Add files using upload-large-folder tool

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-03-13
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2025-03-13
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the pytest dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 19.642201834862384,
+    "num_input_tokens_seen": 44384416,
+    "total_flos": 3.7443435796826685e+18,
+    "train_loss": 0.12719786286233337,
+    "train_runtime": 18727.1135,
+    "train_samples_per_second": 0.931,
+    "train_steps_per_second": 0.058
+}

checkpoint-1026/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1026/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-108/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-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 0.12.0

checkpoint-108/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-108/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-108/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-108/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 15000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-108/trainer_state.json

@@ -0,0 +1,897 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9724770642201834,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.04378490149974823,
+      "learning_rate": 4.999989423013716e-05,
+      "loss": 0.6713,
+      "num_input_tokens_seen": 44136,
+      "step": 1
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.040646992623806,
+      "learning_rate": 4.999957692144361e-05,
+      "loss": 0.533,
+      "num_input_tokens_seen": 83096,
+      "step": 2
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.04658753052353859,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.6048,
+      "num_input_tokens_seen": 122112,
+      "step": 3
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.04322144016623497,
+      "learning_rate": 4.999830770009406e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 163064,
+      "step": 4
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.06536195427179337,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.6607,
+      "num_input_tokens_seen": 203808,
+      "step": 5
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.059904925525188446,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.5802,
+      "num_input_tokens_seen": 241824,
+      "step": 6
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.19818365573883057,
+      "learning_rate": 4.999481745213471e-05,
+      "loss": 0.5148,
+      "num_input_tokens_seen": 287608,
+      "step": 7
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.05985472351312637,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5714,
+      "num_input_tokens_seen": 325320,
+      "step": 8
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.061375778168439865,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.6812,
+      "num_input_tokens_seen": 369848,
+      "step": 9
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.06196414306759834,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.5358,
+      "num_input_tokens_seen": 415104,
+      "step": 10
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.07861393690109253,
+      "learning_rate": 4.9987202929487275e-05,
+      "loss": 0.6527,
+      "num_input_tokens_seen": 467224,
+      "step": 11
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.05596446990966797,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.5354,
+      "num_input_tokens_seen": 502824,
+      "step": 12
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.05289844051003456,
+      "learning_rate": 4.998212701060612e-05,
+      "loss": 0.5263,
+      "num_input_tokens_seen": 544744,
+      "step": 13
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.04996591433882713,
+      "learning_rate": 4.997927195724303e-05,
+      "loss": 0.5536,
+      "num_input_tokens_seen": 591136,
+      "step": 14
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.05822828412055969,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.6106,
+      "num_input_tokens_seen": 629664,
+      "step": 15
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.06353770196437836,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5129,
+      "num_input_tokens_seen": 663392,
+      "step": 16
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.07256966829299927,
+      "learning_rate": 4.996943871672807e-05,
+      "loss": 0.6377,
+      "num_input_tokens_seen": 698360,
+      "step": 17
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.055458713322877884,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 737520,
+      "step": 18
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07792335003614426,
+      "learning_rate": 4.9961826771182784e-05,
+      "loss": 0.6086,
+      "num_input_tokens_seen": 768056,
+      "step": 19
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.06627275049686432,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.4591,
+      "num_input_tokens_seen": 806256,
+      "step": 20
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.05830290913581848,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.3731,
+      "num_input_tokens_seen": 842336,
+      "step": 21
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07277437299489975,
+      "learning_rate": 4.9948824819150185e-05,
+      "loss": 0.6243,
+      "num_input_tokens_seen": 876672,
+      "step": 22
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.07477546483278275,
+      "learning_rate": 4.994406857105136e-05,
+      "loss": 0.5788,
+      "num_input_tokens_seen": 915192,
+      "step": 23
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.06912907212972641,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4753,
+      "num_input_tokens_seen": 951904,
+      "step": 24
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.0655476376414299,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.4518,
+      "num_input_tokens_seen": 1001816,
+      "step": 25
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.06466512382030487,
+      "learning_rate": 4.992853359792444e-05,
+      "loss": 0.5638,
+      "num_input_tokens_seen": 1053064,
+      "step": 26
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0645688995718956,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4644,
+      "num_input_tokens_seen": 1086688,
+      "step": 27
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07181251049041748,
+      "learning_rate": 4.9917122201112656e-05,
+      "loss": 0.6191,
+      "num_input_tokens_seen": 1134824,
+      "step": 28
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.07322589308023453,
+      "learning_rate": 4.9911100220449293e-05,
+      "loss": 0.6752,
+      "num_input_tokens_seen": 1172072,
+      "step": 29
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.06396070122718811,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.3587,
+      "num_input_tokens_seen": 1211096,
+      "step": 30
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.07803395390510559,
+      "learning_rate": 4.989842394938482e-05,
+      "loss": 0.459,
+      "num_input_tokens_seen": 1259456,
+      "step": 31
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.05974648892879486,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 1306944,
+      "step": 32
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.09784268587827682,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.539,
+      "num_input_tokens_seen": 1353744,
+      "step": 33
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.09906516224145889,
+      "learning_rate": 4.987782958627508e-05,
+      "loss": 0.5453,
+      "num_input_tokens_seen": 1394736,
+      "step": 34
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.08984062820672989,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.468,
+      "num_input_tokens_seen": 1442048,
+      "step": 35
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08672655373811722,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.4078,
+      "num_input_tokens_seen": 1478440,
+      "step": 36
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.1327345073223114,
+      "learning_rate": 4.9855340680123905e-05,
+      "loss": 0.5299,
+      "num_input_tokens_seen": 1525992,
+      "step": 37
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.09178602695465088,
+      "learning_rate": 4.9847423660363e-05,
+      "loss": 0.439,
+      "num_input_tokens_seen": 1555608,
+      "step": 38
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.09418320655822754,
+      "learning_rate": 4.983929639191469e-05,
+      "loss": 0.5337,
+      "num_input_tokens_seen": 1597392,
+      "step": 39
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.08294719457626343,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.4536,
+      "num_input_tokens_seen": 1649656,
+      "step": 40
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.09774205833673477,
+      "learning_rate": 4.982241138581273e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 1695952,
+      "step": 41
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.09319107979536057,
+      "learning_rate": 4.9813653791033057e-05,
+      "loss": 0.4279,
+      "num_input_tokens_seen": 1737224,
+      "step": 42
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.09561405330896378,
+      "learning_rate": 4.980468623331273e-05,
+      "loss": 0.5121,
+      "num_input_tokens_seen": 1772320,
+      "step": 43
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08274025470018387,
+      "learning_rate": 4.979550878853154e-05,
+      "loss": 0.54,
+      "num_input_tokens_seen": 1823888,
+      "step": 44
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.08728913217782974,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1872488,
+      "step": 45
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.0787016749382019,
+      "learning_rate": 4.9776524550184965e-05,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 1924744,
+      "step": 46
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.10952188074588776,
+      "learning_rate": 4.97667179172564e-05,
+      "loss": 0.4784,
+      "num_input_tokens_seen": 1959936,
+      "step": 47
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.08525826781988144,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.3586,
+      "num_input_tokens_seen": 2003896,
+      "step": 48
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10409987717866898,
+      "learning_rate": 4.9746476038786496e-05,
+      "loss": 0.4451,
+      "num_input_tokens_seen": 2047632,
+      "step": 49
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.0782993957400322,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.3591,
+      "num_input_tokens_seen": 2096928,
+      "step": 50
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.09829951077699661,
+      "learning_rate": 4.9725396584047925e-05,
+      "loss": 0.3415,
+      "num_input_tokens_seen": 2129536,
+      "step": 51
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.10606162995100021,
+      "learning_rate": 4.971454298742779e-05,
+      "loss": 0.3758,
+      "num_input_tokens_seen": 2169144,
+      "step": 52
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.09280356764793396,
+      "learning_rate": 4.97034802665019e-05,
+      "loss": 0.485,
+      "num_input_tokens_seen": 2207720,
+      "step": 53
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11888203024864197,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.3469,
+      "num_input_tokens_seen": 2236392,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13222463428974152,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.4284,
+      "num_input_tokens_seen": 2259088,
+      "step": 55
+    },
+    {
+      "epoch": 1.018348623853211,
+      "grad_norm": 0.10572745651006699,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4186,
+      "num_input_tokens_seen": 2298496,
+      "step": 56
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11462350189685822,
+      "learning_rate": 4.965714003843079e-05,
+      "loss": 0.4696,
+      "num_input_tokens_seen": 2333016,
+      "step": 57
+    },
+    {
+      "epoch": 1.0550458715596331,
+      "grad_norm": 0.11215240508317947,
+      "learning_rate": 4.9645033135461494e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 2367992,
+      "step": 58
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.0973561555147171,
+      "learning_rate": 4.963271769635024e-05,
+      "loss": 0.3588,
+      "num_input_tokens_seen": 2415328,
+      "step": 59
+    },
+    {
+      "epoch": 1.091743119266055,
+      "grad_norm": 0.10240709036588669,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.5532,
+      "num_input_tokens_seen": 2454792,
+      "step": 60
+    },
+    {
+      "epoch": 1.110091743119266,
+      "grad_norm": 0.0959337130188942,
+      "learning_rate": 4.9607461628298244e-05,
+      "loss": 0.331,
+      "num_input_tokens_seen": 2503072,
+      "step": 61
+    },
+    {
+      "epoch": 1.1284403669724772,
+      "grad_norm": 0.10228750854730606,
+      "learning_rate": 4.9594521213063974e-05,
+      "loss": 0.3728,
+      "num_input_tokens_seen": 2546960,
+      "step": 62
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.09403488785028458,
+      "learning_rate": 4.958137268909887e-05,
+      "loss": 0.4695,
+      "num_input_tokens_seen": 2595432,
+      "step": 63
+    },
+    {
+      "epoch": 1.165137614678899,
+      "grad_norm": 0.11396344751119614,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 2633912,
+      "step": 64
+    },
+    {
+      "epoch": 1.18348623853211,
+      "grad_norm": 0.09487481415271759,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.3498,
+      "num_input_tokens_seen": 2680792,
+      "step": 65
+    },
+    {
+      "epoch": 1.2018348623853212,
+      "grad_norm": 0.1249895691871643,
+      "learning_rate": 4.9540679586191605e-05,
+      "loss": 0.4053,
+      "num_input_tokens_seen": 2716584,
+      "step": 66
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.12268221378326416,
+      "learning_rate": 4.952669975747232e-05,
+      "loss": 0.4189,
+      "num_input_tokens_seen": 2757088,
+      "step": 67
+    },
+    {
+      "epoch": 1.238532110091743,
+      "grad_norm": 0.12126032263040543,
+      "learning_rate": 4.951251239389948e-05,
+      "loss": 0.4994,
+      "num_input_tokens_seen": 2795664,
+      "step": 68
+    },
+    {
+      "epoch": 1.2568807339449541,
+      "grad_norm": 0.1069057360291481,
+      "learning_rate": 4.949811761552074e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 2840936,
+      "step": 69
+    },
+    {
+      "epoch": 1.2752293577981653,
+      "grad_norm": 0.10893313586711884,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.4366,
+      "num_input_tokens_seen": 2886768,
+      "step": 70
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.12898756563663483,
+      "learning_rate": 4.9468706303310355e-05,
+      "loss": 0.3916,
+      "num_input_tokens_seen": 2919328,
+      "step": 71
+    },
+    {
+      "epoch": 1.311926605504587,
+      "grad_norm": 0.12405356019735336,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3249,
+      "num_input_tokens_seen": 2966744,
+      "step": 72
+    },
+    {
+      "epoch": 1.3302752293577982,
+      "grad_norm": 0.13137595355510712,
+      "learning_rate": 4.943846681630479e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3007248,
+      "step": 73
+    },
+    {
+      "epoch": 1.3486238532110093,
+      "grad_norm": 0.13920250535011292,
+      "learning_rate": 4.942303682600178e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3050960,
+      "step": 74
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.1255589872598648,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3773,
+      "num_input_tokens_seen": 3088592,
+      "step": 75
+    },
+    {
+      "epoch": 1.385321100917431,
+      "grad_norm": 0.10222747176885605,
+      "learning_rate": 4.939155700460536e-05,
+      "loss": 0.4,
+      "num_input_tokens_seen": 3153520,
+      "step": 76
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.13205283880233765,
+      "learning_rate": 4.9375507439881266e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 3199272,
+      "step": 77
+    },
+    {
+      "epoch": 1.4220183486238533,
+      "grad_norm": 0.11005694419145584,
+      "learning_rate": 4.9359251619630886e-05,
+      "loss": 0.3881,
+      "num_input_tokens_seen": 3247128,
+      "step": 78
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.14799247682094574,
+      "learning_rate": 4.9342789681404275e-05,
+      "loss": 0.3972,
+      "num_input_tokens_seen": 3294192,
+      "step": 79
+    },
+    {
+      "epoch": 1.4587155963302751,
+      "grad_norm": 0.1279418021440506,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.3438,
+      "num_input_tokens_seen": 3329736,
+      "step": 80
+    },
+    {
+      "epoch": 1.4770642201834863,
+      "grad_norm": 0.11036807298660278,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3189,
+      "num_input_tokens_seen": 3371376,
+      "step": 81
+    },
+    {
+      "epoch": 1.4954128440366974,
+      "grad_norm": 0.11855707317590714,
+      "learning_rate": 4.9292168560522014e-05,
+      "loss": 0.401,
+      "num_input_tokens_seen": 3412368,
+      "step": 82
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.13195356726646423,
+      "learning_rate": 4.9274883560755156e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 3455000,
+      "step": 83
+    },
+    {
+      "epoch": 1.5321100917431192,
+      "grad_norm": 0.1462787538766861,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.3768,
+      "num_input_tokens_seen": 3488960,
+      "step": 84
+    },
+    {
+      "epoch": 1.5504587155963303,
+      "grad_norm": 0.13765974342823029,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 3521320,
+      "step": 85
+    },
+    {
+      "epoch": 1.5688073394495414,
+      "grad_norm": 0.15276113152503967,
+      "learning_rate": 4.9221796730647516e-05,
+      "loss": 0.3638,
+      "num_input_tokens_seen": 3559464,
+      "step": 86
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.1441674381494522,
+      "learning_rate": 4.92036910094527e-05,
+      "loss": 0.3919,
+      "num_input_tokens_seen": 3598080,
+      "step": 87
+    },
+    {
+      "epoch": 1.6055045871559632,
+      "grad_norm": 0.1780252456665039,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.3626,
+      "num_input_tokens_seen": 3630064,
+      "step": 88
+    },
+    {
+      "epoch": 1.6238532110091743,
+      "grad_norm": 0.16947726905345917,
+      "learning_rate": 4.916686531694035e-05,
+      "loss": 0.3439,
+      "num_input_tokens_seen": 3661408,
+      "step": 89
+    },
+    {
+      "epoch": 1.6422018348623855,
+      "grad_norm": 0.1552971601486206,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.3236,
+      "num_input_tokens_seen": 3695480,
+      "step": 90
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.14925938844680786,
+      "learning_rate": 4.912922166582874e-05,
+      "loss": 0.4255,
+      "num_input_tokens_seen": 3734560,
+      "step": 91
+    },
+    {
+      "epoch": 1.6788990825688073,
+      "grad_norm": 0.1332874596118927,
+      "learning_rate": 4.9110093502873476e-05,
+      "loss": 0.3061,
+      "num_input_tokens_seen": 3773112,
+      "step": 92
+    },
+    {
+      "epoch": 1.6972477064220184,
+      "grad_norm": 0.15471243858337402,
+      "learning_rate": 4.909076133021557e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 3813392,
+      "step": 93
+    },
+    {
+      "epoch": 1.7155963302752295,
+      "grad_norm": 0.16010524332523346,
+      "learning_rate": 4.907122531143594e-05,
+      "loss": 0.4179,
+      "num_input_tokens_seen": 3856416,
+      "step": 94
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.13423003256320953,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.3593,
+      "num_input_tokens_seen": 3899472,
+      "step": 95
+    },
+    {
+      "epoch": 1.7522935779816513,
+      "grad_norm": 0.14900773763656616,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.5007,
+      "num_input_tokens_seen": 3962976,
+      "step": 96
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.15728624165058136,
+      "learning_rate": 4.9011395840040144e-05,
+      "loss": 0.3484,
+      "num_input_tokens_seen": 4000696,
+      "step": 97
+    },
+    {
+      "epoch": 1.7889908256880735,
+      "grad_norm": 0.11092367768287659,
+      "learning_rate": 4.8991046107058735e-05,
+      "loss": 0.2889,
+      "num_input_tokens_seen": 4045256,
+      "step": 98
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.1289113610982895,
+      "learning_rate": 4.8970493371704826e-05,
+      "loss": 0.2203,
+      "num_input_tokens_seen": 4076800,
+      "step": 99
+    },
+    {
+      "epoch": 1.8256880733944953,
+      "grad_norm": 0.18886639177799225,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.3966,
+      "num_input_tokens_seen": 4119840,
+      "step": 100
+    },
+    {
+      "epoch": 1.8440366972477065,
+      "grad_norm": 0.1563039869070053,
+      "learning_rate": 4.892877959123097e-05,
+      "loss": 0.4417,
+      "num_input_tokens_seen": 4165848,
+      "step": 101
+    },
+    {
+      "epoch": 1.8623853211009176,
+      "grad_norm": 0.16883380711078644,
+      "learning_rate": 4.890761889907589e-05,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 4202824,
+      "step": 102
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.18241995573043823,
+      "learning_rate": 4.8886255910475054e-05,
+      "loss": 0.3952,
+      "num_input_tokens_seen": 4233888,
+      "step": 103
+    },
+    {
+      "epoch": 1.8990825688073394,
+      "grad_norm": 0.19913265109062195,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.3241,
+      "num_input_tokens_seen": 4267064,
+      "step": 104
+    },
+    {
+      "epoch": 1.9174311926605505,
+      "grad_norm": 0.18295545876026154,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.4239,
+      "num_input_tokens_seen": 4312536,
+      "step": 105
+    },
+    {
+      "epoch": 1.9357798165137616,
+      "grad_norm": 0.16657495498657227,
+      "learning_rate": 4.8820954982195905e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 4356656,
+      "step": 106
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.18504932522773743,
+      "learning_rate": 4.879878463255483e-05,
+      "loss": 0.44,
+      "num_input_tokens_seen": 4400216,
+      "step": 107
+    },
+    {
+      "epoch": 1.9724770642201834,
+      "grad_norm": 0.1923118382692337,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2662,
+      "num_input_tokens_seen": 4436968,
+      "step": 108
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1080,
+  "num_input_tokens_seen": 4436968,
+  "num_train_epochs": 20,
+  "save_steps": 54,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.7431004224710246e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1080/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-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 0.12.0

checkpoint-1080/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1080/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1080/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-1080/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 15000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-162/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-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 0.12.0

checkpoint-162/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-162/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-162/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-162/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 15000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-162/trainer_state.json

@@ -0,0 +1,1329 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9541284403669725,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.04378490149974823,
+      "learning_rate": 4.999989423013716e-05,
+      "loss": 0.6713,
+      "num_input_tokens_seen": 44136,
+      "step": 1
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.040646992623806,
+      "learning_rate": 4.999957692144361e-05,
+      "loss": 0.533,
+      "num_input_tokens_seen": 83096,
+      "step": 2
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.04658753052353859,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.6048,
+      "num_input_tokens_seen": 122112,
+      "step": 3
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.04322144016623497,
+      "learning_rate": 4.999830770009406e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 163064,
+      "step": 4
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.06536195427179337,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.6607,
+      "num_input_tokens_seen": 203808,
+      "step": 5
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.059904925525188446,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.5802,
+      "num_input_tokens_seen": 241824,
+      "step": 6
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.19818365573883057,
+      "learning_rate": 4.999481745213471e-05,
+      "loss": 0.5148,
+      "num_input_tokens_seen": 287608,
+      "step": 7
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.05985472351312637,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5714,
+      "num_input_tokens_seen": 325320,
+      "step": 8
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.061375778168439865,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.6812,
+      "num_input_tokens_seen": 369848,
+      "step": 9
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.06196414306759834,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.5358,
+      "num_input_tokens_seen": 415104,
+      "step": 10
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.07861393690109253,
+      "learning_rate": 4.9987202929487275e-05,
+      "loss": 0.6527,
+      "num_input_tokens_seen": 467224,
+      "step": 11
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.05596446990966797,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.5354,
+      "num_input_tokens_seen": 502824,
+      "step": 12
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.05289844051003456,
+      "learning_rate": 4.998212701060612e-05,
+      "loss": 0.5263,
+      "num_input_tokens_seen": 544744,
+      "step": 13
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.04996591433882713,
+      "learning_rate": 4.997927195724303e-05,
+      "loss": 0.5536,
+      "num_input_tokens_seen": 591136,
+      "step": 14
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.05822828412055969,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.6106,
+      "num_input_tokens_seen": 629664,
+      "step": 15
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.06353770196437836,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5129,
+      "num_input_tokens_seen": 663392,
+      "step": 16
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.07256966829299927,
+      "learning_rate": 4.996943871672807e-05,
+      "loss": 0.6377,
+      "num_input_tokens_seen": 698360,
+      "step": 17
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.055458713322877884,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 737520,
+      "step": 18
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07792335003614426,
+      "learning_rate": 4.9961826771182784e-05,
+      "loss": 0.6086,
+      "num_input_tokens_seen": 768056,
+      "step": 19
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.06627275049686432,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.4591,
+      "num_input_tokens_seen": 806256,
+      "step": 20
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.05830290913581848,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.3731,
+      "num_input_tokens_seen": 842336,
+      "step": 21
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07277437299489975,
+      "learning_rate": 4.9948824819150185e-05,
+      "loss": 0.6243,
+      "num_input_tokens_seen": 876672,
+      "step": 22
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.07477546483278275,
+      "learning_rate": 4.994406857105136e-05,
+      "loss": 0.5788,
+      "num_input_tokens_seen": 915192,
+      "step": 23
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.06912907212972641,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4753,
+      "num_input_tokens_seen": 951904,
+      "step": 24
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.0655476376414299,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.4518,
+      "num_input_tokens_seen": 1001816,
+      "step": 25
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.06466512382030487,
+      "learning_rate": 4.992853359792444e-05,
+      "loss": 0.5638,
+      "num_input_tokens_seen": 1053064,
+      "step": 26
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0645688995718956,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4644,
+      "num_input_tokens_seen": 1086688,
+      "step": 27
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07181251049041748,
+      "learning_rate": 4.9917122201112656e-05,
+      "loss": 0.6191,
+      "num_input_tokens_seen": 1134824,
+      "step": 28
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.07322589308023453,
+      "learning_rate": 4.9911100220449293e-05,
+      "loss": 0.6752,
+      "num_input_tokens_seen": 1172072,
+      "step": 29
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.06396070122718811,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.3587,
+      "num_input_tokens_seen": 1211096,
+      "step": 30
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.07803395390510559,
+      "learning_rate": 4.989842394938482e-05,
+      "loss": 0.459,
+      "num_input_tokens_seen": 1259456,
+      "step": 31
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.05974648892879486,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 1306944,
+      "step": 32
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.09784268587827682,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.539,
+      "num_input_tokens_seen": 1353744,
+      "step": 33
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.09906516224145889,
+      "learning_rate": 4.987782958627508e-05,
+      "loss": 0.5453,
+      "num_input_tokens_seen": 1394736,
+      "step": 34
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.08984062820672989,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.468,
+      "num_input_tokens_seen": 1442048,
+      "step": 35
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08672655373811722,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.4078,
+      "num_input_tokens_seen": 1478440,
+      "step": 36
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.1327345073223114,
+      "learning_rate": 4.9855340680123905e-05,
+      "loss": 0.5299,
+      "num_input_tokens_seen": 1525992,
+      "step": 37
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.09178602695465088,
+      "learning_rate": 4.9847423660363e-05,
+      "loss": 0.439,
+      "num_input_tokens_seen": 1555608,
+      "step": 38
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.09418320655822754,
+      "learning_rate": 4.983929639191469e-05,
+      "loss": 0.5337,
+      "num_input_tokens_seen": 1597392,
+      "step": 39
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.08294719457626343,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.4536,
+      "num_input_tokens_seen": 1649656,
+      "step": 40
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.09774205833673477,
+      "learning_rate": 4.982241138581273e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 1695952,
+      "step": 41
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.09319107979536057,
+      "learning_rate": 4.9813653791033057e-05,
+      "loss": 0.4279,
+      "num_input_tokens_seen": 1737224,
+      "step": 42
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.09561405330896378,
+      "learning_rate": 4.980468623331273e-05,
+      "loss": 0.5121,
+      "num_input_tokens_seen": 1772320,
+      "step": 43
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08274025470018387,
+      "learning_rate": 4.979550878853154e-05,
+      "loss": 0.54,
+      "num_input_tokens_seen": 1823888,
+      "step": 44
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.08728913217782974,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1872488,
+      "step": 45
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.0787016749382019,
+      "learning_rate": 4.9776524550184965e-05,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 1924744,
+      "step": 46
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.10952188074588776,
+      "learning_rate": 4.97667179172564e-05,
+      "loss": 0.4784,
+      "num_input_tokens_seen": 1959936,
+      "step": 47
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.08525826781988144,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.3586,
+      "num_input_tokens_seen": 2003896,
+      "step": 48
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10409987717866898,
+      "learning_rate": 4.9746476038786496e-05,
+      "loss": 0.4451,
+      "num_input_tokens_seen": 2047632,
+      "step": 49
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.0782993957400322,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.3591,
+      "num_input_tokens_seen": 2096928,
+      "step": 50
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.09829951077699661,
+      "learning_rate": 4.9725396584047925e-05,
+      "loss": 0.3415,
+      "num_input_tokens_seen": 2129536,
+      "step": 51
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.10606162995100021,
+      "learning_rate": 4.971454298742779e-05,
+      "loss": 0.3758,
+      "num_input_tokens_seen": 2169144,
+      "step": 52
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.09280356764793396,
+      "learning_rate": 4.97034802665019e-05,
+      "loss": 0.485,
+      "num_input_tokens_seen": 2207720,
+      "step": 53
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11888203024864197,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.3469,
+      "num_input_tokens_seen": 2236392,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13222463428974152,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.4284,
+      "num_input_tokens_seen": 2259088,
+      "step": 55
+    },
+    {
+      "epoch": 1.018348623853211,
+      "grad_norm": 0.10572745651006699,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4186,
+      "num_input_tokens_seen": 2298496,
+      "step": 56
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11462350189685822,
+      "learning_rate": 4.965714003843079e-05,
+      "loss": 0.4696,
+      "num_input_tokens_seen": 2333016,
+      "step": 57
+    },
+    {
+      "epoch": 1.0550458715596331,
+      "grad_norm": 0.11215240508317947,
+      "learning_rate": 4.9645033135461494e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 2367992,
+      "step": 58
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.0973561555147171,
+      "learning_rate": 4.963271769635024e-05,
+      "loss": 0.3588,
+      "num_input_tokens_seen": 2415328,
+      "step": 59
+    },
+    {
+      "epoch": 1.091743119266055,
+      "grad_norm": 0.10240709036588669,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.5532,
+      "num_input_tokens_seen": 2454792,
+      "step": 60
+    },
+    {
+      "epoch": 1.110091743119266,
+      "grad_norm": 0.0959337130188942,
+      "learning_rate": 4.9607461628298244e-05,
+      "loss": 0.331,
+      "num_input_tokens_seen": 2503072,
+      "step": 61
+    },
+    {
+      "epoch": 1.1284403669724772,
+      "grad_norm": 0.10228750854730606,
+      "learning_rate": 4.9594521213063974e-05,
+      "loss": 0.3728,
+      "num_input_tokens_seen": 2546960,
+      "step": 62
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.09403488785028458,
+      "learning_rate": 4.958137268909887e-05,
+      "loss": 0.4695,
+      "num_input_tokens_seen": 2595432,
+      "step": 63
+    },
+    {
+      "epoch": 1.165137614678899,
+      "grad_norm": 0.11396344751119614,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 2633912,
+      "step": 64
+    },
+    {
+      "epoch": 1.18348623853211,
+      "grad_norm": 0.09487481415271759,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.3498,
+      "num_input_tokens_seen": 2680792,
+      "step": 65
+    },
+    {
+      "epoch": 1.2018348623853212,
+      "grad_norm": 0.1249895691871643,
+      "learning_rate": 4.9540679586191605e-05,
+      "loss": 0.4053,
+      "num_input_tokens_seen": 2716584,
+      "step": 66
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.12268221378326416,
+      "learning_rate": 4.952669975747232e-05,
+      "loss": 0.4189,
+      "num_input_tokens_seen": 2757088,
+      "step": 67
+    },
+    {
+      "epoch": 1.238532110091743,
+      "grad_norm": 0.12126032263040543,
+      "learning_rate": 4.951251239389948e-05,
+      "loss": 0.4994,
+      "num_input_tokens_seen": 2795664,
+      "step": 68
+    },
+    {
+      "epoch": 1.2568807339449541,
+      "grad_norm": 0.1069057360291481,
+      "learning_rate": 4.949811761552074e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 2840936,
+      "step": 69
+    },
+    {
+      "epoch": 1.2752293577981653,
+      "grad_norm": 0.10893313586711884,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.4366,
+      "num_input_tokens_seen": 2886768,
+      "step": 70
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.12898756563663483,
+      "learning_rate": 4.9468706303310355e-05,
+      "loss": 0.3916,
+      "num_input_tokens_seen": 2919328,
+      "step": 71
+    },
+    {
+      "epoch": 1.311926605504587,
+      "grad_norm": 0.12405356019735336,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3249,
+      "num_input_tokens_seen": 2966744,
+      "step": 72
+    },
+    {
+      "epoch": 1.3302752293577982,
+      "grad_norm": 0.13137595355510712,
+      "learning_rate": 4.943846681630479e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3007248,
+      "step": 73
+    },
+    {
+      "epoch": 1.3486238532110093,
+      "grad_norm": 0.13920250535011292,
+      "learning_rate": 4.942303682600178e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3050960,
+      "step": 74
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.1255589872598648,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3773,
+      "num_input_tokens_seen": 3088592,
+      "step": 75
+    },
+    {
+      "epoch": 1.385321100917431,
+      "grad_norm": 0.10222747176885605,
+      "learning_rate": 4.939155700460536e-05,
+      "loss": 0.4,
+      "num_input_tokens_seen": 3153520,
+      "step": 76
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.13205283880233765,
+      "learning_rate": 4.9375507439881266e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 3199272,
+      "step": 77
+    },
+    {
+      "epoch": 1.4220183486238533,
+      "grad_norm": 0.11005694419145584,
+      "learning_rate": 4.9359251619630886e-05,
+      "loss": 0.3881,
+      "num_input_tokens_seen": 3247128,
+      "step": 78
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.14799247682094574,
+      "learning_rate": 4.9342789681404275e-05,
+      "loss": 0.3972,
+      "num_input_tokens_seen": 3294192,
+      "step": 79
+    },
+    {
+      "epoch": 1.4587155963302751,
+      "grad_norm": 0.1279418021440506,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.3438,
+      "num_input_tokens_seen": 3329736,
+      "step": 80
+    },
+    {
+      "epoch": 1.4770642201834863,
+      "grad_norm": 0.11036807298660278,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3189,
+      "num_input_tokens_seen": 3371376,
+      "step": 81
+    },
+    {
+      "epoch": 1.4954128440366974,
+      "grad_norm": 0.11855707317590714,
+      "learning_rate": 4.9292168560522014e-05,
+      "loss": 0.401,
+      "num_input_tokens_seen": 3412368,
+      "step": 82
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.13195356726646423,
+      "learning_rate": 4.9274883560755156e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 3455000,
+      "step": 83
+    },
+    {
+      "epoch": 1.5321100917431192,
+      "grad_norm": 0.1462787538766861,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.3768,
+      "num_input_tokens_seen": 3488960,
+      "step": 84
+    },
+    {
+      "epoch": 1.5504587155963303,
+      "grad_norm": 0.13765974342823029,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 3521320,
+      "step": 85
+    },
+    {
+      "epoch": 1.5688073394495414,
+      "grad_norm": 0.15276113152503967,
+      "learning_rate": 4.9221796730647516e-05,
+      "loss": 0.3638,
+      "num_input_tokens_seen": 3559464,
+      "step": 86
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.1441674381494522,
+      "learning_rate": 4.92036910094527e-05,
+      "loss": 0.3919,
+      "num_input_tokens_seen": 3598080,
+      "step": 87
+    },
+    {
+      "epoch": 1.6055045871559632,
+      "grad_norm": 0.1780252456665039,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.3626,
+      "num_input_tokens_seen": 3630064,
+      "step": 88
+    },
+    {
+      "epoch": 1.6238532110091743,
+      "grad_norm": 0.16947726905345917,
+      "learning_rate": 4.916686531694035e-05,
+      "loss": 0.3439,
+      "num_input_tokens_seen": 3661408,
+      "step": 89
+    },
+    {
+      "epoch": 1.6422018348623855,
+      "grad_norm": 0.1552971601486206,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.3236,
+      "num_input_tokens_seen": 3695480,
+      "step": 90
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.14925938844680786,
+      "learning_rate": 4.912922166582874e-05,
+      "loss": 0.4255,
+      "num_input_tokens_seen": 3734560,
+      "step": 91
+    },
+    {
+      "epoch": 1.6788990825688073,
+      "grad_norm": 0.1332874596118927,
+      "learning_rate": 4.9110093502873476e-05,
+      "loss": 0.3061,
+      "num_input_tokens_seen": 3773112,
+      "step": 92
+    },
+    {
+      "epoch": 1.6972477064220184,
+      "grad_norm": 0.15471243858337402,
+      "learning_rate": 4.909076133021557e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 3813392,
+      "step": 93
+    },
+    {
+      "epoch": 1.7155963302752295,
+      "grad_norm": 0.16010524332523346,
+      "learning_rate": 4.907122531143594e-05,
+      "loss": 0.4179,
+      "num_input_tokens_seen": 3856416,
+      "step": 94
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.13423003256320953,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.3593,
+      "num_input_tokens_seen": 3899472,
+      "step": 95
+    },
+    {
+      "epoch": 1.7522935779816513,
+      "grad_norm": 0.14900773763656616,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.5007,
+      "num_input_tokens_seen": 3962976,
+      "step": 96
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.15728624165058136,
+      "learning_rate": 4.9011395840040144e-05,
+      "loss": 0.3484,
+      "num_input_tokens_seen": 4000696,
+      "step": 97
+    },
+    {
+      "epoch": 1.7889908256880735,
+      "grad_norm": 0.11092367768287659,
+      "learning_rate": 4.8991046107058735e-05,
+      "loss": 0.2889,
+      "num_input_tokens_seen": 4045256,
+      "step": 98
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.1289113610982895,
+      "learning_rate": 4.8970493371704826e-05,
+      "loss": 0.2203,
+      "num_input_tokens_seen": 4076800,
+      "step": 99
+    },
+    {
+      "epoch": 1.8256880733944953,
+      "grad_norm": 0.18886639177799225,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.3966,
+      "num_input_tokens_seen": 4119840,
+      "step": 100
+    },
+    {
+      "epoch": 1.8440366972477065,
+      "grad_norm": 0.1563039869070053,
+      "learning_rate": 4.892877959123097e-05,
+      "loss": 0.4417,
+      "num_input_tokens_seen": 4165848,
+      "step": 101
+    },
+    {
+      "epoch": 1.8623853211009176,
+      "grad_norm": 0.16883380711078644,
+      "learning_rate": 4.890761889907589e-05,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 4202824,
+      "step": 102
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.18241995573043823,
+      "learning_rate": 4.8886255910475054e-05,
+      "loss": 0.3952,
+      "num_input_tokens_seen": 4233888,
+      "step": 103
+    },
+    {
+      "epoch": 1.8990825688073394,
+      "grad_norm": 0.19913265109062195,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.3241,
+      "num_input_tokens_seen": 4267064,
+      "step": 104
+    },
+    {
+      "epoch": 1.9174311926605505,
+      "grad_norm": 0.18295545876026154,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.4239,
+      "num_input_tokens_seen": 4312536,
+      "step": 105
+    },
+    {
+      "epoch": 1.9357798165137616,
+      "grad_norm": 0.16657495498657227,
+      "learning_rate": 4.8820954982195905e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 4356656,
+      "step": 106
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.18504932522773743,
+      "learning_rate": 4.879878463255483e-05,
+      "loss": 0.44,
+      "num_input_tokens_seen": 4400216,
+      "step": 107
+    },
+    {
+      "epoch": 1.9724770642201834,
+      "grad_norm": 0.1923118382692337,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2662,
+      "num_input_tokens_seen": 4436968,
+      "step": 108
+    },
+    {
+      "epoch": 1.9908256880733946,
+      "grad_norm": 0.19636788964271545,
+      "learning_rate": 4.875383999596828e-05,
+      "loss": 0.4211,
+      "num_input_tokens_seen": 4488232,
+      "step": 109
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3168099820613861,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.2499,
+      "num_input_tokens_seen": 4518176,
+      "step": 110
+    },
+    {
+      "epoch": 2.018348623853211,
+      "grad_norm": 0.14410308003425598,
+      "learning_rate": 4.8708091380154984e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 4570896,
+      "step": 111
+    },
+    {
+      "epoch": 2.036697247706422,
+      "grad_norm": 0.17840909957885742,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.2758,
+      "num_input_tokens_seen": 4613576,
+      "step": 112
+    },
+    {
+      "epoch": 2.055045871559633,
+      "grad_norm": 0.178523987531662,
+      "learning_rate": 4.866154033353561e-05,
+      "loss": 0.3361,
+      "num_input_tokens_seen": 4652896,
+      "step": 113
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.17396725714206696,
+      "learning_rate": 4.8637964389982926e-05,
+      "loss": 0.2667,
+      "num_input_tokens_seen": 4694256,
+      "step": 114
+    },
+    {
+      "epoch": 2.091743119266055,
+      "grad_norm": 0.19471587240695953,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.3628,
+      "num_input_tokens_seen": 4747552,
+      "step": 115
+    },
+    {
+      "epoch": 2.1100917431192663,
+      "grad_norm": 0.1722450852394104,
+      "learning_rate": 4.859021265983959e-05,
+      "loss": 0.3599,
+      "num_input_tokens_seen": 4794080,
+      "step": 116
+    },
+    {
+      "epoch": 2.128440366972477,
+      "grad_norm": 0.20137006044387817,
+      "learning_rate": 4.856603727730447e-05,
+      "loss": 0.4262,
+      "num_input_tokens_seen": 4847912,
+      "step": 117
+    },
+    {
+      "epoch": 2.146788990825688,
+      "grad_norm": 0.19395771622657776,
+      "learning_rate": 4.854166248864689e-05,
+      "loss": 0.3118,
+      "num_input_tokens_seen": 4885480,
+      "step": 118
+    },
+    {
+      "epoch": 2.165137614678899,
+      "grad_norm": 0.209548681974411,
+      "learning_rate": 4.85170885001163e-05,
+      "loss": 0.3725,
+      "num_input_tokens_seen": 4921240,
+      "step": 119
+    },
+    {
+      "epoch": 2.18348623853211,
+      "grad_norm": 0.18228279054164886,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.3816,
+      "num_input_tokens_seen": 4960224,
+      "step": 120
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 0.24349354207515717,
+      "learning_rate": 4.846734375685989e-05,
+      "loss": 0.3383,
+      "num_input_tokens_seen": 4990536,
+      "step": 121
+    },
+    {
+      "epoch": 2.220183486238532,
+      "grad_norm": 0.17600344121456146,
+      "learning_rate": 4.844217342305363e-05,
+      "loss": 0.3011,
+      "num_input_tokens_seen": 5044296,
+      "step": 122
+    },
+    {
+      "epoch": 2.238532110091743,
+      "grad_norm": 0.18766675889492035,
+      "learning_rate": 4.8416804731209945e-05,
+      "loss": 0.4458,
+      "num_input_tokens_seen": 5088368,
+      "step": 123
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.17657820880413055,
+      "learning_rate": 4.839123789598829e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 5133472,
+      "step": 124
+    },
+    {
+      "epoch": 2.2752293577981653,
+      "grad_norm": 0.20606014132499695,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.313,
+      "num_input_tokens_seen": 5167768,
+      "step": 125
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.23511061072349548,
+      "learning_rate": 4.8339510662430046e-05,
+      "loss": 0.2963,
+      "num_input_tokens_seen": 5209400,
+      "step": 126
+    },
+    {
+      "epoch": 2.311926605504587,
+      "grad_norm": 0.18234293162822723,
+      "learning_rate": 4.8313350701788054e-05,
+      "loss": 0.2566,
+      "num_input_tokens_seen": 5249360,
+      "step": 127
+    },
+    {
+      "epoch": 2.330275229357798,
+      "grad_norm": 0.2223992496728897,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2833,
+      "num_input_tokens_seen": 5300808,
+      "step": 128
+    },
+    {
+      "epoch": 2.3486238532110093,
+      "grad_norm": 0.23101739585399628,
+      "learning_rate": 4.826043919955062e-05,
+      "loss": 0.3099,
+      "num_input_tokens_seen": 5332960,
+      "step": 129
+    },
+    {
+      "epoch": 2.36697247706422,
+      "grad_norm": 0.26640889048576355,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.3238,
+      "num_input_tokens_seen": 5365008,
+      "step": 130
+    },
+    {
+      "epoch": 2.385321100917431,
+      "grad_norm": 0.2374572902917862,
+      "learning_rate": 4.820674041787017e-05,
+      "loss": 0.3153,
+      "num_input_tokens_seen": 5400184,
+      "step": 131
+    },
+    {
+      "epoch": 2.4036697247706424,
+      "grad_norm": 0.22812288999557495,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.2997,
+      "num_input_tokens_seen": 5440320,
+      "step": 132
+    },
+    {
+      "epoch": 2.4220183486238533,
+      "grad_norm": 0.20079149305820465,
+      "learning_rate": 4.815225617425095e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5480832,
+      "step": 133
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.196709543466568,
+      "learning_rate": 4.81247200794554e-05,
+      "loss": 0.2456,
+      "num_input_tokens_seen": 5526936,
+      "step": 134
+    },
+    {
+      "epoch": 2.458715596330275,
+      "grad_norm": 0.17305873334407806,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.2099,
+      "num_input_tokens_seen": 5566384,
+      "step": 135
+    },
+    {
+      "epoch": 2.477064220183486,
+      "grad_norm": 3.584635019302368,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.3485,
+      "num_input_tokens_seen": 5629896,
+      "step": 136
+    },
+    {
+      "epoch": 2.4954128440366974,
+      "grad_norm": 0.23481500148773193,
+      "learning_rate": 4.80409387040756e-05,
+      "loss": 0.2231,
+      "num_input_tokens_seen": 5674504,
+      "step": 137
+    },
+    {
+      "epoch": 2.5137614678899083,
+      "grad_norm": 0.27899855375289917,
+      "learning_rate": 4.8012621336311016e-05,
+      "loss": 0.4285,
+      "num_input_tokens_seen": 5714000,
+      "step": 138
+    },
+    {
+      "epoch": 2.532110091743119,
+      "grad_norm": 0.24404938519001007,
+      "learning_rate": 4.798410924520223e-05,
+      "loss": 0.3343,
+      "num_input_tokens_seen": 5756856,
+      "step": 139
+    },
+    {
+      "epoch": 2.5504587155963305,
+      "grad_norm": 0.26869162917137146,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 5781192,
+      "step": 140
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 0.2057972550392151,
+      "learning_rate": 4.79265018596281e-05,
+      "loss": 0.2991,
+      "num_input_tokens_seen": 5824024,
+      "step": 141
+    },
+    {
+      "epoch": 2.5871559633027523,
+      "grad_norm": 0.2184937596321106,
+      "learning_rate": 4.789740705261278e-05,
+      "loss": 0.2406,
+      "num_input_tokens_seen": 5862584,
+      "step": 142
+    },
+    {
+      "epoch": 2.6055045871559632,
+      "grad_norm": 0.23603741824626923,
+      "learning_rate": 4.786811849714918e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 5897344,
+      "step": 143
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.22983981668949127,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 5931736,
+      "step": 144
+    },
+    {
+      "epoch": 2.6422018348623855,
+      "grad_norm": 0.2825419306755066,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.3386,
+      "num_input_tokens_seen": 5972784,
+      "step": 145
+    },
+    {
+      "epoch": 2.6605504587155964,
+      "grad_norm": 0.4502134621143341,
+      "learning_rate": 4.777909282653042e-05,
+      "loss": 0.2289,
+      "num_input_tokens_seen": 6018968,
+      "step": 146
+    },
+    {
+      "epoch": 2.6788990825688073,
+      "grad_norm": 0.2428288459777832,
+      "learning_rate": 4.7749031771913584e-05,
+      "loss": 0.4061,
+      "num_input_tokens_seen": 6062520,
+      "step": 147
+    },
+    {
+      "epoch": 2.6972477064220186,
+      "grad_norm": 0.2685629725456238,
+      "learning_rate": 4.771877822433911e-05,
+      "loss": 0.2198,
+      "num_input_tokens_seen": 6087928,
+      "step": 148
+    },
+    {
+      "epoch": 2.7155963302752295,
+      "grad_norm": 0.24021446704864502,
+      "learning_rate": 4.7688332439800096e-05,
+      "loss": 0.34,
+      "num_input_tokens_seen": 6134792,
+      "step": 149
+    },
+    {
+      "epoch": 2.7339449541284404,
+      "grad_norm": 0.2568534314632416,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.3292,
+      "num_input_tokens_seen": 6183296,
+      "step": 150
+    },
+    {
+      "epoch": 2.7522935779816513,
+      "grad_norm": 0.20823974907398224,
+      "learning_rate": 4.762686519193175e-05,
+      "loss": 0.2539,
+      "num_input_tokens_seen": 6225840,
+      "step": 151
+    },
+    {
+      "epoch": 2.770642201834862,
+      "grad_norm": 0.23333317041397095,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.3571,
+      "num_input_tokens_seen": 6274760,
+      "step": 152
+    },
+    {
+      "epoch": 2.7889908256880735,
+      "grad_norm": 0.20232398808002472,
+      "learning_rate": 4.756463210874652e-05,
+      "loss": 0.2783,
+      "num_input_tokens_seen": 6326168,
+      "step": 153
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.3479433059692383,
+      "learning_rate": 4.7533229036136553e-05,
+      "loss": 0.2925,
+      "num_input_tokens_seen": 6360312,
+      "step": 154
+    },
+    {
+      "epoch": 2.8256880733944953,
+      "grad_norm": 0.2659524083137512,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.2606,
+      "num_input_tokens_seen": 6395496,
+      "step": 155
+    },
+    {
+      "epoch": 2.8440366972477067,
+      "grad_norm": 0.24823158979415894,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.3721,
+      "num_input_tokens_seen": 6437064,
+      "step": 156
+    },
+    {
+      "epoch": 2.8623853211009176,
+      "grad_norm": 0.32034072279930115,
+      "learning_rate": 4.743787688770932e-05,
+      "loss": 0.3931,
+      "num_input_tokens_seen": 6477616,
+      "step": 157
+    },
+    {
+      "epoch": 2.8807339449541285,
+      "grad_norm": 0.23295725882053375,
+      "learning_rate": 4.740571275784659e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 6518680,
+      "step": 158
+    },
+    {
+      "epoch": 2.8990825688073394,
+      "grad_norm": 0.2758423984050751,
+      "learning_rate": 4.737335904005063e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 6549768,
+      "step": 159
+    },
+    {
+      "epoch": 2.9174311926605503,
+      "grad_norm": 0.26690953969955444,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 6581000,
+      "step": 160
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 0.26657482981681824,
+      "learning_rate": 4.730808393731639e-05,
+      "loss": 0.2597,
+      "num_input_tokens_seen": 6612632,
+      "step": 161
+    },
+    {
+      "epoch": 2.9541284403669725,
+      "grad_norm": 0.22647295892238617,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3335,
+      "num_input_tokens_seen": 6654288,
+      "step": 162
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1080,
+  "num_input_tokens_seen": 6654288,
+  "num_train_epochs": 20,
+  "save_steps": 54,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.613668673991475e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-216/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-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 0.12.0

checkpoint-216/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-216/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-216/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa11018273da1d1d78a5fa4d447a2f826da278b44ddbc4f1c2ec33eff71f373
+size 14512

checkpoint-216/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-216/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 15000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-216/trainer_state.json

@@ -0,0 +1,1761 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9357798165137616,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.04378490149974823,
+      "learning_rate": 4.999989423013716e-05,
+      "loss": 0.6713,
+      "num_input_tokens_seen": 44136,
+      "step": 1
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.040646992623806,
+      "learning_rate": 4.999957692144361e-05,
+      "loss": 0.533,
+      "num_input_tokens_seen": 83096,
+      "step": 2
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.04658753052353859,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.6048,
+      "num_input_tokens_seen": 122112,
+      "step": 3
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.04322144016623497,
+      "learning_rate": 4.999830770009406e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 163064,
+      "step": 4
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.06536195427179337,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.6607,
+      "num_input_tokens_seen": 203808,
+      "step": 5
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.059904925525188446,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.5802,
+      "num_input_tokens_seen": 241824,
+      "step": 6
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.19818365573883057,
+      "learning_rate": 4.999481745213471e-05,
+      "loss": 0.5148,
+      "num_input_tokens_seen": 287608,
+      "step": 7
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.05985472351312637,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5714,
+      "num_input_tokens_seen": 325320,
+      "step": 8
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.061375778168439865,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.6812,
+      "num_input_tokens_seen": 369848,
+      "step": 9
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.06196414306759834,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.5358,
+      "num_input_tokens_seen": 415104,
+      "step": 10
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.07861393690109253,
+      "learning_rate": 4.9987202929487275e-05,
+      "loss": 0.6527,
+      "num_input_tokens_seen": 467224,
+      "step": 11
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.05596446990966797,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.5354,
+      "num_input_tokens_seen": 502824,
+      "step": 12
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.05289844051003456,
+      "learning_rate": 4.998212701060612e-05,
+      "loss": 0.5263,
+      "num_input_tokens_seen": 544744,
+      "step": 13
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.04996591433882713,
+      "learning_rate": 4.997927195724303e-05,
+      "loss": 0.5536,
+      "num_input_tokens_seen": 591136,
+      "step": 14
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.05822828412055969,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.6106,
+      "num_input_tokens_seen": 629664,
+      "step": 15
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.06353770196437836,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5129,
+      "num_input_tokens_seen": 663392,
+      "step": 16
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.07256966829299927,
+      "learning_rate": 4.996943871672807e-05,
+      "loss": 0.6377,
+      "num_input_tokens_seen": 698360,
+      "step": 17
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.055458713322877884,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 737520,
+      "step": 18
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07792335003614426,
+      "learning_rate": 4.9961826771182784e-05,
+      "loss": 0.6086,
+      "num_input_tokens_seen": 768056,
+      "step": 19
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.06627275049686432,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.4591,
+      "num_input_tokens_seen": 806256,
+      "step": 20
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.05830290913581848,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.3731,
+      "num_input_tokens_seen": 842336,
+      "step": 21
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07277437299489975,
+      "learning_rate": 4.9948824819150185e-05,
+      "loss": 0.6243,
+      "num_input_tokens_seen": 876672,
+      "step": 22
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.07477546483278275,
+      "learning_rate": 4.994406857105136e-05,
+      "loss": 0.5788,
+      "num_input_tokens_seen": 915192,
+      "step": 23
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.06912907212972641,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4753,
+      "num_input_tokens_seen": 951904,
+      "step": 24
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.0655476376414299,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.4518,
+      "num_input_tokens_seen": 1001816,
+      "step": 25
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.06466512382030487,
+      "learning_rate": 4.992853359792444e-05,
+      "loss": 0.5638,
+      "num_input_tokens_seen": 1053064,
+      "step": 26
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0645688995718956,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4644,
+      "num_input_tokens_seen": 1086688,
+      "step": 27
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07181251049041748,
+      "learning_rate": 4.9917122201112656e-05,
+      "loss": 0.6191,
+      "num_input_tokens_seen": 1134824,
+      "step": 28
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.07322589308023453,
+      "learning_rate": 4.9911100220449293e-05,
+      "loss": 0.6752,
+      "num_input_tokens_seen": 1172072,
+      "step": 29
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.06396070122718811,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.3587,
+      "num_input_tokens_seen": 1211096,
+      "step": 30
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.07803395390510559,
+      "learning_rate": 4.989842394938482e-05,
+      "loss": 0.459,
+      "num_input_tokens_seen": 1259456,
+      "step": 31
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.05974648892879486,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 1306944,
+      "step": 32
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.09784268587827682,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.539,
+      "num_input_tokens_seen": 1353744,
+      "step": 33
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.09906516224145889,
+      "learning_rate": 4.987782958627508e-05,
+      "loss": 0.5453,
+      "num_input_tokens_seen": 1394736,
+      "step": 34
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.08984062820672989,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.468,
+      "num_input_tokens_seen": 1442048,
+      "step": 35
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08672655373811722,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.4078,
+      "num_input_tokens_seen": 1478440,
+      "step": 36
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.1327345073223114,
+      "learning_rate": 4.9855340680123905e-05,
+      "loss": 0.5299,
+      "num_input_tokens_seen": 1525992,
+      "step": 37
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.09178602695465088,
+      "learning_rate": 4.9847423660363e-05,
+      "loss": 0.439,
+      "num_input_tokens_seen": 1555608,
+      "step": 38
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.09418320655822754,
+      "learning_rate": 4.983929639191469e-05,
+      "loss": 0.5337,
+      "num_input_tokens_seen": 1597392,
+      "step": 39
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.08294719457626343,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.4536,
+      "num_input_tokens_seen": 1649656,
+      "step": 40
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.09774205833673477,
+      "learning_rate": 4.982241138581273e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 1695952,
+      "step": 41
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.09319107979536057,
+      "learning_rate": 4.9813653791033057e-05,
+      "loss": 0.4279,
+      "num_input_tokens_seen": 1737224,
+      "step": 42
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.09561405330896378,
+      "learning_rate": 4.980468623331273e-05,
+      "loss": 0.5121,
+      "num_input_tokens_seen": 1772320,
+      "step": 43
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08274025470018387,
+      "learning_rate": 4.979550878853154e-05,
+      "loss": 0.54,
+      "num_input_tokens_seen": 1823888,
+      "step": 44
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.08728913217782974,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1872488,
+      "step": 45
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.0787016749382019,
+      "learning_rate": 4.9776524550184965e-05,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 1924744,
+      "step": 46
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.10952188074588776,
+      "learning_rate": 4.97667179172564e-05,
+      "loss": 0.4784,
+      "num_input_tokens_seen": 1959936,
+      "step": 47
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.08525826781988144,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.3586,
+      "num_input_tokens_seen": 2003896,
+      "step": 48
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10409987717866898,
+      "learning_rate": 4.9746476038786496e-05,
+      "loss": 0.4451,
+      "num_input_tokens_seen": 2047632,
+      "step": 49
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.0782993957400322,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.3591,
+      "num_input_tokens_seen": 2096928,
+      "step": 50
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.09829951077699661,
+      "learning_rate": 4.9725396584047925e-05,
+      "loss": 0.3415,
+      "num_input_tokens_seen": 2129536,
+      "step": 51
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.10606162995100021,
+      "learning_rate": 4.971454298742779e-05,
+      "loss": 0.3758,
+      "num_input_tokens_seen": 2169144,
+      "step": 52
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.09280356764793396,
+      "learning_rate": 4.97034802665019e-05,
+      "loss": 0.485,
+      "num_input_tokens_seen": 2207720,
+      "step": 53
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11888203024864197,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.3469,
+      "num_input_tokens_seen": 2236392,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13222463428974152,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.4284,
+      "num_input_tokens_seen": 2259088,
+      "step": 55
+    },
+    {
+      "epoch": 1.018348623853211,
+      "grad_norm": 0.10572745651006699,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4186,
+      "num_input_tokens_seen": 2298496,
+      "step": 56
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11462350189685822,
+      "learning_rate": 4.965714003843079e-05,
+      "loss": 0.4696,
+      "num_input_tokens_seen": 2333016,
+      "step": 57
+    },
+    {
+      "epoch": 1.0550458715596331,
+      "grad_norm": 0.11215240508317947,
+      "learning_rate": 4.9645033135461494e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 2367992,
+      "step": 58
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.0973561555147171,
+      "learning_rate": 4.963271769635024e-05,
+      "loss": 0.3588,
+      "num_input_tokens_seen": 2415328,
+      "step": 59
+    },
+    {
+      "epoch": 1.091743119266055,
+      "grad_norm": 0.10240709036588669,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.5532,
+      "num_input_tokens_seen": 2454792,
+      "step": 60
+    },
+    {
+      "epoch": 1.110091743119266,
+      "grad_norm": 0.0959337130188942,
+      "learning_rate": 4.9607461628298244e-05,
+      "loss": 0.331,
+      "num_input_tokens_seen": 2503072,
+      "step": 61
+    },
+    {
+      "epoch": 1.1284403669724772,
+      "grad_norm": 0.10228750854730606,
+      "learning_rate": 4.9594521213063974e-05,
+      "loss": 0.3728,
+      "num_input_tokens_seen": 2546960,
+      "step": 62
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.09403488785028458,
+      "learning_rate": 4.958137268909887e-05,
+      "loss": 0.4695,
+      "num_input_tokens_seen": 2595432,
+      "step": 63
+    },
+    {
+      "epoch": 1.165137614678899,
+      "grad_norm": 0.11396344751119614,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 2633912,
+      "step": 64
+    },
+    {
+      "epoch": 1.18348623853211,
+      "grad_norm": 0.09487481415271759,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.3498,
+      "num_input_tokens_seen": 2680792,
+      "step": 65
+    },
+    {
+      "epoch": 1.2018348623853212,
+      "grad_norm": 0.1249895691871643,
+      "learning_rate": 4.9540679586191605e-05,
+      "loss": 0.4053,
+      "num_input_tokens_seen": 2716584,
+      "step": 66
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.12268221378326416,
+      "learning_rate": 4.952669975747232e-05,
+      "loss": 0.4189,
+      "num_input_tokens_seen": 2757088,
+      "step": 67
+    },
+    {
+      "epoch": 1.238532110091743,
+      "grad_norm": 0.12126032263040543,
+      "learning_rate": 4.951251239389948e-05,
+      "loss": 0.4994,
+      "num_input_tokens_seen": 2795664,
+      "step": 68
+    },
+    {
+      "epoch": 1.2568807339449541,
+      "grad_norm": 0.1069057360291481,
+      "learning_rate": 4.949811761552074e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 2840936,
+      "step": 69
+    },
+    {
+      "epoch": 1.2752293577981653,
+      "grad_norm": 0.10893313586711884,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.4366,
+      "num_input_tokens_seen": 2886768,
+      "step": 70
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.12898756563663483,
+      "learning_rate": 4.9468706303310355e-05,
+      "loss": 0.3916,
+      "num_input_tokens_seen": 2919328,
+      "step": 71
+    },
+    {
+      "epoch": 1.311926605504587,
+      "grad_norm": 0.12405356019735336,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3249,
+      "num_input_tokens_seen": 2966744,
+      "step": 72
+    },
+    {
+      "epoch": 1.3302752293577982,
+      "grad_norm": 0.13137595355510712,
+      "learning_rate": 4.943846681630479e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3007248,
+      "step": 73
+    },
+    {
+      "epoch": 1.3486238532110093,
+      "grad_norm": 0.13920250535011292,
+      "learning_rate": 4.942303682600178e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3050960,
+      "step": 74
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.1255589872598648,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3773,
+      "num_input_tokens_seen": 3088592,
+      "step": 75
+    },
+    {
+      "epoch": 1.385321100917431,
+      "grad_norm": 0.10222747176885605,
+      "learning_rate": 4.939155700460536e-05,
+      "loss": 0.4,
+      "num_input_tokens_seen": 3153520,
+      "step": 76
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.13205283880233765,
+      "learning_rate": 4.9375507439881266e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 3199272,
+      "step": 77
+    },
+    {
+      "epoch": 1.4220183486238533,
+      "grad_norm": 0.11005694419145584,
+      "learning_rate": 4.9359251619630886e-05,
+      "loss": 0.3881,
+      "num_input_tokens_seen": 3247128,
+      "step": 78
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.14799247682094574,
+      "learning_rate": 4.9342789681404275e-05,
+      "loss": 0.3972,
+      "num_input_tokens_seen": 3294192,
+      "step": 79
+    },
+    {
+      "epoch": 1.4587155963302751,
+      "grad_norm": 0.1279418021440506,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.3438,
+      "num_input_tokens_seen": 3329736,
+      "step": 80
+    },
+    {
+      "epoch": 1.4770642201834863,
+      "grad_norm": 0.11036807298660278,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3189,
+      "num_input_tokens_seen": 3371376,
+      "step": 81
+    },
+    {
+      "epoch": 1.4954128440366974,
+      "grad_norm": 0.11855707317590714,
+      "learning_rate": 4.9292168560522014e-05,
+      "loss": 0.401,
+      "num_input_tokens_seen": 3412368,
+      "step": 82
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.13195356726646423,
+      "learning_rate": 4.9274883560755156e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 3455000,
+      "step": 83
+    },
+    {
+      "epoch": 1.5321100917431192,
+      "grad_norm": 0.1462787538766861,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.3768,
+      "num_input_tokens_seen": 3488960,
+      "step": 84
+    },
+    {
+      "epoch": 1.5504587155963303,
+      "grad_norm": 0.13765974342823029,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 3521320,
+      "step": 85
+    },
+    {
+      "epoch": 1.5688073394495414,
+      "grad_norm": 0.15276113152503967,
+      "learning_rate": 4.9221796730647516e-05,
+      "loss": 0.3638,
+      "num_input_tokens_seen": 3559464,
+      "step": 86
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.1441674381494522,
+      "learning_rate": 4.92036910094527e-05,
+      "loss": 0.3919,
+      "num_input_tokens_seen": 3598080,
+      "step": 87
+    },
+    {
+      "epoch": 1.6055045871559632,
+      "grad_norm": 0.1780252456665039,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.3626,
+      "num_input_tokens_seen": 3630064,
+      "step": 88
+    },
+    {
+      "epoch": 1.6238532110091743,
+      "grad_norm": 0.16947726905345917,
+      "learning_rate": 4.916686531694035e-05,
+      "loss": 0.3439,
+      "num_input_tokens_seen": 3661408,
+      "step": 89
+    },
+    {
+      "epoch": 1.6422018348623855,
+      "grad_norm": 0.1552971601486206,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.3236,
+      "num_input_tokens_seen": 3695480,
+      "step": 90
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.14925938844680786,
+      "learning_rate": 4.912922166582874e-05,
+      "loss": 0.4255,
+      "num_input_tokens_seen": 3734560,
+      "step": 91
+    },
+    {
+      "epoch": 1.6788990825688073,
+      "grad_norm": 0.1332874596118927,
+      "learning_rate": 4.9110093502873476e-05,
+      "loss": 0.3061,
+      "num_input_tokens_seen": 3773112,
+      "step": 92
+    },
+    {
+      "epoch": 1.6972477064220184,
+      "grad_norm": 0.15471243858337402,
+      "learning_rate": 4.909076133021557e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 3813392,
+      "step": 93
+    },
+    {
+      "epoch": 1.7155963302752295,
+      "grad_norm": 0.16010524332523346,
+      "learning_rate": 4.907122531143594e-05,
+      "loss": 0.4179,
+      "num_input_tokens_seen": 3856416,
+      "step": 94
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.13423003256320953,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.3593,
+      "num_input_tokens_seen": 3899472,
+      "step": 95
+    },
+    {
+      "epoch": 1.7522935779816513,
+      "grad_norm": 0.14900773763656616,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.5007,
+      "num_input_tokens_seen": 3962976,
+      "step": 96
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.15728624165058136,
+      "learning_rate": 4.9011395840040144e-05,
+      "loss": 0.3484,
+      "num_input_tokens_seen": 4000696,
+      "step": 97
+    },
+    {
+      "epoch": 1.7889908256880735,
+      "grad_norm": 0.11092367768287659,
+      "learning_rate": 4.8991046107058735e-05,
+      "loss": 0.2889,
+      "num_input_tokens_seen": 4045256,
+      "step": 98
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.1289113610982895,
+      "learning_rate": 4.8970493371704826e-05,
+      "loss": 0.2203,
+      "num_input_tokens_seen": 4076800,
+      "step": 99
+    },
+    {
+      "epoch": 1.8256880733944953,
+      "grad_norm": 0.18886639177799225,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.3966,
+      "num_input_tokens_seen": 4119840,
+      "step": 100
+    },
+    {
+      "epoch": 1.8440366972477065,
+      "grad_norm": 0.1563039869070053,
+      "learning_rate": 4.892877959123097e-05,
+      "loss": 0.4417,
+      "num_input_tokens_seen": 4165848,
+      "step": 101
+    },
+    {
+      "epoch": 1.8623853211009176,
+      "grad_norm": 0.16883380711078644,
+      "learning_rate": 4.890761889907589e-05,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 4202824,
+      "step": 102
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.18241995573043823,
+      "learning_rate": 4.8886255910475054e-05,
+      "loss": 0.3952,
+      "num_input_tokens_seen": 4233888,
+      "step": 103
+    },
+    {
+      "epoch": 1.8990825688073394,
+      "grad_norm": 0.19913265109062195,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.3241,
+      "num_input_tokens_seen": 4267064,
+      "step": 104
+    },
+    {
+      "epoch": 1.9174311926605505,
+      "grad_norm": 0.18295545876026154,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.4239,
+      "num_input_tokens_seen": 4312536,
+      "step": 105
+    },
+    {
+      "epoch": 1.9357798165137616,
+      "grad_norm": 0.16657495498657227,
+      "learning_rate": 4.8820954982195905e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 4356656,
+      "step": 106
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.18504932522773743,
+      "learning_rate": 4.879878463255483e-05,
+      "loss": 0.44,
+      "num_input_tokens_seen": 4400216,
+      "step": 107
+    },
+    {
+      "epoch": 1.9724770642201834,
+      "grad_norm": 0.1923118382692337,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2662,
+      "num_input_tokens_seen": 4436968,
+      "step": 108
+    },
+    {
+      "epoch": 1.9908256880733946,
+      "grad_norm": 0.19636788964271545,
+      "learning_rate": 4.875383999596828e-05,
+      "loss": 0.4211,
+      "num_input_tokens_seen": 4488232,
+      "step": 109
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3168099820613861,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.2499,
+      "num_input_tokens_seen": 4518176,
+      "step": 110
+    },
+    {
+      "epoch": 2.018348623853211,
+      "grad_norm": 0.14410308003425598,
+      "learning_rate": 4.8708091380154984e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 4570896,
+      "step": 111
+    },
+    {
+      "epoch": 2.036697247706422,
+      "grad_norm": 0.17840909957885742,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.2758,
+      "num_input_tokens_seen": 4613576,
+      "step": 112
+    },
+    {
+      "epoch": 2.055045871559633,
+      "grad_norm": 0.178523987531662,
+      "learning_rate": 4.866154033353561e-05,
+      "loss": 0.3361,
+      "num_input_tokens_seen": 4652896,
+      "step": 113
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.17396725714206696,
+      "learning_rate": 4.8637964389982926e-05,
+      "loss": 0.2667,
+      "num_input_tokens_seen": 4694256,
+      "step": 114
+    },
+    {
+      "epoch": 2.091743119266055,
+      "grad_norm": 0.19471587240695953,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.3628,
+      "num_input_tokens_seen": 4747552,
+      "step": 115
+    },
+    {
+      "epoch": 2.1100917431192663,
+      "grad_norm": 0.1722450852394104,
+      "learning_rate": 4.859021265983959e-05,
+      "loss": 0.3599,
+      "num_input_tokens_seen": 4794080,
+      "step": 116
+    },
+    {
+      "epoch": 2.128440366972477,
+      "grad_norm": 0.20137006044387817,
+      "learning_rate": 4.856603727730447e-05,
+      "loss": 0.4262,
+      "num_input_tokens_seen": 4847912,
+      "step": 117
+    },
+    {
+      "epoch": 2.146788990825688,
+      "grad_norm": 0.19395771622657776,
+      "learning_rate": 4.854166248864689e-05,
+      "loss": 0.3118,
+      "num_input_tokens_seen": 4885480,
+      "step": 118
+    },
+    {
+      "epoch": 2.165137614678899,
+      "grad_norm": 0.209548681974411,
+      "learning_rate": 4.85170885001163e-05,
+      "loss": 0.3725,
+      "num_input_tokens_seen": 4921240,
+      "step": 119
+    },
+    {
+      "epoch": 2.18348623853211,
+      "grad_norm": 0.18228279054164886,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.3816,
+      "num_input_tokens_seen": 4960224,
+      "step": 120
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 0.24349354207515717,
+      "learning_rate": 4.846734375685989e-05,
+      "loss": 0.3383,
+      "num_input_tokens_seen": 4990536,
+      "step": 121
+    },
+    {
+      "epoch": 2.220183486238532,
+      "grad_norm": 0.17600344121456146,
+      "learning_rate": 4.844217342305363e-05,
+      "loss": 0.3011,
+      "num_input_tokens_seen": 5044296,
+      "step": 122
+    },
+    {
+      "epoch": 2.238532110091743,
+      "grad_norm": 0.18766675889492035,
+      "learning_rate": 4.8416804731209945e-05,
+      "loss": 0.4458,
+      "num_input_tokens_seen": 5088368,
+      "step": 123
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.17657820880413055,
+      "learning_rate": 4.839123789598829e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 5133472,
+      "step": 124
+    },
+    {
+      "epoch": 2.2752293577981653,
+      "grad_norm": 0.20606014132499695,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.313,
+      "num_input_tokens_seen": 5167768,
+      "step": 125
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.23511061072349548,
+      "learning_rate": 4.8339510662430046e-05,
+      "loss": 0.2963,
+      "num_input_tokens_seen": 5209400,
+      "step": 126
+    },
+    {
+      "epoch": 2.311926605504587,
+      "grad_norm": 0.18234293162822723,
+      "learning_rate": 4.8313350701788054e-05,
+      "loss": 0.2566,
+      "num_input_tokens_seen": 5249360,
+      "step": 127
+    },
+    {
+      "epoch": 2.330275229357798,
+      "grad_norm": 0.2223992496728897,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2833,
+      "num_input_tokens_seen": 5300808,
+      "step": 128
+    },
+    {
+      "epoch": 2.3486238532110093,
+      "grad_norm": 0.23101739585399628,
+      "learning_rate": 4.826043919955062e-05,
+      "loss": 0.3099,
+      "num_input_tokens_seen": 5332960,
+      "step": 129
+    },
+    {
+      "epoch": 2.36697247706422,
+      "grad_norm": 0.26640889048576355,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.3238,
+      "num_input_tokens_seen": 5365008,
+      "step": 130
+    },
+    {
+      "epoch": 2.385321100917431,
+      "grad_norm": 0.2374572902917862,
+      "learning_rate": 4.820674041787017e-05,
+      "loss": 0.3153,
+      "num_input_tokens_seen": 5400184,
+      "step": 131
+    },
+    {
+      "epoch": 2.4036697247706424,
+      "grad_norm": 0.22812288999557495,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.2997,
+      "num_input_tokens_seen": 5440320,
+      "step": 132
+    },
+    {
+      "epoch": 2.4220183486238533,
+      "grad_norm": 0.20079149305820465,
+      "learning_rate": 4.815225617425095e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5480832,
+      "step": 133
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.196709543466568,
+      "learning_rate": 4.81247200794554e-05,
+      "loss": 0.2456,
+      "num_input_tokens_seen": 5526936,
+      "step": 134
+    },
+    {
+      "epoch": 2.458715596330275,
+      "grad_norm": 0.17305873334407806,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.2099,
+      "num_input_tokens_seen": 5566384,
+      "step": 135
+    },
+    {
+      "epoch": 2.477064220183486,
+      "grad_norm": 3.584635019302368,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.3485,
+      "num_input_tokens_seen": 5629896,
+      "step": 136
+    },
+    {
+      "epoch": 2.4954128440366974,
+      "grad_norm": 0.23481500148773193,
+      "learning_rate": 4.80409387040756e-05,
+      "loss": 0.2231,
+      "num_input_tokens_seen": 5674504,
+      "step": 137
+    },
+    {
+      "epoch": 2.5137614678899083,
+      "grad_norm": 0.27899855375289917,
+      "learning_rate": 4.8012621336311016e-05,
+      "loss": 0.4285,
+      "num_input_tokens_seen": 5714000,
+      "step": 138
+    },
+    {
+      "epoch": 2.532110091743119,
+      "grad_norm": 0.24404938519001007,
+      "learning_rate": 4.798410924520223e-05,
+      "loss": 0.3343,
+      "num_input_tokens_seen": 5756856,
+      "step": 139
+    },
+    {
+      "epoch": 2.5504587155963305,
+      "grad_norm": 0.26869162917137146,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 5781192,
+      "step": 140
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 0.2057972550392151,
+      "learning_rate": 4.79265018596281e-05,
+      "loss": 0.2991,
+      "num_input_tokens_seen": 5824024,
+      "step": 141
+    },
+    {
+      "epoch": 2.5871559633027523,
+      "grad_norm": 0.2184937596321106,
+      "learning_rate": 4.789740705261278e-05,
+      "loss": 0.2406,
+      "num_input_tokens_seen": 5862584,
+      "step": 142
+    },
+    {
+      "epoch": 2.6055045871559632,
+      "grad_norm": 0.23603741824626923,
+      "learning_rate": 4.786811849714918e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 5897344,
+      "step": 143
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.22983981668949127,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 5931736,
+      "step": 144
+    },
+    {
+      "epoch": 2.6422018348623855,
+      "grad_norm": 0.2825419306755066,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.3386,
+      "num_input_tokens_seen": 5972784,
+      "step": 145
+    },
+    {
+      "epoch": 2.6605504587155964,
+      "grad_norm": 0.4502134621143341,
+      "learning_rate": 4.777909282653042e-05,
+      "loss": 0.2289,
+      "num_input_tokens_seen": 6018968,
+      "step": 146
+    },
+    {
+      "epoch": 2.6788990825688073,
+      "grad_norm": 0.2428288459777832,
+      "learning_rate": 4.7749031771913584e-05,
+      "loss": 0.4061,
+      "num_input_tokens_seen": 6062520,
+      "step": 147
+    },
+    {
+      "epoch": 2.6972477064220186,
+      "grad_norm": 0.2685629725456238,
+      "learning_rate": 4.771877822433911e-05,
+      "loss": 0.2198,
+      "num_input_tokens_seen": 6087928,
+      "step": 148
+    },
+    {
+      "epoch": 2.7155963302752295,
+      "grad_norm": 0.24021446704864502,
+      "learning_rate": 4.7688332439800096e-05,
+      "loss": 0.34,
+      "num_input_tokens_seen": 6134792,
+      "step": 149
+    },
+    {
+      "epoch": 2.7339449541284404,
+      "grad_norm": 0.2568534314632416,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.3292,
+      "num_input_tokens_seen": 6183296,
+      "step": 150
+    },
+    {
+      "epoch": 2.7522935779816513,
+      "grad_norm": 0.20823974907398224,
+      "learning_rate": 4.762686519193175e-05,
+      "loss": 0.2539,
+      "num_input_tokens_seen": 6225840,
+      "step": 151
+    },
+    {
+      "epoch": 2.770642201834862,
+      "grad_norm": 0.23333317041397095,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.3571,
+      "num_input_tokens_seen": 6274760,
+      "step": 152
+    },
+    {
+      "epoch": 2.7889908256880735,
+      "grad_norm": 0.20232398808002472,
+      "learning_rate": 4.756463210874652e-05,
+      "loss": 0.2783,
+      "num_input_tokens_seen": 6326168,
+      "step": 153
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.3479433059692383,
+      "learning_rate": 4.7533229036136553e-05,
+      "loss": 0.2925,
+      "num_input_tokens_seen": 6360312,
+      "step": 154
+    },
+    {
+      "epoch": 2.8256880733944953,
+      "grad_norm": 0.2659524083137512,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.2606,
+      "num_input_tokens_seen": 6395496,
+      "step": 155
+    },
+    {
+      "epoch": 2.8440366972477067,
+      "grad_norm": 0.24823158979415894,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.3721,
+      "num_input_tokens_seen": 6437064,
+      "step": 156
+    },
+    {
+      "epoch": 2.8623853211009176,
+      "grad_norm": 0.32034072279930115,
+      "learning_rate": 4.743787688770932e-05,
+      "loss": 0.3931,
+      "num_input_tokens_seen": 6477616,
+      "step": 157
+    },
+    {
+      "epoch": 2.8807339449541285,
+      "grad_norm": 0.23295725882053375,
+      "learning_rate": 4.740571275784659e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 6518680,
+      "step": 158
+    },
+    {
+      "epoch": 2.8990825688073394,
+      "grad_norm": 0.2758423984050751,
+      "learning_rate": 4.737335904005063e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 6549768,
+      "step": 159
+    },
+    {
+      "epoch": 2.9174311926605503,
+      "grad_norm": 0.26690953969955444,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 6581000,
+      "step": 160
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 0.26657482981681824,
+      "learning_rate": 4.730808393731639e-05,
+      "loss": 0.2597,
+      "num_input_tokens_seen": 6612632,
+      "step": 161
+    },
+    {
+      "epoch": 2.9541284403669725,
+      "grad_norm": 0.22647295892238617,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3335,
+      "num_input_tokens_seen": 6654288,
+      "step": 162
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "grad_norm": 0.2863366901874542,
+      "learning_rate": 4.72420537888263e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 6707208,
+      "step": 163
+    },
+    {
+      "epoch": 2.9908256880733948,
+      "grad_norm": 0.2606408894062042,
+      "learning_rate": 4.7208756269825104e-05,
+      "loss": 0.3477,
+      "num_input_tokens_seen": 6748448,
+      "step": 164
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.440924733877182,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.3214,
+      "num_input_tokens_seen": 6777264,
+      "step": 165
+    },
+    {
+      "epoch": 3.018348623853211,
+      "grad_norm": 0.27583903074264526,
+      "learning_rate": 4.714159775105765e-05,
+      "loss": 0.2681,
+      "num_input_tokens_seen": 6809456,
+      "step": 166
+    },
+    {
+      "epoch": 3.036697247706422,
+      "grad_norm": 0.2995987832546234,
+      "learning_rate": 4.7107737319559176e-05,
+      "loss": 0.2633,
+      "num_input_tokens_seen": 6845768,
+      "step": 167
+    },
+    {
+      "epoch": 3.055045871559633,
+      "grad_norm": 0.23999951779842377,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.1961,
+      "num_input_tokens_seen": 6893056,
+      "step": 168
+    },
+    {
+      "epoch": 3.073394495412844,
+      "grad_norm": 0.23356525599956512,
+      "learning_rate": 4.703945554489558e-05,
+      "loss": 0.2836,
+      "num_input_tokens_seen": 6932480,
+      "step": 169
+    },
+    {
+      "epoch": 3.091743119266055,
+      "grad_norm": 0.29919493198394775,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.2838,
+      "num_input_tokens_seen": 6975992,
+      "step": 170
+    },
+    {
+      "epoch": 3.1100917431192663,
+      "grad_norm": 0.3350690007209778,
+      "learning_rate": 4.697042781654913e-05,
+      "loss": 0.3489,
+      "num_input_tokens_seen": 7021840,
+      "step": 171
+    },
+    {
+      "epoch": 3.128440366972477,
+      "grad_norm": 0.2837466895580292,
+      "learning_rate": 4.693563494886455e-05,
+      "loss": 0.3797,
+      "num_input_tokens_seen": 7065192,
+      "step": 172
+    },
+    {
+      "epoch": 3.146788990825688,
+      "grad_norm": 0.24601787328720093,
+      "learning_rate": 4.6900656470851964e-05,
+      "loss": 0.2046,
+      "num_input_tokens_seen": 7114544,
+      "step": 173
+    },
+    {
+      "epoch": 3.165137614678899,
+      "grad_norm": 0.32290250062942505,
+      "learning_rate": 4.6865492678484895e-05,
+      "loss": 0.2596,
+      "num_input_tokens_seen": 7152736,
+      "step": 174
+    },
+    {
+      "epoch": 3.18348623853211,
+      "grad_norm": 0.33591920137405396,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 7207464,
+      "step": 175
+    },
+    {
+      "epoch": 3.2018348623853212,
+      "grad_norm": 0.25471043586730957,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.2096,
+      "num_input_tokens_seen": 7238640,
+      "step": 176
+    },
+    {
+      "epoch": 3.220183486238532,
+      "grad_norm": 0.31238994002342224,
+      "learning_rate": 4.6758892398497494e-05,
+      "loss": 0.2226,
+      "num_input_tokens_seen": 7279112,
+      "step": 177
+    },
+    {
+      "epoch": 3.238532110091743,
+      "grad_norm": 0.35679712891578674,
+      "learning_rate": 4.672299033977076e-05,
+      "loss": 0.2403,
+      "num_input_tokens_seen": 7311632,
+      "step": 178
+    },
+    {
+      "epoch": 3.2568807339449544,
+      "grad_norm": 0.326914519071579,
+      "learning_rate": 4.6686904470027316e-05,
+      "loss": 0.2156,
+      "num_input_tokens_seen": 7344864,
+      "step": 179
+    },
+    {
+      "epoch": 3.2752293577981653,
+      "grad_norm": 0.3293381929397583,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.238,
+      "num_input_tokens_seen": 7389944,
+      "step": 180
+    },
+    {
+      "epoch": 3.293577981651376,
+      "grad_norm": 0.3313307762145996,
+      "learning_rate": 4.661418252041827e-05,
+      "loss": 0.2251,
+      "num_input_tokens_seen": 7423672,
+      "step": 181
+    },
+    {
+      "epoch": 3.311926605504587,
+      "grad_norm": 0.3328595459461212,
+      "learning_rate": 4.657754705589591e-05,
+      "loss": 0.2922,
+      "num_input_tokens_seen": 7459576,
+      "step": 182
+    },
+    {
+      "epoch": 3.330275229357798,
+      "grad_norm": 0.2721710801124573,
+      "learning_rate": 4.6540729011038146e-05,
+      "loss": 0.2698,
+      "num_input_tokens_seen": 7511736,
+      "step": 183
+    },
+    {
+      "epoch": 3.3486238532110093,
+      "grad_norm": 0.2488890290260315,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.173,
+      "num_input_tokens_seen": 7558552,
+      "step": 184
+    },
+    {
+      "epoch": 3.36697247706422,
+      "grad_norm": 0.3800615668296814,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.32,
+      "num_input_tokens_seen": 7599040,
+      "step": 185
+    },
+    {
+      "epoch": 3.385321100917431,
+      "grad_norm": 0.3377014100551605,
+      "learning_rate": 4.642918251755281e-05,
+      "loss": 0.3058,
+      "num_input_tokens_seen": 7653264,
+      "step": 186
+    },
+    {
+      "epoch": 3.4036697247706424,
+      "grad_norm": 0.25239789485931396,
+      "learning_rate": 4.639163728215463e-05,
+      "loss": 0.1896,
+      "num_input_tokens_seen": 7694272,
+      "step": 187
+    },
+    {
+      "epoch": 3.4220183486238533,
+      "grad_norm": 0.34607502818107605,
+      "learning_rate": 4.6353911039513145e-05,
+      "loss": 0.2933,
+      "num_input_tokens_seen": 7730848,
+      "step": 188
+    },
+    {
+      "epoch": 3.4403669724770642,
+      "grad_norm": 0.30653324723243713,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.2625,
+      "num_input_tokens_seen": 7781200,
+      "step": 189
+    },
+    {
+      "epoch": 3.458715596330275,
+      "grad_norm": 0.2943236231803894,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.3372,
+      "num_input_tokens_seen": 7825032,
+      "step": 190
+    },
+    {
+      "epoch": 3.477064220183486,
+      "grad_norm": 0.30080685019493103,
+      "learning_rate": 4.623964946801027e-05,
+      "loss": 0.2229,
+      "num_input_tokens_seen": 7855840,
+      "step": 191
+    },
+    {
+      "epoch": 3.4954128440366974,
+      "grad_norm": 0.3511403799057007,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3967,
+      "num_input_tokens_seen": 7905928,
+      "step": 192
+    },
+    {
+      "epoch": 3.5137614678899083,
+      "grad_norm": 0.273583322763443,
+      "learning_rate": 4.61625759439494e-05,
+      "loss": 0.2254,
+      "num_input_tokens_seen": 7955992,
+      "step": 193
+    },
+    {
+      "epoch": 3.532110091743119,
+      "grad_norm": 0.3457902669906616,
+      "learning_rate": 4.612377041496776e-05,
+      "loss": 0.2553,
+      "num_input_tokens_seen": 7998024,
+      "step": 194
+    },
+    {
+      "epoch": 3.5504587155963305,
+      "grad_norm": 0.31968954205513,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.2197,
+      "num_input_tokens_seen": 8055672,
+      "step": 195
+    },
+    {
+      "epoch": 3.5688073394495414,
+      "grad_norm": 0.34753403067588806,
+      "learning_rate": 4.604562346488144e-05,
+      "loss": 0.2507,
+      "num_input_tokens_seen": 8090848,
+      "step": 196
+    },
+    {
+      "epoch": 3.5871559633027523,
+      "grad_norm": 0.3808669149875641,
+      "learning_rate": 4.6006282705024144e-05,
+      "loss": 0.2422,
+      "num_input_tokens_seen": 8136680,
+      "step": 197
+    },
+    {
+      "epoch": 3.6055045871559632,
+      "grad_norm": 0.3004499673843384,
+      "learning_rate": 4.5966764198635606e-05,
+      "loss": 0.2107,
+      "num_input_tokens_seen": 8187472,
+      "step": 198
+    },
+    {
+      "epoch": 3.623853211009174,
+      "grad_norm": 0.30718186497688293,
+      "learning_rate": 4.592706828010518e-05,
+      "loss": 0.1854,
+      "num_input_tokens_seen": 8225216,
+      "step": 199
+    },
+    {
+      "epoch": 3.6422018348623855,
+      "grad_norm": 0.23112858831882477,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.1687,
+      "num_input_tokens_seen": 8274456,
+      "step": 200
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "grad_norm": 0.25966888666152954,
+      "learning_rate": 4.5847145551679206e-05,
+      "loss": 0.2549,
+      "num_input_tokens_seen": 8317016,
+      "step": 201
+    },
+    {
+      "epoch": 3.6788990825688073,
+      "grad_norm": 0.25600987672805786,
+      "learning_rate": 4.580691941805695e-05,
+      "loss": 0.1602,
+      "num_input_tokens_seen": 8361856,
+      "step": 202
+    },
+    {
+      "epoch": 3.6972477064220186,
+      "grad_norm": 0.33986184000968933,
+      "learning_rate": 4.5766517224833637e-05,
+      "loss": 0.2495,
+      "num_input_tokens_seen": 8410696,
+      "step": 203
+    },
+    {
+      "epoch": 3.7155963302752295,
+      "grad_norm": 0.36899781227111816,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.2012,
+      "num_input_tokens_seen": 8441872,
+      "step": 204
+    },
+    {
+      "epoch": 3.7339449541284404,
+      "grad_norm": 0.42072632908821106,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 8482544,
+      "step": 205
+    },
+    {
+      "epoch": 3.7522935779816513,
+      "grad_norm": 0.40593233704566956,
+      "learning_rate": 4.5644257713656356e-05,
+      "loss": 0.233,
+      "num_input_tokens_seen": 8519856,
+      "step": 206
+    },
+    {
+      "epoch": 3.770642201834862,
+      "grad_norm": 0.38003161549568176,
+      "learning_rate": 4.5603154715550386e-05,
+      "loss": 0.225,
+      "num_input_tokens_seen": 8551392,
+      "step": 207
+    },
+    {
+      "epoch": 3.7889908256880735,
+      "grad_norm": 0.2564244568347931,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.2975,
+      "num_input_tokens_seen": 8599472,
+      "step": 208
+    },
+    {
+      "epoch": 3.8073394495412844,
+      "grad_norm": 0.29023391008377075,
+      "learning_rate": 4.552042606232668e-05,
+      "loss": 0.2033,
+      "num_input_tokens_seen": 8631880,
+      "step": 209
+    },
+    {
+      "epoch": 3.8256880733944953,
+      "grad_norm": 0.32886001467704773,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.2024,
+      "num_input_tokens_seen": 8675016,
+      "step": 210
+    },
+    {
+      "epoch": 3.8440366972477067,
+      "grad_norm": 0.36749884486198425,
+      "learning_rate": 4.5437002868924166e-05,
+      "loss": 0.2304,
+      "num_input_tokens_seen": 8713248,
+      "step": 211
+    },
+    {
+      "epoch": 3.8623853211009176,
+      "grad_norm": 0.3055097758769989,
+      "learning_rate": 4.539503170110431e-05,
+      "loss": 0.2928,
+      "num_input_tokens_seen": 8748800,
+      "step": 212
+    },
+    {
+      "epoch": 3.8807339449541285,
+      "grad_norm": 0.38436686992645264,
+      "learning_rate": 4.535288795890798e-05,
+      "loss": 0.2214,
+      "num_input_tokens_seen": 8787832,
+      "step": 213
+    },
+    {
+      "epoch": 3.8990825688073394,
+      "grad_norm": 0.44330883026123047,
+      "learning_rate": 4.531057199893824e-05,
+      "loss": 0.2168,
+      "num_input_tokens_seen": 8819616,
+      "step": 214
+    },
+    {
+      "epoch": 3.9174311926605503,
+      "grad_norm": 0.28318527340888977,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.279,
+      "num_input_tokens_seen": 8860744,
+      "step": 215
+    },
+    {
+      "epoch": 3.9357798165137616,
+      "grad_norm": 0.3287319839000702,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.2597,
+      "num_input_tokens_seen": 8906432,
+      "step": 216
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1080,
+  "num_input_tokens_seen": 8906432,
+  "num_train_epochs": 20,
+  "save_steps": 54,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.513615025265705e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-270/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-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 0.12.0

checkpoint-270/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-270/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-270/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-270/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 15000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-270/trainer_state.json

@@ -0,0 +1,2193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.91743119266055,
+  "eval_steps": 500,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.04378490149974823,
+      "learning_rate": 4.999989423013716e-05,
+      "loss": 0.6713,
+      "num_input_tokens_seen": 44136,
+      "step": 1
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.040646992623806,
+      "learning_rate": 4.999957692144361e-05,
+      "loss": 0.533,
+      "num_input_tokens_seen": 83096,
+      "step": 2
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.04658753052353859,
+      "learning_rate": 4.999904807660428e-05,
+      "loss": 0.6048,
+      "num_input_tokens_seen": 122112,
+      "step": 3
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 0.04322144016623497,
+      "learning_rate": 4.999830770009406e-05,
+      "loss": 0.4948,
+      "num_input_tokens_seen": 163064,
+      "step": 4
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 0.06536195427179337,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.6607,
+      "num_input_tokens_seen": 203808,
+      "step": 5
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 0.059904925525188446,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 0.5802,
+      "num_input_tokens_seen": 241824,
+      "step": 6
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 0.19818365573883057,
+      "learning_rate": 4.999481745213471e-05,
+      "loss": 0.5148,
+      "num_input_tokens_seen": 287608,
+      "step": 7
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.05985472351312637,
+      "learning_rate": 4.9993231029486544e-05,
+      "loss": 0.5714,
+      "num_input_tokens_seen": 325320,
+      "step": 8
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 0.061375778168439865,
+      "learning_rate": 4.999143312438893e-05,
+      "loss": 0.6812,
+      "num_input_tokens_seen": 369848,
+      "step": 9
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 0.06196414306759834,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.5358,
+      "num_input_tokens_seen": 415104,
+      "step": 10
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 0.07861393690109253,
+      "learning_rate": 4.9987202929487275e-05,
+      "loss": 0.6527,
+      "num_input_tokens_seen": 467224,
+      "step": 11
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 0.05596446990966797,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 0.5354,
+      "num_input_tokens_seen": 502824,
+      "step": 12
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 0.05289844051003456,
+      "learning_rate": 4.998212701060612e-05,
+      "loss": 0.5263,
+      "num_input_tokens_seen": 544744,
+      "step": 13
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 0.04996591433882713,
+      "learning_rate": 4.997927195724303e-05,
+      "loss": 0.5536,
+      "num_input_tokens_seen": 591136,
+      "step": 14
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 0.05822828412055969,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.6106,
+      "num_input_tokens_seen": 629664,
+      "step": 15
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.06353770196437836,
+      "learning_rate": 4.997292778346312e-05,
+      "loss": 0.5129,
+      "num_input_tokens_seen": 663392,
+      "step": 16
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 0.07256966829299927,
+      "learning_rate": 4.996943871672807e-05,
+      "loss": 0.6377,
+      "num_input_tokens_seen": 698360,
+      "step": 17
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 0.055458713322877884,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 0.4083,
+      "num_input_tokens_seen": 737520,
+      "step": 18
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 0.07792335003614426,
+      "learning_rate": 4.9961826771182784e-05,
+      "loss": 0.6086,
+      "num_input_tokens_seen": 768056,
+      "step": 19
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 0.06627275049686432,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.4591,
+      "num_input_tokens_seen": 806256,
+      "step": 20
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 0.05830290913581848,
+      "learning_rate": 4.9953369960546676e-05,
+      "loss": 0.3731,
+      "num_input_tokens_seen": 842336,
+      "step": 21
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 0.07277437299489975,
+      "learning_rate": 4.9948824819150185e-05,
+      "loss": 0.6243,
+      "num_input_tokens_seen": 876672,
+      "step": 22
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 0.07477546483278275,
+      "learning_rate": 4.994406857105136e-05,
+      "loss": 0.5788,
+      "num_input_tokens_seen": 915192,
+      "step": 23
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.06912907212972641,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4753,
+      "num_input_tokens_seen": 951904,
+      "step": 24
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 0.0655476376414299,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.4518,
+      "num_input_tokens_seen": 1001816,
+      "step": 25
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 0.06466512382030487,
+      "learning_rate": 4.992853359792444e-05,
+      "loss": 0.5638,
+      "num_input_tokens_seen": 1053064,
+      "step": 26
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 0.0645688995718956,
+      "learning_rate": 4.99229333433282e-05,
+      "loss": 0.4644,
+      "num_input_tokens_seen": 1086688,
+      "step": 27
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 0.07181251049041748,
+      "learning_rate": 4.9917122201112656e-05,
+      "loss": 0.6191,
+      "num_input_tokens_seen": 1134824,
+      "step": 28
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 0.07322589308023453,
+      "learning_rate": 4.9911100220449293e-05,
+      "loss": 0.6752,
+      "num_input_tokens_seen": 1172072,
+      "step": 29
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.06396070122718811,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.3587,
+      "num_input_tokens_seen": 1211096,
+      "step": 30
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 0.07803395390510559,
+      "learning_rate": 4.989842394938482e-05,
+      "loss": 0.459,
+      "num_input_tokens_seen": 1259456,
+      "step": 31
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 0.05974648892879486,
+      "learning_rate": 4.989176976624511e-05,
+      "loss": 0.4148,
+      "num_input_tokens_seen": 1306944,
+      "step": 32
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 0.09784268587827682,
+      "learning_rate": 4.988490495917947e-05,
+      "loss": 0.539,
+      "num_input_tokens_seen": 1353744,
+      "step": 33
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 0.09906516224145889,
+      "learning_rate": 4.987782958627508e-05,
+      "loss": 0.5453,
+      "num_input_tokens_seen": 1394736,
+      "step": 34
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 0.08984062820672989,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.468,
+      "num_input_tokens_seen": 1442048,
+      "step": 35
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.08672655373811722,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.4078,
+      "num_input_tokens_seen": 1478440,
+      "step": 36
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 0.1327345073223114,
+      "learning_rate": 4.9855340680123905e-05,
+      "loss": 0.5299,
+      "num_input_tokens_seen": 1525992,
+      "step": 37
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 0.09178602695465088,
+      "learning_rate": 4.9847423660363e-05,
+      "loss": 0.439,
+      "num_input_tokens_seen": 1555608,
+      "step": 38
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 0.09418320655822754,
+      "learning_rate": 4.983929639191469e-05,
+      "loss": 0.5337,
+      "num_input_tokens_seen": 1597392,
+      "step": 39
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.08294719457626343,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.4536,
+      "num_input_tokens_seen": 1649656,
+      "step": 40
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 0.09774205833673477,
+      "learning_rate": 4.982241138581273e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 1695952,
+      "step": 41
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.09319107979536057,
+      "learning_rate": 4.9813653791033057e-05,
+      "loss": 0.4279,
+      "num_input_tokens_seen": 1737224,
+      "step": 42
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 0.09561405330896378,
+      "learning_rate": 4.980468623331273e-05,
+      "loss": 0.5121,
+      "num_input_tokens_seen": 1772320,
+      "step": 43
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 0.08274025470018387,
+      "learning_rate": 4.979550878853154e-05,
+      "loss": 0.54,
+      "num_input_tokens_seen": 1823888,
+      "step": 44
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 0.08728913217782974,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 1872488,
+      "step": 45
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 0.0787016749382019,
+      "learning_rate": 4.9776524550184965e-05,
+      "loss": 0.4353,
+      "num_input_tokens_seen": 1924744,
+      "step": 46
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 0.10952188074588776,
+      "learning_rate": 4.97667179172564e-05,
+      "loss": 0.4784,
+      "num_input_tokens_seen": 1959936,
+      "step": 47
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.08525826781988144,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 0.3586,
+      "num_input_tokens_seen": 2003896,
+      "step": 48
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 0.10409987717866898,
+      "learning_rate": 4.9746476038786496e-05,
+      "loss": 0.4451,
+      "num_input_tokens_seen": 2047632,
+      "step": 49
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 0.0782993957400322,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.3591,
+      "num_input_tokens_seen": 2096928,
+      "step": 50
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 0.09829951077699661,
+      "learning_rate": 4.9725396584047925e-05,
+      "loss": 0.3415,
+      "num_input_tokens_seen": 2129536,
+      "step": 51
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 0.10606162995100021,
+      "learning_rate": 4.971454298742779e-05,
+      "loss": 0.3758,
+      "num_input_tokens_seen": 2169144,
+      "step": 52
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 0.09280356764793396,
+      "learning_rate": 4.97034802665019e-05,
+      "loss": 0.485,
+      "num_input_tokens_seen": 2207720,
+      "step": 53
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.11888203024864197,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 0.3469,
+      "num_input_tokens_seen": 2236392,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13222463428974152,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.4284,
+      "num_input_tokens_seen": 2259088,
+      "step": 55
+    },
+    {
+      "epoch": 1.018348623853211,
+      "grad_norm": 0.10572745651006699,
+      "learning_rate": 4.966903830281449e-05,
+      "loss": 0.4186,
+      "num_input_tokens_seen": 2298496,
+      "step": 56
+    },
+    {
+      "epoch": 1.036697247706422,
+      "grad_norm": 0.11462350189685822,
+      "learning_rate": 4.965714003843079e-05,
+      "loss": 0.4696,
+      "num_input_tokens_seen": 2333016,
+      "step": 57
+    },
+    {
+      "epoch": 1.0550458715596331,
+      "grad_norm": 0.11215240508317947,
+      "learning_rate": 4.9645033135461494e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 2367992,
+      "step": 58
+    },
+    {
+      "epoch": 1.073394495412844,
+      "grad_norm": 0.0973561555147171,
+      "learning_rate": 4.963271769635024e-05,
+      "loss": 0.3588,
+      "num_input_tokens_seen": 2415328,
+      "step": 59
+    },
+    {
+      "epoch": 1.091743119266055,
+      "grad_norm": 0.10240709036588669,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.5532,
+      "num_input_tokens_seen": 2454792,
+      "step": 60
+    },
+    {
+      "epoch": 1.110091743119266,
+      "grad_norm": 0.0959337130188942,
+      "learning_rate": 4.9607461628298244e-05,
+      "loss": 0.331,
+      "num_input_tokens_seen": 2503072,
+      "step": 61
+    },
+    {
+      "epoch": 1.1284403669724772,
+      "grad_norm": 0.10228750854730606,
+      "learning_rate": 4.9594521213063974e-05,
+      "loss": 0.3728,
+      "num_input_tokens_seen": 2546960,
+      "step": 62
+    },
+    {
+      "epoch": 1.146788990825688,
+      "grad_norm": 0.09403488785028458,
+      "learning_rate": 4.958137268909887e-05,
+      "loss": 0.4695,
+      "num_input_tokens_seen": 2595432,
+      "step": 63
+    },
+    {
+      "epoch": 1.165137614678899,
+      "grad_norm": 0.11396344751119614,
+      "learning_rate": 4.9568016167660334e-05,
+      "loss": 0.3653,
+      "num_input_tokens_seen": 2633912,
+      "step": 64
+    },
+    {
+      "epoch": 1.18348623853211,
+      "grad_norm": 0.09487481415271759,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.3498,
+      "num_input_tokens_seen": 2680792,
+      "step": 65
+    },
+    {
+      "epoch": 1.2018348623853212,
+      "grad_norm": 0.1249895691871643,
+      "learning_rate": 4.9540679586191605e-05,
+      "loss": 0.4053,
+      "num_input_tokens_seen": 2716584,
+      "step": 66
+    },
+    {
+      "epoch": 1.2201834862385321,
+      "grad_norm": 0.12268221378326416,
+      "learning_rate": 4.952669975747232e-05,
+      "loss": 0.4189,
+      "num_input_tokens_seen": 2757088,
+      "step": 67
+    },
+    {
+      "epoch": 1.238532110091743,
+      "grad_norm": 0.12126032263040543,
+      "learning_rate": 4.951251239389948e-05,
+      "loss": 0.4994,
+      "num_input_tokens_seen": 2795664,
+      "step": 68
+    },
+    {
+      "epoch": 1.2568807339449541,
+      "grad_norm": 0.1069057360291481,
+      "learning_rate": 4.949811761552074e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 2840936,
+      "step": 69
+    },
+    {
+      "epoch": 1.2752293577981653,
+      "grad_norm": 0.10893313586711884,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.4366,
+      "num_input_tokens_seen": 2886768,
+      "step": 70
+    },
+    {
+      "epoch": 1.2935779816513762,
+      "grad_norm": 0.12898756563663483,
+      "learning_rate": 4.9468706303310355e-05,
+      "loss": 0.3916,
+      "num_input_tokens_seen": 2919328,
+      "step": 71
+    },
+    {
+      "epoch": 1.311926605504587,
+      "grad_norm": 0.12405356019735336,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.3249,
+      "num_input_tokens_seen": 2966744,
+      "step": 72
+    },
+    {
+      "epoch": 1.3302752293577982,
+      "grad_norm": 0.13137595355510712,
+      "learning_rate": 4.943846681630479e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3007248,
+      "step": 73
+    },
+    {
+      "epoch": 1.3486238532110093,
+      "grad_norm": 0.13920250535011292,
+      "learning_rate": 4.942303682600178e-05,
+      "loss": 0.3956,
+      "num_input_tokens_seen": 3050960,
+      "step": 74
+    },
+    {
+      "epoch": 1.3669724770642202,
+      "grad_norm": 0.1255589872598648,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.3773,
+      "num_input_tokens_seen": 3088592,
+      "step": 75
+    },
+    {
+      "epoch": 1.385321100917431,
+      "grad_norm": 0.10222747176885605,
+      "learning_rate": 4.939155700460536e-05,
+      "loss": 0.4,
+      "num_input_tokens_seen": 3153520,
+      "step": 76
+    },
+    {
+      "epoch": 1.4036697247706422,
+      "grad_norm": 0.13205283880233765,
+      "learning_rate": 4.9375507439881266e-05,
+      "loss": 0.4343,
+      "num_input_tokens_seen": 3199272,
+      "step": 77
+    },
+    {
+      "epoch": 1.4220183486238533,
+      "grad_norm": 0.11005694419145584,
+      "learning_rate": 4.9359251619630886e-05,
+      "loss": 0.3881,
+      "num_input_tokens_seen": 3247128,
+      "step": 78
+    },
+    {
+      "epoch": 1.4403669724770642,
+      "grad_norm": 0.14799247682094574,
+      "learning_rate": 4.9342789681404275e-05,
+      "loss": 0.3972,
+      "num_input_tokens_seen": 3294192,
+      "step": 79
+    },
+    {
+      "epoch": 1.4587155963302751,
+      "grad_norm": 0.1279418021440506,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.3438,
+      "num_input_tokens_seen": 3329736,
+      "step": 80
+    },
+    {
+      "epoch": 1.4770642201834863,
+      "grad_norm": 0.11036807298660278,
+      "learning_rate": 4.9309248009941914e-05,
+      "loss": 0.3189,
+      "num_input_tokens_seen": 3371376,
+      "step": 81
+    },
+    {
+      "epoch": 1.4954128440366974,
+      "grad_norm": 0.11855707317590714,
+      "learning_rate": 4.9292168560522014e-05,
+      "loss": 0.401,
+      "num_input_tokens_seen": 3412368,
+      "step": 82
+    },
+    {
+      "epoch": 1.5137614678899083,
+      "grad_norm": 0.13195356726646423,
+      "learning_rate": 4.9274883560755156e-05,
+      "loss": 0.4973,
+      "num_input_tokens_seen": 3455000,
+      "step": 83
+    },
+    {
+      "epoch": 1.5321100917431192,
+      "grad_norm": 0.1462787538766861,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 0.3768,
+      "num_input_tokens_seen": 3488960,
+      "step": 84
+    },
+    {
+      "epoch": 1.5504587155963303,
+      "grad_norm": 0.13765974342823029,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.2999,
+      "num_input_tokens_seen": 3521320,
+      "step": 85
+    },
+    {
+      "epoch": 1.5688073394495414,
+      "grad_norm": 0.15276113152503967,
+      "learning_rate": 4.9221796730647516e-05,
+      "loss": 0.3638,
+      "num_input_tokens_seen": 3559464,
+      "step": 86
+    },
+    {
+      "epoch": 1.5871559633027523,
+      "grad_norm": 0.1441674381494522,
+      "learning_rate": 4.92036910094527e-05,
+      "loss": 0.3919,
+      "num_input_tokens_seen": 3598080,
+      "step": 87
+    },
+    {
+      "epoch": 1.6055045871559632,
+      "grad_norm": 0.1780252456665039,
+      "learning_rate": 4.9185380486571595e-05,
+      "loss": 0.3626,
+      "num_input_tokens_seen": 3630064,
+      "step": 88
+    },
+    {
+      "epoch": 1.6238532110091743,
+      "grad_norm": 0.16947726905345917,
+      "learning_rate": 4.916686531694035e-05,
+      "loss": 0.3439,
+      "num_input_tokens_seen": 3661408,
+      "step": 89
+    },
+    {
+      "epoch": 1.6422018348623855,
+      "grad_norm": 0.1552971601486206,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.3236,
+      "num_input_tokens_seen": 3695480,
+      "step": 90
+    },
+    {
+      "epoch": 1.6605504587155964,
+      "grad_norm": 0.14925938844680786,
+      "learning_rate": 4.912922166582874e-05,
+      "loss": 0.4255,
+      "num_input_tokens_seen": 3734560,
+      "step": 91
+    },
+    {
+      "epoch": 1.6788990825688073,
+      "grad_norm": 0.1332874596118927,
+      "learning_rate": 4.9110093502873476e-05,
+      "loss": 0.3061,
+      "num_input_tokens_seen": 3773112,
+      "step": 92
+    },
+    {
+      "epoch": 1.6972477064220184,
+      "grad_norm": 0.15471243858337402,
+      "learning_rate": 4.909076133021557e-05,
+      "loss": 0.3275,
+      "num_input_tokens_seen": 3813392,
+      "step": 93
+    },
+    {
+      "epoch": 1.7155963302752295,
+      "grad_norm": 0.16010524332523346,
+      "learning_rate": 4.907122531143594e-05,
+      "loss": 0.4179,
+      "num_input_tokens_seen": 3856416,
+      "step": 94
+    },
+    {
+      "epoch": 1.7339449541284404,
+      "grad_norm": 0.13423003256320953,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.3593,
+      "num_input_tokens_seen": 3899472,
+      "step": 95
+    },
+    {
+      "epoch": 1.7522935779816513,
+      "grad_norm": 0.14900773763656616,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.5007,
+      "num_input_tokens_seen": 3962976,
+      "step": 96
+    },
+    {
+      "epoch": 1.7706422018348624,
+      "grad_norm": 0.15728624165058136,
+      "learning_rate": 4.9011395840040144e-05,
+      "loss": 0.3484,
+      "num_input_tokens_seen": 4000696,
+      "step": 97
+    },
+    {
+      "epoch": 1.7889908256880735,
+      "grad_norm": 0.11092367768287659,
+      "learning_rate": 4.8991046107058735e-05,
+      "loss": 0.2889,
+      "num_input_tokens_seen": 4045256,
+      "step": 98
+    },
+    {
+      "epoch": 1.8073394495412844,
+      "grad_norm": 0.1289113610982895,
+      "learning_rate": 4.8970493371704826e-05,
+      "loss": 0.2203,
+      "num_input_tokens_seen": 4076800,
+      "step": 99
+    },
+    {
+      "epoch": 1.8256880733944953,
+      "grad_norm": 0.18886639177799225,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.3966,
+      "num_input_tokens_seen": 4119840,
+      "step": 100
+    },
+    {
+      "epoch": 1.8440366972477065,
+      "grad_norm": 0.1563039869070053,
+      "learning_rate": 4.892877959123097e-05,
+      "loss": 0.4417,
+      "num_input_tokens_seen": 4165848,
+      "step": 101
+    },
+    {
+      "epoch": 1.8623853211009176,
+      "grad_norm": 0.16883380711078644,
+      "learning_rate": 4.890761889907589e-05,
+      "loss": 0.4258,
+      "num_input_tokens_seen": 4202824,
+      "step": 102
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.18241995573043823,
+      "learning_rate": 4.8886255910475054e-05,
+      "loss": 0.3952,
+      "num_input_tokens_seen": 4233888,
+      "step": 103
+    },
+    {
+      "epoch": 1.8990825688073394,
+      "grad_norm": 0.19913265109062195,
+      "learning_rate": 4.88646908061933e-05,
+      "loss": 0.3241,
+      "num_input_tokens_seen": 4267064,
+      "step": 104
+    },
+    {
+      "epoch": 1.9174311926605505,
+      "grad_norm": 0.18295545876026154,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.4239,
+      "num_input_tokens_seen": 4312536,
+      "step": 105
+    },
+    {
+      "epoch": 1.9357798165137616,
+      "grad_norm": 0.16657495498657227,
+      "learning_rate": 4.8820954982195905e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 4356656,
+      "step": 106
+    },
+    {
+      "epoch": 1.9541284403669725,
+      "grad_norm": 0.18504932522773743,
+      "learning_rate": 4.879878463255483e-05,
+      "loss": 0.44,
+      "num_input_tokens_seen": 4400216,
+      "step": 107
+    },
+    {
+      "epoch": 1.9724770642201834,
+      "grad_norm": 0.1923118382692337,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2662,
+      "num_input_tokens_seen": 4436968,
+      "step": 108
+    },
+    {
+      "epoch": 1.9908256880733946,
+      "grad_norm": 0.19636788964271545,
+      "learning_rate": 4.875383999596828e-05,
+      "loss": 0.4211,
+      "num_input_tokens_seen": 4488232,
+      "step": 109
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3168099820613861,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.2499,
+      "num_input_tokens_seen": 4518176,
+      "step": 110
+    },
+    {
+      "epoch": 2.018348623853211,
+      "grad_norm": 0.14410308003425598,
+      "learning_rate": 4.8708091380154984e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 4570896,
+      "step": 111
+    },
+    {
+      "epoch": 2.036697247706422,
+      "grad_norm": 0.17840909957885742,
+      "learning_rate": 4.868491606285823e-05,
+      "loss": 0.2758,
+      "num_input_tokens_seen": 4613576,
+      "step": 112
+    },
+    {
+      "epoch": 2.055045871559633,
+      "grad_norm": 0.178523987531662,
+      "learning_rate": 4.866154033353561e-05,
+      "loss": 0.3361,
+      "num_input_tokens_seen": 4652896,
+      "step": 113
+    },
+    {
+      "epoch": 2.073394495412844,
+      "grad_norm": 0.17396725714206696,
+      "learning_rate": 4.8637964389982926e-05,
+      "loss": 0.2667,
+      "num_input_tokens_seen": 4694256,
+      "step": 114
+    },
+    {
+      "epoch": 2.091743119266055,
+      "grad_norm": 0.19471587240695953,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.3628,
+      "num_input_tokens_seen": 4747552,
+      "step": 115
+    },
+    {
+      "epoch": 2.1100917431192663,
+      "grad_norm": 0.1722450852394104,
+      "learning_rate": 4.859021265983959e-05,
+      "loss": 0.3599,
+      "num_input_tokens_seen": 4794080,
+      "step": 116
+    },
+    {
+      "epoch": 2.128440366972477,
+      "grad_norm": 0.20137006044387817,
+      "learning_rate": 4.856603727730447e-05,
+      "loss": 0.4262,
+      "num_input_tokens_seen": 4847912,
+      "step": 117
+    },
+    {
+      "epoch": 2.146788990825688,
+      "grad_norm": 0.19395771622657776,
+      "learning_rate": 4.854166248864689e-05,
+      "loss": 0.3118,
+      "num_input_tokens_seen": 4885480,
+      "step": 118
+    },
+    {
+      "epoch": 2.165137614678899,
+      "grad_norm": 0.209548681974411,
+      "learning_rate": 4.85170885001163e-05,
+      "loss": 0.3725,
+      "num_input_tokens_seen": 4921240,
+      "step": 119
+    },
+    {
+      "epoch": 2.18348623853211,
+      "grad_norm": 0.18228279054164886,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.3816,
+      "num_input_tokens_seen": 4960224,
+      "step": 120
+    },
+    {
+      "epoch": 2.2018348623853212,
+      "grad_norm": 0.24349354207515717,
+      "learning_rate": 4.846734375685989e-05,
+      "loss": 0.3383,
+      "num_input_tokens_seen": 4990536,
+      "step": 121
+    },
+    {
+      "epoch": 2.220183486238532,
+      "grad_norm": 0.17600344121456146,
+      "learning_rate": 4.844217342305363e-05,
+      "loss": 0.3011,
+      "num_input_tokens_seen": 5044296,
+      "step": 122
+    },
+    {
+      "epoch": 2.238532110091743,
+      "grad_norm": 0.18766675889492035,
+      "learning_rate": 4.8416804731209945e-05,
+      "loss": 0.4458,
+      "num_input_tokens_seen": 5088368,
+      "step": 123
+    },
+    {
+      "epoch": 2.2568807339449544,
+      "grad_norm": 0.17657820880413055,
+      "learning_rate": 4.839123789598829e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 5133472,
+      "step": 124
+    },
+    {
+      "epoch": 2.2752293577981653,
+      "grad_norm": 0.20606014132499695,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.313,
+      "num_input_tokens_seen": 5167768,
+      "step": 125
+    },
+    {
+      "epoch": 2.293577981651376,
+      "grad_norm": 0.23511061072349548,
+      "learning_rate": 4.8339510662430046e-05,
+      "loss": 0.2963,
+      "num_input_tokens_seen": 5209400,
+      "step": 126
+    },
+    {
+      "epoch": 2.311926605504587,
+      "grad_norm": 0.18234293162822723,
+      "learning_rate": 4.8313350701788054e-05,
+      "loss": 0.2566,
+      "num_input_tokens_seen": 5249360,
+      "step": 127
+    },
+    {
+      "epoch": 2.330275229357798,
+      "grad_norm": 0.2223992496728897,
+      "learning_rate": 4.828699347315356e-05,
+      "loss": 0.2833,
+      "num_input_tokens_seen": 5300808,
+      "step": 128
+    },
+    {
+      "epoch": 2.3486238532110093,
+      "grad_norm": 0.23101739585399628,
+      "learning_rate": 4.826043919955062e-05,
+      "loss": 0.3099,
+      "num_input_tokens_seen": 5332960,
+      "step": 129
+    },
+    {
+      "epoch": 2.36697247706422,
+      "grad_norm": 0.26640889048576355,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.3238,
+      "num_input_tokens_seen": 5365008,
+      "step": 130
+    },
+    {
+      "epoch": 2.385321100917431,
+      "grad_norm": 0.2374572902917862,
+      "learning_rate": 4.820674041787017e-05,
+      "loss": 0.3153,
+      "num_input_tokens_seen": 5400184,
+      "step": 131
+    },
+    {
+      "epoch": 2.4036697247706424,
+      "grad_norm": 0.22812288999557495,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.2997,
+      "num_input_tokens_seen": 5440320,
+      "step": 132
+    },
+    {
+      "epoch": 2.4220183486238533,
+      "grad_norm": 0.20079149305820465,
+      "learning_rate": 4.815225617425095e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5480832,
+      "step": 133
+    },
+    {
+      "epoch": 2.4403669724770642,
+      "grad_norm": 0.196709543466568,
+      "learning_rate": 4.81247200794554e-05,
+      "loss": 0.2456,
+      "num_input_tokens_seen": 5526936,
+      "step": 134
+    },
+    {
+      "epoch": 2.458715596330275,
+      "grad_norm": 0.17305873334407806,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.2099,
+      "num_input_tokens_seen": 5566384,
+      "step": 135
+    },
+    {
+      "epoch": 2.477064220183486,
+      "grad_norm": 3.584635019302368,
+      "learning_rate": 4.806906110888606e-05,
+      "loss": 0.3485,
+      "num_input_tokens_seen": 5629896,
+      "step": 136
+    },
+    {
+      "epoch": 2.4954128440366974,
+      "grad_norm": 0.23481500148773193,
+      "learning_rate": 4.80409387040756e-05,
+      "loss": 0.2231,
+      "num_input_tokens_seen": 5674504,
+      "step": 137
+    },
+    {
+      "epoch": 2.5137614678899083,
+      "grad_norm": 0.27899855375289917,
+      "learning_rate": 4.8012621336311016e-05,
+      "loss": 0.4285,
+      "num_input_tokens_seen": 5714000,
+      "step": 138
+    },
+    {
+      "epoch": 2.532110091743119,
+      "grad_norm": 0.24404938519001007,
+      "learning_rate": 4.798410924520223e-05,
+      "loss": 0.3343,
+      "num_input_tokens_seen": 5756856,
+      "step": 139
+    },
+    {
+      "epoch": 2.5504587155963305,
+      "grad_norm": 0.26869162917137146,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 5781192,
+      "step": 140
+    },
+    {
+      "epoch": 2.5688073394495414,
+      "grad_norm": 0.2057972550392151,
+      "learning_rate": 4.79265018596281e-05,
+      "loss": 0.2991,
+      "num_input_tokens_seen": 5824024,
+      "step": 141
+    },
+    {
+      "epoch": 2.5871559633027523,
+      "grad_norm": 0.2184937596321106,
+      "learning_rate": 4.789740705261278e-05,
+      "loss": 0.2406,
+      "num_input_tokens_seen": 5862584,
+      "step": 142
+    },
+    {
+      "epoch": 2.6055045871559632,
+      "grad_norm": 0.23603741824626923,
+      "learning_rate": 4.786811849714918e-05,
+      "loss": 0.2722,
+      "num_input_tokens_seen": 5897344,
+      "step": 143
+    },
+    {
+      "epoch": 2.623853211009174,
+      "grad_norm": 0.22983981668949127,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 5931736,
+      "step": 144
+    },
+    {
+      "epoch": 2.6422018348623855,
+      "grad_norm": 0.2825419306755066,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.3386,
+      "num_input_tokens_seen": 5972784,
+      "step": 145
+    },
+    {
+      "epoch": 2.6605504587155964,
+      "grad_norm": 0.4502134621143341,
+      "learning_rate": 4.777909282653042e-05,
+      "loss": 0.2289,
+      "num_input_tokens_seen": 6018968,
+      "step": 146
+    },
+    {
+      "epoch": 2.6788990825688073,
+      "grad_norm": 0.2428288459777832,
+      "learning_rate": 4.7749031771913584e-05,
+      "loss": 0.4061,
+      "num_input_tokens_seen": 6062520,
+      "step": 147
+    },
+    {
+      "epoch": 2.6972477064220186,
+      "grad_norm": 0.2685629725456238,
+      "learning_rate": 4.771877822433911e-05,
+      "loss": 0.2198,
+      "num_input_tokens_seen": 6087928,
+      "step": 148
+    },
+    {
+      "epoch": 2.7155963302752295,
+      "grad_norm": 0.24021446704864502,
+      "learning_rate": 4.7688332439800096e-05,
+      "loss": 0.34,
+      "num_input_tokens_seen": 6134792,
+      "step": 149
+    },
+    {
+      "epoch": 2.7339449541284404,
+      "grad_norm": 0.2568534314632416,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.3292,
+      "num_input_tokens_seen": 6183296,
+      "step": 150
+    },
+    {
+      "epoch": 2.7522935779816513,
+      "grad_norm": 0.20823974907398224,
+      "learning_rate": 4.762686519193175e-05,
+      "loss": 0.2539,
+      "num_input_tokens_seen": 6225840,
+      "step": 151
+    },
+    {
+      "epoch": 2.770642201834862,
+      "grad_norm": 0.23333317041397095,
+      "learning_rate": 4.759584424871302e-05,
+      "loss": 0.3571,
+      "num_input_tokens_seen": 6274760,
+      "step": 152
+    },
+    {
+      "epoch": 2.7889908256880735,
+      "grad_norm": 0.20232398808002472,
+      "learning_rate": 4.756463210874652e-05,
+      "loss": 0.2783,
+      "num_input_tokens_seen": 6326168,
+      "step": 153
+    },
+    {
+      "epoch": 2.8073394495412844,
+      "grad_norm": 0.3479433059692383,
+      "learning_rate": 4.7533229036136553e-05,
+      "loss": 0.2925,
+      "num_input_tokens_seen": 6360312,
+      "step": 154
+    },
+    {
+      "epoch": 2.8256880733944953,
+      "grad_norm": 0.2659524083137512,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.2606,
+      "num_input_tokens_seen": 6395496,
+      "step": 155
+    },
+    {
+      "epoch": 2.8440366972477067,
+      "grad_norm": 0.24823158979415894,
+      "learning_rate": 4.7469851157479177e-05,
+      "loss": 0.3721,
+      "num_input_tokens_seen": 6437064,
+      "step": 156
+    },
+    {
+      "epoch": 2.8623853211009176,
+      "grad_norm": 0.32034072279930115,
+      "learning_rate": 4.743787688770932e-05,
+      "loss": 0.3931,
+      "num_input_tokens_seen": 6477616,
+      "step": 157
+    },
+    {
+      "epoch": 2.8807339449541285,
+      "grad_norm": 0.23295725882053375,
+      "learning_rate": 4.740571275784659e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 6518680,
+      "step": 158
+    },
+    {
+      "epoch": 2.8990825688073394,
+      "grad_norm": 0.2758423984050751,
+      "learning_rate": 4.737335904005063e-05,
+      "loss": 0.2579,
+      "num_input_tokens_seen": 6549768,
+      "step": 159
+    },
+    {
+      "epoch": 2.9174311926605503,
+      "grad_norm": 0.26690953969955444,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.2575,
+      "num_input_tokens_seen": 6581000,
+      "step": 160
+    },
+    {
+      "epoch": 2.9357798165137616,
+      "grad_norm": 0.26657482981681824,
+      "learning_rate": 4.730808393731639e-05,
+      "loss": 0.2597,
+      "num_input_tokens_seen": 6612632,
+      "step": 161
+    },
+    {
+      "epoch": 2.9541284403669725,
+      "grad_norm": 0.22647295892238617,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.3335,
+      "num_input_tokens_seen": 6654288,
+      "step": 162
+    },
+    {
+      "epoch": 2.9724770642201834,
+      "grad_norm": 0.2863366901874542,
+      "learning_rate": 4.72420537888263e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 6707208,
+      "step": 163
+    },
+    {
+      "epoch": 2.9908256880733948,
+      "grad_norm": 0.2606408894062042,
+      "learning_rate": 4.7208756269825104e-05,
+      "loss": 0.3477,
+      "num_input_tokens_seen": 6748448,
+      "step": 164
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.440924733877182,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.3214,
+      "num_input_tokens_seen": 6777264,
+      "step": 165
+    },
+    {
+      "epoch": 3.018348623853211,
+      "grad_norm": 0.27583903074264526,
+      "learning_rate": 4.714159775105765e-05,
+      "loss": 0.2681,
+      "num_input_tokens_seen": 6809456,
+      "step": 166
+    },
+    {
+      "epoch": 3.036697247706422,
+      "grad_norm": 0.2995987832546234,
+      "learning_rate": 4.7107737319559176e-05,
+      "loss": 0.2633,
+      "num_input_tokens_seen": 6845768,
+      "step": 167
+    },
+    {
+      "epoch": 3.055045871559633,
+      "grad_norm": 0.23999951779842377,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.1961,
+      "num_input_tokens_seen": 6893056,
+      "step": 168
+    },
+    {
+      "epoch": 3.073394495412844,
+      "grad_norm": 0.23356525599956512,
+      "learning_rate": 4.703945554489558e-05,
+      "loss": 0.2836,
+      "num_input_tokens_seen": 6932480,
+      "step": 169
+    },
+    {
+      "epoch": 3.091743119266055,
+      "grad_norm": 0.29919493198394775,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.2838,
+      "num_input_tokens_seen": 6975992,
+      "step": 170
+    },
+    {
+      "epoch": 3.1100917431192663,
+      "grad_norm": 0.3350690007209778,
+      "learning_rate": 4.697042781654913e-05,
+      "loss": 0.3489,
+      "num_input_tokens_seen": 7021840,
+      "step": 171
+    },
+    {
+      "epoch": 3.128440366972477,
+      "grad_norm": 0.2837466895580292,
+      "learning_rate": 4.693563494886455e-05,
+      "loss": 0.3797,
+      "num_input_tokens_seen": 7065192,
+      "step": 172
+    },
+    {
+      "epoch": 3.146788990825688,
+      "grad_norm": 0.24601787328720093,
+      "learning_rate": 4.6900656470851964e-05,
+      "loss": 0.2046,
+      "num_input_tokens_seen": 7114544,
+      "step": 173
+    },
+    {
+      "epoch": 3.165137614678899,
+      "grad_norm": 0.32290250062942505,
+      "learning_rate": 4.6865492678484895e-05,
+      "loss": 0.2596,
+      "num_input_tokens_seen": 7152736,
+      "step": 174
+    },
+    {
+      "epoch": 3.18348623853211,
+      "grad_norm": 0.33591920137405396,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 7207464,
+      "step": 175
+    },
+    {
+      "epoch": 3.2018348623853212,
+      "grad_norm": 0.25471043586730957,
+      "learning_rate": 4.679461034241906e-05,
+      "loss": 0.2096,
+      "num_input_tokens_seen": 7238640,
+      "step": 176
+    },
+    {
+      "epoch": 3.220183486238532,
+      "grad_norm": 0.31238994002342224,
+      "learning_rate": 4.6758892398497494e-05,
+      "loss": 0.2226,
+      "num_input_tokens_seen": 7279112,
+      "step": 177
+    },
+    {
+      "epoch": 3.238532110091743,
+      "grad_norm": 0.35679712891578674,
+      "learning_rate": 4.672299033977076e-05,
+      "loss": 0.2403,
+      "num_input_tokens_seen": 7311632,
+      "step": 178
+    },
+    {
+      "epoch": 3.2568807339449544,
+      "grad_norm": 0.326914519071579,
+      "learning_rate": 4.6686904470027316e-05,
+      "loss": 0.2156,
+      "num_input_tokens_seen": 7344864,
+      "step": 179
+    },
+    {
+      "epoch": 3.2752293577981653,
+      "grad_norm": 0.3293381929397583,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.238,
+      "num_input_tokens_seen": 7389944,
+      "step": 180
+    },
+    {
+      "epoch": 3.293577981651376,
+      "grad_norm": 0.3313307762145996,
+      "learning_rate": 4.661418252041827e-05,
+      "loss": 0.2251,
+      "num_input_tokens_seen": 7423672,
+      "step": 181
+    },
+    {
+      "epoch": 3.311926605504587,
+      "grad_norm": 0.3328595459461212,
+      "learning_rate": 4.657754705589591e-05,
+      "loss": 0.2922,
+      "num_input_tokens_seen": 7459576,
+      "step": 182
+    },
+    {
+      "epoch": 3.330275229357798,
+      "grad_norm": 0.2721710801124573,
+      "learning_rate": 4.6540729011038146e-05,
+      "loss": 0.2698,
+      "num_input_tokens_seen": 7511736,
+      "step": 183
+    },
+    {
+      "epoch": 3.3486238532110093,
+      "grad_norm": 0.2488890290260315,
+      "learning_rate": 4.650372869738414e-05,
+      "loss": 0.173,
+      "num_input_tokens_seen": 7558552,
+      "step": 184
+    },
+    {
+      "epoch": 3.36697247706422,
+      "grad_norm": 0.3800615668296814,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.32,
+      "num_input_tokens_seen": 7599040,
+      "step": 185
+    },
+    {
+      "epoch": 3.385321100917431,
+      "grad_norm": 0.3377014100551605,
+      "learning_rate": 4.642918251755281e-05,
+      "loss": 0.3058,
+      "num_input_tokens_seen": 7653264,
+      "step": 186
+    },
+    {
+      "epoch": 3.4036697247706424,
+      "grad_norm": 0.25239789485931396,
+      "learning_rate": 4.639163728215463e-05,
+      "loss": 0.1896,
+      "num_input_tokens_seen": 7694272,
+      "step": 187
+    },
+    {
+      "epoch": 3.4220183486238533,
+      "grad_norm": 0.34607502818107605,
+      "learning_rate": 4.6353911039513145e-05,
+      "loss": 0.2933,
+      "num_input_tokens_seen": 7730848,
+      "step": 188
+    },
+    {
+      "epoch": 3.4403669724770642,
+      "grad_norm": 0.30653324723243713,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.2625,
+      "num_input_tokens_seen": 7781200,
+      "step": 189
+    },
+    {
+      "epoch": 3.458715596330275,
+      "grad_norm": 0.2943236231803894,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.3372,
+      "num_input_tokens_seen": 7825032,
+      "step": 190
+    },
+    {
+      "epoch": 3.477064220183486,
+      "grad_norm": 0.30080685019493103,
+      "learning_rate": 4.623964946801027e-05,
+      "loss": 0.2229,
+      "num_input_tokens_seen": 7855840,
+      "step": 191
+    },
+    {
+      "epoch": 3.4954128440366974,
+      "grad_norm": 0.3511403799057007,
+      "learning_rate": 4.620120240391065e-05,
+      "loss": 0.3967,
+      "num_input_tokens_seen": 7905928,
+      "step": 192
+    },
+    {
+      "epoch": 3.5137614678899083,
+      "grad_norm": 0.273583322763443,
+      "learning_rate": 4.61625759439494e-05,
+      "loss": 0.2254,
+      "num_input_tokens_seen": 7955992,
+      "step": 193
+    },
+    {
+      "epoch": 3.532110091743119,
+      "grad_norm": 0.3457902669906616,
+      "learning_rate": 4.612377041496776e-05,
+      "loss": 0.2553,
+      "num_input_tokens_seen": 7998024,
+      "step": 194
+    },
+    {
+      "epoch": 3.5504587155963305,
+      "grad_norm": 0.31968954205513,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.2197,
+      "num_input_tokens_seen": 8055672,
+      "step": 195
+    },
+    {
+      "epoch": 3.5688073394495414,
+      "grad_norm": 0.34753403067588806,
+      "learning_rate": 4.604562346488144e-05,
+      "loss": 0.2507,
+      "num_input_tokens_seen": 8090848,
+      "step": 196
+    },
+    {
+      "epoch": 3.5871559633027523,
+      "grad_norm": 0.3808669149875641,
+      "learning_rate": 4.6006282705024144e-05,
+      "loss": 0.2422,
+      "num_input_tokens_seen": 8136680,
+      "step": 197
+    },
+    {
+      "epoch": 3.6055045871559632,
+      "grad_norm": 0.3004499673843384,
+      "learning_rate": 4.5966764198635606e-05,
+      "loss": 0.2107,
+      "num_input_tokens_seen": 8187472,
+      "step": 198
+    },
+    {
+      "epoch": 3.623853211009174,
+      "grad_norm": 0.30718186497688293,
+      "learning_rate": 4.592706828010518e-05,
+      "loss": 0.1854,
+      "num_input_tokens_seen": 8225216,
+      "step": 199
+    },
+    {
+      "epoch": 3.6422018348623855,
+      "grad_norm": 0.23112858831882477,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.1687,
+      "num_input_tokens_seen": 8274456,
+      "step": 200
+    },
+    {
+      "epoch": 3.6605504587155964,
+      "grad_norm": 0.25966888666152954,
+      "learning_rate": 4.5847145551679206e-05,
+      "loss": 0.2549,
+      "num_input_tokens_seen": 8317016,
+      "step": 201
+    },
+    {
+      "epoch": 3.6788990825688073,
+      "grad_norm": 0.25600987672805786,
+      "learning_rate": 4.580691941805695e-05,
+      "loss": 0.1602,
+      "num_input_tokens_seen": 8361856,
+      "step": 202
+    },
+    {
+      "epoch": 3.6972477064220186,
+      "grad_norm": 0.33986184000968933,
+      "learning_rate": 4.5766517224833637e-05,
+      "loss": 0.2495,
+      "num_input_tokens_seen": 8410696,
+      "step": 203
+    },
+    {
+      "epoch": 3.7155963302752295,
+      "grad_norm": 0.36899781227111816,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.2012,
+      "num_input_tokens_seen": 8441872,
+      "step": 204
+    },
+    {
+      "epoch": 3.7339449541284404,
+      "grad_norm": 0.42072632908821106,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 8482544,
+      "step": 205
+    },
+    {
+      "epoch": 3.7522935779816513,
+      "grad_norm": 0.40593233704566956,
+      "learning_rate": 4.5644257713656356e-05,
+      "loss": 0.233,
+      "num_input_tokens_seen": 8519856,
+      "step": 206
+    },
+    {
+      "epoch": 3.770642201834862,
+      "grad_norm": 0.38003161549568176,
+      "learning_rate": 4.5603154715550386e-05,
+      "loss": 0.225,
+      "num_input_tokens_seen": 8551392,
+      "step": 207
+    },
+    {
+      "epoch": 3.7889908256880735,
+      "grad_norm": 0.2564244568347931,
+      "learning_rate": 4.556187738201656e-05,
+      "loss": 0.2975,
+      "num_input_tokens_seen": 8599472,
+      "step": 208
+    },
+    {
+      "epoch": 3.8073394495412844,
+      "grad_norm": 0.29023391008377075,
+      "learning_rate": 4.552042606232668e-05,
+      "loss": 0.2033,
+      "num_input_tokens_seen": 8631880,
+      "step": 209
+    },
+    {
+      "epoch": 3.8256880733944953,
+      "grad_norm": 0.32886001467704773,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.2024,
+      "num_input_tokens_seen": 8675016,
+      "step": 210
+    },
+    {
+      "epoch": 3.8440366972477067,
+      "grad_norm": 0.36749884486198425,
+      "learning_rate": 4.5437002868924166e-05,
+      "loss": 0.2304,
+      "num_input_tokens_seen": 8713248,
+      "step": 211
+    },
+    {
+      "epoch": 3.8623853211009176,
+      "grad_norm": 0.3055097758769989,
+      "learning_rate": 4.539503170110431e-05,
+      "loss": 0.2928,
+      "num_input_tokens_seen": 8748800,
+      "step": 212
+    },
+    {
+      "epoch": 3.8807339449541285,
+      "grad_norm": 0.38436686992645264,
+      "learning_rate": 4.535288795890798e-05,
+      "loss": 0.2214,
+      "num_input_tokens_seen": 8787832,
+      "step": 213
+    },
+    {
+      "epoch": 3.8990825688073394,
+      "grad_norm": 0.44330883026123047,
+      "learning_rate": 4.531057199893824e-05,
+      "loss": 0.2168,
+      "num_input_tokens_seen": 8819616,
+      "step": 214
+    },
+    {
+      "epoch": 3.9174311926605503,
+      "grad_norm": 0.28318527340888977,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.279,
+      "num_input_tokens_seen": 8860744,
+      "step": 215
+    },
+    {
+      "epoch": 3.9357798165137616,
+      "grad_norm": 0.3287319839000702,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.2597,
+      "num_input_tokens_seen": 8906432,
+      "step": 216
+    },
+    {
+      "epoch": 3.9541284403669725,
+      "grad_norm": 0.35815751552581787,
+      "learning_rate": 4.5182594400259e-05,
+      "loss": 0.241,
+      "num_input_tokens_seen": 8955104,
+      "step": 217
+    },
+    {
+      "epoch": 3.9724770642201834,
+      "grad_norm": 0.3299608528614044,
+      "learning_rate": 4.5139593164324986e-05,
+      "loss": 0.2157,
+      "num_input_tokens_seen": 8990200,
+      "step": 218
+    },
+    {
+      "epoch": 3.9908256880733948,
+      "grad_norm": 0.2916093170642853,
+      "learning_rate": 4.509642151543043e-05,
+      "loss": 0.2046,
+      "num_input_tokens_seen": 9020760,
+      "step": 219
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.40076637268066406,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.1714,
+      "num_input_tokens_seen": 9036352,
+      "step": 220
+    },
+    {
+      "epoch": 4.018348623853211,
+      "grad_norm": 0.40515249967575073,
+      "learning_rate": 4.50095684414016e-05,
+      "loss": 0.1811,
+      "num_input_tokens_seen": 9091776,
+      "step": 221
+    },
+    {
+      "epoch": 4.036697247706422,
+      "grad_norm": 0.32984718680381775,
+      "learning_rate": 4.496588775118232e-05,
+      "loss": 0.2101,
+      "num_input_tokens_seen": 9134080,
+      "step": 222
+    },
+    {
+      "epoch": 4.055045871559633,
+      "grad_norm": 0.27288541197776794,
+      "learning_rate": 4.4922038117826334e-05,
+      "loss": 0.1444,
+      "num_input_tokens_seen": 9172720,
+      "step": 223
+    },
+    {
+      "epoch": 4.073394495412844,
+      "grad_norm": 0.5168021321296692,
+      "learning_rate": 4.48780199123712e-05,
+      "loss": 0.2342,
+      "num_input_tokens_seen": 9213664,
+      "step": 224
+    },
+    {
+      "epoch": 4.091743119266055,
+      "grad_norm": 0.3986498713493347,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.1676,
+      "num_input_tokens_seen": 9261768,
+      "step": 225
+    },
+    {
+      "epoch": 4.110091743119266,
+      "grad_norm": 0.4472793936729431,
+      "learning_rate": 4.478947927644258e-05,
+      "loss": 0.295,
+      "num_input_tokens_seen": 9300928,
+      "step": 226
+    },
+    {
+      "epoch": 4.128440366972477,
+      "grad_norm": 0.39240705966949463,
+      "learning_rate": 4.474495759516358e-05,
+      "loss": 0.17,
+      "num_input_tokens_seen": 9329472,
+      "step": 227
+    },
+    {
+      "epoch": 4.146788990825688,
+      "grad_norm": 0.354526549577713,
+      "learning_rate": 4.4700268840168045e-05,
+      "loss": 0.1759,
+      "num_input_tokens_seen": 9365640,
+      "step": 228
+    },
+    {
+      "epoch": 4.165137614678899,
+      "grad_norm": 0.3216766119003296,
+      "learning_rate": 4.4655413389593856e-05,
+      "loss": 0.1878,
+      "num_input_tokens_seen": 9410552,
+      "step": 229
+    },
+    {
+      "epoch": 4.18348623853211,
+      "grad_norm": 0.30976617336273193,
+      "learning_rate": 4.4610391622989396e-05,
+      "loss": 0.1637,
+      "num_input_tokens_seen": 9452416,
+      "step": 230
+    },
+    {
+      "epoch": 4.201834862385321,
+      "grad_norm": 0.385437935590744,
+      "learning_rate": 4.456520392131035e-05,
+      "loss": 0.2748,
+      "num_input_tokens_seen": 9503528,
+      "step": 231
+    },
+    {
+      "epoch": 4.220183486238533,
+      "grad_norm": 0.37948480248451233,
+      "learning_rate": 4.4519850666916484e-05,
+      "loss": 0.2635,
+      "num_input_tokens_seen": 9541592,
+      "step": 232
+    },
+    {
+      "epoch": 4.238532110091743,
+      "grad_norm": 0.36141568422317505,
+      "learning_rate": 4.447433224356839e-05,
+      "loss": 0.2027,
+      "num_input_tokens_seen": 9586064,
+      "step": 233
+    },
+    {
+      "epoch": 4.256880733944954,
+      "grad_norm": 0.4549350440502167,
+      "learning_rate": 4.442864903642428e-05,
+      "loss": 0.2107,
+      "num_input_tokens_seen": 9641688,
+      "step": 234
+    },
+    {
+      "epoch": 4.275229357798165,
+      "grad_norm": 0.3979765474796295,
+      "learning_rate": 4.438280143203665e-05,
+      "loss": 0.2879,
+      "num_input_tokens_seen": 9686240,
+      "step": 235
+    },
+    {
+      "epoch": 4.293577981651376,
+      "grad_norm": 0.35011065006256104,
+      "learning_rate": 4.43367898183491e-05,
+      "loss": 0.2594,
+      "num_input_tokens_seen": 9735632,
+      "step": 236
+    },
+    {
+      "epoch": 4.3119266055045875,
+      "grad_norm": 0.3999224007129669,
+      "learning_rate": 4.4290614584693004e-05,
+      "loss": 0.1907,
+      "num_input_tokens_seen": 9766536,
+      "step": 237
+    },
+    {
+      "epoch": 4.330275229357798,
+      "grad_norm": 0.39629611372947693,
+      "learning_rate": 4.4244276121784195e-05,
+      "loss": 0.1805,
+      "num_input_tokens_seen": 9796400,
+      "step": 238
+    },
+    {
+      "epoch": 4.348623853211009,
+      "grad_norm": 0.36784592270851135,
+      "learning_rate": 4.4197774821719714e-05,
+      "loss": 0.1824,
+      "num_input_tokens_seen": 9831992,
+      "step": 239
+    },
+    {
+      "epoch": 4.36697247706422,
+      "grad_norm": 0.3408430516719818,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.1721,
+      "num_input_tokens_seen": 9875640,
+      "step": 240
+    },
+    {
+      "epoch": 4.385321100917431,
+      "grad_norm": 0.3232553005218506,
+      "learning_rate": 4.410428528539783e-05,
+      "loss": 0.275,
+      "num_input_tokens_seen": 9916816,
+      "step": 241
+    },
+    {
+      "epoch": 4.4036697247706424,
+      "grad_norm": 0.38150206208229065,
+      "learning_rate": 4.405729784021046e-05,
+      "loss": 0.1963,
+      "num_input_tokens_seen": 9962928,
+      "step": 242
+    },
+    {
+      "epoch": 4.422018348623853,
+      "grad_norm": 0.4176963269710541,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.1626,
+      "num_input_tokens_seen": 9997224,
+      "step": 243
+    },
+    {
+      "epoch": 4.440366972477064,
+      "grad_norm": 0.38855600357055664,
+      "learning_rate": 4.396283958372173e-05,
+      "loss": 0.1733,
+      "num_input_tokens_seen": 10036248,
+      "step": 244
+    },
+    {
+      "epoch": 4.458715596330276,
+      "grad_norm": 0.3860638737678528,
+      "learning_rate": 4.391536957168733e-05,
+      "loss": 0.1936,
+      "num_input_tokens_seen": 10070312,
+      "step": 245
+    },
+    {
+      "epoch": 4.477064220183486,
+      "grad_norm": 0.31510865688323975,
+      "learning_rate": 4.386773950556931e-05,
+      "loss": 0.1847,
+      "num_input_tokens_seen": 10114568,
+      "step": 246
+    },
+    {
+      "epoch": 4.495412844036697,
+      "grad_norm": 0.3280925154685974,
+      "learning_rate": 4.381994978839371e-05,
+      "loss": 0.1981,
+      "num_input_tokens_seen": 10150280,
+      "step": 247
+    },
+    {
+      "epoch": 4.513761467889909,
+      "grad_norm": 0.33136090636253357,
+      "learning_rate": 4.377200082453749e-05,
+      "loss": 0.1681,
+      "num_input_tokens_seen": 10194000,
+      "step": 248
+    },
+    {
+      "epoch": 4.532110091743119,
+      "grad_norm": 0.43955501914024353,
+      "learning_rate": 4.372389301972506e-05,
+      "loss": 0.2111,
+      "num_input_tokens_seen": 10232264,
+      "step": 249
+    },
+    {
+      "epoch": 4.5504587155963305,
+      "grad_norm": 0.28938886523246765,
+      "learning_rate": 4.36756267810249e-05,
+      "loss": 0.2307,
+      "num_input_tokens_seen": 10271880,
+      "step": 250
+    },
+    {
+      "epoch": 4.568807339449541,
+      "grad_norm": 0.37232765555381775,
+      "learning_rate": 4.36272025168461e-05,
+      "loss": 0.1609,
+      "num_input_tokens_seen": 10317720,
+      "step": 251
+    },
+    {
+      "epoch": 4.587155963302752,
+      "grad_norm": 0.6248548030853271,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.2456,
+      "num_input_tokens_seen": 10362168,
+      "step": 252
+    },
+    {
+      "epoch": 4.605504587155964,
+      "grad_norm": 0.32828131318092346,
+      "learning_rate": 4.3529881552371096e-05,
+      "loss": 0.3159,
+      "num_input_tokens_seen": 10414312,
+      "step": 253
+    },
+    {
+      "epoch": 4.623853211009174,
+      "grad_norm": 0.4158332049846649,
+      "learning_rate": 4.34809856755649e-05,
+      "loss": 0.2194,
+      "num_input_tokens_seen": 10451800,
+      "step": 254
+    },
+    {
+      "epoch": 4.6422018348623855,
+      "grad_norm": 0.3648194670677185,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.1846,
+      "num_input_tokens_seen": 10496224,
+      "step": 255
+    },
+    {
+      "epoch": 4.660550458715596,
+      "grad_norm": 0.36835575103759766,
+      "learning_rate": 4.3382725201495723e-05,
+      "loss": 0.1906,
+      "num_input_tokens_seen": 10536392,
+      "step": 256
+    },
+    {
+      "epoch": 4.678899082568807,
+      "grad_norm": 0.3501613140106201,
+      "learning_rate": 4.333336143567247e-05,
+      "loss": 0.1793,
+      "num_input_tokens_seen": 10577640,
+      "step": 257
+    },
+    {
+      "epoch": 4.697247706422019,
+      "grad_norm": 0.3431616425514221,
+      "learning_rate": 4.3283842540479264e-05,
+      "loss": 0.1576,
+      "num_input_tokens_seen": 10613376,
+      "step": 258
+    },
+    {
+      "epoch": 4.715596330275229,
+      "grad_norm": 0.3290237784385681,
+      "learning_rate": 4.3234168934924636e-05,
+      "loss": 0.1447,
+      "num_input_tokens_seen": 10647232,
+      "step": 259
+    },
+    {
+      "epoch": 4.73394495412844,
+      "grad_norm": 0.40264153480529785,
+      "learning_rate": 4.318434103932622e-05,
+      "loss": 0.1488,
+      "num_input_tokens_seen": 10696024,
+      "step": 260
+    },
+    {
+      "epoch": 4.752293577981652,
+      "grad_norm": 0.3453703820705414,
+      "learning_rate": 4.313435927530719e-05,
+      "loss": 0.1597,
+      "num_input_tokens_seen": 10730408,
+      "step": 261
+    },
+    {
+      "epoch": 4.770642201834862,
+      "grad_norm": 0.3993653655052185,
+      "learning_rate": 4.30842240657927e-05,
+      "loss": 0.2266,
+      "num_input_tokens_seen": 10764776,
+      "step": 262
+    },
+    {
+      "epoch": 4.7889908256880735,
+      "grad_norm": 0.4080798923969269,
+      "learning_rate": 4.303393583500628e-05,
+      "loss": 0.1562,
+      "num_input_tokens_seen": 10792272,
+      "step": 263
+    },
+    {
+      "epoch": 4.807339449541285,
+      "grad_norm": 0.3028413951396942,
+      "learning_rate": 4.2983495008466276e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 10825240,
+      "step": 264
+    },
+    {
+      "epoch": 4.825688073394495,
+      "grad_norm": 0.3980019688606262,
+      "learning_rate": 4.293290201298223e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 10883592,
+      "step": 265
+    },
+    {
+      "epoch": 4.844036697247707,
+      "grad_norm": 0.42035797238349915,
+      "learning_rate": 4.288215727665129e-05,
+      "loss": 0.1652,
+      "num_input_tokens_seen": 10922640,
+      "step": 266
+    },
+    {
+      "epoch": 4.862385321100917,
+      "grad_norm": 0.37766003608703613,
+      "learning_rate": 4.2831261228854544e-05,
+      "loss": 0.1817,
+      "num_input_tokens_seen": 10967288,
+      "step": 267
+    },
+    {
+      "epoch": 4.8807339449541285,
+      "grad_norm": 0.3495088815689087,
+      "learning_rate": 4.278021430025343e-05,
+      "loss": 0.2066,
+      "num_input_tokens_seen": 11011152,
+      "step": 268
+    },
+    {
+      "epoch": 4.89908256880734,
+      "grad_norm": 0.34071093797683716,
+      "learning_rate": 4.272901692278609e-05,
+      "loss": 0.1522,
+      "num_input_tokens_seen": 11055608,
+      "step": 269
+    },
+    {
+      "epoch": 4.91743119266055,
+      "grad_norm": 0.33437398076057434,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 11101992,
+      "step": 270
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1080,
+  "num_input_tokens_seen": 11101992,
+  "num_train_epochs": 20,
+  "save_steps": 54,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.365826174514627e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}