoch": 1.1360000000000001, "percentage": 37.87, "elapsed_time": "0:14:40", "remaining_time": "0:24:04"}
+{"current_steps": 715, "total_steps": 1875, "loss": 0.6794, "lr": 0.00013642266958918984, "epoch": 1.144, "percentage": 38.13, "elapsed_time": "0:14:46", "remaining_time": "0:23:57"}
+{"current_steps": 720, "total_steps": 1875, "loss": 0.6773, "lr": 0.00013564118787132506, "epoch": 1.152, "percentage": 38.4, "elapsed_time": "0:14:51", "remaining_time": "0:23:50"}
+{"current_steps": 725, "total_steps": 1875, "loss": 0.668, "lr": 0.00013485720473218154, "epoch": 1.16, "percentage": 38.67, "elapsed_time": "0:14:59", "remaining_time": "0:23:46"}
+{"current_steps": 730, "total_steps": 1875, "loss": 0.6997, "lr": 0.0001340707751943952, "epoch": 1.168, "percentage": 38.93, "elapsed_time": "0:15:06", "remaining_time": "0:23:41"}
+{"current_steps": 735, "total_steps": 1875, "loss": 0.831, "lr": 0.00013328195445229868, "epoch": 1.176, "percentage": 39.2, "elapsed_time": "0:15:15", "remaining_time": "0:23:39"}
+{"current_steps": 740, "total_steps": 1875, "loss": 0.6378, "lr": 0.00013249079786804765, "epoch": 1.184, "percentage": 39.47, "elapsed_time": "0:15:21", "remaining_time": "0:23:33"}
+{"current_steps": 745, "total_steps": 1875, "loss": 0.6547, "lr": 0.0001316973609677352, "epoch": 1.192, "percentage": 39.73, "elapsed_time": "0:15:26", "remaining_time": "0:23:25"}
+{"current_steps": 750, "total_steps": 1875, "loss": 0.5808, "lr": 0.00013090169943749476, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:15:31", "remaining_time": "0:23:17"}
+{"current_steps": 755, "total_steps": 1875, "loss": 0.5582, "lr": 0.00013010386911959206, "epoch": 1.208, "percentage": 40.27, "elapsed_time": "0:15:37", "remaining_time": "0:23:10"}
+{"current_steps": 760, "total_steps": 1875, "loss": 0.5801, "lr": 0.00012930392600850573, "epoch": 1.216, "percentage": 40.53, "elapsed_time": "0:15:44", "remaining_time": "0:23:05"}
+{"current_steps": 765, "total_steps": 1875, "loss": 0.65, "lr": 0.0001285019262469976, "epoch": 1.224, "percentage": 40.8, "elapsed_time": "0:15:50", "remaining_time": "0:22:59"}
+{"current_steps": 770, "total_steps": 1875, "loss": 0.6627, "lr": 0.00012769792612217224, "epoch": 1.232, "percentage": 41.07, "elapsed_time": "0:15:57", "remaining_time": "0:22:53"}
+{"current_steps": 775, "total_steps": 1875, "loss": 0.5603, "lr": 0.00012689198206152657, "epoch": 1.24, "percentage": 41.33, "elapsed_time": "0:16:03", "remaining_time": "0:22:46"}
+{"current_steps": 780, "total_steps": 1875, "loss": 0.6525, "lr": 0.00012608415062898972, "epoch": 1.248, "percentage": 41.6, "elapsed_time": "0:16:08", "remaining_time": "0:22:38"}
+{"current_steps": 785, "total_steps": 1875, "loss": 0.6731, "lr": 0.00012527448852095295, "epoch": 1.256, "percentage": 41.87, "elapsed_time": "0:16:14", "remaining_time": "0:22:33"}
+{"current_steps": 790, "total_steps": 1875, "loss": 0.6255, "lr": 0.00012446305256229073, "epoch": 1.264, "percentage": 42.13, "elapsed_time": "0:16:21", "remaining_time": "0:22:27"}
+{"current_steps": 795, "total_steps": 1875, "loss": 0.6585, "lr": 0.00012364989970237248, "epoch": 1.272, "percentage": 42.4, "elapsed_time": "0:16:28", "remaining_time": "0:22:22"}
+{"current_steps": 800, "total_steps": 1875, "loss": 0.5996, "lr": 0.00012283508701106557, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "0:16:35", "remaining_time": "0:22:17"}
+{"current_steps": 805, "total_steps": 1875, "loss": 0.6355, "lr": 0.00012201867167473015, "epoch": 1.288, "percentage": 42.93, "elapsed_time": "0:16:44", "remaining_time": "0:22:15"}
+{"current_steps": 810, "total_steps": 1875, "loss": 0.6615, "lr": 0.00012120071099220549, "epoch": 1.296, "percentage": 43.2, "elapsed_time": "0:16:50", "remaining_time": "0:22:08"}
+{"current_steps": 815, "total_steps": 1875, "loss": 0.6096, "lr": 0.0001203812623707885, "epoch": 1.304, "percentage": 43.47, "elapsed_time": "0:16:58", "remaining_time": "0:22:04"}
+{"current_steps": 820, "total_steps": 1875, "loss": 0.5984, "lr": 0.00011956038332220483, "epoch": 1.312, "percentage": 43.73, "elapsed_time": "0:17:05", "remaining_time": "0:22:00"}
+{"current_steps": 825, "total_steps": 1875, "loss": 0.5569, "lr": 0.00011873813145857249, "epoch": 1.32, "percentage": 44.0, "elapsed_time": "0:17:14", "remaining_time": "0:21:56"}
+{"current_steps": 830, "total_steps": 1875, "loss": 0.7088, "lr": 0.00011791456448835825, "epoch": 1.328, "percentage": 44.27, "elapsed_time": "0:17:20", "remaining_time": "0:21:50"}
+{"current_steps": 835, "total_steps": 1875, "loss": 0.6731, "lr": 0.00011708974021232769, "epoch": 1.336, "percentage": 44.53, "elapsed_time": "0:17:26", "remaining_time": "0:21:43"}
+{"current_steps": 840, "total_steps": 1875, "loss": 0.6188, "lr": 0.00011626371651948838, "epoch": 1.3439999999999999, "percentage": 44.8, "elapsed_time": "0:17:32", "remaining_time": "0:21:36"}
+{"current_steps": 845, "total_steps": 1875, "loss": 0.7004, "lr": 0.00011543655138302714, "epoch": 1.3519999999999999, "percentage": 45.07, "elapsed_time": "0:17:37", "remaining_time": "0:21:29"}
+{"current_steps": 850, "total_steps": 1875, "loss": 0.5884, "lr": 0.00011460830285624118, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "0:17:45", "remaining_time": "0:21:25"}
+{"current_steps": 855, "total_steps": 1875, "loss": 0.5739, "lr": 0.0001137790290684638, "epoch": 1.3679999999999999, "percentage": 45.6, "elapsed_time": "0:17:54", "remaining_time": "0:21:22"}
+{"current_steps": 860, "total_steps": 1875, "loss": 0.6435, "lr": 0.00011294878822098469, "epoch": 1.376, "percentage": 45.87, "elapsed_time": "0:17:59", "remaining_time": "0:21:14"}
+{"current_steps": 865, "total_steps": 1875, "loss": 0.6897, "lr": 0.00011211763858296507, "epoch": 1.384, "percentage": 46.13, "elapsed_time": "0:18:06", "remaining_time": "0:21:08"}
+{"current_steps": 870, "total_steps": 1875, "loss": 0.6641, "lr": 0.00011128563848734816, "epoch": 1.392, "percentage": 46.4, "elapsed_time": "0:18:10", "remaining_time": "0:21:00"}
+{"current_steps": 875, "total_steps": 1875, "loss": 0.6273, "lr": 0.00011045284632676536, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:18:16", "remaining_time": "0:20:53"}
+{"current_steps": 880, "total_steps": 1875, "loss": 0.6437, "lr": 0.00010961932054943778, "epoch": 1.408, "percentage": 46.93, "elapsed_time": "0:18:24", "remaining_time": "0:20:49"}
+{"current_steps": 885, "total_steps": 1875, "loss": 0.6345, "lr": 0.00010878511965507434, "epoch": 1.416, "percentage": 47.2, "elapsed_time": "0:18:31", "remaining_time": "0:20:43"}
+{"current_steps": 890, "total_steps": 1875, "loss": 0.5913, "lr": 0.00010795030219076599, "epoch": 1.424, "percentage": 47.47, "elapsed_time": "0:18:39", "remaining_time": "0:20:39"}
+{"current_steps": 895, "total_steps": 1875, "loss": 0.6482, "lr": 0.00010711492674687671, "epoch": 1.432, "percentage": 47.73, "elapsed_time": "0:18:45", "remaining_time": "0:20:32"}
+{"current_steps": 900, "total_steps": 1875, "loss": 0.6165, "lr": 0.00010627905195293135, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "0:18:52", "remaining_time": "0:20:26"}
+{"current_steps": 905, "total_steps": 1875, "loss": 0.634, "lr": 0.00010544273647350092, "epoch": 1.448, "percentage": 48.27, "elapsed_time": "0:18:59", "remaining_time": "0:20:21"}
+{"current_steps": 910, "total_steps": 1875, "loss": 0.6509, "lr": 0.00010460603900408523, "epoch": 1.456, "percentage": 48.53, "elapsed_time": "0:19:04", "remaining_time": "0:20:13"}
+{"current_steps": 915, "total_steps": 1875, "loss": 0.6212, "lr": 0.00010376901826699348, "epoch": 1.464, "percentage": 48.8, "elapsed_time": "0:19:11", "remaining_time": "0:20:07"}
+{"current_steps": 920, "total_steps": 1875, "loss": 0.7305, "lr": 0.00010293173300722285, "epoch": 1.472, "percentage": 49.07, "elapsed_time": "0:19:17", "remaining_time": "0:20:01"}
+{"current_steps": 925, "total_steps": 1875, "loss": 0.6685, "lr": 0.0001020942419883357, "epoch": 1.48, "percentage": 49.33, "elapsed_time": "0:19:23", "remaining_time": "0:19:54"}
+{"current_steps": 930, "total_steps": 1875, "loss": 0.6214, "lr": 0.00010125660398833528, "epoch": 1.488, "percentage": 49.6, "elapsed_time": "0:19:29", "remaining_time": "0:19:48"}
+{"current_steps": 935, "total_steps": 1875, "loss": 0.6035, "lr": 0.0001004188777955404, "epoch": 1.496, "percentage": 49.87, "elapsed_time": "0:19:37", "remaining_time": "0:19:43"}
+{"current_steps": 940, "total_steps": 1875, "loss": 0.5868, "lr": 9.958112220445963e-05, "epoch": 1.504, "percentage": 50.13, "elapsed_time": "0:19:44", "remaining_time": "0:19:37"}
+{"current_steps": 945, "total_steps": 1875, "loss": 0.6003, "lr": 9.874339601166473e-05, "epoch": 1.512, "percentage": 50.4, "elapsed_time": "0:19:50", "remaining_time": "0:19:31"}
+{"current_steps": 950, "total_steps": 1875, "loss": 0.5854, "lr": 9.790575801166432e-05, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "0:19:55", "remaining_time": "0:19:24"}
+{"current_steps": 955, "total_steps": 1875, "loss": 0.5882, "lr": 9.706826699277718e-05, "epoch": 1.528, "percentage": 50.93, "elapsed_time": "0:20:03", "remaining_time": "0:19:19"}
+{"current_steps": 960, "total_steps": 1875, "loss": 0.7187, "lr": 9.623098173300654e-05, "epoch": 1.536, "percentage": 51.2, "elapsed_time": "0:20:08", "remaining_time": "0:19:11"}
+{"current_steps": 965, "total_steps": 1875, "loss": 0.6156, "lr": 9.539396099591476e-05, "epoch": 1.544, "percentage": 51.47, "elapsed_time": "0:20:13", "remaining_time": "0:19:04"}
+{"current_steps": 970, "total_steps": 1875, "loss": 0.6488, "lr": 9.455726352649911e-05, "epoch": 1.552, "percentage": 51.73, "elapsed_time": "0:20:17", "remaining_time": "0:18:56"}
+{"current_steps": 975, "total_steps": 1875, "loss": 0.6601, "lr": 9.372094804706867e-05, "epoch": 1.56, "percentage": 52.0, "elapsed_time": "0:20:24", "remaining_time": "0:18:50"}
+{"current_steps": 980, "total_steps": 1875, "loss": 0.5968, "lr": 9.288507325312335e-05, "epoch": 1.568, "percentage": 52.27, "elapsed_time": "0:20:31", "remaining_time": "0:18:44"}
+{"current_steps": 985, "total_steps": 1875, "loss": 0.7034, "lr": 9.204969780923403e-05, "epoch": 1.576, "percentage": 52.53, "elapsed_time": "0:20:36", "remaining_time": "0:18:37"}
+{"current_steps": 990, "total_steps": 1875, "loss": 0.5973, "lr": 9.121488034492569e-05, "epoch": 1.584, "percentage": 52.8, "elapsed_time": "0:20:41", "remaining_time": "0:18:29"}
+{"current_steps": 995, "total_steps": 1875, "loss": 0.7877, "lr": 9.038067945056227e-05, "epoch": 1.592, "percentage": 53.07, "elapsed_time": "0:20:45", "remaining_time": "0:18:21"}
+{"current_steps": 1000, "total_steps": 1875, "loss": 0.644, "lr": 8.954715367323468e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:20:51", "remaining_time": "0:18:15"}
+{"current_steps": 1005, "total_steps": 1875, "loss": 0.6678, "lr": 8.871436151265184e-05, "epoch": 1.608, "percentage": 53.6, "elapsed_time": "0:20:58", "remaining_time": "0:18:09"}
+{"current_steps": 1010, "total_steps": 1875, "loss": 0.6088, "lr": 8.788236141703498e-05, "epoch": 1.616, "percentage": 53.87, "elapsed_time": "0:21:03", "remaining_time": "0:18:02"}
+{"current_steps": 1015, "total_steps": 1875, "loss": 0.6219, "lr": 8.705121177901532e-05, "epoch": 1.624, "percentage": 54.13, "elapsed_time": "0:21:10", "remaining_time": "0:17:56"}
+{"current_steps": 1020, "total_steps": 1875, "loss": 0.6698, "lr": 8.62209709315362e-05, "epoch": 1.6320000000000001, "percentage": 54.4, "elapsed_time": "0:21:16", "remaining_time": "0:17:49"}
+{"current_steps": 1025, "total_steps": 1875, "loss": 0.6207, "lr": 8.539169714375885e-05, "epoch": 1.6400000000000001, "percentage": 54.67, "elapsed_time": "0:21:23", "remaining_time": "0:17:44"}
+{"current_steps": 1030, "total_steps": 1875, "loss": 0.626, "lr": 8.456344861697289e-05, "epoch": 1.6480000000000001, "percentage": 54.93, "elapsed_time": "0:21:30", "remaining_time": "0:17:39"}
+{"current_steps": 1035, "total_steps": 1875, "loss": 0.6972, "lr": 8.373628348051165e-05, "epoch": 1.6560000000000001, "percentage": 55.2, "elapsed_time": "0:21:36", "remaining_time": "0:17:32"}
+{"current_steps": 1040, "total_steps": 1875, "loss": 0.6282, "lr": 8.291025978767235e-05, "epoch": 1.6640000000000001, "percentage": 55.47, "elapsed_time": "0:21:41", "remaining_time": "0:17:25"}
+{"current_steps": 1045, "total_steps": 1875, "loss": 0.6219, "lr": 8.208543551164178e-05, "epoch": 1.6720000000000002, "percentage": 55.73, "elapsed_time": "0:21:47", "remaining_time": "0:17:18"}
+{"current_steps": 1050, "total_steps": 1875, "loss": 0.622, "lr": 8.126186854142752e-05, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "0:21:54", "remaining_time": "0:17:12"}
+{"current_steps": 1055, "total_steps": 1875, "loss": 0.5801, "lr": 8.04396166777952e-05, "epoch": 1.688, "percentage": 56.27, "elapsed_time": "0:22:01", "remaining_time": "0:17:06"}
+{"current_steps": 1060, "total_steps": 1875, "loss": 0.598, "lr": 7.961873762921153e-05, "epoch": 1.696, "percentage": 56.53, "elapsed_time": "0:22:07", "remaining_time": "0:17:00"}
+{"current_steps": 1065, "total_steps": 1875, "loss": 0.699, "lr": 7.879928900779456e-05, "epoch": 1.704, "percentage": 56.8, "elapsed_time": "0:22:12", "remaining_time": "0:16:53"}
+{"current_steps": 1070, "total_steps": 1875, "loss": 0.5882, "lr": 7.798132832526986e-05, "epoch": 1.712, "percentage": 57.07, "elapsed_time": "0:22:17", "remaining_time": "0:16:46"}
+{"current_steps": 1075, "total_steps": 1875, "loss": 0.5321, "lr": 7.716491298893442e-05, "epoch": 1.72, "percentage": 57.33, "elapsed_time": "0:22:25", "remaining_time": "0:16:41"}
+{"current_steps": 1080, "total_steps": 1875, "loss": 0.6647, "lr": 7.635010029762756e-05, "epoch": 1.728, "percentage": 57.6, "elapsed_time": "0:22:33", "remaining_time": "0:16:36"}
+{"current_steps": 1085, "total_steps": 1875, "loss": 0.628, "lr": 7.553694743770928e-05, "epoch": 1.736, "percentage": 57.87, "elapsed_time": "0:22:40", "remaining_time": "0:16:30"}
+{"current_steps": 1090, "total_steps": 1875, "loss": 0.6262, "lr": 7.472551147904708e-05, "epoch": 1.744, "percentage": 58.13, "elapsed_time": "0:22:46", "remaining_time": "0:16:24"}
+{"current_steps": 1095, "total_steps": 1875, "loss": 0.6131, "lr": 7.391584937101033e-05, "epoch": 1.752, "percentage": 58.4, "elapsed_time": "0:22:53", "remaining_time": "0:16:18"}
+{"current_steps": 1100, "total_steps": 1875, "loss": 0.6494, "lr": 7.310801793847344e-05, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "0:22:58", "remaining_time": "0:16:11"}
+{"current_steps": 1105, "total_steps": 1875, "loss": 0.5514, "lr": 7.230207387782776e-05, "epoch": 1.768, "percentage": 58.93, "elapsed_time": "0:23:06", "remaining_time": "0:16:06"}
+{"current_steps": 1110, "total_steps": 1875, "loss": 0.5823, "lr": 7.149807375300239e-05, "epoch": 1.776, "percentage": 59.2, "elapsed_time": "0:23:14", "remaining_time": "0:16:01"}
+{"current_steps": 1115, "total_steps": 1875, "loss": 0.7207, "lr": 7.069607399149428e-05, "epoch": 1.784, "percentage": 59.47, "elapsed_time": "0:23:20", "remaining_time": "0:15:54"}
+{"current_steps": 1120, "total_steps": 1875, "loss": 0.7006, "lr": 6.989613088040796e-05, "epoch": 1.792, "percentage": 59.73, "elapsed_time": "0:23:26", "remaining_time": "0:15:48"}
+{"current_steps": 1125, "total_steps": 1875, "loss": 0.6222, "lr": 6.909830056250527e-05, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "0:23:32", "remaining_time": "0:15:41"}
+{"current_steps": 1130, "total_steps": 1875, "loss": 0.6569, "lr": 6.830263903226483e-05, "epoch": 1.808, "percentage": 60.27, "elapsed_time": "0:23:37", "remaining_time": "0:15:34"}
+{"current_steps": 1135, "total_steps": 1875, "loss": 0.543, "lr": 6.750920213195238e-05, "epoch": 1.8159999999999998, "percentage": 60.53, "elapsed_time": "0:23:45", "remaining_time": "0:15:29"}
+{"current_steps": 1140, "total_steps": 1875, "loss": 0.6334, "lr": 6.671804554770135e-05, "epoch": 1.8239999999999998, "percentage": 60.8, "elapsed_time": "0:23:51", "remaining_time": "0:15:23"}
+{"current_steps": 1145, "total_steps": 1875, "loss": 0.6701, "lr": 6.592922480560483e-05, "epoch": 1.8319999999999999, "percentage": 61.07, "elapsed_time": "0:24:00", "remaining_time": "0:15:18"}
+{"current_steps": 1150, "total_steps": 1875, "loss": 0.6216, "lr": 6.51427952678185e-05, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "0:24:07", "remaining_time": "0:15:12"}
+{"current_steps": 1155, "total_steps": 1875, "loss": 0.5877, "lr": 6.435881212867493e-05, "epoch": 1.8479999999999999, "percentage": 61.6, "elapsed_time": "0:24:14", "remaining_time": "0:15:06"}
+{"current_steps": 1160, "total_steps": 1875, "loss": 0.6256, "lr": 6.357733041081018e-05, "epoch": 1.8559999999999999, "percentage": 61.87, "elapsed_time": "0:24:21", "remaining_time": "0:15:00"}
+{"current_steps": 1165, "total_steps": 1875, "loss": 0.7062, "lr": 6.27984049613019e-05, "epoch": 1.8639999999999999, "percentage": 62.13, "elapsed_time": "0:24:26", "remaining_time": "0:14:53"}
+{"current_steps": 1170, "total_steps": 1875, "loss": 0.6304, "lr": 6.20220904478199e-05, "epoch": 1.8719999999999999, "percentage": 62.4, "elapsed_time": "0:24:32", "remaining_time": "0:14:47"}
+{"current_steps": 1175, "total_steps": 1875, "loss": 0.7695, "lr": 6.12484413547897e-05, "epoch": 1.88, "percentage": 62.67, "elapsed_time": "0:24:36", "remaining_time": "0:14:39"}
+{"current_steps": 1180, "total_steps": 1875, "loss": 0.5723, "lr": 6.047751197956838e-05, "epoch": 1.888, "percentage": 62.93, "elapsed_time": "0:24:43", "remaining_time": "0:14:33"}
+{"current_steps": 1185, "total_steps": 1875, "loss": 0.6847, "lr": 5.9709356428633746e-05, "epoch": 1.896, "percentage": 63.2, "elapsed_time": "0:24:48", "remaining_time": "0:14:26"}
+{"current_steps": 1190, "total_steps": 1875, "loss": 0.6618, "lr": 5.8944028613787206e-05, "epoch": 1.904, "percentage": 63.47, "elapsed_time": "0:24:55", "remaining_time": "0:14:20"}
+{"current_steps": 1195, "total_steps": 1875, "loss": 0.6275, "lr": 5.818158224836987e-05, "epoch": 1.912, "percentage": 63.73, "elapsed_time": "0:25:01", "remaining_time": "0:14:14"}
+{"current_steps": 1200, "total_steps": 1875, "loss": 0.5617, "lr": 5.7422070843492734e-05, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "0:25:09", "remaining_time": "0:14:08"}
+{"current_steps": 1205, "total_steps": 1875, "loss": 0.6278, "lr": 5.666554770428129e-05, "epoch": 1.928, "percentage": 64.27, "elapsed_time": "0:25:15", "remaining_time": "0:14:02"}
+{"current_steps": 1210, "total_steps": 1875, "loss": 0.6713, "lr": 5.591206592613416e-05, "epoch": 1.936, "percentage": 64.53, "elapsed_time": "0:25:20", "remaining_time": "0:13:55"}
+{"current_steps": 1215, "total_steps": 1875, "loss": 0.6113, "lr": 5.5161678390996796e-05, "epoch": 1.944, "percentage": 64.8, "elapsed_time": "0:25:25", "remaining_time": "0:13:48"}
+{"current_steps": 1220, "total_steps": 1875, "loss": 0.5587, "lr": 5.441443776365003e-05, "epoch": 1.952, "percentage": 65.07, "elapsed_time": "0:25:31", "remaining_time": "0:13:42"}
+{"current_steps": 1225, "total_steps": 1875, "loss": 0.5601, "lr": 5.3670396488013854e-05, "epoch": 1.96, "percentage": 65.33, "elapsed_time": "0:25:38", "remaining_time": "0:13:36"}
+{"current_steps": 1230, "total_steps": 1875, "loss": 0.5941, "lr": 5.292960678346675e-05, "epoch": 1.968, "percentage": 65.6, "elapsed_time": "0:25:43", "remaining_time": "0:13:29"}
+{"current_steps": 1235, "total_steps": 1875, "loss": 0.6285, "lr": 5.2192120641180786e-05, "epoch": 1.976, "percentage": 65.87, "elapsed_time": "0:25:49", "remaining_time": "0:13:22"}
+{"current_steps": 1240, "total_steps": 1875, "loss": 0.6516, "lr": 5.145798982047261e-05, "epoch": 1.984, "percentage": 66.13, "elapsed_time": "0:25:55", "remaining_time": "0:13:16"}
+{"current_steps": 1245, "total_steps": 1875, "loss": 0.5904, "lr": 5.072726584517086e-05, "epoch": 1.992, "percentage": 66.4, "elapsed_time": "0:26:05", "remaining_time": "0:13:12"}
+{"current_steps": 1250, "total_steps": 1875, "loss": 0.619, "lr": 5.000000000000002e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:26:11", "remaining_time": "0:13:05"}
+{"current_steps": 1255, "total_steps": 1875, "loss": 0.6058, "lr": 4.927624332698109e-05, "epoch": 2.008, "percentage": 66.93, "elapsed_time": "0:26:15", "remaining_time": "0:12:58"}
+{"current_steps": 1260, "total_steps": 1875, "loss": 0.6248, "lr": 4.8556046621849346e-05, "epoch": 2.016, "percentage": 67.2, "elapsed_time": "0:26:20", "remaining_time": "0:12:51"}
+{"current_steps": 1265, "total_steps": 1875, "loss": 0.5247, "lr": 4.783946043048923e-05, "epoch": 2.024, "percentage": 67.47, "elapsed_time": "0:26:27", "remaining_time": "0:12:45"}
+{"current_steps": 1270, "total_steps": 1875, "loss": 0.5439, "lr": 4.712653504538683e-05, "epoch": 2.032, "percentage": 67.73, "elapsed_time": "0:26:34", "remaining_time": "0:12:39"}
+{"current_steps": 1275, "total_steps": 1875, "loss": 0.4491, "lr": 4.6417320502100316e-05, "epoch": 2.04, "percentage": 68.0, "elapsed_time": "0:26:40", "remaining_time": "0:12:33"}
+{"current_steps": 1280, "total_steps": 1875, "loss": 0.52, "lr": 4.5711866575748276e-05, "epoch": 2.048, "percentage": 68.27, "elapsed_time": "0:26:48", "remaining_time": "0:12:27"}
+{"current_steps": 1285, "total_steps": 1875, "loss": 0.5259, "lr": 4.501022277751602e-05, "epoch": 2.056, "percentage": 68.53, "elapsed_time": "0:26:55", "remaining_time": "0:12:21"}
+{"current_steps": 1290, "total_steps": 1875, "loss": 0.5025, "lr": 4.431243835118124e-05, "epoch": 2.064, "percentage": 68.8, "elapsed_time": "0:27:02", "remaining_time": "0:12:15"}
+{"current_steps": 1295, "total_steps": 1875, "loss": 0.4772, "lr": 4.361856226965733e-05, "epoch": 2.072, "percentage": 69.07, "elapsed_time": "0:27:08", "remaining_time": "0:12:09"}
+{"current_steps": 1300, "total_steps": 1875, "loss": 0.5945, "lr": 4.2928643231556844e-05, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "0:27:14", "remaining_time": "0:12:02"}
+{"current_steps": 1305, "total_steps": 1875, "loss": 0.4813, "lr": 4.224272965777326e-05, "epoch": 2.088, "percentage": 69.6, "elapsed_time": "0:27:22", "remaining_time": "0:11:57"}
+{"current_steps": 1310, "total_steps": 1875, "loss": 0.5315, "lr": 4.15608696880828e-05, "epoch": 2.096, "percentage": 69.87, "elapsed_time": "0:27:28", "remaining_time": "0:11:51"}
+{"current_steps": 1315, "total_steps": 1875, "loss": 0.5591, "lr": 4.08831111777658e-05, "epoch": 2.104, "percentage": 70.13, "elapsed_time": "0:27:34", "remaining_time": "0:11:44"}
+{"current_steps": 1320, "total_steps": 1875, "loss": 0.605, "lr": 4.020950169424815e-05, "epoch": 2.112, "percentage": 70.4, "elapsed_time": "0:27:40", "remaining_time": "0:11:37"}
+{"current_steps": 1325, "total_steps": 1875, "loss": 0.4955, "lr": 3.954008851376252e-05, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "0:27:47", "remaining_time": "0:11:32"}
+{"current_steps": 1330, "total_steps": 1875, "loss": 0.5757, "lr": 3.887491861803085e-05, "epoch": 2.128, "percentage": 70.93, "elapsed_time": "0:27:52", "remaining_time": "0:11:25"}
+{"current_steps": 1335, "total_steps": 1875, "loss": 0.5313, "lr": 3.821403869096658e-05, "epoch": 2.136, "percentage": 71.2, "elapsed_time": "0:27:59", "remaining_time": "0:11:19"}
+{"current_steps": 1340, "total_steps": 1875, "loss": 0.5904, "lr": 3.755749511539845e-05, "epoch": 2.144, "percentage": 71.47, "elapsed_time": "0:28:06", "remaining_time": "0:11:13"}
+{"current_steps": 1345, "total_steps": 1875, "loss": 0.4679, "lr": 3.690533396981504e-05, "epoch": 2.152, "percentage": 71.73, "elapsed_time": "0:28:12", "remaining_time": "0:11:06"}
+{"current_steps": 1350, "total_steps": 1875, "loss": 0.5235, "lr": 3.6257601025131026e-05, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "0:28:17", "remaining_time": "0:10:59"}
+{"current_steps": 1355, "total_steps": 1875, "loss": 0.5797, "lr": 3.561434174147463e-05, "epoch": 2.168, "percentage": 72.27, "elapsed_time": "0:28:21", "remaining_time": "0:10:52"}
+{"current_steps": 1360, "total_steps": 1875, "loss": 0.5772, "lr": 3.497560126499709e-05, "epoch": 2.176, "percentage": 72.53, "elapsed_time": "0:28:26", "remaining_time": "0:10:46"}
+{"current_steps": 1365, "total_steps": 1875, "loss": 0.5316, "lr": 3.4341424424704375e-05, "epoch": 2.184, "percentage": 72.8, "elapsed_time": "0:28:32", "remaining_time": "0:10:39"}
+{"current_steps": 1370, "total_steps": 1875, "loss": 0.5646, "lr": 3.371185572931048e-05, "epoch": 2.192, "percentage": 73.07, "elapsed_time": "0:28:38", "remaining_time": "0:10:33"}
+{"current_steps": 1375, "total_steps": 1875, "loss": 0.5431, "lr": 3.308693936411421e-05, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:28:43", "remaining_time": "0:10:26"}
+{"current_steps": 1380, "total_steps": 1875, "loss": 0.5403, "lr": 3.246671918789755e-05, "epoch": 2.208, "percentage": 73.6, "elapsed_time": "0:28:48", "remaining_time": "0:10:20"}
+{"current_steps": 1385, "total_steps": 1875, "loss": 0.5329, "lr": 3.1851238729848034e-05, "epoch": 2.216, "percentage": 73.87, "elapsed_time": "0:28:53", "remaining_time": "0:10:13"}
+{"current_steps": 1390, "total_steps": 1875, "loss": 0.5696, "lr": 3.124054118650327e-05, "epoch": 2.224, "percentage": 74.13, "elapsed_time": "0:29:01", "remaining_time": "0:10:07"}
+{"current_steps": 1395, "total_steps": 1875, "loss": 0.59, "lr": 3.063466941871952e-05, "epoch": 2.232, "percentage": 74.4, "elapsed_time": "0:29:07", "remaining_time": "0:10:01"}
+{"current_steps": 1400, "total_steps": 1875, "loss": 0.5116, "lr": 3.0033665948663448e-05, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "0:29:14", "remaining_time": "0:09:55"}
+{"current_steps": 1405, "total_steps": 1875, "loss": 0.5783, "lr": 2.9437572956827964e-05, "epoch": 2.248, "percentage": 74.93, "elapsed_time": "0:29:21", "remaining_time": "0:09:49"}
+{"current_steps": 1410, "total_steps": 1875, "loss": 0.6259, "lr": 2.8846432279071467e-05, "epoch": 2.2560000000000002, "percentage": 75.2, "elapsed_time": "0:29:27", "remaining_time": "0:09:42"}
+{"current_steps": 1415, "total_steps": 1875, "loss": 0.5759, "lr": 2.826028540368215e-05, "epoch": 2.2640000000000002, "percentage": 75.47, "elapsed_time": "0:29:35", "remaining_time": "0:09:37"}
+{"current_steps": 1420, "total_steps": 1875, "loss": 0.497, "lr": 2.7679173468465812e-05, "epoch": 2.2720000000000002, "percentage": 75.73, "elapsed_time": "0:29:41", "remaining_time": "0:09:30"}
+{"current_steps": 1425, "total_steps": 1875, "loss": 0.619, "lr": 2.7103137257858868e-05, "epoch": 2.2800000000000002, "percentage": 76.0, "elapsed_time": "0:29:47", "remaining_time": "0:09:24"}
+{"current_steps": 1430, "total_steps": 1875, "loss": 0.5858, "lr": 2.6532217200065858e-05, "epoch": 2.288, "percentage": 76.27, "elapsed_time": "0:29:52", "remaining_time": "0:09:17"}
+{"current_steps": 1435, "total_steps": 1875, "loss": 0.6291, "lr": 2.5966453364222186e-05, "epoch": 2.296, "percentage": 76.53, "elapsed_time": "0:29:58", "remaining_time": "0:09:11"}
+{"current_steps": 1440, "total_steps": 1875, "loss": 0.6418, "lr": 2.540588545758179e-05, "epoch": 2.304, "percentage": 76.8, "elapsed_time": "0:30:04", "remaining_time": "0:09:05"}
+{"current_steps": 1445, "total_steps": 1875, "loss": 0.5483, "lr": 2.48505528227304e-05, "epoch": 2.312, "percentage": 77.07, "elapsed_time": "0:30:11", "remaining_time": "0:08:59"}
+{"current_steps": 1450, "total_steps": 1875, "loss": 0.6071, "lr": 2.4300494434824373e-05, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "0:30:18", "remaining_time": "0:08:53"}
+{"current_steps": 1455, "total_steps": 1875, "loss": 0.5099, "lr": 2.37557488988552e-05, "epoch": 2.328, "percentage": 77.6, "elapsed_time": "0:30:25", "remaining_time": "0:08:47"}
+{"current_steps": 1460, "total_steps": 1875, "loss": 0.5186, "lr": 2.321635444694028e-05, "epoch": 2.336, "percentage": 77.87, "elapsed_time": "0:30:30", "remaining_time": "0:08:40"}
+{"current_steps": 1465, "total_steps": 1875, "loss": 0.5043, "lr": 2.2682348935639274e-05, "epoch": 2.344, "percentage": 78.13, "elapsed_time": "0:30:36", "remaining_time": "0:08:33"}
+{"current_steps": 1470, "total_steps": 1875, "loss": 0.61, "lr": 2.2153769843297667e-05, "epoch": 2.352, "percentage": 78.4, "elapsed_time": "0:30:42", "remaining_time": "0:08:27"}
+{"current_steps": 1475, "total_steps": 1875, "loss": 0.5987, "lr": 2.163065426741603e-05, "epoch": 2.36, "percentage": 78.67, "elapsed_time": "0:30:50", "remaining_time": "0:08:21"}
+{"current_steps": 1480, "total_steps": 1875, "loss": 0.5212, "lr": 2.1113038922046602e-05, "epoch": 2.368, "percentage": 78.93, "elapsed_time": "0:30:57", "remaining_time": "0:08:15"}
+{"current_steps": 1485, "total_steps": 1875, "loss": 0.4796, "lr": 2.0600960135216462e-05, "epoch": 2.376, "percentage": 79.2, "elapsed_time": "0:31:04", "remaining_time": "0:08:09"}
+{"current_steps": 1490, "total_steps": 1875, "loss": 0.4844, "lr": 2.009445384637805e-05, "epoch": 2.384, "percentage": 79.47, "elapsed_time": "0:31:11", "remaining_time": "0:08:03"}
+{"current_steps": 1495, "total_steps": 1875, "loss": 0.5085, "lr": 1.9593555603886538e-05, "epoch": 2.392, "percentage": 79.73, "elapsed_time": "0:31:16", "remaining_time": "0:07:57"}
+{"current_steps": 1500, "total_steps": 1875, "loss": 0.4839, "lr": 1.9098300562505266e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:31:23", "remaining_time": "0:07:50"}
+{"current_steps": 1505, "total_steps": 1875, "loss": 0.5715, "lr": 1.8608723480938206e-05, "epoch": 2.408, "percentage": 80.27, "elapsed_time": "0:31:32", "remaining_time": "0:07:45"}
+{"current_steps": 1510, "total_steps": 1875, "loss": 0.5266, "lr": 1.812485871939056e-05, "epoch": 2.416, "percentage": 80.53, "elapsed_time": "0:31:36", "remaining_time": "0:07:38"}
+{"current_steps": 1515, "total_steps": 1875, "loss": 0.5422, "lr": 1.7646740237157256e-05, "epoch": 2.424, "percentage": 80.8, "elapsed_time": "0:31:43", "remaining_time": "0:07:32"}
+{"current_steps": 1520, "total_steps": 1875, "loss": 0.5553, "lr": 1.7174401590239587e-05, "epoch": 2.432, "percentage": 81.07, "elapsed_time": "0:31:49", "remaining_time": "0:07:25"}
+{"current_steps": 1525, "total_steps": 1875, "loss": 0.5765, "lr": 1.6707875928990058e-05, "epoch": 2.44, "percentage": 81.33, "elapsed_time": "0:31:57", "remaining_time": "0:07:20"}
+{"current_steps": 1530, "total_steps": 1875, "loss": 0.549, "lr": 1.6247195995785837e-05, "epoch": 2.448, "percentage": 81.6, "elapsed_time": "0:32:03", "remaining_time": "0:07:13"}
+{"current_steps": 1535, "total_steps": 1875, "loss": 0.4876, "lr": 1.579239412273078e-05, "epoch": 2.456, "percentage": 81.87, "elapsed_time": "0:32:08", "remaining_time": "0:07:07"}
+{"current_steps": 1540, "total_steps": 1875, "loss": 0.5546, "lr": 1.5343502229386207e-05, "epoch": 2.464, "percentage": 82.13, "elapsed_time": "0:32:13", "remaining_time": "0:07:00"}
+{"current_steps": 1545, "total_steps": 1875, "loss": 0.5356, "lr": 1.4900551820530828e-05, "epoch": 2.472, "percentage": 82.4, "elapsed_time": "0:32:18", "remaining_time": "0:06:54"}
+{"current_steps": 1550, "total_steps": 1875, "loss": 0.5142, "lr": 1.4463573983949341e-05, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "0:32:25", "remaining_time": "0:06:47"}
+{"current_steps": 1555, "total_steps": 1875, "loss": 0.6054, "lr": 1.40325993882509e-05, "epoch": 2.488, "percentage": 82.93, "elapsed_time": "0:32:29", "remaining_time": "0:06:41"}
+{"current_steps": 1560, "total_steps": 1875, "loss": 0.5294, "lr": 1.3607658280716473e-05, "epoch": 2.496, "percentage": 83.2, "elapsed_time": "0:32:35", "remaining_time": "0:06:34"}
+{"current_steps": 1565, "total_steps": 1875, "loss": 0.5294, "lr": 1.3188780485176088e-05, "epoch": 2.504, "percentage": 83.47, "elapsed_time": "0:32:40", "remaining_time": "0:06:28"}
+{"current_steps": 1570, "total_steps": 1875, "loss": 0.4905, "lr": 1.2775995399915631e-05, "epoch": 2.512, "percentage": 83.73, "elapsed_time": "0:32:47", "remaining_time": "0:06:22"}
+{"current_steps": 1575, "total_steps": 1875, "loss": 0.5186, "lr": 1.2369331995613665e-05, "epoch": 2.52, "percentage": 84.0, "elapsed_time": "0:32:54", "remaining_time": "0:06:16"}
+{"current_steps": 1580, "total_steps": 1875, "loss": 0.4909, "lr": 1.196881881330798e-05, "epoch": 2.528, "percentage": 84.27, "elapsed_time": "0:33:00", "remaining_time": "0:06:09"}
+{"current_steps": 1585, "total_steps": 1875, "loss": 0.5303, "lr": 1.1574483962392767e-05, "epoch": 2.536, "percentage": 84.53, "elapsed_time": "0:33:05", "remaining_time": "0:06:03"}
+{"current_steps": 1590, "total_steps": 1875, "loss": 0.5169, "lr": 1.1186355118645554e-05, "epoch": 2.544, "percentage": 84.8, "elapsed_time": "0:33:11", "remaining_time": "0:05:57"}
+{"current_steps": 1595, "total_steps": 1875, "loss": 0.5339, "lr": 1.0804459522284926e-05, "epoch": 2.552, "percentage": 85.07, "elapsed_time": "0:33:19", "remaining_time": "0:05:50"}
+{"current_steps": 1600, "total_steps": 1875, "loss": 0.5283, "lr": 1.042882397605871e-05, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "0:33:23", "remaining_time": "0:05:44"}
+{"current_steps": 1605, "total_steps": 1875, "loss": 0.5576, "lr": 1.0059474843362892e-05, "epoch": 2.568, "percentage": 85.6, "elapsed_time": "0:33:30", "remaining_time": "0:05:38"}
+{"current_steps": 1610, "total_steps": 1875, "loss": 0.5136, "lr": 9.696438046391288e-06, "epoch": 2.576, "percentage": 85.87, "elapsed_time": "0:33:36", "remaining_time": "0:05:31"}
+{"current_steps": 1615, "total_steps": 1875, "loss": 0.5885, "lr": 9.339739064316233e-06, "epoch": 2.584, "percentage": 86.13, "elapsed_time": "0:33:43", "remaining_time": "0:05:25"}
+{"current_steps": 1620, "total_steps": 1875, "loss": 0.5, "lr": 8.989402931500434e-06, "epoch": 2.592, "percentage": 86.4, "elapsed_time": "0:33:51", "remaining_time": "0:05:19"}
+{"current_steps": 1625, "total_steps": 1875, "loss": 0.5325, "lr": 8.645454235739903e-06, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "0:33:58", "remaining_time": "0:05:13"}
+{"current_steps": 1630, "total_steps": 1875, "loss": 0.5772, "lr": 8.307917116538378e-06, "epoch": 2.608, "percentage": 86.93, "elapsed_time": "0:34:04", "remaining_time": "0:05:07"}
+{"current_steps": 1635, "total_steps": 1875, "loss": 0.5736, "lr": 7.976815263412963e-06, "epoch": 2.616, "percentage": 87.2, "elapsed_time": "0:34:11", "remaining_time": "0:05:01"}
+{"current_steps": 1640, "total_steps": 1875, "loss": 0.5199, "lr": 7.652171914231776e-06, "epoch": 2.624, "percentage": 87.47, "elapsed_time": "0:34:18", "remaining_time": "0:04:54"}
+{"current_steps": 1645, "total_steps": 1875, "loss": 0.5753, "lr": 7.3340098535827905e-06, "epoch": 2.632, "percentage": 87.73, "elapsed_time": "0:34:24", "remaining_time": "0:04:48"}
+{"current_steps": 1650, "total_steps": 1875, "loss": 0.5424, "lr": 7.022351411174866e-06, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "0:34:29", "remaining_time": "0:04:42"}
+{"current_steps": 1655, "total_steps": 1875, "loss": 0.5555, "lr": 6.717218460270536e-06, "epoch": 2.648, "percentage": 88.27, "elapsed_time": "0:34:37", "remaining_time": "0:04:36"}
+{"current_steps": 1660, "total_steps": 1875, "loss": 0.4936, "lr": 6.418632416150927e-06, "epoch": 2.656, "percentage": 88.53, "elapsed_time": "0:34:44", "remaining_time": "0:04:29"}
+{"current_steps": 1665, "total_steps": 1875, "loss": 0.6291, "lr": 6.126614234612593e-06, "epoch": 2.664, "percentage": 88.8, "elapsed_time": "0:34:50", "remaining_time": "0:04:23"}
+{"current_steps": 1670, "total_steps": 1875, "loss": 0.5197, "lr": 5.8411844104969916e-06, "epoch": 2.672, "percentage": 89.07, "elapsed_time": "0:34:55", "remaining_time": "0:04:17"}
+{"current_steps": 1675, "total_steps": 1875, "loss": 0.5398, "lr": 5.562362976251901e-06, "epoch": 2.68, "percentage": 89.33, "elapsed_time": "0:35:02", "remaining_time": "0:04:11"}
+{"current_steps": 1680, "total_steps": 1875, "loss": 0.6059, "lr": 5.290169500525577e-06, "epoch": 2.6879999999999997, "percentage": 89.6, "elapsed_time": "0:35:08", "remaining_time": "0:04:04"}
+{"current_steps": 1685, "total_steps": 1875, "loss": 0.531, "lr": 5.024623086793323e-06, "epoch": 2.6959999999999997, "percentage": 89.87, "elapsed_time": "0:35:14", "remaining_time": "0:03:58"}
+{"current_steps": 1690, "total_steps": 1875, "loss": 0.6054, "lr": 4.765742372016735e-06, "epoch": 2.7039999999999997, "percentage": 90.13, "elapsed_time": "0:35:19", "remaining_time": "0:03:51"}
+{"current_steps": 1695, "total_steps": 1875, "loss": 0.5173, "lr": 4.513545525335705e-06, "epoch": 2.7119999999999997, "percentage": 90.4, "elapsed_time": "0:35:25", "remaining_time": "0:03:45"}
+{"current_steps": 1700, "total_steps": 1875, "loss": 0.4944, "lr": 4.268050246793276e-06, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "0:35:31", "remaining_time": "0:03:39"}
+{"current_steps": 1705, "total_steps": 1875, "loss": 0.5183, "lr": 4.029273766093333e-06, "epoch": 2.7279999999999998, "percentage": 90.93, "elapsed_time": "0:35:38", "remaining_time": "0:03:33"}
+{"current_steps": 1710, "total_steps": 1875, "loss": 0.668, "lr": 3.797232841391407e-06, "epoch": 2.7359999999999998, "percentage": 91.2, "elapsed_time": "0:35:44", "remaining_time": "0:03:26"}
+{"current_steps": 1715, "total_steps": 1875, "loss": 0.5068, "lr": 3.5719437581185454e-06, "epoch": 2.7439999999999998, "percentage": 91.47, "elapsed_time": "0:35:50", "remaining_time": "0:03:20"}
+{"current_steps": 1720, "total_steps": 1875, "loss": 0.5823, "lr": 3.3534223278382405e-06, "epoch": 2.752, "percentage": 91.73, "elapsed_time": "0:35:57", "remaining_time": "0:03:14"}
+{"current_steps": 1725, "total_steps": 1875, "loss": 0.6111, "lr": 3.1416838871368924e-06, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "0:36:02", "remaining_time": "0:03:08"}
+{"current_steps": 1730, "total_steps": 1875, "loss": 0.5231, "lr": 2.936743296547273e-06, "epoch": 2.768, "percentage": 92.27, "elapsed_time": "0:36:07", "remaining_time": "0:03:01"}
+{"current_steps": 1735, "total_steps": 1875, "loss": 0.5236, "lr": 2.738614939505646e-06, "epoch": 2.776, "percentage": 92.53, "elapsed_time": "0:36:14", "remaining_time": "0:02:55"}
+{"current_steps": 1740, "total_steps": 1875, "loss": 0.5657, "lr": 2.5473127213422763e-06, "epoch": 2.784, "percentage": 92.8, "elapsed_time": "0:36:23", "remaining_time": "0:02:49"}
+{"current_steps": 1745, "total_steps": 1875, "loss": 0.5518, "lr": 2.3628500683055222e-06, "epoch": 2.792, "percentage": 93.07, "elapsed_time": "0:36:28", "remaining_time": "0:02:43"}
+{"current_steps": 1750, "total_steps": 1875, "loss": 0.4908, "lr": 2.1852399266194314e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:36:34", "remaining_time": "0:02:36"}
+{"current_steps": 1755, "total_steps": 1875, "loss": 0.5459, "lr": 2.014494761575314e-06, "epoch": 2.808, "percentage": 93.6, "elapsed_time": "0:36:43", "remaining_time": "0:02:30"}
+{"current_steps": 1760, "total_steps": 1875, "loss": 0.5208, "lr": 1.8506265566567094e-06, "epoch": 2.816, "percentage": 93.87, "elapsed_time": "0:36:50", "remaining_time": "0:02:24"}
+{"current_steps": 1765, "total_steps": 1875, "loss": 0.5824, "lr": 1.6936468126984572e-06, "epoch": 2.824, "percentage": 94.13, "elapsed_time": "0:36:56", "remaining_time": "0:02:18"}
+{"current_steps": 1770, "total_steps": 1875, "loss": 0.5512, "lr": 1.543566547079467e-06, "epoch": 2.832, "percentage": 94.4, "elapsed_time": "0:37:05", "remaining_time": "0:02:12"}
+{"current_steps": 1775, "total_steps": 1875, "loss": 0.6327, "lr": 1.400396292949513e-06, "epoch": 2.84, "percentage": 94.67, "elapsed_time": "0:37:12", "remaining_time": "0:02:05"}
+{"current_steps": 1780, "total_steps": 1875, "loss": 0.5292, "lr": 1.26414609848996e-06, "epoch": 2.848, "percentage": 94.93, "elapsed_time": "0:37:20", "remaining_time": "0:01:59"}
+{"current_steps": 1785, "total_steps": 1875, "loss": 0.5692, "lr": 1.134825526208605e-06, "epoch": 2.856, "percentage": 95.2, "elapsed_time": "0:37:26", "remaining_time": "0:01:53"}
+{"current_steps": 1790, "total_steps": 1875, "loss": 0.5532, "lr": 1.0124436522684243e-06, "epoch": 2.864, "percentage": 95.47, "elapsed_time": "0:37:33", "remaining_time": "0:01:47"}
+{"current_steps": 1795, "total_steps": 1875, "loss": 0.5314, "lr": 8.970090658507291e-07, "epoch": 2.872, "percentage": 95.73, "elapsed_time": "0:37:38", "remaining_time": "0:01:40"}
+{"current_steps": 1800, "total_steps": 1875, "loss": 0.524, "lr": 7.885298685522235e-07, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "0:37:45", "remaining_time": "0:01:34"}
+{"current_steps": 1805, "total_steps": 1875, "loss": 0.5227, "lr": 6.870136738164612e-07, "epoch": 2.888, "percentage": 96.27, "elapsed_time": "0:37:52", "remaining_time": "0:01:28"}
+{"current_steps": 1810, "total_steps": 1875, "loss": 0.5993, "lr": 5.924676063995382e-07, "epoch": 2.896, "percentage": 96.53, "elapsed_time": "0:37:58", "remaining_time": "0:01:21"}
+{"current_steps": 1815, "total_steps": 1875, "loss": 0.5618, "lr": 5.048983018699827e-07, "epoch": 2.904, "percentage": 96.8, "elapsed_time": "0:38:06", "remaining_time": "0:01:15"}
+{"current_steps": 1820, "total_steps": 1875, "loss": 0.5504, "lr": 4.2431190614309335e-07, "epoch": 2.912, "percentage": 97.07, "elapsed_time": "0:38:12", "remaining_time": "0:01:09"}
+{"current_steps": 1825, "total_steps": 1875, "loss": 0.5147, "lr": 3.50714075049563e-07, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "0:38:19", "remaining_time": "0:01:02"}
+{"current_steps": 1830, "total_steps": 1875, "loss": 0.5564, "lr": 2.841099739386066e-07, "epoch": 2.928, "percentage": 97.6, "elapsed_time": "0:38:26", "remaining_time": "0:00:56"}
+{"current_steps": 1835, "total_steps": 1875, "loss": 0.5188, "lr": 2.2450427731534053e-07, "epoch": 2.936, "percentage": 97.87, "elapsed_time": "0:38:34", "remaining_time": "0:00:50"}
+{"current_steps": 1840, "total_steps": 1875, "loss": 0.5438, "lr": 1.7190116851280026e-07, "epoch": 2.944, "percentage": 98.13, "elapsed_time": "0:38:39", "remaining_time": "0:00:44"}
+{"current_steps": 1845, "total_steps": 1875, "loss": 0.4962, "lr": 1.2630433939825327e-07, "epoch": 2.952, "percentage": 98.4, "elapsed_time": "0:38:45", "remaining_time": "0:00:37"}
+{"current_steps": 1850, "total_steps": 1875, "loss": 0.5021, "lr": 8.771699011416168e-08, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "0:38:52", "remaining_time": "0:00:31"}
+{"current_steps": 1855, "total_steps": 1875, "loss": 0.5277, "lr": 5.6141828853573106e-08, "epoch": 2.968, "percentage": 98.93, "elapsed_time": "0:38:58", "remaining_time": "0:00:25"}
+{"current_steps": 1860, "total_steps": 1875, "loss": 0.5764, "lr": 3.1581071670006015e-08, "epoch": 2.976, "percentage": 99.2, "elapsed_time": "0:39:01", "remaining_time": "0:00:18"}
+{"current_steps": 1865, "total_steps": 1875, "loss": 0.5408, "lr": 1.4036442321962995e-08, "epoch": 2.984, "percentage": 99.47, "elapsed_time": "0:39:08", "remaining_time": "0:00:12"}
+{"current_steps": 1870, "total_steps": 1875, "loss": 0.5014, "lr": 3.509172151938689e-09, "epoch": 2.992, "percentage": 99.73, "elapsed_time": "0:39:17", "remaining_time": "0:00:06"}
+{"current_steps": 1875, "total_steps": 1875, "loss": 0.6182, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:39:23", "remaining_time": "0:00:00"}
+{"current_steps": 1875, "total_steps": 1875, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:39:25", "remaining_time": "0:00:00"}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5b8b227e539a162d3769a6a052c3a5adfa6820f9
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,2667 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 0.8485889434814453,
+      "learning_rate": 0.0001999964908278481,
+      "loss": 1.2049,
+      "step": 5
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.47789862751960754,
+      "learning_rate": 0.00019998596355767805,
+      "loss": 0.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 1.017558217048645,
+      "learning_rate": 0.00019996841892833,
+      "loss": 0.8671,
+      "step": 15
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.6610977053642273,
+      "learning_rate": 0.00019994385817114646,
+      "loss": 0.7979,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6075429320335388,
+      "learning_rate": 0.00019991228300988585,
+      "loss": 0.7662,
+      "step": 25
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.6595763564109802,
+      "learning_rate": 0.00019987369566060176,
+      "loss": 0.7929,
+      "step": 30
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.6968618035316467,
+      "learning_rate": 0.00019982809883148722,
+      "loss": 0.7683,
+      "step": 35
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.4889592230319977,
+      "learning_rate": 0.00019977549572268468,
+      "loss": 0.8667,
+      "step": 40
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.6651108264923096,
+      "learning_rate": 0.0001997158900260614,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5898510217666626,
+      "learning_rate": 0.00019964928592495045,
+      "loss": 0.9051,
+      "step": 50
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.4398016035556793,
+      "learning_rate": 0.00019957568809385694,
+      "loss": 0.7235,
+      "step": 55
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.6901968121528625,
+      "learning_rate": 0.00019949510169813003,
+      "loss": 0.8169,
+      "step": 60
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.6267213225364685,
+      "learning_rate": 0.00019940753239360047,
+      "loss": 0.8266,
+      "step": 65
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.48524895310401917,
+      "learning_rate": 0.00019931298632618356,
+      "loss": 0.758,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5294132232666016,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7759,
+      "step": 75
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.48957982659339905,
+      "learning_rate": 0.0001991029909341493,
+      "loss": 0.7797,
+      "step": 80
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.645412802696228,
+      "learning_rate": 0.00019898755634773158,
+      "loss": 0.7437,
+      "step": 85
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.43297675251960754,
+      "learning_rate": 0.0001988651744737914,
+      "loss": 0.8043,
+      "step": 90
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.5513920783996582,
+      "learning_rate": 0.00019873585390151003,
+      "loss": 0.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8462435007095337,
+      "learning_rate": 0.0001985996037070505,
+      "loss": 0.709,
+      "step": 100
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.6892585158348083,
+      "learning_rate": 0.00019845643345292054,
+      "loss": 0.7377,
+      "step": 105
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.4617864191532135,
+      "learning_rate": 0.00019830635318730154,
+      "loss": 0.8352,
+      "step": 110
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.6300354599952698,
+      "learning_rate": 0.0001981493734433433,
+      "loss": 0.7738,
+      "step": 115
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8086859583854675,
+      "learning_rate": 0.0001979855052384247,
+      "loss": 0.8067,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6272985935211182,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7456,
+      "step": 125
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.44750839471817017,
+      "learning_rate": 0.00019763714993169452,
+      "loss": 0.758,
+      "step": 130
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.5053977370262146,
+      "learning_rate": 0.00019745268727865774,
+      "loss": 0.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.41920769214630127,
+      "learning_rate": 0.00019726138506049438,
+      "loss": 0.7302,
+      "step": 140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.38280290365219116,
+      "learning_rate": 0.00019706325670345275,
+      "loss": 0.8152,
+      "step": 145
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.554710865020752,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.8461,
+      "step": 150
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.5612509250640869,
+      "learning_rate": 0.00019664657767216176,
+      "loss": 0.7787,
+      "step": 155
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.610614538192749,
+      "learning_rate": 0.00019642805624188147,
+      "loss": 0.7574,
+      "step": 160
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.679517924785614,
+      "learning_rate": 0.0001962027671586086,
+      "loss": 0.8487,
+      "step": 165
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.6685434579849243,
+      "learning_rate": 0.00019597072623390668,
+      "loss": 0.6611,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.480293869972229,
+      "learning_rate": 0.00019573194975320673,
+      "loss": 0.7802,
+      "step": 175
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.7727369070053101,
+      "learning_rate": 0.00019548645447466431,
+      "loss": 0.6727,
+      "step": 180
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.6371043920516968,
+      "learning_rate": 0.00019523425762798329,
+      "loss": 0.7502,
+      "step": 185
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.6399966478347778,
+      "learning_rate": 0.00019497537691320668,
+      "loss": 0.8401,
+      "step": 190
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.7263137698173523,
+      "learning_rate": 0.00019470983049947444,
+      "loss": 0.7494,
+      "step": 195
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.402416467666626,
+      "learning_rate": 0.00019443763702374812,
+      "loss": 0.7842,
+      "step": 200
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.6639626026153564,
+      "learning_rate": 0.00019415881558950302,
+      "loss": 0.8082,
+      "step": 205
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5801042914390564,
+      "learning_rate": 0.00019387338576538744,
+      "loss": 0.7883,
+      "step": 210
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.5533607006072998,
+      "learning_rate": 0.00019358136758384912,
+      "loss": 0.7356,
+      "step": 215
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.6019654273986816,
+      "learning_rate": 0.00019328278153972947,
+      "loss": 0.7891,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5344104170799255,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.7671,
+      "step": 225
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5494843125343323,
+      "learning_rate": 0.0001926659901464172,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.465420126914978,
+      "learning_rate": 0.00019234782808576824,
+      "loss": 0.647,
+      "step": 235
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.5202775001525879,
+      "learning_rate": 0.00019202318473658705,
+      "loss": 0.729,
+      "step": 240
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5757818222045898,
+      "learning_rate": 0.00019169208288346166,
+      "loss": 0.6713,
+      "step": 245
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.46555572748184204,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7049,
+      "step": 250
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5101790428161621,
+      "learning_rate": 0.00019101059706849957,
+      "loss": 0.7419,
+      "step": 255
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6083744764328003,
+      "learning_rate": 0.00019066026093568378,
+      "loss": 0.7148,
+      "step": 260
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.4719640612602234,
+      "learning_rate": 0.00019030356195360874,
+      "loss": 0.7493,
+      "step": 265
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.7365225553512573,
+      "learning_rate": 0.0001899405251566371,
+      "loss": 0.7652,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4452705383300781,
+      "learning_rate": 0.0001895711760239413,
+      "loss": 0.7438,
+      "step": 275
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6071786284446716,
+      "learning_rate": 0.0001891955404777151,
+      "loss": 0.7683,
+      "step": 280
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5774498581886292,
+      "learning_rate": 0.00018881364488135448,
+      "loss": 0.8115,
+      "step": 285
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.6134682893753052,
+      "learning_rate": 0.00018842551603760724,
+      "loss": 0.8335,
+      "step": 290
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.4869893193244934,
+      "learning_rate": 0.00018803118118669202,
+      "loss": 0.6933,
+      "step": 295
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6457111239433289,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.7515,
+      "step": 300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.59674471616745,
+      "learning_rate": 0.0001872240046000844,
+      "loss": 0.6931,
+      "step": 305
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.44608160853385925,
+      "learning_rate": 0.00018681121951482393,
+      "loss": 0.782,
+      "step": 310
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5934664607048035,
+      "learning_rate": 0.00018639234171928353,
+      "loss": 0.7361,
+      "step": 315
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.49716323614120483,
+      "learning_rate": 0.0001859674006117491,
+      "loss": 0.7443,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.47995495796203613,
+      "learning_rate": 0.00018553642601605068,
+      "loss": 0.7221,
+      "step": 325
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5177399516105652,
+      "learning_rate": 0.00018509944817946922,
+      "loss": 0.7622,
+      "step": 330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.6638798713684082,
+      "learning_rate": 0.0001846564977706138,
+      "loss": 0.8556,
+      "step": 335
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5056771636009216,
+      "learning_rate": 0.00018420760587726923,
+      "loss": 0.7814,
+      "step": 340
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.44543707370758057,
+      "learning_rate": 0.0001837528040042142,
+      "loss": 0.722,
+      "step": 345
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6765120625495911,
+      "learning_rate": 0.00018329212407100994,
+      "loss": 0.7903,
+      "step": 350
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.49232372641563416,
+      "learning_rate": 0.00018282559840976042,
+      "loss": 0.6996,
+      "step": 355
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.47392791509628296,
+      "learning_rate": 0.00018235325976284275,
+      "loss": 0.773,
+      "step": 360
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5056615471839905,
+      "learning_rate": 0.00018187514128060946,
+      "loss": 0.728,
+      "step": 365
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5857616662979126,
+      "learning_rate": 0.00018139127651906184,
+      "loss": 0.7659,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5966864228248596,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7039,
+      "step": 375
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4524347484111786,
+      "learning_rate": 0.00018040644439611348,
+      "loss": 0.7125,
+      "step": 380
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5570976138114929,
+      "learning_rate": 0.00017990554615362198,
+      "loss": 0.698,
+      "step": 385
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.6045777201652527,
+      "learning_rate": 0.00017939903986478355,
+      "loss": 0.8255,
+      "step": 390
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.6149687767028809,
+      "learning_rate": 0.00017888696107795342,
+      "loss": 0.6616,
+      "step": 395
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4873579144477844,
+      "learning_rate": 0.000178369345732584,
+      "loss": 0.7452,
+      "step": 400
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.5569061636924744,
+      "learning_rate": 0.00017784623015670238,
+      "loss": 0.7652,
+      "step": 405
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5825181603431702,
+      "learning_rate": 0.00017731765106436073,
+      "loss": 0.7793,
+      "step": 410
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.4047383666038513,
+      "learning_rate": 0.00017678364555305978,
+      "loss": 0.6875,
+      "step": 415
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5080836415290833,
+      "learning_rate": 0.0001762442511011448,
+      "loss": 0.7465,
+      "step": 420
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5825940370559692,
+      "learning_rate": 0.00017569950556517566,
+      "loss": 0.7205,
+      "step": 425
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.476992666721344,
+      "learning_rate": 0.00017514944717726962,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.7424727082252502,
+      "learning_rate": 0.00017459411454241822,
+      "loss": 0.7035,
+      "step": 435
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.6544787287712097,
+      "learning_rate": 0.00017403354663577783,
+      "loss": 0.787,
+      "step": 440
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.49425187706947327,
+      "learning_rate": 0.00017346778279993415,
+      "loss": 0.7515,
+      "step": 445
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5473236441612244,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.7199,
+      "step": 450
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.6773544549942017,
+      "learning_rate": 0.00017232082653153422,
+      "loss": 0.8037,
+      "step": 455
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.6355096101760864,
+      "learning_rate": 0.00017173971459631787,
+      "loss": 0.7502,
+      "step": 460
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.47867000102996826,
+      "learning_rate": 0.00017115356772092857,
+      "loss": 0.7446,
+      "step": 465
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.5135357975959778,
+      "learning_rate": 0.0001705624270431721,
+      "loss": 0.6507,
+      "step": 470
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.48866042494773865,
+      "learning_rate": 0.00016996633405133655,
+      "loss": 0.7164,
+      "step": 475
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5892354249954224,
+      "learning_rate": 0.0001693653305812805,
+      "loss": 0.7621,
+      "step": 480
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.6633970141410828,
+      "learning_rate": 0.00016875945881349676,
+      "loss": 0.7623,
+      "step": 485
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.6444060802459717,
+      "learning_rate": 0.000168148761270152,
+      "loss": 0.6606,
+      "step": 490
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.7012648582458496,
+      "learning_rate": 0.00016753328081210245,
+      "loss": 0.6941,
+      "step": 495
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7064160704612732,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.7241398096084595,
+      "learning_rate": 0.00016628814427068953,
+      "loss": 0.6996,
+      "step": 505
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.7807374596595764,
+      "learning_rate": 0.00016565857557529566,
+      "loss": 0.7542,
+      "step": 510
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.763768196105957,
+      "learning_rate": 0.00016502439873500289,
+      "loss": 0.7175,
+      "step": 515
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.6105090379714966,
+      "learning_rate": 0.0001643856582585254,
+      "loss": 0.7565,
+      "step": 520
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5686540603637695,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.7339,
+      "step": 525
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5341500043869019,
+      "learning_rate": 0.00016309466603018496,
+      "loss": 0.569,
+      "step": 530
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.7274748682975769,
+      "learning_rate": 0.00016244250488460158,
+      "loss": 0.7556,
+      "step": 535
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.7321165204048157,
+      "learning_rate": 0.00016178596130903344,
+      "loss": 0.7084,
+      "step": 540
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5086159110069275,
+      "learning_rate": 0.00016112508138196917,
+      "loss": 0.6935,
+      "step": 545
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4714389443397522,
+      "learning_rate": 0.0001604599114862375,
+      "loss": 0.7076,
+      "step": 550
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5031452178955078,
+      "learning_rate": 0.0001597904983057519,
+      "loss": 0.7151,
+      "step": 555
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7745943665504456,
+      "learning_rate": 0.0001591168888222342,
+      "loss": 0.7001,
+      "step": 560
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.6076303124427795,
+      "learning_rate": 0.00015843913031191723,
+      "loss": 0.7285,
+      "step": 565
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.7456529140472412,
+      "learning_rate": 0.00015775727034222675,
+      "loss": 0.8041,
+      "step": 570
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5760998725891113,
+      "learning_rate": 0.0001570713567684432,
+      "loss": 0.7353,
+      "step": 575
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.7057327032089233,
+      "learning_rate": 0.00015638143773034267,
+      "loss": 0.7792,
+      "step": 580
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.7615967392921448,
+      "learning_rate": 0.00015568756164881882,
+      "loss": 1.0121,
+      "step": 585
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.6304950714111328,
+      "learning_rate": 0.000154989777222484,
+      "loss": 0.7727,
+      "step": 590
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.6852543950080872,
+      "learning_rate": 0.00015428813342425177,
+      "loss": 0.741,
+      "step": 595
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6379660964012146,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.6919,
+      "step": 600
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5846463441848755,
+      "learning_rate": 0.00015287346495461315,
+      "loss": 0.7163,
+      "step": 605
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5999557971954346,
+      "learning_rate": 0.0001521605395695108,
+      "loss": 0.8152,
+      "step": 610
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.5806307196617126,
+      "learning_rate": 0.00015144395337815064,
+      "loss": 0.6709,
+      "step": 615
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.6559942960739136,
+      "learning_rate": 0.00015072375667301893,
+      "loss": 0.6527,
+      "step": 620
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6287715435028076,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8194,
+      "step": 625
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.616222620010376,
+      "learning_rate": 0.00014927273415482915,
+      "loss": 0.6627,
+      "step": 630
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.4750412106513977,
+      "learning_rate": 0.0001485420101795274,
+      "loss": 0.6366,
+      "step": 635
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.5122964978218079,
+      "learning_rate": 0.00014780787935881923,
+      "loss": 0.6717,
+      "step": 640
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.7382633090019226,
+      "learning_rate": 0.0001470703932165333,
+      "loss": 0.6483,
+      "step": 645
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6540554761886597,
+      "learning_rate": 0.00014632960351198618,
+      "loss": 0.6151,
+      "step": 650
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4776591956615448,
+      "learning_rate": 0.00014558556223635003,
+      "loss": 0.6707,
+      "step": 655
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.8012662529945374,
+      "learning_rate": 0.00014483832160900326,
+      "loss": 0.6125,
+      "step": 660
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.6735953092575073,
+      "learning_rate": 0.00014408793407386588,
+      "loss": 0.6206,
+      "step": 665
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.5640230774879456,
+      "learning_rate": 0.00014333445229571873,
+      "loss": 0.6161,
+      "step": 670
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5928654074668884,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.6583,
+      "step": 675
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.7347397208213806,
+      "learning_rate": 0.00014181841775163013,
+      "loss": 0.6222,
+      "step": 680
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.593773365020752,
+      "learning_rate": 0.0001410559713862128,
+      "loss": 0.716,
+      "step": 685
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.6244611144065857,
+      "learning_rate": 0.00014029064357136628,
+      "loss": 0.6198,
+      "step": 690
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.5083370804786682,
+      "learning_rate": 0.00013952248802043165,
+      "loss": 0.6389,
+      "step": 695
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5241413116455078,
+      "learning_rate": 0.0001387515586452103,
+      "loss": 0.6842,
+      "step": 700
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.524029016494751,
+      "learning_rate": 0.00013797790955218014,
+      "loss": 0.6071,
+      "step": 705
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5097878575325012,
+      "learning_rate": 0.00013720159503869815,
+      "loss": 0.5915,
+      "step": 710
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5782963037490845,
+      "learning_rate": 0.00013642266958918984,
+      "loss": 0.6794,
+      "step": 715
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.6088266372680664,
+      "learning_rate": 0.00013564118787132506,
+      "loss": 0.6773,
+      "step": 720
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.7768995761871338,
+      "learning_rate": 0.00013485720473218154,
+      "loss": 0.668,
+      "step": 725
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.6645551919937134,
+      "learning_rate": 0.0001340707751943952,
+      "loss": 0.6997,
+      "step": 730
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.9228842258453369,
+      "learning_rate": 0.00013328195445229868,
+      "loss": 0.831,
+      "step": 735
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.7556049823760986,
+      "learning_rate": 0.00013249079786804765,
+      "loss": 0.6378,
+      "step": 740
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.832775354385376,
+      "learning_rate": 0.0001316973609677352,
+      "loss": 0.6547,
+      "step": 745
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7329304814338684,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5808,
+      "step": 750
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.7193475961685181,
+      "learning_rate": 0.00013010386911959206,
+      "loss": 0.5582,
+      "step": 755
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.6274734735488892,
+      "learning_rate": 0.00012930392600850573,
+      "loss": 0.5801,
+      "step": 760
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.6485865712165833,
+      "learning_rate": 0.0001285019262469976,
+      "loss": 0.65,
+      "step": 765
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.7164427042007446,
+      "learning_rate": 0.00012769792612217224,
+      "loss": 0.6627,
+      "step": 770
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.600775957107544,
+      "learning_rate": 0.00012689198206152657,
+      "loss": 0.5603,
+      "step": 775
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8377975225448608,
+      "learning_rate": 0.00012608415062898972,
+      "loss": 0.6525,
+      "step": 780
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8069924116134644,
+      "learning_rate": 0.00012527448852095295,
+      "loss": 0.6731,
+      "step": 785
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6501213908195496,
+      "learning_rate": 0.00012446305256229073,
+      "loss": 0.6255,
+      "step": 790
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.62812340259552,
+      "learning_rate": 0.00012364989970237248,
+      "loss": 0.6585,
+      "step": 795
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.5702307820320129,
+      "learning_rate": 0.00012283508701106557,
+      "loss": 0.5996,
+      "step": 800
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.6311281323432922,
+      "learning_rate": 0.00012201867167473015,
+      "loss": 0.6355,
+      "step": 805
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5885419249534607,
+      "learning_rate": 0.00012120071099220549,
+      "loss": 0.6615,
+      "step": 810
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.5239307284355164,
+      "learning_rate": 0.0001203812623707885,
+      "loss": 0.6096,
+      "step": 815
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.6101869940757751,
+      "learning_rate": 0.00011956038332220483,
+      "loss": 0.5984,
+      "step": 820
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4395413100719452,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.5569,
+      "step": 825
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8984820246696472,
+      "learning_rate": 0.00011791456448835825,
+      "loss": 0.7088,
+      "step": 830
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.7709664106369019,
+      "learning_rate": 0.00011708974021232769,
+      "loss": 0.6731,
+      "step": 835
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.6782217025756836,
+      "learning_rate": 0.00011626371651948838,
+      "loss": 0.6188,
+      "step": 840
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.6427358984947205,
+      "learning_rate": 0.00011543655138302714,
+      "loss": 0.7004,
+      "step": 845
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5902594923973083,
+      "learning_rate": 0.00011460830285624118,
+      "loss": 0.5884,
+      "step": 850
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5935835838317871,
+      "learning_rate": 0.0001137790290684638,
+      "loss": 0.5739,
+      "step": 855
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.6752728223800659,
+      "learning_rate": 0.00011294878822098469,
+      "loss": 0.6435,
+      "step": 860
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7927135825157166,
+      "learning_rate": 0.00011211763858296507,
+      "loss": 0.6897,
+      "step": 865
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.714499294757843,
+      "learning_rate": 0.00011128563848734816,
+      "loss": 0.6641,
+      "step": 870
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.7086356282234192,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6273,
+      "step": 875
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.6125518679618835,
+      "learning_rate": 0.00010961932054943778,
+      "loss": 0.6437,
+      "step": 880
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.5635287165641785,
+      "learning_rate": 0.00010878511965507434,
+      "loss": 0.6345,
+      "step": 885
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.47936007380485535,
+      "learning_rate": 0.00010795030219076599,
+      "loss": 0.5913,
+      "step": 890
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.7142558097839355,
+      "learning_rate": 0.00010711492674687671,
+      "loss": 0.6482,
+      "step": 895
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5252729058265686,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.6165,
+      "step": 900
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.896318793296814,
+      "learning_rate": 0.00010544273647350092,
+      "loss": 0.634,
+      "step": 905
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.6029036045074463,
+      "learning_rate": 0.00010460603900408523,
+      "loss": 0.6509,
+      "step": 910
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.6835671663284302,
+      "learning_rate": 0.00010376901826699348,
+      "loss": 0.6212,
+      "step": 915
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.7098750472068787,
+      "learning_rate": 0.00010293173300722285,
+      "loss": 0.7305,
+      "step": 920
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.675316333770752,
+      "learning_rate": 0.0001020942419883357,
+      "loss": 0.6685,
+      "step": 925
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.6675406098365784,
+      "learning_rate": 0.00010125660398833528,
+      "loss": 0.6214,
+      "step": 930
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.6629154682159424,
+      "learning_rate": 0.0001004188777955404,
+      "loss": 0.6035,
+      "step": 935
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.7732692360877991,
+      "learning_rate": 9.958112220445963e-05,
+      "loss": 0.5868,
+      "step": 940
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6238484978675842,
+      "learning_rate": 9.874339601166473e-05,
+      "loss": 0.6003,
+      "step": 945
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.6622412800788879,
+      "learning_rate": 9.790575801166432e-05,
+      "loss": 0.5854,
+      "step": 950
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.7598085999488831,
+      "learning_rate": 9.706826699277718e-05,
+      "loss": 0.5882,
+      "step": 955
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.8870390057563782,
+      "learning_rate": 9.623098173300654e-05,
+      "loss": 0.7187,
+      "step": 960
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.702232837677002,
+      "learning_rate": 9.539396099591476e-05,
+      "loss": 0.6156,
+      "step": 965
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.694139301776886,
+      "learning_rate": 9.455726352649911e-05,
+      "loss": 0.6488,
+      "step": 970
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5684956312179565,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6601,
+      "step": 975
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.6327118277549744,
+      "learning_rate": 9.288507325312335e-05,
+      "loss": 0.5968,
+      "step": 980
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5732144117355347,
+      "learning_rate": 9.204969780923403e-05,
+      "loss": 0.7034,
+      "step": 985
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7025273442268372,
+      "learning_rate": 9.121488034492569e-05,
+      "loss": 0.5973,
+      "step": 990
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.9270740151405334,
+      "learning_rate": 9.038067945056227e-05,
+      "loss": 0.7877,
+      "step": 995
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6676818132400513,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.6687547564506531,
+      "learning_rate": 8.871436151265184e-05,
+      "loss": 0.6678,
+      "step": 1005
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.7400322556495667,
+      "learning_rate": 8.788236141703498e-05,
+      "loss": 0.6088,
+      "step": 1010
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.5504963994026184,
+      "learning_rate": 8.705121177901532e-05,
+      "loss": 0.6219,
+      "step": 1015
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.8088738322257996,
+      "learning_rate": 8.62209709315362e-05,
+      "loss": 0.6698,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.7380816340446472,
+      "learning_rate": 8.539169714375885e-05,
+      "loss": 0.6207,
+      "step": 1025
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6346850395202637,
+      "learning_rate": 8.456344861697289e-05,
+      "loss": 0.626,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.49918702244758606,
+      "learning_rate": 8.373628348051165e-05,
+      "loss": 0.6972,
+      "step": 1035
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7200607657432556,
+      "learning_rate": 8.291025978767235e-05,
+      "loss": 0.6282,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.8350688815116882,
+      "learning_rate": 8.208543551164178e-05,
+      "loss": 0.6219,
+      "step": 1045
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.5957468748092651,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 0.622,
+      "step": 1050
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.7494757175445557,
+      "learning_rate": 8.04396166777952e-05,
+      "loss": 0.5801,
+      "step": 1055
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7109113931655884,
+      "learning_rate": 7.961873762921153e-05,
+      "loss": 0.598,
+      "step": 1060
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.7941219210624695,
+      "learning_rate": 7.879928900779456e-05,
+      "loss": 0.699,
+      "step": 1065
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.7282152771949768,
+      "learning_rate": 7.798132832526986e-05,
+      "loss": 0.5882,
+      "step": 1070
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.5923735499382019,
+      "learning_rate": 7.716491298893442e-05,
+      "loss": 0.5321,
+      "step": 1075
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.5571523308753967,
+      "learning_rate": 7.635010029762756e-05,
+      "loss": 0.6647,
+      "step": 1080
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6043043732643127,
+      "learning_rate": 7.553694743770928e-05,
+      "loss": 0.628,
+      "step": 1085
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.8733720183372498,
+      "learning_rate": 7.472551147904708e-05,
+      "loss": 0.6262,
+      "step": 1090
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.5561848878860474,
+      "learning_rate": 7.391584937101033e-05,
+      "loss": 0.6131,
+      "step": 1095
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6611356735229492,
+      "learning_rate": 7.310801793847344e-05,
+      "loss": 0.6494,
+      "step": 1100
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5700333714485168,
+      "learning_rate": 7.230207387782776e-05,
+      "loss": 0.5514,
+      "step": 1105
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.705662727355957,
+      "learning_rate": 7.149807375300239e-05,
+      "loss": 0.5823,
+      "step": 1110
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.9632449150085449,
+      "learning_rate": 7.069607399149428e-05,
+      "loss": 0.7207,
+      "step": 1115
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.6412242650985718,
+      "learning_rate": 6.989613088040796e-05,
+      "loss": 0.7006,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.538044273853302,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6222,
+      "step": 1125
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6124762296676636,
+      "learning_rate": 6.830263903226483e-05,
+      "loss": 0.6569,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.7250857949256897,
+      "learning_rate": 6.750920213195238e-05,
+      "loss": 0.543,
+      "step": 1135
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.6840488910675049,
+      "learning_rate": 6.671804554770135e-05,
+      "loss": 0.6334,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.8932304382324219,
+      "learning_rate": 6.592922480560483e-05,
+      "loss": 0.6701,
+      "step": 1145
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.9220761656761169,
+      "learning_rate": 6.51427952678185e-05,
+      "loss": 0.6216,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.688731849193573,
+      "learning_rate": 6.435881212867493e-05,
+      "loss": 0.5877,
+      "step": 1155
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.6370134949684143,
+      "learning_rate": 6.357733041081018e-05,
+      "loss": 0.6256,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.7421153783798218,
+      "learning_rate": 6.27984049613019e-05,
+      "loss": 0.7062,
+      "step": 1165
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.8129108548164368,
+      "learning_rate": 6.20220904478199e-05,
+      "loss": 0.6304,
+      "step": 1170
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7866687774658203,
+      "learning_rate": 6.12484413547897e-05,
+      "loss": 0.7695,
+      "step": 1175
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.8307198882102966,
+      "learning_rate": 6.047751197956838e-05,
+      "loss": 0.5723,
+      "step": 1180
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.5541536211967468,
+      "learning_rate": 5.9709356428633746e-05,
+      "loss": 0.6847,
+      "step": 1185
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.731555163860321,
+      "learning_rate": 5.8944028613787206e-05,
+      "loss": 0.6618,
+      "step": 1190
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 1.020991325378418,
+      "learning_rate": 5.818158224836987e-05,
+      "loss": 0.6275,
+      "step": 1195
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.7172287702560425,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.5617,
+      "step": 1200
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.7232096791267395,
+      "learning_rate": 5.666554770428129e-05,
+      "loss": 0.6278,
+      "step": 1205
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.7234194278717041,
+      "learning_rate": 5.591206592613416e-05,
+      "loss": 0.6713,
+      "step": 1210
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.6906010508537292,
+      "learning_rate": 5.5161678390996796e-05,
+      "loss": 0.6113,
+      "step": 1215
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.9057906270027161,
+      "learning_rate": 5.441443776365003e-05,
+      "loss": 0.5587,
+      "step": 1220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7144932150840759,
+      "learning_rate": 5.3670396488013854e-05,
+      "loss": 0.5601,
+      "step": 1225
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 1.0071252584457397,
+      "learning_rate": 5.292960678346675e-05,
+      "loss": 0.5941,
+      "step": 1230
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7061260342597961,
+      "learning_rate": 5.2192120641180786e-05,
+      "loss": 0.6285,
+      "step": 1235
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6937069892883301,
+      "learning_rate": 5.145798982047261e-05,
+      "loss": 0.6516,
+      "step": 1240
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5176392793655396,
+      "learning_rate": 5.072726584517086e-05,
+      "loss": 0.5904,
+      "step": 1245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8501409292221069,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.619,
+      "step": 1250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5451085567474365,
+      "learning_rate": 4.927624332698109e-05,
+      "loss": 0.6058,
+      "step": 1255
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.8410437107086182,
+      "learning_rate": 4.8556046621849346e-05,
+      "loss": 0.6248,
+      "step": 1260
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.6089378595352173,
+      "learning_rate": 4.783946043048923e-05,
+      "loss": 0.5247,
+      "step": 1265
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.47437986731529236,
+      "learning_rate": 4.712653504538683e-05,
+      "loss": 0.5439,
+      "step": 1270
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6925654411315918,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 0.4491,
+      "step": 1275
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.8538162708282471,
+      "learning_rate": 4.5711866575748276e-05,
+      "loss": 0.52,
+      "step": 1280
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.8048768639564514,
+      "learning_rate": 4.501022277751602e-05,
+      "loss": 0.5259,
+      "step": 1285
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.7191641330718994,
+      "learning_rate": 4.431243835118124e-05,
+      "loss": 0.5025,
+      "step": 1290
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 1.0918892621994019,
+      "learning_rate": 4.361856226965733e-05,
+      "loss": 0.4772,
+      "step": 1295
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.8152824640274048,
+      "learning_rate": 4.2928643231556844e-05,
+      "loss": 0.5945,
+      "step": 1300
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.640073299407959,
+      "learning_rate": 4.224272965777326e-05,
+      "loss": 0.4813,
+      "step": 1305
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.7172432541847229,
+      "learning_rate": 4.15608696880828e-05,
+      "loss": 0.5315,
+      "step": 1310
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 1.1283674240112305,
+      "learning_rate": 4.08831111777658e-05,
+      "loss": 0.5591,
+      "step": 1315
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.8184736967086792,
+      "learning_rate": 4.020950169424815e-05,
+      "loss": 0.605,
+      "step": 1320
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.6823618412017822,
+      "learning_rate": 3.954008851376252e-05,
+      "loss": 0.4955,
+      "step": 1325
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.8576385378837585,
+      "learning_rate": 3.887491861803085e-05,
+      "loss": 0.5757,
+      "step": 1330
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.967835009098053,
+      "learning_rate": 3.821403869096658e-05,
+      "loss": 0.5313,
+      "step": 1335
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.7330173254013062,
+      "learning_rate": 3.755749511539845e-05,
+      "loss": 0.5904,
+      "step": 1340
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.6664792895317078,
+      "learning_rate": 3.690533396981504e-05,
+      "loss": 0.4679,
+      "step": 1345
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.7639065980911255,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 0.5235,
+      "step": 1350
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.6960520148277283,
+      "learning_rate": 3.561434174147463e-05,
+      "loss": 0.5797,
+      "step": 1355
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.8231356143951416,
+      "learning_rate": 3.497560126499709e-05,
+      "loss": 0.5772,
+      "step": 1360
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.8968437910079956,
+      "learning_rate": 3.4341424424704375e-05,
+      "loss": 0.5316,
+      "step": 1365
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.8037480711936951,
+      "learning_rate": 3.371185572931048e-05,
+      "loss": 0.5646,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9330148696899414,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5431,
+      "step": 1375
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.6958775520324707,
+      "learning_rate": 3.246671918789755e-05,
+      "loss": 0.5403,
+      "step": 1380
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.9870476126670837,
+      "learning_rate": 3.1851238729848034e-05,
+      "loss": 0.5329,
+      "step": 1385
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.5036590099334717,
+      "learning_rate": 3.124054118650327e-05,
+      "loss": 0.5696,
+      "step": 1390
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.8640053868293762,
+      "learning_rate": 3.063466941871952e-05,
+      "loss": 0.59,
+      "step": 1395
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6065173149108887,
+      "learning_rate": 3.0033665948663448e-05,
+      "loss": 0.5116,
+      "step": 1400
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 1.083775520324707,
+      "learning_rate": 2.9437572956827964e-05,
+      "loss": 0.5783,
+      "step": 1405
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.7090497016906738,
+      "learning_rate": 2.8846432279071467e-05,
+      "loss": 0.6259,
+      "step": 1410
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.742468535900116,
+      "learning_rate": 2.826028540368215e-05,
+      "loss": 0.5759,
+      "step": 1415
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.9219839572906494,
+      "learning_rate": 2.7679173468465812e-05,
+      "loss": 0.497,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.7159206867218018,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.619,
+      "step": 1425
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.6997727751731873,
+      "learning_rate": 2.6532217200065858e-05,
+      "loss": 0.5858,
+      "step": 1430
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.7493643164634705,
+      "learning_rate": 2.5966453364222186e-05,
+      "loss": 0.6291,
+      "step": 1435
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.8311699032783508,
+      "learning_rate": 2.540588545758179e-05,
+      "loss": 0.6418,
+      "step": 1440
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.7084354758262634,
+      "learning_rate": 2.48505528227304e-05,
+      "loss": 0.5483,
+      "step": 1445
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.734438955783844,
+      "learning_rate": 2.4300494434824373e-05,
+      "loss": 0.6071,
+      "step": 1450
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.8913635015487671,
+      "learning_rate": 2.37557488988552e-05,
+      "loss": 0.5099,
+      "step": 1455
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.8349048495292664,
+      "learning_rate": 2.321635444694028e-05,
+      "loss": 0.5186,
+      "step": 1460
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.6164011359214783,
+      "learning_rate": 2.2682348935639274e-05,
+      "loss": 0.5043,
+      "step": 1465
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 1.044892430305481,
+      "learning_rate": 2.2153769843297667e-05,
+      "loss": 0.61,
+      "step": 1470
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9142879247665405,
+      "learning_rate": 2.163065426741603e-05,
+      "loss": 0.5987,
+      "step": 1475
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.6232836842536926,
+      "learning_rate": 2.1113038922046602e-05,
+      "loss": 0.5212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.49558231234550476,
+      "learning_rate": 2.0600960135216462e-05,
+      "loss": 0.4796,
+      "step": 1485
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.7887687683105469,
+      "learning_rate": 2.009445384637805e-05,
+      "loss": 0.4844,
+      "step": 1490
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.8086990714073181,
+      "learning_rate": 1.9593555603886538e-05,
+      "loss": 0.5085,
+      "step": 1495
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6713303327560425,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4839,
+      "step": 1500
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.6262741684913635,
+      "learning_rate": 1.8608723480938206e-05,
+      "loss": 0.5715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.8025808334350586,
+      "learning_rate": 1.812485871939056e-05,
+      "loss": 0.5266,
+      "step": 1510
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.8753231167793274,
+      "learning_rate": 1.7646740237157256e-05,
+      "loss": 0.5422,
+      "step": 1515
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.6459301710128784,
+      "learning_rate": 1.7174401590239587e-05,
+      "loss": 0.5553,
+      "step": 1520
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.6917416453361511,
+      "learning_rate": 1.6707875928990058e-05,
+      "loss": 0.5765,
+      "step": 1525
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.7890029549598694,
+      "learning_rate": 1.6247195995785837e-05,
+      "loss": 0.549,
+      "step": 1530
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.9913660883903503,
+      "learning_rate": 1.579239412273078e-05,
+      "loss": 0.4876,
+      "step": 1535
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.9030985832214355,
+      "learning_rate": 1.5343502229386207e-05,
+      "loss": 0.5546,
+      "step": 1540
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.9133403301239014,
+      "learning_rate": 1.4900551820530828e-05,
+      "loss": 0.5356,
+      "step": 1545
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.7083793878555298,
+      "learning_rate": 1.4463573983949341e-05,
+      "loss": 0.5142,
+      "step": 1550
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 1.095435619354248,
+      "learning_rate": 1.40325993882509e-05,
+      "loss": 0.6054,
+      "step": 1555
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.8825190663337708,
+      "learning_rate": 1.3607658280716473e-05,
+      "loss": 0.5294,
+      "step": 1560
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.9436343908309937,
+      "learning_rate": 1.3188780485176088e-05,
+      "loss": 0.5294,
+      "step": 1565
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 1.0125439167022705,
+      "learning_rate": 1.2775995399915631e-05,
+      "loss": 0.4905,
+      "step": 1570
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.8476350903511047,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 0.5186,
+      "step": 1575
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.9092681407928467,
+      "learning_rate": 1.196881881330798e-05,
+      "loss": 0.4909,
+      "step": 1580
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.7970360517501831,
+      "learning_rate": 1.1574483962392767e-05,
+      "loss": 0.5303,
+      "step": 1585
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.8575041890144348,
+      "learning_rate": 1.1186355118645554e-05,
+      "loss": 0.5169,
+      "step": 1590
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.7397408485412598,
+      "learning_rate": 1.0804459522284926e-05,
+      "loss": 0.5339,
+      "step": 1595
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7415968179702759,
+      "learning_rate": 1.042882397605871e-05,
+      "loss": 0.5283,
+      "step": 1600
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 0.7035180926322937,
+      "learning_rate": 1.0059474843362892e-05,
+      "loss": 0.5576,
+      "step": 1605
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.9805112481117249,
+      "learning_rate": 9.696438046391288e-06,
+      "loss": 0.5136,
+      "step": 1610
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 0.6661838889122009,
+      "learning_rate": 9.339739064316233e-06,
+      "loss": 0.5885,
+      "step": 1615
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.8581559062004089,
+      "learning_rate": 8.989402931500434e-06,
+      "loss": 0.5,
+      "step": 1620
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7146279811859131,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5325,
+      "step": 1625
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.9474234580993652,
+      "learning_rate": 8.307917116538378e-06,
+      "loss": 0.5772,
+      "step": 1630
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 0.9583209753036499,
+      "learning_rate": 7.976815263412963e-06,
+      "loss": 0.5736,
+      "step": 1635
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.7156705260276794,
+      "learning_rate": 7.652171914231776e-06,
+      "loss": 0.5199,
+      "step": 1640
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 0.8224849700927734,
+      "learning_rate": 7.3340098535827905e-06,
+      "loss": 0.5753,
+      "step": 1645
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.8689257502555847,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5424,
+      "step": 1650
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 0.6636053323745728,
+      "learning_rate": 6.717218460270536e-06,
+      "loss": 0.5555,
+      "step": 1655
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.8688860535621643,
+      "learning_rate": 6.418632416150927e-06,
+      "loss": 0.4936,
+      "step": 1660
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 0.6272854208946228,
+      "learning_rate": 6.126614234612593e-06,
+      "loss": 0.6291,
+      "step": 1665
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 1.2240337133407593,
+      "learning_rate": 5.8411844104969916e-06,
+      "loss": 0.5197,
+      "step": 1670
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9820936918258667,
+      "learning_rate": 5.562362976251901e-06,
+      "loss": 0.5398,
+      "step": 1675
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 1.1582359075546265,
+      "learning_rate": 5.290169500525577e-06,
+      "loss": 0.6059,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 0.5501114726066589,
+      "learning_rate": 5.024623086793323e-06,
+      "loss": 0.531,
+      "step": 1685
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.8848717212677002,
+      "learning_rate": 4.765742372016735e-06,
+      "loss": 0.6054,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 0.7358693480491638,
+      "learning_rate": 4.513545525335705e-06,
+      "loss": 0.5173,
+      "step": 1695
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.9218215942382812,
+      "learning_rate": 4.268050246793276e-06,
+      "loss": 0.4944,
+      "step": 1700
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 0.6374716758728027,
+      "learning_rate": 4.029273766093333e-06,
+      "loss": 0.5183,
+      "step": 1705
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.583243191242218,
+      "learning_rate": 3.797232841391407e-06,
+      "loss": 0.668,
+      "step": 1710
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 0.8384690284729004,
+      "learning_rate": 3.5719437581185454e-06,
+      "loss": 0.5068,
+      "step": 1715
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.8034130334854126,
+      "learning_rate": 3.3534223278382405e-06,
+      "loss": 0.5823,
+      "step": 1720
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.8146041631698608,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 0.6111,
+      "step": 1725
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.8122982382774353,
+      "learning_rate": 2.936743296547273e-06,
+      "loss": 0.5231,
+      "step": 1730
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 0.7326982021331787,
+      "learning_rate": 2.738614939505646e-06,
+      "loss": 0.5236,
+      "step": 1735
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.7472147345542908,
+      "learning_rate": 2.5473127213422763e-06,
+      "loss": 0.5657,
+      "step": 1740
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 0.8197700381278992,
+      "learning_rate": 2.3628500683055222e-06,
+      "loss": 0.5518,
+      "step": 1745
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.8733732104301453,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4908,
+      "step": 1750
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 0.8913092017173767,
+      "learning_rate": 2.014494761575314e-06,
+      "loss": 0.5459,
+      "step": 1755
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 1.1259772777557373,
+      "learning_rate": 1.8506265566567094e-06,
+      "loss": 0.5208,
+      "step": 1760
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 0.7692184448242188,
+      "learning_rate": 1.6936468126984572e-06,
+      "loss": 0.5824,
+      "step": 1765
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.588602602481842,
+      "learning_rate": 1.543566547079467e-06,
+      "loss": 0.5512,
+      "step": 1770
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.6324055790901184,
+      "learning_rate": 1.400396292949513e-06,
+      "loss": 0.6327,
+      "step": 1775
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.7608378529548645,
+      "learning_rate": 1.26414609848996e-06,
+      "loss": 0.5292,
+      "step": 1780
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 0.7972851395606995,
+      "learning_rate": 1.134825526208605e-06,
+      "loss": 0.5692,
+      "step": 1785
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.9705446362495422,
+      "learning_rate": 1.0124436522684243e-06,
+      "loss": 0.5532,
+      "step": 1790
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 0.6317399144172668,
+      "learning_rate": 8.970090658507291e-07,
+      "loss": 0.5314,
+      "step": 1795
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6457757949829102,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 0.524,
+      "step": 1800
+    },
+    {
+      "epoch": 2.888,
+      "grad_norm": 0.8593656420707703,
+      "learning_rate": 6.870136738164612e-07,
+      "loss": 0.5227,
+      "step": 1805
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 1.0187020301818848,
+      "learning_rate": 5.924676063995382e-07,
+      "loss": 0.5993,
+      "step": 1810
+    },
+    {
+      "epoch": 2.904,
+      "grad_norm": 0.7082214951515198,
+      "learning_rate": 5.048983018699827e-07,
+      "loss": 0.5618,
+      "step": 1815
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.6521438956260681,
+      "learning_rate": 4.2431190614309335e-07,
+      "loss": 0.5504,
+      "step": 1820
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.8906036615371704,
+      "learning_rate": 3.50714075049563e-07,
+      "loss": 0.5147,
+      "step": 1825
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 1.0908008813858032,
+      "learning_rate": 2.841099739386066e-07,
+      "loss": 0.5564,
+      "step": 1830
+    },
+    {
+      "epoch": 2.936,
+      "grad_norm": 0.6374122500419617,
+      "learning_rate": 2.2450427731534053e-07,
+      "loss": 0.5188,
+      "step": 1835
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.9616740345954895,
+      "learning_rate": 1.7190116851280026e-07,
+      "loss": 0.5438,
+      "step": 1840
+    },
+    {
+      "epoch": 2.952,
+      "grad_norm": 1.0712924003601074,
+      "learning_rate": 1.2630433939825327e-07,
+      "loss": 0.4962,
+      "step": 1845
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.8226613998413086,
+      "learning_rate": 8.771699011416168e-08,
+      "loss": 0.5021,
+      "step": 1850
+    },
+    {
+      "epoch": 2.968,
+      "grad_norm": 0.9519492983818054,
+      "learning_rate": 5.6141828853573106e-08,
+      "loss": 0.5277,
+      "step": 1855
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.9817518591880798,
+      "learning_rate": 3.1581071670006015e-08,
+      "loss": 0.5764,
+      "step": 1860
+    },
+    {
+      "epoch": 2.984,
+      "grad_norm": 0.7039242386817932,
+      "learning_rate": 1.4036442321962995e-08,
+      "loss": 0.5408,
+      "step": 1865
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 0.591012179851532,
+      "learning_rate": 3.509172151938689e-09,
+      "loss": 0.5014,
+      "step": 1870
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7672661542892456,
+      "learning_rate": 0.0,
+      "loss": 0.6182,
+      "step": 1875
+    },
+    {
+      "epoch": 3.0,
+      "step": 1875,
+      "total_flos": 1.1764404625814323e+17,
+      "train_loss": 0.6465437274932861,
+      "train_runtime": 2365.2475,
+      "train_samples_per_second": 12.684,
+      "train_steps_per_second": 0.793
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1764404625814323e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b72392a9094690809605a9b89988a05f68c770c0
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6303cd7c1754cff6fd463f0e4dddf2a566ba7f29bbf2a72fbb560b32d5ce98
+size 5432
diff --git a/training_args.yaml b/training_args.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d3531daa1b6021e6cd4149789c5764370e389fe0
--- /dev/null
+++ b/training_args.yaml
@@ -0,0 +1,33 @@
+bf16: true
+cutoff_len: 1024
+dataset: mathinstruct
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 1
+learning_rate: 0.0002
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 10000
+model_name_or_path: meta-llama/Llama-3.2-1B
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Llama-3.2-1B/lora/llama3.2-1b
+packing: false
+per_device_train_batch_size: 16
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+rope_scaling: linear
+save_steps: 100
+stage: sft
+template: default
+trust_remote_code: true
+warmup_steps: 0
diff --git a/training_loss.png b/training_loss.png
new file mode 100644
index 0000000000000000000000000000000000000000..2b176a65172e62e3c82d61a73bf727642ee89055
Binary files /dev/null and b/training_loss.png differ