Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-846/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+model_name: qwen2-7b-instruct-trl-sft-newick_extraction_1
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for qwen2-7b-instruct-trl-sft-newick_extraction_1
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/markush/qwen2-7b-instruct-trl-sft-ChartQA/runs/zlo118q6) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.15.2
+- TRL: 0.20.0
+- Transformers: 4.53.2
+- Pytorch: 2.4.1+cu121
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daed0f98de9e6a012f9a7c75a65b09cc3c94bccef358b8aae286050c6ed8238
+size 10108960

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6687d03010b9554acfa9db87f5b1de39211d3cdc83a505f34021b03d8df28f
+size 10108960

checkpoint-200/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90c6409c779c34dab9260796290110f59ab8528b16329d2cbbbd2957790f495
+size 20280890

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bab0f660c6299bc1533a2fde26e6614e49d2975366d6b8770ae69b588d827e
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,414 @@
+{
+  "best_global_step": 200,
+  "best_metric": 6.104866770328954e-06,
+  "best_model_checkpoint": "qwen2-7b-instruct-trl-sft-newick_extraction_1/checkpoint-200",
+  "epoch": 0.7111111111111111,
+  "eval_steps": 10,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 4.419339179992676,
+      "learning_rate": 0.0002,
+      "loss": 14.4699,
+      "mean_token_accuracy": 0.5754725567996501,
+      "num_tokens": 570240.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "eval_loss": 1.5543439388275146,
+      "eval_mean_token_accuracy": 0.6078731870651245,
+      "eval_num_tokens": 570240.0,
+      "eval_runtime": 648.0159,
+      "eval_samples_per_second": 1.543,
+      "eval_steps_per_second": 0.386,
+      "step": 10
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 9.82264232635498,
+      "learning_rate": 0.0002,
+      "loss": 10.3302,
+      "mean_token_accuracy": 0.6614481717348099,
+      "num_tokens": 1140480.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "eval_loss": 0.9738740921020508,
+      "eval_mean_token_accuracy": 0.7448731756210327,
+      "eval_num_tokens": 1140480.0,
+      "eval_runtime": 630.2188,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 20
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 11.91273307800293,
+      "learning_rate": 0.0002,
+      "loss": 5.6105,
+      "mean_token_accuracy": 0.8060442075133324,
+      "num_tokens": 1710720.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.3900993764400482,
+      "eval_mean_token_accuracy": 0.8829268217086792,
+      "eval_num_tokens": 1710720.0,
+      "eval_runtime": 631.6971,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 30
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 6.84392786026001,
+      "learning_rate": 0.0002,
+      "loss": 1.7204,
+      "mean_token_accuracy": 0.943353658914566,
+      "num_tokens": 2280960.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "eval_loss": 0.06896545737981796,
+      "eval_mean_token_accuracy": 0.9878048896789551,
+      "eval_num_tokens": 2280960.0,
+      "eval_runtime": 627.3952,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 40
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.21437789499759674,
+      "learning_rate": 0.0002,
+      "loss": 0.3396,
+      "mean_token_accuracy": 0.9958536624908447,
+      "num_tokens": 2851200.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.03179474174976349,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 2851200.0,
+      "eval_runtime": 631.7748,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 50
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.2222466468811035,
+      "learning_rate": 0.0002,
+      "loss": 0.2231,
+      "mean_token_accuracy": 0.997560977935791,
+      "num_tokens": 3421440.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.017346156761050224,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 3421440.0,
+      "eval_runtime": 627.3871,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 60
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.549639105796814,
+      "learning_rate": 0.0002,
+      "loss": 0.0636,
+      "mean_token_accuracy": 0.9984908550977707,
+      "num_tokens": 3991680.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "eval_loss": 0.0006659275386482477,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 3991680.0,
+      "eval_runtime": 627.7647,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 70
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.034244876354932785,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4561920.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "eval_loss": 4.906835238216445e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 4561920.0,
+      "eval_runtime": 627.866,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.004514188971370459,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5132160.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 2.5992721930379048e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5132160.0,
+      "eval_runtime": 630.504,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 90
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.0026128594763576984,
+      "learning_rate": 0.0002,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5702400.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 1.878049260994885e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5702400.0,
+      "eval_runtime": 628.0227,
+      "eval_samples_per_second": 1.592,
+      "eval_steps_per_second": 0.398,
+      "step": 100
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.0018496178090572357,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6272640.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "eval_loss": 1.4819584976066835e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6272640.0,
+      "eval_runtime": 632.337,
+      "eval_samples_per_second": 1.581,
+      "eval_steps_per_second": 0.395,
+      "step": 110
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.001428118092007935,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6842880.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 1.2422192412486766e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6842880.0,
+      "eval_runtime": 627.3485,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.399,
+      "step": 120
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.0011839906219393015,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7413120.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "eval_loss": 1.0789405678224284e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7413120.0,
+      "eval_runtime": 630.5032,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 130
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.001027945545502007,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7983360.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "eval_loss": 9.804618457565084e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7983360.0,
+      "eval_runtime": 626.6713,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 140
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0009170864359475672,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8553600.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 8.696494660398457e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 8553600.0,
+      "eval_runtime": 630.4604,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 150
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.0008168203639797866,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9123840.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "eval_loss": 7.992691280378494e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9123840.0,
+      "eval_runtime": 628.5297,
+      "eval_samples_per_second": 1.591,
+      "eval_steps_per_second": 0.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.0007576971547678113,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9694080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "eval_loss": 7.28438317310065e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9694080.0,
+      "eval_runtime": 626.7184,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 170
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0006879908032715321,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10264320.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 6.8836661739624105e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10264320.0,
+      "eval_runtime": 756.3063,
+      "eval_samples_per_second": 1.322,
+      "eval_steps_per_second": 0.331,
+      "step": 180
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.0006444182363338768,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10834560.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "eval_loss": 6.4065607148222625e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10834560.0,
+      "eval_runtime": 628.8265,
+      "eval_samples_per_second": 1.59,
+      "eval_steps_per_second": 0.398,
+      "step": 190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0005997396074235439,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11404800.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 6.104866770328954e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 11404800.0,
+      "eval_runtime": 688.2367,
+      "eval_samples_per_second": 1.453,
+      "eval_steps_per_second": 0.363,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 846,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.302480224780288e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea9672706e844d882368a147887a0a30f825af7ec487e8e243dda0b8a0c6d19
+size 5816

checkpoint-400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-400/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0196dbee231c6c6e204fae008bdab92460b65e793f3dd574fd6d7af63a2310c
+size 10108960

checkpoint-400/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-400/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4157b772ea7b8001eee99b3bca61b815fcac64acc41c3a6c99deb3642b3b3c
+size 20280890

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b512b6800d6897f77a46ae993b5b833e5cd130167fa746a50ce5a03fc4dc99
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3dedf52aaea6588501a76bbcc0db7c74d91e0049f19cb86f239096b664186d
+size 1064

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,794 @@
+{
+  "best_global_step": 400,
+  "best_metric": 2.613794549688464e-06,
+  "best_model_checkpoint": "qwen2-7b-instruct-trl-sft-newick_extraction_1/checkpoint-400",
+  "epoch": 1.4195555555555557,
+  "eval_steps": 10,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 4.419339179992676,
+      "learning_rate": 0.0002,
+      "loss": 14.4699,
+      "mean_token_accuracy": 0.5754725567996501,
+      "num_tokens": 570240.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "eval_loss": 1.5543439388275146,
+      "eval_mean_token_accuracy": 0.6078731870651245,
+      "eval_num_tokens": 570240.0,
+      "eval_runtime": 648.0159,
+      "eval_samples_per_second": 1.543,
+      "eval_steps_per_second": 0.386,
+      "step": 10
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 9.82264232635498,
+      "learning_rate": 0.0002,
+      "loss": 10.3302,
+      "mean_token_accuracy": 0.6614481717348099,
+      "num_tokens": 1140480.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "eval_loss": 0.9738740921020508,
+      "eval_mean_token_accuracy": 0.7448731756210327,
+      "eval_num_tokens": 1140480.0,
+      "eval_runtime": 630.2188,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 20
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 11.91273307800293,
+      "learning_rate": 0.0002,
+      "loss": 5.6105,
+      "mean_token_accuracy": 0.8060442075133324,
+      "num_tokens": 1710720.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.3900993764400482,
+      "eval_mean_token_accuracy": 0.8829268217086792,
+      "eval_num_tokens": 1710720.0,
+      "eval_runtime": 631.6971,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 30
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 6.84392786026001,
+      "learning_rate": 0.0002,
+      "loss": 1.7204,
+      "mean_token_accuracy": 0.943353658914566,
+      "num_tokens": 2280960.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "eval_loss": 0.06896545737981796,
+      "eval_mean_token_accuracy": 0.9878048896789551,
+      "eval_num_tokens": 2280960.0,
+      "eval_runtime": 627.3952,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 40
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.21437789499759674,
+      "learning_rate": 0.0002,
+      "loss": 0.3396,
+      "mean_token_accuracy": 0.9958536624908447,
+      "num_tokens": 2851200.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.03179474174976349,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 2851200.0,
+      "eval_runtime": 631.7748,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 50
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.2222466468811035,
+      "learning_rate": 0.0002,
+      "loss": 0.2231,
+      "mean_token_accuracy": 0.997560977935791,
+      "num_tokens": 3421440.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.017346156761050224,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 3421440.0,
+      "eval_runtime": 627.3871,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 60
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.549639105796814,
+      "learning_rate": 0.0002,
+      "loss": 0.0636,
+      "mean_token_accuracy": 0.9984908550977707,
+      "num_tokens": 3991680.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "eval_loss": 0.0006659275386482477,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 3991680.0,
+      "eval_runtime": 627.7647,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 70
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.034244876354932785,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4561920.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "eval_loss": 4.906835238216445e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 4561920.0,
+      "eval_runtime": 627.866,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.004514188971370459,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5132160.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 2.5992721930379048e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5132160.0,
+      "eval_runtime": 630.504,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 90
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.0026128594763576984,
+      "learning_rate": 0.0002,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5702400.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 1.878049260994885e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5702400.0,
+      "eval_runtime": 628.0227,
+      "eval_samples_per_second": 1.592,
+      "eval_steps_per_second": 0.398,
+      "step": 100
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.0018496178090572357,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6272640.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "eval_loss": 1.4819584976066835e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6272640.0,
+      "eval_runtime": 632.337,
+      "eval_samples_per_second": 1.581,
+      "eval_steps_per_second": 0.395,
+      "step": 110
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.001428118092007935,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6842880.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 1.2422192412486766e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6842880.0,
+      "eval_runtime": 627.3485,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.399,
+      "step": 120
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.0011839906219393015,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7413120.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "eval_loss": 1.0789405678224284e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7413120.0,
+      "eval_runtime": 630.5032,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 130
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.001027945545502007,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7983360.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "eval_loss": 9.804618457565084e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7983360.0,
+      "eval_runtime": 626.6713,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 140
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0009170864359475672,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8553600.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 8.696494660398457e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 8553600.0,
+      "eval_runtime": 630.4604,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 150
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.0008168203639797866,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9123840.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "eval_loss": 7.992691280378494e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9123840.0,
+      "eval_runtime": 628.5297,
+      "eval_samples_per_second": 1.591,
+      "eval_steps_per_second": 0.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.0007576971547678113,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9694080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "eval_loss": 7.28438317310065e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9694080.0,
+      "eval_runtime": 626.7184,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 170
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0006879908032715321,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10264320.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 6.8836661739624105e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10264320.0,
+      "eval_runtime": 756.3063,
+      "eval_samples_per_second": 1.322,
+      "eval_steps_per_second": 0.331,
+      "step": 180
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.0006444182363338768,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10834560.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "eval_loss": 6.4065607148222625e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10834560.0,
+      "eval_runtime": 628.8265,
+      "eval_samples_per_second": 1.59,
+      "eval_steps_per_second": 0.398,
+      "step": 190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0005997396074235439,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11404800.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 6.104866770328954e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 11404800.0,
+      "eval_runtime": 688.2367,
+      "eval_samples_per_second": 1.453,
+      "eval_steps_per_second": 0.363,
+      "step": 200
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.0005526828463189304,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11975040.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 5.683682047674665e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 11975040.0,
+      "eval_runtime": 754.3494,
+      "eval_samples_per_second": 1.326,
+      "eval_steps_per_second": 0.331,
+      "step": 210
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0005140851717442274,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 12545280.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "eval_loss": 5.339933522918727e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 12545280.0,
+      "eval_runtime": 647.6999,
+      "eval_samples_per_second": 1.544,
+      "eval_steps_per_second": 0.386,
+      "step": 220
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.0004886530223302543,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 13115520.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "eval_loss": 5.0328567340329755e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 13115520.0,
+      "eval_runtime": 631.1227,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 230
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0004592030309140682,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 13685760.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 4.829912541026715e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 13685760.0,
+      "eval_runtime": 631.5138,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 240
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0004404531209729612,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 14256000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 4.590192020259565e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 14256000.0,
+      "eval_runtime": 631.121,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 250
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.00041581166442483664,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 14826240.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "eval_loss": 4.422760412126081e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 14826240.0,
+      "eval_runtime": 626.5972,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 260
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.00039238750468939543,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 15396480.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 4.159514901402872e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 15396480.0,
+      "eval_runtime": 626.6804,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 270
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0003751284384634346,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 15966720.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "eval_loss": 4.007378265669104e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 15966720.0,
+      "eval_runtime": 626.6082,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 280
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "grad_norm": 0.0003600440395530313,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 16492410.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "eval_loss": 3.86876126867719e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 16492410.0,
+      "eval_runtime": 630.0967,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 290
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.00035800470504909754,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 17062650.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.064,
+      "eval_loss": 3.728666797542246e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 17062650.0,
+      "eval_runtime": 630.6538,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.396,
+      "step": 300
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "grad_norm": 0.0003293608024250716,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 17632890.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "eval_loss": 3.5069003843091195e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 17632890.0,
+      "eval_runtime": 626.3062,
+      "eval_samples_per_second": 1.597,
+      "eval_steps_per_second": 0.399,
+      "step": 310
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "grad_norm": 0.000320440623909235,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 18203130.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "eval_loss": 3.4313563901378075e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 18203130.0,
+      "eval_runtime": 626.8382,
+      "eval_samples_per_second": 1.595,
+      "eval_steps_per_second": 0.399,
+      "step": 320
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 0.00031058763852342963,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 18773370.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "eval_loss": 3.2939326501946198e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 18773370.0,
+      "eval_runtime": 631.1457,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 330
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "grad_norm": 0.0002935119846370071,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 19343610.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "eval_loss": 3.1630906960344873e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 19343610.0,
+      "eval_runtime": 631.1257,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 340
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "grad_norm": 0.00028090347768738866,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 19913850.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "eval_loss": 3.1076663162821205e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 19913850.0,
+      "eval_runtime": 631.1307,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 350
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 0.000271222204901278,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 20484090.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "eval_loss": 2.9442144295899197e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 20484090.0,
+      "eval_runtime": 631.362,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 360
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "grad_norm": 0.0002641026512719691,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 21054330.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "eval_loss": 2.8731856218655594e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 21054330.0,
+      "eval_runtime": 626.4927,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 370
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "grad_norm": 0.0002599551226012409,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 21624570.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "eval_loss": 2.7712894734577276e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 21624570.0,
+      "eval_runtime": 626.4481,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 380
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.0002494712534826249,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 22194810.0,
+      "step": 390
+    },
+    {
+      "epoch": 1.384,
+      "eval_loss": 2.666238515303121e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 22194810.0,
+      "eval_runtime": 626.3873,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 390
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "grad_norm": 0.00024175533326342702,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 22765050.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "eval_loss": 2.613794549688464e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 22765050.0,
+      "eval_runtime": 625.5663,
+      "eval_samples_per_second": 1.599,
+      "eval_steps_per_second": 0.4,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 846,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0584247636182528e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea9672706e844d882368a147887a0a30f825af7ec487e8e243dda0b8a0c6d19
+size 5816

checkpoint-600/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-600/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "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"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fffde15cdd1d4a437909c2b61d5eba13827c3fa0e5db74352a628e9c6f08bd
+size 10108960

checkpoint-600/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-600/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0bd7056c8c1530dbcda56531a3ff2ebdeed16638cb20805cf0fe7a4ca783f0
+size 20280890

checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a25e56acc665b9751dc14932c7ed1db292bc3cd7daa227da924cbcca4ad4172
+size 14244

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d85fd0dcc980904bdfd3763281a80094639a2b2b63af9676380dd57c838a883
+size 1064

checkpoint-600/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-600/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-600/trainer_state.json

@@ -0,0 +1,1174 @@
+{
+  "best_global_step": 600,
+  "best_metric": 1.558861640660325e-06,
+  "best_model_checkpoint": "qwen2-7b-instruct-trl-sft-newick_extraction_1/checkpoint-600",
+  "epoch": 2.128,
+  "eval_steps": 10,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 4.419339179992676,
+      "learning_rate": 0.0002,
+      "loss": 14.4699,
+      "mean_token_accuracy": 0.5754725567996501,
+      "num_tokens": 570240.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "eval_loss": 1.5543439388275146,
+      "eval_mean_token_accuracy": 0.6078731870651245,
+      "eval_num_tokens": 570240.0,
+      "eval_runtime": 648.0159,
+      "eval_samples_per_second": 1.543,
+      "eval_steps_per_second": 0.386,
+      "step": 10
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 9.82264232635498,
+      "learning_rate": 0.0002,
+      "loss": 10.3302,
+      "mean_token_accuracy": 0.6614481717348099,
+      "num_tokens": 1140480.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "eval_loss": 0.9738740921020508,
+      "eval_mean_token_accuracy": 0.7448731756210327,
+      "eval_num_tokens": 1140480.0,
+      "eval_runtime": 630.2188,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 20
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 11.91273307800293,
+      "learning_rate": 0.0002,
+      "loss": 5.6105,
+      "mean_token_accuracy": 0.8060442075133324,
+      "num_tokens": 1710720.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "eval_loss": 0.3900993764400482,
+      "eval_mean_token_accuracy": 0.8829268217086792,
+      "eval_num_tokens": 1710720.0,
+      "eval_runtime": 631.6971,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 30
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 6.84392786026001,
+      "learning_rate": 0.0002,
+      "loss": 1.7204,
+      "mean_token_accuracy": 0.943353658914566,
+      "num_tokens": 2280960.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "eval_loss": 0.06896545737981796,
+      "eval_mean_token_accuracy": 0.9878048896789551,
+      "eval_num_tokens": 2280960.0,
+      "eval_runtime": 627.3952,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 40
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.21437789499759674,
+      "learning_rate": 0.0002,
+      "loss": 0.3396,
+      "mean_token_accuracy": 0.9958536624908447,
+      "num_tokens": 2851200.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.03179474174976349,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 2851200.0,
+      "eval_runtime": 631.7748,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 50
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.2222466468811035,
+      "learning_rate": 0.0002,
+      "loss": 0.2231,
+      "mean_token_accuracy": 0.997560977935791,
+      "num_tokens": 3421440.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 0.017346156761050224,
+      "eval_mean_token_accuracy": 0.997560977935791,
+      "eval_num_tokens": 3421440.0,
+      "eval_runtime": 627.3871,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.398,
+      "step": 60
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.549639105796814,
+      "learning_rate": 0.0002,
+      "loss": 0.0636,
+      "mean_token_accuracy": 0.9984908550977707,
+      "num_tokens": 3991680.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "eval_loss": 0.0006659275386482477,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 3991680.0,
+      "eval_runtime": 627.7647,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 70
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.034244876354932785,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4561920.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "eval_loss": 4.906835238216445e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 4561920.0,
+      "eval_runtime": 627.866,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.004514188971370459,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5132160.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 2.5992721930379048e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5132160.0,
+      "eval_runtime": 630.504,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 90
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.0026128594763576984,
+      "learning_rate": 0.0002,
+      "loss": 0.0002,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5702400.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 1.878049260994885e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 5702400.0,
+      "eval_runtime": 628.0227,
+      "eval_samples_per_second": 1.592,
+      "eval_steps_per_second": 0.398,
+      "step": 100
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.0018496178090572357,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6272640.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "eval_loss": 1.4819584976066835e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6272640.0,
+      "eval_runtime": 632.337,
+      "eval_samples_per_second": 1.581,
+      "eval_steps_per_second": 0.395,
+      "step": 110
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.001428118092007935,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6842880.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 1.2422192412486766e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6842880.0,
+      "eval_runtime": 627.3485,
+      "eval_samples_per_second": 1.594,
+      "eval_steps_per_second": 0.399,
+      "step": 120
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.0011839906219393015,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7413120.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "eval_loss": 1.0789405678224284e-05,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7413120.0,
+      "eval_runtime": 630.5032,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 130
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.001027945545502007,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 7983360.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "eval_loss": 9.804618457565084e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 7983360.0,
+      "eval_runtime": 626.6713,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 140
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0009170864359475672,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 8553600.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 8.696494660398457e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 8553600.0,
+      "eval_runtime": 630.4604,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 150
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.0008168203639797866,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9123840.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "eval_loss": 7.992691280378494e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9123840.0,
+      "eval_runtime": 628.5297,
+      "eval_samples_per_second": 1.591,
+      "eval_steps_per_second": 0.398,
+      "step": 160
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.0007576971547678113,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 9694080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "eval_loss": 7.28438317310065e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 9694080.0,
+      "eval_runtime": 626.7184,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 170
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0006879908032715321,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10264320.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 6.8836661739624105e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10264320.0,
+      "eval_runtime": 756.3063,
+      "eval_samples_per_second": 1.322,
+      "eval_steps_per_second": 0.331,
+      "step": 180
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.0006444182363338768,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 10834560.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "eval_loss": 6.4065607148222625e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 10834560.0,
+      "eval_runtime": 628.8265,
+      "eval_samples_per_second": 1.59,
+      "eval_steps_per_second": 0.398,
+      "step": 190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0005997396074235439,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11404800.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 6.104866770328954e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 11404800.0,
+      "eval_runtime": 688.2367,
+      "eval_samples_per_second": 1.453,
+      "eval_steps_per_second": 0.363,
+      "step": 200
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.0005526828463189304,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 11975040.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "eval_loss": 5.683682047674665e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 11975040.0,
+      "eval_runtime": 754.3494,
+      "eval_samples_per_second": 1.326,
+      "eval_steps_per_second": 0.331,
+      "step": 210
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0005140851717442274,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 12545280.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "eval_loss": 5.339933522918727e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 12545280.0,
+      "eval_runtime": 647.6999,
+      "eval_samples_per_second": 1.544,
+      "eval_steps_per_second": 0.386,
+      "step": 220
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.0004886530223302543,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 13115520.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "eval_loss": 5.0328567340329755e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 13115520.0,
+      "eval_runtime": 631.1227,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 230
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0004592030309140682,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 13685760.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 4.829912541026715e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 13685760.0,
+      "eval_runtime": 631.5138,
+      "eval_samples_per_second": 1.583,
+      "eval_steps_per_second": 0.396,
+      "step": 240
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0004404531209729612,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 14256000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 4.590192020259565e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 14256000.0,
+      "eval_runtime": 631.121,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 250
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.00041581166442483664,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 14826240.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "eval_loss": 4.422760412126081e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 14826240.0,
+      "eval_runtime": 626.5972,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 260
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.00039238750468939543,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 15396480.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 4.159514901402872e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 15396480.0,
+      "eval_runtime": 626.6804,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 270
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0003751284384634346,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 15966720.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "eval_loss": 4.007378265669104e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 15966720.0,
+      "eval_runtime": 626.6082,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 280
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "grad_norm": 0.0003600440395530313,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 16492410.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "eval_loss": 3.86876126867719e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 16492410.0,
+      "eval_runtime": 630.0967,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 290
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.00035800470504909754,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 17062650.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.064,
+      "eval_loss": 3.728666797542246e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 17062650.0,
+      "eval_runtime": 630.6538,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.396,
+      "step": 300
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "grad_norm": 0.0003293608024250716,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 17632890.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "eval_loss": 3.5069003843091195e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 17632890.0,
+      "eval_runtime": 626.3062,
+      "eval_samples_per_second": 1.597,
+      "eval_steps_per_second": 0.399,
+      "step": 310
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "grad_norm": 0.000320440623909235,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 18203130.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.1351111111111112,
+      "eval_loss": 3.4313563901378075e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 18203130.0,
+      "eval_runtime": 626.8382,
+      "eval_samples_per_second": 1.595,
+      "eval_steps_per_second": 0.399,
+      "step": 320
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 0.00031058763852342963,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 18773370.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "eval_loss": 3.2939326501946198e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 18773370.0,
+      "eval_runtime": 631.1457,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 330
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "grad_norm": 0.0002935119846370071,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 19343610.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.2062222222222223,
+      "eval_loss": 3.1630906960344873e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 19343610.0,
+      "eval_runtime": 631.1257,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 340
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "grad_norm": 0.00028090347768738866,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 19913850.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "eval_loss": 3.1076663162821205e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 19913850.0,
+      "eval_runtime": 631.1307,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 350
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 0.000271222204901278,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 20484090.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "eval_loss": 2.9442144295899197e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 20484090.0,
+      "eval_runtime": 631.362,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 360
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "grad_norm": 0.0002641026512719691,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 21054330.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "eval_loss": 2.8731856218655594e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 21054330.0,
+      "eval_runtime": 626.4927,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 370
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "grad_norm": 0.0002599551226012409,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 21624570.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.3484444444444446,
+      "eval_loss": 2.7712894734577276e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 21624570.0,
+      "eval_runtime": 626.4481,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 380
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.0002494712534826249,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 22194810.0,
+      "step": 390
+    },
+    {
+      "epoch": 1.384,
+      "eval_loss": 2.666238515303121e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 22194810.0,
+      "eval_runtime": 626.3873,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 390
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "grad_norm": 0.00024175533326342702,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 22765050.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.4195555555555557,
+      "eval_loss": 2.613794549688464e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 22765050.0,
+      "eval_runtime": 625.5663,
+      "eval_samples_per_second": 1.599,
+      "eval_steps_per_second": 0.4,
+      "step": 400
+    },
+    {
+      "epoch": 1.455111111111111,
+      "grad_norm": 0.0002301511267432943,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 23335290.0,
+      "step": 410
+    },
+    {
+      "epoch": 1.455111111111111,
+      "eval_loss": 2.55880513577722e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 23335290.0,
+      "eval_runtime": 630.8138,
+      "eval_samples_per_second": 1.585,
+      "eval_steps_per_second": 0.396,
+      "step": 410
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "grad_norm": 0.00023040513042360544,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 23905530.0,
+      "step": 420
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "eval_loss": 2.4679234229552094e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 23905530.0,
+      "eval_runtime": 630.4552,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 420
+    },
+    {
+      "epoch": 1.5262222222222221,
+      "grad_norm": 0.0002182941243518144,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 24475770.0,
+      "step": 430
+    },
+    {
+      "epoch": 1.5262222222222221,
+      "eval_loss": 2.395064711890882e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 24475770.0,
+      "eval_runtime": 627.55,
+      "eval_samples_per_second": 1.593,
+      "eval_steps_per_second": 0.398,
+      "step": 430
+    },
+    {
+      "epoch": 1.561777777777778,
+      "grad_norm": 0.00021538310102187097,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 25046010.0,
+      "step": 440
+    },
+    {
+      "epoch": 1.561777777777778,
+      "eval_loss": 2.3233274077938404e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 25046010.0,
+      "eval_runtime": 626.3834,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 440
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 0.000205744436243549,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 25616250.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "eval_loss": 2.2373139927367447e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 25616250.0,
+      "eval_runtime": 626.4713,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 450
+    },
+    {
+      "epoch": 1.6328888888888888,
+      "grad_norm": 0.00020622971351258457,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 26186490.0,
+      "step": 460
+    },
+    {
+      "epoch": 1.6328888888888888,
+      "eval_loss": 2.2288552372629056e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 26186490.0,
+      "eval_runtime": 629.9221,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 460
+    },
+    {
+      "epoch": 1.6684444444444444,
+      "grad_norm": 0.0001915807370096445,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 26756730.0,
+      "step": 470
+    },
+    {
+      "epoch": 1.6684444444444444,
+      "eval_loss": 2.1382338672992773e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 26756730.0,
+      "eval_runtime": 631.3677,
+      "eval_samples_per_second": 1.584,
+      "eval_steps_per_second": 0.396,
+      "step": 470
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.0001857055613072589,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 27326970.0,
+      "step": 480
+    },
+    {
+      "epoch": 1.704,
+      "eval_loss": 2.078363195323618e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 27326970.0,
+      "eval_runtime": 626.5474,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 480
+    },
+    {
+      "epoch": 1.7395555555555555,
+      "grad_norm": 0.0001786583598004654,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 27897210.0,
+      "step": 490
+    },
+    {
+      "epoch": 1.7395555555555555,
+      "eval_loss": 2.0040279196109623e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 27897210.0,
+      "eval_runtime": 630.3478,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.397,
+      "step": 490
+    },
+    {
+      "epoch": 1.775111111111111,
+      "grad_norm": 0.00017898347869049758,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 28467450.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.775111111111111,
+      "eval_loss": 1.946991005752352e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 28467450.0,
+      "eval_runtime": 630.0683,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.397,
+      "step": 500
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "grad_norm": 0.00017079812823794782,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 29037690.0,
+      "step": 510
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "eval_loss": 1.950623527591233e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 29037690.0,
+      "eval_runtime": 626.6265,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 510
+    },
+    {
+      "epoch": 1.8462222222222222,
+      "grad_norm": 0.00016901094932109118,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 29607930.0,
+      "step": 520
+    },
+    {
+      "epoch": 1.8462222222222222,
+      "eval_loss": 1.898369532682409e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 29607930.0,
+      "eval_runtime": 626.583,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 520
+    },
+    {
+      "epoch": 1.8817777777777778,
+      "grad_norm": 0.00017019332153722644,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 30178170.0,
+      "step": 530
+    },
+    {
+      "epoch": 1.8817777777777778,
+      "eval_loss": 1.8598769884192734e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 30178170.0,
+      "eval_runtime": 626.4907,
+      "eval_samples_per_second": 1.596,
+      "eval_steps_per_second": 0.399,
+      "step": 530
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "grad_norm": 0.0001607046724529937,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 30748410.0,
+      "step": 540
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "eval_loss": 1.798646053430275e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 30748410.0,
+      "eval_runtime": 626.1949,
+      "eval_samples_per_second": 1.597,
+      "eval_steps_per_second": 0.399,
+      "step": 540
+    },
+    {
+      "epoch": 1.952888888888889,
+      "grad_norm": 0.00015570198593195528,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 31318650.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.952888888888889,
+      "eval_loss": 1.7364616269333055e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 31318650.0,
+      "eval_runtime": 631.0041,
+      "eval_samples_per_second": 1.585,
+      "eval_steps_per_second": 0.396,
+      "step": 550
+    },
+    {
+      "epoch": 1.9884444444444445,
+      "grad_norm": 0.00015243745292536914,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 31888890.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.9884444444444445,
+      "eval_loss": 1.7059577430700301e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 31888890.0,
+      "eval_runtime": 628.2317,
+      "eval_samples_per_second": 1.592,
+      "eval_steps_per_second": 0.398,
+      "step": 560
+    },
+    {
+      "epoch": 2.021333333333333,
+      "grad_norm": 0.00014857217320241034,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 32414580.0,
+      "step": 570
+    },
+    {
+      "epoch": 2.021333333333333,
+      "eval_loss": 1.6856015463417862e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 32414580.0,
+      "eval_runtime": 1329.2357,
+      "eval_samples_per_second": 0.752,
+      "eval_steps_per_second": 0.188,
+      "step": 570
+    },
+    {
+      "epoch": 2.056888888888889,
+      "grad_norm": 0.00014311449194792658,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 32984820.0,
+      "step": 580
+    },
+    {
+      "epoch": 2.056888888888889,
+      "eval_loss": 1.6173969470401062e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 32984820.0,
+      "eval_runtime": 1323.5911,
+      "eval_samples_per_second": 0.756,
+      "eval_steps_per_second": 0.189,
+      "step": 580
+    },
+    {
+      "epoch": 2.0924444444444443,
+      "grad_norm": 0.0001415183360222727,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 33555060.0,
+      "step": 590
+    },
+    {
+      "epoch": 2.0924444444444443,
+      "eval_loss": 1.6115862990773167e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 33555060.0,
+      "eval_runtime": 1365.3901,
+      "eval_samples_per_second": 0.732,
+      "eval_steps_per_second": 0.183,
+      "step": 590
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.0001429204421583563,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 34125300.0,
+      "step": 600
+    },
+    {
+      "epoch": 2.128,
+      "eval_loss": 1.558861640660325e-06,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 34125300.0,
+      "eval_runtime": 1397.439,
+      "eval_samples_per_second": 0.716,
+      "eval_steps_per_second": 0.179,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 846,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5866015047584768e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea9672706e844d882368a147887a0a30f825af7ec487e8e243dda0b8a0c6d19
+size 5816