Upload LoRA model

README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+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

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d372471e86dddfe3fd923d34818731d26ee14eeed16c64cbf70cb18e85187d
+size 184592616

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+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

checkpoint-1000/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398a1933876f22bd8ac8d250b1c889e35d3f712fceec94eb8a4355304a7e2dcc
+size 184592616

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531d16abb01811b5b696291476ee9197bc0e96ca69f468ff492e8f036d073c37
+size 92836436

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a938523584f04cc1c10c8aaff8ae9505d99d5f9349645f7e6cb36e7ec824123
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9ac9d3d72f4984a465c665a679676619a56dd2c29252965c0000f3f08c4419
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "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": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,740 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.567398119122257,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001567398119122257,
+      "grad_norm": 0.5552594661712646,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 3.3921,
+      "step": 1
+    },
+    {
+      "epoch": 0.01567398119122257,
+      "grad_norm": 0.660531222820282,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 3.5922,
+      "step": 10
+    },
+    {
+      "epoch": 0.03134796238244514,
+      "grad_norm": 0.5598097443580627,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 3.619,
+      "step": 20
+    },
+    {
+      "epoch": 0.047021943573667714,
+      "grad_norm": 0.5996779799461365,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 3.4824,
+      "step": 30
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 0.8172075152397156,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 3.3997,
+      "step": 40
+    },
+    {
+      "epoch": 0.07836990595611286,
+      "grad_norm": 1.6439019441604614,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 3.2485,
+      "step": 50
+    },
+    {
+      "epoch": 0.09404388714733543,
+      "grad_norm": 0.28180772066116333,
+      "learning_rate": 0.00019999942697524717,
+      "loss": 2.9975,
+      "step": 60
+    },
+    {
+      "epoch": 0.109717868338558,
+      "grad_norm": 0.3870689868927002,
+      "learning_rate": 0.00019997937179843937,
+      "loss": 3.0446,
+      "step": 70
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.575548529624939,
+      "learning_rate": 0.00019993067195079803,
+      "loss": 3.0178,
+      "step": 80
+    },
+    {
+      "epoch": 0.14106583072100312,
+      "grad_norm": 0.781446635723114,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 3.0394,
+      "step": 90
+    },
+    {
+      "epoch": 0.15673981191222572,
+      "grad_norm": 1.725696325302124,
+      "learning_rate": 0.00019974740225703878,
+      "loss": 3.0751,
+      "step": 100
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.2845414876937866,
+      "learning_rate": 0.00019961288491875278,
+      "loss": 2.9291,
+      "step": 110
+    },
+    {
+      "epoch": 0.18808777429467086,
+      "grad_norm": 0.36810651421546936,
+      "learning_rate": 0.00019944982791025333,
+      "loss": 2.9491,
+      "step": 120
+    },
+    {
+      "epoch": 0.20376175548589343,
+      "grad_norm": 0.5454439520835876,
+      "learning_rate": 0.00019925827794832056,
+      "loss": 3.0337,
+      "step": 130
+    },
+    {
+      "epoch": 0.219435736677116,
+      "grad_norm": 0.6503669619560242,
+      "learning_rate": 0.00019903828991313138,
+      "loss": 3.0246,
+      "step": 140
+    },
+    {
+      "epoch": 0.23510971786833856,
+      "grad_norm": 1.4392451047897339,
+      "learning_rate": 0.00019878992683253582,
+      "loss": 3.0232,
+      "step": 150
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.2859440743923187,
+      "learning_rate": 0.00019851325986399934,
+      "loss": 2.8955,
+      "step": 160
+    },
+    {
+      "epoch": 0.2664576802507837,
+      "grad_norm": 0.44268104434013367,
+      "learning_rate": 0.0001982083682742156,
+      "loss": 2.9338,
+      "step": 170
+    },
+    {
+      "epoch": 0.28213166144200624,
+      "grad_norm": 0.5128395557403564,
+      "learning_rate": 0.00019787533941639638,
+      "loss": 3.0089,
+      "step": 180
+    },
+    {
+      "epoch": 0.29780564263322884,
+      "grad_norm": 0.7328920364379883,
+      "learning_rate": 0.00019751426870524407,
+      "loss": 3.0157,
+      "step": 190
+    },
+    {
+      "epoch": 0.31347962382445144,
+      "grad_norm": 1.5265012979507446,
+      "learning_rate": 0.000197125259589615,
+      "loss": 2.9007,
+      "step": 200
+    },
+    {
+      "epoch": 0.329153605015674,
+      "grad_norm": 0.2766813635826111,
+      "learning_rate": 0.0001967084235228807,
+      "loss": 2.8275,
+      "step": 210
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.36695396900177,
+      "learning_rate": 0.00019626387993099579,
+      "loss": 2.9158,
+      "step": 220
+    },
+    {
+      "epoch": 0.3605015673981191,
+      "grad_norm": 0.5359162092208862,
+      "learning_rate": 0.00019579175617828187,
+      "loss": 2.9465,
+      "step": 230
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.6529833674430847,
+      "learning_rate": 0.0001952921875309368,
+      "loss": 2.981,
+      "step": 240
+    },
+    {
+      "epoch": 0.39184952978056425,
+      "grad_norm": 1.5314627885818481,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 2.9737,
+      "step": 250
+    },
+    {
+      "epoch": 0.40752351097178685,
+      "grad_norm": 0.2949506342411041,
+      "learning_rate": 0.00019421129589174618,
+      "loss": 2.8208,
+      "step": 260
+    },
+    {
+      "epoch": 0.4231974921630094,
+      "grad_norm": 0.39567869901657104,
+      "learning_rate": 0.00019363028258163447,
+      "loss": 2.8557,
+      "step": 270
+    },
+    {
+      "epoch": 0.438871473354232,
+      "grad_norm": 0.5587254166603088,
+      "learning_rate": 0.00019302244365163376,
+      "loss": 2.9494,
+      "step": 280
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.7218978404998779,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 2.9742,
+      "step": 290
+    },
+    {
+      "epoch": 0.4702194357366771,
+      "grad_norm": 1.4482598304748535,
+      "learning_rate": 0.0001917269931653049,
+      "loss": 2.8646,
+      "step": 300
+    },
+    {
+      "epoch": 0.48589341692789967,
+      "grad_norm": 0.2901701033115387,
+      "learning_rate": 0.00019103975276306678,
+      "loss": 2.7788,
+      "step": 310
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.4310539960861206,
+      "learning_rate": 0.00019032642894278192,
+      "loss": 2.8655,
+      "step": 320
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.5589954853057861,
+      "learning_rate": 0.0001895872260758688,
+      "loss": 2.914,
+      "step": 330
+    },
+    {
+      "epoch": 0.5329153605015674,
+      "grad_norm": 0.7243526577949524,
+      "learning_rate": 0.00018882235594824308,
+      "loss": 2.9191,
+      "step": 340
+    },
+    {
+      "epoch": 0.54858934169279,
+      "grad_norm": 1.4200222492218018,
+      "learning_rate": 0.00018803203769963967,
+      "loss": 2.8128,
+      "step": 350
+    },
+    {
+      "epoch": 0.5642633228840125,
+      "grad_norm": 0.26594147086143494,
+      "learning_rate": 0.000187216497760828,
+      "loss": 2.762,
+      "step": 360
+    },
+    {
+      "epoch": 0.5799373040752351,
+      "grad_norm": 0.3894258439540863,
+      "learning_rate": 0.00018637596978873835,
+      "loss": 2.9077,
+      "step": 370
+    },
+    {
+      "epoch": 0.5956112852664577,
+      "grad_norm": 0.5348561406135559,
+      "learning_rate": 0.00018551069459951758,
+      "loss": 2.9292,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112852664576802,
+      "grad_norm": 0.746507465839386,
+      "learning_rate": 0.00018462092009953408,
+      "loss": 2.8795,
+      "step": 390
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 1.5225753784179688,
+      "learning_rate": 0.0001837069012143511,
+      "loss": 2.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.6426332288401254,
+      "grad_norm": 0.26905450224876404,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 2.7218,
+      "step": 410
+    },
+    {
+      "epoch": 0.658307210031348,
+      "grad_norm": 0.3912515342235565,
+      "learning_rate": 0.00018180718464639787,
+      "loss": 2.819,
+      "step": 420
+    },
+    {
+      "epoch": 0.6739811912225705,
+      "grad_norm": 0.5661373138427734,
+      "learning_rate": 0.00018082203124346045,
+      "loss": 2.8772,
+      "step": 430
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.805776059627533,
+      "learning_rate": 0.0001798137218590498,
+      "loss": 2.9562,
+      "step": 440
+    },
+    {
+      "epoch": 0.7053291536050157,
+      "grad_norm": 1.4879732131958008,
+      "learning_rate": 0.00017878254537966216,
+      "loss": 2.7925,
+      "step": 450
+    },
+    {
+      "epoch": 0.7210031347962382,
+      "grad_norm": 0.28762391209602356,
+      "learning_rate": 0.00017772879724334937,
+      "loss": 2.8006,
+      "step": 460
+    },
+    {
+      "epoch": 0.7366771159874608,
+      "grad_norm": 0.41769474744796753,
+      "learning_rate": 0.00017665277935507398,
+      "loss": 2.8148,
+      "step": 470
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.633671760559082,
+      "learning_rate": 0.00017555480000021198,
+      "loss": 2.8461,
+      "step": 480
+    },
+    {
+      "epoch": 0.768025078369906,
+      "grad_norm": 0.816681444644928,
+      "learning_rate": 0.00017443517375622704,
+      "loss": 2.8826,
+      "step": 490
+    },
+    {
+      "epoch": 0.7836990595611285,
+      "grad_norm": 1.3913438320159912,
+      "learning_rate": 0.00017329422140254235,
+      "loss": 2.7449,
+      "step": 500
+    },
+    {
+      "epoch": 0.799373040752351,
+      "grad_norm": 0.30519339442253113,
+      "learning_rate": 0.0001721322698286354,
+      "loss": 2.7933,
+      "step": 510
+    },
+    {
+      "epoch": 0.8150470219435737,
+      "grad_norm": 0.3911365270614624,
+      "learning_rate": 0.0001709496519403823,
+      "loss": 2.8433,
+      "step": 520
+    },
+    {
+      "epoch": 0.8307210031347962,
+      "grad_norm": 0.5197113752365112,
+      "learning_rate": 0.00016974670656467824,
+      "loss": 2.828,
+      "step": 530
+    },
+    {
+      "epoch": 0.8463949843260188,
+      "grad_norm": 0.7463776469230652,
+      "learning_rate": 0.00016852377835236166,
+      "loss": 2.9549,
+      "step": 540
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.6616039276123047,
+      "learning_rate": 0.00016728121767946977,
+      "loss": 2.8843,
+      "step": 550
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.2525625228881836,
+      "learning_rate": 0.00016601938054685385,
+      "loss": 2.7715,
+      "step": 560
+    },
+    {
+      "epoch": 0.8934169278996865,
+      "grad_norm": 0.4268622100353241,
+      "learning_rate": 0.00016473862847818277,
+      "loss": 2.8196,
+      "step": 570
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5538944005966187,
+      "learning_rate": 0.00016343932841636456,
+      "loss": 2.8619,
+      "step": 580
+    },
+    {
+      "epoch": 0.9247648902821317,
+      "grad_norm": 0.7213597297668457,
+      "learning_rate": 0.00016212185261841499,
+      "loss": 2.9276,
+      "step": 590
+    },
+    {
+      "epoch": 0.9404388714733543,
+      "grad_norm": 1.6927486658096313,
+      "learning_rate": 0.00016078657854880376,
+      "loss": 2.7446,
+      "step": 600
+    },
+    {
+      "epoch": 0.9561128526645768,
+      "grad_norm": 0.3090650141239166,
+      "learning_rate": 0.000159433888771309,
+      "loss": 2.747,
+      "step": 610
+    },
+    {
+      "epoch": 0.9717868338557993,
+      "grad_norm": 0.4454885423183441,
+      "learning_rate": 0.00015806417083941002,
+      "loss": 2.8622,
+      "step": 620
+    },
+    {
+      "epoch": 0.987460815047022,
+      "grad_norm": 0.8089830279350281,
+      "learning_rate": 0.00015667781718525157,
+      "loss": 2.8568,
+      "step": 630
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.21911662817001343,
+      "learning_rate": 0.00015527522500720934,
+      "loss": 2.7012,
+      "step": 640
+    },
+    {
+      "epoch": 1.0188087774294672,
+      "grad_norm": 0.3196061849594116,
+      "learning_rate": 0.00015385679615609042,
+      "loss": 2.7127,
+      "step": 650
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.4679659605026245,
+      "learning_rate": 0.00015242293702000086,
+      "loss": 2.7103,
+      "step": 660
+    },
+    {
+      "epoch": 1.0501567398119123,
+      "grad_norm": 0.6506277322769165,
+      "learning_rate": 0.00015097405840791276,
+      "loss": 2.6762,
+      "step": 670
+    },
+    {
+      "epoch": 1.0658307210031348,
+      "grad_norm": 0.9151834845542908,
+      "learning_rate": 0.00014951057543196566,
+      "loss": 2.6503,
+      "step": 680
+    },
+    {
+      "epoch": 1.0815047021943573,
+      "grad_norm": 0.2834145724773407,
+      "learning_rate": 0.00014803290738853395,
+      "loss": 2.5103,
+      "step": 690
+    },
+    {
+      "epoch": 1.09717868338558,
+      "grad_norm": 0.3199128210544586,
+      "learning_rate": 0.00014654147763809637,
+      "loss": 2.7147,
+      "step": 700
+    },
+    {
+      "epoch": 1.1128526645768024,
+      "grad_norm": 0.5001178979873657,
+      "learning_rate": 0.00014503671348394057,
+      "loss": 2.7124,
+      "step": 710
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.6373796463012695,
+      "learning_rate": 0.0001435190460497384,
+      "loss": 2.7012,
+      "step": 720
+    },
+    {
+      "epoch": 1.1442006269592477,
+      "grad_norm": 0.9262835383415222,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 2.6493,
+      "step": 730
+    },
+    {
+      "epoch": 1.1598746081504703,
+      "grad_norm": 0.2955109775066376,
+      "learning_rate": 0.00014044674419562734,
+      "loss": 2.5023,
+      "step": 740
+    },
+    {
+      "epoch": 1.1755485893416928,
+      "grad_norm": 0.34623944759368896,
+      "learning_rate": 0.0001388929900080476,
+      "loss": 2.6849,
+      "step": 750
+    },
+    {
+      "epoch": 1.1912225705329154,
+      "grad_norm": 0.43281346559524536,
+      "learning_rate": 0.00013732809275288828,
+      "loss": 2.6655,
+      "step": 760
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.6403496265411377,
+      "learning_rate": 0.000135752500782304,
+      "loss": 2.6557,
+      "step": 770
+    },
+    {
+      "epoch": 1.2225705329153604,
+      "grad_norm": 0.8644494414329529,
+      "learning_rate": 0.00013416666551254748,
+      "loss": 2.6162,
+      "step": 780
+    },
+    {
+      "epoch": 1.238244514106583,
+      "grad_norm": 0.2673655152320862,
+      "learning_rate": 0.00013257104129463614,
+      "loss": 2.4991,
+      "step": 790
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.3414609432220459,
+      "learning_rate": 0.00013096608528417788,
+      "loss": 2.6638,
+      "step": 800
+    },
+    {
+      "epoch": 1.2695924764890283,
+      "grad_norm": 0.47588247060775757,
+      "learning_rate": 0.00012935225731039348,
+      "loss": 2.6465,
+      "step": 810
+    },
+    {
+      "epoch": 1.2852664576802508,
+      "grad_norm": 0.6843693852424622,
+      "learning_rate": 0.00012773001974437267,
+      "loss": 2.6697,
+      "step": 820
+    },
+    {
+      "epoch": 1.3009404388714734,
+      "grad_norm": 0.9213519096374512,
+      "learning_rate": 0.0001260998373666022,
+      "loss": 2.6691,
+      "step": 830
+    },
+    {
+      "epoch": 1.316614420062696,
+      "grad_norm": 0.26475438475608826,
+      "learning_rate": 0.0001244621772338036,
+      "loss": 2.5109,
+      "step": 840
+    },
+    {
+      "epoch": 1.3322884012539185,
+      "grad_norm": 0.3754674196243286,
+      "learning_rate": 0.0001228175085451186,
+      "loss": 2.6699,
+      "step": 850
+    },
+    {
+      "epoch": 1.347962382445141,
+      "grad_norm": 0.49352237582206726,
+      "learning_rate": 0.00012116630250768097,
+      "loss": 2.6889,
+      "step": 860
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.7134298086166382,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 2.6502,
+      "step": 870
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.9475263953208923,
+      "learning_rate": 0.00011784617244448451,
+      "loss": 2.6062,
+      "step": 880
+    },
+    {
+      "epoch": 1.3949843260188088,
+      "grad_norm": 0.2767506539821625,
+      "learning_rate": 0.0001161781996552765,
+      "loss": 2.4584,
+      "step": 890
+    },
+    {
+      "epoch": 1.4106583072100314,
+      "grad_norm": 0.38563597202301025,
+      "learning_rate": 0.00011450559171788269,
+      "loss": 2.6751,
+      "step": 900
+    },
+    {
+      "epoch": 1.426332288401254,
+      "grad_norm": 0.466782808303833,
+      "learning_rate": 0.00011282882784419398,
+      "loss": 2.6181,
+      "step": 910
+    },
+    {
+      "epoch": 1.4420062695924765,
+      "grad_norm": 0.7600008845329285,
+      "learning_rate": 0.00011114838843680095,
+      "loss": 2.6729,
+      "step": 920
+    },
+    {
+      "epoch": 1.457680250783699,
+      "grad_norm": 0.956167459487915,
+      "learning_rate": 0.0001094647549513561,
+      "loss": 2.5486,
+      "step": 930
+    },
+    {
+      "epoch": 1.4733542319749215,
+      "grad_norm": 0.257744699716568,
+      "learning_rate": 0.00010777840975863383,
+      "loss": 2.4545,
+      "step": 940
+    },
+    {
+      "epoch": 1.489028213166144,
+      "grad_norm": 0.347033828496933,
+      "learning_rate": 0.00010608983600632831,
+      "loss": 2.6313,
+      "step": 950
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.5105902552604675,
+      "learning_rate": 0.00010439951748062912,
+      "loss": 2.623,
+      "step": 960
+    },
+    {
+      "epoch": 1.5203761755485894,
+      "grad_norm": 0.7116357684135437,
+      "learning_rate": 0.00010270793846761347,
+      "loss": 2.6493,
+      "step": 970
+    },
+    {
+      "epoch": 1.536050156739812,
+      "grad_norm": 0.9367708563804626,
+      "learning_rate": 0.00010101558361449552,
+      "loss": 2.6081,
+      "step": 980
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.25939515233039856,
+      "learning_rate": 9.932293779077216e-05,
+      "loss": 2.4289,
+      "step": 990
+    },
+    {
+      "epoch": 1.567398119122257,
+      "grad_norm": 0.3675819933414459,
+      "learning_rate": 9.763048594930502e-05,
+      "loss": 2.6617,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1914,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8760263209474458e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad729f37531a1c2749c64acb68f56a57b1c0c8e47ff21416db8f780a21d903d
+size 5432

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+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

checkpoint-1500/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4bf096d2b3fe22594dd8336e74d09d3b84e3d8bcd6d23c538c54c3cf60d785
+size 184592616

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089491edbc4e56ac62eb31968485ec43fbddb6d1f4bd4ef4ba5b1986072da134
+size 92836436

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a2f1ea9ed8d1b1978dbecd0849d41dc23d82ac20d05ea41f1101d5fea053f6
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d602411eccad93d10c915e860b433ad004769feef93ab6c8bbdb88d26653d7e
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "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": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1090 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3510971786833856,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001567398119122257,
+      "grad_norm": 0.5552594661712646,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 3.3921,
+      "step": 1
+    },
+    {
+      "epoch": 0.01567398119122257,
+      "grad_norm": 0.660531222820282,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 3.5922,
+      "step": 10
+    },
+    {
+      "epoch": 0.03134796238244514,
+      "grad_norm": 0.5598097443580627,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 3.619,
+      "step": 20
+    },
+    {
+      "epoch": 0.047021943573667714,
+      "grad_norm": 0.5996779799461365,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 3.4824,
+      "step": 30
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 0.8172075152397156,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 3.3997,
+      "step": 40
+    },
+    {
+      "epoch": 0.07836990595611286,
+      "grad_norm": 1.6439019441604614,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 3.2485,
+      "step": 50
+    },
+    {
+      "epoch": 0.09404388714733543,
+      "grad_norm": 0.28180772066116333,
+      "learning_rate": 0.00019999942697524717,
+      "loss": 2.9975,
+      "step": 60
+    },
+    {
+      "epoch": 0.109717868338558,
+      "grad_norm": 0.3870689868927002,
+      "learning_rate": 0.00019997937179843937,
+      "loss": 3.0446,
+      "step": 70
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.575548529624939,
+      "learning_rate": 0.00019993067195079803,
+      "loss": 3.0178,
+      "step": 80
+    },
+    {
+      "epoch": 0.14106583072100312,
+      "grad_norm": 0.781446635723114,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 3.0394,
+      "step": 90
+    },
+    {
+      "epoch": 0.15673981191222572,
+      "grad_norm": 1.725696325302124,
+      "learning_rate": 0.00019974740225703878,
+      "loss": 3.0751,
+      "step": 100
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.2845414876937866,
+      "learning_rate": 0.00019961288491875278,
+      "loss": 2.9291,
+      "step": 110
+    },
+    {
+      "epoch": 0.18808777429467086,
+      "grad_norm": 0.36810651421546936,
+      "learning_rate": 0.00019944982791025333,
+      "loss": 2.9491,
+      "step": 120
+    },
+    {
+      "epoch": 0.20376175548589343,
+      "grad_norm": 0.5454439520835876,
+      "learning_rate": 0.00019925827794832056,
+      "loss": 3.0337,
+      "step": 130
+    },
+    {
+      "epoch": 0.219435736677116,
+      "grad_norm": 0.6503669619560242,
+      "learning_rate": 0.00019903828991313138,
+      "loss": 3.0246,
+      "step": 140
+    },
+    {
+      "epoch": 0.23510971786833856,
+      "grad_norm": 1.4392451047897339,
+      "learning_rate": 0.00019878992683253582,
+      "loss": 3.0232,
+      "step": 150
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.2859440743923187,
+      "learning_rate": 0.00019851325986399934,
+      "loss": 2.8955,
+      "step": 160
+    },
+    {
+      "epoch": 0.2664576802507837,
+      "grad_norm": 0.44268104434013367,
+      "learning_rate": 0.0001982083682742156,
+      "loss": 2.9338,
+      "step": 170
+    },
+    {
+      "epoch": 0.28213166144200624,
+      "grad_norm": 0.5128395557403564,
+      "learning_rate": 0.00019787533941639638,
+      "loss": 3.0089,
+      "step": 180
+    },
+    {
+      "epoch": 0.29780564263322884,
+      "grad_norm": 0.7328920364379883,
+      "learning_rate": 0.00019751426870524407,
+      "loss": 3.0157,
+      "step": 190
+    },
+    {
+      "epoch": 0.31347962382445144,
+      "grad_norm": 1.5265012979507446,
+      "learning_rate": 0.000197125259589615,
+      "loss": 2.9007,
+      "step": 200
+    },
+    {
+      "epoch": 0.329153605015674,
+      "grad_norm": 0.2766813635826111,
+      "learning_rate": 0.0001967084235228807,
+      "loss": 2.8275,
+      "step": 210
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.36695396900177,
+      "learning_rate": 0.00019626387993099579,
+      "loss": 2.9158,
+      "step": 220
+    },
+    {
+      "epoch": 0.3605015673981191,
+      "grad_norm": 0.5359162092208862,
+      "learning_rate": 0.00019579175617828187,
+      "loss": 2.9465,
+      "step": 230
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.6529833674430847,
+      "learning_rate": 0.0001952921875309368,
+      "loss": 2.981,
+      "step": 240
+    },
+    {
+      "epoch": 0.39184952978056425,
+      "grad_norm": 1.5314627885818481,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 2.9737,
+      "step": 250
+    },
+    {
+      "epoch": 0.40752351097178685,
+      "grad_norm": 0.2949506342411041,
+      "learning_rate": 0.00019421129589174618,
+      "loss": 2.8208,
+      "step": 260
+    },
+    {
+      "epoch": 0.4231974921630094,
+      "grad_norm": 0.39567869901657104,
+      "learning_rate": 0.00019363028258163447,
+      "loss": 2.8557,
+      "step": 270
+    },
+    {
+      "epoch": 0.438871473354232,
+      "grad_norm": 0.5587254166603088,
+      "learning_rate": 0.00019302244365163376,
+      "loss": 2.9494,
+      "step": 280
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.7218978404998779,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 2.9742,
+      "step": 290
+    },
+    {
+      "epoch": 0.4702194357366771,
+      "grad_norm": 1.4482598304748535,
+      "learning_rate": 0.0001917269931653049,
+      "loss": 2.8646,
+      "step": 300
+    },
+    {
+      "epoch": 0.48589341692789967,
+      "grad_norm": 0.2901701033115387,
+      "learning_rate": 0.00019103975276306678,
+      "loss": 2.7788,
+      "step": 310
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.4310539960861206,
+      "learning_rate": 0.00019032642894278192,
+      "loss": 2.8655,
+      "step": 320
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.5589954853057861,
+      "learning_rate": 0.0001895872260758688,
+      "loss": 2.914,
+      "step": 330
+    },
+    {
+      "epoch": 0.5329153605015674,
+      "grad_norm": 0.7243526577949524,
+      "learning_rate": 0.00018882235594824308,
+      "loss": 2.9191,
+      "step": 340
+    },
+    {
+      "epoch": 0.54858934169279,
+      "grad_norm": 1.4200222492218018,
+      "learning_rate": 0.00018803203769963967,
+      "loss": 2.8128,
+      "step": 350
+    },
+    {
+      "epoch": 0.5642633228840125,
+      "grad_norm": 0.26594147086143494,
+      "learning_rate": 0.000187216497760828,
+      "loss": 2.762,
+      "step": 360
+    },
+    {
+      "epoch": 0.5799373040752351,
+      "grad_norm": 0.3894258439540863,
+      "learning_rate": 0.00018637596978873835,
+      "loss": 2.9077,
+      "step": 370
+    },
+    {
+      "epoch": 0.5956112852664577,
+      "grad_norm": 0.5348561406135559,
+      "learning_rate": 0.00018551069459951758,
+      "loss": 2.9292,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112852664576802,
+      "grad_norm": 0.746507465839386,
+      "learning_rate": 0.00018462092009953408,
+      "loss": 2.8795,
+      "step": 390
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 1.5225753784179688,
+      "learning_rate": 0.0001837069012143511,
+      "loss": 2.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.6426332288401254,
+      "grad_norm": 0.26905450224876404,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 2.7218,
+      "step": 410
+    },
+    {
+      "epoch": 0.658307210031348,
+      "grad_norm": 0.3912515342235565,
+      "learning_rate": 0.00018180718464639787,
+      "loss": 2.819,
+      "step": 420
+    },
+    {
+      "epoch": 0.6739811912225705,
+      "grad_norm": 0.5661373138427734,
+      "learning_rate": 0.00018082203124346045,
+      "loss": 2.8772,
+      "step": 430
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.805776059627533,
+      "learning_rate": 0.0001798137218590498,
+      "loss": 2.9562,
+      "step": 440
+    },
+    {
+      "epoch": 0.7053291536050157,
+      "grad_norm": 1.4879732131958008,
+      "learning_rate": 0.00017878254537966216,
+      "loss": 2.7925,
+      "step": 450
+    },
+    {
+      "epoch": 0.7210031347962382,
+      "grad_norm": 0.28762391209602356,
+      "learning_rate": 0.00017772879724334937,
+      "loss": 2.8006,
+      "step": 460
+    },
+    {
+      "epoch": 0.7366771159874608,
+      "grad_norm": 0.41769474744796753,
+      "learning_rate": 0.00017665277935507398,
+      "loss": 2.8148,
+      "step": 470
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.633671760559082,
+      "learning_rate": 0.00017555480000021198,
+      "loss": 2.8461,
+      "step": 480
+    },
+    {
+      "epoch": 0.768025078369906,
+      "grad_norm": 0.816681444644928,
+      "learning_rate": 0.00017443517375622704,
+      "loss": 2.8826,
+      "step": 490
+    },
+    {
+      "epoch": 0.7836990595611285,
+      "grad_norm": 1.3913438320159912,
+      "learning_rate": 0.00017329422140254235,
+      "loss": 2.7449,
+      "step": 500
+    },
+    {
+      "epoch": 0.799373040752351,
+      "grad_norm": 0.30519339442253113,
+      "learning_rate": 0.0001721322698286354,
+      "loss": 2.7933,
+      "step": 510
+    },
+    {
+      "epoch": 0.8150470219435737,
+      "grad_norm": 0.3911365270614624,
+      "learning_rate": 0.0001709496519403823,
+      "loss": 2.8433,
+      "step": 520
+    },
+    {
+      "epoch": 0.8307210031347962,
+      "grad_norm": 0.5197113752365112,
+      "learning_rate": 0.00016974670656467824,
+      "loss": 2.828,
+      "step": 530
+    },
+    {
+      "epoch": 0.8463949843260188,
+      "grad_norm": 0.7463776469230652,
+      "learning_rate": 0.00016852377835236166,
+      "loss": 2.9549,
+      "step": 540
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.6616039276123047,
+      "learning_rate": 0.00016728121767946977,
+      "loss": 2.8843,
+      "step": 550
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.2525625228881836,
+      "learning_rate": 0.00016601938054685385,
+      "loss": 2.7715,
+      "step": 560
+    },
+    {
+      "epoch": 0.8934169278996865,
+      "grad_norm": 0.4268622100353241,
+      "learning_rate": 0.00016473862847818277,
+      "loss": 2.8196,
+      "step": 570
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5538944005966187,
+      "learning_rate": 0.00016343932841636456,
+      "loss": 2.8619,
+      "step": 580
+    },
+    {
+      "epoch": 0.9247648902821317,
+      "grad_norm": 0.7213597297668457,
+      "learning_rate": 0.00016212185261841499,
+      "loss": 2.9276,
+      "step": 590
+    },
+    {
+      "epoch": 0.9404388714733543,
+      "grad_norm": 1.6927486658096313,
+      "learning_rate": 0.00016078657854880376,
+      "loss": 2.7446,
+      "step": 600
+    },
+    {
+      "epoch": 0.9561128526645768,
+      "grad_norm": 0.3090650141239166,
+      "learning_rate": 0.000159433888771309,
+      "loss": 2.747,
+      "step": 610
+    },
+    {
+      "epoch": 0.9717868338557993,
+      "grad_norm": 0.4454885423183441,
+      "learning_rate": 0.00015806417083941002,
+      "loss": 2.8622,
+      "step": 620
+    },
+    {
+      "epoch": 0.987460815047022,
+      "grad_norm": 0.8089830279350281,
+      "learning_rate": 0.00015667781718525157,
+      "loss": 2.8568,
+      "step": 630
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.21911662817001343,
+      "learning_rate": 0.00015527522500720934,
+      "loss": 2.7012,
+      "step": 640
+    },
+    {
+      "epoch": 1.0188087774294672,
+      "grad_norm": 0.3196061849594116,
+      "learning_rate": 0.00015385679615609042,
+      "loss": 2.7127,
+      "step": 650
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.4679659605026245,
+      "learning_rate": 0.00015242293702000086,
+      "loss": 2.7103,
+      "step": 660
+    },
+    {
+      "epoch": 1.0501567398119123,
+      "grad_norm": 0.6506277322769165,
+      "learning_rate": 0.00015097405840791276,
+      "loss": 2.6762,
+      "step": 670
+    },
+    {
+      "epoch": 1.0658307210031348,
+      "grad_norm": 0.9151834845542908,
+      "learning_rate": 0.00014951057543196566,
+      "loss": 2.6503,
+      "step": 680
+    },
+    {
+      "epoch": 1.0815047021943573,
+      "grad_norm": 0.2834145724773407,
+      "learning_rate": 0.00014803290738853395,
+      "loss": 2.5103,
+      "step": 690
+    },
+    {
+      "epoch": 1.09717868338558,
+      "grad_norm": 0.3199128210544586,
+      "learning_rate": 0.00014654147763809637,
+      "loss": 2.7147,
+      "step": 700
+    },
+    {
+      "epoch": 1.1128526645768024,
+      "grad_norm": 0.5001178979873657,
+      "learning_rate": 0.00014503671348394057,
+      "loss": 2.7124,
+      "step": 710
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.6373796463012695,
+      "learning_rate": 0.0001435190460497384,
+      "loss": 2.7012,
+      "step": 720
+    },
+    {
+      "epoch": 1.1442006269592477,
+      "grad_norm": 0.9262835383415222,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 2.6493,
+      "step": 730
+    },
+    {
+      "epoch": 1.1598746081504703,
+      "grad_norm": 0.2955109775066376,
+      "learning_rate": 0.00014044674419562734,
+      "loss": 2.5023,
+      "step": 740
+    },
+    {
+      "epoch": 1.1755485893416928,
+      "grad_norm": 0.34623944759368896,
+      "learning_rate": 0.0001388929900080476,
+      "loss": 2.6849,
+      "step": 750
+    },
+    {
+      "epoch": 1.1912225705329154,
+      "grad_norm": 0.43281346559524536,
+      "learning_rate": 0.00013732809275288828,
+      "loss": 2.6655,
+      "step": 760
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.6403496265411377,
+      "learning_rate": 0.000135752500782304,
+      "loss": 2.6557,
+      "step": 770
+    },
+    {
+      "epoch": 1.2225705329153604,
+      "grad_norm": 0.8644494414329529,
+      "learning_rate": 0.00013416666551254748,
+      "loss": 2.6162,
+      "step": 780
+    },
+    {
+      "epoch": 1.238244514106583,
+      "grad_norm": 0.2673655152320862,
+      "learning_rate": 0.00013257104129463614,
+      "loss": 2.4991,
+      "step": 790
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.3414609432220459,
+      "learning_rate": 0.00013096608528417788,
+      "loss": 2.6638,
+      "step": 800
+    },
+    {
+      "epoch": 1.2695924764890283,
+      "grad_norm": 0.47588247060775757,
+      "learning_rate": 0.00012935225731039348,
+      "loss": 2.6465,
+      "step": 810
+    },
+    {
+      "epoch": 1.2852664576802508,
+      "grad_norm": 0.6843693852424622,
+      "learning_rate": 0.00012773001974437267,
+      "loss": 2.6697,
+      "step": 820
+    },
+    {
+      "epoch": 1.3009404388714734,
+      "grad_norm": 0.9213519096374512,
+      "learning_rate": 0.0001260998373666022,
+      "loss": 2.6691,
+      "step": 830
+    },
+    {
+      "epoch": 1.316614420062696,
+      "grad_norm": 0.26475438475608826,
+      "learning_rate": 0.0001244621772338036,
+      "loss": 2.5109,
+      "step": 840
+    },
+    {
+      "epoch": 1.3322884012539185,
+      "grad_norm": 0.3754674196243286,
+      "learning_rate": 0.0001228175085451186,
+      "loss": 2.6699,
+      "step": 850
+    },
+    {
+      "epoch": 1.347962382445141,
+      "grad_norm": 0.49352237582206726,
+      "learning_rate": 0.00012116630250768097,
+      "loss": 2.6889,
+      "step": 860
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.7134298086166382,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 2.6502,
+      "step": 870
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.9475263953208923,
+      "learning_rate": 0.00011784617244448451,
+      "loss": 2.6062,
+      "step": 880
+    },
+    {
+      "epoch": 1.3949843260188088,
+      "grad_norm": 0.2767506539821625,
+      "learning_rate": 0.0001161781996552765,
+      "loss": 2.4584,
+      "step": 890
+    },
+    {
+      "epoch": 1.4106583072100314,
+      "grad_norm": 0.38563597202301025,
+      "learning_rate": 0.00011450559171788269,
+      "loss": 2.6751,
+      "step": 900
+    },
+    {
+      "epoch": 1.426332288401254,
+      "grad_norm": 0.466782808303833,
+      "learning_rate": 0.00011282882784419398,
+      "loss": 2.6181,
+      "step": 910
+    },
+    {
+      "epoch": 1.4420062695924765,
+      "grad_norm": 0.7600008845329285,
+      "learning_rate": 0.00011114838843680095,
+      "loss": 2.6729,
+      "step": 920
+    },
+    {
+      "epoch": 1.457680250783699,
+      "grad_norm": 0.956167459487915,
+      "learning_rate": 0.0001094647549513561,
+      "loss": 2.5486,
+      "step": 930
+    },
+    {
+      "epoch": 1.4733542319749215,
+      "grad_norm": 0.257744699716568,
+      "learning_rate": 0.00010777840975863383,
+      "loss": 2.4545,
+      "step": 940
+    },
+    {
+      "epoch": 1.489028213166144,
+      "grad_norm": 0.347033828496933,
+      "learning_rate": 0.00010608983600632831,
+      "loss": 2.6313,
+      "step": 950
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.5105902552604675,
+      "learning_rate": 0.00010439951748062912,
+      "loss": 2.623,
+      "step": 960
+    },
+    {
+      "epoch": 1.5203761755485894,
+      "grad_norm": 0.7116357684135437,
+      "learning_rate": 0.00010270793846761347,
+      "loss": 2.6493,
+      "step": 970
+    },
+    {
+      "epoch": 1.536050156739812,
+      "grad_norm": 0.9367708563804626,
+      "learning_rate": 0.00010101558361449552,
+      "loss": 2.6081,
+      "step": 980
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.25939515233039856,
+      "learning_rate": 9.932293779077216e-05,
+      "loss": 2.4289,
+      "step": 990
+    },
+    {
+      "epoch": 1.567398119122257,
+      "grad_norm": 0.3675819933414459,
+      "learning_rate": 9.763048594930502e-05,
+      "loss": 2.6617,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5830721003134798,
+      "grad_norm": 0.47927770018577576,
+      "learning_rate": 9.59387129873787e-05,
+      "loss": 2.661,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5987460815047023,
+      "grad_norm": 0.6929473876953125,
+      "learning_rate": 9.42481036077749e-05,
+      "loss": 2.6103,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6144200626959249,
+      "grad_norm": 0.9767149090766907,
+      "learning_rate": 9.255914217990211e-05,
+      "loss": 2.5943,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.24275819957256317,
+      "learning_rate": 9.08723126010212e-05,
+      "loss": 2.4676,
+      "step": 1040
+    },
+    {
+      "epoch": 1.64576802507837,
+      "grad_norm": 0.3554080128669739,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 2.6107,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6614420062695925,
+      "grad_norm": 0.5181464552879333,
+      "learning_rate": 8.750698138687827e-05,
+      "loss": 2.617,
+      "step": 1060
+    },
+    {
+      "epoch": 1.677115987460815,
+      "grad_norm": 0.7479755282402039,
+      "learning_rate": 8.582944393855941e-05,
+      "loss": 2.6401,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6927899686520376,
+      "grad_norm": 0.9864292740821838,
+      "learning_rate": 8.415596643687363e-05,
+      "loss": 2.6327,
+      "step": 1080
+    },
+    {
+      "epoch": 1.70846394984326,
+      "grad_norm": 0.24126508831977844,
+      "learning_rate": 8.248702834284693e-05,
+      "loss": 2.4569,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.3491465449333191,
+      "learning_rate": 8.082310781693865e-05,
+      "loss": 2.6473,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7398119122257052,
+      "grad_norm": 0.5092320442199707,
+      "learning_rate": 7.916468158204576e-05,
+      "loss": 2.6587,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.6617609262466431,
+      "learning_rate": 7.751222478691884e-05,
+      "loss": 2.6862,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7711598746081505,
+      "grad_norm": 1.0016579627990723,
+      "learning_rate": 7.586621087002945e-05,
+      "loss": 2.6226,
+      "step": 1130
+    },
+    {
+      "epoch": 1.786833855799373,
+      "grad_norm": 0.2429930418729782,
+      "learning_rate": 7.422711142392695e-05,
+      "loss": 2.5479,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8025078369905956,
+      "grad_norm": 0.396308034658432,
+      "learning_rate": 7.259539606012478e-05,
+      "loss": 2.6005,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5580389499664307,
+      "learning_rate": 7.097153227455379e-05,
+      "loss": 2.6714,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8338557993730409,
+      "grad_norm": 0.7043899893760681,
+      "learning_rate": 6.93559853136221e-05,
+      "loss": 2.6417,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8495297805642634,
+      "grad_norm": 0.9616154432296753,
+      "learning_rate": 6.774921804091934e-05,
+      "loss": 2.5572,
+      "step": 1180
+    },
+    {
+      "epoch": 1.865203761755486,
+      "grad_norm": 0.2324633002281189,
+      "learning_rate": 6.615169080460331e-05,
+      "loss": 2.4474,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.3579946756362915,
+      "learning_rate": 6.456386130550782e-05,
+      "loss": 2.6281,
+      "step": 1200
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.5167599320411682,
+      "learning_rate": 6.298618446600856e-05,
+      "loss": 2.6397,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9122257053291536,
+      "grad_norm": 0.7201157808303833,
+      "learning_rate": 6.141911229968533e-05,
+      "loss": 2.6389,
+      "step": 1220
+    },
+    {
+      "epoch": 1.9278996865203761,
+      "grad_norm": 1.1355105638504028,
+      "learning_rate": 5.9863093781817394e-05,
+      "loss": 2.6135,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9435736677115987,
+      "grad_norm": 0.2417139708995819,
+      "learning_rate": 5.831857472074956e-05,
+      "loss": 2.456,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9592476489028212,
+      "grad_norm": 0.4348711669445038,
+      "learning_rate": 5.6785997630165435e-05,
+      "loss": 2.6756,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9749216300940438,
+      "grad_norm": 0.6851107478141785,
+      "learning_rate": 5.526580160230476e-05,
+      "loss": 2.6338,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9905956112852663,
+      "grad_norm": 1.0602185726165771,
+      "learning_rate": 5.375842218216076e-05,
+      "loss": 2.5925,
+      "step": 1270
+    },
+    {
+      "epoch": 2.006269592476489,
+      "grad_norm": 0.23286418616771698,
+      "learning_rate": 5.226429124269423e-05,
+      "loss": 2.4199,
+      "step": 1280
+    },
+    {
+      "epoch": 2.0219435736677114,
+      "grad_norm": 0.41238126158714294,
+      "learning_rate": 5.078383686109926e-05,
+      "loss": 2.5441,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0376175548589344,
+      "grad_norm": 0.5980674624443054,
+      "learning_rate": 4.931748319615656e-05,
+      "loss": 2.5002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.053291536050157,
+      "grad_norm": 0.8170694708824158,
+      "learning_rate": 4.786565036670972e-05,
+      "loss": 2.4228,
+      "step": 1310
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 1.1204980611801147,
+      "learning_rate": 4.642875433129854e-05,
+      "loss": 2.3089,
+      "step": 1320
+    },
+    {
+      "epoch": 2.084639498432602,
+      "grad_norm": 0.28670328855514526,
+      "learning_rate": 4.500720676898452e-05,
+      "loss": 2.2163,
+      "step": 1330
+    },
+    {
+      "epoch": 2.1003134796238245,
+      "grad_norm": 0.45365315675735474,
+      "learning_rate": 4.36014149614026e-05,
+      "loss": 2.5476,
+      "step": 1340
+    },
+    {
+      "epoch": 2.115987460815047,
+      "grad_norm": 0.589374840259552,
+      "learning_rate": 4.221178167607226e-05,
+      "loss": 2.4646,
+      "step": 1350
+    },
+    {
+      "epoch": 2.1316614420062696,
+      "grad_norm": 0.9127137064933777,
+      "learning_rate": 4.083870505100263e-05,
+      "loss": 2.3819,
+      "step": 1360
+    },
+    {
+      "epoch": 2.147335423197492,
+      "grad_norm": 1.167529582977295,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 2.3445,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1630094043887147,
+      "grad_norm": 0.26559045910835266,
+      "learning_rate": 3.8143790503075403e-05,
+      "loss": 2.228,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1786833855799372,
+      "grad_norm": 0.5015429258346558,
+      "learning_rate": 3.6822724688891416e-05,
+      "loss": 2.5579,
+      "step": 1390
+    },
+    {
+      "epoch": 2.19435736677116,
+      "grad_norm": 0.7187398672103882,
+      "learning_rate": 3.551975953110177e-05,
+      "loss": 2.4841,
+      "step": 1400
+    },
+    {
+      "epoch": 2.2100313479623823,
+      "grad_norm": 0.872721791267395,
+      "learning_rate": 3.423526833679355e-05,
+      "loss": 2.418,
+      "step": 1410
+    },
+    {
+      "epoch": 2.225705329153605,
+      "grad_norm": 1.3087424039840698,
+      "learning_rate": 3.296961912015598e-05,
+      "loss": 2.2849,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.31001710891723633,
+      "learning_rate": 3.172317449704216e-05,
+      "loss": 2.2705,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2570532915360504,
+      "grad_norm": 0.47308361530303955,
+      "learning_rate": 3.0496291581077673e-05,
+      "loss": 2.5207,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6600085496902466,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.4747,
+      "step": 1450
+    },
+    {
+      "epoch": 2.2884012539184955,
+      "grad_norm": 0.8648523092269897,
+      "learning_rate": 2.8102611201675598e-05,
+      "loss": 2.4407,
+      "step": 1460
+    },
+    {
+      "epoch": 2.304075235109718,
+      "grad_norm": 1.2338064908981323,
+      "learning_rate": 2.6936499541572445e-05,
+      "loss": 2.3066,
+      "step": 1470
+    },
+    {
+      "epoch": 2.3197492163009406,
+      "grad_norm": 0.2991880476474762,
+      "learning_rate": 2.5791320998800695e-05,
+      "loss": 2.2581,
+      "step": 1480
+    },
+    {
+      "epoch": 2.335423197492163,
+      "grad_norm": 0.48960086703300476,
+      "learning_rate": 2.4667403673665623e-05,
+      "loss": 2.5032,
+      "step": 1490
+    },
+    {
+      "epoch": 2.3510971786833856,
+      "grad_norm": 0.6952352523803711,
+      "learning_rate": 2.3565069575010035e-05,
+      "loss": 2.4815,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1914,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.797148359776338e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad729f37531a1c2749c64acb68f56a57b1c0c8e47ff21416db8f780a21d903d
+size 5432

checkpoint-1914/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+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

checkpoint-1914/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1914/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d372471e86dddfe3fd923d34818731d26ee14eeed16c64cbf70cb18e85187d
+size 184592616

checkpoint-1914/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a97ec0878fada10b751cc15713d911bbdb9edcf2978188f88ea246038b8f8da
+size 92836436

checkpoint-1914/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26be4df30e2b35c9c4864c65062413f0eb502c19abbe21bd7af8892ebb92de5e
+size 14244

checkpoint-1914/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdc7520c9aaea7e9c6241b157163f11a2809d069574b57f4f92289403f222ac
+size 1064

checkpoint-1914/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1914/tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "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": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-1914/trainer_state.json

@@ -0,0 +1,1377 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1914,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001567398119122257,
+      "grad_norm": 0.5552594661712646,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 3.3921,
+      "step": 1
+    },
+    {
+      "epoch": 0.01567398119122257,
+      "grad_norm": 0.660531222820282,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 3.5922,
+      "step": 10
+    },
+    {
+      "epoch": 0.03134796238244514,
+      "grad_norm": 0.5598097443580627,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 3.619,
+      "step": 20
+    },
+    {
+      "epoch": 0.047021943573667714,
+      "grad_norm": 0.5996779799461365,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 3.4824,
+      "step": 30
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 0.8172075152397156,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 3.3997,
+      "step": 40
+    },
+    {
+      "epoch": 0.07836990595611286,
+      "grad_norm": 1.6439019441604614,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 3.2485,
+      "step": 50
+    },
+    {
+      "epoch": 0.09404388714733543,
+      "grad_norm": 0.28180772066116333,
+      "learning_rate": 0.00019999942697524717,
+      "loss": 2.9975,
+      "step": 60
+    },
+    {
+      "epoch": 0.109717868338558,
+      "grad_norm": 0.3870689868927002,
+      "learning_rate": 0.00019997937179843937,
+      "loss": 3.0446,
+      "step": 70
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.575548529624939,
+      "learning_rate": 0.00019993067195079803,
+      "loss": 3.0178,
+      "step": 80
+    },
+    {
+      "epoch": 0.14106583072100312,
+      "grad_norm": 0.781446635723114,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 3.0394,
+      "step": 90
+    },
+    {
+      "epoch": 0.15673981191222572,
+      "grad_norm": 1.725696325302124,
+      "learning_rate": 0.00019974740225703878,
+      "loss": 3.0751,
+      "step": 100
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.2845414876937866,
+      "learning_rate": 0.00019961288491875278,
+      "loss": 2.9291,
+      "step": 110
+    },
+    {
+      "epoch": 0.18808777429467086,
+      "grad_norm": 0.36810651421546936,
+      "learning_rate": 0.00019944982791025333,
+      "loss": 2.9491,
+      "step": 120
+    },
+    {
+      "epoch": 0.20376175548589343,
+      "grad_norm": 0.5454439520835876,
+      "learning_rate": 0.00019925827794832056,
+      "loss": 3.0337,
+      "step": 130
+    },
+    {
+      "epoch": 0.219435736677116,
+      "grad_norm": 0.6503669619560242,
+      "learning_rate": 0.00019903828991313138,
+      "loss": 3.0246,
+      "step": 140
+    },
+    {
+      "epoch": 0.23510971786833856,
+      "grad_norm": 1.4392451047897339,
+      "learning_rate": 0.00019878992683253582,
+      "loss": 3.0232,
+      "step": 150
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.2859440743923187,
+      "learning_rate": 0.00019851325986399934,
+      "loss": 2.8955,
+      "step": 160
+    },
+    {
+      "epoch": 0.2664576802507837,
+      "grad_norm": 0.44268104434013367,
+      "learning_rate": 0.0001982083682742156,
+      "loss": 2.9338,
+      "step": 170
+    },
+    {
+      "epoch": 0.28213166144200624,
+      "grad_norm": 0.5128395557403564,
+      "learning_rate": 0.00019787533941639638,
+      "loss": 3.0089,
+      "step": 180
+    },
+    {
+      "epoch": 0.29780564263322884,
+      "grad_norm": 0.7328920364379883,
+      "learning_rate": 0.00019751426870524407,
+      "loss": 3.0157,
+      "step": 190
+    },
+    {
+      "epoch": 0.31347962382445144,
+      "grad_norm": 1.5265012979507446,
+      "learning_rate": 0.000197125259589615,
+      "loss": 2.9007,
+      "step": 200
+    },
+    {
+      "epoch": 0.329153605015674,
+      "grad_norm": 0.2766813635826111,
+      "learning_rate": 0.0001967084235228807,
+      "loss": 2.8275,
+      "step": 210
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.36695396900177,
+      "learning_rate": 0.00019626387993099579,
+      "loss": 2.9158,
+      "step": 220
+    },
+    {
+      "epoch": 0.3605015673981191,
+      "grad_norm": 0.5359162092208862,
+      "learning_rate": 0.00019579175617828187,
+      "loss": 2.9465,
+      "step": 230
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.6529833674430847,
+      "learning_rate": 0.0001952921875309368,
+      "loss": 2.981,
+      "step": 240
+    },
+    {
+      "epoch": 0.39184952978056425,
+      "grad_norm": 1.5314627885818481,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 2.9737,
+      "step": 250
+    },
+    {
+      "epoch": 0.40752351097178685,
+      "grad_norm": 0.2949506342411041,
+      "learning_rate": 0.00019421129589174618,
+      "loss": 2.8208,
+      "step": 260
+    },
+    {
+      "epoch": 0.4231974921630094,
+      "grad_norm": 0.39567869901657104,
+      "learning_rate": 0.00019363028258163447,
+      "loss": 2.8557,
+      "step": 270
+    },
+    {
+      "epoch": 0.438871473354232,
+      "grad_norm": 0.5587254166603088,
+      "learning_rate": 0.00019302244365163376,
+      "loss": 2.9494,
+      "step": 280
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.7218978404998779,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 2.9742,
+      "step": 290
+    },
+    {
+      "epoch": 0.4702194357366771,
+      "grad_norm": 1.4482598304748535,
+      "learning_rate": 0.0001917269931653049,
+      "loss": 2.8646,
+      "step": 300
+    },
+    {
+      "epoch": 0.48589341692789967,
+      "grad_norm": 0.2901701033115387,
+      "learning_rate": 0.00019103975276306678,
+      "loss": 2.7788,
+      "step": 310
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.4310539960861206,
+      "learning_rate": 0.00019032642894278192,
+      "loss": 2.8655,
+      "step": 320
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.5589954853057861,
+      "learning_rate": 0.0001895872260758688,
+      "loss": 2.914,
+      "step": 330
+    },
+    {
+      "epoch": 0.5329153605015674,
+      "grad_norm": 0.7243526577949524,
+      "learning_rate": 0.00018882235594824308,
+      "loss": 2.9191,
+      "step": 340
+    },
+    {
+      "epoch": 0.54858934169279,
+      "grad_norm": 1.4200222492218018,
+      "learning_rate": 0.00018803203769963967,
+      "loss": 2.8128,
+      "step": 350
+    },
+    {
+      "epoch": 0.5642633228840125,
+      "grad_norm": 0.26594147086143494,
+      "learning_rate": 0.000187216497760828,
+      "loss": 2.762,
+      "step": 360
+    },
+    {
+      "epoch": 0.5799373040752351,
+      "grad_norm": 0.3894258439540863,
+      "learning_rate": 0.00018637596978873835,
+      "loss": 2.9077,
+      "step": 370
+    },
+    {
+      "epoch": 0.5956112852664577,
+      "grad_norm": 0.5348561406135559,
+      "learning_rate": 0.00018551069459951758,
+      "loss": 2.9292,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112852664576802,
+      "grad_norm": 0.746507465839386,
+      "learning_rate": 0.00018462092009953408,
+      "loss": 2.8795,
+      "step": 390
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 1.5225753784179688,
+      "learning_rate": 0.0001837069012143511,
+      "loss": 2.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.6426332288401254,
+      "grad_norm": 0.26905450224876404,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 2.7218,
+      "step": 410
+    },
+    {
+      "epoch": 0.658307210031348,
+      "grad_norm": 0.3912515342235565,
+      "learning_rate": 0.00018180718464639787,
+      "loss": 2.819,
+      "step": 420
+    },
+    {
+      "epoch": 0.6739811912225705,
+      "grad_norm": 0.5661373138427734,
+      "learning_rate": 0.00018082203124346045,
+      "loss": 2.8772,
+      "step": 430
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.805776059627533,
+      "learning_rate": 0.0001798137218590498,
+      "loss": 2.9562,
+      "step": 440
+    },
+    {
+      "epoch": 0.7053291536050157,
+      "grad_norm": 1.4879732131958008,
+      "learning_rate": 0.00017878254537966216,
+      "loss": 2.7925,
+      "step": 450
+    },
+    {
+      "epoch": 0.7210031347962382,
+      "grad_norm": 0.28762391209602356,
+      "learning_rate": 0.00017772879724334937,
+      "loss": 2.8006,
+      "step": 460
+    },
+    {
+      "epoch": 0.7366771159874608,
+      "grad_norm": 0.41769474744796753,
+      "learning_rate": 0.00017665277935507398,
+      "loss": 2.8148,
+      "step": 470
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.633671760559082,
+      "learning_rate": 0.00017555480000021198,
+      "loss": 2.8461,
+      "step": 480
+    },
+    {
+      "epoch": 0.768025078369906,
+      "grad_norm": 0.816681444644928,
+      "learning_rate": 0.00017443517375622704,
+      "loss": 2.8826,
+      "step": 490
+    },
+    {
+      "epoch": 0.7836990595611285,
+      "grad_norm": 1.3913438320159912,
+      "learning_rate": 0.00017329422140254235,
+      "loss": 2.7449,
+      "step": 500
+    },
+    {
+      "epoch": 0.799373040752351,
+      "grad_norm": 0.30519339442253113,
+      "learning_rate": 0.0001721322698286354,
+      "loss": 2.7933,
+      "step": 510
+    },
+    {
+      "epoch": 0.8150470219435737,
+      "grad_norm": 0.3911365270614624,
+      "learning_rate": 0.0001709496519403823,
+      "loss": 2.8433,
+      "step": 520
+    },
+    {
+      "epoch": 0.8307210031347962,
+      "grad_norm": 0.5197113752365112,
+      "learning_rate": 0.00016974670656467824,
+      "loss": 2.828,
+      "step": 530
+    },
+    {
+      "epoch": 0.8463949843260188,
+      "grad_norm": 0.7463776469230652,
+      "learning_rate": 0.00016852377835236166,
+      "loss": 2.9549,
+      "step": 540
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.6616039276123047,
+      "learning_rate": 0.00016728121767946977,
+      "loss": 2.8843,
+      "step": 550
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.2525625228881836,
+      "learning_rate": 0.00016601938054685385,
+      "loss": 2.7715,
+      "step": 560
+    },
+    {
+      "epoch": 0.8934169278996865,
+      "grad_norm": 0.4268622100353241,
+      "learning_rate": 0.00016473862847818277,
+      "loss": 2.8196,
+      "step": 570
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5538944005966187,
+      "learning_rate": 0.00016343932841636456,
+      "loss": 2.8619,
+      "step": 580
+    },
+    {
+      "epoch": 0.9247648902821317,
+      "grad_norm": 0.7213597297668457,
+      "learning_rate": 0.00016212185261841499,
+      "loss": 2.9276,
+      "step": 590
+    },
+    {
+      "epoch": 0.9404388714733543,
+      "grad_norm": 1.6927486658096313,
+      "learning_rate": 0.00016078657854880376,
+      "loss": 2.7446,
+      "step": 600
+    },
+    {
+      "epoch": 0.9561128526645768,
+      "grad_norm": 0.3090650141239166,
+      "learning_rate": 0.000159433888771309,
+      "loss": 2.747,
+      "step": 610
+    },
+    {
+      "epoch": 0.9717868338557993,
+      "grad_norm": 0.4454885423183441,
+      "learning_rate": 0.00015806417083941002,
+      "loss": 2.8622,
+      "step": 620
+    },
+    {
+      "epoch": 0.987460815047022,
+      "grad_norm": 0.8089830279350281,
+      "learning_rate": 0.00015667781718525157,
+      "loss": 2.8568,
+      "step": 630
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.21911662817001343,
+      "learning_rate": 0.00015527522500720934,
+      "loss": 2.7012,
+      "step": 640
+    },
+    {
+      "epoch": 1.0188087774294672,
+      "grad_norm": 0.3196061849594116,
+      "learning_rate": 0.00015385679615609042,
+      "loss": 2.7127,
+      "step": 650
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.4679659605026245,
+      "learning_rate": 0.00015242293702000086,
+      "loss": 2.7103,
+      "step": 660
+    },
+    {
+      "epoch": 1.0501567398119123,
+      "grad_norm": 0.6506277322769165,
+      "learning_rate": 0.00015097405840791276,
+      "loss": 2.6762,
+      "step": 670
+    },
+    {
+      "epoch": 1.0658307210031348,
+      "grad_norm": 0.9151834845542908,
+      "learning_rate": 0.00014951057543196566,
+      "loss": 2.6503,
+      "step": 680
+    },
+    {
+      "epoch": 1.0815047021943573,
+      "grad_norm": 0.2834145724773407,
+      "learning_rate": 0.00014803290738853395,
+      "loss": 2.5103,
+      "step": 690
+    },
+    {
+      "epoch": 1.09717868338558,
+      "grad_norm": 0.3199128210544586,
+      "learning_rate": 0.00014654147763809637,
+      "loss": 2.7147,
+      "step": 700
+    },
+    {
+      "epoch": 1.1128526645768024,
+      "grad_norm": 0.5001178979873657,
+      "learning_rate": 0.00014503671348394057,
+      "loss": 2.7124,
+      "step": 710
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.6373796463012695,
+      "learning_rate": 0.0001435190460497384,
+      "loss": 2.7012,
+      "step": 720
+    },
+    {
+      "epoch": 1.1442006269592477,
+      "grad_norm": 0.9262835383415222,
+      "learning_rate": 0.00014198891015602646,
+      "loss": 2.6493,
+      "step": 730
+    },
+    {
+      "epoch": 1.1598746081504703,
+      "grad_norm": 0.2955109775066376,
+      "learning_rate": 0.00014044674419562734,
+      "loss": 2.5023,
+      "step": 740
+    },
+    {
+      "epoch": 1.1755485893416928,
+      "grad_norm": 0.34623944759368896,
+      "learning_rate": 0.0001388929900080476,
+      "loss": 2.6849,
+      "step": 750
+    },
+    {
+      "epoch": 1.1912225705329154,
+      "grad_norm": 0.43281346559524536,
+      "learning_rate": 0.00013732809275288828,
+      "loss": 2.6655,
+      "step": 760
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.6403496265411377,
+      "learning_rate": 0.000135752500782304,
+      "loss": 2.6557,
+      "step": 770
+    },
+    {
+      "epoch": 1.2225705329153604,
+      "grad_norm": 0.8644494414329529,
+      "learning_rate": 0.00013416666551254748,
+      "loss": 2.6162,
+      "step": 780
+    },
+    {
+      "epoch": 1.238244514106583,
+      "grad_norm": 0.2673655152320862,
+      "learning_rate": 0.00013257104129463614,
+      "loss": 2.4991,
+      "step": 790
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.3414609432220459,
+      "learning_rate": 0.00013096608528417788,
+      "loss": 2.6638,
+      "step": 800
+    },
+    {
+      "epoch": 1.2695924764890283,
+      "grad_norm": 0.47588247060775757,
+      "learning_rate": 0.00012935225731039348,
+      "loss": 2.6465,
+      "step": 810
+    },
+    {
+      "epoch": 1.2852664576802508,
+      "grad_norm": 0.6843693852424622,
+      "learning_rate": 0.00012773001974437267,
+      "loss": 2.6697,
+      "step": 820
+    },
+    {
+      "epoch": 1.3009404388714734,
+      "grad_norm": 0.9213519096374512,
+      "learning_rate": 0.0001260998373666022,
+      "loss": 2.6691,
+      "step": 830
+    },
+    {
+      "epoch": 1.316614420062696,
+      "grad_norm": 0.26475438475608826,
+      "learning_rate": 0.0001244621772338036,
+      "loss": 2.5109,
+      "step": 840
+    },
+    {
+      "epoch": 1.3322884012539185,
+      "grad_norm": 0.3754674196243286,
+      "learning_rate": 0.0001228175085451186,
+      "loss": 2.6699,
+      "step": 850
+    },
+    {
+      "epoch": 1.347962382445141,
+      "grad_norm": 0.49352237582206726,
+      "learning_rate": 0.00012116630250768097,
+      "loss": 2.6889,
+      "step": 860
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.7134298086166382,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 2.6502,
+      "step": 870
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.9475263953208923,
+      "learning_rate": 0.00011784617244448451,
+      "loss": 2.6062,
+      "step": 880
+    },
+    {
+      "epoch": 1.3949843260188088,
+      "grad_norm": 0.2767506539821625,
+      "learning_rate": 0.0001161781996552765,
+      "loss": 2.4584,
+      "step": 890
+    },
+    {
+      "epoch": 1.4106583072100314,
+      "grad_norm": 0.38563597202301025,
+      "learning_rate": 0.00011450559171788269,
+      "loss": 2.6751,
+      "step": 900
+    },
+    {
+      "epoch": 1.426332288401254,
+      "grad_norm": 0.466782808303833,
+      "learning_rate": 0.00011282882784419398,
+      "loss": 2.6181,
+      "step": 910
+    },
+    {
+      "epoch": 1.4420062695924765,
+      "grad_norm": 0.7600008845329285,
+      "learning_rate": 0.00011114838843680095,
+      "loss": 2.6729,
+      "step": 920
+    },
+    {
+      "epoch": 1.457680250783699,
+      "grad_norm": 0.956167459487915,
+      "learning_rate": 0.0001094647549513561,
+      "loss": 2.5486,
+      "step": 930
+    },
+    {
+      "epoch": 1.4733542319749215,
+      "grad_norm": 0.257744699716568,
+      "learning_rate": 0.00010777840975863383,
+      "loss": 2.4545,
+      "step": 940
+    },
+    {
+      "epoch": 1.489028213166144,
+      "grad_norm": 0.347033828496933,
+      "learning_rate": 0.00010608983600632831,
+      "loss": 2.6313,
+      "step": 950
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.5105902552604675,
+      "learning_rate": 0.00010439951748062912,
+      "loss": 2.623,
+      "step": 960
+    },
+    {
+      "epoch": 1.5203761755485894,
+      "grad_norm": 0.7116357684135437,
+      "learning_rate": 0.00010270793846761347,
+      "loss": 2.6493,
+      "step": 970
+    },
+    {
+      "epoch": 1.536050156739812,
+      "grad_norm": 0.9367708563804626,
+      "learning_rate": 0.00010101558361449552,
+      "loss": 2.6081,
+      "step": 980
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.25939515233039856,
+      "learning_rate": 9.932293779077216e-05,
+      "loss": 2.4289,
+      "step": 990
+    },
+    {
+      "epoch": 1.567398119122257,
+      "grad_norm": 0.3675819933414459,
+      "learning_rate": 9.763048594930502e-05,
+      "loss": 2.6617,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5830721003134798,
+      "grad_norm": 0.47927770018577576,
+      "learning_rate": 9.59387129873787e-05,
+      "loss": 2.661,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5987460815047023,
+      "grad_norm": 0.6929473876953125,
+      "learning_rate": 9.42481036077749e-05,
+      "loss": 2.6103,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6144200626959249,
+      "grad_norm": 0.9767149090766907,
+      "learning_rate": 9.255914217990211e-05,
+      "loss": 2.5943,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.24275819957256317,
+      "learning_rate": 9.08723126010212e-05,
+      "loss": 2.4676,
+      "step": 1040
+    },
+    {
+      "epoch": 1.64576802507837,
+      "grad_norm": 0.3554080128669739,
+      "learning_rate": 8.918809815760585e-05,
+      "loss": 2.6107,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6614420062695925,
+      "grad_norm": 0.5181464552879333,
+      "learning_rate": 8.750698138687827e-05,
+      "loss": 2.617,
+      "step": 1060
+    },
+    {
+      "epoch": 1.677115987460815,
+      "grad_norm": 0.7479755282402039,
+      "learning_rate": 8.582944393855941e-05,
+      "loss": 2.6401,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6927899686520376,
+      "grad_norm": 0.9864292740821838,
+      "learning_rate": 8.415596643687363e-05,
+      "loss": 2.6327,
+      "step": 1080
+    },
+    {
+      "epoch": 1.70846394984326,
+      "grad_norm": 0.24126508831977844,
+      "learning_rate": 8.248702834284693e-05,
+      "loss": 2.4569,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.3491465449333191,
+      "learning_rate": 8.082310781693865e-05,
+      "loss": 2.6473,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7398119122257052,
+      "grad_norm": 0.5092320442199707,
+      "learning_rate": 7.916468158204576e-05,
+      "loss": 2.6587,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.6617609262466431,
+      "learning_rate": 7.751222478691884e-05,
+      "loss": 2.6862,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7711598746081505,
+      "grad_norm": 1.0016579627990723,
+      "learning_rate": 7.586621087002945e-05,
+      "loss": 2.6226,
+      "step": 1130
+    },
+    {
+      "epoch": 1.786833855799373,
+      "grad_norm": 0.2429930418729782,
+      "learning_rate": 7.422711142392695e-05,
+      "loss": 2.5479,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8025078369905956,
+      "grad_norm": 0.396308034658432,
+      "learning_rate": 7.259539606012478e-05,
+      "loss": 2.6005,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5580389499664307,
+      "learning_rate": 7.097153227455379e-05,
+      "loss": 2.6714,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8338557993730409,
+      "grad_norm": 0.7043899893760681,
+      "learning_rate": 6.93559853136221e-05,
+      "loss": 2.6417,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8495297805642634,
+      "grad_norm": 0.9616154432296753,
+      "learning_rate": 6.774921804091934e-05,
+      "loss": 2.5572,
+      "step": 1180
+    },
+    {
+      "epoch": 1.865203761755486,
+      "grad_norm": 0.2324633002281189,
+      "learning_rate": 6.615169080460331e-05,
+      "loss": 2.4474,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.3579946756362915,
+      "learning_rate": 6.456386130550782e-05,
+      "loss": 2.6281,
+      "step": 1200
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.5167599320411682,
+      "learning_rate": 6.298618446600856e-05,
+      "loss": 2.6397,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9122257053291536,
+      "grad_norm": 0.7201157808303833,
+      "learning_rate": 6.141911229968533e-05,
+      "loss": 2.6389,
+      "step": 1220
+    },
+    {
+      "epoch": 1.9278996865203761,
+      "grad_norm": 1.1355105638504028,
+      "learning_rate": 5.9863093781817394e-05,
+      "loss": 2.6135,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9435736677115987,
+      "grad_norm": 0.2417139708995819,
+      "learning_rate": 5.831857472074956e-05,
+      "loss": 2.456,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9592476489028212,
+      "grad_norm": 0.4348711669445038,
+      "learning_rate": 5.6785997630165435e-05,
+      "loss": 2.6756,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9749216300940438,
+      "grad_norm": 0.6851107478141785,
+      "learning_rate": 5.526580160230476e-05,
+      "loss": 2.6338,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9905956112852663,
+      "grad_norm": 1.0602185726165771,
+      "learning_rate": 5.375842218216076e-05,
+      "loss": 2.5925,
+      "step": 1270
+    },
+    {
+      "epoch": 2.006269592476489,
+      "grad_norm": 0.23286418616771698,
+      "learning_rate": 5.226429124269423e-05,
+      "loss": 2.4199,
+      "step": 1280
+    },
+    {
+      "epoch": 2.0219435736677114,
+      "grad_norm": 0.41238126158714294,
+      "learning_rate": 5.078383686109926e-05,
+      "loss": 2.5441,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0376175548589344,
+      "grad_norm": 0.5980674624443054,
+      "learning_rate": 4.931748319615656e-05,
+      "loss": 2.5002,
+      "step": 1300
+    },
+    {
+      "epoch": 2.053291536050157,
+      "grad_norm": 0.8170694708824158,
+      "learning_rate": 4.786565036670972e-05,
+      "loss": 2.4228,
+      "step": 1310
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 1.1204980611801147,
+      "learning_rate": 4.642875433129854e-05,
+      "loss": 2.3089,
+      "step": 1320
+    },
+    {
+      "epoch": 2.084639498432602,
+      "grad_norm": 0.28670328855514526,
+      "learning_rate": 4.500720676898452e-05,
+      "loss": 2.2163,
+      "step": 1330
+    },
+    {
+      "epoch": 2.1003134796238245,
+      "grad_norm": 0.45365315675735474,
+      "learning_rate": 4.36014149614026e-05,
+      "loss": 2.5476,
+      "step": 1340
+    },
+    {
+      "epoch": 2.115987460815047,
+      "grad_norm": 0.589374840259552,
+      "learning_rate": 4.221178167607226e-05,
+      "loss": 2.4646,
+      "step": 1350
+    },
+    {
+      "epoch": 2.1316614420062696,
+      "grad_norm": 0.9127137064933777,
+      "learning_rate": 4.083870505100263e-05,
+      "loss": 2.3819,
+      "step": 1360
+    },
+    {
+      "epoch": 2.147335423197492,
+      "grad_norm": 1.167529582977295,
+      "learning_rate": 3.948257848062351e-05,
+      "loss": 2.3445,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1630094043887147,
+      "grad_norm": 0.26559045910835266,
+      "learning_rate": 3.8143790503075403e-05,
+      "loss": 2.228,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1786833855799372,
+      "grad_norm": 0.5015429258346558,
+      "learning_rate": 3.6822724688891416e-05,
+      "loss": 2.5579,
+      "step": 1390
+    },
+    {
+      "epoch": 2.19435736677116,
+      "grad_norm": 0.7187398672103882,
+      "learning_rate": 3.551975953110177e-05,
+      "loss": 2.4841,
+      "step": 1400
+    },
+    {
+      "epoch": 2.2100313479623823,
+      "grad_norm": 0.872721791267395,
+      "learning_rate": 3.423526833679355e-05,
+      "loss": 2.418,
+      "step": 1410
+    },
+    {
+      "epoch": 2.225705329153605,
+      "grad_norm": 1.3087424039840698,
+      "learning_rate": 3.296961912015598e-05,
+      "loss": 2.2849,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.31001710891723633,
+      "learning_rate": 3.172317449704216e-05,
+      "loss": 2.2705,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2570532915360504,
+      "grad_norm": 0.47308361530303955,
+      "learning_rate": 3.0496291581077673e-05,
+      "loss": 2.5207,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6600085496902466,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.4747,
+      "step": 1450
+    },
+    {
+      "epoch": 2.2884012539184955,
+      "grad_norm": 0.8648523092269897,
+      "learning_rate": 2.8102611201675598e-05,
+      "loss": 2.4407,
+      "step": 1460
+    },
+    {
+      "epoch": 2.304075235109718,
+      "grad_norm": 1.2338064908981323,
+      "learning_rate": 2.6936499541572445e-05,
+      "loss": 2.3066,
+      "step": 1470
+    },
+    {
+      "epoch": 2.3197492163009406,
+      "grad_norm": 0.2991880476474762,
+      "learning_rate": 2.5791320998800695e-05,
+      "loss": 2.2581,
+      "step": 1480
+    },
+    {
+      "epoch": 2.335423197492163,
+      "grad_norm": 0.48960086703300476,
+      "learning_rate": 2.4667403673665623e-05,
+      "loss": 2.5032,
+      "step": 1490
+    },
+    {
+      "epoch": 2.3510971786833856,
+      "grad_norm": 0.6952352523803711,
+      "learning_rate": 2.3565069575010035e-05,
+      "loss": 2.4815,
+      "step": 1500
+    },
+    {
+      "epoch": 2.366771159874608,
+      "grad_norm": 0.9776033163070679,
+      "learning_rate": 2.248463452795705e-05,
+      "loss": 2.4033,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3824451410658307,
+      "grad_norm": 1.2295323610305786,
+      "learning_rate": 2.142640808342429e-05,
+      "loss": 2.2546,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3981191222570533,
+      "grad_norm": 0.2598329782485962,
+      "learning_rate": 2.0390693429435627e-05,
+      "loss": 2.2122,
+      "step": 1530
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.4593777358531952,
+      "learning_rate": 1.9377787304256302e-05,
+      "loss": 2.518,
+      "step": 1540
+    },
+    {
+      "epoch": 2.4294670846394983,
+      "grad_norm": 0.6363881826400757,
+      "learning_rate": 1.838797991137543e-05,
+      "loss": 2.4564,
+      "step": 1550
+    },
+    {
+      "epoch": 2.445141065830721,
+      "grad_norm": 0.9114318490028381,
+      "learning_rate": 1.742155483636123e-05,
+      "loss": 2.4088,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4608150470219434,
+      "grad_norm": 1.3736695051193237,
+      "learning_rate": 1.6478788965611993e-05,
+      "loss": 2.3423,
+      "step": 1570
+    },
+    {
+      "epoch": 2.476489028213166,
+      "grad_norm": 0.2641979157924652,
+      "learning_rate": 1.555995240702648e-05,
+      "loss": 2.1546,
+      "step": 1580
+    },
+    {
+      "epoch": 2.492163009404389,
+      "grad_norm": 0.5061512589454651,
+      "learning_rate": 1.4665308412616596e-05,
+      "loss": 2.5098,
+      "step": 1590
+    },
+    {
+      "epoch": 2.507836990595611,
+      "grad_norm": 0.6692546606063843,
+      "learning_rate": 1.3795113303084006e-05,
+      "loss": 2.4528,
+      "step": 1600
+    },
+    {
+      "epoch": 2.523510971786834,
+      "grad_norm": 0.9549630880355835,
+      "learning_rate": 1.2949616394382802e-05,
+      "loss": 2.4189,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5391849529780566,
+      "grad_norm": 1.450711727142334,
+      "learning_rate": 1.2129059926289166e-05,
+      "loss": 2.2557,
+      "step": 1620
+    },
+    {
+      "epoch": 2.554858934169279,
+      "grad_norm": 0.2581474781036377,
+      "learning_rate": 1.1333678992998043e-05,
+      "loss": 2.2043,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5705329153605017,
+      "grad_norm": 0.4815433621406555,
+      "learning_rate": 1.0563701475767462e-05,
+      "loss": 2.5434,
+      "step": 1640
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.6861922144889832,
+      "learning_rate": 9.819347977629202e-06,
+      "loss": 2.4619,
+      "step": 1650
+    },
+    {
+      "epoch": 2.6018808777429467,
+      "grad_norm": 0.9293055534362793,
+      "learning_rate": 9.100831760184625e-06,
+      "loss": 2.4539,
+      "step": 1660
+    },
+    {
+      "epoch": 2.6175548589341693,
+      "grad_norm": 1.2631028890609741,
+      "learning_rate": 8.408358682504147e-06,
+      "loss": 2.2262,
+      "step": 1670
+    },
+    {
+      "epoch": 2.633228840125392,
+      "grad_norm": 0.3051944673061371,
+      "learning_rate": 7.742127142147337e-06,
+      "loss": 2.2413,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6489028213166144,
+      "grad_norm": 0.5327479243278503,
+      "learning_rate": 7.102328018320858e-06,
+      "loss": 2.5487,
+      "step": 1690
+    },
+    {
+      "epoch": 2.664576802507837,
+      "grad_norm": 0.6830099821090698,
+      "learning_rate": 6.489144617190501e-06,
+      "loss": 2.492,
+      "step": 1700
+    },
+    {
+      "epoch": 2.6802507836990594,
+      "grad_norm": 1.006087303161621,
+      "learning_rate": 5.902752619362861e-06,
+      "loss": 2.4549,
+      "step": 1710
+    },
+    {
+      "epoch": 2.695924764890282,
+      "grad_norm": 1.3168909549713135,
+      "learning_rate": 5.343320029551868e-06,
+      "loss": 2.2644,
+      "step": 1720
+    },
+    {
+      "epoch": 2.7115987460815045,
+      "grad_norm": 0.29884764552116394,
+      "learning_rate": 4.811007128444445e-06,
+      "loss": 2.3007,
+      "step": 1730
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.4936012029647827,
+      "learning_rate": 4.305966426779118e-06,
+      "loss": 2.502,
+      "step": 1740
+    },
+    {
+      "epoch": 2.7429467084639496,
+      "grad_norm": 0.689198911190033,
+      "learning_rate": 3.828342621650882e-06,
+      "loss": 2.4674,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.9643833041191101,
+      "learning_rate": 3.3782725550545625e-06,
+      "loss": 2.4213,
+      "step": 1760
+    },
+    {
+      "epoch": 2.774294670846395,
+      "grad_norm": 1.3325724601745605,
+      "learning_rate": 2.9558851746788517e-06,
+      "loss": 2.2601,
+      "step": 1770
+    },
+    {
+      "epoch": 2.7899686520376177,
+      "grad_norm": 0.2799229621887207,
+      "learning_rate": 2.561301496962043e-06,
+      "loss": 2.2256,
+      "step": 1780
+    },
+    {
+      "epoch": 2.80564263322884,
+      "grad_norm": 0.5209997296333313,
+      "learning_rate": 2.194634572420029e-06,
+      "loss": 2.5132,
+      "step": 1790
+    },
+    {
+      "epoch": 2.8213166144200628,
+      "grad_norm": 0.6882754564285278,
+      "learning_rate": 1.8559894532568122e-06,
+      "loss": 2.428,
+      "step": 1800
+    },
+    {
+      "epoch": 2.8369905956112853,
+      "grad_norm": 0.9445529580116272,
+      "learning_rate": 1.545463163266303e-06,
+      "loss": 2.4341,
+      "step": 1810
+    },
+    {
+      "epoch": 2.852664576802508,
+      "grad_norm": 1.3681193590164185,
+      "learning_rate": 1.263144670034555e-06,
+      "loss": 2.2468,
+      "step": 1820
+    },
+    {
+      "epoch": 2.8683385579937304,
+      "grad_norm": 0.2578428089618683,
+      "learning_rate": 1.0091148594499666e-06,
+      "loss": 2.2084,
+      "step": 1830
+    },
+    {
+      "epoch": 2.884012539184953,
+      "grad_norm": 0.5128017663955688,
+      "learning_rate": 7.83446512529007e-07,
+      "loss": 2.5086,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8996865203761755,
+      "grad_norm": 0.7125623226165771,
+      "learning_rate": 5.862042845640403e-07,
+      "loss": 2.4374,
+      "step": 1850
+    },
+    {
+      "epoch": 2.915360501567398,
+      "grad_norm": 1.0510890483856201,
+      "learning_rate": 4.174446865992332e-07,
+      "loss": 2.4102,
+      "step": 1860
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 1.4845973253250122,
+      "learning_rate": 2.7721606923978293e-07,
+      "loss": 2.2825,
+      "step": 1870
+    },
+    {
+      "epoch": 2.946708463949843,
+      "grad_norm": 0.3054816722869873,
+      "learning_rate": 1.6555860879919892e-07,
+      "loss": 2.1791,
+      "step": 1880
+    },
+    {
+      "epoch": 2.962382445141066,
+      "grad_norm": 0.6139517426490784,
+      "learning_rate": 8.250429578855467e-08,
+      "loss": 2.5106,
+      "step": 1890
+    },
+    {
+      "epoch": 2.978056426332288,
+      "grad_norm": 0.9643613696098328,
+      "learning_rate": 2.8076925751008286e-08,
+      "loss": 2.4253,
+      "step": 1900
+    },
+    {
+      "epoch": 2.993730407523511,
+      "grad_norm": 1.5458600521087646,
+      "learning_rate": 2.292092444255989e-09,
+      "loss": 2.2764,
+      "step": 1910
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1914,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5314350752283034e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1914/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad729f37531a1c2749c64acb68f56a57b1c0c8e47ff21416db8f780a21d903d
+size 5432

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+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

checkpoint-500/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f1730cf6df10d5503de803b879f639257aec87708883fc80981fb398661664
+size 184592616

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a21d55e3107d8a4236dbb2f461e36cd790aa430e679270908fccef24da5532
+size 92836436

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b397cb0a4cbb6c38810526ea6e3fd8338eefd8699084e6e17e4272ffaf1744b
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b538b284177176460d2dccf5a83304a438937a4cfb820f411417371e70e9b84e
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "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": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,390 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7836990595611285,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001567398119122257,
+      "grad_norm": 0.5552594661712646,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 3.3921,
+      "step": 1
+    },
+    {
+      "epoch": 0.01567398119122257,
+      "grad_norm": 0.660531222820282,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 3.5922,
+      "step": 10
+    },
+    {
+      "epoch": 0.03134796238244514,
+      "grad_norm": 0.5598097443580627,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 3.619,
+      "step": 20
+    },
+    {
+      "epoch": 0.047021943573667714,
+      "grad_norm": 0.5996779799461365,
+      "learning_rate": 0.00010344827586206898,
+      "loss": 3.4824,
+      "step": 30
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 0.8172075152397156,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 3.3997,
+      "step": 40
+    },
+    {
+      "epoch": 0.07836990595611286,
+      "grad_norm": 1.6439019441604614,
+      "learning_rate": 0.00017241379310344826,
+      "loss": 3.2485,
+      "step": 50
+    },
+    {
+      "epoch": 0.09404388714733543,
+      "grad_norm": 0.28180772066116333,
+      "learning_rate": 0.00019999942697524717,
+      "loss": 2.9975,
+      "step": 60
+    },
+    {
+      "epoch": 0.109717868338558,
+      "grad_norm": 0.3870689868927002,
+      "learning_rate": 0.00019997937179843937,
+      "loss": 3.0446,
+      "step": 70
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.575548529624939,
+      "learning_rate": 0.00019993067195079803,
+      "loss": 3.0178,
+      "step": 80
+    },
+    {
+      "epoch": 0.14106583072100312,
+      "grad_norm": 0.781446635723114,
+      "learning_rate": 0.00019985334138511237,
+      "loss": 3.0394,
+      "step": 90
+    },
+    {
+      "epoch": 0.15673981191222572,
+      "grad_norm": 1.725696325302124,
+      "learning_rate": 0.00019974740225703878,
+      "loss": 3.0751,
+      "step": 100
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.2845414876937866,
+      "learning_rate": 0.00019961288491875278,
+      "loss": 2.9291,
+      "step": 110
+    },
+    {
+      "epoch": 0.18808777429467086,
+      "grad_norm": 0.36810651421546936,
+      "learning_rate": 0.00019944982791025333,
+      "loss": 2.9491,
+      "step": 120
+    },
+    {
+      "epoch": 0.20376175548589343,
+      "grad_norm": 0.5454439520835876,
+      "learning_rate": 0.00019925827794832056,
+      "loss": 3.0337,
+      "step": 130
+    },
+    {
+      "epoch": 0.219435736677116,
+      "grad_norm": 0.6503669619560242,
+      "learning_rate": 0.00019903828991313138,
+      "loss": 3.0246,
+      "step": 140
+    },
+    {
+      "epoch": 0.23510971786833856,
+      "grad_norm": 1.4392451047897339,
+      "learning_rate": 0.00019878992683253582,
+      "loss": 3.0232,
+      "step": 150
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.2859440743923187,
+      "learning_rate": 0.00019851325986399934,
+      "loss": 2.8955,
+      "step": 160
+    },
+    {
+      "epoch": 0.2664576802507837,
+      "grad_norm": 0.44268104434013367,
+      "learning_rate": 0.0001982083682742156,
+      "loss": 2.9338,
+      "step": 170
+    },
+    {
+      "epoch": 0.28213166144200624,
+      "grad_norm": 0.5128395557403564,
+      "learning_rate": 0.00019787533941639638,
+      "loss": 3.0089,
+      "step": 180
+    },
+    {
+      "epoch": 0.29780564263322884,
+      "grad_norm": 0.7328920364379883,
+      "learning_rate": 0.00019751426870524407,
+      "loss": 3.0157,
+      "step": 190
+    },
+    {
+      "epoch": 0.31347962382445144,
+      "grad_norm": 1.5265012979507446,
+      "learning_rate": 0.000197125259589615,
+      "loss": 2.9007,
+      "step": 200
+    },
+    {
+      "epoch": 0.329153605015674,
+      "grad_norm": 0.2766813635826111,
+      "learning_rate": 0.0001967084235228807,
+      "loss": 2.8275,
+      "step": 210
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.36695396900177,
+      "learning_rate": 0.00019626387993099579,
+      "loss": 2.9158,
+      "step": 220
+    },
+    {
+      "epoch": 0.3605015673981191,
+      "grad_norm": 0.5359162092208862,
+      "learning_rate": 0.00019579175617828187,
+      "loss": 2.9465,
+      "step": 230
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.6529833674430847,
+      "learning_rate": 0.0001952921875309368,
+      "loss": 2.981,
+      "step": 240
+    },
+    {
+      "epoch": 0.39184952978056425,
+      "grad_norm": 1.5314627885818481,
+      "learning_rate": 0.00019476531711828027,
+      "loss": 2.9737,
+      "step": 250
+    },
+    {
+      "epoch": 0.40752351097178685,
+      "grad_norm": 0.2949506342411041,
+      "learning_rate": 0.00019421129589174618,
+      "loss": 2.8208,
+      "step": 260
+    },
+    {
+      "epoch": 0.4231974921630094,
+      "grad_norm": 0.39567869901657104,
+      "learning_rate": 0.00019363028258163447,
+      "loss": 2.8557,
+      "step": 270
+    },
+    {
+      "epoch": 0.438871473354232,
+      "grad_norm": 0.5587254166603088,
+      "learning_rate": 0.00019302244365163376,
+      "loss": 2.9494,
+      "step": 280
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.7218978404998779,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 2.9742,
+      "step": 290
+    },
+    {
+      "epoch": 0.4702194357366771,
+      "grad_norm": 1.4482598304748535,
+      "learning_rate": 0.0001917269931653049,
+      "loss": 2.8646,
+      "step": 300
+    },
+    {
+      "epoch": 0.48589341692789967,
+      "grad_norm": 0.2901701033115387,
+      "learning_rate": 0.00019103975276306678,
+      "loss": 2.7788,
+      "step": 310
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.4310539960861206,
+      "learning_rate": 0.00019032642894278192,
+      "loss": 2.8655,
+      "step": 320
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.5589954853057861,
+      "learning_rate": 0.0001895872260758688,
+      "loss": 2.914,
+      "step": 330
+    },
+    {
+      "epoch": 0.5329153605015674,
+      "grad_norm": 0.7243526577949524,
+      "learning_rate": 0.00018882235594824308,
+      "loss": 2.9191,
+      "step": 340
+    },
+    {
+      "epoch": 0.54858934169279,
+      "grad_norm": 1.4200222492218018,
+      "learning_rate": 0.00018803203769963967,
+      "loss": 2.8128,
+      "step": 350
+    },
+    {
+      "epoch": 0.5642633228840125,
+      "grad_norm": 0.26594147086143494,
+      "learning_rate": 0.000187216497760828,
+      "loss": 2.762,
+      "step": 360
+    },
+    {
+      "epoch": 0.5799373040752351,
+      "grad_norm": 0.3894258439540863,
+      "learning_rate": 0.00018637596978873835,
+      "loss": 2.9077,
+      "step": 370
+    },
+    {
+      "epoch": 0.5956112852664577,
+      "grad_norm": 0.5348561406135559,
+      "learning_rate": 0.00018551069459951758,
+      "loss": 2.9292,
+      "step": 380
+    },
+    {
+      "epoch": 0.6112852664576802,
+      "grad_norm": 0.746507465839386,
+      "learning_rate": 0.00018462092009953408,
+      "loss": 2.8795,
+      "step": 390
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 1.5225753784179688,
+      "learning_rate": 0.0001837069012143511,
+      "loss": 2.8263,
+      "step": 400
+    },
+    {
+      "epoch": 0.6426332288401254,
+      "grad_norm": 0.26905450224876404,
+      "learning_rate": 0.00018276889981568906,
+      "loss": 2.7218,
+      "step": 410
+    },
+    {
+      "epoch": 0.658307210031348,
+      "grad_norm": 0.3912515342235565,
+      "learning_rate": 0.00018180718464639787,
+      "loss": 2.819,
+      "step": 420
+    },
+    {
+      "epoch": 0.6739811912225705,
+      "grad_norm": 0.5661373138427734,
+      "learning_rate": 0.00018082203124346045,
+      "loss": 2.8772,
+      "step": 430
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.805776059627533,
+      "learning_rate": 0.0001798137218590498,
+      "loss": 2.9562,
+      "step": 440
+    },
+    {
+      "epoch": 0.7053291536050157,
+      "grad_norm": 1.4879732131958008,
+      "learning_rate": 0.00017878254537966216,
+      "loss": 2.7925,
+      "step": 450
+    },
+    {
+      "epoch": 0.7210031347962382,
+      "grad_norm": 0.28762391209602356,
+      "learning_rate": 0.00017772879724334937,
+      "loss": 2.8006,
+      "step": 460
+    },
+    {
+      "epoch": 0.7366771159874608,
+      "grad_norm": 0.41769474744796753,
+      "learning_rate": 0.00017665277935507398,
+      "loss": 2.8148,
+      "step": 470
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.633671760559082,
+      "learning_rate": 0.00017555480000021198,
+      "loss": 2.8461,
+      "step": 480
+    },
+    {
+      "epoch": 0.768025078369906,
+      "grad_norm": 0.816681444644928,
+      "learning_rate": 0.00017443517375622704,
+      "loss": 2.8826,
+      "step": 490
+    },
+    {
+      "epoch": 0.7836990595611285,
+      "grad_norm": 1.3913438320159912,
+      "learning_rate": 0.00017329422140254235,
+      "loss": 2.7449,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1914,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.158266300583117e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad729f37531a1c2749c64acb68f56a57b1c0c8e47ff21416db8f780a21d903d
+size 5432