Add files using upload-large-folder tool

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-14B-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-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the parsed_data 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: 4
+- total_train_batch_size: 8
+- 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: 8
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.0
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "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": 7.9523809523809526,
+    "total_flos": 2.698353498390528e+16,
+    "train_loss": 0.720484851841714,
+    "train_runtime": 3774.6002,
+    "train_samples_per_second": 2.67,
+    "train_steps_per_second": 0.333
+}

card.json

@@ -0,0 +1,24 @@
+{
+    "name": "openshift-microshift-epoch8-2025-Apr-06",
+    "base_model": "Qwen/Qwen2.5-Coder-14B-Instruct" ,
+    "context_length": 8192,
+    "model_type": "qwen",
+    "quantized": "true",
+    "finetune_steps": [
+        {
+            "base_model": "Qwen/Qwen2.5-Coder-14B-Instruct",
+            "step": 2,
+            "data": "parsed_data",
+            "epochs": "8",
+            "batch_size": "8",
+            "dataset_size": "1260",
+            "num_tests": ""
+        }
+    ],
+    "project": "openshift/microshift",
+    "prompt_template": {
+        "user_tag": "<|start_header_id|>user<|end_header_id|>",
+        "end_tag": "<|eot_id|>",
+        "assistant_tag": "<|start_header_id|>assistant<|end_header_id|>"
+    }
+}

checkpoint-1099/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-1099/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1099/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-1099/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-1099/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-1099/trainer_state.json

@@ -0,0 +1,1567 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.958730158730159,
+  "eval_steps": 500,
+  "global_step": 1099,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    },
+    {
+      "epoch": 1.0126984126984127,
+      "grad_norm": 1.5468761920928955,
+      "learning_rate": 4.9888394060315975e-05,
+      "loss": 1.0614,
+      "step": 160
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 1.3189973831176758,
+      "learning_rate": 4.9853189685938837e-05,
+      "loss": 0.8396,
+      "step": 165
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 1.0562372207641602,
+      "learning_rate": 4.981318291512396e-05,
+      "loss": 0.8926,
+      "step": 170
+    },
+    {
+      "epoch": 1.107936507936508,
+      "grad_norm": 0.9939103722572327,
+      "learning_rate": 4.976838147840314e-05,
+      "loss": 0.9728,
+      "step": 175
+    },
+    {
+      "epoch": 1.1396825396825396,
+      "grad_norm": 1.6342549324035645,
+      "learning_rate": 4.971879403278432e-05,
+      "loss": 0.8781,
+      "step": 180
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 1.3527770042419434,
+      "learning_rate": 4.966443016007873e-05,
+      "loss": 1.0276,
+      "step": 185
+    },
+    {
+      "epoch": 1.2031746031746031,
+      "grad_norm": 1.2593631744384766,
+      "learning_rate": 4.960530036504942e-05,
+      "loss": 0.9742,
+      "step": 190
+    },
+    {
+      "epoch": 1.234920634920635,
+      "grad_norm": 1.2724119424819946,
+      "learning_rate": 4.9541416073381395e-05,
+      "loss": 0.7572,
+      "step": 195
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.2241063117980957,
+      "learning_rate": 4.947278962947387e-05,
+      "loss": 0.8872,
+      "step": 200
+    },
+    {
+      "epoch": 1.2984126984126985,
+      "grad_norm": 1.0864907503128052,
+      "learning_rate": 4.9399434294054894e-05,
+      "loss": 0.9463,
+      "step": 205
+    },
+    {
+      "epoch": 1.33015873015873,
+      "grad_norm": 1.2503291368484497,
+      "learning_rate": 4.9321364241618994e-05,
+      "loss": 0.8187,
+      "step": 210
+    },
+    {
+      "epoch": 1.361904761904762,
+      "grad_norm": 1.2996984720230103,
+      "learning_rate": 4.9238594557688265e-05,
+      "loss": 0.9949,
+      "step": 215
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 1.2346172332763672,
+      "learning_rate": 4.9151141235897324e-05,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 1.4253968253968254,
+      "grad_norm": 1.3184157609939575,
+      "learning_rate": 4.905902117490291e-05,
+      "loss": 0.9109,
+      "step": 225
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 1.4319523572921753,
+      "learning_rate": 4.89622521751185e-05,
+      "loss": 0.9854,
+      "step": 230
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.458723545074463,
+      "learning_rate": 4.886085293527474e-05,
+      "loss": 0.9916,
+      "step": 235
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 1.2609443664550781,
+      "learning_rate": 4.8754843048806296e-05,
+      "loss": 0.9446,
+      "step": 240
+    },
+    {
+      "epoch": 1.5523809523809524,
+      "grad_norm": 1.1162338256835938,
+      "learning_rate": 4.864424300006579e-05,
+      "loss": 0.746,
+      "step": 245
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "grad_norm": 1.4760407209396362,
+      "learning_rate": 4.852907416036559e-05,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 1.615873015873016,
+      "grad_norm": 1.4606406688690186,
+      "learning_rate": 4.8409358783848216e-05,
+      "loss": 0.8501,
+      "step": 255
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 1.4926954507827759,
+      "learning_rate": 4.828512000318617e-05,
+      "loss": 0.8581,
+      "step": 260
+    },
+    {
+      "epoch": 1.6793650793650794,
+      "grad_norm": 1.7399059534072876,
+      "learning_rate": 4.8156381825112006e-05,
+      "loss": 0.8994,
+      "step": 265
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.2087697982788086,
+      "learning_rate": 4.8023169125779466e-05,
+      "loss": 0.8272,
+      "step": 270
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.5295592546463013,
+      "learning_rate": 4.788550764595667e-05,
+      "loss": 0.8555,
+      "step": 275
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 1.6441818475723267,
+      "learning_rate": 4.774342398605221e-05,
+      "loss": 0.768,
+      "step": 280
+    },
+    {
+      "epoch": 1.8063492063492064,
+      "grad_norm": 1.8932971954345703,
+      "learning_rate": 4.759694560097513e-05,
+      "loss": 0.9286,
+      "step": 285
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 1.565648078918457,
+      "learning_rate": 4.7446100794829785e-05,
+      "loss": 0.7844,
+      "step": 290
+    },
+    {
+      "epoch": 1.8698412698412699,
+      "grad_norm": 1.4803764820098877,
+      "learning_rate": 4.7290918715446644e-05,
+      "loss": 0.9625,
+      "step": 295
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 1.2535064220428467,
+      "learning_rate": 4.7131429348750055e-05,
+      "loss": 0.7778,
+      "step": 300
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4900981187820435,
+      "learning_rate": 4.6967663512963986e-05,
+      "loss": 0.6377,
+      "step": 305
+    },
+    {
+      "epoch": 1.9650793650793652,
+      "grad_norm": 1.5180715322494507,
+      "learning_rate": 4.6799652852657064e-05,
+      "loss": 0.8705,
+      "step": 310
+    },
+    {
+      "epoch": 1.9968253968253968,
+      "grad_norm": 1.074388027191162,
+      "learning_rate": 4.662742983262784e-05,
+      "loss": 0.589,
+      "step": 315
+    },
+    {
+      "epoch": 2.0253968253968253,
+      "grad_norm": 1.4143909215927124,
+      "learning_rate": 4.64510277316316e-05,
+      "loss": 0.675,
+      "step": 320
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 1.4869240522384644,
+      "learning_rate": 4.6270480635949933e-05,
+      "loss": 0.7768,
+      "step": 325
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.4446533918380737,
+      "learning_rate": 4.6085823432804144e-05,
+      "loss": 0.6516,
+      "step": 330
+    },
+    {
+      "epoch": 2.1206349206349207,
+      "grad_norm": 1.8745191097259521,
+      "learning_rate": 4.589709180361403e-05,
+      "loss": 0.7022,
+      "step": 335
+    },
+    {
+      "epoch": 2.1523809523809523,
+      "grad_norm": 1.678874135017395,
+      "learning_rate": 4.5704322217103146e-05,
+      "loss": 0.7443,
+      "step": 340
+    },
+    {
+      "epoch": 2.1841269841269844,
+      "grad_norm": 2.3285534381866455,
+      "learning_rate": 4.550755192225188e-05,
+      "loss": 0.6574,
+      "step": 345
+    },
+    {
+      "epoch": 2.215873015873016,
+      "grad_norm": 1.537413239479065,
+      "learning_rate": 4.530681894109987e-05,
+      "loss": 0.6493,
+      "step": 350
+    },
+    {
+      "epoch": 2.2476190476190476,
+      "grad_norm": 1.8794249296188354,
+      "learning_rate": 4.510216206139894e-05,
+      "loss": 0.7287,
+      "step": 355
+    },
+    {
+      "epoch": 2.2793650793650793,
+      "grad_norm": 1.5752090215682983,
+      "learning_rate": 4.489362082911813e-05,
+      "loss": 0.6171,
+      "step": 360
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5545966625213623,
+      "learning_rate": 4.4681235540802216e-05,
+      "loss": 0.5651,
+      "step": 365
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 1.6034917831420898,
+      "learning_rate": 4.446504723578519e-05,
+      "loss": 0.6758,
+      "step": 370
+    },
+    {
+      "epoch": 2.3746031746031746,
+      "grad_norm": 2.2822070121765137,
+      "learning_rate": 4.424509768826017e-05,
+      "loss": 0.7167,
+      "step": 375
+    },
+    {
+      "epoch": 2.4063492063492062,
+      "grad_norm": 1.3968263864517212,
+      "learning_rate": 4.4021429399207405e-05,
+      "loss": 0.6388,
+      "step": 380
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 2.0151493549346924,
+      "learning_rate": 4.3794085588181725e-05,
+      "loss": 0.8385,
+      "step": 385
+    },
+    {
+      "epoch": 2.46984126984127,
+      "grad_norm": 2.2131729125976562,
+      "learning_rate": 4.3563110184961235e-05,
+      "loss": 0.8482,
+      "step": 390
+    },
+    {
+      "epoch": 2.5015873015873016,
+      "grad_norm": 1.9444142580032349,
+      "learning_rate": 4.332854782105875e-05,
+      "loss": 0.7357,
+      "step": 395
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.3676568269729614,
+      "learning_rate": 4.309044382109757e-05,
+      "loss": 0.6352,
+      "step": 400
+    },
+    {
+      "epoch": 2.565079365079365,
+      "grad_norm": 1.5921475887298584,
+      "learning_rate": 4.2848844194053455e-05,
+      "loss": 0.6742,
+      "step": 405
+    },
+    {
+      "epoch": 2.596825396825397,
+      "grad_norm": 2.04608154296875,
+      "learning_rate": 4.26037956243642e-05,
+      "loss": 0.7472,
+      "step": 410
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 1.6338012218475342,
+      "learning_rate": 4.235534546290883e-05,
+      "loss": 0.5659,
+      "step": 415
+    },
+    {
+      "epoch": 2.66031746031746,
+      "grad_norm": 2.2755625247955322,
+      "learning_rate": 4.2103541717857956e-05,
+      "loss": 0.6775,
+      "step": 420
+    },
+    {
+      "epoch": 2.6920634920634923,
+      "grad_norm": 1.8385895490646362,
+      "learning_rate": 4.184843304539708e-05,
+      "loss": 0.5902,
+      "step": 425
+    },
+    {
+      "epoch": 2.723809523809524,
+      "grad_norm": 2.394862174987793,
+      "learning_rate": 4.1590068740324806e-05,
+      "loss": 0.623,
+      "step": 430
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9886717796325684,
+      "learning_rate": 4.132849872652751e-05,
+      "loss": 0.6361,
+      "step": 435
+    },
+    {
+      "epoch": 2.787301587301587,
+      "grad_norm": 2.674502372741699,
+      "learning_rate": 4.106377354733259e-05,
+      "loss": 0.6835,
+      "step": 440
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 2.432657480239868,
+      "learning_rate": 4.079594435574186e-05,
+      "loss": 0.592,
+      "step": 445
+    },
+    {
+      "epoch": 2.850793650793651,
+      "grad_norm": 1.8935447931289673,
+      "learning_rate": 4.0525062904547276e-05,
+      "loss": 0.629,
+      "step": 450
+    },
+    {
+      "epoch": 2.8825396825396825,
+      "grad_norm": 2.635646343231201,
+      "learning_rate": 4.025118153633075e-05,
+      "loss": 0.7282,
+      "step": 455
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 2.8444085121154785,
+      "learning_rate": 3.9974353173349886e-05,
+      "loss": 0.7106,
+      "step": 460
+    },
+    {
+      "epoch": 2.9460317460317462,
+      "grad_norm": 2.6861064434051514,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.6447,
+      "step": 465
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 2.7277615070343018,
+      "learning_rate": 3.9412069989037015e-05,
+      "loss": 0.563,
+      "step": 470
+    },
+    {
+      "epoch": 3.0063492063492063,
+      "grad_norm": 1.8300037384033203,
+      "learning_rate": 3.91267238180149e-05,
+      "loss": 0.5555,
+      "step": 475
+    },
+    {
+      "epoch": 3.038095238095238,
+      "grad_norm": 2.206399917602539,
+      "learning_rate": 3.883864793185369e-05,
+      "loss": 0.4926,
+      "step": 480
+    },
+    {
+      "epoch": 3.06984126984127,
+      "grad_norm": 2.5881357192993164,
+      "learning_rate": 3.854789799562602e-05,
+      "loss": 0.5441,
+      "step": 485
+    },
+    {
+      "epoch": 3.1015873015873017,
+      "grad_norm": 2.2896475791931152,
+      "learning_rate": 3.825453019111281e-05,
+      "loss": 0.498,
+      "step": 490
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 2.622668981552124,
+      "learning_rate": 3.7958601205947234e-05,
+      "loss": 0.5055,
+      "step": 495
+    },
+    {
+      "epoch": 3.165079365079365,
+      "grad_norm": 3.064993381500244,
+      "learning_rate": 3.766016822266083e-05,
+      "loss": 0.5348,
+      "step": 500
+    },
+    {
+      "epoch": 3.196825396825397,
+      "grad_norm": 3.3422789573669434,
+      "learning_rate": 3.7359288907634225e-05,
+      "loss": 0.5869,
+      "step": 505
+    },
+    {
+      "epoch": 3.2285714285714286,
+      "grad_norm": 2.460176467895508,
+      "learning_rate": 3.705602139995416e-05,
+      "loss": 0.5228,
+      "step": 510
+    },
+    {
+      "epoch": 3.2603174603174603,
+      "grad_norm": 2.6845529079437256,
+      "learning_rate": 3.675042430017923e-05,
+      "loss": 0.4544,
+      "step": 515
+    },
+    {
+      "epoch": 3.292063492063492,
+      "grad_norm": 2.378709077835083,
+      "learning_rate": 3.6442556659016484e-05,
+      "loss": 0.5201,
+      "step": 520
+    },
+    {
+      "epoch": 3.323809523809524,
+      "grad_norm": 2.2331037521362305,
+      "learning_rate": 3.613247796591101e-05,
+      "loss": 0.4924,
+      "step": 525
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 2.702828884124756,
+      "learning_rate": 3.582024813755077e-05,
+      "loss": 0.5358,
+      "step": 530
+    },
+    {
+      "epoch": 3.3873015873015873,
+      "grad_norm": 2.3180782794952393,
+      "learning_rate": 3.550592750628885e-05,
+      "loss": 0.5862,
+      "step": 535
+    },
+    {
+      "epoch": 3.419047619047619,
+      "grad_norm": 2.6038239002227783,
+      "learning_rate": 3.5189576808485407e-05,
+      "loss": 0.5303,
+      "step": 540
+    },
+    {
+      "epoch": 3.450793650793651,
+      "grad_norm": 3.0068862438201904,
+      "learning_rate": 3.4871257172771555e-05,
+      "loss": 0.4848,
+      "step": 545
+    },
+    {
+      "epoch": 3.4825396825396826,
+      "grad_norm": 2.6912105083465576,
+      "learning_rate": 3.455103010823744e-05,
+      "loss": 0.5653,
+      "step": 550
+    },
+    {
+      "epoch": 3.5142857142857142,
+      "grad_norm": 3.0676960945129395,
+      "learning_rate": 3.422895749254677e-05,
+      "loss": 0.5993,
+      "step": 555
+    },
+    {
+      "epoch": 3.546031746031746,
+      "grad_norm": 2.376481533050537,
+      "learning_rate": 3.390510155998023e-05,
+      "loss": 0.5484,
+      "step": 560
+    },
+    {
+      "epoch": 3.5777777777777775,
+      "grad_norm": 2.4998154640197754,
+      "learning_rate": 3.357952488940984e-05,
+      "loss": 0.502,
+      "step": 565
+    },
+    {
+      "epoch": 3.6095238095238096,
+      "grad_norm": 2.900434970855713,
+      "learning_rate": 3.325229039220684e-05,
+      "loss": 0.4531,
+      "step": 570
+    },
+    {
+      "epoch": 3.641269841269841,
+      "grad_norm": 3.2575416564941406,
+      "learning_rate": 3.2923461300085305e-05,
+      "loss": 0.5703,
+      "step": 575
+    },
+    {
+      "epoch": 3.6730158730158733,
+      "grad_norm": 2.449436902999878,
+      "learning_rate": 3.2593101152883796e-05,
+      "loss": 0.5894,
+      "step": 580
+    },
+    {
+      "epoch": 3.704761904761905,
+      "grad_norm": 2.860034227371216,
+      "learning_rate": 3.226127378628756e-05,
+      "loss": 0.557,
+      "step": 585
+    },
+    {
+      "epoch": 3.7365079365079366,
+      "grad_norm": 2.4020888805389404,
+      "learning_rate": 3.19280433194935e-05,
+      "loss": 0.4805,
+      "step": 590
+    },
+    {
+      "epoch": 3.768253968253968,
+      "grad_norm": 2.56815767288208,
+      "learning_rate": 3.15934741428204e-05,
+      "loss": 0.5097,
+      "step": 595
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 1.385717749595642,
+      "learning_rate": 3.1257630905266746e-05,
+      "loss": 0.4136,
+      "step": 600
+    },
+    {
+      "epoch": 3.831746031746032,
+      "grad_norm": 2.7889769077301025,
+      "learning_rate": 3.092057850201855e-05,
+      "loss": 0.4979,
+      "step": 605
+    },
+    {
+      "epoch": 3.8634920634920635,
+      "grad_norm": 2.0486621856689453,
+      "learning_rate": 3.058238206190962e-05,
+      "loss": 0.4226,
+      "step": 610
+    },
+    {
+      "epoch": 3.895238095238095,
+      "grad_norm": 2.6471216678619385,
+      "learning_rate": 3.0243106934836686e-05,
+      "loss": 0.5591,
+      "step": 615
+    },
+    {
+      "epoch": 3.9269841269841272,
+      "grad_norm": 2.7665154933929443,
+      "learning_rate": 2.9902818679131776e-05,
+      "loss": 0.4856,
+      "step": 620
+    },
+    {
+      "epoch": 3.958730158730159,
+      "grad_norm": 2.2888855934143066,
+      "learning_rate": 2.9561583048894382e-05,
+      "loss": 0.4661,
+      "step": 625
+    },
+    {
+      "epoch": 3.9904761904761905,
+      "grad_norm": 2.540665864944458,
+      "learning_rate": 2.9219465981285716e-05,
+      "loss": 0.5027,
+      "step": 630
+    },
+    {
+      "epoch": 4.019047619047619,
+      "grad_norm": 2.840465545654297,
+      "learning_rate": 2.8876533583787647e-05,
+      "loss": 0.5111,
+      "step": 635
+    },
+    {
+      "epoch": 4.050793650793651,
+      "grad_norm": 2.362541437149048,
+      "learning_rate": 2.8532852121428737e-05,
+      "loss": 0.4652,
+      "step": 640
+    },
+    {
+      "epoch": 4.082539682539682,
+      "grad_norm": 2.4384407997131348,
+      "learning_rate": 2.8188488003979784e-05,
+      "loss": 0.4227,
+      "step": 645
+    },
+    {
+      "epoch": 4.114285714285714,
+      "grad_norm": 2.5572218894958496,
+      "learning_rate": 2.784350777312142e-05,
+      "loss": 0.3772,
+      "step": 650
+    },
+    {
+      "epoch": 4.146031746031746,
+      "grad_norm": 2.4390878677368164,
+      "learning_rate": 2.7497978089586236e-05,
+      "loss": 0.4704,
+      "step": 655
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 3.3781797885894775,
+      "learning_rate": 2.7151965720277893e-05,
+      "loss": 0.4303,
+      "step": 660
+    },
+    {
+      "epoch": 4.20952380952381,
+      "grad_norm": 2.8656809329986572,
+      "learning_rate": 2.6805537525369713e-05,
+      "loss": 0.4128,
+      "step": 665
+    },
+    {
+      "epoch": 4.241269841269841,
+      "grad_norm": 4.3884100914001465,
+      "learning_rate": 2.6458760445385216e-05,
+      "loss": 0.4682,
+      "step": 670
+    },
+    {
+      "epoch": 4.273015873015873,
+      "grad_norm": 3.1728439331054688,
+      "learning_rate": 2.6111701488263224e-05,
+      "loss": 0.4208,
+      "step": 675
+    },
+    {
+      "epoch": 4.304761904761905,
+      "grad_norm": 2.4535300731658936,
+      "learning_rate": 2.5764427716409815e-05,
+      "loss": 0.4489,
+      "step": 680
+    },
+    {
+      "epoch": 4.336507936507936,
+      "grad_norm": 2.231412887573242,
+      "learning_rate": 2.5417006233739864e-05,
+      "loss": 0.4079,
+      "step": 685
+    },
+    {
+      "epoch": 4.368253968253969,
+      "grad_norm": 2.2064919471740723,
+      "learning_rate": 2.5069504172710494e-05,
+      "loss": 0.4157,
+      "step": 690
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.6554882526397705,
+      "learning_rate": 2.4721988681349012e-05,
+      "loss": 0.544,
+      "step": 695
+    },
+    {
+      "epoch": 4.431746031746032,
+      "grad_norm": 2.739560842514038,
+      "learning_rate": 2.437452691027789e-05,
+      "loss": 0.4366,
+      "step": 700
+    },
+    {
+      "epoch": 4.463492063492064,
+      "grad_norm": 2.2243738174438477,
+      "learning_rate": 2.402718599973919e-05,
+      "loss": 0.3831,
+      "step": 705
+    },
+    {
+      "epoch": 4.495238095238095,
+      "grad_norm": 2.6665985584259033,
+      "learning_rate": 2.3680033066621043e-05,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 4.526984126984127,
+      "grad_norm": 2.7318532466888428,
+      "learning_rate": 2.3333135191488563e-05,
+      "loss": 0.4055,
+      "step": 715
+    },
+    {
+      "epoch": 4.5587301587301585,
+      "grad_norm": 2.6442530155181885,
+      "learning_rate": 2.298655940562189e-05,
+      "loss": 0.3967,
+      "step": 720
+    },
+    {
+      "epoch": 4.59047619047619,
+      "grad_norm": 2.543417453765869,
+      "learning_rate": 2.2640372678063628e-05,
+      "loss": 0.3863,
+      "step": 725
+    },
+    {
+      "epoch": 4.622222222222222,
+      "grad_norm": 2.905043363571167,
+      "learning_rate": 2.2294641902678445e-05,
+      "loss": 0.3996,
+      "step": 730
+    },
+    {
+      "epoch": 4.653968253968254,
+      "grad_norm": 1.9619908332824707,
+      "learning_rate": 2.19494338852271e-05,
+      "loss": 0.4122,
+      "step": 735
+    },
+    {
+      "epoch": 4.685714285714286,
+      "grad_norm": 2.6673147678375244,
+      "learning_rate": 2.1604815330457512e-05,
+      "loss": 0.478,
+      "step": 740
+    },
+    {
+      "epoch": 4.717460317460318,
+      "grad_norm": 2.735572099685669,
+      "learning_rate": 2.1260852829215406e-05,
+      "loss": 0.4408,
+      "step": 745
+    },
+    {
+      "epoch": 4.749206349206349,
+      "grad_norm": 2.9399704933166504,
+      "learning_rate": 2.0917612845576885e-05,
+      "loss": 0.4422,
+      "step": 750
+    },
+    {
+      "epoch": 4.780952380952381,
+      "grad_norm": 2.5321192741394043,
+      "learning_rate": 2.057516170400554e-05,
+      "loss": 0.3983,
+      "step": 755
+    },
+    {
+      "epoch": 4.8126984126984125,
+      "grad_norm": 2.2827346324920654,
+      "learning_rate": 2.0233565576536567e-05,
+      "loss": 0.4235,
+      "step": 760
+    },
+    {
+      "epoch": 4.844444444444444,
+      "grad_norm": 3.497560739517212,
+      "learning_rate": 1.9892890469990264e-05,
+      "loss": 0.4277,
+      "step": 765
+    },
+    {
+      "epoch": 4.876190476190477,
+      "grad_norm": 2.7729287147521973,
+      "learning_rate": 1.955320221321754e-05,
+      "loss": 0.3638,
+      "step": 770
+    },
+    {
+      "epoch": 4.907936507936508,
+      "grad_norm": 3.169905424118042,
+      "learning_rate": 1.921456644437972e-05,
+      "loss": 0.4323,
+      "step": 775
+    },
+    {
+      "epoch": 4.93968253968254,
+      "grad_norm": 3.217583417892456,
+      "learning_rate": 1.8877048598265283e-05,
+      "loss": 0.4467,
+      "step": 780
+    },
+    {
+      "epoch": 4.9714285714285715,
+      "grad_norm": 2.79040789604187,
+      "learning_rate": 1.8540713893645827e-05,
+      "loss": 0.3856,
+      "step": 785
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.346138000488281,
+      "learning_rate": 1.8205627320673837e-05,
+      "loss": 0.4324,
+      "step": 790
+    },
+    {
+      "epoch": 5.031746031746032,
+      "grad_norm": 2.163886070251465,
+      "learning_rate": 1.787185362832459e-05,
+      "loss": 0.3076,
+      "step": 795
+    },
+    {
+      "epoch": 5.063492063492063,
+      "grad_norm": 2.5888731479644775,
+      "learning_rate": 1.7539457311884676e-05,
+      "loss": 0.3277,
+      "step": 800
+    },
+    {
+      "epoch": 5.095238095238095,
+      "grad_norm": 2.4321916103363037,
+      "learning_rate": 1.720850260048948e-05,
+      "loss": 0.286,
+      "step": 805
+    },
+    {
+      "epoch": 5.1269841269841265,
+      "grad_norm": 1.7569212913513184,
+      "learning_rate": 1.687905344471226e-05,
+      "loss": 0.3328,
+      "step": 810
+    },
+    {
+      "epoch": 5.158730158730159,
+      "grad_norm": 2.9200055599212646,
+      "learning_rate": 1.6551173504206853e-05,
+      "loss": 0.4124,
+      "step": 815
+    },
+    {
+      "epoch": 5.190476190476191,
+      "grad_norm": 3.5868027210235596,
+      "learning_rate": 1.6224926135406693e-05,
+      "loss": 0.3896,
+      "step": 820
+    },
+    {
+      "epoch": 5.222222222222222,
+      "grad_norm": 2.3882710933685303,
+      "learning_rate": 1.5900374379282445e-05,
+      "loss": 0.4112,
+      "step": 825
+    },
+    {
+      "epoch": 5.253968253968254,
+      "grad_norm": 2.136838912963867,
+      "learning_rate": 1.557758094916053e-05,
+      "loss": 0.3479,
+      "step": 830
+    },
+    {
+      "epoch": 5.285714285714286,
+      "grad_norm": 2.6616430282592773,
+      "learning_rate": 1.5256608218605015e-05,
+      "loss": 0.3211,
+      "step": 835
+    },
+    {
+      "epoch": 5.317460317460317,
+      "grad_norm": 4.097353458404541,
+      "learning_rate": 1.493751820936511e-05,
+      "loss": 0.4213,
+      "step": 840
+    },
+    {
+      "epoch": 5.349206349206349,
+      "grad_norm": 3.042466402053833,
+      "learning_rate": 1.4620372579390678e-05,
+      "loss": 0.3856,
+      "step": 845
+    },
+    {
+      "epoch": 5.380952380952381,
+      "grad_norm": 2.485643148422241,
+      "learning_rate": 1.4305232610918045e-05,
+      "loss": 0.3751,
+      "step": 850
+    },
+    {
+      "epoch": 5.412698412698413,
+      "grad_norm": 2.9114632606506348,
+      "learning_rate": 1.3992159198628373e-05,
+      "loss": 0.3557,
+      "step": 855
+    },
+    {
+      "epoch": 5.444444444444445,
+      "grad_norm": 1.9394385814666748,
+      "learning_rate": 1.3681212837880978e-05,
+      "loss": 0.357,
+      "step": 860
+    },
+    {
+      "epoch": 5.476190476190476,
+      "grad_norm": 3.1689724922180176,
+      "learning_rate": 1.3372453613023728e-05,
+      "loss": 0.3665,
+      "step": 865
+    },
+    {
+      "epoch": 5.507936507936508,
+      "grad_norm": 2.9183590412139893,
+      "learning_rate": 1.3065941185782979e-05,
+      "loss": 0.3786,
+      "step": 870
+    },
+    {
+      "epoch": 5.5396825396825395,
+      "grad_norm": 3.520986795425415,
+      "learning_rate": 1.2761734783735036e-05,
+      "loss": 0.3562,
+      "step": 875
+    },
+    {
+      "epoch": 5.571428571428571,
+      "grad_norm": 3.4199678897857666,
+      "learning_rate": 1.2459893188861613e-05,
+      "loss": 0.3871,
+      "step": 880
+    },
+    {
+      "epoch": 5.603174603174603,
+      "grad_norm": 2.38875675201416,
+      "learning_rate": 1.2160474726191323e-05,
+      "loss": 0.3532,
+      "step": 885
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 2.554577350616455,
+      "learning_rate": 1.186353725252955e-05,
+      "loss": 0.3241,
+      "step": 890
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 2.4856674671173096,
+      "learning_rate": 1.1569138145278696e-05,
+      "loss": 0.3571,
+      "step": 895
+    },
+    {
+      "epoch": 5.698412698412699,
+      "grad_norm": 3.3535118103027344,
+      "learning_rate": 1.1277334291351147e-05,
+      "loss": 0.3456,
+      "step": 900
+    },
+    {
+      "epoch": 5.73015873015873,
+      "grad_norm": 2.534107208251953,
+      "learning_rate": 1.0988182076176939e-05,
+      "loss": 0.3895,
+      "step": 905
+    },
+    {
+      "epoch": 5.761904761904762,
+      "grad_norm": 2.346252202987671,
+      "learning_rate": 1.0701737372808432e-05,
+      "loss": 0.3796,
+      "step": 910
+    },
+    {
+      "epoch": 5.7936507936507935,
+      "grad_norm": 2.958519220352173,
+      "learning_rate": 1.0418055531123857e-05,
+      "loss": 0.392,
+      "step": 915
+    },
+    {
+      "epoch": 5.825396825396825,
+      "grad_norm": 1.7530192136764526,
+      "learning_rate": 1.013719136713208e-05,
+      "loss": 0.2836,
+      "step": 920
+    },
+    {
+      "epoch": 5.857142857142857,
+      "grad_norm": 3.0703108310699463,
+      "learning_rate": 9.859199152380432e-06,
+      "loss": 0.4059,
+      "step": 925
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 3.0952444076538086,
+      "learning_rate": 9.584132603467827e-06,
+      "loss": 0.3901,
+      "step": 930
+    },
+    {
+      "epoch": 5.920634920634921,
+      "grad_norm": 2.6520533561706543,
+      "learning_rate": 9.312044871665032e-06,
+      "loss": 0.3285,
+      "step": 935
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 2.382810354232788,
+      "learning_rate": 9.04298853264425e-06,
+      "loss": 0.3998,
+      "step": 940
+    },
+    {
+      "epoch": 5.984126984126984,
+      "grad_norm": 3.09870982170105,
+      "learning_rate": 8.777015576319869e-06,
+      "loss": 0.3804,
+      "step": 945
+    },
+    {
+      "epoch": 6.012698412698413,
+      "grad_norm": 2.542013645172119,
+      "learning_rate": 8.514177396802428e-06,
+      "loss": 0.3471,
+      "step": 950
+    },
+    {
+      "epoch": 6.044444444444444,
+      "grad_norm": 3.0190534591674805,
+      "learning_rate": 8.254524782467692e-06,
+      "loss": 0.3275,
+      "step": 955
+    },
+    {
+      "epoch": 6.076190476190476,
+      "grad_norm": 2.745600461959839,
+      "learning_rate": 7.99810790614284e-06,
+      "loss": 0.3089,
+      "step": 960
+    },
+    {
+      "epoch": 6.1079365079365076,
+      "grad_norm": 2.2067768573760986,
+      "learning_rate": 7.744976315411428e-06,
+      "loss": 0.2902,
+      "step": 965
+    },
+    {
+      "epoch": 6.13968253968254,
+      "grad_norm": 2.806065320968628,
+      "learning_rate": 7.495178923039398e-06,
+      "loss": 0.3349,
+      "step": 970
+    },
+    {
+      "epoch": 6.171428571428572,
+      "grad_norm": 2.4265201091766357,
+      "learning_rate": 7.248763997523561e-06,
+      "loss": 0.3295,
+      "step": 975
+    },
+    {
+      "epoch": 6.203174603174603,
+      "grad_norm": 2.9042932987213135,
+      "learning_rate": 7.005779153764683e-06,
+      "loss": 0.3285,
+      "step": 980
+    },
+    {
+      "epoch": 6.234920634920635,
+      "grad_norm": 3.585085391998291,
+      "learning_rate": 6.766271343866812e-06,
+      "loss": 0.3635,
+      "step": 985
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 2.554619312286377,
+      "learning_rate": 6.530286848064699e-06,
+      "loss": 0.2845,
+      "step": 990
+    },
+    {
+      "epoch": 6.298412698412698,
+      "grad_norm": 2.951251745223999,
+      "learning_rate": 6.297871265781055e-06,
+      "loss": 0.3259,
+      "step": 995
+    },
+    {
+      "epoch": 6.33015873015873,
+      "grad_norm": 2.6404244899749756,
+      "learning_rate": 6.069069506815325e-06,
+      "loss": 0.2872,
+      "step": 1000
+    },
+    {
+      "epoch": 6.3619047619047615,
+      "grad_norm": 2.684638261795044,
+      "learning_rate": 5.843925782665754e-06,
+      "loss": 0.3206,
+      "step": 1005
+    },
+    {
+      "epoch": 6.393650793650794,
+      "grad_norm": 2.080413341522217,
+      "learning_rate": 5.622483597986372e-06,
+      "loss": 0.3099,
+      "step": 1010
+    },
+    {
+      "epoch": 6.425396825396826,
+      "grad_norm": 3.5247743129730225,
+      "learning_rate": 5.404785742180565e-06,
+      "loss": 0.3275,
+      "step": 1015
+    },
+    {
+      "epoch": 6.457142857142857,
+      "grad_norm": 3.3956446647644043,
+      "learning_rate": 5.190874281132851e-06,
+      "loss": 0.3097,
+      "step": 1020
+    },
+    {
+      "epoch": 6.488888888888889,
+      "grad_norm": 2.5341458320617676,
+      "learning_rate": 4.980790549080463e-06,
+      "loss": 0.3346,
+      "step": 1025
+    },
+    {
+      "epoch": 6.520634920634921,
+      "grad_norm": 3.2887229919433594,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.3282,
+      "step": 1030
+    },
+    {
+      "epoch": 6.552380952380952,
+      "grad_norm": 2.290588617324829,
+      "learning_rate": 4.572267902894884e-06,
+      "loss": 0.2956,
+      "step": 1035
+    },
+    {
+      "epoch": 6.584126984126984,
+      "grad_norm": 4.084680080413818,
+      "learning_rate": 4.3739079278325125e-06,
+      "loss": 0.3452,
+      "step": 1040
+    },
+    {
+      "epoch": 6.6158730158730155,
+      "grad_norm": 2.976604700088501,
+      "learning_rate": 4.179533544653674e-06,
+      "loss": 0.3414,
+      "step": 1045
+    },
+    {
+      "epoch": 6.647619047619048,
+      "grad_norm": 3.1176273822784424,
+      "learning_rate": 3.989182312434567e-06,
+      "loss": 0.3179,
+      "step": 1050
+    },
+    {
+      "epoch": 6.67936507936508,
+      "grad_norm": 2.9681129455566406,
+      "learning_rate": 3.8028910128555804e-06,
+      "loss": 0.2868,
+      "step": 1055
+    },
+    {
+      "epoch": 6.711111111111111,
+      "grad_norm": 3.6012775897979736,
+      "learning_rate": 3.6206956430939244e-06,
+      "loss": 0.3446,
+      "step": 1060
+    },
+    {
+      "epoch": 6.742857142857143,
+      "grad_norm": 2.876650810241699,
+      "learning_rate": 3.442631408867894e-06,
+      "loss": 0.3363,
+      "step": 1065
+    },
+    {
+      "epoch": 6.7746031746031745,
+      "grad_norm": 2.6718950271606445,
+      "learning_rate": 3.2687327176340322e-06,
+      "loss": 0.2764,
+      "step": 1070
+    },
+    {
+      "epoch": 6.806349206349206,
+      "grad_norm": 4.247652530670166,
+      "learning_rate": 3.099033171938567e-06,
+      "loss": 0.3326,
+      "step": 1075
+    },
+    {
+      "epoch": 6.838095238095238,
+      "grad_norm": 3.0778801441192627,
+      "learning_rate": 2.9335655629243645e-06,
+      "loss": 0.3685,
+      "step": 1080
+    },
+    {
+      "epoch": 6.86984126984127,
+      "grad_norm": 3.640263795852661,
+      "learning_rate": 2.772361863994688e-06,
+      "loss": 0.3011,
+      "step": 1085
+    },
+    {
+      "epoch": 6.901587301587302,
+      "grad_norm": 3.859355926513672,
+      "learning_rate": 2.6154532246349477e-06,
+      "loss": 0.3587,
+      "step": 1090
+    },
+    {
+      "epoch": 6.933333333333334,
+      "grad_norm": 2.7156548500061035,
+      "learning_rate": 2.462869964393666e-06,
+      "loss": 0.3402,
+      "step": 1095
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.361193959469875e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1256/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-1256/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1256/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-1256/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-1256/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-1256/trainer_state.json

@@ -0,0 +1,1791 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.9523809523809526,
+  "eval_steps": 500,
+  "global_step": 1256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    },
+    {
+      "epoch": 1.0126984126984127,
+      "grad_norm": 1.5468761920928955,
+      "learning_rate": 4.9888394060315975e-05,
+      "loss": 1.0614,
+      "step": 160
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 1.3189973831176758,
+      "learning_rate": 4.9853189685938837e-05,
+      "loss": 0.8396,
+      "step": 165
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 1.0562372207641602,
+      "learning_rate": 4.981318291512396e-05,
+      "loss": 0.8926,
+      "step": 170
+    },
+    {
+      "epoch": 1.107936507936508,
+      "grad_norm": 0.9939103722572327,
+      "learning_rate": 4.976838147840314e-05,
+      "loss": 0.9728,
+      "step": 175
+    },
+    {
+      "epoch": 1.1396825396825396,
+      "grad_norm": 1.6342549324035645,
+      "learning_rate": 4.971879403278432e-05,
+      "loss": 0.8781,
+      "step": 180
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 1.3527770042419434,
+      "learning_rate": 4.966443016007873e-05,
+      "loss": 1.0276,
+      "step": 185
+    },
+    {
+      "epoch": 1.2031746031746031,
+      "grad_norm": 1.2593631744384766,
+      "learning_rate": 4.960530036504942e-05,
+      "loss": 0.9742,
+      "step": 190
+    },
+    {
+      "epoch": 1.234920634920635,
+      "grad_norm": 1.2724119424819946,
+      "learning_rate": 4.9541416073381395e-05,
+      "loss": 0.7572,
+      "step": 195
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.2241063117980957,
+      "learning_rate": 4.947278962947387e-05,
+      "loss": 0.8872,
+      "step": 200
+    },
+    {
+      "epoch": 1.2984126984126985,
+      "grad_norm": 1.0864907503128052,
+      "learning_rate": 4.9399434294054894e-05,
+      "loss": 0.9463,
+      "step": 205
+    },
+    {
+      "epoch": 1.33015873015873,
+      "grad_norm": 1.2503291368484497,
+      "learning_rate": 4.9321364241618994e-05,
+      "loss": 0.8187,
+      "step": 210
+    },
+    {
+      "epoch": 1.361904761904762,
+      "grad_norm": 1.2996984720230103,
+      "learning_rate": 4.9238594557688265e-05,
+      "loss": 0.9949,
+      "step": 215
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 1.2346172332763672,
+      "learning_rate": 4.9151141235897324e-05,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 1.4253968253968254,
+      "grad_norm": 1.3184157609939575,
+      "learning_rate": 4.905902117490291e-05,
+      "loss": 0.9109,
+      "step": 225
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 1.4319523572921753,
+      "learning_rate": 4.89622521751185e-05,
+      "loss": 0.9854,
+      "step": 230
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.458723545074463,
+      "learning_rate": 4.886085293527474e-05,
+      "loss": 0.9916,
+      "step": 235
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 1.2609443664550781,
+      "learning_rate": 4.8754843048806296e-05,
+      "loss": 0.9446,
+      "step": 240
+    },
+    {
+      "epoch": 1.5523809523809524,
+      "grad_norm": 1.1162338256835938,
+      "learning_rate": 4.864424300006579e-05,
+      "loss": 0.746,
+      "step": 245
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "grad_norm": 1.4760407209396362,
+      "learning_rate": 4.852907416036559e-05,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 1.615873015873016,
+      "grad_norm": 1.4606406688690186,
+      "learning_rate": 4.8409358783848216e-05,
+      "loss": 0.8501,
+      "step": 255
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 1.4926954507827759,
+      "learning_rate": 4.828512000318617e-05,
+      "loss": 0.8581,
+      "step": 260
+    },
+    {
+      "epoch": 1.6793650793650794,
+      "grad_norm": 1.7399059534072876,
+      "learning_rate": 4.8156381825112006e-05,
+      "loss": 0.8994,
+      "step": 265
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.2087697982788086,
+      "learning_rate": 4.8023169125779466e-05,
+      "loss": 0.8272,
+      "step": 270
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.5295592546463013,
+      "learning_rate": 4.788550764595667e-05,
+      "loss": 0.8555,
+      "step": 275
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 1.6441818475723267,
+      "learning_rate": 4.774342398605221e-05,
+      "loss": 0.768,
+      "step": 280
+    },
+    {
+      "epoch": 1.8063492063492064,
+      "grad_norm": 1.8932971954345703,
+      "learning_rate": 4.759694560097513e-05,
+      "loss": 0.9286,
+      "step": 285
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 1.565648078918457,
+      "learning_rate": 4.7446100794829785e-05,
+      "loss": 0.7844,
+      "step": 290
+    },
+    {
+      "epoch": 1.8698412698412699,
+      "grad_norm": 1.4803764820098877,
+      "learning_rate": 4.7290918715446644e-05,
+      "loss": 0.9625,
+      "step": 295
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 1.2535064220428467,
+      "learning_rate": 4.7131429348750055e-05,
+      "loss": 0.7778,
+      "step": 300
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4900981187820435,
+      "learning_rate": 4.6967663512963986e-05,
+      "loss": 0.6377,
+      "step": 305
+    },
+    {
+      "epoch": 1.9650793650793652,
+      "grad_norm": 1.5180715322494507,
+      "learning_rate": 4.6799652852657064e-05,
+      "loss": 0.8705,
+      "step": 310
+    },
+    {
+      "epoch": 1.9968253968253968,
+      "grad_norm": 1.074388027191162,
+      "learning_rate": 4.662742983262784e-05,
+      "loss": 0.589,
+      "step": 315
+    },
+    {
+      "epoch": 2.0253968253968253,
+      "grad_norm": 1.4143909215927124,
+      "learning_rate": 4.64510277316316e-05,
+      "loss": 0.675,
+      "step": 320
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 1.4869240522384644,
+      "learning_rate": 4.6270480635949933e-05,
+      "loss": 0.7768,
+      "step": 325
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.4446533918380737,
+      "learning_rate": 4.6085823432804144e-05,
+      "loss": 0.6516,
+      "step": 330
+    },
+    {
+      "epoch": 2.1206349206349207,
+      "grad_norm": 1.8745191097259521,
+      "learning_rate": 4.589709180361403e-05,
+      "loss": 0.7022,
+      "step": 335
+    },
+    {
+      "epoch": 2.1523809523809523,
+      "grad_norm": 1.678874135017395,
+      "learning_rate": 4.5704322217103146e-05,
+      "loss": 0.7443,
+      "step": 340
+    },
+    {
+      "epoch": 2.1841269841269844,
+      "grad_norm": 2.3285534381866455,
+      "learning_rate": 4.550755192225188e-05,
+      "loss": 0.6574,
+      "step": 345
+    },
+    {
+      "epoch": 2.215873015873016,
+      "grad_norm": 1.537413239479065,
+      "learning_rate": 4.530681894109987e-05,
+      "loss": 0.6493,
+      "step": 350
+    },
+    {
+      "epoch": 2.2476190476190476,
+      "grad_norm": 1.8794249296188354,
+      "learning_rate": 4.510216206139894e-05,
+      "loss": 0.7287,
+      "step": 355
+    },
+    {
+      "epoch": 2.2793650793650793,
+      "grad_norm": 1.5752090215682983,
+      "learning_rate": 4.489362082911813e-05,
+      "loss": 0.6171,
+      "step": 360
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5545966625213623,
+      "learning_rate": 4.4681235540802216e-05,
+      "loss": 0.5651,
+      "step": 365
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 1.6034917831420898,
+      "learning_rate": 4.446504723578519e-05,
+      "loss": 0.6758,
+      "step": 370
+    },
+    {
+      "epoch": 2.3746031746031746,
+      "grad_norm": 2.2822070121765137,
+      "learning_rate": 4.424509768826017e-05,
+      "loss": 0.7167,
+      "step": 375
+    },
+    {
+      "epoch": 2.4063492063492062,
+      "grad_norm": 1.3968263864517212,
+      "learning_rate": 4.4021429399207405e-05,
+      "loss": 0.6388,
+      "step": 380
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 2.0151493549346924,
+      "learning_rate": 4.3794085588181725e-05,
+      "loss": 0.8385,
+      "step": 385
+    },
+    {
+      "epoch": 2.46984126984127,
+      "grad_norm": 2.2131729125976562,
+      "learning_rate": 4.3563110184961235e-05,
+      "loss": 0.8482,
+      "step": 390
+    },
+    {
+      "epoch": 2.5015873015873016,
+      "grad_norm": 1.9444142580032349,
+      "learning_rate": 4.332854782105875e-05,
+      "loss": 0.7357,
+      "step": 395
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.3676568269729614,
+      "learning_rate": 4.309044382109757e-05,
+      "loss": 0.6352,
+      "step": 400
+    },
+    {
+      "epoch": 2.565079365079365,
+      "grad_norm": 1.5921475887298584,
+      "learning_rate": 4.2848844194053455e-05,
+      "loss": 0.6742,
+      "step": 405
+    },
+    {
+      "epoch": 2.596825396825397,
+      "grad_norm": 2.04608154296875,
+      "learning_rate": 4.26037956243642e-05,
+      "loss": 0.7472,
+      "step": 410
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 1.6338012218475342,
+      "learning_rate": 4.235534546290883e-05,
+      "loss": 0.5659,
+      "step": 415
+    },
+    {
+      "epoch": 2.66031746031746,
+      "grad_norm": 2.2755625247955322,
+      "learning_rate": 4.2103541717857956e-05,
+      "loss": 0.6775,
+      "step": 420
+    },
+    {
+      "epoch": 2.6920634920634923,
+      "grad_norm": 1.8385895490646362,
+      "learning_rate": 4.184843304539708e-05,
+      "loss": 0.5902,
+      "step": 425
+    },
+    {
+      "epoch": 2.723809523809524,
+      "grad_norm": 2.394862174987793,
+      "learning_rate": 4.1590068740324806e-05,
+      "loss": 0.623,
+      "step": 430
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9886717796325684,
+      "learning_rate": 4.132849872652751e-05,
+      "loss": 0.6361,
+      "step": 435
+    },
+    {
+      "epoch": 2.787301587301587,
+      "grad_norm": 2.674502372741699,
+      "learning_rate": 4.106377354733259e-05,
+      "loss": 0.6835,
+      "step": 440
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 2.432657480239868,
+      "learning_rate": 4.079594435574186e-05,
+      "loss": 0.592,
+      "step": 445
+    },
+    {
+      "epoch": 2.850793650793651,
+      "grad_norm": 1.8935447931289673,
+      "learning_rate": 4.0525062904547276e-05,
+      "loss": 0.629,
+      "step": 450
+    },
+    {
+      "epoch": 2.8825396825396825,
+      "grad_norm": 2.635646343231201,
+      "learning_rate": 4.025118153633075e-05,
+      "loss": 0.7282,
+      "step": 455
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 2.8444085121154785,
+      "learning_rate": 3.9974353173349886e-05,
+      "loss": 0.7106,
+      "step": 460
+    },
+    {
+      "epoch": 2.9460317460317462,
+      "grad_norm": 2.6861064434051514,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.6447,
+      "step": 465
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 2.7277615070343018,
+      "learning_rate": 3.9412069989037015e-05,
+      "loss": 0.563,
+      "step": 470
+    },
+    {
+      "epoch": 3.0063492063492063,
+      "grad_norm": 1.8300037384033203,
+      "learning_rate": 3.91267238180149e-05,
+      "loss": 0.5555,
+      "step": 475
+    },
+    {
+      "epoch": 3.038095238095238,
+      "grad_norm": 2.206399917602539,
+      "learning_rate": 3.883864793185369e-05,
+      "loss": 0.4926,
+      "step": 480
+    },
+    {
+      "epoch": 3.06984126984127,
+      "grad_norm": 2.5881357192993164,
+      "learning_rate": 3.854789799562602e-05,
+      "loss": 0.5441,
+      "step": 485
+    },
+    {
+      "epoch": 3.1015873015873017,
+      "grad_norm": 2.2896475791931152,
+      "learning_rate": 3.825453019111281e-05,
+      "loss": 0.498,
+      "step": 490
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 2.622668981552124,
+      "learning_rate": 3.7958601205947234e-05,
+      "loss": 0.5055,
+      "step": 495
+    },
+    {
+      "epoch": 3.165079365079365,
+      "grad_norm": 3.064993381500244,
+      "learning_rate": 3.766016822266083e-05,
+      "loss": 0.5348,
+      "step": 500
+    },
+    {
+      "epoch": 3.196825396825397,
+      "grad_norm": 3.3422789573669434,
+      "learning_rate": 3.7359288907634225e-05,
+      "loss": 0.5869,
+      "step": 505
+    },
+    {
+      "epoch": 3.2285714285714286,
+      "grad_norm": 2.460176467895508,
+      "learning_rate": 3.705602139995416e-05,
+      "loss": 0.5228,
+      "step": 510
+    },
+    {
+      "epoch": 3.2603174603174603,
+      "grad_norm": 2.6845529079437256,
+      "learning_rate": 3.675042430017923e-05,
+      "loss": 0.4544,
+      "step": 515
+    },
+    {
+      "epoch": 3.292063492063492,
+      "grad_norm": 2.378709077835083,
+      "learning_rate": 3.6442556659016484e-05,
+      "loss": 0.5201,
+      "step": 520
+    },
+    {
+      "epoch": 3.323809523809524,
+      "grad_norm": 2.2331037521362305,
+      "learning_rate": 3.613247796591101e-05,
+      "loss": 0.4924,
+      "step": 525
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 2.702828884124756,
+      "learning_rate": 3.582024813755077e-05,
+      "loss": 0.5358,
+      "step": 530
+    },
+    {
+      "epoch": 3.3873015873015873,
+      "grad_norm": 2.3180782794952393,
+      "learning_rate": 3.550592750628885e-05,
+      "loss": 0.5862,
+      "step": 535
+    },
+    {
+      "epoch": 3.419047619047619,
+      "grad_norm": 2.6038239002227783,
+      "learning_rate": 3.5189576808485407e-05,
+      "loss": 0.5303,
+      "step": 540
+    },
+    {
+      "epoch": 3.450793650793651,
+      "grad_norm": 3.0068862438201904,
+      "learning_rate": 3.4871257172771555e-05,
+      "loss": 0.4848,
+      "step": 545
+    },
+    {
+      "epoch": 3.4825396825396826,
+      "grad_norm": 2.6912105083465576,
+      "learning_rate": 3.455103010823744e-05,
+      "loss": 0.5653,
+      "step": 550
+    },
+    {
+      "epoch": 3.5142857142857142,
+      "grad_norm": 3.0676960945129395,
+      "learning_rate": 3.422895749254677e-05,
+      "loss": 0.5993,
+      "step": 555
+    },
+    {
+      "epoch": 3.546031746031746,
+      "grad_norm": 2.376481533050537,
+      "learning_rate": 3.390510155998023e-05,
+      "loss": 0.5484,
+      "step": 560
+    },
+    {
+      "epoch": 3.5777777777777775,
+      "grad_norm": 2.4998154640197754,
+      "learning_rate": 3.357952488940984e-05,
+      "loss": 0.502,
+      "step": 565
+    },
+    {
+      "epoch": 3.6095238095238096,
+      "grad_norm": 2.900434970855713,
+      "learning_rate": 3.325229039220684e-05,
+      "loss": 0.4531,
+      "step": 570
+    },
+    {
+      "epoch": 3.641269841269841,
+      "grad_norm": 3.2575416564941406,
+      "learning_rate": 3.2923461300085305e-05,
+      "loss": 0.5703,
+      "step": 575
+    },
+    {
+      "epoch": 3.6730158730158733,
+      "grad_norm": 2.449436902999878,
+      "learning_rate": 3.2593101152883796e-05,
+      "loss": 0.5894,
+      "step": 580
+    },
+    {
+      "epoch": 3.704761904761905,
+      "grad_norm": 2.860034227371216,
+      "learning_rate": 3.226127378628756e-05,
+      "loss": 0.557,
+      "step": 585
+    },
+    {
+      "epoch": 3.7365079365079366,
+      "grad_norm": 2.4020888805389404,
+      "learning_rate": 3.19280433194935e-05,
+      "loss": 0.4805,
+      "step": 590
+    },
+    {
+      "epoch": 3.768253968253968,
+      "grad_norm": 2.56815767288208,
+      "learning_rate": 3.15934741428204e-05,
+      "loss": 0.5097,
+      "step": 595
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 1.385717749595642,
+      "learning_rate": 3.1257630905266746e-05,
+      "loss": 0.4136,
+      "step": 600
+    },
+    {
+      "epoch": 3.831746031746032,
+      "grad_norm": 2.7889769077301025,
+      "learning_rate": 3.092057850201855e-05,
+      "loss": 0.4979,
+      "step": 605
+    },
+    {
+      "epoch": 3.8634920634920635,
+      "grad_norm": 2.0486621856689453,
+      "learning_rate": 3.058238206190962e-05,
+      "loss": 0.4226,
+      "step": 610
+    },
+    {
+      "epoch": 3.895238095238095,
+      "grad_norm": 2.6471216678619385,
+      "learning_rate": 3.0243106934836686e-05,
+      "loss": 0.5591,
+      "step": 615
+    },
+    {
+      "epoch": 3.9269841269841272,
+      "grad_norm": 2.7665154933929443,
+      "learning_rate": 2.9902818679131776e-05,
+      "loss": 0.4856,
+      "step": 620
+    },
+    {
+      "epoch": 3.958730158730159,
+      "grad_norm": 2.2888855934143066,
+      "learning_rate": 2.9561583048894382e-05,
+      "loss": 0.4661,
+      "step": 625
+    },
+    {
+      "epoch": 3.9904761904761905,
+      "grad_norm": 2.540665864944458,
+      "learning_rate": 2.9219465981285716e-05,
+      "loss": 0.5027,
+      "step": 630
+    },
+    {
+      "epoch": 4.019047619047619,
+      "grad_norm": 2.840465545654297,
+      "learning_rate": 2.8876533583787647e-05,
+      "loss": 0.5111,
+      "step": 635
+    },
+    {
+      "epoch": 4.050793650793651,
+      "grad_norm": 2.362541437149048,
+      "learning_rate": 2.8532852121428737e-05,
+      "loss": 0.4652,
+      "step": 640
+    },
+    {
+      "epoch": 4.082539682539682,
+      "grad_norm": 2.4384407997131348,
+      "learning_rate": 2.8188488003979784e-05,
+      "loss": 0.4227,
+      "step": 645
+    },
+    {
+      "epoch": 4.114285714285714,
+      "grad_norm": 2.5572218894958496,
+      "learning_rate": 2.784350777312142e-05,
+      "loss": 0.3772,
+      "step": 650
+    },
+    {
+      "epoch": 4.146031746031746,
+      "grad_norm": 2.4390878677368164,
+      "learning_rate": 2.7497978089586236e-05,
+      "loss": 0.4704,
+      "step": 655
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 3.3781797885894775,
+      "learning_rate": 2.7151965720277893e-05,
+      "loss": 0.4303,
+      "step": 660
+    },
+    {
+      "epoch": 4.20952380952381,
+      "grad_norm": 2.8656809329986572,
+      "learning_rate": 2.6805537525369713e-05,
+      "loss": 0.4128,
+      "step": 665
+    },
+    {
+      "epoch": 4.241269841269841,
+      "grad_norm": 4.3884100914001465,
+      "learning_rate": 2.6458760445385216e-05,
+      "loss": 0.4682,
+      "step": 670
+    },
+    {
+      "epoch": 4.273015873015873,
+      "grad_norm": 3.1728439331054688,
+      "learning_rate": 2.6111701488263224e-05,
+      "loss": 0.4208,
+      "step": 675
+    },
+    {
+      "epoch": 4.304761904761905,
+      "grad_norm": 2.4535300731658936,
+      "learning_rate": 2.5764427716409815e-05,
+      "loss": 0.4489,
+      "step": 680
+    },
+    {
+      "epoch": 4.336507936507936,
+      "grad_norm": 2.231412887573242,
+      "learning_rate": 2.5417006233739864e-05,
+      "loss": 0.4079,
+      "step": 685
+    },
+    {
+      "epoch": 4.368253968253969,
+      "grad_norm": 2.2064919471740723,
+      "learning_rate": 2.5069504172710494e-05,
+      "loss": 0.4157,
+      "step": 690
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.6554882526397705,
+      "learning_rate": 2.4721988681349012e-05,
+      "loss": 0.544,
+      "step": 695
+    },
+    {
+      "epoch": 4.431746031746032,
+      "grad_norm": 2.739560842514038,
+      "learning_rate": 2.437452691027789e-05,
+      "loss": 0.4366,
+      "step": 700
+    },
+    {
+      "epoch": 4.463492063492064,
+      "grad_norm": 2.2243738174438477,
+      "learning_rate": 2.402718599973919e-05,
+      "loss": 0.3831,
+      "step": 705
+    },
+    {
+      "epoch": 4.495238095238095,
+      "grad_norm": 2.6665985584259033,
+      "learning_rate": 2.3680033066621043e-05,
+      "loss": 0.3785,
+      "step": 710
+    },
+    {
+      "epoch": 4.526984126984127,
+      "grad_norm": 2.7318532466888428,
+      "learning_rate": 2.3333135191488563e-05,
+      "loss": 0.4055,
+      "step": 715
+    },
+    {
+      "epoch": 4.5587301587301585,
+      "grad_norm": 2.6442530155181885,
+      "learning_rate": 2.298655940562189e-05,
+      "loss": 0.3967,
+      "step": 720
+    },
+    {
+      "epoch": 4.59047619047619,
+      "grad_norm": 2.543417453765869,
+      "learning_rate": 2.2640372678063628e-05,
+      "loss": 0.3863,
+      "step": 725
+    },
+    {
+      "epoch": 4.622222222222222,
+      "grad_norm": 2.905043363571167,
+      "learning_rate": 2.2294641902678445e-05,
+      "loss": 0.3996,
+      "step": 730
+    },
+    {
+      "epoch": 4.653968253968254,
+      "grad_norm": 1.9619908332824707,
+      "learning_rate": 2.19494338852271e-05,
+      "loss": 0.4122,
+      "step": 735
+    },
+    {
+      "epoch": 4.685714285714286,
+      "grad_norm": 2.6673147678375244,
+      "learning_rate": 2.1604815330457512e-05,
+      "loss": 0.478,
+      "step": 740
+    },
+    {
+      "epoch": 4.717460317460318,
+      "grad_norm": 2.735572099685669,
+      "learning_rate": 2.1260852829215406e-05,
+      "loss": 0.4408,
+      "step": 745
+    },
+    {
+      "epoch": 4.749206349206349,
+      "grad_norm": 2.9399704933166504,
+      "learning_rate": 2.0917612845576885e-05,
+      "loss": 0.4422,
+      "step": 750
+    },
+    {
+      "epoch": 4.780952380952381,
+      "grad_norm": 2.5321192741394043,
+      "learning_rate": 2.057516170400554e-05,
+      "loss": 0.3983,
+      "step": 755
+    },
+    {
+      "epoch": 4.8126984126984125,
+      "grad_norm": 2.2827346324920654,
+      "learning_rate": 2.0233565576536567e-05,
+      "loss": 0.4235,
+      "step": 760
+    },
+    {
+      "epoch": 4.844444444444444,
+      "grad_norm": 3.497560739517212,
+      "learning_rate": 1.9892890469990264e-05,
+      "loss": 0.4277,
+      "step": 765
+    },
+    {
+      "epoch": 4.876190476190477,
+      "grad_norm": 2.7729287147521973,
+      "learning_rate": 1.955320221321754e-05,
+      "loss": 0.3638,
+      "step": 770
+    },
+    {
+      "epoch": 4.907936507936508,
+      "grad_norm": 3.169905424118042,
+      "learning_rate": 1.921456644437972e-05,
+      "loss": 0.4323,
+      "step": 775
+    },
+    {
+      "epoch": 4.93968253968254,
+      "grad_norm": 3.217583417892456,
+      "learning_rate": 1.8877048598265283e-05,
+      "loss": 0.4467,
+      "step": 780
+    },
+    {
+      "epoch": 4.9714285714285715,
+      "grad_norm": 2.79040789604187,
+      "learning_rate": 1.8540713893645827e-05,
+      "loss": 0.3856,
+      "step": 785
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.346138000488281,
+      "learning_rate": 1.8205627320673837e-05,
+      "loss": 0.4324,
+      "step": 790
+    },
+    {
+      "epoch": 5.031746031746032,
+      "grad_norm": 2.163886070251465,
+      "learning_rate": 1.787185362832459e-05,
+      "loss": 0.3076,
+      "step": 795
+    },
+    {
+      "epoch": 5.063492063492063,
+      "grad_norm": 2.5888731479644775,
+      "learning_rate": 1.7539457311884676e-05,
+      "loss": 0.3277,
+      "step": 800
+    },
+    {
+      "epoch": 5.095238095238095,
+      "grad_norm": 2.4321916103363037,
+      "learning_rate": 1.720850260048948e-05,
+      "loss": 0.286,
+      "step": 805
+    },
+    {
+      "epoch": 5.1269841269841265,
+      "grad_norm": 1.7569212913513184,
+      "learning_rate": 1.687905344471226e-05,
+      "loss": 0.3328,
+      "step": 810
+    },
+    {
+      "epoch": 5.158730158730159,
+      "grad_norm": 2.9200055599212646,
+      "learning_rate": 1.6551173504206853e-05,
+      "loss": 0.4124,
+      "step": 815
+    },
+    {
+      "epoch": 5.190476190476191,
+      "grad_norm": 3.5868027210235596,
+      "learning_rate": 1.6224926135406693e-05,
+      "loss": 0.3896,
+      "step": 820
+    },
+    {
+      "epoch": 5.222222222222222,
+      "grad_norm": 2.3882710933685303,
+      "learning_rate": 1.5900374379282445e-05,
+      "loss": 0.4112,
+      "step": 825
+    },
+    {
+      "epoch": 5.253968253968254,
+      "grad_norm": 2.136838912963867,
+      "learning_rate": 1.557758094916053e-05,
+      "loss": 0.3479,
+      "step": 830
+    },
+    {
+      "epoch": 5.285714285714286,
+      "grad_norm": 2.6616430282592773,
+      "learning_rate": 1.5256608218605015e-05,
+      "loss": 0.3211,
+      "step": 835
+    },
+    {
+      "epoch": 5.317460317460317,
+      "grad_norm": 4.097353458404541,
+      "learning_rate": 1.493751820936511e-05,
+      "loss": 0.4213,
+      "step": 840
+    },
+    {
+      "epoch": 5.349206349206349,
+      "grad_norm": 3.042466402053833,
+      "learning_rate": 1.4620372579390678e-05,
+      "loss": 0.3856,
+      "step": 845
+    },
+    {
+      "epoch": 5.380952380952381,
+      "grad_norm": 2.485643148422241,
+      "learning_rate": 1.4305232610918045e-05,
+      "loss": 0.3751,
+      "step": 850
+    },
+    {
+      "epoch": 5.412698412698413,
+      "grad_norm": 2.9114632606506348,
+      "learning_rate": 1.3992159198628373e-05,
+      "loss": 0.3557,
+      "step": 855
+    },
+    {
+      "epoch": 5.444444444444445,
+      "grad_norm": 1.9394385814666748,
+      "learning_rate": 1.3681212837880978e-05,
+      "loss": 0.357,
+      "step": 860
+    },
+    {
+      "epoch": 5.476190476190476,
+      "grad_norm": 3.1689724922180176,
+      "learning_rate": 1.3372453613023728e-05,
+      "loss": 0.3665,
+      "step": 865
+    },
+    {
+      "epoch": 5.507936507936508,
+      "grad_norm": 2.9183590412139893,
+      "learning_rate": 1.3065941185782979e-05,
+      "loss": 0.3786,
+      "step": 870
+    },
+    {
+      "epoch": 5.5396825396825395,
+      "grad_norm": 3.520986795425415,
+      "learning_rate": 1.2761734783735036e-05,
+      "loss": 0.3562,
+      "step": 875
+    },
+    {
+      "epoch": 5.571428571428571,
+      "grad_norm": 3.4199678897857666,
+      "learning_rate": 1.2459893188861613e-05,
+      "loss": 0.3871,
+      "step": 880
+    },
+    {
+      "epoch": 5.603174603174603,
+      "grad_norm": 2.38875675201416,
+      "learning_rate": 1.2160474726191323e-05,
+      "loss": 0.3532,
+      "step": 885
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 2.554577350616455,
+      "learning_rate": 1.186353725252955e-05,
+      "loss": 0.3241,
+      "step": 890
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 2.4856674671173096,
+      "learning_rate": 1.1569138145278696e-05,
+      "loss": 0.3571,
+      "step": 895
+    },
+    {
+      "epoch": 5.698412698412699,
+      "grad_norm": 3.3535118103027344,
+      "learning_rate": 1.1277334291351147e-05,
+      "loss": 0.3456,
+      "step": 900
+    },
+    {
+      "epoch": 5.73015873015873,
+      "grad_norm": 2.534107208251953,
+      "learning_rate": 1.0988182076176939e-05,
+      "loss": 0.3895,
+      "step": 905
+    },
+    {
+      "epoch": 5.761904761904762,
+      "grad_norm": 2.346252202987671,
+      "learning_rate": 1.0701737372808432e-05,
+      "loss": 0.3796,
+      "step": 910
+    },
+    {
+      "epoch": 5.7936507936507935,
+      "grad_norm": 2.958519220352173,
+      "learning_rate": 1.0418055531123857e-05,
+      "loss": 0.392,
+      "step": 915
+    },
+    {
+      "epoch": 5.825396825396825,
+      "grad_norm": 1.7530192136764526,
+      "learning_rate": 1.013719136713208e-05,
+      "loss": 0.2836,
+      "step": 920
+    },
+    {
+      "epoch": 5.857142857142857,
+      "grad_norm": 3.0703108310699463,
+      "learning_rate": 9.859199152380432e-06,
+      "loss": 0.4059,
+      "step": 925
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 3.0952444076538086,
+      "learning_rate": 9.584132603467827e-06,
+      "loss": 0.3901,
+      "step": 930
+    },
+    {
+      "epoch": 5.920634920634921,
+      "grad_norm": 2.6520533561706543,
+      "learning_rate": 9.312044871665032e-06,
+      "loss": 0.3285,
+      "step": 935
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 2.382810354232788,
+      "learning_rate": 9.04298853264425e-06,
+      "loss": 0.3998,
+      "step": 940
+    },
+    {
+      "epoch": 5.984126984126984,
+      "grad_norm": 3.09870982170105,
+      "learning_rate": 8.777015576319869e-06,
+      "loss": 0.3804,
+      "step": 945
+    },
+    {
+      "epoch": 6.012698412698413,
+      "grad_norm": 2.542013645172119,
+      "learning_rate": 8.514177396802428e-06,
+      "loss": 0.3471,
+      "step": 950
+    },
+    {
+      "epoch": 6.044444444444444,
+      "grad_norm": 3.0190534591674805,
+      "learning_rate": 8.254524782467692e-06,
+      "loss": 0.3275,
+      "step": 955
+    },
+    {
+      "epoch": 6.076190476190476,
+      "grad_norm": 2.745600461959839,
+      "learning_rate": 7.99810790614284e-06,
+      "loss": 0.3089,
+      "step": 960
+    },
+    {
+      "epoch": 6.1079365079365076,
+      "grad_norm": 2.2067768573760986,
+      "learning_rate": 7.744976315411428e-06,
+      "loss": 0.2902,
+      "step": 965
+    },
+    {
+      "epoch": 6.13968253968254,
+      "grad_norm": 2.806065320968628,
+      "learning_rate": 7.495178923039398e-06,
+      "loss": 0.3349,
+      "step": 970
+    },
+    {
+      "epoch": 6.171428571428572,
+      "grad_norm": 2.4265201091766357,
+      "learning_rate": 7.248763997523561e-06,
+      "loss": 0.3295,
+      "step": 975
+    },
+    {
+      "epoch": 6.203174603174603,
+      "grad_norm": 2.9042932987213135,
+      "learning_rate": 7.005779153764683e-06,
+      "loss": 0.3285,
+      "step": 980
+    },
+    {
+      "epoch": 6.234920634920635,
+      "grad_norm": 3.585085391998291,
+      "learning_rate": 6.766271343866812e-06,
+      "loss": 0.3635,
+      "step": 985
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 2.554619312286377,
+      "learning_rate": 6.530286848064699e-06,
+      "loss": 0.2845,
+      "step": 990
+    },
+    {
+      "epoch": 6.298412698412698,
+      "grad_norm": 2.951251745223999,
+      "learning_rate": 6.297871265781055e-06,
+      "loss": 0.3259,
+      "step": 995
+    },
+    {
+      "epoch": 6.33015873015873,
+      "grad_norm": 2.6404244899749756,
+      "learning_rate": 6.069069506815325e-06,
+      "loss": 0.2872,
+      "step": 1000
+    },
+    {
+      "epoch": 6.3619047619047615,
+      "grad_norm": 2.684638261795044,
+      "learning_rate": 5.843925782665754e-06,
+      "loss": 0.3206,
+      "step": 1005
+    },
+    {
+      "epoch": 6.393650793650794,
+      "grad_norm": 2.080413341522217,
+      "learning_rate": 5.622483597986372e-06,
+      "loss": 0.3099,
+      "step": 1010
+    },
+    {
+      "epoch": 6.425396825396826,
+      "grad_norm": 3.5247743129730225,
+      "learning_rate": 5.404785742180565e-06,
+      "loss": 0.3275,
+      "step": 1015
+    },
+    {
+      "epoch": 6.457142857142857,
+      "grad_norm": 3.3956446647644043,
+      "learning_rate": 5.190874281132851e-06,
+      "loss": 0.3097,
+      "step": 1020
+    },
+    {
+      "epoch": 6.488888888888889,
+      "grad_norm": 2.5341458320617676,
+      "learning_rate": 4.980790549080463e-06,
+      "loss": 0.3346,
+      "step": 1025
+    },
+    {
+      "epoch": 6.520634920634921,
+      "grad_norm": 3.2887229919433594,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.3282,
+      "step": 1030
+    },
+    {
+      "epoch": 6.552380952380952,
+      "grad_norm": 2.290588617324829,
+      "learning_rate": 4.572267902894884e-06,
+      "loss": 0.2956,
+      "step": 1035
+    },
+    {
+      "epoch": 6.584126984126984,
+      "grad_norm": 4.084680080413818,
+      "learning_rate": 4.3739079278325125e-06,
+      "loss": 0.3452,
+      "step": 1040
+    },
+    {
+      "epoch": 6.6158730158730155,
+      "grad_norm": 2.976604700088501,
+      "learning_rate": 4.179533544653674e-06,
+      "loss": 0.3414,
+      "step": 1045
+    },
+    {
+      "epoch": 6.647619047619048,
+      "grad_norm": 3.1176273822784424,
+      "learning_rate": 3.989182312434567e-06,
+      "loss": 0.3179,
+      "step": 1050
+    },
+    {
+      "epoch": 6.67936507936508,
+      "grad_norm": 2.9681129455566406,
+      "learning_rate": 3.8028910128555804e-06,
+      "loss": 0.2868,
+      "step": 1055
+    },
+    {
+      "epoch": 6.711111111111111,
+      "grad_norm": 3.6012775897979736,
+      "learning_rate": 3.6206956430939244e-06,
+      "loss": 0.3446,
+      "step": 1060
+    },
+    {
+      "epoch": 6.742857142857143,
+      "grad_norm": 2.876650810241699,
+      "learning_rate": 3.442631408867894e-06,
+      "loss": 0.3363,
+      "step": 1065
+    },
+    {
+      "epoch": 6.7746031746031745,
+      "grad_norm": 2.6718950271606445,
+      "learning_rate": 3.2687327176340322e-06,
+      "loss": 0.2764,
+      "step": 1070
+    },
+    {
+      "epoch": 6.806349206349206,
+      "grad_norm": 4.247652530670166,
+      "learning_rate": 3.099033171938567e-06,
+      "loss": 0.3326,
+      "step": 1075
+    },
+    {
+      "epoch": 6.838095238095238,
+      "grad_norm": 3.0778801441192627,
+      "learning_rate": 2.9335655629243645e-06,
+      "loss": 0.3685,
+      "step": 1080
+    },
+    {
+      "epoch": 6.86984126984127,
+      "grad_norm": 3.640263795852661,
+      "learning_rate": 2.772361863994688e-06,
+      "loss": 0.3011,
+      "step": 1085
+    },
+    {
+      "epoch": 6.901587301587302,
+      "grad_norm": 3.859355926513672,
+      "learning_rate": 2.6154532246349477e-06,
+      "loss": 0.3587,
+      "step": 1090
+    },
+    {
+      "epoch": 6.933333333333334,
+      "grad_norm": 2.7156548500061035,
+      "learning_rate": 2.462869964393666e-06,
+      "loss": 0.3402,
+      "step": 1095
+    },
+    {
+      "epoch": 6.965079365079365,
+      "grad_norm": 3.4168052673339844,
+      "learning_rate": 2.31464156702382e-06,
+      "loss": 0.3349,
+      "step": 1100
+    },
+    {
+      "epoch": 6.996825396825397,
+      "grad_norm": 2.9093616008758545,
+      "learning_rate": 2.170796674785683e-06,
+      "loss": 0.3261,
+      "step": 1105
+    },
+    {
+      "epoch": 7.025396825396825,
+      "grad_norm": 2.839615821838379,
+      "learning_rate": 2.0313630829122522e-06,
+      "loss": 0.3031,
+      "step": 1110
+    },
+    {
+      "epoch": 7.057142857142857,
+      "grad_norm": 3.0792160034179688,
+      "learning_rate": 1.8963677342383663e-06,
+      "loss": 0.3013,
+      "step": 1115
+    },
+    {
+      "epoch": 7.088888888888889,
+      "grad_norm": 2.227898120880127,
+      "learning_rate": 1.7658367139945232e-06,
+      "loss": 0.2666,
+      "step": 1120
+    },
+    {
+      "epoch": 7.12063492063492,
+      "grad_norm": 2.5210745334625244,
+      "learning_rate": 1.6397952447664177e-06,
+      "loss": 0.2693,
+      "step": 1125
+    },
+    {
+      "epoch": 7.152380952380953,
+      "grad_norm": 3.3494973182678223,
+      "learning_rate": 1.5182676816211633e-06,
+      "loss": 0.3525,
+      "step": 1130
+    },
+    {
+      "epoch": 7.184126984126984,
+      "grad_norm": 2.7284188270568848,
+      "learning_rate": 1.4012775074011553e-06,
+      "loss": 0.2972,
+      "step": 1135
+    },
+    {
+      "epoch": 7.215873015873016,
+      "grad_norm": 2.1954691410064697,
+      "learning_rate": 1.28884732818646e-06,
+      "loss": 0.3037,
+      "step": 1140
+    },
+    {
+      "epoch": 7.247619047619048,
+      "grad_norm": 2.8341176509857178,
+      "learning_rate": 1.180998868926625e-06,
+      "loss": 0.314,
+      "step": 1145
+    },
+    {
+      "epoch": 7.279365079365079,
+      "grad_norm": 3.621948719024658,
+      "learning_rate": 1.077752969242768e-06,
+      "loss": 0.2931,
+      "step": 1150
+    },
+    {
+      "epoch": 7.311111111111111,
+      "grad_norm": 3.365598440170288,
+      "learning_rate": 9.791295794007172e-07,
+      "loss": 0.344,
+      "step": 1155
+    },
+    {
+      "epoch": 7.3428571428571425,
+      "grad_norm": 3.006441116333008,
+      "learning_rate": 8.851477564560062e-07,
+      "loss": 0.3121,
+      "step": 1160
+    },
+    {
+      "epoch": 7.374603174603175,
+      "grad_norm": 2.3393473625183105,
+      "learning_rate": 7.958256605714726e-07,
+      "loss": 0.2873,
+      "step": 1165
+    },
+    {
+      "epoch": 7.406349206349207,
+      "grad_norm": 2.6204307079315186,
+      "learning_rate": 7.111805515081532e-07,
+      "loss": 0.2897,
+      "step": 1170
+    },
+    {
+      "epoch": 7.438095238095238,
+      "grad_norm": 3.66949725151062,
+      "learning_rate": 6.312287852901832e-07,
+      "loss": 0.323,
+      "step": 1175
+    },
+    {
+      "epoch": 7.46984126984127,
+      "grad_norm": 3.176905393600464,
+      "learning_rate": 5.559858110443017e-07,
+      "loss": 0.3114,
+      "step": 1180
+    },
+    {
+      "epoch": 7.501587301587302,
+      "grad_norm": 2.6001551151275635,
+      "learning_rate": 4.854661680146033e-07,
+      "loss": 0.3147,
+      "step": 1185
+    },
+    {
+      "epoch": 7.533333333333333,
+      "grad_norm": 2.6408729553222656,
+      "learning_rate": 4.1968348275312763e-07,
+      "loss": 0.2926,
+      "step": 1190
+    },
+    {
+      "epoch": 7.565079365079365,
+      "grad_norm": 2.4512081146240234,
+      "learning_rate": 3.586504664867707e-07,
+      "loss": 0.2575,
+      "step": 1195
+    },
+    {
+      "epoch": 7.5968253968253965,
+      "grad_norm": 2.964920997619629,
+      "learning_rate": 3.023789126611137e-07,
+      "loss": 0.3054,
+      "step": 1200
+    },
+    {
+      "epoch": 7.628571428571428,
+      "grad_norm": 3.3851871490478516,
+      "learning_rate": 2.508796946615405e-07,
+      "loss": 0.3041,
+      "step": 1205
+    },
+    {
+      "epoch": 7.660317460317461,
+      "grad_norm": 2.6496877670288086,
+      "learning_rate": 2.0416276371219289e-07,
+      "loss": 0.3293,
+      "step": 1210
+    },
+    {
+      "epoch": 7.692063492063492,
+      "grad_norm": 3.0116524696350098,
+      "learning_rate": 1.6223714695306757e-07,
+      "loss": 0.3449,
+      "step": 1215
+    },
+    {
+      "epoch": 7.723809523809524,
+      "grad_norm": 3.024155855178833,
+      "learning_rate": 1.2511094569571668e-07,
+      "loss": 0.3051,
+      "step": 1220
+    },
+    {
+      "epoch": 7.7555555555555555,
+      "grad_norm": 3.3377327919006348,
+      "learning_rate": 9.27913338578057e-08,
+      "loss": 0.3011,
+      "step": 1225
+    },
+    {
+      "epoch": 7.787301587301587,
+      "grad_norm": 3.6456995010375977,
+      "learning_rate": 6.528455657691113e-08,
+      "loss": 0.3179,
+      "step": 1230
+    },
+    {
+      "epoch": 7.819047619047619,
+      "grad_norm": 2.919464111328125,
+      "learning_rate": 4.259592900376363e-08,
+      "loss": 0.2799,
+      "step": 1235
+    },
+    {
+      "epoch": 7.85079365079365,
+      "grad_norm": 3.5842061042785645,
+      "learning_rate": 2.4729835275189018e-08,
+      "loss": 0.3065,
+      "step": 1240
+    },
+    {
+      "epoch": 7.882539682539683,
+      "grad_norm": 2.56817364692688,
+      "learning_rate": 1.1689727666969186e-08,
+      "loss": 0.2864,
+      "step": 1245
+    },
+    {
+      "epoch": 7.914285714285715,
+      "grad_norm": 3.4104034900665283,
+      "learning_rate": 3.478125926756337e-09,
+      "loss": 0.3002,
+      "step": 1250
+    },
+    {
+      "epoch": 7.946031746031746,
+      "grad_norm": 3.37762451171875,
+      "learning_rate": 9.66167871790935e-11,
+      "loss": 0.2886,
+      "step": 1255
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.698353498390528e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-157/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-157/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-157/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-157/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-157/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-157/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9968253968253968,
+  "eval_steps": 500,
+  "global_step": 157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3382367259459584.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-314/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-314/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-314/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-314/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-314/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-314/trainer_state.json

@@ -0,0 +1,468 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9904761904761905,
+  "eval_steps": 500,
+  "global_step": 314,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    },
+    {
+      "epoch": 1.0126984126984127,
+      "grad_norm": 1.5468761920928955,
+      "learning_rate": 4.9888394060315975e-05,
+      "loss": 1.0614,
+      "step": 160
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 1.3189973831176758,
+      "learning_rate": 4.9853189685938837e-05,
+      "loss": 0.8396,
+      "step": 165
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 1.0562372207641602,
+      "learning_rate": 4.981318291512396e-05,
+      "loss": 0.8926,
+      "step": 170
+    },
+    {
+      "epoch": 1.107936507936508,
+      "grad_norm": 0.9939103722572327,
+      "learning_rate": 4.976838147840314e-05,
+      "loss": 0.9728,
+      "step": 175
+    },
+    {
+      "epoch": 1.1396825396825396,
+      "grad_norm": 1.6342549324035645,
+      "learning_rate": 4.971879403278432e-05,
+      "loss": 0.8781,
+      "step": 180
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 1.3527770042419434,
+      "learning_rate": 4.966443016007873e-05,
+      "loss": 1.0276,
+      "step": 185
+    },
+    {
+      "epoch": 1.2031746031746031,
+      "grad_norm": 1.2593631744384766,
+      "learning_rate": 4.960530036504942e-05,
+      "loss": 0.9742,
+      "step": 190
+    },
+    {
+      "epoch": 1.234920634920635,
+      "grad_norm": 1.2724119424819946,
+      "learning_rate": 4.9541416073381395e-05,
+      "loss": 0.7572,
+      "step": 195
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.2241063117980957,
+      "learning_rate": 4.947278962947387e-05,
+      "loss": 0.8872,
+      "step": 200
+    },
+    {
+      "epoch": 1.2984126984126985,
+      "grad_norm": 1.0864907503128052,
+      "learning_rate": 4.9399434294054894e-05,
+      "loss": 0.9463,
+      "step": 205
+    },
+    {
+      "epoch": 1.33015873015873,
+      "grad_norm": 1.2503291368484497,
+      "learning_rate": 4.9321364241618994e-05,
+      "loss": 0.8187,
+      "step": 210
+    },
+    {
+      "epoch": 1.361904761904762,
+      "grad_norm": 1.2996984720230103,
+      "learning_rate": 4.9238594557688265e-05,
+      "loss": 0.9949,
+      "step": 215
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 1.2346172332763672,
+      "learning_rate": 4.9151141235897324e-05,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 1.4253968253968254,
+      "grad_norm": 1.3184157609939575,
+      "learning_rate": 4.905902117490291e-05,
+      "loss": 0.9109,
+      "step": 225
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 1.4319523572921753,
+      "learning_rate": 4.89622521751185e-05,
+      "loss": 0.9854,
+      "step": 230
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.458723545074463,
+      "learning_rate": 4.886085293527474e-05,
+      "loss": 0.9916,
+      "step": 235
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 1.2609443664550781,
+      "learning_rate": 4.8754843048806296e-05,
+      "loss": 0.9446,
+      "step": 240
+    },
+    {
+      "epoch": 1.5523809523809524,
+      "grad_norm": 1.1162338256835938,
+      "learning_rate": 4.864424300006579e-05,
+      "loss": 0.746,
+      "step": 245
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "grad_norm": 1.4760407209396362,
+      "learning_rate": 4.852907416036559e-05,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 1.615873015873016,
+      "grad_norm": 1.4606406688690186,
+      "learning_rate": 4.8409358783848216e-05,
+      "loss": 0.8501,
+      "step": 255
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 1.4926954507827759,
+      "learning_rate": 4.828512000318617e-05,
+      "loss": 0.8581,
+      "step": 260
+    },
+    {
+      "epoch": 1.6793650793650794,
+      "grad_norm": 1.7399059534072876,
+      "learning_rate": 4.8156381825112006e-05,
+      "loss": 0.8994,
+      "step": 265
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.2087697982788086,
+      "learning_rate": 4.8023169125779466e-05,
+      "loss": 0.8272,
+      "step": 270
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.5295592546463013,
+      "learning_rate": 4.788550764595667e-05,
+      "loss": 0.8555,
+      "step": 275
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 1.6441818475723267,
+      "learning_rate": 4.774342398605221e-05,
+      "loss": 0.768,
+      "step": 280
+    },
+    {
+      "epoch": 1.8063492063492064,
+      "grad_norm": 1.8932971954345703,
+      "learning_rate": 4.759694560097513e-05,
+      "loss": 0.9286,
+      "step": 285
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 1.565648078918457,
+      "learning_rate": 4.7446100794829785e-05,
+      "loss": 0.7844,
+      "step": 290
+    },
+    {
+      "epoch": 1.8698412698412699,
+      "grad_norm": 1.4803764820098877,
+      "learning_rate": 4.7290918715446644e-05,
+      "loss": 0.9625,
+      "step": 295
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 1.2535064220428467,
+      "learning_rate": 4.7131429348750055e-05,
+      "loss": 0.7778,
+      "step": 300
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4900981187820435,
+      "learning_rate": 4.6967663512963986e-05,
+      "loss": 0.6377,
+      "step": 305
+    },
+    {
+      "epoch": 1.9650793650793652,
+      "grad_norm": 1.5180715322494507,
+      "learning_rate": 4.6799652852657064e-05,
+      "loss": 0.8705,
+      "step": 310
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6753962648666112.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-471/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-471/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-471/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-471/trainer_state.json

@@ -0,0 +1,692 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.984126984126984,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    },
+    {
+      "epoch": 1.0126984126984127,
+      "grad_norm": 1.5468761920928955,
+      "learning_rate": 4.9888394060315975e-05,
+      "loss": 1.0614,
+      "step": 160
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 1.3189973831176758,
+      "learning_rate": 4.9853189685938837e-05,
+      "loss": 0.8396,
+      "step": 165
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 1.0562372207641602,
+      "learning_rate": 4.981318291512396e-05,
+      "loss": 0.8926,
+      "step": 170
+    },
+    {
+      "epoch": 1.107936507936508,
+      "grad_norm": 0.9939103722572327,
+      "learning_rate": 4.976838147840314e-05,
+      "loss": 0.9728,
+      "step": 175
+    },
+    {
+      "epoch": 1.1396825396825396,
+      "grad_norm": 1.6342549324035645,
+      "learning_rate": 4.971879403278432e-05,
+      "loss": 0.8781,
+      "step": 180
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 1.3527770042419434,
+      "learning_rate": 4.966443016007873e-05,
+      "loss": 1.0276,
+      "step": 185
+    },
+    {
+      "epoch": 1.2031746031746031,
+      "grad_norm": 1.2593631744384766,
+      "learning_rate": 4.960530036504942e-05,
+      "loss": 0.9742,
+      "step": 190
+    },
+    {
+      "epoch": 1.234920634920635,
+      "grad_norm": 1.2724119424819946,
+      "learning_rate": 4.9541416073381395e-05,
+      "loss": 0.7572,
+      "step": 195
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.2241063117980957,
+      "learning_rate": 4.947278962947387e-05,
+      "loss": 0.8872,
+      "step": 200
+    },
+    {
+      "epoch": 1.2984126984126985,
+      "grad_norm": 1.0864907503128052,
+      "learning_rate": 4.9399434294054894e-05,
+      "loss": 0.9463,
+      "step": 205
+    },
+    {
+      "epoch": 1.33015873015873,
+      "grad_norm": 1.2503291368484497,
+      "learning_rate": 4.9321364241618994e-05,
+      "loss": 0.8187,
+      "step": 210
+    },
+    {
+      "epoch": 1.361904761904762,
+      "grad_norm": 1.2996984720230103,
+      "learning_rate": 4.9238594557688265e-05,
+      "loss": 0.9949,
+      "step": 215
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 1.2346172332763672,
+      "learning_rate": 4.9151141235897324e-05,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 1.4253968253968254,
+      "grad_norm": 1.3184157609939575,
+      "learning_rate": 4.905902117490291e-05,
+      "loss": 0.9109,
+      "step": 225
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 1.4319523572921753,
+      "learning_rate": 4.89622521751185e-05,
+      "loss": 0.9854,
+      "step": 230
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.458723545074463,
+      "learning_rate": 4.886085293527474e-05,
+      "loss": 0.9916,
+      "step": 235
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 1.2609443664550781,
+      "learning_rate": 4.8754843048806296e-05,
+      "loss": 0.9446,
+      "step": 240
+    },
+    {
+      "epoch": 1.5523809523809524,
+      "grad_norm": 1.1162338256835938,
+      "learning_rate": 4.864424300006579e-05,
+      "loss": 0.746,
+      "step": 245
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "grad_norm": 1.4760407209396362,
+      "learning_rate": 4.852907416036559e-05,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 1.615873015873016,
+      "grad_norm": 1.4606406688690186,
+      "learning_rate": 4.8409358783848216e-05,
+      "loss": 0.8501,
+      "step": 255
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 1.4926954507827759,
+      "learning_rate": 4.828512000318617e-05,
+      "loss": 0.8581,
+      "step": 260
+    },
+    {
+      "epoch": 1.6793650793650794,
+      "grad_norm": 1.7399059534072876,
+      "learning_rate": 4.8156381825112006e-05,
+      "loss": 0.8994,
+      "step": 265
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.2087697982788086,
+      "learning_rate": 4.8023169125779466e-05,
+      "loss": 0.8272,
+      "step": 270
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.5295592546463013,
+      "learning_rate": 4.788550764595667e-05,
+      "loss": 0.8555,
+      "step": 275
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 1.6441818475723267,
+      "learning_rate": 4.774342398605221e-05,
+      "loss": 0.768,
+      "step": 280
+    },
+    {
+      "epoch": 1.8063492063492064,
+      "grad_norm": 1.8932971954345703,
+      "learning_rate": 4.759694560097513e-05,
+      "loss": 0.9286,
+      "step": 285
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 1.565648078918457,
+      "learning_rate": 4.7446100794829785e-05,
+      "loss": 0.7844,
+      "step": 290
+    },
+    {
+      "epoch": 1.8698412698412699,
+      "grad_norm": 1.4803764820098877,
+      "learning_rate": 4.7290918715446644e-05,
+      "loss": 0.9625,
+      "step": 295
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 1.2535064220428467,
+      "learning_rate": 4.7131429348750055e-05,
+      "loss": 0.7778,
+      "step": 300
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4900981187820435,
+      "learning_rate": 4.6967663512963986e-05,
+      "loss": 0.6377,
+      "step": 305
+    },
+    {
+      "epoch": 1.9650793650793652,
+      "grad_norm": 1.5180715322494507,
+      "learning_rate": 4.6799652852657064e-05,
+      "loss": 0.8705,
+      "step": 310
+    },
+    {
+      "epoch": 1.9968253968253968,
+      "grad_norm": 1.074388027191162,
+      "learning_rate": 4.662742983262784e-05,
+      "loss": 0.589,
+      "step": 315
+    },
+    {
+      "epoch": 2.0253968253968253,
+      "grad_norm": 1.4143909215927124,
+      "learning_rate": 4.64510277316316e-05,
+      "loss": 0.675,
+      "step": 320
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 1.4869240522384644,
+      "learning_rate": 4.6270480635949933e-05,
+      "loss": 0.7768,
+      "step": 325
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.4446533918380737,
+      "learning_rate": 4.6085823432804144e-05,
+      "loss": 0.6516,
+      "step": 330
+    },
+    {
+      "epoch": 2.1206349206349207,
+      "grad_norm": 1.8745191097259521,
+      "learning_rate": 4.589709180361403e-05,
+      "loss": 0.7022,
+      "step": 335
+    },
+    {
+      "epoch": 2.1523809523809523,
+      "grad_norm": 1.678874135017395,
+      "learning_rate": 4.5704322217103146e-05,
+      "loss": 0.7443,
+      "step": 340
+    },
+    {
+      "epoch": 2.1841269841269844,
+      "grad_norm": 2.3285534381866455,
+      "learning_rate": 4.550755192225188e-05,
+      "loss": 0.6574,
+      "step": 345
+    },
+    {
+      "epoch": 2.215873015873016,
+      "grad_norm": 1.537413239479065,
+      "learning_rate": 4.530681894109987e-05,
+      "loss": 0.6493,
+      "step": 350
+    },
+    {
+      "epoch": 2.2476190476190476,
+      "grad_norm": 1.8794249296188354,
+      "learning_rate": 4.510216206139894e-05,
+      "loss": 0.7287,
+      "step": 355
+    },
+    {
+      "epoch": 2.2793650793650793,
+      "grad_norm": 1.5752090215682983,
+      "learning_rate": 4.489362082911813e-05,
+      "loss": 0.6171,
+      "step": 360
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5545966625213623,
+      "learning_rate": 4.4681235540802216e-05,
+      "loss": 0.5651,
+      "step": 365
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 1.6034917831420898,
+      "learning_rate": 4.446504723578519e-05,
+      "loss": 0.6758,
+      "step": 370
+    },
+    {
+      "epoch": 2.3746031746031746,
+      "grad_norm": 2.2822070121765137,
+      "learning_rate": 4.424509768826017e-05,
+      "loss": 0.7167,
+      "step": 375
+    },
+    {
+      "epoch": 2.4063492063492062,
+      "grad_norm": 1.3968263864517212,
+      "learning_rate": 4.4021429399207405e-05,
+      "loss": 0.6388,
+      "step": 380
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 2.0151493549346924,
+      "learning_rate": 4.3794085588181725e-05,
+      "loss": 0.8385,
+      "step": 385
+    },
+    {
+      "epoch": 2.46984126984127,
+      "grad_norm": 2.2131729125976562,
+      "learning_rate": 4.3563110184961235e-05,
+      "loss": 0.8482,
+      "step": 390
+    },
+    {
+      "epoch": 2.5015873015873016,
+      "grad_norm": 1.9444142580032349,
+      "learning_rate": 4.332854782105875e-05,
+      "loss": 0.7357,
+      "step": 395
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.3676568269729614,
+      "learning_rate": 4.309044382109757e-05,
+      "loss": 0.6352,
+      "step": 400
+    },
+    {
+      "epoch": 2.565079365079365,
+      "grad_norm": 1.5921475887298584,
+      "learning_rate": 4.2848844194053455e-05,
+      "loss": 0.6742,
+      "step": 405
+    },
+    {
+      "epoch": 2.596825396825397,
+      "grad_norm": 2.04608154296875,
+      "learning_rate": 4.26037956243642e-05,
+      "loss": 0.7472,
+      "step": 410
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 1.6338012218475342,
+      "learning_rate": 4.235534546290883e-05,
+      "loss": 0.5659,
+      "step": 415
+    },
+    {
+      "epoch": 2.66031746031746,
+      "grad_norm": 2.2755625247955322,
+      "learning_rate": 4.2103541717857956e-05,
+      "loss": 0.6775,
+      "step": 420
+    },
+    {
+      "epoch": 2.6920634920634923,
+      "grad_norm": 1.8385895490646362,
+      "learning_rate": 4.184843304539708e-05,
+      "loss": 0.5902,
+      "step": 425
+    },
+    {
+      "epoch": 2.723809523809524,
+      "grad_norm": 2.394862174987793,
+      "learning_rate": 4.1590068740324806e-05,
+      "loss": 0.623,
+      "step": 430
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9886717796325684,
+      "learning_rate": 4.132849872652751e-05,
+      "loss": 0.6361,
+      "step": 435
+    },
+    {
+      "epoch": 2.787301587301587,
+      "grad_norm": 2.674502372741699,
+      "learning_rate": 4.106377354733259e-05,
+      "loss": 0.6835,
+      "step": 440
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 2.432657480239868,
+      "learning_rate": 4.079594435574186e-05,
+      "loss": 0.592,
+      "step": 445
+    },
+    {
+      "epoch": 2.850793650793651,
+      "grad_norm": 1.8935447931289673,
+      "learning_rate": 4.0525062904547276e-05,
+      "loss": 0.629,
+      "step": 450
+    },
+    {
+      "epoch": 2.8825396825396825,
+      "grad_norm": 2.635646343231201,
+      "learning_rate": 4.025118153633075e-05,
+      "loss": 0.7282,
+      "step": 455
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 2.8444085121154785,
+      "learning_rate": 3.9974353173349886e-05,
+      "loss": 0.7106,
+      "step": 460
+    },
+    {
+      "epoch": 2.9460317460317462,
+      "grad_norm": 2.6861064434051514,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.6447,
+      "step": 465
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 2.7277615070343018,
+      "learning_rate": 3.9412069989037015e-05,
+      "loss": 0.563,
+      "step": 470
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.012555803787264e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-628/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-628/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-628/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-628/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-628/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-628/trainer_state.json

@@ -0,0 +1,909 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.977777777777778,
+  "eval_steps": 500,
+  "global_step": 628,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 0.557715117931366,
+      "learning_rate": 1.984126984126984e-06,
+      "loss": 3.7156,
+      "step": 5
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 0.6210838556289673,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 3.9392,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.574651837348938,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 3.9172,
+      "step": 15
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 0.49391403794288635,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 3.7298,
+      "step": 20
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.6184353232383728,
+      "learning_rate": 9.92063492063492e-06,
+      "loss": 3.8158,
+      "step": 25
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.880232572555542,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 3.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7022971510887146,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 3.8494,
+      "step": 35
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 0.8043017387390137,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 3.8021,
+      "step": 40
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.975318431854248,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.5457,
+      "step": 45
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.9920660853385925,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 3.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 1.0266857147216797,
+      "learning_rate": 2.1825396825396827e-05,
+      "loss": 3.3562,
+      "step": 55
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.0816854238510132,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 3.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 0.9915212988853455,
+      "learning_rate": 2.5793650793650796e-05,
+      "loss": 2.5454,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.2306663990020752,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.2502392530441284,
+      "learning_rate": 2.9761904761904762e-05,
+      "loss": 2.0371,
+      "step": 75
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 1.5857068300247192,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 1.9495,
+      "step": 80
+    },
+    {
+      "epoch": 0.5396825396825397,
+      "grad_norm": 1.2740144729614258,
+      "learning_rate": 3.3730158730158734e-05,
+      "loss": 1.8084,
+      "step": 85
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.813217043876648,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4826,
+      "step": 90
+    },
+    {
+      "epoch": 0.6031746031746031,
+      "grad_norm": 1.1831731796264648,
+      "learning_rate": 3.76984126984127e-05,
+      "loss": 1.1703,
+      "step": 95
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 2.0489368438720703,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 1.2717,
+      "step": 100
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.4326945543289185,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.0786,
+      "step": 105
+    },
+    {
+      "epoch": 0.6984126984126984,
+      "grad_norm": 1.4672375917434692,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 1.2461,
+      "step": 110
+    },
+    {
+      "epoch": 0.7301587301587301,
+      "grad_norm": 1.7501994371414185,
+      "learning_rate": 4.563492063492064e-05,
+      "loss": 1.3453,
+      "step": 115
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3067994117736816,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.3366992473602295,
+      "learning_rate": 4.960317460317461e-05,
+      "loss": 1.2212,
+      "step": 125
+    },
+    {
+      "epoch": 0.8253968253968254,
+      "grad_norm": 1.0570944547653198,
+      "learning_rate": 4.9998454146340764e-05,
+      "loss": 1.014,
+      "step": 130
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 1.225695252418518,
+      "learning_rate": 4.999217444349398e-05,
+      "loss": 1.2156,
+      "step": 135
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4539202451705933,
+      "learning_rate": 4.998106548810312e-05,
+      "loss": 1.2021,
+      "step": 140
+    },
+    {
+      "epoch": 0.9206349206349206,
+      "grad_norm": 1.0543771982192993,
+      "learning_rate": 4.996512942675816e-05,
+      "loss": 0.9998,
+      "step": 145
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.205698013305664,
+      "learning_rate": 4.99443693387936e-05,
+      "loss": 0.8978,
+      "step": 150
+    },
+    {
+      "epoch": 0.9841269841269841,
+      "grad_norm": 1.279111385345459,
+      "learning_rate": 4.991878923569342e-05,
+      "loss": 1.0797,
+      "step": 155
+    },
+    {
+      "epoch": 1.0126984126984127,
+      "grad_norm": 1.5468761920928955,
+      "learning_rate": 4.9888394060315975e-05,
+      "loss": 1.0614,
+      "step": 160
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 1.3189973831176758,
+      "learning_rate": 4.9853189685938837e-05,
+      "loss": 0.8396,
+      "step": 165
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 1.0562372207641602,
+      "learning_rate": 4.981318291512396e-05,
+      "loss": 0.8926,
+      "step": 170
+    },
+    {
+      "epoch": 1.107936507936508,
+      "grad_norm": 0.9939103722572327,
+      "learning_rate": 4.976838147840314e-05,
+      "loss": 0.9728,
+      "step": 175
+    },
+    {
+      "epoch": 1.1396825396825396,
+      "grad_norm": 1.6342549324035645,
+      "learning_rate": 4.971879403278432e-05,
+      "loss": 0.8781,
+      "step": 180
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 1.3527770042419434,
+      "learning_rate": 4.966443016007873e-05,
+      "loss": 1.0276,
+      "step": 185
+    },
+    {
+      "epoch": 1.2031746031746031,
+      "grad_norm": 1.2593631744384766,
+      "learning_rate": 4.960530036504942e-05,
+      "loss": 0.9742,
+      "step": 190
+    },
+    {
+      "epoch": 1.234920634920635,
+      "grad_norm": 1.2724119424819946,
+      "learning_rate": 4.9541416073381395e-05,
+      "loss": 0.7572,
+      "step": 195
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 1.2241063117980957,
+      "learning_rate": 4.947278962947387e-05,
+      "loss": 0.8872,
+      "step": 200
+    },
+    {
+      "epoch": 1.2984126984126985,
+      "grad_norm": 1.0864907503128052,
+      "learning_rate": 4.9399434294054894e-05,
+      "loss": 0.9463,
+      "step": 205
+    },
+    {
+      "epoch": 1.33015873015873,
+      "grad_norm": 1.2503291368484497,
+      "learning_rate": 4.9321364241618994e-05,
+      "loss": 0.8187,
+      "step": 210
+    },
+    {
+      "epoch": 1.361904761904762,
+      "grad_norm": 1.2996984720230103,
+      "learning_rate": 4.9238594557688265e-05,
+      "loss": 0.9949,
+      "step": 215
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 1.2346172332763672,
+      "learning_rate": 4.9151141235897324e-05,
+      "loss": 0.8104,
+      "step": 220
+    },
+    {
+      "epoch": 1.4253968253968254,
+      "grad_norm": 1.3184157609939575,
+      "learning_rate": 4.905902117490291e-05,
+      "loss": 0.9109,
+      "step": 225
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 1.4319523572921753,
+      "learning_rate": 4.89622521751185e-05,
+      "loss": 0.9854,
+      "step": 230
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 1.458723545074463,
+      "learning_rate": 4.886085293527474e-05,
+      "loss": 0.9916,
+      "step": 235
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 1.2609443664550781,
+      "learning_rate": 4.8754843048806296e-05,
+      "loss": 0.9446,
+      "step": 240
+    },
+    {
+      "epoch": 1.5523809523809524,
+      "grad_norm": 1.1162338256835938,
+      "learning_rate": 4.864424300006579e-05,
+      "loss": 0.746,
+      "step": 245
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "grad_norm": 1.4760407209396362,
+      "learning_rate": 4.852907416036559e-05,
+      "loss": 0.8856,
+      "step": 250
+    },
+    {
+      "epoch": 1.615873015873016,
+      "grad_norm": 1.4606406688690186,
+      "learning_rate": 4.8409358783848216e-05,
+      "loss": 0.8501,
+      "step": 255
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 1.4926954507827759,
+      "learning_rate": 4.828512000318617e-05,
+      "loss": 0.8581,
+      "step": 260
+    },
+    {
+      "epoch": 1.6793650793650794,
+      "grad_norm": 1.7399059534072876,
+      "learning_rate": 4.8156381825112006e-05,
+      "loss": 0.8994,
+      "step": 265
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 1.2087697982788086,
+      "learning_rate": 4.8023169125779466e-05,
+      "loss": 0.8272,
+      "step": 270
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.5295592546463013,
+      "learning_rate": 4.788550764595667e-05,
+      "loss": 0.8555,
+      "step": 275
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 1.6441818475723267,
+      "learning_rate": 4.774342398605221e-05,
+      "loss": 0.768,
+      "step": 280
+    },
+    {
+      "epoch": 1.8063492063492064,
+      "grad_norm": 1.8932971954345703,
+      "learning_rate": 4.759694560097513e-05,
+      "loss": 0.9286,
+      "step": 285
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 1.565648078918457,
+      "learning_rate": 4.7446100794829785e-05,
+      "loss": 0.7844,
+      "step": 290
+    },
+    {
+      "epoch": 1.8698412698412699,
+      "grad_norm": 1.4803764820098877,
+      "learning_rate": 4.7290918715446644e-05,
+      "loss": 0.9625,
+      "step": 295
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 1.2535064220428467,
+      "learning_rate": 4.7131429348750055e-05,
+      "loss": 0.7778,
+      "step": 300
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 1.4900981187820435,
+      "learning_rate": 4.6967663512963986e-05,
+      "loss": 0.6377,
+      "step": 305
+    },
+    {
+      "epoch": 1.9650793650793652,
+      "grad_norm": 1.5180715322494507,
+      "learning_rate": 4.6799652852657064e-05,
+      "loss": 0.8705,
+      "step": 310
+    },
+    {
+      "epoch": 1.9968253968253968,
+      "grad_norm": 1.074388027191162,
+      "learning_rate": 4.662742983262784e-05,
+      "loss": 0.589,
+      "step": 315
+    },
+    {
+      "epoch": 2.0253968253968253,
+      "grad_norm": 1.4143909215927124,
+      "learning_rate": 4.64510277316316e-05,
+      "loss": 0.675,
+      "step": 320
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 1.4869240522384644,
+      "learning_rate": 4.6270480635949933e-05,
+      "loss": 0.7768,
+      "step": 325
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.4446533918380737,
+      "learning_rate": 4.6085823432804144e-05,
+      "loss": 0.6516,
+      "step": 330
+    },
+    {
+      "epoch": 2.1206349206349207,
+      "grad_norm": 1.8745191097259521,
+      "learning_rate": 4.589709180361403e-05,
+      "loss": 0.7022,
+      "step": 335
+    },
+    {
+      "epoch": 2.1523809523809523,
+      "grad_norm": 1.678874135017395,
+      "learning_rate": 4.5704322217103146e-05,
+      "loss": 0.7443,
+      "step": 340
+    },
+    {
+      "epoch": 2.1841269841269844,
+      "grad_norm": 2.3285534381866455,
+      "learning_rate": 4.550755192225188e-05,
+      "loss": 0.6574,
+      "step": 345
+    },
+    {
+      "epoch": 2.215873015873016,
+      "grad_norm": 1.537413239479065,
+      "learning_rate": 4.530681894109987e-05,
+      "loss": 0.6493,
+      "step": 350
+    },
+    {
+      "epoch": 2.2476190476190476,
+      "grad_norm": 1.8794249296188354,
+      "learning_rate": 4.510216206139894e-05,
+      "loss": 0.7287,
+      "step": 355
+    },
+    {
+      "epoch": 2.2793650793650793,
+      "grad_norm": 1.5752090215682983,
+      "learning_rate": 4.489362082911813e-05,
+      "loss": 0.6171,
+      "step": 360
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5545966625213623,
+      "learning_rate": 4.4681235540802216e-05,
+      "loss": 0.5651,
+      "step": 365
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 1.6034917831420898,
+      "learning_rate": 4.446504723578519e-05,
+      "loss": 0.6758,
+      "step": 370
+    },
+    {
+      "epoch": 2.3746031746031746,
+      "grad_norm": 2.2822070121765137,
+      "learning_rate": 4.424509768826017e-05,
+      "loss": 0.7167,
+      "step": 375
+    },
+    {
+      "epoch": 2.4063492063492062,
+      "grad_norm": 1.3968263864517212,
+      "learning_rate": 4.4021429399207405e-05,
+      "loss": 0.6388,
+      "step": 380
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 2.0151493549346924,
+      "learning_rate": 4.3794085588181725e-05,
+      "loss": 0.8385,
+      "step": 385
+    },
+    {
+      "epoch": 2.46984126984127,
+      "grad_norm": 2.2131729125976562,
+      "learning_rate": 4.3563110184961235e-05,
+      "loss": 0.8482,
+      "step": 390
+    },
+    {
+      "epoch": 2.5015873015873016,
+      "grad_norm": 1.9444142580032349,
+      "learning_rate": 4.332854782105875e-05,
+      "loss": 0.7357,
+      "step": 395
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.3676568269729614,
+      "learning_rate": 4.309044382109757e-05,
+      "loss": 0.6352,
+      "step": 400
+    },
+    {
+      "epoch": 2.565079365079365,
+      "grad_norm": 1.5921475887298584,
+      "learning_rate": 4.2848844194053455e-05,
+      "loss": 0.6742,
+      "step": 405
+    },
+    {
+      "epoch": 2.596825396825397,
+      "grad_norm": 2.04608154296875,
+      "learning_rate": 4.26037956243642e-05,
+      "loss": 0.7472,
+      "step": 410
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 1.6338012218475342,
+      "learning_rate": 4.235534546290883e-05,
+      "loss": 0.5659,
+      "step": 415
+    },
+    {
+      "epoch": 2.66031746031746,
+      "grad_norm": 2.2755625247955322,
+      "learning_rate": 4.2103541717857956e-05,
+      "loss": 0.6775,
+      "step": 420
+    },
+    {
+      "epoch": 2.6920634920634923,
+      "grad_norm": 1.8385895490646362,
+      "learning_rate": 4.184843304539708e-05,
+      "loss": 0.5902,
+      "step": 425
+    },
+    {
+      "epoch": 2.723809523809524,
+      "grad_norm": 2.394862174987793,
+      "learning_rate": 4.1590068740324806e-05,
+      "loss": 0.623,
+      "step": 430
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9886717796325684,
+      "learning_rate": 4.132849872652751e-05,
+      "loss": 0.6361,
+      "step": 435
+    },
+    {
+      "epoch": 2.787301587301587,
+      "grad_norm": 2.674502372741699,
+      "learning_rate": 4.106377354733259e-05,
+      "loss": 0.6835,
+      "step": 440
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 2.432657480239868,
+      "learning_rate": 4.079594435574186e-05,
+      "loss": 0.592,
+      "step": 445
+    },
+    {
+      "epoch": 2.850793650793651,
+      "grad_norm": 1.8935447931289673,
+      "learning_rate": 4.0525062904547276e-05,
+      "loss": 0.629,
+      "step": 450
+    },
+    {
+      "epoch": 2.8825396825396825,
+      "grad_norm": 2.635646343231201,
+      "learning_rate": 4.025118153633075e-05,
+      "loss": 0.7282,
+      "step": 455
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 2.8444085121154785,
+      "learning_rate": 3.9974353173349886e-05,
+      "loss": 0.7106,
+      "step": 460
+    },
+    {
+      "epoch": 2.9460317460317462,
+      "grad_norm": 2.6861064434051514,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.6447,
+      "step": 465
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 2.7277615070343018,
+      "learning_rate": 3.9412069989037015e-05,
+      "loss": 0.563,
+      "step": 470
+    },
+    {
+      "epoch": 3.0063492063492063,
+      "grad_norm": 1.8300037384033203,
+      "learning_rate": 3.91267238180149e-05,
+      "loss": 0.5555,
+      "step": 475
+    },
+    {
+      "epoch": 3.038095238095238,
+      "grad_norm": 2.206399917602539,
+      "learning_rate": 3.883864793185369e-05,
+      "loss": 0.4926,
+      "step": 480
+    },
+    {
+      "epoch": 3.06984126984127,
+      "grad_norm": 2.5881357192993164,
+      "learning_rate": 3.854789799562602e-05,
+      "loss": 0.5441,
+      "step": 485
+    },
+    {
+      "epoch": 3.1015873015873017,
+      "grad_norm": 2.2896475791931152,
+      "learning_rate": 3.825453019111281e-05,
+      "loss": 0.498,
+      "step": 490
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 2.622668981552124,
+      "learning_rate": 3.7958601205947234e-05,
+      "loss": 0.5055,
+      "step": 495
+    },
+    {
+      "epoch": 3.165079365079365,
+      "grad_norm": 3.064993381500244,
+      "learning_rate": 3.766016822266083e-05,
+      "loss": 0.5348,
+      "step": 500
+    },
+    {
+      "epoch": 3.196825396825397,
+      "grad_norm": 3.3422789573669434,
+      "learning_rate": 3.7359288907634225e-05,
+      "loss": 0.5869,
+      "step": 505
+    },
+    {
+      "epoch": 3.2285714285714286,
+      "grad_norm": 2.460176467895508,
+      "learning_rate": 3.705602139995416e-05,
+      "loss": 0.5228,
+      "step": 510
+    },
+    {
+      "epoch": 3.2603174603174603,
+      "grad_norm": 2.6845529079437256,
+      "learning_rate": 3.675042430017923e-05,
+      "loss": 0.4544,
+      "step": 515
+    },
+    {
+      "epoch": 3.292063492063492,
+      "grad_norm": 2.378709077835083,
+      "learning_rate": 3.6442556659016484e-05,
+      "loss": 0.5201,
+      "step": 520
+    },
+    {
+      "epoch": 3.323809523809524,
+      "grad_norm": 2.2331037521362305,
+      "learning_rate": 3.613247796591101e-05,
+      "loss": 0.4924,
+      "step": 525
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 2.702828884124756,
+      "learning_rate": 3.582024813755077e-05,
+      "loss": 0.5358,
+      "step": 530
+    },
+    {
+      "epoch": 3.3873015873015873,
+      "grad_norm": 2.3180782794952393,
+      "learning_rate": 3.550592750628885e-05,
+      "loss": 0.5862,
+      "step": 535
+    },
+    {
+      "epoch": 3.419047619047619,
+      "grad_norm": 2.6038239002227783,
+      "learning_rate": 3.5189576808485407e-05,
+      "loss": 0.5303,
+      "step": 540
+    },
+    {
+      "epoch": 3.450793650793651,
+      "grad_norm": 3.0068862438201904,
+      "learning_rate": 3.4871257172771555e-05,
+      "loss": 0.4848,
+      "step": 545
+    },
+    {
+      "epoch": 3.4825396825396826,
+      "grad_norm": 2.6912105083465576,
+      "learning_rate": 3.455103010823744e-05,
+      "loss": 0.5653,
+      "step": 550
+    },
+    {
+      "epoch": 3.5142857142857142,
+      "grad_norm": 3.0676960945129395,
+      "learning_rate": 3.422895749254677e-05,
+      "loss": 0.5993,
+      "step": 555
+    },
+    {
+      "epoch": 3.546031746031746,
+      "grad_norm": 2.376481533050537,
+      "learning_rate": 3.390510155998023e-05,
+      "loss": 0.5484,
+      "step": 560
+    },
+    {
+      "epoch": 3.5777777777777775,
+      "grad_norm": 2.4998154640197754,
+      "learning_rate": 3.357952488940984e-05,
+      "loss": 0.502,
+      "step": 565
+    },
+    {
+      "epoch": 3.6095238095238096,
+      "grad_norm": 2.900434970855713,
+      "learning_rate": 3.325229039220684e-05,
+      "loss": 0.4531,
+      "step": 570
+    },
+    {
+      "epoch": 3.641269841269841,
+      "grad_norm": 3.2575416564941406,
+      "learning_rate": 3.2923461300085305e-05,
+      "loss": 0.5703,
+      "step": 575
+    },
+    {
+      "epoch": 3.6730158730158733,
+      "grad_norm": 2.449436902999878,
+      "learning_rate": 3.2593101152883796e-05,
+      "loss": 0.5894,
+      "step": 580
+    },
+    {
+      "epoch": 3.704761904761905,
+      "grad_norm": 2.860034227371216,
+      "learning_rate": 3.226127378628756e-05,
+      "loss": 0.557,
+      "step": 585
+    },
+    {
+      "epoch": 3.7365079365079366,
+      "grad_norm": 2.4020888805389404,
+      "learning_rate": 3.19280433194935e-05,
+      "loss": 0.4805,
+      "step": 590
+    },
+    {
+      "epoch": 3.768253968253968,
+      "grad_norm": 2.56815767288208,
+      "learning_rate": 3.15934741428204e-05,
+      "loss": 0.5097,
+      "step": 595
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 1.385717749595642,
+      "learning_rate": 3.1257630905266746e-05,
+      "loss": 0.4136,
+      "step": 600
+    },
+    {
+      "epoch": 3.831746031746032,
+      "grad_norm": 2.7889769077301025,
+      "learning_rate": 3.092057850201855e-05,
+      "loss": 0.4979,
+      "step": 605
+    },
+    {
+      "epoch": 3.8634920634920635,
+      "grad_norm": 2.0486621856689453,
+      "learning_rate": 3.058238206190962e-05,
+      "loss": 0.4226,
+      "step": 610
+    },
+    {
+      "epoch": 3.895238095238095,
+      "grad_norm": 2.6471216678619385,
+      "learning_rate": 3.0243106934836686e-05,
+      "loss": 0.5591,
+      "step": 615
+    },
+    {
+      "epoch": 3.9269841269841272,
+      "grad_norm": 2.7665154933929443,
+      "learning_rate": 2.9902818679131776e-05,
+      "loss": 0.4856,
+      "step": 620
+    },
+    {
+      "epoch": 3.958730158730159,
+      "grad_norm": 2.2888855934143066,
+      "learning_rate": 2.9561583048894382e-05,
+      "loss": 0.4661,
+      "step": 625
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 157,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3497153427079168e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}