Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,28 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_5.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/rng_state_6.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1377/tokenizer.model filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_5.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/rng_state_6.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-459/tokenizer.model filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_5.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/rng_state_6.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-918/tokenizer.model filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,158 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openlm-research/open_llama_3b_v2
+model-index:
+- name: outputs/lora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: openlm-research/open_llama_3b_v2
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+push_dataset_to_hub:
+datasets:
+  - path: "./raft_oracle_context_alpaca.json"
+    type: alpaca
+dataset_prepared_path: ./dataset-pre
+val_set_size: 0.02
+adapter: lora
+lora_model_dir:
+sequence_len: 1024
+sample_packing: true
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.0
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+lora_fan_in_fan_out:
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+output_dir: ./outputs/lora-out
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+torchdistx_path:
+lr_scheduler: cosine
+learning_rate: 0.0002
+train_on_inputs: false
+group_by_length: false
+bf16: false
+fp16: true
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+gptq_groupsize:
+s2_attention:
+gptq_model_v1:
+warmup_steps: 20
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.1
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# outputs/lora-out
+
+This model is a fine-tuned version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4426
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 7
+- total_train_batch_size: 14
+- total_eval_batch_size: 14
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9628        | 0.0022 | 1    | 1.9150          |
+| 0.5816        | 0.2505 | 115  | 0.6157          |
+| 0.3604        | 0.5011 | 230  | 0.4307          |
+| 0.2598        | 0.7516 | 345  | 0.3558          |
+| 0.2227        | 1.0022 | 460  | 0.3434          |
+| 0.1381        | 1.2266 | 575  | 0.3376          |
+| 0.0718        | 1.4771 | 690  | 0.3372          |
+| 0.0684        | 1.7277 | 805  | 0.3608          |
+| 0.0817        | 1.9782 | 920  | 0.3663          |
+| 0.0315        | 2.2004 | 1035 | 0.3888          |
+| 0.0331        | 2.4510 | 1150 | 0.4003          |
+| 0.0222        | 2.7015 | 1265 | 0.4145          |
+| 0.0222        | 2.9521 | 1380 | 0.4216          |
+| 0.0166        | 3.1743 | 1495 | 0.4330          |
+| 0.017         | 3.4248 | 1610 | 0.4391          |
+| 0.0142        | 3.6754 | 1725 | 0.4426          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677a50c1b9d0850d2cec3f7b7f4f48c48b1ee972cb2035101a85db8d424296cb
+size 50982842

checkpoint-1377/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openlm-research/open_llama_3b_v2
+---
+
+# 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 0.10.0

checkpoint-1377/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1377/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64e7265af1602760cb6765df9d12208ad7e4d8228dd48f7994a67b4da975462
+size 50899792

checkpoint-1377/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4b5f71f597d712b6e2ca4d8fec319aaff06839dea03ce75d149b4adb39c99b
+size 25871876

checkpoint-1377/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5defeb91698ab6360f6216c8fabe695c077c8654d953a8daff86e8cf12ac6f
+size 15728

checkpoint-1377/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8cd6242aea8a6a67e50efdbc6675b2331391d7cb99b0f91636f6cebb247fc6
+size 15728

checkpoint-1377/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f99cd40889231e537abfb45dcbb6e55838c2e72a30b89341ab0ad583b0b960
+size 15728

checkpoint-1377/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90417ba680fa5bb09ef8a8ec398b7257d0636eb9c7b2ad515cefe3d7407cde71
+size 15728

checkpoint-1377/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499b2fe2efbdc7898fb314f5e08537284a5f372d58390b1752628c101c097fc0
+size 15728

checkpoint-1377/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63014041ad8399310e60df2026b42ef3ff4ba8bdfe812a4644440582152f21fd
+size 15728

checkpoint-1377/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694faa19a67bf5098b4669d83e2b2d644639b59e4ba1b2574f64019340cde48c
+size 15728

checkpoint-1377/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd1ed30b1ed2729d9f26cdc448998fb7a2617a21add5df7cc852b5bedc40d45
+size 1064

checkpoint-1377/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1377/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

checkpoint-1377/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-1377/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eeec319c5500d881c83ddf7f3e737b7843c548db9958907577f93d03ba7823
+size 5816

checkpoint-459/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openlm-research/open_llama_3b_v2
+---
+
+# 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 0.10.0

checkpoint-459/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-459/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65853739bfa38f24d209091ef89729fc8483f62b9458acd129e27c84ff647381
+size 50899792

checkpoint-459/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66949e01021ea3c116412bc78bd8416d04b91edc93268b8ec285568996ad86f4
+size 25871876

checkpoint-459/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ede3a41c76eab8d5a1109b390a56df16ebb33aa97144d7374657806fe7680ec
+size 15728

checkpoint-459/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5a3f71bd916448b335fc12b81ee46376136a8b88160f46dc05a2c519f7dc69
+size 15728

checkpoint-459/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1498f85638b156d84ed9814b2ee749b87a840b1cebc2023ed62f199cdf2db62a
+size 15728

checkpoint-459/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7e82267f597a2bf81008683b4aea5c1841ac18b6f7d3817788768df2bd57ca
+size 15728

checkpoint-459/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881e950a2ccd0819e0af6ba6c8686e05169bc934182acceb756ddbcc66ba79d5
+size 15728

checkpoint-459/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7d85a882a0a197e2b4aadcdeca8bd3ab751aff35caf44543574dadb7638446
+size 15728

checkpoint-459/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccc34bb3651a068b5415059e67db3f95a4450f8a810669e910ccbd146669019
+size 15728

checkpoint-459/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a751b4b1e6d1ebcbd0865f7e06be0ccb8edd80211daf4876d48ed2983b57ef5
+size 1064

checkpoint-459/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-459/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

checkpoint-459/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-459/trainer_state.json

@@ -0,0 +1,3266 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 115,
+  "global_step": 459,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002178649237472767,
+      "grad_norm": 0.4049851596355438,
+      "learning_rate": 1e-05,
+      "loss": 1.9628,
+      "step": 1
+    },
+    {
+      "epoch": 0.002178649237472767,
+      "eval_loss": 1.915004849433899,
+      "eval_runtime": 0.9396,
+      "eval_samples_per_second": 181.996,
+      "eval_steps_per_second": 13.836,
+      "step": 1
+    },
+    {
+      "epoch": 0.004357298474945534,
+      "grad_norm": 0.38593971729278564,
+      "learning_rate": 2e-05,
+      "loss": 2.0388,
+      "step": 2
+    },
+    {
+      "epoch": 0.006535947712418301,
+      "grad_norm": 0.38570573925971985,
+      "learning_rate": 3e-05,
+      "loss": 1.932,
+      "step": 3
+    },
+    {
+      "epoch": 0.008714596949891068,
+      "grad_norm": 0.35365748405456543,
+      "learning_rate": 4e-05,
+      "loss": 1.866,
+      "step": 4
+    },
+    {
+      "epoch": 0.010893246187363835,
+      "grad_norm": 0.4407881796360016,
+      "learning_rate": 5e-05,
+      "loss": 1.9959,
+      "step": 5
+    },
+    {
+      "epoch": 0.013071895424836602,
+      "grad_norm": 0.3517284095287323,
+      "learning_rate": 6e-05,
+      "loss": 1.8822,
+      "step": 6
+    },
+    {
+      "epoch": 0.015250544662309368,
+      "grad_norm": 0.45338165760040283,
+      "learning_rate": 7e-05,
+      "loss": 1.8933,
+      "step": 7
+    },
+    {
+      "epoch": 0.017429193899782137,
+      "grad_norm": 0.3475826680660248,
+      "learning_rate": 8e-05,
+      "loss": 1.8337,
+      "step": 8
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 0.4348187744617462,
+      "learning_rate": 9e-05,
+      "loss": 1.9261,
+      "step": 9
+    },
+    {
+      "epoch": 0.02178649237472767,
+      "grad_norm": 0.3879510164260864,
+      "learning_rate": 0.0001,
+      "loss": 1.7648,
+      "step": 10
+    },
+    {
+      "epoch": 0.023965141612200435,
+      "grad_norm": 0.3244905471801758,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 1.7833,
+      "step": 11
+    },
+    {
+      "epoch": 0.026143790849673203,
+      "grad_norm": 0.3566845953464508,
+      "learning_rate": 0.00012,
+      "loss": 1.786,
+      "step": 12
+    },
+    {
+      "epoch": 0.02832244008714597,
+      "grad_norm": 0.35482919216156006,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 1.6593,
+      "step": 13
+    },
+    {
+      "epoch": 0.030501089324618737,
+      "grad_norm": 0.3647037744522095,
+      "learning_rate": 0.00014,
+      "loss": 1.696,
+      "step": 14
+    },
+    {
+      "epoch": 0.032679738562091505,
+      "grad_norm": 0.41642501950263977,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5964,
+      "step": 15
+    },
+    {
+      "epoch": 0.034858387799564274,
+      "grad_norm": 0.3616989254951477,
+      "learning_rate": 0.00016,
+      "loss": 1.7121,
+      "step": 16
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 0.39412033557891846,
+      "learning_rate": 0.00017,
+      "loss": 1.7392,
+      "step": 17
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 0.3788229823112488,
+      "learning_rate": 0.00018,
+      "loss": 1.793,
+      "step": 18
+    },
+    {
+      "epoch": 0.04139433551198257,
+      "grad_norm": 0.3376384377479553,
+      "learning_rate": 0.00019,
+      "loss": 1.6145,
+      "step": 19
+    },
+    {
+      "epoch": 0.04357298474945534,
+      "grad_norm": 0.3674631714820862,
+      "learning_rate": 0.0002,
+      "loss": 1.6802,
+      "step": 20
+    },
+    {
+      "epoch": 0.0457516339869281,
+      "grad_norm": 0.406034916639328,
+      "learning_rate": 0.00019999985036335823,
+      "loss": 1.7272,
+      "step": 21
+    },
+    {
+      "epoch": 0.04793028322440087,
+      "grad_norm": 0.34544336795806885,
+      "learning_rate": 0.00019999940145388063,
+      "loss": 1.592,
+      "step": 22
+    },
+    {
+      "epoch": 0.05010893246187364,
+      "grad_norm": 0.4000962972640991,
+      "learning_rate": 0.00019999865327291073,
+      "loss": 1.6177,
+      "step": 23
+    },
+    {
+      "epoch": 0.05228758169934641,
+      "grad_norm": 0.36951783299446106,
+      "learning_rate": 0.00019999760582268763,
+      "loss": 1.6261,
+      "step": 24
+    },
+    {
+      "epoch": 0.054466230936819175,
+      "grad_norm": 0.3870888948440552,
+      "learning_rate": 0.00019999625910634605,
+      "loss": 1.544,
+      "step": 25
+    },
+    {
+      "epoch": 0.05664488017429194,
+      "grad_norm": 0.4127906560897827,
+      "learning_rate": 0.00019999461312791638,
+      "loss": 1.5375,
+      "step": 26
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.43752938508987427,
+      "learning_rate": 0.00019999266789232455,
+      "loss": 1.4055,
+      "step": 27
+    },
+    {
+      "epoch": 0.06100217864923747,
+      "grad_norm": 0.44983282685279846,
+      "learning_rate": 0.0001999904234053922,
+      "loss": 1.5742,
+      "step": 28
+    },
+    {
+      "epoch": 0.06318082788671024,
+      "grad_norm": 0.4332844614982605,
+      "learning_rate": 0.0001999878796738364,
+      "loss": 1.5264,
+      "step": 29
+    },
+    {
+      "epoch": 0.06535947712418301,
+      "grad_norm": 0.4228737950325012,
+      "learning_rate": 0.00019998503670526994,
+      "loss": 1.4985,
+      "step": 30
+    },
+    {
+      "epoch": 0.06753812636165578,
+      "grad_norm": 0.4225306808948517,
+      "learning_rate": 0.000199981894508201,
+      "loss": 1.447,
+      "step": 31
+    },
+    {
+      "epoch": 0.06971677559912855,
+      "grad_norm": 0.5055080056190491,
+      "learning_rate": 0.00019997845309203334,
+      "loss": 1.4575,
+      "step": 32
+    },
+    {
+      "epoch": 0.0718954248366013,
+      "grad_norm": 0.4757756292819977,
+      "learning_rate": 0.0001999747124670662,
+      "loss": 1.3472,
+      "step": 33
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.4340977966785431,
+      "learning_rate": 0.00019997067264449433,
+      "loss": 1.3273,
+      "step": 34
+    },
+    {
+      "epoch": 0.07625272331154684,
+      "grad_norm": 0.4556865692138672,
+      "learning_rate": 0.0001999663336364078,
+      "loss": 1.43,
+      "step": 35
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.5178071856498718,
+      "learning_rate": 0.00019996169545579207,
+      "loss": 1.3286,
+      "step": 36
+    },
+    {
+      "epoch": 0.08061002178649238,
+      "grad_norm": 0.5154844522476196,
+      "learning_rate": 0.00019995675811652802,
+      "loss": 1.2845,
+      "step": 37
+    },
+    {
+      "epoch": 0.08278867102396514,
+      "grad_norm": 0.5944285988807678,
+      "learning_rate": 0.00019995152163339178,
+      "loss": 1.4411,
+      "step": 38
+    },
+    {
+      "epoch": 0.08496732026143791,
+      "grad_norm": 0.5691947340965271,
+      "learning_rate": 0.00019994598602205473,
+      "loss": 1.3807,
+      "step": 39
+    },
+    {
+      "epoch": 0.08714596949891068,
+      "grad_norm": 0.575366199016571,
+      "learning_rate": 0.00019994015129908346,
+      "loss": 1.3347,
+      "step": 40
+    },
+    {
+      "epoch": 0.08932461873638345,
+      "grad_norm": 0.5233891010284424,
+      "learning_rate": 0.00019993401748193978,
+      "loss": 1.303,
+      "step": 41
+    },
+    {
+      "epoch": 0.0915032679738562,
+      "grad_norm": 0.5643051862716675,
+      "learning_rate": 0.00019992758458898055,
+      "loss": 1.2618,
+      "step": 42
+    },
+    {
+      "epoch": 0.09368191721132897,
+      "grad_norm": 0.6836549043655396,
+      "learning_rate": 0.0001999208526394577,
+      "loss": 1.3218,
+      "step": 43
+    },
+    {
+      "epoch": 0.09586056644880174,
+      "grad_norm": 0.6471132040023804,
+      "learning_rate": 0.00019991382165351814,
+      "loss": 1.1933,
+      "step": 44
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 0.5644765496253967,
+      "learning_rate": 0.00019990649165220375,
+      "loss": 1.1135,
+      "step": 45
+    },
+    {
+      "epoch": 0.10021786492374728,
+      "grad_norm": 0.7101904153823853,
+      "learning_rate": 0.00019989886265745128,
+      "loss": 1.1919,
+      "step": 46
+    },
+    {
+      "epoch": 0.10239651416122005,
+      "grad_norm": 0.706234872341156,
+      "learning_rate": 0.00019989093469209224,
+      "loss": 1.1607,
+      "step": 47
+    },
+    {
+      "epoch": 0.10457516339869281,
+      "grad_norm": 0.6854044795036316,
+      "learning_rate": 0.00019988270777985292,
+      "loss": 1.1441,
+      "step": 48
+    },
+    {
+      "epoch": 0.10675381263616558,
+      "grad_norm": 0.6608173251152039,
+      "learning_rate": 0.00019987418194535427,
+      "loss": 1.0626,
+      "step": 49
+    },
+    {
+      "epoch": 0.10893246187363835,
+      "grad_norm": 0.7540091276168823,
+      "learning_rate": 0.00019986535721411186,
+      "loss": 1.1346,
+      "step": 50
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.783423125743866,
+      "learning_rate": 0.00019985623361253572,
+      "loss": 1.2105,
+      "step": 51
+    },
+    {
+      "epoch": 0.11328976034858387,
+      "grad_norm": 0.7029076814651489,
+      "learning_rate": 0.00019984681116793038,
+      "loss": 0.9689,
+      "step": 52
+    },
+    {
+      "epoch": 0.11546840958605664,
+      "grad_norm": 0.8416129350662231,
+      "learning_rate": 0.00019983708990849468,
+      "loss": 1.1176,
+      "step": 53
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.7312731146812439,
+      "learning_rate": 0.00019982706986332175,
+      "loss": 1.1695,
+      "step": 54
+    },
+    {
+      "epoch": 0.11982570806100218,
+      "grad_norm": 0.8590166568756104,
+      "learning_rate": 0.00019981675106239895,
+      "loss": 1.016,
+      "step": 55
+    },
+    {
+      "epoch": 0.12200435729847495,
+      "grad_norm": 0.8634907603263855,
+      "learning_rate": 0.00019980613353660763,
+      "loss": 1.0777,
+      "step": 56
+    },
+    {
+      "epoch": 0.12418300653594772,
+      "grad_norm": 0.6608163714408875,
+      "learning_rate": 0.00019979521731772323,
+      "loss": 0.9661,
+      "step": 57
+    },
+    {
+      "epoch": 0.12636165577342048,
+      "grad_norm": 0.9486388564109802,
+      "learning_rate": 0.00019978400243841508,
+      "loss": 0.8715,
+      "step": 58
+    },
+    {
+      "epoch": 0.12854030501089325,
+      "grad_norm": 0.8431762456893921,
+      "learning_rate": 0.00019977248893224636,
+      "loss": 1.0458,
+      "step": 59
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 1.00847589969635,
+      "learning_rate": 0.00019976067683367385,
+      "loss": 0.9081,
+      "step": 60
+    },
+    {
+      "epoch": 0.1328976034858388,
+      "grad_norm": 1.3647116422653198,
+      "learning_rate": 0.00019974856617804807,
+      "loss": 1.0181,
+      "step": 61
+    },
+    {
+      "epoch": 0.13507625272331156,
+      "grad_norm": 1.2597001791000366,
+      "learning_rate": 0.0001997361570016129,
+      "loss": 0.9373,
+      "step": 62
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 1.238145351409912,
+      "learning_rate": 0.00019972344934150577,
+      "loss": 0.9464,
+      "step": 63
+    },
+    {
+      "epoch": 0.1394335511982571,
+      "grad_norm": 1.114610195159912,
+      "learning_rate": 0.00019971044323575728,
+      "loss": 0.9163,
+      "step": 64
+    },
+    {
+      "epoch": 0.14161220043572983,
+      "grad_norm": 0.9760491847991943,
+      "learning_rate": 0.0001996971387232912,
+      "loss": 0.8424,
+      "step": 65
+    },
+    {
+      "epoch": 0.1437908496732026,
+      "grad_norm": 0.999609649181366,
+      "learning_rate": 0.0001996835358439244,
+      "loss": 0.8027,
+      "step": 66
+    },
+    {
+      "epoch": 0.14596949891067537,
+      "grad_norm": 0.9615645408630371,
+      "learning_rate": 0.00019966963463836668,
+      "loss": 0.9491,
+      "step": 67
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.9067331552505493,
+      "learning_rate": 0.00019965543514822062,
+      "loss": 0.9756,
+      "step": 68
+    },
+    {
+      "epoch": 0.1503267973856209,
+      "grad_norm": 1.0316940546035767,
+      "learning_rate": 0.00019964093741598152,
+      "loss": 0.7276,
+      "step": 69
+    },
+    {
+      "epoch": 0.15250544662309368,
+      "grad_norm": 0.7774396538734436,
+      "learning_rate": 0.00019962614148503718,
+      "loss": 0.8904,
+      "step": 70
+    },
+    {
+      "epoch": 0.15468409586056645,
+      "grad_norm": 1.0500309467315674,
+      "learning_rate": 0.0001996110473996679,
+      "loss": 0.8801,
+      "step": 71
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.8712791800498962,
+      "learning_rate": 0.00019959565520504623,
+      "loss": 0.992,
+      "step": 72
+    },
+    {
+      "epoch": 0.15904139433551198,
+      "grad_norm": 1.006437063217163,
+      "learning_rate": 0.0001995799649472369,
+      "loss": 0.6761,
+      "step": 73
+    },
+    {
+      "epoch": 0.16122004357298475,
+      "grad_norm": 1.0199809074401855,
+      "learning_rate": 0.00019956397667319668,
+      "loss": 0.7066,
+      "step": 74
+    },
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 1.2605611085891724,
+      "learning_rate": 0.0001995476904307742,
+      "loss": 0.6546,
+      "step": 75
+    },
+    {
+      "epoch": 0.1655773420479303,
+      "grad_norm": 0.9553707242012024,
+      "learning_rate": 0.00019953110626870979,
+      "loss": 0.9392,
+      "step": 76
+    },
+    {
+      "epoch": 0.16775599128540306,
+      "grad_norm": 0.909253716468811,
+      "learning_rate": 0.00019951422423663547,
+      "loss": 0.8757,
+      "step": 77
+    },
+    {
+      "epoch": 0.16993464052287582,
+      "grad_norm": 1.007814645767212,
+      "learning_rate": 0.00019949704438507459,
+      "loss": 0.877,
+      "step": 78
+    },
+    {
+      "epoch": 0.1721132897603486,
+      "grad_norm": 1.341426968574524,
+      "learning_rate": 0.00019947956676544192,
+      "loss": 0.8002,
+      "step": 79
+    },
+    {
+      "epoch": 0.17429193899782136,
+      "grad_norm": 1.153745174407959,
+      "learning_rate": 0.00019946179143004325,
+      "loss": 0.714,
+      "step": 80
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 1.0699673891067505,
+      "learning_rate": 0.00019944371843207546,
+      "loss": 0.9575,
+      "step": 81
+    },
+    {
+      "epoch": 0.1786492374727669,
+      "grad_norm": 0.9054269194602966,
+      "learning_rate": 0.0001994253478256262,
+      "loss": 0.8967,
+      "step": 82
+    },
+    {
+      "epoch": 0.18082788671023964,
+      "grad_norm": 1.3790533542633057,
+      "learning_rate": 0.0001994066796656737,
+      "loss": 1.0535,
+      "step": 83
+    },
+    {
+      "epoch": 0.1830065359477124,
+      "grad_norm": 1.1256961822509766,
+      "learning_rate": 0.0001993877140080869,
+      "loss": 0.7872,
+      "step": 84
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.8870573043823242,
+      "learning_rate": 0.0001993684509096249,
+      "loss": 0.9137,
+      "step": 85
+    },
+    {
+      "epoch": 0.18736383442265794,
+      "grad_norm": 1.1747201681137085,
+      "learning_rate": 0.000199348890427937,
+      "loss": 0.779,
+      "step": 86
+    },
+    {
+      "epoch": 0.1895424836601307,
+      "grad_norm": 0.8280813694000244,
+      "learning_rate": 0.00019932903262156245,
+      "loss": 0.8289,
+      "step": 87
+    },
+    {
+      "epoch": 0.19172113289760348,
+      "grad_norm": 0.984609842300415,
+      "learning_rate": 0.00019930887754993044,
+      "loss": 0.8238,
+      "step": 88
+    },
+    {
+      "epoch": 0.19389978213507625,
+      "grad_norm": 1.030261516571045,
+      "learning_rate": 0.00019928842527335968,
+      "loss": 0.7061,
+      "step": 89
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.8822032809257507,
+      "learning_rate": 0.00019926767585305835,
+      "loss": 0.8622,
+      "step": 90
+    },
+    {
+      "epoch": 0.19825708061002179,
+      "grad_norm": 0.996427059173584,
+      "learning_rate": 0.00019924662935112393,
+      "loss": 0.5348,
+      "step": 91
+    },
+    {
+      "epoch": 0.20043572984749455,
+      "grad_norm": 1.0308480262756348,
+      "learning_rate": 0.000199225285830543,
+      "loss": 0.8325,
+      "step": 92
+    },
+    {
+      "epoch": 0.20261437908496732,
+      "grad_norm": 0.8959431648254395,
+      "learning_rate": 0.000199203645355191,
+      "loss": 0.6136,
+      "step": 93
+    },
+    {
+      "epoch": 0.2047930283224401,
+      "grad_norm": 0.8773916363716125,
+      "learning_rate": 0.00019918170798983211,
+      "loss": 0.577,
+      "step": 94
+    },
+    {
+      "epoch": 0.20697167755991286,
+      "grad_norm": 1.091194748878479,
+      "learning_rate": 0.00019915947380011898,
+      "loss": 0.7751,
+      "step": 95
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 0.8473864197731018,
+      "learning_rate": 0.00019913694285259256,
+      "loss": 0.5831,
+      "step": 96
+    },
+    {
+      "epoch": 0.2113289760348584,
+      "grad_norm": 0.801262378692627,
+      "learning_rate": 0.00019911411521468205,
+      "loss": 0.6089,
+      "step": 97
+    },
+    {
+      "epoch": 0.21350762527233116,
+      "grad_norm": 0.9437965154647827,
+      "learning_rate": 0.00019909099095470444,
+      "loss": 0.7343,
+      "step": 98
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 1.1255544424057007,
+      "learning_rate": 0.00019906757014186442,
+      "loss": 0.6728,
+      "step": 99
+    },
+    {
+      "epoch": 0.2178649237472767,
+      "grad_norm": 0.930216372013092,
+      "learning_rate": 0.00019904385284625424,
+      "loss": 0.5675,
+      "step": 100
+    },
+    {
+      "epoch": 0.22004357298474944,
+      "grad_norm": 0.8021939396858215,
+      "learning_rate": 0.00019901983913885344,
+      "loss": 0.4423,
+      "step": 101
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.5028183460235596,
+      "learning_rate": 0.00019899552909152866,
+      "loss": 0.9797,
+      "step": 102
+    },
+    {
+      "epoch": 0.22440087145969498,
+      "grad_norm": 0.7115923762321472,
+      "learning_rate": 0.00019897092277703333,
+      "loss": 0.4128,
+      "step": 103
+    },
+    {
+      "epoch": 0.22657952069716775,
+      "grad_norm": 0.9592722058296204,
+      "learning_rate": 0.00019894602026900758,
+      "loss": 0.8714,
+      "step": 104
+    },
+    {
+      "epoch": 0.22875816993464052,
+      "grad_norm": 0.8745520114898682,
+      "learning_rate": 0.000198920821641978,
+      "loss": 0.5991,
+      "step": 105
+    },
+    {
+      "epoch": 0.23093681917211328,
+      "grad_norm": 0.7649117708206177,
+      "learning_rate": 0.00019889532697135734,
+      "loss": 0.5501,
+      "step": 106
+    },
+    {
+      "epoch": 0.23311546840958605,
+      "grad_norm": 1.1097913980484009,
+      "learning_rate": 0.0001988695363334443,
+      "loss": 0.5863,
+      "step": 107
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.9224969148635864,
+      "learning_rate": 0.00019884344980542338,
+      "loss": 0.5883,
+      "step": 108
+    },
+    {
+      "epoch": 0.2374727668845316,
+      "grad_norm": 0.7770025134086609,
+      "learning_rate": 0.00019881706746536462,
+      "loss": 0.8375,
+      "step": 109
+    },
+    {
+      "epoch": 0.23965141612200436,
+      "grad_norm": 0.8830885887145996,
+      "learning_rate": 0.00019879038939222329,
+      "loss": 0.6464,
+      "step": 110
+    },
+    {
+      "epoch": 0.24183006535947713,
+      "grad_norm": 0.8932918310165405,
+      "learning_rate": 0.00019876341566583977,
+      "loss": 0.4851,
+      "step": 111
+    },
+    {
+      "epoch": 0.2440087145969499,
+      "grad_norm": 0.8250621557235718,
+      "learning_rate": 0.0001987361463669392,
+      "loss": 0.5658,
+      "step": 112
+    },
+    {
+      "epoch": 0.24618736383442266,
+      "grad_norm": 0.9288647174835205,
+      "learning_rate": 0.00019870858157713123,
+      "loss": 0.5441,
+      "step": 113
+    },
+    {
+      "epoch": 0.24836601307189543,
+      "grad_norm": 0.8258922100067139,
+      "learning_rate": 0.00019868072137891002,
+      "loss": 0.764,
+      "step": 114
+    },
+    {
+      "epoch": 0.25054466230936817,
+      "grad_norm": 0.8087350726127625,
+      "learning_rate": 0.00019865256585565363,
+      "loss": 0.5816,
+      "step": 115
+    },
+    {
+      "epoch": 0.25054466230936817,
+      "eval_loss": 0.6156808733940125,
+      "eval_runtime": 0.937,
+      "eval_samples_per_second": 182.501,
+      "eval_steps_per_second": 13.874,
+      "step": 115
+    },
+    {
+      "epoch": 0.25272331154684097,
+      "grad_norm": 1.0198040008544922,
+      "learning_rate": 0.00019862411509162406,
+      "loss": 0.9471,
+      "step": 116
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "grad_norm": 0.8376523852348328,
+      "learning_rate": 0.00019859536917196687,
+      "loss": 0.6166,
+      "step": 117
+    },
+    {
+      "epoch": 0.2570806100217865,
+      "grad_norm": 0.8766109347343445,
+      "learning_rate": 0.0001985663281827108,
+      "loss": 0.6737,
+      "step": 118
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 1.072192668914795,
+      "learning_rate": 0.00019853699221076792,
+      "loss": 0.6403,
+      "step": 119
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.8205565214157104,
+      "learning_rate": 0.00019850736134393286,
+      "loss": 0.4247,
+      "step": 120
+    },
+    {
+      "epoch": 0.2636165577342048,
+      "grad_norm": 1.0622146129608154,
+      "learning_rate": 0.00019847743567088293,
+      "loss": 0.6497,
+      "step": 121
+    },
+    {
+      "epoch": 0.2657952069716776,
+      "grad_norm": 0.8463292717933655,
+      "learning_rate": 0.00019844721528117766,
+      "loss": 0.6587,
+      "step": 122
+    },
+    {
+      "epoch": 0.2679738562091503,
+      "grad_norm": 0.9597845673561096,
+      "learning_rate": 0.0001984167002652586,
+      "loss": 0.4752,
+      "step": 123
+    },
+    {
+      "epoch": 0.2701525054466231,
+      "grad_norm": 0.8975586295127869,
+      "learning_rate": 0.00019838589071444903,
+      "loss": 0.7978,
+      "step": 124
+    },
+    {
+      "epoch": 0.27233115468409586,
+      "grad_norm": 0.8363540768623352,
+      "learning_rate": 0.00019835478672095374,
+      "loss": 0.7359,
+      "step": 125
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 1.0208615064620972,
+      "learning_rate": 0.00019832338837785863,
+      "loss": 0.518,
+      "step": 126
+    },
+    {
+      "epoch": 0.2766884531590414,
+      "grad_norm": 1.14145028591156,
+      "learning_rate": 0.0001982916957791306,
+      "loss": 0.7642,
+      "step": 127
+    },
+    {
+      "epoch": 0.2788671023965142,
+      "grad_norm": 0.9274200797080994,
+      "learning_rate": 0.00019825970901961705,
+      "loss": 0.5288,
+      "step": 128
+    },
+    {
+      "epoch": 0.28104575163398693,
+      "grad_norm": 0.8783562779426575,
+      "learning_rate": 0.0001982274281950459,
+      "loss": 0.5958,
+      "step": 129
+    },
+    {
+      "epoch": 0.28322440087145967,
+      "grad_norm": 0.9028067588806152,
+      "learning_rate": 0.000198194853402025,
+      "loss": 0.6075,
+      "step": 130
+    },
+    {
+      "epoch": 0.28540305010893247,
+      "grad_norm": 0.9846379160881042,
+      "learning_rate": 0.00019816198473804198,
+      "loss": 0.8254,
+      "step": 131
+    },
+    {
+      "epoch": 0.2875816993464052,
+      "grad_norm": 0.9409753680229187,
+      "learning_rate": 0.00019812882230146398,
+      "loss": 0.704,
+      "step": 132
+    },
+    {
+      "epoch": 0.289760348583878,
+      "grad_norm": 0.8969582915306091,
+      "learning_rate": 0.00019809536619153732,
+      "loss": 0.6107,
+      "step": 133
+    },
+    {
+      "epoch": 0.29193899782135074,
+      "grad_norm": 0.7812852263450623,
+      "learning_rate": 0.00019806161650838723,
+      "loss": 0.5671,
+      "step": 134
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.8860548734664917,
+      "learning_rate": 0.00019802757335301741,
+      "loss": 0.5248,
+      "step": 135
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.8217918276786804,
+      "learning_rate": 0.00019799323682731,
+      "loss": 0.4935,
+      "step": 136
+    },
+    {
+      "epoch": 0.2984749455337691,
+      "grad_norm": 0.7621735334396362,
+      "learning_rate": 0.00019795860703402505,
+      "loss": 0.5984,
+      "step": 137
+    },
+    {
+      "epoch": 0.3006535947712418,
+      "grad_norm": 0.9418565630912781,
+      "learning_rate": 0.00019792368407680025,
+      "loss": 0.558,
+      "step": 138
+    },
+    {
+      "epoch": 0.3028322440087146,
+      "grad_norm": 0.819114625453949,
+      "learning_rate": 0.00019788846806015066,
+      "loss": 0.3791,
+      "step": 139
+    },
+    {
+      "epoch": 0.30501089324618735,
+      "grad_norm": 0.9072156548500061,
+      "learning_rate": 0.00019785295908946848,
+      "loss": 0.4462,
+      "step": 140
+    },
+    {
+      "epoch": 0.30718954248366015,
+      "grad_norm": 0.8303220868110657,
+      "learning_rate": 0.00019781715727102252,
+      "loss": 0.4959,
+      "step": 141
+    },
+    {
+      "epoch": 0.3093681917211329,
+      "grad_norm": 0.8586477041244507,
+      "learning_rate": 0.00019778106271195806,
+      "loss": 0.4701,
+      "step": 142
+    },
+    {
+      "epoch": 0.3115468409586057,
+      "grad_norm": 0.7374873757362366,
+      "learning_rate": 0.00019774467552029646,
+      "loss": 0.407,
+      "step": 143
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 1.1180788278579712,
+      "learning_rate": 0.00019770799580493494,
+      "loss": 0.6304,
+      "step": 144
+    },
+    {
+      "epoch": 0.3159041394335512,
+      "grad_norm": 0.9823700189590454,
+      "learning_rate": 0.000197671023675646,
+      "loss": 0.5079,
+      "step": 145
+    },
+    {
+      "epoch": 0.31808278867102396,
+      "grad_norm": 0.8474340438842773,
+      "learning_rate": 0.00019763375924307735,
+      "loss": 0.5708,
+      "step": 146
+    },
+    {
+      "epoch": 0.3202614379084967,
+      "grad_norm": 0.9172300100326538,
+      "learning_rate": 0.00019759620261875155,
+      "loss": 0.418,
+      "step": 147
+    },
+    {
+      "epoch": 0.3224400871459695,
+      "grad_norm": 0.7413074374198914,
+      "learning_rate": 0.0001975583539150655,
+      "loss": 0.4531,
+      "step": 148
+    },
+    {
+      "epoch": 0.32461873638344224,
+      "grad_norm": 0.7417133450508118,
+      "learning_rate": 0.00019752021324529023,
+      "loss": 0.5158,
+      "step": 149
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 0.774067223072052,
+      "learning_rate": 0.00019748178072357065,
+      "loss": 0.5995,
+      "step": 150
+    },
+    {
+      "epoch": 0.3289760348583878,
+      "grad_norm": 0.9123216867446899,
+      "learning_rate": 0.00019744305646492497,
+      "loss": 0.6477,
+      "step": 151
+    },
+    {
+      "epoch": 0.3311546840958606,
+      "grad_norm": 0.8347046375274658,
+      "learning_rate": 0.00019740404058524457,
+      "loss": 0.6527,
+      "step": 152
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.9968402981758118,
+      "learning_rate": 0.00019736473320129352,
+      "loss": 0.5282,
+      "step": 153
+    },
+    {
+      "epoch": 0.3355119825708061,
+      "grad_norm": 0.7431806921958923,
+      "learning_rate": 0.00019732513443070836,
+      "loss": 0.5553,
+      "step": 154
+    },
+    {
+      "epoch": 0.33769063180827885,
+      "grad_norm": 0.9280023574829102,
+      "learning_rate": 0.0001972852443919976,
+      "loss": 0.7504,
+      "step": 155
+    },
+    {
+      "epoch": 0.33986928104575165,
+      "grad_norm": 0.9563156366348267,
+      "learning_rate": 0.00019724506320454153,
+      "loss": 0.4566,
+      "step": 156
+    },
+    {
+      "epoch": 0.3420479302832244,
+      "grad_norm": 0.744659960269928,
+      "learning_rate": 0.00019720459098859165,
+      "loss": 0.5929,
+      "step": 157
+    },
+    {
+      "epoch": 0.3442265795206972,
+      "grad_norm": 0.8504654765129089,
+      "learning_rate": 0.0001971638278652705,
+      "loss": 0.5152,
+      "step": 158
+    },
+    {
+      "epoch": 0.3464052287581699,
+      "grad_norm": 0.9335165023803711,
+      "learning_rate": 0.0001971227739565712,
+      "loss": 0.5115,
+      "step": 159
+    },
+    {
+      "epoch": 0.3485838779956427,
+      "grad_norm": 1.0398534536361694,
+      "learning_rate": 0.0001970814293853572,
+      "loss": 0.4626,
+      "step": 160
+    },
+    {
+      "epoch": 0.35076252723311546,
+      "grad_norm": 0.7855281233787537,
+      "learning_rate": 0.0001970397942753617,
+      "loss": 0.4245,
+      "step": 161
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.7897714972496033,
+      "learning_rate": 0.00019699786875118747,
+      "loss": 0.5555,
+      "step": 162
+    },
+    {
+      "epoch": 0.355119825708061,
+      "grad_norm": 0.8648003935813904,
+      "learning_rate": 0.0001969556529383064,
+      "loss": 0.5558,
+      "step": 163
+    },
+    {
+      "epoch": 0.3572984749455338,
+      "grad_norm": 1.0440359115600586,
+      "learning_rate": 0.00019691314696305913,
+      "loss": 0.4879,
+      "step": 164
+    },
+    {
+      "epoch": 0.35947712418300654,
+      "grad_norm": 0.8991299867630005,
+      "learning_rate": 0.00019687035095265475,
+      "loss": 0.4131,
+      "step": 165
+    },
+    {
+      "epoch": 0.3616557734204793,
+      "grad_norm": 1.070555329322815,
+      "learning_rate": 0.00019682726503517017,
+      "loss": 0.4959,
+      "step": 166
+    },
+    {
+      "epoch": 0.3638344226579521,
+      "grad_norm": 0.751699686050415,
+      "learning_rate": 0.00019678388933955015,
+      "loss": 0.4098,
+      "step": 167
+    },
+    {
+      "epoch": 0.3660130718954248,
+      "grad_norm": 0.7820857763290405,
+      "learning_rate": 0.00019674022399560648,
+      "loss": 0.4611,
+      "step": 168
+    },
+    {
+      "epoch": 0.3681917211328976,
+      "grad_norm": 0.7827489376068115,
+      "learning_rate": 0.00019669626913401792,
+      "loss": 0.3593,
+      "step": 169
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.8705342411994934,
+      "learning_rate": 0.00019665202488632956,
+      "loss": 0.4037,
+      "step": 170
+    },
+    {
+      "epoch": 0.37254901960784315,
+      "grad_norm": 0.9181383848190308,
+      "learning_rate": 0.00019660749138495268,
+      "loss": 0.5621,
+      "step": 171
+    },
+    {
+      "epoch": 0.3747276688453159,
+      "grad_norm": 0.7258014678955078,
+      "learning_rate": 0.0001965626687631641,
+      "loss": 0.3909,
+      "step": 172
+    },
+    {
+      "epoch": 0.3769063180827887,
+      "grad_norm": 0.7386276721954346,
+      "learning_rate": 0.00019651755715510602,
+      "loss": 0.5974,
+      "step": 173
+    },
+    {
+      "epoch": 0.3790849673202614,
+      "grad_norm": 0.7849751710891724,
+      "learning_rate": 0.00019647215669578536,
+      "loss": 0.4947,
+      "step": 174
+    },
+    {
+      "epoch": 0.3812636165577342,
+      "grad_norm": 0.7632936239242554,
+      "learning_rate": 0.00019642646752107362,
+      "loss": 0.4886,
+      "step": 175
+    },
+    {
+      "epoch": 0.38344226579520696,
+      "grad_norm": 0.8370786309242249,
+      "learning_rate": 0.00019638048976770628,
+      "loss": 0.4741,
+      "step": 176
+    },
+    {
+      "epoch": 0.38562091503267976,
+      "grad_norm": 0.8441713452339172,
+      "learning_rate": 0.00019633422357328239,
+      "loss": 0.4939,
+      "step": 177
+    },
+    {
+      "epoch": 0.3877995642701525,
+      "grad_norm": 0.7680661082267761,
+      "learning_rate": 0.00019628766907626446,
+      "loss": 0.5976,
+      "step": 178
+    },
+    {
+      "epoch": 0.3899782135076253,
+      "grad_norm": 0.8030869364738464,
+      "learning_rate": 0.00019624082641597754,
+      "loss": 0.4914,
+      "step": 179
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.8066624402999878,
+      "learning_rate": 0.00019619369573260924,
+      "loss": 0.4982,
+      "step": 180
+    },
+    {
+      "epoch": 0.39433551198257083,
+      "grad_norm": 0.7550255060195923,
+      "learning_rate": 0.00019614627716720912,
+      "loss": 0.3796,
+      "step": 181
+    },
+    {
+      "epoch": 0.39651416122004357,
+      "grad_norm": 0.761080265045166,
+      "learning_rate": 0.00019609857086168823,
+      "loss": 0.4118,
+      "step": 182
+    },
+    {
+      "epoch": 0.39869281045751637,
+      "grad_norm": 1.061673641204834,
+      "learning_rate": 0.00019605057695881885,
+      "loss": 0.4461,
+      "step": 183
+    },
+    {
+      "epoch": 0.4008714596949891,
+      "grad_norm": 0.8266555070877075,
+      "learning_rate": 0.00019600229560223388,
+      "loss": 0.4915,
+      "step": 184
+    },
+    {
+      "epoch": 0.40305010893246185,
+      "grad_norm": 0.769981861114502,
+      "learning_rate": 0.00019595372693642654,
+      "loss": 0.3993,
+      "step": 185
+    },
+    {
+      "epoch": 0.40522875816993464,
+      "grad_norm": 0.8316985368728638,
+      "learning_rate": 0.00019590487110674983,
+      "loss": 0.598,
+      "step": 186
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.7869564890861511,
+      "learning_rate": 0.00019585572825941627,
+      "loss": 0.5088,
+      "step": 187
+    },
+    {
+      "epoch": 0.4095860566448802,
+      "grad_norm": 0.7254141569137573,
+      "learning_rate": 0.0001958062985414972,
+      "loss": 0.3948,
+      "step": 188
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.7505261898040771,
+      "learning_rate": 0.00019575658210092259,
+      "loss": 0.3883,
+      "step": 189
+    },
+    {
+      "epoch": 0.4139433551198257,
+      "grad_norm": 0.7498146891593933,
+      "learning_rate": 0.00019570657908648048,
+      "loss": 0.4072,
+      "step": 190
+    },
+    {
+      "epoch": 0.41612200435729846,
+      "grad_norm": 0.9777516722679138,
+      "learning_rate": 0.00019565628964781647,
+      "loss": 0.4711,
+      "step": 191
+    },
+    {
+      "epoch": 0.41830065359477125,
+      "grad_norm": 0.719313383102417,
+      "learning_rate": 0.0001956057139354335,
+      "loss": 0.2645,
+      "step": 192
+    },
+    {
+      "epoch": 0.420479302832244,
+      "grad_norm": 0.826934814453125,
+      "learning_rate": 0.0001955548521006911,
+      "loss": 0.4608,
+      "step": 193
+    },
+    {
+      "epoch": 0.4226579520697168,
+      "grad_norm": 0.7773908376693726,
+      "learning_rate": 0.0001955037042958052,
+      "loss": 0.6364,
+      "step": 194
+    },
+    {
+      "epoch": 0.42483660130718953,
+      "grad_norm": 0.8829189538955688,
+      "learning_rate": 0.00019545227067384747,
+      "loss": 0.5166,
+      "step": 195
+    },
+    {
+      "epoch": 0.42701525054466233,
+      "grad_norm": 0.7444214820861816,
+      "learning_rate": 0.00019540055138874505,
+      "loss": 0.4784,
+      "step": 196
+    },
+    {
+      "epoch": 0.42919389978213507,
+      "grad_norm": 0.7535512447357178,
+      "learning_rate": 0.0001953485465952799,
+      "loss": 0.328,
+      "step": 197
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 0.867964506149292,
+      "learning_rate": 0.00019529625644908847,
+      "loss": 0.4954,
+      "step": 198
+    },
+    {
+      "epoch": 0.4335511982570806,
+      "grad_norm": 0.8096396923065186,
+      "learning_rate": 0.00019524368110666122,
+      "loss": 0.409,
+      "step": 199
+    },
+    {
+      "epoch": 0.4357298474945534,
+      "grad_norm": 0.6851803064346313,
+      "learning_rate": 0.0001951908207253421,
+      "loss": 0.3642,
+      "step": 200
+    },
+    {
+      "epoch": 0.43790849673202614,
+      "grad_norm": 1.0261396169662476,
+      "learning_rate": 0.00019513767546332813,
+      "loss": 0.5437,
+      "step": 201
+    },
+    {
+      "epoch": 0.4400871459694989,
+      "grad_norm": 0.6751096248626709,
+      "learning_rate": 0.00019508424547966884,
+      "loss": 0.3054,
+      "step": 202
+    },
+    {
+      "epoch": 0.4422657952069717,
+      "grad_norm": 0.9070213437080383,
+      "learning_rate": 0.00019503053093426593,
+      "loss": 0.5467,
+      "step": 203
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.7909525632858276,
+      "learning_rate": 0.00019497653198787264,
+      "loss": 0.4506,
+      "step": 204
+    },
+    {
+      "epoch": 0.4466230936819172,
+      "grad_norm": 0.8636406064033508,
+      "learning_rate": 0.00019492224880209344,
+      "loss": 0.4917,
+      "step": 205
+    },
+    {
+      "epoch": 0.44880174291938996,
+      "grad_norm": 0.8827958106994629,
+      "learning_rate": 0.00019486768153938338,
+      "loss": 0.6783,
+      "step": 206
+    },
+    {
+      "epoch": 0.45098039215686275,
+      "grad_norm": 0.8108576536178589,
+      "learning_rate": 0.00019481283036304768,
+      "loss": 0.5415,
+      "step": 207
+    },
+    {
+      "epoch": 0.4531590413943355,
+      "grad_norm": 0.700524091720581,
+      "learning_rate": 0.0001947576954372413,
+      "loss": 0.2578,
+      "step": 208
+    },
+    {
+      "epoch": 0.4553376906318083,
+      "grad_norm": 0.6894106268882751,
+      "learning_rate": 0.00019470227692696833,
+      "loss": 0.4008,
+      "step": 209
+    },
+    {
+      "epoch": 0.45751633986928103,
+      "grad_norm": 0.762399435043335,
+      "learning_rate": 0.00019464657499808152,
+      "loss": 0.448,
+      "step": 210
+    },
+    {
+      "epoch": 0.4596949891067538,
+      "grad_norm": 0.7530399560928345,
+      "learning_rate": 0.00019459058981728192,
+      "loss": 0.4793,
+      "step": 211
+    },
+    {
+      "epoch": 0.46187363834422657,
+      "grad_norm": 0.8698046803474426,
+      "learning_rate": 0.0001945343215521182,
+      "loss": 0.5627,
+      "step": 212
+    },
+    {
+      "epoch": 0.46405228758169936,
+      "grad_norm": 0.9562462568283081,
+      "learning_rate": 0.00019447777037098622,
+      "loss": 0.6461,
+      "step": 213
+    },
+    {
+      "epoch": 0.4662309368191721,
+      "grad_norm": 0.7317548990249634,
+      "learning_rate": 0.0001944209364431286,
+      "loss": 0.2913,
+      "step": 214
+    },
+    {
+      "epoch": 0.4684095860566449,
+      "grad_norm": 0.8016018271446228,
+      "learning_rate": 0.00019436381993863405,
+      "loss": 0.4218,
+      "step": 215
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.7906899452209473,
+      "learning_rate": 0.00019430642102843707,
+      "loss": 0.3951,
+      "step": 216
+    },
+    {
+      "epoch": 0.47276688453159044,
+      "grad_norm": 0.7488080859184265,
+      "learning_rate": 0.0001942487398843172,
+      "loss": 0.2522,
+      "step": 217
+    },
+    {
+      "epoch": 0.4749455337690632,
+      "grad_norm": 0.7537955641746521,
+      "learning_rate": 0.00019419077667889872,
+      "loss": 0.4182,
+      "step": 218
+    },
+    {
+      "epoch": 0.477124183006536,
+      "grad_norm": 1.090034008026123,
+      "learning_rate": 0.00019413253158565006,
+      "loss": 0.4396,
+      "step": 219
+    },
+    {
+      "epoch": 0.4793028322440087,
+      "grad_norm": 0.8850147724151611,
+      "learning_rate": 0.00019407400477888315,
+      "loss": 0.4225,
+      "step": 220
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.6652522683143616,
+      "learning_rate": 0.00019401519643375315,
+      "loss": 0.3252,
+      "step": 221
+    },
+    {
+      "epoch": 0.48366013071895425,
+      "grad_norm": 0.9398255348205566,
+      "learning_rate": 0.00019395610672625767,
+      "loss": 0.3825,
+      "step": 222
+    },
+    {
+      "epoch": 0.485838779956427,
+      "grad_norm": 0.7577664852142334,
+      "learning_rate": 0.00019389673583323645,
+      "loss": 0.4972,
+      "step": 223
+    },
+    {
+      "epoch": 0.4880174291938998,
+      "grad_norm": 0.7722988724708557,
+      "learning_rate": 0.00019383708393237075,
+      "loss": 0.3655,
+      "step": 224
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.9242033958435059,
+      "learning_rate": 0.0001937771512021827,
+      "loss": 0.5322,
+      "step": 225
+    },
+    {
+      "epoch": 0.4923747276688453,
+      "grad_norm": 0.7697513699531555,
+      "learning_rate": 0.00019371693782203498,
+      "loss": 0.3516,
+      "step": 226
+    },
+    {
+      "epoch": 0.49455337690631807,
+      "grad_norm": 1.0141658782958984,
+      "learning_rate": 0.00019365644397213014,
+      "loss": 0.4072,
+      "step": 227
+    },
+    {
+      "epoch": 0.49673202614379086,
+      "grad_norm": 0.8579118847846985,
+      "learning_rate": 0.00019359566983351013,
+      "loss": 0.5341,
+      "step": 228
+    },
+    {
+      "epoch": 0.4989106753812636,
+      "grad_norm": 0.9969218969345093,
+      "learning_rate": 0.0001935346155880557,
+      "loss": 0.5544,
+      "step": 229
+    },
+    {
+      "epoch": 0.5010893246187363,
+      "grad_norm": 0.7654063105583191,
+      "learning_rate": 0.0001934732814184859,
+      "loss": 0.3604,
+      "step": 230
+    },
+    {
+      "epoch": 0.5010893246187363,
+      "eval_loss": 0.430705189704895,
+      "eval_runtime": 0.9369,
+      "eval_samples_per_second": 182.508,
+      "eval_steps_per_second": 13.875,
+      "step": 230
+    },
+    {
+      "epoch": 0.5032679738562091,
+      "grad_norm": 0.8155052661895752,
+      "learning_rate": 0.00019341166750835748,
+      "loss": 0.3841,
+      "step": 231
+    },
+    {
+      "epoch": 0.5054466230936819,
+      "grad_norm": 1.005814790725708,
+      "learning_rate": 0.00019334977404206443,
+      "loss": 0.4976,
+      "step": 232
+    },
+    {
+      "epoch": 0.5076252723311547,
+      "grad_norm": 0.795301079750061,
+      "learning_rate": 0.00019328760120483743,
+      "loss": 0.347,
+      "step": 233
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 0.8294497728347778,
+      "learning_rate": 0.00019322514918274308,
+      "loss": 0.3366,
+      "step": 234
+    },
+    {
+      "epoch": 0.5119825708061002,
+      "grad_norm": 1.0151102542877197,
+      "learning_rate": 0.0001931624181626836,
+      "loss": 0.3217,
+      "step": 235
+    },
+    {
+      "epoch": 0.514161220043573,
+      "grad_norm": 0.8590940833091736,
+      "learning_rate": 0.00019309940833239626,
+      "loss": 0.4399,
+      "step": 236
+    },
+    {
+      "epoch": 0.5163398692810458,
+      "grad_norm": 0.8852725028991699,
+      "learning_rate": 0.00019303611988045257,
+      "loss": 0.3737,
+      "step": 237
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.8230773210525513,
+      "learning_rate": 0.00019297255299625797,
+      "loss": 0.4262,
+      "step": 238
+    },
+    {
+      "epoch": 0.5206971677559913,
+      "grad_norm": 0.6675543785095215,
+      "learning_rate": 0.00019290870787005114,
+      "loss": 0.291,
+      "step": 239
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.867770791053772,
+      "learning_rate": 0.00019284458469290354,
+      "loss": 0.4791,
+      "step": 240
+    },
+    {
+      "epoch": 0.5250544662309368,
+      "grad_norm": 0.6569726467132568,
+      "learning_rate": 0.0001927801836567187,
+      "loss": 0.3331,
+      "step": 241
+    },
+    {
+      "epoch": 0.5272331154684096,
+      "grad_norm": 0.9207850098609924,
+      "learning_rate": 0.00019271550495423168,
+      "loss": 0.3867,
+      "step": 242
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.9937344789505005,
+      "learning_rate": 0.00019265054877900858,
+      "loss": 0.4788,
+      "step": 243
+    },
+    {
+      "epoch": 0.5315904139433552,
+      "grad_norm": 0.6370213627815247,
+      "learning_rate": 0.00019258531532544585,
+      "loss": 0.2628,
+      "step": 244
+    },
+    {
+      "epoch": 0.5337690631808278,
+      "grad_norm": 0.7503904104232788,
+      "learning_rate": 0.00019251980478876985,
+      "loss": 0.3214,
+      "step": 245
+    },
+    {
+      "epoch": 0.5359477124183006,
+      "grad_norm": 0.8075821399688721,
+      "learning_rate": 0.00019245401736503608,
+      "loss": 0.4626,
+      "step": 246
+    },
+    {
+      "epoch": 0.5381263616557734,
+      "grad_norm": 0.7386597990989685,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.366,
+      "step": 247
+    },
+    {
+      "epoch": 0.5403050108932462,
+      "grad_norm": 0.7394566535949707,
+      "learning_rate": 0.00019232161264475997,
+      "loss": 0.387,
+      "step": 248
+    },
+    {
+      "epoch": 0.5424836601307189,
+      "grad_norm": 0.7640907168388367,
+      "learning_rate": 0.0001922549957444696,
+      "loss": 0.58,
+      "step": 249
+    },
+    {
+      "epoch": 0.5446623093681917,
+      "grad_norm": 0.6614570021629333,
+      "learning_rate": 0.00019218810274962417,
+      "loss": 0.3073,
+      "step": 250
+    },
+    {
+      "epoch": 0.5468409586056645,
+      "grad_norm": 0.966230034828186,
+      "learning_rate": 0.0001921209338604166,
+      "loss": 0.5173,
+      "step": 251
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 0.822700560092926,
+      "learning_rate": 0.00019205348927786532,
+      "loss": 0.4205,
+      "step": 252
+    },
+    {
+      "epoch": 0.55119825708061,
+      "grad_norm": 0.7053878307342529,
+      "learning_rate": 0.00019198576920381405,
+      "loss": 0.3872,
+      "step": 253
+    },
+    {
+      "epoch": 0.5533769063180828,
+      "grad_norm": 0.7365344166755676,
+      "learning_rate": 0.00019191777384093081,
+      "loss": 0.2189,
+      "step": 254
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.738994300365448,
+      "learning_rate": 0.0001918495033927076,
+      "loss": 0.4104,
+      "step": 255
+    },
+    {
+      "epoch": 0.5577342047930284,
+      "grad_norm": 0.6301658153533936,
+      "learning_rate": 0.0001917809580634596,
+      "loss": 0.217,
+      "step": 256
+    },
+    {
+      "epoch": 0.5599128540305011,
+      "grad_norm": 0.6912908554077148,
+      "learning_rate": 0.0001917121380583247,
+      "loss": 0.2477,
+      "step": 257
+    },
+    {
+      "epoch": 0.5620915032679739,
+      "grad_norm": 0.7470822930335999,
+      "learning_rate": 0.00019164304358326275,
+      "loss": 0.2822,
+      "step": 258
+    },
+    {
+      "epoch": 0.5642701525054467,
+      "grad_norm": 0.8313736915588379,
+      "learning_rate": 0.0001915736748450551,
+      "loss": 0.4136,
+      "step": 259
+    },
+    {
+      "epoch": 0.5664488017429193,
+      "grad_norm": 0.9498727321624756,
+      "learning_rate": 0.00019150403205130383,
+      "loss": 0.4656,
+      "step": 260
+    },
+    {
+      "epoch": 0.5686274509803921,
+      "grad_norm": 0.7486637830734253,
+      "learning_rate": 0.0001914341154104312,
+      "loss": 0.3612,
+      "step": 261
+    },
+    {
+      "epoch": 0.5708061002178649,
+      "grad_norm": 0.7852402925491333,
+      "learning_rate": 0.00019136392513167903,
+      "loss": 0.3849,
+      "step": 262
+    },
+    {
+      "epoch": 0.5729847494553377,
+      "grad_norm": 0.7787222862243652,
+      "learning_rate": 0.00019129346142510812,
+      "loss": 0.3202,
+      "step": 263
+    },
+    {
+      "epoch": 0.5751633986928104,
+      "grad_norm": 0.7108213305473328,
+      "learning_rate": 0.00019122272450159745,
+      "loss": 0.2964,
+      "step": 264
+    },
+    {
+      "epoch": 0.5773420479302832,
+      "grad_norm": 0.7679167985916138,
+      "learning_rate": 0.00019115171457284382,
+      "loss": 0.3068,
+      "step": 265
+    },
+    {
+      "epoch": 0.579520697167756,
+      "grad_norm": 0.9409091472625732,
+      "learning_rate": 0.0001910804318513609,
+      "loss": 0.3865,
+      "step": 266
+    },
+    {
+      "epoch": 0.5816993464052288,
+      "grad_norm": 0.7475356459617615,
+      "learning_rate": 0.00019100887655047885,
+      "loss": 0.3727,
+      "step": 267
+    },
+    {
+      "epoch": 0.5838779956427015,
+      "grad_norm": 0.8223069310188293,
+      "learning_rate": 0.0001909370488843436,
+      "loss": 0.3594,
+      "step": 268
+    },
+    {
+      "epoch": 0.5860566448801743,
+      "grad_norm": 0.8433902263641357,
+      "learning_rate": 0.00019086494906791614,
+      "loss": 0.3627,
+      "step": 269
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.7213712334632874,
+      "learning_rate": 0.00019079257731697196,
+      "loss": 0.3216,
+      "step": 270
+    },
+    {
+      "epoch": 0.5904139433551199,
+      "grad_norm": 0.9422861337661743,
+      "learning_rate": 0.00019071993384810036,
+      "loss": 0.4973,
+      "step": 271
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.7964383363723755,
+      "learning_rate": 0.0001906470188787039,
+      "loss": 0.3558,
+      "step": 272
+    },
+    {
+      "epoch": 0.5947712418300654,
+      "grad_norm": 0.8275824785232544,
+      "learning_rate": 0.0001905738326269975,
+      "loss": 0.2985,
+      "step": 273
+    },
+    {
+      "epoch": 0.5969498910675382,
+      "grad_norm": 0.9769518971443176,
+      "learning_rate": 0.00019050037531200814,
+      "loss": 0.5299,
+      "step": 274
+    },
+    {
+      "epoch": 0.599128540305011,
+      "grad_norm": 0.6739898920059204,
+      "learning_rate": 0.0001904266471535739,
+      "loss": 0.2324,
+      "step": 275
+    },
+    {
+      "epoch": 0.6013071895424836,
+      "grad_norm": 0.78001868724823,
+      "learning_rate": 0.00019035264837234347,
+      "loss": 0.3311,
+      "step": 276
+    },
+    {
+      "epoch": 0.6034858387799564,
+      "grad_norm": 0.6510067582130432,
+      "learning_rate": 0.00019027837918977544,
+      "loss": 0.2284,
+      "step": 277
+    },
+    {
+      "epoch": 0.6056644880174292,
+      "grad_norm": 0.7791504859924316,
+      "learning_rate": 0.00019020383982813765,
+      "loss": 0.3247,
+      "step": 278
+    },
+    {
+      "epoch": 0.6078431372549019,
+      "grad_norm": 0.7968712449073792,
+      "learning_rate": 0.00019012903051050643,
+      "loss": 0.3379,
+      "step": 279
+    },
+    {
+      "epoch": 0.6100217864923747,
+      "grad_norm": 0.7802785038948059,
+      "learning_rate": 0.00019005395146076616,
+      "loss": 0.3113,
+      "step": 280
+    },
+    {
+      "epoch": 0.6122004357298475,
+      "grad_norm": 0.8003398180007935,
+      "learning_rate": 0.00018997860290360832,
+      "loss": 0.3467,
+      "step": 281
+    },
+    {
+      "epoch": 0.6143790849673203,
+      "grad_norm": 0.9283706545829773,
+      "learning_rate": 0.00018990298506453104,
+      "loss": 0.3301,
+      "step": 282
+    },
+    {
+      "epoch": 0.616557734204793,
+      "grad_norm": 0.95260089635849,
+      "learning_rate": 0.00018982709816983828,
+      "loss": 0.4446,
+      "step": 283
+    },
+    {
+      "epoch": 0.6187363834422658,
+      "grad_norm": 0.8746076226234436,
+      "learning_rate": 0.0001897509424466393,
+      "loss": 0.3264,
+      "step": 284
+    },
+    {
+      "epoch": 0.6209150326797386,
+      "grad_norm": 0.9784271717071533,
+      "learning_rate": 0.00018967451812284777,
+      "loss": 0.3103,
+      "step": 285
+    },
+    {
+      "epoch": 0.6230936819172114,
+      "grad_norm": 0.7417327165603638,
+      "learning_rate": 0.00018959782542718128,
+      "loss": 0.3489,
+      "step": 286
+    },
+    {
+      "epoch": 0.6252723311546841,
+      "grad_norm": 0.835861325263977,
+      "learning_rate": 0.00018952086458916064,
+      "loss": 0.4059,
+      "step": 287
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.7815294861793518,
+      "learning_rate": 0.000189443635839109,
+      "loss": 0.3252,
+      "step": 288
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.7762477993965149,
+      "learning_rate": 0.00018936613940815145,
+      "loss": 0.3905,
+      "step": 289
+    },
+    {
+      "epoch": 0.6318082788671024,
+      "grad_norm": 0.7671297192573547,
+      "learning_rate": 0.00018928837552821404,
+      "loss": 0.3945,
+      "step": 290
+    },
+    {
+      "epoch": 0.6339869281045751,
+      "grad_norm": 0.7193905711174011,
+      "learning_rate": 0.00018921034443202333,
+      "loss": 0.2897,
+      "step": 291
+    },
+    {
+      "epoch": 0.6361655773420479,
+      "grad_norm": 0.7806922793388367,
+      "learning_rate": 0.0001891320463531055,
+      "loss": 0.3675,
+      "step": 292
+    },
+    {
+      "epoch": 0.6383442265795207,
+      "grad_norm": 0.9675951600074768,
+      "learning_rate": 0.0001890534815257858,
+      "loss": 0.2949,
+      "step": 293
+    },
+    {
+      "epoch": 0.6405228758169934,
+      "grad_norm": 0.7414330840110779,
+      "learning_rate": 0.00018897465018518782,
+      "loss": 0.2468,
+      "step": 294
+    },
+    {
+      "epoch": 0.6427015250544662,
+      "grad_norm": 0.9123559594154358,
+      "learning_rate": 0.00018889555256723262,
+      "loss": 0.3618,
+      "step": 295
+    },
+    {
+      "epoch": 0.644880174291939,
+      "grad_norm": 0.8628408312797546,
+      "learning_rate": 0.0001888161889086383,
+      "loss": 0.4728,
+      "step": 296
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.9308063983917236,
+      "learning_rate": 0.00018873655944691902,
+      "loss": 0.3469,
+      "step": 297
+    },
+    {
+      "epoch": 0.6492374727668845,
+      "grad_norm": 0.7682824730873108,
+      "learning_rate": 0.00018865666442038456,
+      "loss": 0.4138,
+      "step": 298
+    },
+    {
+      "epoch": 0.6514161220043573,
+      "grad_norm": 0.8124529123306274,
+      "learning_rate": 0.00018857650406813937,
+      "loss": 0.3172,
+      "step": 299
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 1.0015543699264526,
+      "learning_rate": 0.00018849607863008193,
+      "loss": 0.3274,
+      "step": 300
+    },
+    {
+      "epoch": 0.6557734204793029,
+      "grad_norm": 0.8008652329444885,
+      "learning_rate": 0.0001884153883469041,
+      "loss": 0.2765,
+      "step": 301
+    },
+    {
+      "epoch": 0.6579520697167756,
+      "grad_norm": 0.8472908139228821,
+      "learning_rate": 0.0001883344334600904,
+      "loss": 0.362,
+      "step": 302
+    },
+    {
+      "epoch": 0.6601307189542484,
+      "grad_norm": 0.953235387802124,
+      "learning_rate": 0.0001882532142119171,
+      "loss": 0.383,
+      "step": 303
+    },
+    {
+      "epoch": 0.6623093681917211,
+      "grad_norm": 0.9220999479293823,
+      "learning_rate": 0.00018817173084545176,
+      "loss": 0.4209,
+      "step": 304
+    },
+    {
+      "epoch": 0.664488017429194,
+      "grad_norm": 0.7949219942092896,
+      "learning_rate": 0.00018808998360455233,
+      "loss": 0.3869,
+      "step": 305
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.851177990436554,
+      "learning_rate": 0.0001880079727338664,
+      "loss": 0.2691,
+      "step": 306
+    },
+    {
+      "epoch": 0.6688453159041394,
+      "grad_norm": 0.8438466787338257,
+      "learning_rate": 0.00018792569847883068,
+      "loss": 0.3314,
+      "step": 307
+    },
+    {
+      "epoch": 0.6710239651416122,
+      "grad_norm": 0.842267632484436,
+      "learning_rate": 0.00018784316108566996,
+      "loss": 0.3046,
+      "step": 308
+    },
+    {
+      "epoch": 0.673202614379085,
+      "grad_norm": 0.6835848689079285,
+      "learning_rate": 0.00018776036080139666,
+      "loss": 0.2026,
+      "step": 309
+    },
+    {
+      "epoch": 0.6753812636165577,
+      "grad_norm": 0.8685810565948486,
+      "learning_rate": 0.00018767729787380985,
+      "loss": 0.2611,
+      "step": 310
+    },
+    {
+      "epoch": 0.6775599128540305,
+      "grad_norm": 0.8736341595649719,
+      "learning_rate": 0.00018759397255149475,
+      "loss": 0.3135,
+      "step": 311
+    },
+    {
+      "epoch": 0.6797385620915033,
+      "grad_norm": 0.6718863844871521,
+      "learning_rate": 0.00018751038508382176,
+      "loss": 0.2202,
+      "step": 312
+    },
+    {
+      "epoch": 0.681917211328976,
+      "grad_norm": 0.686114490032196,
+      "learning_rate": 0.00018742653572094583,
+      "loss": 0.2861,
+      "step": 313
+    },
+    {
+      "epoch": 0.6840958605664488,
+      "grad_norm": 0.7779257297515869,
+      "learning_rate": 0.00018734242471380572,
+      "loss": 0.2375,
+      "step": 314
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.7334826588630676,
+      "learning_rate": 0.00018725805231412318,
+      "loss": 0.2855,
+      "step": 315
+    },
+    {
+      "epoch": 0.6884531590413944,
+      "grad_norm": 0.8215782046318054,
+      "learning_rate": 0.00018717341877440226,
+      "loss": 0.2827,
+      "step": 316
+    },
+    {
+      "epoch": 0.690631808278867,
+      "grad_norm": 0.7793420553207397,
+      "learning_rate": 0.00018708852434792857,
+      "loss": 0.3593,
+      "step": 317
+    },
+    {
+      "epoch": 0.6928104575163399,
+      "grad_norm": 0.6807507872581482,
+      "learning_rate": 0.0001870033692887684,
+      "loss": 0.2489,
+      "step": 318
+    },
+    {
+      "epoch": 0.6949891067538126,
+      "grad_norm": 0.8848825097084045,
+      "learning_rate": 0.00018691795385176815,
+      "loss": 0.3622,
+      "step": 319
+    },
+    {
+      "epoch": 0.6971677559912854,
+      "grad_norm": 0.7745735049247742,
+      "learning_rate": 0.00018683227829255334,
+      "loss": 0.2808,
+      "step": 320
+    },
+    {
+      "epoch": 0.6993464052287581,
+      "grad_norm": 0.8624871969223022,
+      "learning_rate": 0.00018674634286752805,
+      "loss": 0.326,
+      "step": 321
+    },
+    {
+      "epoch": 0.7015250544662309,
+      "grad_norm": 0.7500248551368713,
+      "learning_rate": 0.00018666014783387408,
+      "loss": 0.3413,
+      "step": 322
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.7700647115707397,
+      "learning_rate": 0.0001865736934495501,
+      "loss": 0.2878,
+      "step": 323
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.7682783603668213,
+      "learning_rate": 0.000186486979973291,
+      "loss": 0.3626,
+      "step": 324
+    },
+    {
+      "epoch": 0.7080610021786492,
+      "grad_norm": 0.8913851976394653,
+      "learning_rate": 0.00018640000766460704,
+      "loss": 0.3684,
+      "step": 325
+    },
+    {
+      "epoch": 0.710239651416122,
+      "grad_norm": 0.6541398763656616,
+      "learning_rate": 0.0001863127767837831,
+      "loss": 0.3203,
+      "step": 326
+    },
+    {
+      "epoch": 0.7124183006535948,
+      "grad_norm": 0.9459714889526367,
+      "learning_rate": 0.00018622528759187795,
+      "loss": 0.3794,
+      "step": 327
+    },
+    {
+      "epoch": 0.7145969498910676,
+      "grad_norm": 0.8284517526626587,
+      "learning_rate": 0.0001861375403507233,
+      "loss": 0.2859,
+      "step": 328
+    },
+    {
+      "epoch": 0.7167755991285403,
+      "grad_norm": 0.7966834306716919,
+      "learning_rate": 0.00018604953532292323,
+      "loss": 0.3299,
+      "step": 329
+    },
+    {
+      "epoch": 0.7189542483660131,
+      "grad_norm": 0.9105852842330933,
+      "learning_rate": 0.00018596127277185329,
+      "loss": 0.3489,
+      "step": 330
+    },
+    {
+      "epoch": 0.7211328976034859,
+      "grad_norm": 0.9086281657218933,
+      "learning_rate": 0.0001858727529616597,
+      "loss": 0.4104,
+      "step": 331
+    },
+    {
+      "epoch": 0.7233115468409586,
+      "grad_norm": 0.8128787875175476,
+      "learning_rate": 0.0001857839761572586,
+      "loss": 0.3057,
+      "step": 332
+    },
+    {
+      "epoch": 0.7254901960784313,
+      "grad_norm": 0.7139798402786255,
+      "learning_rate": 0.0001856949426243352,
+      "loss": 0.2226,
+      "step": 333
+    },
+    {
+      "epoch": 0.7276688453159041,
+      "grad_norm": 0.8051466941833496,
+      "learning_rate": 0.00018560565262934318,
+      "loss": 0.2778,
+      "step": 334
+    },
+    {
+      "epoch": 0.7298474945533769,
+      "grad_norm": 0.7806089520454407,
+      "learning_rate": 0.00018551610643950358,
+      "loss": 0.3074,
+      "step": 335
+    },
+    {
+      "epoch": 0.7320261437908496,
+      "grad_norm": 0.8499903678894043,
+      "learning_rate": 0.00018542630432280422,
+      "loss": 0.2625,
+      "step": 336
+    },
+    {
+      "epoch": 0.7342047930283224,
+      "grad_norm": 0.9724310040473938,
+      "learning_rate": 0.00018533624654799887,
+      "loss": 0.3267,
+      "step": 337
+    },
+    {
+      "epoch": 0.7363834422657952,
+      "grad_norm": 0.845237135887146,
+      "learning_rate": 0.00018524593338460635,
+      "loss": 0.3624,
+      "step": 338
+    },
+    {
+      "epoch": 0.738562091503268,
+      "grad_norm": 0.8381814360618591,
+      "learning_rate": 0.00018515536510290987,
+      "loss": 0.2973,
+      "step": 339
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.7939983606338501,
+      "learning_rate": 0.00018506454197395606,
+      "loss": 0.2893,
+      "step": 340
+    },
+    {
+      "epoch": 0.7429193899782135,
+      "grad_norm": 1.1554635763168335,
+      "learning_rate": 0.00018497346426955434,
+      "loss": 0.4355,
+      "step": 341
+    },
+    {
+      "epoch": 0.7450980392156863,
+      "grad_norm": 0.7291870713233948,
+      "learning_rate": 0.00018488213226227588,
+      "loss": 0.3172,
+      "step": 342
+    },
+    {
+      "epoch": 0.7472766884531591,
+      "grad_norm": 0.6162805557250977,
+      "learning_rate": 0.00018479054622545302,
+      "loss": 0.1914,
+      "step": 343
+    },
+    {
+      "epoch": 0.7494553376906318,
+      "grad_norm": 0.800554096698761,
+      "learning_rate": 0.0001846987064331783,
+      "loss": 0.3092,
+      "step": 344
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "grad_norm": 0.8024484515190125,
+      "learning_rate": 0.00018460661316030365,
+      "loss": 0.2598,
+      "step": 345
+    },
+    {
+      "epoch": 0.7516339869281046,
+      "eval_loss": 0.35579976439476013,
+      "eval_runtime": 0.9369,
+      "eval_samples_per_second": 182.512,
+      "eval_steps_per_second": 13.875,
+      "step": 345
+    },
+    {
+      "epoch": 0.7538126361655774,
+      "grad_norm": 0.6010091304779053,
+      "learning_rate": 0.00018451426668243963,
+      "loss": 0.1268,
+      "step": 346
+    },
+    {
+      "epoch": 0.7559912854030502,
+      "grad_norm": 0.909592866897583,
+      "learning_rate": 0.0001844216672759546,
+      "loss": 0.2808,
+      "step": 347
+    },
+    {
+      "epoch": 0.7581699346405228,
+      "grad_norm": 0.8788052201271057,
+      "learning_rate": 0.0001843288152179739,
+      "loss": 0.3516,
+      "step": 348
+    },
+    {
+      "epoch": 0.7603485838779956,
+      "grad_norm": 0.987259030342102,
+      "learning_rate": 0.00018423571078637885,
+      "loss": 0.4607,
+      "step": 349
+    },
+    {
+      "epoch": 0.7625272331154684,
+      "grad_norm": 1.0777586698532104,
+      "learning_rate": 0.00018414235425980616,
+      "loss": 0.3367,
+      "step": 350
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.8233873844146729,
+      "learning_rate": 0.00018404874591764696,
+      "loss": 0.2616,
+      "step": 351
+    },
+    {
+      "epoch": 0.7668845315904139,
+      "grad_norm": 0.6623446345329285,
+      "learning_rate": 0.00018395488604004603,
+      "loss": 0.154,
+      "step": 352
+    },
+    {
+      "epoch": 0.7690631808278867,
+      "grad_norm": 0.9828007817268372,
+      "learning_rate": 0.0001838607749079009,
+      "loss": 0.3084,
+      "step": 353
+    },
+    {
+      "epoch": 0.7712418300653595,
+      "grad_norm": 0.7043982148170471,
+      "learning_rate": 0.00018376641280286107,
+      "loss": 0.2568,
+      "step": 354
+    },
+    {
+      "epoch": 0.7734204793028322,
+      "grad_norm": 0.7597530484199524,
+      "learning_rate": 0.00018367180000732706,
+      "loss": 0.306,
+      "step": 355
+    },
+    {
+      "epoch": 0.775599128540305,
+      "grad_norm": 0.8099778890609741,
+      "learning_rate": 0.00018357693680444976,
+      "loss": 0.2389,
+      "step": 356
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.7014642953872681,
+      "learning_rate": 0.00018348182347812931,
+      "loss": 0.2601,
+      "step": 357
+    },
+    {
+      "epoch": 0.7799564270152506,
+      "grad_norm": 0.8545548915863037,
+      "learning_rate": 0.00018338646031301458,
+      "loss": 0.3604,
+      "step": 358
+    },
+    {
+      "epoch": 0.7821350762527233,
+      "grad_norm": 0.7516512870788574,
+      "learning_rate": 0.00018329084759450192,
+      "loss": 0.2489,
+      "step": 359
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.8581446409225464,
+      "learning_rate": 0.00018319498560873476,
+      "loss": 0.28,
+      "step": 360
+    },
+    {
+      "epoch": 0.7864923747276689,
+      "grad_norm": 0.8704679608345032,
+      "learning_rate": 0.00018309887464260238,
+      "loss": 0.3917,
+      "step": 361
+    },
+    {
+      "epoch": 0.7886710239651417,
+      "grad_norm": 0.832797110080719,
+      "learning_rate": 0.00018300251498373923,
+      "loss": 0.3356,
+      "step": 362
+    },
+    {
+      "epoch": 0.7908496732026143,
+      "grad_norm": 0.787756085395813,
+      "learning_rate": 0.00018290590692052398,
+      "loss": 0.3156,
+      "step": 363
+    },
+    {
+      "epoch": 0.7930283224400871,
+      "grad_norm": 1.014853596687317,
+      "learning_rate": 0.00018280905074207884,
+      "loss": 0.3131,
+      "step": 364
+    },
+    {
+      "epoch": 0.7952069716775599,
+      "grad_norm": 0.7135484218597412,
+      "learning_rate": 0.00018271194673826838,
+      "loss": 0.1935,
+      "step": 365
+    },
+    {
+      "epoch": 0.7973856209150327,
+      "grad_norm": 0.6172918677330017,
+      "learning_rate": 0.000182614595199699,
+      "loss": 0.1916,
+      "step": 366
+    },
+    {
+      "epoch": 0.7995642701525054,
+      "grad_norm": 0.689791738986969,
+      "learning_rate": 0.00018251699641771784,
+      "loss": 0.1738,
+      "step": 367
+    },
+    {
+      "epoch": 0.8017429193899782,
+      "grad_norm": 0.8571555614471436,
+      "learning_rate": 0.00018241915068441196,
+      "loss": 0.2738,
+      "step": 368
+    },
+    {
+      "epoch": 0.803921568627451,
+      "grad_norm": 0.7348290681838989,
+      "learning_rate": 0.00018232105829260752,
+      "loss": 0.1617,
+      "step": 369
+    },
+    {
+      "epoch": 0.8061002178649237,
+      "grad_norm": 0.72556471824646,
+      "learning_rate": 0.00018222271953586883,
+      "loss": 0.2201,
+      "step": 370
+    },
+    {
+      "epoch": 0.8082788671023965,
+      "grad_norm": 0.915581226348877,
+      "learning_rate": 0.0001821241347084975,
+      "loss": 0.3508,
+      "step": 371
+    },
+    {
+      "epoch": 0.8104575163398693,
+      "grad_norm": 0.9371058344841003,
+      "learning_rate": 0.00018202530410553163,
+      "loss": 0.3495,
+      "step": 372
+    },
+    {
+      "epoch": 0.8126361655773421,
+      "grad_norm": 0.696180522441864,
+      "learning_rate": 0.00018192622802274476,
+      "loss": 0.2297,
+      "step": 373
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 1.2849663496017456,
+      "learning_rate": 0.00018182690675664514,
+      "loss": 0.3872,
+      "step": 374
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 0.7671440243721008,
+      "learning_rate": 0.00018172734060447482,
+      "loss": 0.2522,
+      "step": 375
+    },
+    {
+      "epoch": 0.8191721132897604,
+      "grad_norm": 0.7630666494369507,
+      "learning_rate": 0.00018162752986420868,
+      "loss": 0.1857,
+      "step": 376
+    },
+    {
+      "epoch": 0.8213507625272332,
+      "grad_norm": 0.8664875626564026,
+      "learning_rate": 0.00018152747483455358,
+      "loss": 0.3085,
+      "step": 377
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.7418748140335083,
+      "learning_rate": 0.0001814271758149475,
+      "loss": 0.2537,
+      "step": 378
+    },
+    {
+      "epoch": 0.8257080610021786,
+      "grad_norm": 0.9873255491256714,
+      "learning_rate": 0.0001813266331055586,
+      "loss": 0.335,
+      "step": 379
+    },
+    {
+      "epoch": 0.8278867102396514,
+      "grad_norm": 0.8407981991767883,
+      "learning_rate": 0.00018122584700728443,
+      "loss": 0.2625,
+      "step": 380
+    },
+    {
+      "epoch": 0.8300653594771242,
+      "grad_norm": 0.8493285179138184,
+      "learning_rate": 0.0001811248178217507,
+      "loss": 0.2167,
+      "step": 381
+    },
+    {
+      "epoch": 0.8322440087145969,
+      "grad_norm": 0.7906709909439087,
+      "learning_rate": 0.00018102354585131092,
+      "loss": 0.2919,
+      "step": 382
+    },
+    {
+      "epoch": 0.8344226579520697,
+      "grad_norm": 0.8033335208892822,
+      "learning_rate": 0.00018092203139904496,
+      "loss": 0.2571,
+      "step": 383
+    },
+    {
+      "epoch": 0.8366013071895425,
+      "grad_norm": 0.616438627243042,
+      "learning_rate": 0.00018082027476875847,
+      "loss": 0.2102,
+      "step": 384
+    },
+    {
+      "epoch": 0.8387799564270153,
+      "grad_norm": 0.6517376899719238,
+      "learning_rate": 0.00018071827626498185,
+      "loss": 0.2242,
+      "step": 385
+    },
+    {
+      "epoch": 0.840958605664488,
+      "grad_norm": 0.7315549254417419,
+      "learning_rate": 0.00018061603619296942,
+      "loss": 0.2594,
+      "step": 386
+    },
+    {
+      "epoch": 0.8431372549019608,
+      "grad_norm": 0.6937726736068726,
+      "learning_rate": 0.00018051355485869833,
+      "loss": 0.1991,
+      "step": 387
+    },
+    {
+      "epoch": 0.8453159041394336,
+      "grad_norm": 0.7155842185020447,
+      "learning_rate": 0.0001804108325688679,
+      "loss": 0.2051,
+      "step": 388
+    },
+    {
+      "epoch": 0.8474945533769063,
+      "grad_norm": 1.1797689199447632,
+      "learning_rate": 0.00018030786963089845,
+      "loss": 0.3421,
+      "step": 389
+    },
+    {
+      "epoch": 0.8496732026143791,
+      "grad_norm": 0.7603274583816528,
+      "learning_rate": 0.00018020466635293057,
+      "loss": 0.1985,
+      "step": 390
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.7939961552619934,
+      "learning_rate": 0.0001801012230438241,
+      "loss": 0.2753,
+      "step": 391
+    },
+    {
+      "epoch": 0.8540305010893247,
+      "grad_norm": 0.8357366323471069,
+      "learning_rate": 0.0001799975400131572,
+      "loss": 0.3453,
+      "step": 392
+    },
+    {
+      "epoch": 0.8562091503267973,
+      "grad_norm": 0.7716991305351257,
+      "learning_rate": 0.00017989361757122553,
+      "loss": 0.2441,
+      "step": 393
+    },
+    {
+      "epoch": 0.8583877995642701,
+      "grad_norm": 0.7844340205192566,
+      "learning_rate": 0.00017978945602904116,
+      "loss": 0.3635,
+      "step": 394
+    },
+    {
+      "epoch": 0.8605664488017429,
+      "grad_norm": 0.6692304611206055,
+      "learning_rate": 0.00017968505569833173,
+      "loss": 0.1895,
+      "step": 395
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 0.7669034004211426,
+      "learning_rate": 0.0001795804168915396,
+      "loss": 0.1833,
+      "step": 396
+    },
+    {
+      "epoch": 0.8649237472766884,
+      "grad_norm": 0.9231857657432556,
+      "learning_rate": 0.00017947553992182075,
+      "loss": 0.3172,
+      "step": 397
+    },
+    {
+      "epoch": 0.8671023965141612,
+      "grad_norm": 0.9847748875617981,
+      "learning_rate": 0.00017937042510304392,
+      "loss": 0.3479,
+      "step": 398
+    },
+    {
+      "epoch": 0.869281045751634,
+      "grad_norm": 0.719962477684021,
+      "learning_rate": 0.00017926507274978963,
+      "loss": 0.2653,
+      "step": 399
+    },
+    {
+      "epoch": 0.8714596949891068,
+      "grad_norm": 0.7490435242652893,
+      "learning_rate": 0.00017915948317734942,
+      "loss": 0.2387,
+      "step": 400
+    },
+    {
+      "epoch": 0.8736383442265795,
+      "grad_norm": 0.744804322719574,
+      "learning_rate": 0.00017905365670172458,
+      "loss": 0.2368,
+      "step": 401
+    },
+    {
+      "epoch": 0.8758169934640523,
+      "grad_norm": 0.6886241436004639,
+      "learning_rate": 0.00017894759363962554,
+      "loss": 0.2125,
+      "step": 402
+    },
+    {
+      "epoch": 0.8779956427015251,
+      "grad_norm": 0.7730022072792053,
+      "learning_rate": 0.0001788412943084707,
+      "loss": 0.2253,
+      "step": 403
+    },
+    {
+      "epoch": 0.8801742919389978,
+      "grad_norm": 0.8058857321739197,
+      "learning_rate": 0.00017873475902638553,
+      "loss": 0.2845,
+      "step": 404
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.6579281091690063,
+      "learning_rate": 0.0001786279881122017,
+      "loss": 0.1922,
+      "step": 405
+    },
+    {
+      "epoch": 0.8845315904139434,
+      "grad_norm": 0.6769328713417053,
+      "learning_rate": 0.00017852098188545602,
+      "loss": 0.1609,
+      "step": 406
+    },
+    {
+      "epoch": 0.8867102396514162,
+      "grad_norm": 0.7010467648506165,
+      "learning_rate": 0.0001784137406663895,
+      "loss": 0.2387,
+      "step": 407
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.7626838088035583,
+      "learning_rate": 0.00017830626477594654,
+      "loss": 0.237,
+      "step": 408
+    },
+    {
+      "epoch": 0.8910675381263616,
+      "grad_norm": 0.8782392144203186,
+      "learning_rate": 0.0001781985545357737,
+      "loss": 0.3278,
+      "step": 409
+    },
+    {
+      "epoch": 0.8932461873638344,
+      "grad_norm": 0.6178898215293884,
+      "learning_rate": 0.00017809061026821896,
+      "loss": 0.1584,
+      "step": 410
+    },
+    {
+      "epoch": 0.8954248366013072,
+      "grad_norm": 0.7101506590843201,
+      "learning_rate": 0.00017798243229633068,
+      "loss": 0.2384,
+      "step": 411
+    },
+    {
+      "epoch": 0.8976034858387799,
+      "grad_norm": 0.5807170867919922,
+      "learning_rate": 0.00017787402094385666,
+      "loss": 0.1256,
+      "step": 412
+    },
+    {
+      "epoch": 0.8997821350762527,
+      "grad_norm": 0.6202595829963684,
+      "learning_rate": 0.00017776537653524307,
+      "loss": 0.168,
+      "step": 413
+    },
+    {
+      "epoch": 0.9019607843137255,
+      "grad_norm": 0.5887298583984375,
+      "learning_rate": 0.00017765649939563365,
+      "loss": 0.1411,
+      "step": 414
+    },
+    {
+      "epoch": 0.9041394335511983,
+      "grad_norm": 0.745570957660675,
+      "learning_rate": 0.0001775473898508685,
+      "loss": 0.2842,
+      "step": 415
+    },
+    {
+      "epoch": 0.906318082788671,
+      "grad_norm": 0.8904745578765869,
+      "learning_rate": 0.00017743804822748345,
+      "loss": 0.3217,
+      "step": 416
+    },
+    {
+      "epoch": 0.9084967320261438,
+      "grad_norm": 0.8730976581573486,
+      "learning_rate": 0.0001773284748527087,
+      "loss": 0.3403,
+      "step": 417
+    },
+    {
+      "epoch": 0.9106753812636166,
+      "grad_norm": 0.7911598086357117,
+      "learning_rate": 0.00017721867005446806,
+      "loss": 0.2731,
+      "step": 418
+    },
+    {
+      "epoch": 0.9128540305010894,
+      "grad_norm": 0.6702750325202942,
+      "learning_rate": 0.00017710863416137805,
+      "loss": 0.2073,
+      "step": 419
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.5198416113853455,
+      "learning_rate": 0.00017699836750274662,
+      "loss": 0.129,
+      "step": 420
+    },
+    {
+      "epoch": 0.9172113289760349,
+      "grad_norm": 0.6400766372680664,
+      "learning_rate": 0.00017688787040857245,
+      "loss": 0.1682,
+      "step": 421
+    },
+    {
+      "epoch": 0.9193899782135077,
+      "grad_norm": 0.7851924896240234,
+      "learning_rate": 0.00017677714320954378,
+      "loss": 0.221,
+      "step": 422
+    },
+    {
+      "epoch": 0.9215686274509803,
+      "grad_norm": 0.7246972918510437,
+      "learning_rate": 0.0001766661862370376,
+      "loss": 0.2438,
+      "step": 423
+    },
+    {
+      "epoch": 0.9237472766884531,
+      "grad_norm": 0.7575098872184753,
+      "learning_rate": 0.00017655499982311847,
+      "loss": 0.2633,
+      "step": 424
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.902695894241333,
+      "learning_rate": 0.0001764435843005376,
+      "loss": 0.3567,
+      "step": 425
+    },
+    {
+      "epoch": 0.9281045751633987,
+      "grad_norm": 0.7910832762718201,
+      "learning_rate": 0.00017633194000273188,
+      "loss": 0.2578,
+      "step": 426
+    },
+    {
+      "epoch": 0.9302832244008714,
+      "grad_norm": 0.7221683263778687,
+      "learning_rate": 0.00017622006726382287,
+      "loss": 0.2075,
+      "step": 427
+    },
+    {
+      "epoch": 0.9324618736383442,
+      "grad_norm": 0.7584638595581055,
+      "learning_rate": 0.00017610796641861581,
+      "loss": 0.2313,
+      "step": 428
+    },
+    {
+      "epoch": 0.934640522875817,
+      "grad_norm": 0.6272245645523071,
+      "learning_rate": 0.00017599563780259858,
+      "loss": 0.1876,
+      "step": 429
+    },
+    {
+      "epoch": 0.9368191721132898,
+      "grad_norm": 0.8224185705184937,
+      "learning_rate": 0.0001758830817519407,
+      "loss": 0.2558,
+      "step": 430
+    },
+    {
+      "epoch": 0.9389978213507625,
+      "grad_norm": 0.7095481157302856,
+      "learning_rate": 0.00017577029860349233,
+      "loss": 0.2256,
+      "step": 431
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.7715668678283691,
+      "learning_rate": 0.00017565728869478337,
+      "loss": 0.2483,
+      "step": 432
+    },
+    {
+      "epoch": 0.9433551198257081,
+      "grad_norm": 0.905522882938385,
+      "learning_rate": 0.00017554405236402222,
+      "loss": 0.2525,
+      "step": 433
+    },
+    {
+      "epoch": 0.9455337690631809,
+      "grad_norm": 0.6268091797828674,
+      "learning_rate": 0.00017543058995009503,
+      "loss": 0.1703,
+      "step": 434
+    },
+    {
+      "epoch": 0.9477124183006536,
+      "grad_norm": 0.730185329914093,
+      "learning_rate": 0.0001753169017925644,
+      "loss": 0.2187,
+      "step": 435
+    },
+    {
+      "epoch": 0.9498910675381264,
+      "grad_norm": 0.7279319763183594,
+      "learning_rate": 0.00017520298823166873,
+      "loss": 0.2584,
+      "step": 436
+    },
+    {
+      "epoch": 0.9520697167755992,
+      "grad_norm": 0.7050124406814575,
+      "learning_rate": 0.00017508884960832076,
+      "loss": 0.1723,
+      "step": 437
+    },
+    {
+      "epoch": 0.954248366013072,
+      "grad_norm": 0.7544010281562805,
+      "learning_rate": 0.000174974486264107,
+      "loss": 0.1899,
+      "step": 438
+    },
+    {
+      "epoch": 0.9564270152505446,
+      "grad_norm": 0.8714267015457153,
+      "learning_rate": 0.00017485989854128627,
+      "loss": 0.2518,
+      "step": 439
+    },
+    {
+      "epoch": 0.9586056644880174,
+      "grad_norm": 0.7128406167030334,
+      "learning_rate": 0.00017474508678278915,
+      "loss": 0.1832,
+      "step": 440
+    },
+    {
+      "epoch": 0.9607843137254902,
+      "grad_norm": 0.7446244955062866,
+      "learning_rate": 0.00017463005133221645,
+      "loss": 0.2089,
+      "step": 441
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.7556454539299011,
+      "learning_rate": 0.00017451479253383857,
+      "loss": 0.2327,
+      "step": 442
+    },
+    {
+      "epoch": 0.9651416122004357,
+      "grad_norm": 0.5932292938232422,
+      "learning_rate": 0.00017439931073259427,
+      "loss": 0.1094,
+      "step": 443
+    },
+    {
+      "epoch": 0.9673202614379085,
+      "grad_norm": 0.909900426864624,
+      "learning_rate": 0.00017428360627408978,
+      "loss": 0.2175,
+      "step": 444
+    },
+    {
+      "epoch": 0.9694989106753813,
+      "grad_norm": 0.7743591666221619,
+      "learning_rate": 0.00017416767950459766,
+      "loss": 0.1818,
+      "step": 445
+    },
+    {
+      "epoch": 0.971677559912854,
+      "grad_norm": 0.7306420207023621,
+      "learning_rate": 0.0001740515307710557,
+      "loss": 0.1957,
+      "step": 446
+    },
+    {
+      "epoch": 0.9738562091503268,
+      "grad_norm": 0.5480270981788635,
+      "learning_rate": 0.00017393516042106603,
+      "loss": 0.1477,
+      "step": 447
+    },
+    {
+      "epoch": 0.9760348583877996,
+      "grad_norm": 0.7661142945289612,
+      "learning_rate": 0.000173818568802894,
+      "loss": 0.2177,
+      "step": 448
+    },
+    {
+      "epoch": 0.9782135076252724,
+      "grad_norm": 0.8411223292350769,
+      "learning_rate": 0.00017370175626546728,
+      "loss": 0.2104,
+      "step": 449
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.816074013710022,
+      "learning_rate": 0.00017358472315837447,
+      "loss": 0.2349,
+      "step": 450
+    },
+    {
+      "epoch": 0.9825708061002179,
+      "grad_norm": 1.0009855031967163,
+      "learning_rate": 0.00017346746983186442,
+      "loss": 0.2917,
+      "step": 451
+    },
+    {
+      "epoch": 0.9847494553376906,
+      "grad_norm": 0.7690507769584656,
+      "learning_rate": 0.00017334999663684504,
+      "loss": 0.2216,
+      "step": 452
+    },
+    {
+      "epoch": 0.9869281045751634,
+      "grad_norm": 0.7864702939987183,
+      "learning_rate": 0.00017323230392488222,
+      "loss": 0.2601,
+      "step": 453
+    },
+    {
+      "epoch": 0.9891067538126361,
+      "grad_norm": 0.8309422731399536,
+      "learning_rate": 0.00017311439204819874,
+      "loss": 0.2257,
+      "step": 454
+    },
+    {
+      "epoch": 0.9912854030501089,
+      "grad_norm": 0.7395288944244385,
+      "learning_rate": 0.00017299626135967343,
+      "loss": 0.1859,
+      "step": 455
+    },
+    {
+      "epoch": 0.9934640522875817,
+      "grad_norm": 0.6524999737739563,
+      "learning_rate": 0.00017287791221283984,
+      "loss": 0.1523,
+      "step": 456
+    },
+    {
+      "epoch": 0.9956427015250545,
+      "grad_norm": 0.6195773482322693,
+      "learning_rate": 0.00017275934496188534,
+      "loss": 0.1307,
+      "step": 457
+    },
+    {
+      "epoch": 0.9978213507625272,
+      "grad_norm": 0.8236491084098816,
+      "learning_rate": 0.00017264055996165007,
+      "loss": 0.2214,
+      "step": 458
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5916262865066528,
+      "learning_rate": 0.00017252155756762575,
+      "loss": 0.1633,
+      "step": 459
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1836,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 459,
+  "total_flos": 1.1104996358828851e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-459/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eeec319c5500d881c83ddf7f3e737b7843c548db9958907577f93d03ba7823
+size 5816

checkpoint-918/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: openlm-research/open_llama_3b_v2
+---
+
+# 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 0.10.0

checkpoint-918/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-918/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c077041d2bd55d117bdeb5140d2fe925df1c1b8672e885c909dd1f13368840
+size 50899792

checkpoint-918/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9062004d0d48ed3f7ab85d455e8d65d54e33dcd839b56c0126ae26a1459fc29b
+size 25871876

checkpoint-918/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0fcc11abd20f1a9174bbd06b5f2f8ccad20881dcf76721a16310a896cefc52
+size 15728

checkpoint-918/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc2c0266830e2f380ad8aceb33cfde1823ae161760b7a73c6ca56f40d400644
+size 15728

checkpoint-918/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a920727f161e0d35ff28f876fe19f4a4caee9243bc910ef1d84d28ef8f7dbe2e
+size 15728

checkpoint-918/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f56d07ea54e1bb8aef48d14cac39ca9512427d91cb8094fd820e31507117d9e
+size 15728

checkpoint-918/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3ca4f825f4f74d51df84d275f470905817740a9b124452305129545b5b89b0
+size 15728

checkpoint-918/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33c7fd2a7fe36132e45f5a23c5fbb81ffc3e66651b099f11de79c4a8b10446f
+size 15728

checkpoint-918/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5859d294a67360676b74ea53ce57de6b9d145fb1da5e19c7b80d0bd9ebecbb97
+size 15728

checkpoint-918/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c89bd40f22c5bbadbe6722093d08dd165870f47389735f80dfaf961199ba106
+size 1064