Add files using upload-large-folder tool

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: test
+  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. -->
+
+# test
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the eco-gotest-training 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: 16
+- total_train_batch_size: 32
+- 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
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- 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-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_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 +1,8 @@
+{
+    "epoch": 19.681204569055037,
+    "total_flos": 5.17534376829911e+16,
+    "train_loss": 0.5945307578643163,
+    "train_runtime": 10002.7859,
+    "train_samples_per_second": 3.849,
+    "train_steps_per_second": 0.12
+}

checkpoint-1020/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-1020/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1020/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-1020/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-1020/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1020/trainer_state.json

@@ -0,0 +1,1461 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.73104880581516,
+  "eval_steps": 500,
+  "global_step": 1020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.6620935797691345,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.985,
+      "step": 125
+    },
+    {
+      "epoch": 2.132917964693666,
+      "grad_norm": 0.7846258878707886,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.9594,
+      "step": 130
+    },
+    {
+      "epoch": 2.2159916926272065,
+      "grad_norm": 0.652454137802124,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.9322,
+      "step": 135
+    },
+    {
+      "epoch": 2.2990654205607477,
+      "grad_norm": 0.7020059823989868,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.9242,
+      "step": 140
+    },
+    {
+      "epoch": 2.382139148494289,
+      "grad_norm": 0.8148695826530457,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.8394,
+      "step": 145
+    },
+    {
+      "epoch": 2.4652128764278296,
+      "grad_norm": 0.8813133835792542,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.992,
+      "step": 150
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 0.7893730401992798,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.899,
+      "step": 155
+    },
+    {
+      "epoch": 2.6313603322949115,
+      "grad_norm": 0.7719221711158752,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.9416,
+      "step": 160
+    },
+    {
+      "epoch": 2.7144340602284527,
+      "grad_norm": 0.8439667820930481,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.8401,
+      "step": 165
+    },
+    {
+      "epoch": 2.797507788161994,
+      "grad_norm": 0.833251953125,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.817,
+      "step": 170
+    },
+    {
+      "epoch": 2.8805815160955346,
+      "grad_norm": 0.7526916265487671,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.8191,
+      "step": 175
+    },
+    {
+      "epoch": 2.9636552440290758,
+      "grad_norm": 1.0640058517456055,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8607,
+      "step": 180
+    },
+    {
+      "epoch": 3.0332294911734166,
+      "grad_norm": 0.784114420413971,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.761,
+      "step": 185
+    },
+    {
+      "epoch": 3.1163032191069573,
+      "grad_norm": 0.9396352767944336,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.6821,
+      "step": 190
+    },
+    {
+      "epoch": 3.1993769470404985,
+      "grad_norm": 0.9770582914352417,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.742,
+      "step": 195
+    },
+    {
+      "epoch": 3.2824506749740396,
+      "grad_norm": 0.8752853870391846,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.69,
+      "step": 200
+    },
+    {
+      "epoch": 3.3655244029075804,
+      "grad_norm": 0.8496589064598083,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.769,
+      "step": 205
+    },
+    {
+      "epoch": 3.4485981308411215,
+      "grad_norm": 0.8192639350891113,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.7298,
+      "step": 210
+    },
+    {
+      "epoch": 3.5316718587746623,
+      "grad_norm": 1.00070059299469,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.7815,
+      "step": 215
+    },
+    {
+      "epoch": 3.6147455867082035,
+      "grad_norm": 1.1614112854003906,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.7975,
+      "step": 220
+    },
+    {
+      "epoch": 3.6978193146417446,
+      "grad_norm": 1.014397382736206,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 3.7808930425752854,
+      "grad_norm": 0.9468530416488647,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.7194,
+      "step": 230
+    },
+    {
+      "epoch": 3.8639667705088265,
+      "grad_norm": 1.2201341390609741,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.7795,
+      "step": 235
+    },
+    {
+      "epoch": 3.9470404984423677,
+      "grad_norm": 0.9476346373558044,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.7202,
+      "step": 240
+    },
+    {
+      "epoch": 4.0166147455867085,
+      "grad_norm": 0.9945451021194458,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.6931,
+      "step": 245
+    },
+    {
+      "epoch": 4.099688473520249,
+      "grad_norm": 1.1113696098327637,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.6557,
+      "step": 250
+    },
+    {
+      "epoch": 4.18276220145379,
+      "grad_norm": 1.3515146970748901,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.6295,
+      "step": 255
+    },
+    {
+      "epoch": 4.265835929387332,
+      "grad_norm": 1.375272274017334,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.6423,
+      "step": 260
+    },
+    {
+      "epoch": 4.348909657320872,
+      "grad_norm": 1.1683202981948853,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.6167,
+      "step": 265
+    },
+    {
+      "epoch": 4.431983385254413,
+      "grad_norm": 1.2091785669326782,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.6373,
+      "step": 270
+    },
+    {
+      "epoch": 4.515057113187955,
+      "grad_norm": 1.3007235527038574,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.5941,
+      "step": 275
+    },
+    {
+      "epoch": 4.598130841121495,
+      "grad_norm": 1.2785530090332031,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.6384,
+      "step": 280
+    },
+    {
+      "epoch": 4.681204569055036,
+      "grad_norm": 1.2808083295822144,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.6592,
+      "step": 285
+    },
+    {
+      "epoch": 4.764278296988578,
+      "grad_norm": 1.1978651285171509,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.6285,
+      "step": 290
+    },
+    {
+      "epoch": 4.8473520249221185,
+      "grad_norm": 1.3983532190322876,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.5941,
+      "step": 295
+    },
+    {
+      "epoch": 4.930425752855659,
+      "grad_norm": 1.286287784576416,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5652,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1714959144592285,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.5657,
+      "step": 305
+    },
+    {
+      "epoch": 5.083073727933541,
+      "grad_norm": 1.0886554718017578,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.4776,
+      "step": 310
+    },
+    {
+      "epoch": 5.166147455867082,
+      "grad_norm": 1.3735958337783813,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.5114,
+      "step": 315
+    },
+    {
+      "epoch": 5.249221183800623,
+      "grad_norm": 1.5809016227722168,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.5537,
+      "step": 320
+    },
+    {
+      "epoch": 5.332294911734164,
+      "grad_norm": 1.401424765586853,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.5299,
+      "step": 325
+    },
+    {
+      "epoch": 5.415368639667705,
+      "grad_norm": 1.467054009437561,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.5236,
+      "step": 330
+    },
+    {
+      "epoch": 5.498442367601246,
+      "grad_norm": 1.253794550895691,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.5632,
+      "step": 335
+    },
+    {
+      "epoch": 5.581516095534787,
+      "grad_norm": 1.4579623937606812,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.5556,
+      "step": 340
+    },
+    {
+      "epoch": 5.6645898234683285,
+      "grad_norm": 1.171007513999939,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.4934,
+      "step": 345
+    },
+    {
+      "epoch": 5.747663551401869,
+      "grad_norm": 1.4656859636306763,
+      "learning_rate": 4.4610391622989396e-05,
+      "loss": 0.5697,
+      "step": 350
+    },
+    {
+      "epoch": 5.83073727933541,
+      "grad_norm": 1.4671518802642822,
+      "learning_rate": 4.438280143203665e-05,
+      "loss": 0.5289,
+      "step": 355
+    },
+    {
+      "epoch": 5.913811007268951,
+      "grad_norm": 1.4010504484176636,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5205,
+      "step": 360
+    },
+    {
+      "epoch": 5.996884735202492,
+      "grad_norm": 1.6909047365188599,
+      "learning_rate": 4.391536957168733e-05,
+      "loss": 0.5469,
+      "step": 365
+    },
+    {
+      "epoch": 6.066458982346833,
+      "grad_norm": 1.3057804107666016,
+      "learning_rate": 4.36756267810249e-05,
+      "loss": 0.5087,
+      "step": 370
+    },
+    {
+      "epoch": 6.149532710280374,
+      "grad_norm": 1.7389354705810547,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.446,
+      "step": 375
+    },
+    {
+      "epoch": 6.232606438213915,
+      "grad_norm": 1.6178336143493652,
+      "learning_rate": 4.318434103932622e-05,
+      "loss": 0.4888,
+      "step": 380
+    },
+    {
+      "epoch": 6.315680166147456,
+      "grad_norm": 1.6565852165222168,
+      "learning_rate": 4.293290201298223e-05,
+      "loss": 0.4784,
+      "step": 385
+    },
+    {
+      "epoch": 6.398753894080997,
+      "grad_norm": 1.4080264568328857,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.4155,
+      "step": 390
+    },
+    {
+      "epoch": 6.481827622014538,
+      "grad_norm": 1.4906692504882812,
+      "learning_rate": 4.241869758026638e-05,
+      "loss": 0.4854,
+      "step": 395
+    },
+    {
+      "epoch": 6.564901349948079,
+      "grad_norm": 1.6544594764709473,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.4753,
+      "step": 400
+    },
+    {
+      "epoch": 6.64797507788162,
+      "grad_norm": 1.3182097673416138,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.4352,
+      "step": 405
+    },
+    {
+      "epoch": 6.731048805815161,
+      "grad_norm": 1.531633734703064,
+      "learning_rate": 4.1619896640348445e-05,
+      "loss": 0.4786,
+      "step": 410
+    },
+    {
+      "epoch": 6.814122533748702,
+      "grad_norm": 1.358223557472229,
+      "learning_rate": 4.1346522381426744e-05,
+      "loss": 0.4108,
+      "step": 415
+    },
+    {
+      "epoch": 6.897196261682243,
+      "grad_norm": 1.6483898162841797,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4828,
+      "step": 420
+    },
+    {
+      "epoch": 6.980269989615784,
+      "grad_norm": 1.5941141843795776,
+      "learning_rate": 4.078945878256244e-05,
+      "loss": 0.4276,
+      "step": 425
+    },
+    {
+      "epoch": 7.049844236760125,
+      "grad_norm": 1.367634892463684,
+      "learning_rate": 4.05058872817065e-05,
+      "loss": 0.3997,
+      "step": 430
+    },
+    {
+      "epoch": 7.132917964693665,
+      "grad_norm": 1.3028111457824707,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.3919,
+      "step": 435
+    },
+    {
+      "epoch": 7.215991692627207,
+      "grad_norm": 1.8897424936294556,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.3778,
+      "step": 440
+    },
+    {
+      "epoch": 7.299065420560748,
+      "grad_norm": 1.6549698114395142,
+      "learning_rate": 3.963573584424852e-05,
+      "loss": 0.408,
+      "step": 445
+    },
+    {
+      "epoch": 7.382139148494288,
+      "grad_norm": 1.3696308135986328,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.4262,
+      "step": 450
+    },
+    {
+      "epoch": 7.46521287642783,
+      "grad_norm": 1.6997928619384766,
+      "learning_rate": 3.9040052669587325e-05,
+      "loss": 0.3982,
+      "step": 455
+    },
+    {
+      "epoch": 7.548286604361371,
+      "grad_norm": 1.3938806056976318,
+      "learning_rate": 3.873772445177015e-05,
+      "loss": 0.4113,
+      "step": 460
+    },
+    {
+      "epoch": 7.6313603322949115,
+      "grad_norm": 1.8341262340545654,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.4265,
+      "step": 465
+    },
+    {
+      "epoch": 7.714434060228453,
+      "grad_norm": 1.6543951034545898,
+      "learning_rate": 3.8124414508364e-05,
+      "loss": 0.4112,
+      "step": 470
+    },
+    {
+      "epoch": 7.797507788161994,
+      "grad_norm": 1.5131211280822754,
+      "learning_rate": 3.781356251999663e-05,
+      "loss": 0.4098,
+      "step": 475
+    },
+    {
+      "epoch": 7.880581516095535,
+      "grad_norm": 1.7143309116363525,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4183,
+      "step": 480
+    },
+    {
+      "epoch": 7.963655244029075,
+      "grad_norm": 1.4201680421829224,
+      "learning_rate": 3.718379327818106e-05,
+      "loss": 0.388,
+      "step": 485
+    },
+    {
+      "epoch": 8.033229491173417,
+      "grad_norm": 1.36739182472229,
+      "learning_rate": 3.686500924369101e-05,
+      "loss": 0.3927,
+      "step": 490
+    },
+    {
+      "epoch": 8.116303219106957,
+      "grad_norm": 1.348694086074829,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.3614,
+      "step": 495
+    },
+    {
+      "epoch": 8.199376947040498,
+      "grad_norm": 1.7005705833435059,
+      "learning_rate": 3.621997950501156e-05,
+      "loss": 0.3509,
+      "step": 500
+    },
+    {
+      "epoch": 8.28245067497404,
+      "grad_norm": 1.4668842554092407,
+      "learning_rate": 3.589387024792699e-05,
+      "loss": 0.344,
+      "step": 505
+    },
+    {
+      "epoch": 8.36552440290758,
+      "grad_norm": 1.6029119491577148,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.3599,
+      "step": 510
+    },
+    {
+      "epoch": 8.448598130841122,
+      "grad_norm": 1.5699125528335571,
+      "learning_rate": 3.523480786315231e-05,
+      "loss": 0.3579,
+      "step": 515
+    },
+    {
+      "epoch": 8.531671858774663,
+      "grad_norm": 1.4507211446762085,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3341,
+      "step": 520
+    },
+    {
+      "epoch": 8.614745586708203,
+      "grad_norm": 1.460924744606018,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3762,
+      "step": 525
+    },
+    {
+      "epoch": 8.697819314641745,
+      "grad_norm": 1.6329962015151978,
+      "learning_rate": 3.423015368281711e-05,
+      "loss": 0.3948,
+      "step": 530
+    },
+    {
+      "epoch": 8.780893042575286,
+      "grad_norm": 1.5261616706848145,
+      "learning_rate": 3.389126904537192e-05,
+      "loss": 0.3594,
+      "step": 535
+    },
+    {
+      "epoch": 8.863966770508826,
+      "grad_norm": 1.6733344793319702,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.3856,
+      "step": 540
+    },
+    {
+      "epoch": 8.947040498442368,
+      "grad_norm": 1.4160898923873901,
+      "learning_rate": 3.3207929380339034e-05,
+      "loss": 0.3875,
+      "step": 545
+    },
+    {
+      "epoch": 9.016614745586708,
+      "grad_norm": 1.2456085681915283,
+      "learning_rate": 3.2863618903790346e-05,
+      "loss": 0.3318,
+      "step": 550
+    },
+    {
+      "epoch": 9.09968847352025,
+      "grad_norm": 1.309977650642395,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.3239,
+      "step": 555
+    },
+    {
+      "epoch": 9.18276220145379,
+      "grad_norm": 1.6747145652770996,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.342,
+      "step": 560
+    },
+    {
+      "epoch": 9.26583592938733,
+      "grad_norm": 1.6204376220703125,
+      "learning_rate": 3.182099991668653e-05,
+      "loss": 0.3368,
+      "step": 565
+    },
+    {
+      "epoch": 9.348909657320872,
+      "grad_norm": 1.6952364444732666,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.333,
+      "step": 570
+    },
+    {
+      "epoch": 9.431983385254414,
+      "grad_norm": 1.6254109144210815,
+      "learning_rate": 3.11185835988581e-05,
+      "loss": 0.3488,
+      "step": 575
+    },
+    {
+      "epoch": 9.515057113187954,
+      "grad_norm": 1.7684122323989868,
+      "learning_rate": 3.076539676856101e-05,
+      "loss": 0.3461,
+      "step": 580
+    },
+    {
+      "epoch": 9.598130841121495,
+      "grad_norm": 1.480283260345459,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.3457,
+      "step": 585
+    },
+    {
+      "epoch": 9.681204569055037,
+      "grad_norm": 1.4912574291229248,
+      "learning_rate": 3.0055439308300952e-05,
+      "loss": 0.3307,
+      "step": 590
+    },
+    {
+      "epoch": 9.764278296988577,
+      "grad_norm": 1.5759741067886353,
+      "learning_rate": 2.9698818860002797e-05,
+      "loss": 0.3387,
+      "step": 595
+    },
+    {
+      "epoch": 9.847352024922118,
+      "grad_norm": 1.475316047668457,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.342,
+      "step": 600
+    },
+    {
+      "epoch": 9.93042575285566,
+      "grad_norm": 1.5280460119247437,
+      "learning_rate": 2.898267170168807e-05,
+      "loss": 0.3325,
+      "step": 605
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.123524188995361,
+      "learning_rate": 2.8623296482681166e-05,
+      "loss": 0.3528,
+      "step": 610
+    },
+    {
+      "epoch": 10.083073727933542,
+      "grad_norm": 1.3620072603225708,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.3282,
+      "step": 615
+    },
+    {
+      "epoch": 10.166147455867081,
+      "grad_norm": 1.8294273614883423,
+      "learning_rate": 2.7902322853130757e-05,
+      "loss": 0.3066,
+      "step": 620
+    },
+    {
+      "epoch": 10.249221183800623,
+      "grad_norm": 1.5608752965927124,
+      "learning_rate": 2.7540876954570048e-05,
+      "loss": 0.3033,
+      "step": 625
+    },
+    {
+      "epoch": 10.332294911734165,
+      "grad_norm": 1.7856054306030273,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.2969,
+      "step": 630
+    },
+    {
+      "epoch": 10.415368639667705,
+      "grad_norm": 1.4942408800125122,
+      "learning_rate": 2.681644926806527e-05,
+      "loss": 0.3153,
+      "step": 635
+    },
+    {
+      "epoch": 10.498442367601246,
+      "grad_norm": 1.6234569549560547,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.3277,
+      "step": 640
+    },
+    {
+      "epoch": 10.581516095534788,
+      "grad_norm": 1.6694717407226562,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.3228,
+      "step": 645
+    },
+    {
+      "epoch": 10.664589823468328,
+      "grad_norm": 1.6755950450897217,
+      "learning_rate": 2.5727117968577784e-05,
+      "loss": 0.3316,
+      "step": 650
+    },
+    {
+      "epoch": 10.74766355140187,
+      "grad_norm": 1.3962074518203735,
+      "learning_rate": 2.536359744128957e-05,
+      "loss": 0.3188,
+      "step": 655
+    },
+    {
+      "epoch": 10.83073727933541,
+      "grad_norm": 1.7147635221481323,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3463,
+      "step": 660
+    },
+    {
+      "epoch": 10.91381100726895,
+      "grad_norm": 1.5997766256332397,
+      "learning_rate": 2.4636402558710432e-05,
+      "loss": 0.335,
+      "step": 665
+    },
+    {
+      "epoch": 10.996884735202492,
+      "grad_norm": 1.483155369758606,
+      "learning_rate": 2.4272882031422215e-05,
+      "loss": 0.3084,
+      "step": 670
+    },
+    {
+      "epoch": 11.066458982346832,
+      "grad_norm": 1.3599936962127686,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.311,
+      "step": 675
+    },
+    {
+      "epoch": 11.149532710280374,
+      "grad_norm": 1.5479919910430908,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.2999,
+      "step": 680
+    },
+    {
+      "epoch": 11.232606438213915,
+      "grad_norm": 1.5448635816574097,
+      "learning_rate": 2.3183550731934735e-05,
+      "loss": 0.291,
+      "step": 685
+    },
+    {
+      "epoch": 11.315680166147455,
+      "grad_norm": 1.4930479526519775,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.2879,
+      "step": 690
+    },
+    {
+      "epoch": 11.398753894080997,
+      "grad_norm": 1.578282356262207,
+      "learning_rate": 2.2459123045429954e-05,
+      "loss": 0.3033,
+      "step": 695
+    },
+    {
+      "epoch": 11.481827622014539,
+      "grad_norm": 1.4327830076217651,
+      "learning_rate": 2.2097677146869242e-05,
+      "loss": 0.2946,
+      "step": 700
+    },
+    {
+      "epoch": 11.564901349948078,
+      "grad_norm": 1.75092351436615,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.2965,
+      "step": 705
+    },
+    {
+      "epoch": 11.64797507788162,
+      "grad_norm": 1.4633839130401611,
+      "learning_rate": 2.1376703517318837e-05,
+      "loss": 0.3082,
+      "step": 710
+    },
+    {
+      "epoch": 11.731048805815162,
+      "grad_norm": 1.4483939409255981,
+      "learning_rate": 2.101732829831194e-05,
+      "loss": 0.3048,
+      "step": 715
+    },
+    {
+      "epoch": 11.814122533748701,
+      "grad_norm": 1.4273526668548584,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3093,
+      "step": 720
+    },
+    {
+      "epoch": 11.897196261682243,
+      "grad_norm": 1.536641240119934,
+      "learning_rate": 2.0301181139997205e-05,
+      "loss": 0.3185,
+      "step": 725
+    },
+    {
+      "epoch": 11.980269989615785,
+      "grad_norm": 1.6694177389144897,
+      "learning_rate": 1.9944560691699057e-05,
+      "loss": 0.3197,
+      "step": 730
+    },
+    {
+      "epoch": 12.049844236760125,
+      "grad_norm": 1.5738413333892822,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.3235,
+      "step": 735
+    },
+    {
+      "epoch": 12.132917964693666,
+      "grad_norm": 1.4949880838394165,
+      "learning_rate": 1.9234603231438995e-05,
+      "loss": 0.2752,
+      "step": 740
+    },
+    {
+      "epoch": 12.215991692627206,
+      "grad_norm": 1.7407513856887817,
+      "learning_rate": 1.8881416401141904e-05,
+      "loss": 0.282,
+      "step": 745
+    },
+    {
+      "epoch": 12.299065420560748,
+      "grad_norm": 1.6446201801300049,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.2847,
+      "step": 750
+    },
+    {
+      "epoch": 12.38213914849429,
+      "grad_norm": 1.5613073110580444,
+      "learning_rate": 1.8179000083313483e-05,
+      "loss": 0.2923,
+      "step": 755
+    },
+    {
+      "epoch": 12.46521287642783,
+      "grad_norm": 1.3661807775497437,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.2881,
+      "step": 760
+    },
+    {
+      "epoch": 12.54828660436137,
+      "grad_norm": 1.5903205871582031,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.2897,
+      "step": 765
+    },
+    {
+      "epoch": 12.631360332294912,
+      "grad_norm": 1.5441614389419556,
+      "learning_rate": 1.7136381096209664e-05,
+      "loss": 0.292,
+      "step": 770
+    },
+    {
+      "epoch": 12.714434060228452,
+      "grad_norm": 1.6512565612792969,
+      "learning_rate": 1.6792070619660975e-05,
+      "loss": 0.289,
+      "step": 775
+    },
+    {
+      "epoch": 12.797507788161994,
+      "grad_norm": 1.5514371395111084,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.3012,
+      "step": 780
+    },
+    {
+      "epoch": 12.880581516095535,
+      "grad_norm": 1.7717050313949585,
+      "learning_rate": 1.6108730954628093e-05,
+      "loss": 0.3055,
+      "step": 785
+    },
+    {
+      "epoch": 12.963655244029075,
+      "grad_norm": 1.4902904033660889,
+      "learning_rate": 1.5769846317182893e-05,
+      "loss": 0.2913,
+      "step": 790
+    },
+    {
+      "epoch": 13.033229491173417,
+      "grad_norm": 1.3144031763076782,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.3069,
+      "step": 795
+    },
+    {
+      "epoch": 13.116303219106957,
+      "grad_norm": 1.3925071954727173,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.2701,
+      "step": 800
+    },
+    {
+      "epoch": 13.199376947040498,
+      "grad_norm": 1.7400624752044678,
+      "learning_rate": 1.4765192136847685e-05,
+      "loss": 0.2742,
+      "step": 805
+    },
+    {
+      "epoch": 13.28245067497404,
+      "grad_norm": 1.5998958349227905,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.2778,
+      "step": 810
+    },
+    {
+      "epoch": 13.36552440290758,
+      "grad_norm": 1.7994098663330078,
+      "learning_rate": 1.4106129752073022e-05,
+      "loss": 0.2836,
+      "step": 815
+    },
+    {
+      "epoch": 13.448598130841122,
+      "grad_norm": 1.672831416130066,
+      "learning_rate": 1.3780020494988446e-05,
+      "loss": 0.2709,
+      "step": 820
+    },
+    {
+      "epoch": 13.531671858774663,
+      "grad_norm": 1.7876700162887573,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.2687,
+      "step": 825
+    },
+    {
+      "epoch": 13.614745586708203,
+      "grad_norm": 1.6950455904006958,
+      "learning_rate": 1.313499075630899e-05,
+      "loss": 0.2904,
+      "step": 830
+    },
+    {
+      "epoch": 13.697819314641745,
+      "grad_norm": 1.6819844245910645,
+      "learning_rate": 1.2816206721818944e-05,
+      "loss": 0.2876,
+      "step": 835
+    },
+    {
+      "epoch": 13.780893042575286,
+      "grad_norm": 1.5784549713134766,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.286,
+      "step": 840
+    },
+    {
+      "epoch": 13.863966770508826,
+      "grad_norm": 1.6307650804519653,
+      "learning_rate": 1.2186437480003372e-05,
+      "loss": 0.3009,
+      "step": 845
+    },
+    {
+      "epoch": 13.947040498442368,
+      "grad_norm": 1.4225823879241943,
+      "learning_rate": 1.1875585491636e-05,
+      "loss": 0.2741,
+      "step": 850
+    },
+    {
+      "epoch": 14.016614745586708,
+      "grad_norm": 1.2541974782943726,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.271,
+      "step": 855
+    },
+    {
+      "epoch": 14.09968847352025,
+      "grad_norm": 1.3735196590423584,
+      "learning_rate": 1.126227554822985e-05,
+      "loss": 0.2576,
+      "step": 860
+    },
+    {
+      "epoch": 14.18276220145379,
+      "grad_norm": 1.4082770347595215,
+      "learning_rate": 1.0959947330412682e-05,
+      "loss": 0.2705,
+      "step": 865
+    },
+    {
+      "epoch": 14.26583592938733,
+      "grad_norm": 1.5013236999511719,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.2641,
+      "step": 870
+    },
+    {
+      "epoch": 14.348909657320872,
+      "grad_norm": 1.8321263790130615,
+      "learning_rate": 1.0364264155751488e-05,
+      "loss": 0.2646,
+      "step": 875
+    },
+    {
+      "epoch": 14.431983385254414,
+      "grad_norm": 1.5073516368865967,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.267,
+      "step": 880
+    },
+    {
+      "epoch": 14.515057113187954,
+      "grad_norm": 1.5713279247283936,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.275,
+      "step": 885
+    },
+    {
+      "epoch": 14.598130841121495,
+      "grad_norm": 1.4692318439483643,
+      "learning_rate": 9.494112718293501e-06,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 14.681204569055037,
+      "grad_norm": 1.9062477350234985,
+      "learning_rate": 9.210541217437565e-06,
+      "loss": 0.2703,
+      "step": 895
+    },
+    {
+      "epoch": 14.764278296988577,
+      "grad_norm": 1.4207799434661865,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.2751,
+      "step": 900
+    },
+    {
+      "epoch": 14.847352024922118,
+      "grad_norm": 1.4608951807022095,
+      "learning_rate": 8.65347761857326e-06,
+      "loss": 0.2828,
+      "step": 905
+    },
+    {
+      "epoch": 14.93042575285566,
+      "grad_norm": 1.5288583040237427,
+      "learning_rate": 8.380103359651553e-06,
+      "loss": 0.2739,
+      "step": 910
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.328437328338623,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.2715,
+      "step": 915
+    },
+    {
+      "epoch": 15.083073727933542,
+      "grad_norm": 1.4342622756958008,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.2562,
+      "step": 920
+    },
+    {
+      "epoch": 15.166147455867081,
+      "grad_norm": 1.3755466938018799,
+      "learning_rate": 7.581302419733632e-06,
+      "loss": 0.2488,
+      "step": 925
+    },
+    {
+      "epoch": 15.249221183800623,
+      "grad_norm": 1.6790114641189575,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.2675,
+      "step": 930
+    },
+    {
+      "epoch": 15.332294911734165,
+      "grad_norm": 1.7311410903930664,
+      "learning_rate": 7.067097987017762e-06,
+      "loss": 0.2678,
+      "step": 935
+    },
+    {
+      "epoch": 15.415368639667705,
+      "grad_norm": 1.565371036529541,
+      "learning_rate": 6.815658960673782e-06,
+      "loss": 0.269,
+      "step": 940
+    },
+    {
+      "epoch": 15.498442367601246,
+      "grad_norm": 1.6030529737472534,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.2539,
+      "step": 945
+    },
+    {
+      "epoch": 15.581516095534788,
+      "grad_norm": 1.7192659378051758,
+      "learning_rate": 6.324373218975105e-06,
+      "loss": 0.261,
+      "step": 950
+    },
+    {
+      "epoch": 15.664589823468328,
+      "grad_norm": 1.6753857135772705,
+      "learning_rate": 6.08463042831268e-06,
+      "loss": 0.2521,
+      "step": 955
+    },
+    {
+      "epoch": 15.74766355140187,
+      "grad_norm": 1.9638776779174805,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.2615,
+      "step": 960
+    },
+    {
+      "epoch": 15.83073727933541,
+      "grad_norm": 1.5389426946640015,
+      "learning_rate": 5.617198567963352e-06,
+      "loss": 0.2584,
+      "step": 965
+    },
+    {
+      "epoch": 15.91381100726895,
+      "grad_norm": 1.8820122480392456,
+      "learning_rate": 5.389608377010608e-06,
+      "loss": 0.2667,
+      "step": 970
+    },
+    {
+      "epoch": 15.996884735202492,
+      "grad_norm": 1.8412877321243286,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.2697,
+      "step": 975
+    },
+    {
+      "epoch": 16.066458982346834,
+      "grad_norm": 1.7076417207717896,
+      "learning_rate": 4.946920181123904e-06,
+      "loss": 0.2451,
+      "step": 980
+    },
+    {
+      "epoch": 16.149532710280372,
+      "grad_norm": 1.4559515714645386,
+      "learning_rate": 4.731915820744695e-06,
+      "loss": 0.2448,
+      "step": 985
+    },
+    {
+      "epoch": 16.232606438213914,
+      "grad_norm": 1.4542195796966553,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.2525,
+      "step": 990
+    },
+    {
+      "epoch": 16.315680166147455,
+      "grad_norm": 1.7294296026229858,
+      "learning_rate": 4.314813971462237e-06,
+      "loss": 0.2452,
+      "step": 995
+    },
+    {
+      "epoch": 16.398753894080997,
+      "grad_norm": 1.694813847541809,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.2533,
+      "step": 1000
+    },
+    {
+      "epoch": 16.48182762201454,
+      "grad_norm": 1.7992663383483887,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.2604,
+      "step": 1005
+    },
+    {
+      "epoch": 16.56490134994808,
+      "grad_norm": 1.520974040031433,
+      "learning_rate": 3.7220831890750067e-06,
+      "loss": 0.2571,
+      "step": 1010
+    },
+    {
+      "epoch": 16.64797507788162,
+      "grad_norm": 1.9732450246810913,
+      "learning_rate": 3.5334535719846766e-06,
+      "loss": 0.2659,
+      "step": 1015
+    },
+    {
+      "epoch": 16.73104880581516,
+      "grad_norm": 1.7136303186416626,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.2565,
+      "step": 1020
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.39957467388969e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1080/trainer_state.json

@@ -0,0 +1,1545 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 17.714434060228452,
+  "eval_steps": 500,
+  "global_step": 1080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.6620935797691345,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.985,
+      "step": 125
+    },
+    {
+      "epoch": 2.132917964693666,
+      "grad_norm": 0.7846258878707886,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.9594,
+      "step": 130
+    },
+    {
+      "epoch": 2.2159916926272065,
+      "grad_norm": 0.652454137802124,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.9322,
+      "step": 135
+    },
+    {
+      "epoch": 2.2990654205607477,
+      "grad_norm": 0.7020059823989868,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.9242,
+      "step": 140
+    },
+    {
+      "epoch": 2.382139148494289,
+      "grad_norm": 0.8148695826530457,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.8394,
+      "step": 145
+    },
+    {
+      "epoch": 2.4652128764278296,
+      "grad_norm": 0.8813133835792542,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.992,
+      "step": 150
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 0.7893730401992798,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.899,
+      "step": 155
+    },
+    {
+      "epoch": 2.6313603322949115,
+      "grad_norm": 0.7719221711158752,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.9416,
+      "step": 160
+    },
+    {
+      "epoch": 2.7144340602284527,
+      "grad_norm": 0.8439667820930481,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.8401,
+      "step": 165
+    },
+    {
+      "epoch": 2.797507788161994,
+      "grad_norm": 0.833251953125,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.817,
+      "step": 170
+    },
+    {
+      "epoch": 2.8805815160955346,
+      "grad_norm": 0.7526916265487671,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.8191,
+      "step": 175
+    },
+    {
+      "epoch": 2.9636552440290758,
+      "grad_norm": 1.0640058517456055,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8607,
+      "step": 180
+    },
+    {
+      "epoch": 3.0332294911734166,
+      "grad_norm": 0.784114420413971,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.761,
+      "step": 185
+    },
+    {
+      "epoch": 3.1163032191069573,
+      "grad_norm": 0.9396352767944336,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.6821,
+      "step": 190
+    },
+    {
+      "epoch": 3.1993769470404985,
+      "grad_norm": 0.9770582914352417,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.742,
+      "step": 195
+    },
+    {
+      "epoch": 3.2824506749740396,
+      "grad_norm": 0.8752853870391846,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.69,
+      "step": 200
+    },
+    {
+      "epoch": 3.3655244029075804,
+      "grad_norm": 0.8496589064598083,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.769,
+      "step": 205
+    },
+    {
+      "epoch": 3.4485981308411215,
+      "grad_norm": 0.8192639350891113,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.7298,
+      "step": 210
+    },
+    {
+      "epoch": 3.5316718587746623,
+      "grad_norm": 1.00070059299469,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.7815,
+      "step": 215
+    },
+    {
+      "epoch": 3.6147455867082035,
+      "grad_norm": 1.1614112854003906,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.7975,
+      "step": 220
+    },
+    {
+      "epoch": 3.6978193146417446,
+      "grad_norm": 1.014397382736206,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 3.7808930425752854,
+      "grad_norm": 0.9468530416488647,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.7194,
+      "step": 230
+    },
+    {
+      "epoch": 3.8639667705088265,
+      "grad_norm": 1.2201341390609741,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.7795,
+      "step": 235
+    },
+    {
+      "epoch": 3.9470404984423677,
+      "grad_norm": 0.9476346373558044,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.7202,
+      "step": 240
+    },
+    {
+      "epoch": 4.0166147455867085,
+      "grad_norm": 0.9945451021194458,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.6931,
+      "step": 245
+    },
+    {
+      "epoch": 4.099688473520249,
+      "grad_norm": 1.1113696098327637,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.6557,
+      "step": 250
+    },
+    {
+      "epoch": 4.18276220145379,
+      "grad_norm": 1.3515146970748901,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.6295,
+      "step": 255
+    },
+    {
+      "epoch": 4.265835929387332,
+      "grad_norm": 1.375272274017334,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.6423,
+      "step": 260
+    },
+    {
+      "epoch": 4.348909657320872,
+      "grad_norm": 1.1683202981948853,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.6167,
+      "step": 265
+    },
+    {
+      "epoch": 4.431983385254413,
+      "grad_norm": 1.2091785669326782,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.6373,
+      "step": 270
+    },
+    {
+      "epoch": 4.515057113187955,
+      "grad_norm": 1.3007235527038574,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.5941,
+      "step": 275
+    },
+    {
+      "epoch": 4.598130841121495,
+      "grad_norm": 1.2785530090332031,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.6384,
+      "step": 280
+    },
+    {
+      "epoch": 4.681204569055036,
+      "grad_norm": 1.2808083295822144,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.6592,
+      "step": 285
+    },
+    {
+      "epoch": 4.764278296988578,
+      "grad_norm": 1.1978651285171509,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.6285,
+      "step": 290
+    },
+    {
+      "epoch": 4.8473520249221185,
+      "grad_norm": 1.3983532190322876,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.5941,
+      "step": 295
+    },
+    {
+      "epoch": 4.930425752855659,
+      "grad_norm": 1.286287784576416,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5652,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1714959144592285,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.5657,
+      "step": 305
+    },
+    {
+      "epoch": 5.083073727933541,
+      "grad_norm": 1.0886554718017578,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.4776,
+      "step": 310
+    },
+    {
+      "epoch": 5.166147455867082,
+      "grad_norm": 1.3735958337783813,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.5114,
+      "step": 315
+    },
+    {
+      "epoch": 5.249221183800623,
+      "grad_norm": 1.5809016227722168,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.5537,
+      "step": 320
+    },
+    {
+      "epoch": 5.332294911734164,
+      "grad_norm": 1.401424765586853,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.5299,
+      "step": 325
+    },
+    {
+      "epoch": 5.415368639667705,
+      "grad_norm": 1.467054009437561,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.5236,
+      "step": 330
+    },
+    {
+      "epoch": 5.498442367601246,
+      "grad_norm": 1.253794550895691,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.5632,
+      "step": 335
+    },
+    {
+      "epoch": 5.581516095534787,
+      "grad_norm": 1.4579623937606812,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.5556,
+      "step": 340
+    },
+    {
+      "epoch": 5.6645898234683285,
+      "grad_norm": 1.171007513999939,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.4934,
+      "step": 345
+    },
+    {
+      "epoch": 5.747663551401869,
+      "grad_norm": 1.4656859636306763,
+      "learning_rate": 4.4610391622989396e-05,
+      "loss": 0.5697,
+      "step": 350
+    },
+    {
+      "epoch": 5.83073727933541,
+      "grad_norm": 1.4671518802642822,
+      "learning_rate": 4.438280143203665e-05,
+      "loss": 0.5289,
+      "step": 355
+    },
+    {
+      "epoch": 5.913811007268951,
+      "grad_norm": 1.4010504484176636,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5205,
+      "step": 360
+    },
+    {
+      "epoch": 5.996884735202492,
+      "grad_norm": 1.6909047365188599,
+      "learning_rate": 4.391536957168733e-05,
+      "loss": 0.5469,
+      "step": 365
+    },
+    {
+      "epoch": 6.066458982346833,
+      "grad_norm": 1.3057804107666016,
+      "learning_rate": 4.36756267810249e-05,
+      "loss": 0.5087,
+      "step": 370
+    },
+    {
+      "epoch": 6.149532710280374,
+      "grad_norm": 1.7389354705810547,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.446,
+      "step": 375
+    },
+    {
+      "epoch": 6.232606438213915,
+      "grad_norm": 1.6178336143493652,
+      "learning_rate": 4.318434103932622e-05,
+      "loss": 0.4888,
+      "step": 380
+    },
+    {
+      "epoch": 6.315680166147456,
+      "grad_norm": 1.6565852165222168,
+      "learning_rate": 4.293290201298223e-05,
+      "loss": 0.4784,
+      "step": 385
+    },
+    {
+      "epoch": 6.398753894080997,
+      "grad_norm": 1.4080264568328857,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.4155,
+      "step": 390
+    },
+    {
+      "epoch": 6.481827622014538,
+      "grad_norm": 1.4906692504882812,
+      "learning_rate": 4.241869758026638e-05,
+      "loss": 0.4854,
+      "step": 395
+    },
+    {
+      "epoch": 6.564901349948079,
+      "grad_norm": 1.6544594764709473,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.4753,
+      "step": 400
+    },
+    {
+      "epoch": 6.64797507788162,
+      "grad_norm": 1.3182097673416138,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.4352,
+      "step": 405
+    },
+    {
+      "epoch": 6.731048805815161,
+      "grad_norm": 1.531633734703064,
+      "learning_rate": 4.1619896640348445e-05,
+      "loss": 0.4786,
+      "step": 410
+    },
+    {
+      "epoch": 6.814122533748702,
+      "grad_norm": 1.358223557472229,
+      "learning_rate": 4.1346522381426744e-05,
+      "loss": 0.4108,
+      "step": 415
+    },
+    {
+      "epoch": 6.897196261682243,
+      "grad_norm": 1.6483898162841797,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4828,
+      "step": 420
+    },
+    {
+      "epoch": 6.980269989615784,
+      "grad_norm": 1.5941141843795776,
+      "learning_rate": 4.078945878256244e-05,
+      "loss": 0.4276,
+      "step": 425
+    },
+    {
+      "epoch": 7.049844236760125,
+      "grad_norm": 1.367634892463684,
+      "learning_rate": 4.05058872817065e-05,
+      "loss": 0.3997,
+      "step": 430
+    },
+    {
+      "epoch": 7.132917964693665,
+      "grad_norm": 1.3028111457824707,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.3919,
+      "step": 435
+    },
+    {
+      "epoch": 7.215991692627207,
+      "grad_norm": 1.8897424936294556,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.3778,
+      "step": 440
+    },
+    {
+      "epoch": 7.299065420560748,
+      "grad_norm": 1.6549698114395142,
+      "learning_rate": 3.963573584424852e-05,
+      "loss": 0.408,
+      "step": 445
+    },
+    {
+      "epoch": 7.382139148494288,
+      "grad_norm": 1.3696308135986328,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.4262,
+      "step": 450
+    },
+    {
+      "epoch": 7.46521287642783,
+      "grad_norm": 1.6997928619384766,
+      "learning_rate": 3.9040052669587325e-05,
+      "loss": 0.3982,
+      "step": 455
+    },
+    {
+      "epoch": 7.548286604361371,
+      "grad_norm": 1.3938806056976318,
+      "learning_rate": 3.873772445177015e-05,
+      "loss": 0.4113,
+      "step": 460
+    },
+    {
+      "epoch": 7.6313603322949115,
+      "grad_norm": 1.8341262340545654,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.4265,
+      "step": 465
+    },
+    {
+      "epoch": 7.714434060228453,
+      "grad_norm": 1.6543951034545898,
+      "learning_rate": 3.8124414508364e-05,
+      "loss": 0.4112,
+      "step": 470
+    },
+    {
+      "epoch": 7.797507788161994,
+      "grad_norm": 1.5131211280822754,
+      "learning_rate": 3.781356251999663e-05,
+      "loss": 0.4098,
+      "step": 475
+    },
+    {
+      "epoch": 7.880581516095535,
+      "grad_norm": 1.7143309116363525,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4183,
+      "step": 480
+    },
+    {
+      "epoch": 7.963655244029075,
+      "grad_norm": 1.4201680421829224,
+      "learning_rate": 3.718379327818106e-05,
+      "loss": 0.388,
+      "step": 485
+    },
+    {
+      "epoch": 8.033229491173417,
+      "grad_norm": 1.36739182472229,
+      "learning_rate": 3.686500924369101e-05,
+      "loss": 0.3927,
+      "step": 490
+    },
+    {
+      "epoch": 8.116303219106957,
+      "grad_norm": 1.348694086074829,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.3614,
+      "step": 495
+    },
+    {
+      "epoch": 8.199376947040498,
+      "grad_norm": 1.7005705833435059,
+      "learning_rate": 3.621997950501156e-05,
+      "loss": 0.3509,
+      "step": 500
+    },
+    {
+      "epoch": 8.28245067497404,
+      "grad_norm": 1.4668842554092407,
+      "learning_rate": 3.589387024792699e-05,
+      "loss": 0.344,
+      "step": 505
+    },
+    {
+      "epoch": 8.36552440290758,
+      "grad_norm": 1.6029119491577148,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.3599,
+      "step": 510
+    },
+    {
+      "epoch": 8.448598130841122,
+      "grad_norm": 1.5699125528335571,
+      "learning_rate": 3.523480786315231e-05,
+      "loss": 0.3579,
+      "step": 515
+    },
+    {
+      "epoch": 8.531671858774663,
+      "grad_norm": 1.4507211446762085,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3341,
+      "step": 520
+    },
+    {
+      "epoch": 8.614745586708203,
+      "grad_norm": 1.460924744606018,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3762,
+      "step": 525
+    },
+    {
+      "epoch": 8.697819314641745,
+      "grad_norm": 1.6329962015151978,
+      "learning_rate": 3.423015368281711e-05,
+      "loss": 0.3948,
+      "step": 530
+    },
+    {
+      "epoch": 8.780893042575286,
+      "grad_norm": 1.5261616706848145,
+      "learning_rate": 3.389126904537192e-05,
+      "loss": 0.3594,
+      "step": 535
+    },
+    {
+      "epoch": 8.863966770508826,
+      "grad_norm": 1.6733344793319702,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.3856,
+      "step": 540
+    },
+    {
+      "epoch": 8.947040498442368,
+      "grad_norm": 1.4160898923873901,
+      "learning_rate": 3.3207929380339034e-05,
+      "loss": 0.3875,
+      "step": 545
+    },
+    {
+      "epoch": 9.016614745586708,
+      "grad_norm": 1.2456085681915283,
+      "learning_rate": 3.2863618903790346e-05,
+      "loss": 0.3318,
+      "step": 550
+    },
+    {
+      "epoch": 9.09968847352025,
+      "grad_norm": 1.309977650642395,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.3239,
+      "step": 555
+    },
+    {
+      "epoch": 9.18276220145379,
+      "grad_norm": 1.6747145652770996,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.342,
+      "step": 560
+    },
+    {
+      "epoch": 9.26583592938733,
+      "grad_norm": 1.6204376220703125,
+      "learning_rate": 3.182099991668653e-05,
+      "loss": 0.3368,
+      "step": 565
+    },
+    {
+      "epoch": 9.348909657320872,
+      "grad_norm": 1.6952364444732666,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.333,
+      "step": 570
+    },
+    {
+      "epoch": 9.431983385254414,
+      "grad_norm": 1.6254109144210815,
+      "learning_rate": 3.11185835988581e-05,
+      "loss": 0.3488,
+      "step": 575
+    },
+    {
+      "epoch": 9.515057113187954,
+      "grad_norm": 1.7684122323989868,
+      "learning_rate": 3.076539676856101e-05,
+      "loss": 0.3461,
+      "step": 580
+    },
+    {
+      "epoch": 9.598130841121495,
+      "grad_norm": 1.480283260345459,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.3457,
+      "step": 585
+    },
+    {
+      "epoch": 9.681204569055037,
+      "grad_norm": 1.4912574291229248,
+      "learning_rate": 3.0055439308300952e-05,
+      "loss": 0.3307,
+      "step": 590
+    },
+    {
+      "epoch": 9.764278296988577,
+      "grad_norm": 1.5759741067886353,
+      "learning_rate": 2.9698818860002797e-05,
+      "loss": 0.3387,
+      "step": 595
+    },
+    {
+      "epoch": 9.847352024922118,
+      "grad_norm": 1.475316047668457,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.342,
+      "step": 600
+    },
+    {
+      "epoch": 9.93042575285566,
+      "grad_norm": 1.5280460119247437,
+      "learning_rate": 2.898267170168807e-05,
+      "loss": 0.3325,
+      "step": 605
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.123524188995361,
+      "learning_rate": 2.8623296482681166e-05,
+      "loss": 0.3528,
+      "step": 610
+    },
+    {
+      "epoch": 10.083073727933542,
+      "grad_norm": 1.3620072603225708,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.3282,
+      "step": 615
+    },
+    {
+      "epoch": 10.166147455867081,
+      "grad_norm": 1.8294273614883423,
+      "learning_rate": 2.7902322853130757e-05,
+      "loss": 0.3066,
+      "step": 620
+    },
+    {
+      "epoch": 10.249221183800623,
+      "grad_norm": 1.5608752965927124,
+      "learning_rate": 2.7540876954570048e-05,
+      "loss": 0.3033,
+      "step": 625
+    },
+    {
+      "epoch": 10.332294911734165,
+      "grad_norm": 1.7856054306030273,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.2969,
+      "step": 630
+    },
+    {
+      "epoch": 10.415368639667705,
+      "grad_norm": 1.4942408800125122,
+      "learning_rate": 2.681644926806527e-05,
+      "loss": 0.3153,
+      "step": 635
+    },
+    {
+      "epoch": 10.498442367601246,
+      "grad_norm": 1.6234569549560547,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.3277,
+      "step": 640
+    },
+    {
+      "epoch": 10.581516095534788,
+      "grad_norm": 1.6694717407226562,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.3228,
+      "step": 645
+    },
+    {
+      "epoch": 10.664589823468328,
+      "grad_norm": 1.6755950450897217,
+      "learning_rate": 2.5727117968577784e-05,
+      "loss": 0.3316,
+      "step": 650
+    },
+    {
+      "epoch": 10.74766355140187,
+      "grad_norm": 1.3962074518203735,
+      "learning_rate": 2.536359744128957e-05,
+      "loss": 0.3188,
+      "step": 655
+    },
+    {
+      "epoch": 10.83073727933541,
+      "grad_norm": 1.7147635221481323,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3463,
+      "step": 660
+    },
+    {
+      "epoch": 10.91381100726895,
+      "grad_norm": 1.5997766256332397,
+      "learning_rate": 2.4636402558710432e-05,
+      "loss": 0.335,
+      "step": 665
+    },
+    {
+      "epoch": 10.996884735202492,
+      "grad_norm": 1.483155369758606,
+      "learning_rate": 2.4272882031422215e-05,
+      "loss": 0.3084,
+      "step": 670
+    },
+    {
+      "epoch": 11.066458982346832,
+      "grad_norm": 1.3599936962127686,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.311,
+      "step": 675
+    },
+    {
+      "epoch": 11.149532710280374,
+      "grad_norm": 1.5479919910430908,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.2999,
+      "step": 680
+    },
+    {
+      "epoch": 11.232606438213915,
+      "grad_norm": 1.5448635816574097,
+      "learning_rate": 2.3183550731934735e-05,
+      "loss": 0.291,
+      "step": 685
+    },
+    {
+      "epoch": 11.315680166147455,
+      "grad_norm": 1.4930479526519775,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.2879,
+      "step": 690
+    },
+    {
+      "epoch": 11.398753894080997,
+      "grad_norm": 1.578282356262207,
+      "learning_rate": 2.2459123045429954e-05,
+      "loss": 0.3033,
+      "step": 695
+    },
+    {
+      "epoch": 11.481827622014539,
+      "grad_norm": 1.4327830076217651,
+      "learning_rate": 2.2097677146869242e-05,
+      "loss": 0.2946,
+      "step": 700
+    },
+    {
+      "epoch": 11.564901349948078,
+      "grad_norm": 1.75092351436615,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.2965,
+      "step": 705
+    },
+    {
+      "epoch": 11.64797507788162,
+      "grad_norm": 1.4633839130401611,
+      "learning_rate": 2.1376703517318837e-05,
+      "loss": 0.3082,
+      "step": 710
+    },
+    {
+      "epoch": 11.731048805815162,
+      "grad_norm": 1.4483939409255981,
+      "learning_rate": 2.101732829831194e-05,
+      "loss": 0.3048,
+      "step": 715
+    },
+    {
+      "epoch": 11.814122533748701,
+      "grad_norm": 1.4273526668548584,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3093,
+      "step": 720
+    },
+    {
+      "epoch": 11.897196261682243,
+      "grad_norm": 1.536641240119934,
+      "learning_rate": 2.0301181139997205e-05,
+      "loss": 0.3185,
+      "step": 725
+    },
+    {
+      "epoch": 11.980269989615785,
+      "grad_norm": 1.6694177389144897,
+      "learning_rate": 1.9944560691699057e-05,
+      "loss": 0.3197,
+      "step": 730
+    },
+    {
+      "epoch": 12.049844236760125,
+      "grad_norm": 1.5738413333892822,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.3235,
+      "step": 735
+    },
+    {
+      "epoch": 12.132917964693666,
+      "grad_norm": 1.4949880838394165,
+      "learning_rate": 1.9234603231438995e-05,
+      "loss": 0.2752,
+      "step": 740
+    },
+    {
+      "epoch": 12.215991692627206,
+      "grad_norm": 1.7407513856887817,
+      "learning_rate": 1.8881416401141904e-05,
+      "loss": 0.282,
+      "step": 745
+    },
+    {
+      "epoch": 12.299065420560748,
+      "grad_norm": 1.6446201801300049,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.2847,
+      "step": 750
+    },
+    {
+      "epoch": 12.38213914849429,
+      "grad_norm": 1.5613073110580444,
+      "learning_rate": 1.8179000083313483e-05,
+      "loss": 0.2923,
+      "step": 755
+    },
+    {
+      "epoch": 12.46521287642783,
+      "grad_norm": 1.3661807775497437,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.2881,
+      "step": 760
+    },
+    {
+      "epoch": 12.54828660436137,
+      "grad_norm": 1.5903205871582031,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.2897,
+      "step": 765
+    },
+    {
+      "epoch": 12.631360332294912,
+      "grad_norm": 1.5441614389419556,
+      "learning_rate": 1.7136381096209664e-05,
+      "loss": 0.292,
+      "step": 770
+    },
+    {
+      "epoch": 12.714434060228452,
+      "grad_norm": 1.6512565612792969,
+      "learning_rate": 1.6792070619660975e-05,
+      "loss": 0.289,
+      "step": 775
+    },
+    {
+      "epoch": 12.797507788161994,
+      "grad_norm": 1.5514371395111084,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.3012,
+      "step": 780
+    },
+    {
+      "epoch": 12.880581516095535,
+      "grad_norm": 1.7717050313949585,
+      "learning_rate": 1.6108730954628093e-05,
+      "loss": 0.3055,
+      "step": 785
+    },
+    {
+      "epoch": 12.963655244029075,
+      "grad_norm": 1.4902904033660889,
+      "learning_rate": 1.5769846317182893e-05,
+      "loss": 0.2913,
+      "step": 790
+    },
+    {
+      "epoch": 13.033229491173417,
+      "grad_norm": 1.3144031763076782,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.3069,
+      "step": 795
+    },
+    {
+      "epoch": 13.116303219106957,
+      "grad_norm": 1.3925071954727173,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.2701,
+      "step": 800
+    },
+    {
+      "epoch": 13.199376947040498,
+      "grad_norm": 1.7400624752044678,
+      "learning_rate": 1.4765192136847685e-05,
+      "loss": 0.2742,
+      "step": 805
+    },
+    {
+      "epoch": 13.28245067497404,
+      "grad_norm": 1.5998958349227905,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.2778,
+      "step": 810
+    },
+    {
+      "epoch": 13.36552440290758,
+      "grad_norm": 1.7994098663330078,
+      "learning_rate": 1.4106129752073022e-05,
+      "loss": 0.2836,
+      "step": 815
+    },
+    {
+      "epoch": 13.448598130841122,
+      "grad_norm": 1.672831416130066,
+      "learning_rate": 1.3780020494988446e-05,
+      "loss": 0.2709,
+      "step": 820
+    },
+    {
+      "epoch": 13.531671858774663,
+      "grad_norm": 1.7876700162887573,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.2687,
+      "step": 825
+    },
+    {
+      "epoch": 13.614745586708203,
+      "grad_norm": 1.6950455904006958,
+      "learning_rate": 1.313499075630899e-05,
+      "loss": 0.2904,
+      "step": 830
+    },
+    {
+      "epoch": 13.697819314641745,
+      "grad_norm": 1.6819844245910645,
+      "learning_rate": 1.2816206721818944e-05,
+      "loss": 0.2876,
+      "step": 835
+    },
+    {
+      "epoch": 13.780893042575286,
+      "grad_norm": 1.5784549713134766,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.286,
+      "step": 840
+    },
+    {
+      "epoch": 13.863966770508826,
+      "grad_norm": 1.6307650804519653,
+      "learning_rate": 1.2186437480003372e-05,
+      "loss": 0.3009,
+      "step": 845
+    },
+    {
+      "epoch": 13.947040498442368,
+      "grad_norm": 1.4225823879241943,
+      "learning_rate": 1.1875585491636e-05,
+      "loss": 0.2741,
+      "step": 850
+    },
+    {
+      "epoch": 14.016614745586708,
+      "grad_norm": 1.2541974782943726,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.271,
+      "step": 855
+    },
+    {
+      "epoch": 14.09968847352025,
+      "grad_norm": 1.3735196590423584,
+      "learning_rate": 1.126227554822985e-05,
+      "loss": 0.2576,
+      "step": 860
+    },
+    {
+      "epoch": 14.18276220145379,
+      "grad_norm": 1.4082770347595215,
+      "learning_rate": 1.0959947330412682e-05,
+      "loss": 0.2705,
+      "step": 865
+    },
+    {
+      "epoch": 14.26583592938733,
+      "grad_norm": 1.5013236999511719,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.2641,
+      "step": 870
+    },
+    {
+      "epoch": 14.348909657320872,
+      "grad_norm": 1.8321263790130615,
+      "learning_rate": 1.0364264155751488e-05,
+      "loss": 0.2646,
+      "step": 875
+    },
+    {
+      "epoch": 14.431983385254414,
+      "grad_norm": 1.5073516368865967,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.267,
+      "step": 880
+    },
+    {
+      "epoch": 14.515057113187954,
+      "grad_norm": 1.5713279247283936,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.275,
+      "step": 885
+    },
+    {
+      "epoch": 14.598130841121495,
+      "grad_norm": 1.4692318439483643,
+      "learning_rate": 9.494112718293501e-06,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 14.681204569055037,
+      "grad_norm": 1.9062477350234985,
+      "learning_rate": 9.210541217437565e-06,
+      "loss": 0.2703,
+      "step": 895
+    },
+    {
+      "epoch": 14.764278296988577,
+      "grad_norm": 1.4207799434661865,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.2751,
+      "step": 900
+    },
+    {
+      "epoch": 14.847352024922118,
+      "grad_norm": 1.4608951807022095,
+      "learning_rate": 8.65347761857326e-06,
+      "loss": 0.2828,
+      "step": 905
+    },
+    {
+      "epoch": 14.93042575285566,
+      "grad_norm": 1.5288583040237427,
+      "learning_rate": 8.380103359651553e-06,
+      "loss": 0.2739,
+      "step": 910
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.328437328338623,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.2715,
+      "step": 915
+    },
+    {
+      "epoch": 15.083073727933542,
+      "grad_norm": 1.4342622756958008,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.2562,
+      "step": 920
+    },
+    {
+      "epoch": 15.166147455867081,
+      "grad_norm": 1.3755466938018799,
+      "learning_rate": 7.581302419733632e-06,
+      "loss": 0.2488,
+      "step": 925
+    },
+    {
+      "epoch": 15.249221183800623,
+      "grad_norm": 1.6790114641189575,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.2675,
+      "step": 930
+    },
+    {
+      "epoch": 15.332294911734165,
+      "grad_norm": 1.7311410903930664,
+      "learning_rate": 7.067097987017762e-06,
+      "loss": 0.2678,
+      "step": 935
+    },
+    {
+      "epoch": 15.415368639667705,
+      "grad_norm": 1.565371036529541,
+      "learning_rate": 6.815658960673782e-06,
+      "loss": 0.269,
+      "step": 940
+    },
+    {
+      "epoch": 15.498442367601246,
+      "grad_norm": 1.6030529737472534,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.2539,
+      "step": 945
+    },
+    {
+      "epoch": 15.581516095534788,
+      "grad_norm": 1.7192659378051758,
+      "learning_rate": 6.324373218975105e-06,
+      "loss": 0.261,
+      "step": 950
+    },
+    {
+      "epoch": 15.664589823468328,
+      "grad_norm": 1.6753857135772705,
+      "learning_rate": 6.08463042831268e-06,
+      "loss": 0.2521,
+      "step": 955
+    },
+    {
+      "epoch": 15.74766355140187,
+      "grad_norm": 1.9638776779174805,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.2615,
+      "step": 960
+    },
+    {
+      "epoch": 15.83073727933541,
+      "grad_norm": 1.5389426946640015,
+      "learning_rate": 5.617198567963352e-06,
+      "loss": 0.2584,
+      "step": 965
+    },
+    {
+      "epoch": 15.91381100726895,
+      "grad_norm": 1.8820122480392456,
+      "learning_rate": 5.389608377010608e-06,
+      "loss": 0.2667,
+      "step": 970
+    },
+    {
+      "epoch": 15.996884735202492,
+      "grad_norm": 1.8412877321243286,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.2697,
+      "step": 975
+    },
+    {
+      "epoch": 16.066458982346834,
+      "grad_norm": 1.7076417207717896,
+      "learning_rate": 4.946920181123904e-06,
+      "loss": 0.2451,
+      "step": 980
+    },
+    {
+      "epoch": 16.149532710280372,
+      "grad_norm": 1.4559515714645386,
+      "learning_rate": 4.731915820744695e-06,
+      "loss": 0.2448,
+      "step": 985
+    },
+    {
+      "epoch": 16.232606438213914,
+      "grad_norm": 1.4542195796966553,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.2525,
+      "step": 990
+    },
+    {
+      "epoch": 16.315680166147455,
+      "grad_norm": 1.7294296026229858,
+      "learning_rate": 4.314813971462237e-06,
+      "loss": 0.2452,
+      "step": 995
+    },
+    {
+      "epoch": 16.398753894080997,
+      "grad_norm": 1.694813847541809,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.2533,
+      "step": 1000
+    },
+    {
+      "epoch": 16.48182762201454,
+      "grad_norm": 1.7992663383483887,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.2604,
+      "step": 1005
+    },
+    {
+      "epoch": 16.56490134994808,
+      "grad_norm": 1.520974040031433,
+      "learning_rate": 3.7220831890750067e-06,
+      "loss": 0.2571,
+      "step": 1010
+    },
+    {
+      "epoch": 16.64797507788162,
+      "grad_norm": 1.9732450246810913,
+      "learning_rate": 3.5334535719846766e-06,
+      "loss": 0.2659,
+      "step": 1015
+    },
+    {
+      "epoch": 16.73104880581516,
+      "grad_norm": 1.7136303186416626,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.2565,
+      "step": 1020
+    },
+    {
+      "epoch": 16.8141225337487,
+      "grad_norm": 1.6919972896575928,
+      "learning_rate": 3.1698561306951064e-06,
+      "loss": 0.254,
+      "step": 1025
+    },
+    {
+      "epoch": 16.897196261682243,
+      "grad_norm": 1.8692378997802734,
+      "learning_rate": 2.9949652204972254e-06,
+      "loss": 0.2529,
+      "step": 1030
+    },
+    {
+      "epoch": 16.980269989615785,
+      "grad_norm": 1.798110842704773,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.2631,
+      "step": 1035
+    },
+    {
+      "epoch": 17.049844236760123,
+      "grad_norm": 1.5230650901794434,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.2521,
+      "step": 1040
+    },
+    {
+      "epoch": 17.132917964693664,
+      "grad_norm": 1.6472920179367065,
+      "learning_rate": 2.4983647033969714e-06,
+      "loss": 0.2463,
+      "step": 1045
+    },
+    {
+      "epoch": 17.215991692627206,
+      "grad_norm": 1.6704550981521606,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.2453,
+      "step": 1050
+    },
+    {
+      "epoch": 17.299065420560748,
+      "grad_norm": 1.550706386566162,
+      "learning_rate": 2.1910388661746493e-06,
+      "loss": 0.2487,
+      "step": 1055
+    },
+    {
+      "epoch": 17.38213914849429,
+      "grad_norm": 1.7238280773162842,
+      "learning_rate": 2.044597327993153e-06,
+      "loss": 0.2511,
+      "step": 1060
+    },
+    {
+      "epoch": 17.46521287642783,
+      "grad_norm": 1.5124459266662598,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.2436,
+      "step": 1065
+    },
+    {
+      "epoch": 17.54828660436137,
+      "grad_norm": 1.7043637037277222,
+      "learning_rate": 1.7663118943294366e-06,
+      "loss": 0.2491,
+      "step": 1070
+    },
+    {
+      "epoch": 17.63136033229491,
+      "grad_norm": 1.7300227880477905,
+      "learning_rate": 1.6345268662752906e-06,
+      "loss": 0.2464,
+      "step": 1075
+    },
+    {
+      "epoch": 17.714434060228452,
+      "grad_norm": 1.9400359392166138,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.2576,
+      "step": 1080
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.658164372026163e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-120/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-120/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-120/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-120/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-120/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.980269989615784,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5207292018425856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-1200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1200/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-1200/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-1200/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,1713 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.681204569055037,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.6620935797691345,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.985,
+      "step": 125
+    },
+    {
+      "epoch": 2.132917964693666,
+      "grad_norm": 0.7846258878707886,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.9594,
+      "step": 130
+    },
+    {
+      "epoch": 2.2159916926272065,
+      "grad_norm": 0.652454137802124,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.9322,
+      "step": 135
+    },
+    {
+      "epoch": 2.2990654205607477,
+      "grad_norm": 0.7020059823989868,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.9242,
+      "step": 140
+    },
+    {
+      "epoch": 2.382139148494289,
+      "grad_norm": 0.8148695826530457,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.8394,
+      "step": 145
+    },
+    {
+      "epoch": 2.4652128764278296,
+      "grad_norm": 0.8813133835792542,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.992,
+      "step": 150
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 0.7893730401992798,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.899,
+      "step": 155
+    },
+    {
+      "epoch": 2.6313603322949115,
+      "grad_norm": 0.7719221711158752,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.9416,
+      "step": 160
+    },
+    {
+      "epoch": 2.7144340602284527,
+      "grad_norm": 0.8439667820930481,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.8401,
+      "step": 165
+    },
+    {
+      "epoch": 2.797507788161994,
+      "grad_norm": 0.833251953125,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.817,
+      "step": 170
+    },
+    {
+      "epoch": 2.8805815160955346,
+      "grad_norm": 0.7526916265487671,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.8191,
+      "step": 175
+    },
+    {
+      "epoch": 2.9636552440290758,
+      "grad_norm": 1.0640058517456055,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8607,
+      "step": 180
+    },
+    {
+      "epoch": 3.0332294911734166,
+      "grad_norm": 0.784114420413971,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.761,
+      "step": 185
+    },
+    {
+      "epoch": 3.1163032191069573,
+      "grad_norm": 0.9396352767944336,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.6821,
+      "step": 190
+    },
+    {
+      "epoch": 3.1993769470404985,
+      "grad_norm": 0.9770582914352417,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.742,
+      "step": 195
+    },
+    {
+      "epoch": 3.2824506749740396,
+      "grad_norm": 0.8752853870391846,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.69,
+      "step": 200
+    },
+    {
+      "epoch": 3.3655244029075804,
+      "grad_norm": 0.8496589064598083,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.769,
+      "step": 205
+    },
+    {
+      "epoch": 3.4485981308411215,
+      "grad_norm": 0.8192639350891113,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.7298,
+      "step": 210
+    },
+    {
+      "epoch": 3.5316718587746623,
+      "grad_norm": 1.00070059299469,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.7815,
+      "step": 215
+    },
+    {
+      "epoch": 3.6147455867082035,
+      "grad_norm": 1.1614112854003906,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.7975,
+      "step": 220
+    },
+    {
+      "epoch": 3.6978193146417446,
+      "grad_norm": 1.014397382736206,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 3.7808930425752854,
+      "grad_norm": 0.9468530416488647,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.7194,
+      "step": 230
+    },
+    {
+      "epoch": 3.8639667705088265,
+      "grad_norm": 1.2201341390609741,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.7795,
+      "step": 235
+    },
+    {
+      "epoch": 3.9470404984423677,
+      "grad_norm": 0.9476346373558044,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.7202,
+      "step": 240
+    },
+    {
+      "epoch": 4.0166147455867085,
+      "grad_norm": 0.9945451021194458,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.6931,
+      "step": 245
+    },
+    {
+      "epoch": 4.099688473520249,
+      "grad_norm": 1.1113696098327637,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.6557,
+      "step": 250
+    },
+    {
+      "epoch": 4.18276220145379,
+      "grad_norm": 1.3515146970748901,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.6295,
+      "step": 255
+    },
+    {
+      "epoch": 4.265835929387332,
+      "grad_norm": 1.375272274017334,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.6423,
+      "step": 260
+    },
+    {
+      "epoch": 4.348909657320872,
+      "grad_norm": 1.1683202981948853,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.6167,
+      "step": 265
+    },
+    {
+      "epoch": 4.431983385254413,
+      "grad_norm": 1.2091785669326782,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.6373,
+      "step": 270
+    },
+    {
+      "epoch": 4.515057113187955,
+      "grad_norm": 1.3007235527038574,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.5941,
+      "step": 275
+    },
+    {
+      "epoch": 4.598130841121495,
+      "grad_norm": 1.2785530090332031,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.6384,
+      "step": 280
+    },
+    {
+      "epoch": 4.681204569055036,
+      "grad_norm": 1.2808083295822144,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.6592,
+      "step": 285
+    },
+    {
+      "epoch": 4.764278296988578,
+      "grad_norm": 1.1978651285171509,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.6285,
+      "step": 290
+    },
+    {
+      "epoch": 4.8473520249221185,
+      "grad_norm": 1.3983532190322876,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.5941,
+      "step": 295
+    },
+    {
+      "epoch": 4.930425752855659,
+      "grad_norm": 1.286287784576416,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5652,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1714959144592285,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.5657,
+      "step": 305
+    },
+    {
+      "epoch": 5.083073727933541,
+      "grad_norm": 1.0886554718017578,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.4776,
+      "step": 310
+    },
+    {
+      "epoch": 5.166147455867082,
+      "grad_norm": 1.3735958337783813,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.5114,
+      "step": 315
+    },
+    {
+      "epoch": 5.249221183800623,
+      "grad_norm": 1.5809016227722168,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.5537,
+      "step": 320
+    },
+    {
+      "epoch": 5.332294911734164,
+      "grad_norm": 1.401424765586853,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.5299,
+      "step": 325
+    },
+    {
+      "epoch": 5.415368639667705,
+      "grad_norm": 1.467054009437561,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.5236,
+      "step": 330
+    },
+    {
+      "epoch": 5.498442367601246,
+      "grad_norm": 1.253794550895691,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.5632,
+      "step": 335
+    },
+    {
+      "epoch": 5.581516095534787,
+      "grad_norm": 1.4579623937606812,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.5556,
+      "step": 340
+    },
+    {
+      "epoch": 5.6645898234683285,
+      "grad_norm": 1.171007513999939,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.4934,
+      "step": 345
+    },
+    {
+      "epoch": 5.747663551401869,
+      "grad_norm": 1.4656859636306763,
+      "learning_rate": 4.4610391622989396e-05,
+      "loss": 0.5697,
+      "step": 350
+    },
+    {
+      "epoch": 5.83073727933541,
+      "grad_norm": 1.4671518802642822,
+      "learning_rate": 4.438280143203665e-05,
+      "loss": 0.5289,
+      "step": 355
+    },
+    {
+      "epoch": 5.913811007268951,
+      "grad_norm": 1.4010504484176636,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5205,
+      "step": 360
+    },
+    {
+      "epoch": 5.996884735202492,
+      "grad_norm": 1.6909047365188599,
+      "learning_rate": 4.391536957168733e-05,
+      "loss": 0.5469,
+      "step": 365
+    },
+    {
+      "epoch": 6.066458982346833,
+      "grad_norm": 1.3057804107666016,
+      "learning_rate": 4.36756267810249e-05,
+      "loss": 0.5087,
+      "step": 370
+    },
+    {
+      "epoch": 6.149532710280374,
+      "grad_norm": 1.7389354705810547,
+      "learning_rate": 4.34319334202531e-05,
+      "loss": 0.446,
+      "step": 375
+    },
+    {
+      "epoch": 6.232606438213915,
+      "grad_norm": 1.6178336143493652,
+      "learning_rate": 4.318434103932622e-05,
+      "loss": 0.4888,
+      "step": 380
+    },
+    {
+      "epoch": 6.315680166147456,
+      "grad_norm": 1.6565852165222168,
+      "learning_rate": 4.293290201298223e-05,
+      "loss": 0.4784,
+      "step": 385
+    },
+    {
+      "epoch": 6.398753894080997,
+      "grad_norm": 1.4080264568328857,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.4155,
+      "step": 390
+    },
+    {
+      "epoch": 6.481827622014538,
+      "grad_norm": 1.4906692504882812,
+      "learning_rate": 4.241869758026638e-05,
+      "loss": 0.4854,
+      "step": 395
+    },
+    {
+      "epoch": 6.564901349948079,
+      "grad_norm": 1.6544594764709473,
+      "learning_rate": 4.215604094671835e-05,
+      "loss": 0.4753,
+      "step": 400
+    },
+    {
+      "epoch": 6.64797507788162,
+      "grad_norm": 1.3182097673416138,
+      "learning_rate": 4.188975519039151e-05,
+      "loss": 0.4352,
+      "step": 405
+    },
+    {
+      "epoch": 6.731048805815161,
+      "grad_norm": 1.531633734703064,
+      "learning_rate": 4.1619896640348445e-05,
+      "loss": 0.4786,
+      "step": 410
+    },
+    {
+      "epoch": 6.814122533748702,
+      "grad_norm": 1.358223557472229,
+      "learning_rate": 4.1346522381426744e-05,
+      "loss": 0.4108,
+      "step": 415
+    },
+    {
+      "epoch": 6.897196261682243,
+      "grad_norm": 1.6483898162841797,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.4828,
+      "step": 420
+    },
+    {
+      "epoch": 6.980269989615784,
+      "grad_norm": 1.5941141843795776,
+      "learning_rate": 4.078945878256244e-05,
+      "loss": 0.4276,
+      "step": 425
+    },
+    {
+      "epoch": 7.049844236760125,
+      "grad_norm": 1.367634892463684,
+      "learning_rate": 4.05058872817065e-05,
+      "loss": 0.3997,
+      "step": 430
+    },
+    {
+      "epoch": 7.132917964693665,
+      "grad_norm": 1.3028111457824707,
+      "learning_rate": 4.021903572521802e-05,
+      "loss": 0.3919,
+      "step": 435
+    },
+    {
+      "epoch": 7.215991692627207,
+      "grad_norm": 1.8897424936294556,
+      "learning_rate": 3.9928964792569655e-05,
+      "loss": 0.3778,
+      "step": 440
+    },
+    {
+      "epoch": 7.299065420560748,
+      "grad_norm": 1.6549698114395142,
+      "learning_rate": 3.963573584424852e-05,
+      "loss": 0.408,
+      "step": 445
+    },
+    {
+      "epoch": 7.382139148494288,
+      "grad_norm": 1.3696308135986328,
+      "learning_rate": 3.933941090877615e-05,
+      "loss": 0.4262,
+      "step": 450
+    },
+    {
+      "epoch": 7.46521287642783,
+      "grad_norm": 1.6997928619384766,
+      "learning_rate": 3.9040052669587325e-05,
+      "loss": 0.3982,
+      "step": 455
+    },
+    {
+      "epoch": 7.548286604361371,
+      "grad_norm": 1.3938806056976318,
+      "learning_rate": 3.873772445177015e-05,
+      "loss": 0.4113,
+      "step": 460
+    },
+    {
+      "epoch": 7.6313603322949115,
+      "grad_norm": 1.8341262340545654,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.4265,
+      "step": 465
+    },
+    {
+      "epoch": 7.714434060228453,
+      "grad_norm": 1.6543951034545898,
+      "learning_rate": 3.8124414508364e-05,
+      "loss": 0.4112,
+      "step": 470
+    },
+    {
+      "epoch": 7.797507788161994,
+      "grad_norm": 1.5131211280822754,
+      "learning_rate": 3.781356251999663e-05,
+      "loss": 0.4098,
+      "step": 475
+    },
+    {
+      "epoch": 7.880581516095535,
+      "grad_norm": 1.7143309116363525,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4183,
+      "step": 480
+    },
+    {
+      "epoch": 7.963655244029075,
+      "grad_norm": 1.4201680421829224,
+      "learning_rate": 3.718379327818106e-05,
+      "loss": 0.388,
+      "step": 485
+    },
+    {
+      "epoch": 8.033229491173417,
+      "grad_norm": 1.36739182472229,
+      "learning_rate": 3.686500924369101e-05,
+      "loss": 0.3927,
+      "step": 490
+    },
+    {
+      "epoch": 8.116303219106957,
+      "grad_norm": 1.348694086074829,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.3614,
+      "step": 495
+    },
+    {
+      "epoch": 8.199376947040498,
+      "grad_norm": 1.7005705833435059,
+      "learning_rate": 3.621997950501156e-05,
+      "loss": 0.3509,
+      "step": 500
+    },
+    {
+      "epoch": 8.28245067497404,
+      "grad_norm": 1.4668842554092407,
+      "learning_rate": 3.589387024792699e-05,
+      "loss": 0.344,
+      "step": 505
+    },
+    {
+      "epoch": 8.36552440290758,
+      "grad_norm": 1.6029119491577148,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.3599,
+      "step": 510
+    },
+    {
+      "epoch": 8.448598130841122,
+      "grad_norm": 1.5699125528335571,
+      "learning_rate": 3.523480786315231e-05,
+      "loss": 0.3579,
+      "step": 515
+    },
+    {
+      "epoch": 8.531671858774663,
+      "grad_norm": 1.4507211446762085,
+      "learning_rate": 3.490199415097892e-05,
+      "loss": 0.3341,
+      "step": 520
+    },
+    {
+      "epoch": 8.614745586708203,
+      "grad_norm": 1.460924744606018,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.3762,
+      "step": 525
+    },
+    {
+      "epoch": 8.697819314641745,
+      "grad_norm": 1.6329962015151978,
+      "learning_rate": 3.423015368281711e-05,
+      "loss": 0.3948,
+      "step": 530
+    },
+    {
+      "epoch": 8.780893042575286,
+      "grad_norm": 1.5261616706848145,
+      "learning_rate": 3.389126904537192e-05,
+      "loss": 0.3594,
+      "step": 535
+    },
+    {
+      "epoch": 8.863966770508826,
+      "grad_norm": 1.6733344793319702,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.3856,
+      "step": 540
+    },
+    {
+      "epoch": 8.947040498442368,
+      "grad_norm": 1.4160898923873901,
+      "learning_rate": 3.3207929380339034e-05,
+      "loss": 0.3875,
+      "step": 545
+    },
+    {
+      "epoch": 9.016614745586708,
+      "grad_norm": 1.2456085681915283,
+      "learning_rate": 3.2863618903790346e-05,
+      "loss": 0.3318,
+      "step": 550
+    },
+    {
+      "epoch": 9.09968847352025,
+      "grad_norm": 1.309977650642395,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.3239,
+      "step": 555
+    },
+    {
+      "epoch": 9.18276220145379,
+      "grad_norm": 1.6747145652770996,
+      "learning_rate": 3.217008081777726e-05,
+      "loss": 0.342,
+      "step": 560
+    },
+    {
+      "epoch": 9.26583592938733,
+      "grad_norm": 1.6204376220703125,
+      "learning_rate": 3.182099991668653e-05,
+      "loss": 0.3368,
+      "step": 565
+    },
+    {
+      "epoch": 9.348909657320872,
+      "grad_norm": 1.6952364444732666,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.333,
+      "step": 570
+    },
+    {
+      "epoch": 9.431983385254414,
+      "grad_norm": 1.6254109144210815,
+      "learning_rate": 3.11185835988581e-05,
+      "loss": 0.3488,
+      "step": 575
+    },
+    {
+      "epoch": 9.515057113187954,
+      "grad_norm": 1.7684122323989868,
+      "learning_rate": 3.076539676856101e-05,
+      "loss": 0.3461,
+      "step": 580
+    },
+    {
+      "epoch": 9.598130841121495,
+      "grad_norm": 1.480283260345459,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.3457,
+      "step": 585
+    },
+    {
+      "epoch": 9.681204569055037,
+      "grad_norm": 1.4912574291229248,
+      "learning_rate": 3.0055439308300952e-05,
+      "loss": 0.3307,
+      "step": 590
+    },
+    {
+      "epoch": 9.764278296988577,
+      "grad_norm": 1.5759741067886353,
+      "learning_rate": 2.9698818860002797e-05,
+      "loss": 0.3387,
+      "step": 595
+    },
+    {
+      "epoch": 9.847352024922118,
+      "grad_norm": 1.475316047668457,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.342,
+      "step": 600
+    },
+    {
+      "epoch": 9.93042575285566,
+      "grad_norm": 1.5280460119247437,
+      "learning_rate": 2.898267170168807e-05,
+      "loss": 0.3325,
+      "step": 605
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.123524188995361,
+      "learning_rate": 2.8623296482681166e-05,
+      "loss": 0.3528,
+      "step": 610
+    },
+    {
+      "epoch": 10.083073727933542,
+      "grad_norm": 1.3620072603225708,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.3282,
+      "step": 615
+    },
+    {
+      "epoch": 10.166147455867081,
+      "grad_norm": 1.8294273614883423,
+      "learning_rate": 2.7902322853130757e-05,
+      "loss": 0.3066,
+      "step": 620
+    },
+    {
+      "epoch": 10.249221183800623,
+      "grad_norm": 1.5608752965927124,
+      "learning_rate": 2.7540876954570048e-05,
+      "loss": 0.3033,
+      "step": 625
+    },
+    {
+      "epoch": 10.332294911734165,
+      "grad_norm": 1.7856054306030273,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.2969,
+      "step": 630
+    },
+    {
+      "epoch": 10.415368639667705,
+      "grad_norm": 1.4942408800125122,
+      "learning_rate": 2.681644926806527e-05,
+      "loss": 0.3153,
+      "step": 635
+    },
+    {
+      "epoch": 10.498442367601246,
+      "grad_norm": 1.6234569549560547,
+      "learning_rate": 2.6453620722761896e-05,
+      "loss": 0.3277,
+      "step": 640
+    },
+    {
+      "epoch": 10.581516095534788,
+      "grad_norm": 1.6694717407226562,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.3228,
+      "step": 645
+    },
+    {
+      "epoch": 10.664589823468328,
+      "grad_norm": 1.6755950450897217,
+      "learning_rate": 2.5727117968577784e-05,
+      "loss": 0.3316,
+      "step": 650
+    },
+    {
+      "epoch": 10.74766355140187,
+      "grad_norm": 1.3962074518203735,
+      "learning_rate": 2.536359744128957e-05,
+      "loss": 0.3188,
+      "step": 655
+    },
+    {
+      "epoch": 10.83073727933541,
+      "grad_norm": 1.7147635221481323,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3463,
+      "step": 660
+    },
+    {
+      "epoch": 10.91381100726895,
+      "grad_norm": 1.5997766256332397,
+      "learning_rate": 2.4636402558710432e-05,
+      "loss": 0.335,
+      "step": 665
+    },
+    {
+      "epoch": 10.996884735202492,
+      "grad_norm": 1.483155369758606,
+      "learning_rate": 2.4272882031422215e-05,
+      "loss": 0.3084,
+      "step": 670
+    },
+    {
+      "epoch": 11.066458982346832,
+      "grad_norm": 1.3599936962127686,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.311,
+      "step": 675
+    },
+    {
+      "epoch": 11.149532710280374,
+      "grad_norm": 1.5479919910430908,
+      "learning_rate": 2.3546379277238107e-05,
+      "loss": 0.2999,
+      "step": 680
+    },
+    {
+      "epoch": 11.232606438213915,
+      "grad_norm": 1.5448635816574097,
+      "learning_rate": 2.3183550731934735e-05,
+      "loss": 0.291,
+      "step": 685
+    },
+    {
+      "epoch": 11.315680166147455,
+      "grad_norm": 1.4930479526519775,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.2879,
+      "step": 690
+    },
+    {
+      "epoch": 11.398753894080997,
+      "grad_norm": 1.578282356262207,
+      "learning_rate": 2.2459123045429954e-05,
+      "loss": 0.3033,
+      "step": 695
+    },
+    {
+      "epoch": 11.481827622014539,
+      "grad_norm": 1.4327830076217651,
+      "learning_rate": 2.2097677146869242e-05,
+      "loss": 0.2946,
+      "step": 700
+    },
+    {
+      "epoch": 11.564901349948078,
+      "grad_norm": 1.75092351436615,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.2965,
+      "step": 705
+    },
+    {
+      "epoch": 11.64797507788162,
+      "grad_norm": 1.4633839130401611,
+      "learning_rate": 2.1376703517318837e-05,
+      "loss": 0.3082,
+      "step": 710
+    },
+    {
+      "epoch": 11.731048805815162,
+      "grad_norm": 1.4483939409255981,
+      "learning_rate": 2.101732829831194e-05,
+      "loss": 0.3048,
+      "step": 715
+    },
+    {
+      "epoch": 11.814122533748701,
+      "grad_norm": 1.4273526668548584,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3093,
+      "step": 720
+    },
+    {
+      "epoch": 11.897196261682243,
+      "grad_norm": 1.536641240119934,
+      "learning_rate": 2.0301181139997205e-05,
+      "loss": 0.3185,
+      "step": 725
+    },
+    {
+      "epoch": 11.980269989615785,
+      "grad_norm": 1.6694177389144897,
+      "learning_rate": 1.9944560691699057e-05,
+      "loss": 0.3197,
+      "step": 730
+    },
+    {
+      "epoch": 12.049844236760125,
+      "grad_norm": 1.5738413333892822,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.3235,
+      "step": 735
+    },
+    {
+      "epoch": 12.132917964693666,
+      "grad_norm": 1.4949880838394165,
+      "learning_rate": 1.9234603231438995e-05,
+      "loss": 0.2752,
+      "step": 740
+    },
+    {
+      "epoch": 12.215991692627206,
+      "grad_norm": 1.7407513856887817,
+      "learning_rate": 1.8881416401141904e-05,
+      "loss": 0.282,
+      "step": 745
+    },
+    {
+      "epoch": 12.299065420560748,
+      "grad_norm": 1.6446201801300049,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.2847,
+      "step": 750
+    },
+    {
+      "epoch": 12.38213914849429,
+      "grad_norm": 1.5613073110580444,
+      "learning_rate": 1.8179000083313483e-05,
+      "loss": 0.2923,
+      "step": 755
+    },
+    {
+      "epoch": 12.46521287642783,
+      "grad_norm": 1.3661807775497437,
+      "learning_rate": 1.7829919182222752e-05,
+      "loss": 0.2881,
+      "step": 760
+    },
+    {
+      "epoch": 12.54828660436137,
+      "grad_norm": 1.5903205871582031,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.2897,
+      "step": 765
+    },
+    {
+      "epoch": 12.631360332294912,
+      "grad_norm": 1.5441614389419556,
+      "learning_rate": 1.7136381096209664e-05,
+      "loss": 0.292,
+      "step": 770
+    },
+    {
+      "epoch": 12.714434060228452,
+      "grad_norm": 1.6512565612792969,
+      "learning_rate": 1.6792070619660975e-05,
+      "loss": 0.289,
+      "step": 775
+    },
+    {
+      "epoch": 12.797507788161994,
+      "grad_norm": 1.5514371395111084,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.3012,
+      "step": 780
+    },
+    {
+      "epoch": 12.880581516095535,
+      "grad_norm": 1.7717050313949585,
+      "learning_rate": 1.6108730954628093e-05,
+      "loss": 0.3055,
+      "step": 785
+    },
+    {
+      "epoch": 12.963655244029075,
+      "grad_norm": 1.4902904033660889,
+      "learning_rate": 1.5769846317182893e-05,
+      "loss": 0.2913,
+      "step": 790
+    },
+    {
+      "epoch": 13.033229491173417,
+      "grad_norm": 1.3144031763076782,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.3069,
+      "step": 795
+    },
+    {
+      "epoch": 13.116303219106957,
+      "grad_norm": 1.3925071954727173,
+      "learning_rate": 1.509800584902108e-05,
+      "loss": 0.2701,
+      "step": 800
+    },
+    {
+      "epoch": 13.199376947040498,
+      "grad_norm": 1.7400624752044678,
+      "learning_rate": 1.4765192136847685e-05,
+      "loss": 0.2742,
+      "step": 805
+    },
+    {
+      "epoch": 13.28245067497404,
+      "grad_norm": 1.5998958349227905,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.2778,
+      "step": 810
+    },
+    {
+      "epoch": 13.36552440290758,
+      "grad_norm": 1.7994098663330078,
+      "learning_rate": 1.4106129752073022e-05,
+      "loss": 0.2836,
+      "step": 815
+    },
+    {
+      "epoch": 13.448598130841122,
+      "grad_norm": 1.672831416130066,
+      "learning_rate": 1.3780020494988446e-05,
+      "loss": 0.2709,
+      "step": 820
+    },
+    {
+      "epoch": 13.531671858774663,
+      "grad_norm": 1.7876700162887573,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.2687,
+      "step": 825
+    },
+    {
+      "epoch": 13.614745586708203,
+      "grad_norm": 1.6950455904006958,
+      "learning_rate": 1.313499075630899e-05,
+      "loss": 0.2904,
+      "step": 830
+    },
+    {
+      "epoch": 13.697819314641745,
+      "grad_norm": 1.6819844245910645,
+      "learning_rate": 1.2816206721818944e-05,
+      "loss": 0.2876,
+      "step": 835
+    },
+    {
+      "epoch": 13.780893042575286,
+      "grad_norm": 1.5784549713134766,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.286,
+      "step": 840
+    },
+    {
+      "epoch": 13.863966770508826,
+      "grad_norm": 1.6307650804519653,
+      "learning_rate": 1.2186437480003372e-05,
+      "loss": 0.3009,
+      "step": 845
+    },
+    {
+      "epoch": 13.947040498442368,
+      "grad_norm": 1.4225823879241943,
+      "learning_rate": 1.1875585491636e-05,
+      "loss": 0.2741,
+      "step": 850
+    },
+    {
+      "epoch": 14.016614745586708,
+      "grad_norm": 1.2541974782943726,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.271,
+      "step": 855
+    },
+    {
+      "epoch": 14.09968847352025,
+      "grad_norm": 1.3735196590423584,
+      "learning_rate": 1.126227554822985e-05,
+      "loss": 0.2576,
+      "step": 860
+    },
+    {
+      "epoch": 14.18276220145379,
+      "grad_norm": 1.4082770347595215,
+      "learning_rate": 1.0959947330412682e-05,
+      "loss": 0.2705,
+      "step": 865
+    },
+    {
+      "epoch": 14.26583592938733,
+      "grad_norm": 1.5013236999511719,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.2641,
+      "step": 870
+    },
+    {
+      "epoch": 14.348909657320872,
+      "grad_norm": 1.8321263790130615,
+      "learning_rate": 1.0364264155751488e-05,
+      "loss": 0.2646,
+      "step": 875
+    },
+    {
+      "epoch": 14.431983385254414,
+      "grad_norm": 1.5073516368865967,
+      "learning_rate": 1.0071035207430352e-05,
+      "loss": 0.267,
+      "step": 880
+    },
+    {
+      "epoch": 14.515057113187954,
+      "grad_norm": 1.5713279247283936,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.275,
+      "step": 885
+    },
+    {
+      "epoch": 14.598130841121495,
+      "grad_norm": 1.4692318439483643,
+      "learning_rate": 9.494112718293501e-06,
+      "loss": 0.2674,
+      "step": 890
+    },
+    {
+      "epoch": 14.681204569055037,
+      "grad_norm": 1.9062477350234985,
+      "learning_rate": 9.210541217437565e-06,
+      "loss": 0.2703,
+      "step": 895
+    },
+    {
+      "epoch": 14.764278296988577,
+      "grad_norm": 1.4207799434661865,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.2751,
+      "step": 900
+    },
+    {
+      "epoch": 14.847352024922118,
+      "grad_norm": 1.4608951807022095,
+      "learning_rate": 8.65347761857326e-06,
+      "loss": 0.2828,
+      "step": 905
+    },
+    {
+      "epoch": 14.93042575285566,
+      "grad_norm": 1.5288583040237427,
+      "learning_rate": 8.380103359651553e-06,
+      "loss": 0.2739,
+      "step": 910
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.328437328338623,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.2715,
+      "step": 915
+    },
+    {
+      "epoch": 15.083073727933542,
+      "grad_norm": 1.4342622756958008,
+      "learning_rate": 7.843959053281663e-06,
+      "loss": 0.2562,
+      "step": 920
+    },
+    {
+      "epoch": 15.166147455867081,
+      "grad_norm": 1.3755466938018799,
+      "learning_rate": 7.581302419733632e-06,
+      "loss": 0.2488,
+      "step": 925
+    },
+    {
+      "epoch": 15.249221183800623,
+      "grad_norm": 1.6790114641189575,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.2675,
+      "step": 930
+    },
+    {
+      "epoch": 15.332294911734165,
+      "grad_norm": 1.7311410903930664,
+      "learning_rate": 7.067097987017762e-06,
+      "loss": 0.2678,
+      "step": 935
+    },
+    {
+      "epoch": 15.415368639667705,
+      "grad_norm": 1.565371036529541,
+      "learning_rate": 6.815658960673782e-06,
+      "loss": 0.269,
+      "step": 940
+    },
+    {
+      "epoch": 15.498442367601246,
+      "grad_norm": 1.6030529737472534,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.2539,
+      "step": 945
+    },
+    {
+      "epoch": 15.581516095534788,
+      "grad_norm": 1.7192659378051758,
+      "learning_rate": 6.324373218975105e-06,
+      "loss": 0.261,
+      "step": 950
+    },
+    {
+      "epoch": 15.664589823468328,
+      "grad_norm": 1.6753857135772705,
+      "learning_rate": 6.08463042831268e-06,
+      "loss": 0.2521,
+      "step": 955
+    },
+    {
+      "epoch": 15.74766355140187,
+      "grad_norm": 1.9638776779174805,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.2615,
+      "step": 960
+    },
+    {
+      "epoch": 15.83073727933541,
+      "grad_norm": 1.5389426946640015,
+      "learning_rate": 5.617198567963352e-06,
+      "loss": 0.2584,
+      "step": 965
+    },
+    {
+      "epoch": 15.91381100726895,
+      "grad_norm": 1.8820122480392456,
+      "learning_rate": 5.389608377010608e-06,
+      "loss": 0.2667,
+      "step": 970
+    },
+    {
+      "epoch": 15.996884735202492,
+      "grad_norm": 1.8412877321243286,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.2697,
+      "step": 975
+    },
+    {
+      "epoch": 16.066458982346834,
+      "grad_norm": 1.7076417207717896,
+      "learning_rate": 4.946920181123904e-06,
+      "loss": 0.2451,
+      "step": 980
+    },
+    {
+      "epoch": 16.149532710280372,
+      "grad_norm": 1.4559515714645386,
+      "learning_rate": 4.731915820744695e-06,
+      "loss": 0.2448,
+      "step": 985
+    },
+    {
+      "epoch": 16.232606438213914,
+      "grad_norm": 1.4542195796966553,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.2525,
+      "step": 990
+    },
+    {
+      "epoch": 16.315680166147455,
+      "grad_norm": 1.7294296026229858,
+      "learning_rate": 4.314813971462237e-06,
+      "loss": 0.2452,
+      "step": 995
+    },
+    {
+      "epoch": 16.398753894080997,
+      "grad_norm": 1.694813847541809,
+      "learning_rate": 4.112804714676594e-06,
+      "loss": 0.2533,
+      "step": 1000
+    },
+    {
+      "epoch": 16.48182762201454,
+      "grad_norm": 1.7992663383483887,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.2604,
+      "step": 1005
+    },
+    {
+      "epoch": 16.56490134994808,
+      "grad_norm": 1.520974040031433,
+      "learning_rate": 3.7220831890750067e-06,
+      "loss": 0.2571,
+      "step": 1010
+    },
+    {
+      "epoch": 16.64797507788162,
+      "grad_norm": 1.9732450246810913,
+      "learning_rate": 3.5334535719846766e-06,
+      "loss": 0.2659,
+      "step": 1015
+    },
+    {
+      "epoch": 16.73104880581516,
+      "grad_norm": 1.7136303186416626,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.2565,
+      "step": 1020
+    },
+    {
+      "epoch": 16.8141225337487,
+      "grad_norm": 1.6919972896575928,
+      "learning_rate": 3.1698561306951064e-06,
+      "loss": 0.254,
+      "step": 1025
+    },
+    {
+      "epoch": 16.897196261682243,
+      "grad_norm": 1.8692378997802734,
+      "learning_rate": 2.9949652204972254e-06,
+      "loss": 0.2529,
+      "step": 1030
+    },
+    {
+      "epoch": 16.980269989615785,
+      "grad_norm": 1.798110842704773,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.2631,
+      "step": 1035
+    },
+    {
+      "epoch": 17.049844236760123,
+      "grad_norm": 1.5230650901794434,
+      "learning_rate": 2.659183991914696e-06,
+      "loss": 0.2521,
+      "step": 1040
+    },
+    {
+      "epoch": 17.132917964693664,
+      "grad_norm": 1.6472920179367065,
+      "learning_rate": 2.4983647033969714e-06,
+      "loss": 0.2463,
+      "step": 1045
+    },
+    {
+      "epoch": 17.215991692627206,
+      "grad_norm": 1.6704550981521606,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.2453,
+      "step": 1050
+    },
+    {
+      "epoch": 17.299065420560748,
+      "grad_norm": 1.550706386566162,
+      "learning_rate": 2.1910388661746493e-06,
+      "loss": 0.2487,
+      "step": 1055
+    },
+    {
+      "epoch": 17.38213914849429,
+      "grad_norm": 1.7238280773162842,
+      "learning_rate": 2.044597327993153e-06,
+      "loss": 0.2511,
+      "step": 1060
+    },
+    {
+      "epoch": 17.46521287642783,
+      "grad_norm": 1.5124459266662598,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.2436,
+      "step": 1065
+    },
+    {
+      "epoch": 17.54828660436137,
+      "grad_norm": 1.7043637037277222,
+      "learning_rate": 1.7663118943294366e-06,
+      "loss": 0.2491,
+      "step": 1070
+    },
+    {
+      "epoch": 17.63136033229491,
+      "grad_norm": 1.7300227880477905,
+      "learning_rate": 1.6345268662752906e-06,
+      "loss": 0.2464,
+      "step": 1075
+    },
+    {
+      "epoch": 17.714434060228452,
+      "grad_norm": 1.9400359392166138,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.2576,
+      "step": 1080
+    },
+    {
+      "epoch": 17.797507788161994,
+      "grad_norm": 1.5764034986495972,
+      "learning_rate": 1.3858115683098832e-06,
+      "loss": 0.2512,
+      "step": 1085
+    },
+    {
+      "epoch": 17.880581516095535,
+      "grad_norm": 1.7540063858032227,
+      "learning_rate": 1.2689339106741527e-06,
+      "loss": 0.2484,
+      "step": 1090
+    },
+    {
+      "epoch": 17.963655244029077,
+      "grad_norm": 1.5876474380493164,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.247,
+      "step": 1095
+    },
+    {
+      "epoch": 18.033229491173415,
+      "grad_norm": 1.723120093345642,
+      "learning_rate": 1.0502621921127776e-06,
+      "loss": 0.2509,
+      "step": 1100
+    },
+    {
+      "epoch": 18.116303219106957,
+      "grad_norm": 1.549980640411377,
+      "learning_rate": 9.485143881596714e-07,
+      "loss": 0.2565,
+      "step": 1105
+    },
+    {
+      "epoch": 18.1993769470405,
+      "grad_norm": 1.685396671295166,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.2386,
+      "step": 1110
+    },
+    {
+      "epoch": 18.28245067497404,
+      "grad_norm": 1.5742353200912476,
+      "learning_rate": 7.603025030471e-07,
+      "loss": 0.2429,
+      "step": 1115
+    },
+    {
+      "epoch": 18.36552440290758,
+      "grad_norm": 1.8015878200531006,
+      "learning_rate": 6.738782355044049e-07,
+      "loss": 0.2441,
+      "step": 1120
+    },
+    {
+      "epoch": 18.44859813084112,
+      "grad_norm": 1.6814690828323364,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.2445,
+      "step": 1125
+    },
+    {
+      "epoch": 18.53167185877466,
+      "grad_norm": 1.7425857782363892,
+      "learning_rate": 5.164844558612131e-07,
+      "loss": 0.2429,
+      "step": 1130
+    },
+    {
+      "epoch": 18.614745586708203,
+      "grad_norm": 1.6815589666366577,
+      "learning_rate": 4.4554823823423354e-07,
+      "loss": 0.2523,
+      "step": 1135
+    },
+    {
+      "epoch": 18.697819314641745,
+      "grad_norm": 1.819124698638916,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.2567,
+      "step": 1140
+    },
+    {
+      "epoch": 18.780893042575286,
+      "grad_norm": 1.7623286247253418,
+      "learning_rate": 3.192721720656489e-07,
+      "loss": 0.2354,
+      "step": 1145
+    },
+    {
+      "epoch": 18.863966770508828,
+      "grad_norm": 1.9344545602798462,
+      "learning_rate": 2.6395903547638825e-07,
+      "loss": 0.2535,
+      "step": 1150
+    },
+    {
+      "epoch": 18.947040498442366,
+      "grad_norm": 1.6039988994598389,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.2361,
+      "step": 1155
+    },
+    {
+      "epoch": 19.016614745586708,
+      "grad_norm": 1.6311196088790894,
+      "learning_rate": 1.6904105645142444e-07,
+      "loss": 0.2456,
+      "step": 1160
+    },
+    {
+      "epoch": 19.09968847352025,
+      "grad_norm": 1.8545303344726562,
+      "learning_rate": 1.2945629259917546e-07,
+      "loss": 0.2582,
+      "step": 1165
+    },
+    {
+      "epoch": 19.18276220145379,
+      "grad_norm": 1.8312244415283203,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.2447,
+      "step": 1170
+    },
+    {
+      "epoch": 19.265835929387332,
+      "grad_norm": 1.65512216091156,
+      "learning_rate": 6.607708248569377e-08,
+      "loss": 0.2456,
+      "step": 1175
+    },
+    {
+      "epoch": 19.34890965732087,
+      "grad_norm": 1.5663472414016724,
+      "learning_rate": 4.229604321829561e-08,
+      "loss": 0.246,
+      "step": 1180
+    },
+    {
+      "epoch": 19.431983385254412,
+      "grad_norm": 1.8947585821151733,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.243,
+      "step": 1185
+    },
+    {
+      "epoch": 19.515057113187954,
+      "grad_norm": 1.7258800268173218,
+      "learning_rate": 1.0576247944985018e-08,
+      "loss": 0.2435,
+      "step": 1190
+    },
+    {
+      "epoch": 19.598130841121495,
+      "grad_norm": 1.59407639503479,
+      "learning_rate": 2.6442018223132857e-09,
+      "loss": 0.2415,
+      "step": 1195
+    },
+    {
+      "epoch": 19.681204569055037,
+      "grad_norm": 1.5066112279891968,
+      "learning_rate": 0.0,
+      "loss": 0.2383,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.17534376829911e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-240/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/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-300/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-300/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,453 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.930425752855659,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.6620935797691345,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.985,
+      "step": 125
+    },
+    {
+      "epoch": 2.132917964693666,
+      "grad_norm": 0.7846258878707886,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.9594,
+      "step": 130
+    },
+    {
+      "epoch": 2.2159916926272065,
+      "grad_norm": 0.652454137802124,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.9322,
+      "step": 135
+    },
+    {
+      "epoch": 2.2990654205607477,
+      "grad_norm": 0.7020059823989868,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.9242,
+      "step": 140
+    },
+    {
+      "epoch": 2.382139148494289,
+      "grad_norm": 0.8148695826530457,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.8394,
+      "step": 145
+    },
+    {
+      "epoch": 2.4652128764278296,
+      "grad_norm": 0.8813133835792542,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.992,
+      "step": 150
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 0.7893730401992798,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.899,
+      "step": 155
+    },
+    {
+      "epoch": 2.6313603322949115,
+      "grad_norm": 0.7719221711158752,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.9416,
+      "step": 160
+    },
+    {
+      "epoch": 2.7144340602284527,
+      "grad_norm": 0.8439667820930481,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.8401,
+      "step": 165
+    },
+    {
+      "epoch": 2.797507788161994,
+      "grad_norm": 0.833251953125,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.817,
+      "step": 170
+    },
+    {
+      "epoch": 2.8805815160955346,
+      "grad_norm": 0.7526916265487671,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.8191,
+      "step": 175
+    },
+    {
+      "epoch": 2.9636552440290758,
+      "grad_norm": 1.0640058517456055,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8607,
+      "step": 180
+    },
+    {
+      "epoch": 3.0332294911734166,
+      "grad_norm": 0.784114420413971,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.761,
+      "step": 185
+    },
+    {
+      "epoch": 3.1163032191069573,
+      "grad_norm": 0.9396352767944336,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.6821,
+      "step": 190
+    },
+    {
+      "epoch": 3.1993769470404985,
+      "grad_norm": 0.9770582914352417,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.742,
+      "step": 195
+    },
+    {
+      "epoch": 3.2824506749740396,
+      "grad_norm": 0.8752853870391846,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.69,
+      "step": 200
+    },
+    {
+      "epoch": 3.3655244029075804,
+      "grad_norm": 0.8496589064598083,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.769,
+      "step": 205
+    },
+    {
+      "epoch": 3.4485981308411215,
+      "grad_norm": 0.8192639350891113,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.7298,
+      "step": 210
+    },
+    {
+      "epoch": 3.5316718587746623,
+      "grad_norm": 1.00070059299469,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.7815,
+      "step": 215
+    },
+    {
+      "epoch": 3.6147455867082035,
+      "grad_norm": 1.1614112854003906,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.7975,
+      "step": 220
+    },
+    {
+      "epoch": 3.6978193146417446,
+      "grad_norm": 1.014397382736206,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 3.7808930425752854,
+      "grad_norm": 0.9468530416488647,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.7194,
+      "step": 230
+    },
+    {
+      "epoch": 3.8639667705088265,
+      "grad_norm": 1.2201341390609741,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.7795,
+      "step": 235
+    },
+    {
+      "epoch": 3.9470404984423677,
+      "grad_norm": 0.9476346373558044,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.7202,
+      "step": 240
+    },
+    {
+      "epoch": 4.0166147455867085,
+      "grad_norm": 0.9945451021194458,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.6931,
+      "step": 245
+    },
+    {
+      "epoch": 4.099688473520249,
+      "grad_norm": 1.1113696098327637,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.6557,
+      "step": 250
+    },
+    {
+      "epoch": 4.18276220145379,
+      "grad_norm": 1.3515146970748901,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.6295,
+      "step": 255
+    },
+    {
+      "epoch": 4.265835929387332,
+      "grad_norm": 1.375272274017334,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.6423,
+      "step": 260
+    },
+    {
+      "epoch": 4.348909657320872,
+      "grad_norm": 1.1683202981948853,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.6167,
+      "step": 265
+    },
+    {
+      "epoch": 4.431983385254413,
+      "grad_norm": 1.2091785669326782,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.6373,
+      "step": 270
+    },
+    {
+      "epoch": 4.515057113187955,
+      "grad_norm": 1.3007235527038574,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.5941,
+      "step": 275
+    },
+    {
+      "epoch": 4.598130841121495,
+      "grad_norm": 1.2785530090332031,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.6384,
+      "step": 280
+    },
+    {
+      "epoch": 4.681204569055036,
+      "grad_norm": 1.2808083295822144,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.6592,
+      "step": 285
+    },
+    {
+      "epoch": 4.764278296988578,
+      "grad_norm": 1.1978651285171509,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.6285,
+      "step": 290
+    },
+    {
+      "epoch": 4.8473520249221185,
+      "grad_norm": 1.3983532190322876,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.5941,
+      "step": 295
+    },
+    {
+      "epoch": 4.930425752855659,
+      "grad_norm": 1.286287784576416,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5652,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2964982962520064e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-360/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-360/trainer_state.json

@@ -0,0 +1,537 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.913811007268951,
+  "eval_steps": 500,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.5125107169151306,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 3.5515,
+      "step": 5
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.4532736539840698,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 3.6807,
+      "step": 10
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.4483909606933594,
+      "learning_rate": 6.25e-06,
+      "loss": 3.5357,
+      "step": 15
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.5020395517349243,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.645,
+      "step": 20
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.8230155110359192,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 3.5682,
+      "step": 25
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 1.3333394527435303,
+      "learning_rate": 1.25e-05,
+      "loss": 3.5155,
+      "step": 30
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.7118450999259949,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 3.4724,
+      "step": 35
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 1.0282073020935059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.4205,
+      "step": 40
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0468826293945312,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.8730693459510803,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 3.0831,
+      "step": 50
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.9377574324607849,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 2.8412,
+      "step": 55
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 1.0129190683364868,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3229,
+      "step": 60
+    },
+    {
+      "epoch": 1.066458982346833,
+      "grad_norm": 0.8808080554008484,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 2.0489,
+      "step": 65
+    },
+    {
+      "epoch": 1.1495327102803738,
+      "grad_norm": 0.8092290759086609,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.9307,
+      "step": 70
+    },
+    {
+      "epoch": 1.2326064382139148,
+      "grad_norm": 0.8002105951309204,
+      "learning_rate": 3.125e-05,
+      "loss": 1.7402,
+      "step": 75
+    },
+    {
+      "epoch": 1.3156801661474558,
+      "grad_norm": 0.8581973314285278,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6696,
+      "step": 80
+    },
+    {
+      "epoch": 1.398753894080997,
+      "grad_norm": 0.7443532347679138,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 1.5175,
+      "step": 85
+    },
+    {
+      "epoch": 1.4818276220145379,
+      "grad_norm": 0.9584633708000183,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3968,
+      "step": 90
+    },
+    {
+      "epoch": 1.5649013499480788,
+      "grad_norm": 0.8683136105537415,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.299,
+      "step": 95
+    },
+    {
+      "epoch": 1.64797507788162,
+      "grad_norm": 0.7825261950492859,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.1271,
+      "step": 100
+    },
+    {
+      "epoch": 1.731048805815161,
+      "grad_norm": 0.654670000076294,
+      "learning_rate": 4.375e-05,
+      "loss": 1.14,
+      "step": 105
+    },
+    {
+      "epoch": 1.814122533748702,
+      "grad_norm": 0.7511588335037231,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.1614,
+      "step": 110
+    },
+    {
+      "epoch": 1.897196261682243,
+      "grad_norm": 0.6596113443374634,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.0587,
+      "step": 115
+    },
+    {
+      "epoch": 1.980269989615784,
+      "grad_norm": 0.7166474461555481,
+      "learning_rate": 5e-05,
+      "loss": 1.0169,
+      "step": 120
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.6620935797691345,
+      "learning_rate": 4.999735579817769e-05,
+      "loss": 0.985,
+      "step": 125
+    },
+    {
+      "epoch": 2.132917964693666,
+      "grad_norm": 0.7846258878707886,
+      "learning_rate": 4.998942375205502e-05,
+      "loss": 0.9594,
+      "step": 130
+    },
+    {
+      "epoch": 2.2159916926272065,
+      "grad_norm": 0.652454137802124,
+      "learning_rate": 4.997620553954645e-05,
+      "loss": 0.9322,
+      "step": 135
+    },
+    {
+      "epoch": 2.2990654205607477,
+      "grad_norm": 0.7020059823989868,
+      "learning_rate": 4.995770395678171e-05,
+      "loss": 0.9242,
+      "step": 140
+    },
+    {
+      "epoch": 2.382139148494289,
+      "grad_norm": 0.8148695826530457,
+      "learning_rate": 4.993392291751431e-05,
+      "loss": 0.8394,
+      "step": 145
+    },
+    {
+      "epoch": 2.4652128764278296,
+      "grad_norm": 0.8813133835792542,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 0.992,
+      "step": 150
+    },
+    {
+      "epoch": 2.5482866043613708,
+      "grad_norm": 0.7893730401992798,
+      "learning_rate": 4.987054370740083e-05,
+      "loss": 0.899,
+      "step": 155
+    },
+    {
+      "epoch": 2.6313603322949115,
+      "grad_norm": 0.7719221711158752,
+      "learning_rate": 4.983095894354858e-05,
+      "loss": 0.9416,
+      "step": 160
+    },
+    {
+      "epoch": 2.7144340602284527,
+      "grad_norm": 0.8439667820930481,
+      "learning_rate": 4.9786121534345265e-05,
+      "loss": 0.8401,
+      "step": 165
+    },
+    {
+      "epoch": 2.797507788161994,
+      "grad_norm": 0.833251953125,
+      "learning_rate": 4.973604096452361e-05,
+      "loss": 0.817,
+      "step": 170
+    },
+    {
+      "epoch": 2.8805815160955346,
+      "grad_norm": 0.7526916265487671,
+      "learning_rate": 4.9680727827934354e-05,
+      "loss": 0.8191,
+      "step": 175
+    },
+    {
+      "epoch": 2.9636552440290758,
+      "grad_norm": 1.0640058517456055,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8607,
+      "step": 180
+    },
+    {
+      "epoch": 3.0332294911734166,
+      "grad_norm": 0.784114420413971,
+      "learning_rate": 4.9554451761765766e-05,
+      "loss": 0.761,
+      "step": 185
+    },
+    {
+      "epoch": 3.1163032191069573,
+      "grad_norm": 0.9396352767944336,
+      "learning_rate": 4.948351554413879e-05,
+      "loss": 0.6821,
+      "step": 190
+    },
+    {
+      "epoch": 3.1993769470404985,
+      "grad_norm": 0.9770582914352417,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 0.742,
+      "step": 195
+    },
+    {
+      "epoch": 3.2824506749740396,
+      "grad_norm": 0.8752853870391846,
+      "learning_rate": 4.9326121764495596e-05,
+      "loss": 0.69,
+      "step": 200
+    },
+    {
+      "epoch": 3.3655244029075804,
+      "grad_norm": 0.8496589064598083,
+      "learning_rate": 4.92396974969529e-05,
+      "loss": 0.769,
+      "step": 205
+    },
+    {
+      "epoch": 3.4485981308411215,
+      "grad_norm": 0.8192639350891113,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.7298,
+      "step": 210
+    },
+    {
+      "epoch": 3.5316718587746623,
+      "grad_norm": 1.00070059299469,
+      "learning_rate": 4.905148561184033e-05,
+      "loss": 0.7815,
+      "step": 215
+    },
+    {
+      "epoch": 3.6147455867082035,
+      "grad_norm": 1.1614112854003906,
+      "learning_rate": 4.894973780788722e-05,
+      "loss": 0.7975,
+      "step": 220
+    },
+    {
+      "epoch": 3.6978193146417446,
+      "grad_norm": 1.014397382736206,
+      "learning_rate": 4.884292376870567e-05,
+      "loss": 0.696,
+      "step": 225
+    },
+    {
+      "epoch": 3.7808930425752854,
+      "grad_norm": 0.9468530416488647,
+      "learning_rate": 4.873106608932585e-05,
+      "loss": 0.7194,
+      "step": 230
+    },
+    {
+      "epoch": 3.8639667705088265,
+      "grad_norm": 1.2201341390609741,
+      "learning_rate": 4.8614188431690125e-05,
+      "loss": 0.7795,
+      "step": 235
+    },
+    {
+      "epoch": 3.9470404984423677,
+      "grad_norm": 0.9476346373558044,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.7202,
+      "step": 240
+    },
+    {
+      "epoch": 4.0166147455867085,
+      "grad_norm": 0.9945451021194458,
+      "learning_rate": 4.836547313372471e-05,
+      "loss": 0.6931,
+      "step": 245
+    },
+    {
+      "epoch": 4.099688473520249,
+      "grad_norm": 1.1113696098327637,
+      "learning_rate": 4.823368810567056e-05,
+      "loss": 0.6557,
+      "step": 250
+    },
+    {
+      "epoch": 4.18276220145379,
+      "grad_norm": 1.3515146970748901,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.6295,
+      "step": 255
+    },
+    {
+      "epoch": 4.265835929387332,
+      "grad_norm": 1.375272274017334,
+      "learning_rate": 4.7955402672006854e-05,
+      "loss": 0.6423,
+      "step": 260
+    },
+    {
+      "epoch": 4.348909657320872,
+      "grad_norm": 1.1683202981948853,
+      "learning_rate": 4.780896113382536e-05,
+      "loss": 0.6167,
+      "step": 265
+    },
+    {
+      "epoch": 4.431983385254413,
+      "grad_norm": 1.2091785669326782,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 0.6373,
+      "step": 270
+    },
+    {
+      "epoch": 4.515057113187955,
+      "grad_norm": 1.3007235527038574,
+      "learning_rate": 4.750163529660303e-05,
+      "loss": 0.5941,
+      "step": 275
+    },
+    {
+      "epoch": 4.598130841121495,
+      "grad_norm": 1.2785530090332031,
+      "learning_rate": 4.734081600808531e-05,
+      "loss": 0.6384,
+      "step": 280
+    },
+    {
+      "epoch": 4.681204569055036,
+      "grad_norm": 1.2808083295822144,
+      "learning_rate": 4.717527082945554e-05,
+      "loss": 0.6592,
+      "step": 285
+    },
+    {
+      "epoch": 4.764278296988578,
+      "grad_norm": 1.1978651285171509,
+      "learning_rate": 4.700503477950278e-05,
+      "loss": 0.6285,
+      "step": 290
+    },
+    {
+      "epoch": 4.8473520249221185,
+      "grad_norm": 1.3983532190322876,
+      "learning_rate": 4.68301438693049e-05,
+      "loss": 0.5941,
+      "step": 295
+    },
+    {
+      "epoch": 4.930425752855659,
+      "grad_norm": 1.286287784576416,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5652,
+      "step": 300
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1714959144592285,
+      "learning_rate": 4.6466546428015336e-05,
+      "loss": 0.5657,
+      "step": 305
+    },
+    {
+      "epoch": 5.083073727933541,
+      "grad_norm": 1.0886554718017578,
+      "learning_rate": 4.627791681092499e-05,
+      "loss": 0.4776,
+      "step": 310
+    },
+    {
+      "epoch": 5.166147455867082,
+      "grad_norm": 1.3735958337783813,
+      "learning_rate": 4.608478614532215e-05,
+      "loss": 0.5114,
+      "step": 315
+    },
+    {
+      "epoch": 5.249221183800623,
+      "grad_norm": 1.5809016227722168,
+      "learning_rate": 4.588719528532342e-05,
+      "loss": 0.5537,
+      "step": 320
+    },
+    {
+      "epoch": 5.332294911734164,
+      "grad_norm": 1.401424765586853,
+      "learning_rate": 4.568518602853776e-05,
+      "loss": 0.5299,
+      "step": 325
+    },
+    {
+      "epoch": 5.415368639667705,
+      "grad_norm": 1.467054009437561,
+      "learning_rate": 4.54788011072248e-05,
+      "loss": 0.5236,
+      "step": 330
+    },
+    {
+      "epoch": 5.498442367601246,
+      "grad_norm": 1.253794550895691,
+      "learning_rate": 4.526808417925531e-05,
+      "loss": 0.5632,
+      "step": 335
+    },
+    {
+      "epoch": 5.581516095534787,
+      "grad_norm": 1.4579623937606812,
+      "learning_rate": 4.50530798188761e-05,
+      "loss": 0.5556,
+      "step": 340
+    },
+    {
+      "epoch": 5.6645898234683285,
+      "grad_norm": 1.171007513999939,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 0.4934,
+      "step": 345
+    },
+    {
+      "epoch": 5.747663551401869,
+      "grad_norm": 1.4656859636306763,
+      "learning_rate": 4.4610391622989396e-05,
+      "loss": 0.5697,
+      "step": 350
+    },
+    {
+      "epoch": 5.83073727933541,
+      "grad_norm": 1.4671518802642822,
+      "learning_rate": 4.438280143203665e-05,
+      "loss": 0.5289,
+      "step": 355
+    },
+    {
+      "epoch": 5.913811007268951,
+      "grad_norm": 1.4010504484176636,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.5205,
+      "step": 360
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.55508799438848e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508d90851f4db1439298132930380474391f2e78406a216cc2d4a2ac7b8a691d
+size 5624

checkpoint-420/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-540/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d338e8c50bedd17cce5e4eb20522109aaff1ade960d2c72bddac80cd74f16905
+size 1064

checkpoint-540/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-60/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
+}