Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-106/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-159/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-212/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-265/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-7B
+tags:
+- generated_from_trainer
+datasets:
+- phxdev/creed
+model-index:
+- name: outputs/mymodel
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen2.5-7B
+bf16: auto
+dataset_processes: 32
+datasets:
+- type: completion
+  field: text
+  path: phxdev/creed
+  trust_remote_code: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+learning_rate: 0.0002
+lisa_layers_attribute: model.layers
+load_best_model_at_end: false
+load_in_4bit: false
+load_in_8bit: true
+lora_alpha: 16
+lora_dropout: 0.05
+lora_r: 8
+lora_target_modules:
+- q_proj
+- v_proj
+- k_proj
+- o_proj
+- gate_proj
+- down_proj
+- up_proj
+loraplus_lr_embedding: 1.0e-06
+lr_scheduler: cosine
+max_prompt_len: 512
+mean_resizing_embeddings: false
+micro_batch_size: 16
+num_epochs: 5
+optimizer: adamw_bnb_8bit
+output_dir: ./outputs/mymodel
+pretrain_multipack_attn: true
+pretrain_multipack_buffer_size: 10000
+qlora_sharded_model_loading: false
+ray_num_workers: 1
+resources_per_worker:
+  GPU: 1
+sample_packing_bin_size: 200
+sample_packing_group_size: 100000
+save_only_model: false
+save_safetensors: true
+sequence_len: 4096
+shuffle_merged_datasets: true
+skip_prepare_dataset: false
+strict: false
+train_on_inputs: false
+trl:
+  log_completions: false
+  ref_model_mixup_alpha: 0.9
+  ref_model_sync_steps: 64
+  sync_ref_model: false
+  use_vllm: false
+  vllm_device: auto
+  vllm_dtype: auto
+  vllm_gpu_memory_utilization: 0.9
+use_ray: false
+val_set_size: 0.0
+weight_decay: 0.0
+
+```
+
+</details><br>
+
+# outputs/mymodel
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the phxdev/creed 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 7
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1626c27c148d75be565ca192cd6f82889d748d4dba5ef6c4270fbfb973ff4c6
+size 80792096

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-106/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.14.0

checkpoint-106/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-106/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb627811b0867687ca96b9ee6019d6bc8d352c039f08ed0e4680b6cb3ab50bf
+size 80792096

checkpoint-106/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-106/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98181ebd7e4fc883cf115e191d9028695fd73292d19262b8118ab721774615f5
+size 41459700

checkpoint-106/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f1682767c2e35493d17fd3ddb3719d19646ca6c3ae729476831278904425f7
+size 14244

checkpoint-106/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfed095f3456264cfa69050e98b10faaf4fe38374b7dfca4afe2bc9b2d06571f
+size 1064

checkpoint-106/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-106/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-106/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-106/trainer_state.json

@@ -0,0 +1,775 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 106,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018867924528301886,
+      "grad_norm": 1.115654468536377,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.156,
+      "step": 1
+    },
+    {
+      "epoch": 0.03773584905660377,
+      "grad_norm": 0.9932883381843567,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 3.7357,
+      "step": 2
+    },
+    {
+      "epoch": 0.05660377358490566,
+      "grad_norm": 0.8334120512008667,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 3.618,
+      "step": 3
+    },
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 1.4111299514770508,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 4.7022,
+      "step": 4
+    },
+    {
+      "epoch": 0.09433962264150944,
+      "grad_norm": 1.1680220365524292,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 4.2272,
+      "step": 5
+    },
+    {
+      "epoch": 0.11320754716981132,
+      "grad_norm": 1.3442370891571045,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 3.7404,
+      "step": 6
+    },
+    {
+      "epoch": 0.1320754716981132,
+      "grad_norm": 1.1529392004013062,
+      "learning_rate": 0.0002,
+      "loss": 3.4162,
+      "step": 7
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 1.2701945304870605,
+      "learning_rate": 0.00019999258647132646,
+      "loss": 3.1241,
+      "step": 8
+    },
+    {
+      "epoch": 0.16981132075471697,
+      "grad_norm": 1.121218204498291,
+      "learning_rate": 0.00019997034698451395,
+      "loss": 2.9459,
+      "step": 9
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.7760863304138184,
+      "learning_rate": 0.00019993328483702393,
+      "loss": 3.5142,
+      "step": 10
+    },
+    {
+      "epoch": 0.20754716981132076,
+      "grad_norm": 1.8232007026672363,
+      "learning_rate": 0.0001998814055240823,
+      "loss": 3.4311,
+      "step": 11
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 1.6853322982788086,
+      "learning_rate": 0.00019981471673786452,
+      "loss": 3.3544,
+      "step": 12
+    },
+    {
+      "epoch": 0.24528301886792453,
+      "grad_norm": 2.0504536628723145,
+      "learning_rate": 0.00019973322836635518,
+      "loss": 3.2197,
+      "step": 13
+    },
+    {
+      "epoch": 0.2641509433962264,
+      "grad_norm": 1.896530270576477,
+      "learning_rate": 0.00019963695249188183,
+      "loss": 2.8467,
+      "step": 14
+    },
+    {
+      "epoch": 0.2830188679245283,
+      "grad_norm": 2.1596853733062744,
+      "learning_rate": 0.00019952590338932356,
+      "loss": 2.7842,
+      "step": 15
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 1.9467144012451172,
+      "learning_rate": 0.0001994000975239946,
+      "loss": 2.899,
+      "step": 16
+    },
+    {
+      "epoch": 0.32075471698113206,
+      "grad_norm": 1.5376367568969727,
+      "learning_rate": 0.00019925955354920265,
+      "loss": 2.6298,
+      "step": 17
+    },
+    {
+      "epoch": 0.33962264150943394,
+      "grad_norm": 1.997107982635498,
+      "learning_rate": 0.00019910429230348347,
+      "loss": 2.6655,
+      "step": 18
+    },
+    {
+      "epoch": 0.3584905660377358,
+      "grad_norm": 1.7822234630584717,
+      "learning_rate": 0.00019893433680751103,
+      "loss": 2.5176,
+      "step": 19
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 1.6853346824645996,
+      "learning_rate": 0.00019874971226068415,
+      "loss": 2.5518,
+      "step": 20
+    },
+    {
+      "epoch": 0.39622641509433965,
+      "grad_norm": 1.7381702661514282,
+      "learning_rate": 0.0001985504460373903,
+      "loss": 2.4681,
+      "step": 21
+    },
+    {
+      "epoch": 0.41509433962264153,
+      "grad_norm": 2.258498191833496,
+      "learning_rate": 0.00019833656768294662,
+      "loss": 2.519,
+      "step": 22
+    },
+    {
+      "epoch": 0.4339622641509434,
+      "grad_norm": 2.1127548217773438,
+      "learning_rate": 0.00019810810890921943,
+      "loss": 2.3028,
+      "step": 23
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 2.1267170906066895,
+      "learning_rate": 0.00019786510358992213,
+      "loss": 2.6239,
+      "step": 24
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 2.239455223083496,
+      "learning_rate": 0.00019760758775559274,
+      "loss": 2.5443,
+      "step": 25
+    },
+    {
+      "epoch": 0.49056603773584906,
+      "grad_norm": 2.42448353767395,
+      "learning_rate": 0.00019733559958825167,
+      "loss": 2.3706,
+      "step": 26
+    },
+    {
+      "epoch": 0.5094339622641509,
+      "grad_norm": 7.652919769287109,
+      "learning_rate": 0.00019704917941574051,
+      "loss": 2.3151,
+      "step": 27
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 2.243516683578491,
+      "learning_rate": 0.00019674836970574254,
+      "loss": 2.3693,
+      "step": 28
+    },
+    {
+      "epoch": 0.5471698113207547,
+      "grad_norm": 1.7010178565979004,
+      "learning_rate": 0.00019643321505948585,
+      "loss": 2.3783,
+      "step": 29
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 2.033024311065674,
+      "learning_rate": 0.00019610376220513068,
+      "loss": 2.2247,
+      "step": 30
+    },
+    {
+      "epoch": 0.5849056603773585,
+      "grad_norm": 2.2775955200195312,
+      "learning_rate": 0.0001957600599908406,
+      "loss": 2.3057,
+      "step": 31
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 1.7552495002746582,
+      "learning_rate": 0.00019540215937754007,
+      "loss": 2.4025,
+      "step": 32
+    },
+    {
+      "epoch": 0.6226415094339622,
+      "grad_norm": 2.3164401054382324,
+      "learning_rate": 0.00019503011343135825,
+      "loss": 2.5287,
+      "step": 33
+    },
+    {
+      "epoch": 0.6415094339622641,
+      "grad_norm": 1.6297874450683594,
+      "learning_rate": 0.00019464397731576094,
+      "loss": 2.3998,
+      "step": 34
+    },
+    {
+      "epoch": 0.660377358490566,
+      "grad_norm": 2.4134299755096436,
+      "learning_rate": 0.00019424380828337144,
+      "loss": 2.7639,
+      "step": 35
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 2.0522265434265137,
+      "learning_rate": 0.00019382966566748168,
+      "loss": 2.3176,
+      "step": 36
+    },
+    {
+      "epoch": 0.6981132075471698,
+      "grad_norm": 1.6699758768081665,
+      "learning_rate": 0.0001934016108732548,
+      "loss": 2.22,
+      "step": 37
+    },
+    {
+      "epoch": 0.7169811320754716,
+      "grad_norm": 2.503006935119629,
+      "learning_rate": 0.00019295970736862064,
+      "loss": 2.2503,
+      "step": 38
+    },
+    {
+      "epoch": 0.7358490566037735,
+      "grad_norm": 1.6840308904647827,
+      "learning_rate": 0.00019250402067486522,
+      "loss": 2.1508,
+      "step": 39
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 1.8616701364517212,
+      "learning_rate": 0.00019203461835691594,
+      "loss": 2.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.7735849056603774,
+      "grad_norm": 2.4246277809143066,
+      "learning_rate": 0.00019155157001332374,
+      "loss": 2.1372,
+      "step": 41
+    },
+    {
+      "epoch": 0.7924528301886793,
+      "grad_norm": 1.6494338512420654,
+      "learning_rate": 0.00019105494726594344,
+      "loss": 2.2013,
+      "step": 42
+    },
+    {
+      "epoch": 0.8113207547169812,
+      "grad_norm": 1.6298986673355103,
+      "learning_rate": 0.00019054482374931467,
+      "loss": 2.1511,
+      "step": 43
+    },
+    {
+      "epoch": 0.8301886792452831,
+      "grad_norm": 1.7853538990020752,
+      "learning_rate": 0.00019002127509974376,
+      "loss": 2.0782,
+      "step": 44
+    },
+    {
+      "epoch": 0.8490566037735849,
+      "grad_norm": 2.286972761154175,
+      "learning_rate": 0.00018948437894408918,
+      "loss": 1.9976,
+      "step": 45
+    },
+    {
+      "epoch": 0.8679245283018868,
+      "grad_norm": 2.409770965576172,
+      "learning_rate": 0.0001889342148882519,
+      "loss": 2.0205,
+      "step": 46
+    },
+    {
+      "epoch": 0.8867924528301887,
+      "grad_norm": 1.7730302810668945,
+      "learning_rate": 0.00018837086450537193,
+      "loss": 2.2549,
+      "step": 47
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 1.6488885879516602,
+      "learning_rate": 0.00018779441132373362,
+      "loss": 2.1286,
+      "step": 48
+    },
+    {
+      "epoch": 0.9245283018867925,
+      "grad_norm": 2.2842915058135986,
+      "learning_rate": 0.00018720494081438078,
+      "loss": 2.3106,
+      "step": 49
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 1.8777570724487305,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.0654,
+      "step": 50
+    },
+    {
+      "epoch": 0.9622641509433962,
+      "grad_norm": 1.8540980815887451,
+      "learning_rate": 0.000185987299334181,
+      "loss": 2.0328,
+      "step": 51
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 1.8285068273544312,
+      "learning_rate": 0.00018535930890373466,
+      "loss": 2.2068,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.4762396812438965,
+      "learning_rate": 0.00018471866219960602,
+      "loss": 1.9356,
+      "step": 53
+    },
+    {
+      "epoch": 1.0188679245283019,
+      "grad_norm": 2.077688455581665,
+      "learning_rate": 0.0001840654542108494,
+      "loss": 1.6721,
+      "step": 54
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 1.9822959899902344,
+      "learning_rate": 0.0001833997817889878,
+      "loss": 1.7122,
+      "step": 55
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 1.534433126449585,
+      "learning_rate": 0.000182721743633653,
+      "loss": 1.6987,
+      "step": 56
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 1.8601195812225342,
+      "learning_rate": 0.0001820314402779511,
+      "loss": 1.8424,
+      "step": 57
+    },
+    {
+      "epoch": 1.0943396226415094,
+      "grad_norm": 2.4600484371185303,
+      "learning_rate": 0.00018132897407355657,
+      "loss": 1.7138,
+      "step": 58
+    },
+    {
+      "epoch": 1.1132075471698113,
+      "grad_norm": 2.065377712249756,
+      "learning_rate": 0.00018061444917553629,
+      "loss": 1.5979,
+      "step": 59
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 2.640429973602295,
+      "learning_rate": 0.00017988797152690671,
+      "loss": 1.7678,
+      "step": 60
+    },
+    {
+      "epoch": 1.150943396226415,
+      "grad_norm": 3.0183305740356445,
+      "learning_rate": 0.00017914964884292544,
+      "loss": 1.9477,
+      "step": 61
+    },
+    {
+      "epoch": 1.169811320754717,
+      "grad_norm": 2.360927104949951,
+      "learning_rate": 0.00017839959059512016,
+      "loss": 1.4201,
+      "step": 62
+    },
+    {
+      "epoch": 1.1886792452830188,
+      "grad_norm": 2.2188379764556885,
+      "learning_rate": 0.00017763790799505747,
+      "loss": 1.5198,
+      "step": 63
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 2.1047656536102295,
+      "learning_rate": 0.0001768647139778532,
+      "loss": 1.6074,
+      "step": 64
+    },
+    {
+      "epoch": 1.2264150943396226,
+      "grad_norm": 2.154175043106079,
+      "learning_rate": 0.0001760801231854278,
+      "loss": 1.6812,
+      "step": 65
+    },
+    {
+      "epoch": 1.2452830188679245,
+      "grad_norm": 3.0521650314331055,
+      "learning_rate": 0.00017528425194950794,
+      "loss": 1.4974,
+      "step": 66
+    },
+    {
+      "epoch": 1.2641509433962264,
+      "grad_norm": 2.580881118774414,
+      "learning_rate": 0.0001744772182743782,
+      "loss": 1.541,
+      "step": 67
+    },
+    {
+      "epoch": 1.2830188679245282,
+      "grad_norm": 3.367107391357422,
+      "learning_rate": 0.0001736591418193844,
+      "loss": 1.4454,
+      "step": 68
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 3.1948163509368896,
+      "learning_rate": 0.00017283014388119159,
+      "loss": 1.4197,
+      "step": 69
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 3.0210657119750977,
+      "learning_rate": 0.0001719903473757996,
+      "loss": 1.5188,
+      "step": 70
+    },
+    {
+      "epoch": 1.3396226415094339,
+      "grad_norm": 3.215881586074829,
+      "learning_rate": 0.0001711398768203178,
+      "loss": 1.7274,
+      "step": 71
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "grad_norm": 3.664365530014038,
+      "learning_rate": 0.00017027885831450318,
+      "loss": 1.5503,
+      "step": 72
+    },
+    {
+      "epoch": 1.3773584905660377,
+      "grad_norm": 3.535518169403076,
+      "learning_rate": 0.0001694074195220634,
+      "loss": 1.5357,
+      "step": 73
+    },
+    {
+      "epoch": 1.3962264150943398,
+      "grad_norm": 3.6230850219726562,
+      "learning_rate": 0.00016852568965172791,
+      "loss": 1.8018,
+      "step": 74
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "grad_norm": 3.4955344200134277,
+      "learning_rate": 0.00016763379943809028,
+      "loss": 1.4862,
+      "step": 75
+    },
+    {
+      "epoch": 1.4339622641509435,
+      "grad_norm": 3.559926748275757,
+      "learning_rate": 0.00016673188112222394,
+      "loss": 1.6273,
+      "step": 76
+    },
+    {
+      "epoch": 1.4528301886792452,
+      "grad_norm": 2.655087947845459,
+      "learning_rate": 0.0001658200684320748,
+      "loss": 1.6323,
+      "step": 77
+    },
+    {
+      "epoch": 1.4716981132075473,
+      "grad_norm": 2.3575522899627686,
+      "learning_rate": 0.00016489849656263337,
+      "loss": 1.4034,
+      "step": 78
+    },
+    {
+      "epoch": 1.490566037735849,
+      "grad_norm": 3.3757848739624023,
+      "learning_rate": 0.00016396730215588915,
+      "loss": 1.4618,
+      "step": 79
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 3.6009631156921387,
+      "learning_rate": 0.00016302662328057088,
+      "loss": 1.5391,
+      "step": 80
+    },
+    {
+      "epoch": 1.5283018867924527,
+      "grad_norm": 3.2048425674438477,
+      "learning_rate": 0.00016207659941167485,
+      "loss": 1.7071,
+      "step": 81
+    },
+    {
+      "epoch": 1.5471698113207548,
+      "grad_norm": 3.4440090656280518,
+      "learning_rate": 0.00016111737140978494,
+      "loss": 1.7924,
+      "step": 82
+    },
+    {
+      "epoch": 1.5660377358490565,
+      "grad_norm": 3.539468288421631,
+      "learning_rate": 0.00016014908150018703,
+      "loss": 1.3348,
+      "step": 83
+    },
+    {
+      "epoch": 1.5849056603773586,
+      "grad_norm": 4.010547161102295,
+      "learning_rate": 0.00015917187325178138,
+      "loss": 1.4573,
+      "step": 84
+    },
+    {
+      "epoch": 1.6037735849056602,
+      "grad_norm": 3.605386734008789,
+      "learning_rate": 0.0001581858915557953,
+      "loss": 1.5987,
+      "step": 85
+    },
+    {
+      "epoch": 1.6226415094339623,
+      "grad_norm": 2.3369998931884766,
+      "learning_rate": 0.0001571912826043003,
+      "loss": 1.555,
+      "step": 86
+    },
+    {
+      "epoch": 1.641509433962264,
+      "grad_norm": 3.1403045654296875,
+      "learning_rate": 0.00015618819386853606,
+      "loss": 1.5138,
+      "step": 87
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "grad_norm": 3.0938310623168945,
+      "learning_rate": 0.0001551767740770446,
+      "loss": 1.444,
+      "step": 88
+    },
+    {
+      "epoch": 1.6792452830188678,
+      "grad_norm": 2.6411221027374268,
+      "learning_rate": 0.00015415717319361847,
+      "loss": 1.2681,
+      "step": 89
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 3.132369041442871,
+      "learning_rate": 0.00015312954239506533,
+      "loss": 1.6189,
+      "step": 90
+    },
+    {
+      "epoch": 1.7169811320754715,
+      "grad_norm": 2.8721351623535156,
+      "learning_rate": 0.00015209403404879303,
+      "loss": 1.351,
+      "step": 91
+    },
+    {
+      "epoch": 1.7358490566037736,
+      "grad_norm": 3.856358051300049,
+      "learning_rate": 0.0001510508016902179,
+      "loss": 1.5624,
+      "step": 92
+    },
+    {
+      "epoch": 1.7547169811320755,
+      "grad_norm": 3.9972498416900635,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.447,
+      "step": 93
+    },
+    {
+      "epoch": 1.7735849056603774,
+      "grad_norm": 2.7673652172088623,
+      "learning_rate": 0.00014894178478110857,
+      "loss": 1.4526,
+      "step": 94
+    },
+    {
+      "epoch": 1.7924528301886793,
+      "grad_norm": 3.1705822944641113,
+      "learning_rate": 0.00014787631293572092,
+      "loss": 1.2079,
+      "step": 95
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 2.8597121238708496,
+      "learning_rate": 0.0001468037424419586,
+      "loss": 1.1173,
+      "step": 96
+    },
+    {
+      "epoch": 1.830188679245283,
+      "grad_norm": 2.7988481521606445,
+      "learning_rate": 0.00014572423233046386,
+      "loss": 1.5903,
+      "step": 97
+    },
+    {
+      "epoch": 1.849056603773585,
+      "grad_norm": 2.7639687061309814,
+      "learning_rate": 0.00014463794266081993,
+      "loss": 1.2,
+      "step": 98
+    },
+    {
+      "epoch": 1.8679245283018868,
+      "grad_norm": 3.7310075759887695,
+      "learning_rate": 0.00014354503449781912,
+      "loss": 1.5971,
+      "step": 99
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 3.9048783779144287,
+      "learning_rate": 0.00014244566988758152,
+      "loss": 1.4054,
+      "step": 100
+    },
+    {
+      "epoch": 1.9056603773584906,
+      "grad_norm": 3.424018144607544,
+      "learning_rate": 0.00014134001183352832,
+      "loss": 1.4166,
+      "step": 101
+    },
+    {
+      "epoch": 1.9245283018867925,
+      "grad_norm": 3.7610878944396973,
+      "learning_rate": 0.00014022822427221324,
+      "loss": 1.3645,
+      "step": 102
+    },
+    {
+      "epoch": 1.9433962264150944,
+      "grad_norm": 3.938345193862915,
+      "learning_rate": 0.0001391104720490156,
+      "loss": 1.2987,
+      "step": 103
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 3.1331722736358643,
+      "learning_rate": 0.00013798692089369855,
+      "loss": 1.4195,
+      "step": 104
+    },
+    {
+      "epoch": 1.9811320754716981,
+      "grad_norm": 3.347231388092041,
+      "learning_rate": 0.00013685773739583617,
+      "loss": 1.4004,
+      "step": 105
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.958104610443115,
+      "learning_rate": 0.0001357230889801133,
+      "loss": 1.295,
+      "step": 106
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8778529082179584.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-106/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b1f3cc06609e6c3214b2ec2bc88284bb9f2f0a116540d08a78d352d59fb1b5
+size 6456

checkpoint-159/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.14.0

checkpoint-159/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-159/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604aae6b33aa7f0144deaa8cde4216e4512dc294bba21317dceae39a0151bcb8
+size 80792096

checkpoint-159/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-159/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4038a3ce018ef1f1ee99dbb65401fb9b364e78ff27eeb604ae40a0d0b69a331b
+size 41459700

checkpoint-159/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c36074402a64ff2f9af2cd8564fc0ef569503b2de64e7e00df32d58f6e187c
+size 14244

checkpoint-159/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d803b9078a7e4d1d3cfb3fce63c02055c831a94a439aa7100556ccfe69281ab3
+size 1064

checkpoint-159/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-159/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-159/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-159/trainer_state.json

@@ -0,0 +1,1146 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018867924528301886,
+      "grad_norm": 1.115654468536377,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.156,
+      "step": 1
+    },
+    {
+      "epoch": 0.03773584905660377,
+      "grad_norm": 0.9932883381843567,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 3.7357,
+      "step": 2
+    },
+    {
+      "epoch": 0.05660377358490566,
+      "grad_norm": 0.8334120512008667,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 3.618,
+      "step": 3
+    },
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 1.4111299514770508,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 4.7022,
+      "step": 4
+    },
+    {
+      "epoch": 0.09433962264150944,
+      "grad_norm": 1.1680220365524292,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 4.2272,
+      "step": 5
+    },
+    {
+      "epoch": 0.11320754716981132,
+      "grad_norm": 1.3442370891571045,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 3.7404,
+      "step": 6
+    },
+    {
+      "epoch": 0.1320754716981132,
+      "grad_norm": 1.1529392004013062,
+      "learning_rate": 0.0002,
+      "loss": 3.4162,
+      "step": 7
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 1.2701945304870605,
+      "learning_rate": 0.00019999258647132646,
+      "loss": 3.1241,
+      "step": 8
+    },
+    {
+      "epoch": 0.16981132075471697,
+      "grad_norm": 1.121218204498291,
+      "learning_rate": 0.00019997034698451395,
+      "loss": 2.9459,
+      "step": 9
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.7760863304138184,
+      "learning_rate": 0.00019993328483702393,
+      "loss": 3.5142,
+      "step": 10
+    },
+    {
+      "epoch": 0.20754716981132076,
+      "grad_norm": 1.8232007026672363,
+      "learning_rate": 0.0001998814055240823,
+      "loss": 3.4311,
+      "step": 11
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 1.6853322982788086,
+      "learning_rate": 0.00019981471673786452,
+      "loss": 3.3544,
+      "step": 12
+    },
+    {
+      "epoch": 0.24528301886792453,
+      "grad_norm": 2.0504536628723145,
+      "learning_rate": 0.00019973322836635518,
+      "loss": 3.2197,
+      "step": 13
+    },
+    {
+      "epoch": 0.2641509433962264,
+      "grad_norm": 1.896530270576477,
+      "learning_rate": 0.00019963695249188183,
+      "loss": 2.8467,
+      "step": 14
+    },
+    {
+      "epoch": 0.2830188679245283,
+      "grad_norm": 2.1596853733062744,
+      "learning_rate": 0.00019952590338932356,
+      "loss": 2.7842,
+      "step": 15
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 1.9467144012451172,
+      "learning_rate": 0.0001994000975239946,
+      "loss": 2.899,
+      "step": 16
+    },
+    {
+      "epoch": 0.32075471698113206,
+      "grad_norm": 1.5376367568969727,
+      "learning_rate": 0.00019925955354920265,
+      "loss": 2.6298,
+      "step": 17
+    },
+    {
+      "epoch": 0.33962264150943394,
+      "grad_norm": 1.997107982635498,
+      "learning_rate": 0.00019910429230348347,
+      "loss": 2.6655,
+      "step": 18
+    },
+    {
+      "epoch": 0.3584905660377358,
+      "grad_norm": 1.7822234630584717,
+      "learning_rate": 0.00019893433680751103,
+      "loss": 2.5176,
+      "step": 19
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 1.6853346824645996,
+      "learning_rate": 0.00019874971226068415,
+      "loss": 2.5518,
+      "step": 20
+    },
+    {
+      "epoch": 0.39622641509433965,
+      "grad_norm": 1.7381702661514282,
+      "learning_rate": 0.0001985504460373903,
+      "loss": 2.4681,
+      "step": 21
+    },
+    {
+      "epoch": 0.41509433962264153,
+      "grad_norm": 2.258498191833496,
+      "learning_rate": 0.00019833656768294662,
+      "loss": 2.519,
+      "step": 22
+    },
+    {
+      "epoch": 0.4339622641509434,
+      "grad_norm": 2.1127548217773438,
+      "learning_rate": 0.00019810810890921943,
+      "loss": 2.3028,
+      "step": 23
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 2.1267170906066895,
+      "learning_rate": 0.00019786510358992213,
+      "loss": 2.6239,
+      "step": 24
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 2.239455223083496,
+      "learning_rate": 0.00019760758775559274,
+      "loss": 2.5443,
+      "step": 25
+    },
+    {
+      "epoch": 0.49056603773584906,
+      "grad_norm": 2.42448353767395,
+      "learning_rate": 0.00019733559958825167,
+      "loss": 2.3706,
+      "step": 26
+    },
+    {
+      "epoch": 0.5094339622641509,
+      "grad_norm": 7.652919769287109,
+      "learning_rate": 0.00019704917941574051,
+      "loss": 2.3151,
+      "step": 27
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 2.243516683578491,
+      "learning_rate": 0.00019674836970574254,
+      "loss": 2.3693,
+      "step": 28
+    },
+    {
+      "epoch": 0.5471698113207547,
+      "grad_norm": 1.7010178565979004,
+      "learning_rate": 0.00019643321505948585,
+      "loss": 2.3783,
+      "step": 29
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 2.033024311065674,
+      "learning_rate": 0.00019610376220513068,
+      "loss": 2.2247,
+      "step": 30
+    },
+    {
+      "epoch": 0.5849056603773585,
+      "grad_norm": 2.2775955200195312,
+      "learning_rate": 0.0001957600599908406,
+      "loss": 2.3057,
+      "step": 31
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 1.7552495002746582,
+      "learning_rate": 0.00019540215937754007,
+      "loss": 2.4025,
+      "step": 32
+    },
+    {
+      "epoch": 0.6226415094339622,
+      "grad_norm": 2.3164401054382324,
+      "learning_rate": 0.00019503011343135825,
+      "loss": 2.5287,
+      "step": 33
+    },
+    {
+      "epoch": 0.6415094339622641,
+      "grad_norm": 1.6297874450683594,
+      "learning_rate": 0.00019464397731576094,
+      "loss": 2.3998,
+      "step": 34
+    },
+    {
+      "epoch": 0.660377358490566,
+      "grad_norm": 2.4134299755096436,
+      "learning_rate": 0.00019424380828337144,
+      "loss": 2.7639,
+      "step": 35
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 2.0522265434265137,
+      "learning_rate": 0.00019382966566748168,
+      "loss": 2.3176,
+      "step": 36
+    },
+    {
+      "epoch": 0.6981132075471698,
+      "grad_norm": 1.6699758768081665,
+      "learning_rate": 0.0001934016108732548,
+      "loss": 2.22,
+      "step": 37
+    },
+    {
+      "epoch": 0.7169811320754716,
+      "grad_norm": 2.503006935119629,
+      "learning_rate": 0.00019295970736862064,
+      "loss": 2.2503,
+      "step": 38
+    },
+    {
+      "epoch": 0.7358490566037735,
+      "grad_norm": 1.6840308904647827,
+      "learning_rate": 0.00019250402067486522,
+      "loss": 2.1508,
+      "step": 39
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 1.8616701364517212,
+      "learning_rate": 0.00019203461835691594,
+      "loss": 2.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.7735849056603774,
+      "grad_norm": 2.4246277809143066,
+      "learning_rate": 0.00019155157001332374,
+      "loss": 2.1372,
+      "step": 41
+    },
+    {
+      "epoch": 0.7924528301886793,
+      "grad_norm": 1.6494338512420654,
+      "learning_rate": 0.00019105494726594344,
+      "loss": 2.2013,
+      "step": 42
+    },
+    {
+      "epoch": 0.8113207547169812,
+      "grad_norm": 1.6298986673355103,
+      "learning_rate": 0.00019054482374931467,
+      "loss": 2.1511,
+      "step": 43
+    },
+    {
+      "epoch": 0.8301886792452831,
+      "grad_norm": 1.7853538990020752,
+      "learning_rate": 0.00019002127509974376,
+      "loss": 2.0782,
+      "step": 44
+    },
+    {
+      "epoch": 0.8490566037735849,
+      "grad_norm": 2.286972761154175,
+      "learning_rate": 0.00018948437894408918,
+      "loss": 1.9976,
+      "step": 45
+    },
+    {
+      "epoch": 0.8679245283018868,
+      "grad_norm": 2.409770965576172,
+      "learning_rate": 0.0001889342148882519,
+      "loss": 2.0205,
+      "step": 46
+    },
+    {
+      "epoch": 0.8867924528301887,
+      "grad_norm": 1.7730302810668945,
+      "learning_rate": 0.00018837086450537193,
+      "loss": 2.2549,
+      "step": 47
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 1.6488885879516602,
+      "learning_rate": 0.00018779441132373362,
+      "loss": 2.1286,
+      "step": 48
+    },
+    {
+      "epoch": 0.9245283018867925,
+      "grad_norm": 2.2842915058135986,
+      "learning_rate": 0.00018720494081438078,
+      "loss": 2.3106,
+      "step": 49
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 1.8777570724487305,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.0654,
+      "step": 50
+    },
+    {
+      "epoch": 0.9622641509433962,
+      "grad_norm": 1.8540980815887451,
+      "learning_rate": 0.000185987299334181,
+      "loss": 2.0328,
+      "step": 51
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 1.8285068273544312,
+      "learning_rate": 0.00018535930890373466,
+      "loss": 2.2068,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.4762396812438965,
+      "learning_rate": 0.00018471866219960602,
+      "loss": 1.9356,
+      "step": 53
+    },
+    {
+      "epoch": 1.0188679245283019,
+      "grad_norm": 2.077688455581665,
+      "learning_rate": 0.0001840654542108494,
+      "loss": 1.6721,
+      "step": 54
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 1.9822959899902344,
+      "learning_rate": 0.0001833997817889878,
+      "loss": 1.7122,
+      "step": 55
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 1.534433126449585,
+      "learning_rate": 0.000182721743633653,
+      "loss": 1.6987,
+      "step": 56
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 1.8601195812225342,
+      "learning_rate": 0.0001820314402779511,
+      "loss": 1.8424,
+      "step": 57
+    },
+    {
+      "epoch": 1.0943396226415094,
+      "grad_norm": 2.4600484371185303,
+      "learning_rate": 0.00018132897407355657,
+      "loss": 1.7138,
+      "step": 58
+    },
+    {
+      "epoch": 1.1132075471698113,
+      "grad_norm": 2.065377712249756,
+      "learning_rate": 0.00018061444917553629,
+      "loss": 1.5979,
+      "step": 59
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 2.640429973602295,
+      "learning_rate": 0.00017988797152690671,
+      "loss": 1.7678,
+      "step": 60
+    },
+    {
+      "epoch": 1.150943396226415,
+      "grad_norm": 3.0183305740356445,
+      "learning_rate": 0.00017914964884292544,
+      "loss": 1.9477,
+      "step": 61
+    },
+    {
+      "epoch": 1.169811320754717,
+      "grad_norm": 2.360927104949951,
+      "learning_rate": 0.00017839959059512016,
+      "loss": 1.4201,
+      "step": 62
+    },
+    {
+      "epoch": 1.1886792452830188,
+      "grad_norm": 2.2188379764556885,
+      "learning_rate": 0.00017763790799505747,
+      "loss": 1.5198,
+      "step": 63
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 2.1047656536102295,
+      "learning_rate": 0.0001768647139778532,
+      "loss": 1.6074,
+      "step": 64
+    },
+    {
+      "epoch": 1.2264150943396226,
+      "grad_norm": 2.154175043106079,
+      "learning_rate": 0.0001760801231854278,
+      "loss": 1.6812,
+      "step": 65
+    },
+    {
+      "epoch": 1.2452830188679245,
+      "grad_norm": 3.0521650314331055,
+      "learning_rate": 0.00017528425194950794,
+      "loss": 1.4974,
+      "step": 66
+    },
+    {
+      "epoch": 1.2641509433962264,
+      "grad_norm": 2.580881118774414,
+      "learning_rate": 0.0001744772182743782,
+      "loss": 1.541,
+      "step": 67
+    },
+    {
+      "epoch": 1.2830188679245282,
+      "grad_norm": 3.367107391357422,
+      "learning_rate": 0.0001736591418193844,
+      "loss": 1.4454,
+      "step": 68
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 3.1948163509368896,
+      "learning_rate": 0.00017283014388119159,
+      "loss": 1.4197,
+      "step": 69
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 3.0210657119750977,
+      "learning_rate": 0.0001719903473757996,
+      "loss": 1.5188,
+      "step": 70
+    },
+    {
+      "epoch": 1.3396226415094339,
+      "grad_norm": 3.215881586074829,
+      "learning_rate": 0.0001711398768203178,
+      "loss": 1.7274,
+      "step": 71
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "grad_norm": 3.664365530014038,
+      "learning_rate": 0.00017027885831450318,
+      "loss": 1.5503,
+      "step": 72
+    },
+    {
+      "epoch": 1.3773584905660377,
+      "grad_norm": 3.535518169403076,
+      "learning_rate": 0.0001694074195220634,
+      "loss": 1.5357,
+      "step": 73
+    },
+    {
+      "epoch": 1.3962264150943398,
+      "grad_norm": 3.6230850219726562,
+      "learning_rate": 0.00016852568965172791,
+      "loss": 1.8018,
+      "step": 74
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "grad_norm": 3.4955344200134277,
+      "learning_rate": 0.00016763379943809028,
+      "loss": 1.4862,
+      "step": 75
+    },
+    {
+      "epoch": 1.4339622641509435,
+      "grad_norm": 3.559926748275757,
+      "learning_rate": 0.00016673188112222394,
+      "loss": 1.6273,
+      "step": 76
+    },
+    {
+      "epoch": 1.4528301886792452,
+      "grad_norm": 2.655087947845459,
+      "learning_rate": 0.0001658200684320748,
+      "loss": 1.6323,
+      "step": 77
+    },
+    {
+      "epoch": 1.4716981132075473,
+      "grad_norm": 2.3575522899627686,
+      "learning_rate": 0.00016489849656263337,
+      "loss": 1.4034,
+      "step": 78
+    },
+    {
+      "epoch": 1.490566037735849,
+      "grad_norm": 3.3757848739624023,
+      "learning_rate": 0.00016396730215588915,
+      "loss": 1.4618,
+      "step": 79
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 3.6009631156921387,
+      "learning_rate": 0.00016302662328057088,
+      "loss": 1.5391,
+      "step": 80
+    },
+    {
+      "epoch": 1.5283018867924527,
+      "grad_norm": 3.2048425674438477,
+      "learning_rate": 0.00016207659941167485,
+      "loss": 1.7071,
+      "step": 81
+    },
+    {
+      "epoch": 1.5471698113207548,
+      "grad_norm": 3.4440090656280518,
+      "learning_rate": 0.00016111737140978494,
+      "loss": 1.7924,
+      "step": 82
+    },
+    {
+      "epoch": 1.5660377358490565,
+      "grad_norm": 3.539468288421631,
+      "learning_rate": 0.00016014908150018703,
+      "loss": 1.3348,
+      "step": 83
+    },
+    {
+      "epoch": 1.5849056603773586,
+      "grad_norm": 4.010547161102295,
+      "learning_rate": 0.00015917187325178138,
+      "loss": 1.4573,
+      "step": 84
+    },
+    {
+      "epoch": 1.6037735849056602,
+      "grad_norm": 3.605386734008789,
+      "learning_rate": 0.0001581858915557953,
+      "loss": 1.5987,
+      "step": 85
+    },
+    {
+      "epoch": 1.6226415094339623,
+      "grad_norm": 2.3369998931884766,
+      "learning_rate": 0.0001571912826043003,
+      "loss": 1.555,
+      "step": 86
+    },
+    {
+      "epoch": 1.641509433962264,
+      "grad_norm": 3.1403045654296875,
+      "learning_rate": 0.00015618819386853606,
+      "loss": 1.5138,
+      "step": 87
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "grad_norm": 3.0938310623168945,
+      "learning_rate": 0.0001551767740770446,
+      "loss": 1.444,
+      "step": 88
+    },
+    {
+      "epoch": 1.6792452830188678,
+      "grad_norm": 2.6411221027374268,
+      "learning_rate": 0.00015415717319361847,
+      "loss": 1.2681,
+      "step": 89
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 3.132369041442871,
+      "learning_rate": 0.00015312954239506533,
+      "loss": 1.6189,
+      "step": 90
+    },
+    {
+      "epoch": 1.7169811320754715,
+      "grad_norm": 2.8721351623535156,
+      "learning_rate": 0.00015209403404879303,
+      "loss": 1.351,
+      "step": 91
+    },
+    {
+      "epoch": 1.7358490566037736,
+      "grad_norm": 3.856358051300049,
+      "learning_rate": 0.0001510508016902179,
+      "loss": 1.5624,
+      "step": 92
+    },
+    {
+      "epoch": 1.7547169811320755,
+      "grad_norm": 3.9972498416900635,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.447,
+      "step": 93
+    },
+    {
+      "epoch": 1.7735849056603774,
+      "grad_norm": 2.7673652172088623,
+      "learning_rate": 0.00014894178478110857,
+      "loss": 1.4526,
+      "step": 94
+    },
+    {
+      "epoch": 1.7924528301886793,
+      "grad_norm": 3.1705822944641113,
+      "learning_rate": 0.00014787631293572092,
+      "loss": 1.2079,
+      "step": 95
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 2.8597121238708496,
+      "learning_rate": 0.0001468037424419586,
+      "loss": 1.1173,
+      "step": 96
+    },
+    {
+      "epoch": 1.830188679245283,
+      "grad_norm": 2.7988481521606445,
+      "learning_rate": 0.00014572423233046386,
+      "loss": 1.5903,
+      "step": 97
+    },
+    {
+      "epoch": 1.849056603773585,
+      "grad_norm": 2.7639687061309814,
+      "learning_rate": 0.00014463794266081993,
+      "loss": 1.2,
+      "step": 98
+    },
+    {
+      "epoch": 1.8679245283018868,
+      "grad_norm": 3.7310075759887695,
+      "learning_rate": 0.00014354503449781912,
+      "loss": 1.5971,
+      "step": 99
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 3.9048783779144287,
+      "learning_rate": 0.00014244566988758152,
+      "loss": 1.4054,
+      "step": 100
+    },
+    {
+      "epoch": 1.9056603773584906,
+      "grad_norm": 3.424018144607544,
+      "learning_rate": 0.00014134001183352832,
+      "loss": 1.4166,
+      "step": 101
+    },
+    {
+      "epoch": 1.9245283018867925,
+      "grad_norm": 3.7610878944396973,
+      "learning_rate": 0.00014022822427221324,
+      "loss": 1.3645,
+      "step": 102
+    },
+    {
+      "epoch": 1.9433962264150944,
+      "grad_norm": 3.938345193862915,
+      "learning_rate": 0.0001391104720490156,
+      "loss": 1.2987,
+      "step": 103
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 3.1331722736358643,
+      "learning_rate": 0.00013798692089369855,
+      "loss": 1.4195,
+      "step": 104
+    },
+    {
+      "epoch": 1.9811320754716981,
+      "grad_norm": 3.347231388092041,
+      "learning_rate": 0.00013685773739583617,
+      "loss": 1.4004,
+      "step": 105
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.958104610443115,
+      "learning_rate": 0.0001357230889801133,
+      "loss": 1.295,
+      "step": 106
+    },
+    {
+      "epoch": 2.018867924528302,
+      "grad_norm": 2.7938392162323,
+      "learning_rate": 0.00013458314388150114,
+      "loss": 0.8655,
+      "step": 107
+    },
+    {
+      "epoch": 2.0377358490566038,
+      "grad_norm": 3.1623213291168213,
+      "learning_rate": 0.00013343807112031327,
+      "loss": 0.8786,
+      "step": 108
+    },
+    {
+      "epoch": 2.056603773584906,
+      "grad_norm": 2.9963018894195557,
+      "learning_rate": 0.00013228804047714463,
+      "loss": 0.8819,
+      "step": 109
+    },
+    {
+      "epoch": 2.0754716981132075,
+      "grad_norm": 2.4673538208007812,
+      "learning_rate": 0.00013113322246769817,
+      "loss": 0.8189,
+      "step": 110
+    },
+    {
+      "epoch": 2.0943396226415096,
+      "grad_norm": 3.187716245651245,
+      "learning_rate": 0.00012997378831750242,
+      "loss": 0.8267,
+      "step": 111
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 2.730367422103882,
+      "learning_rate": 0.00012880990993652377,
+      "loss": 0.7693,
+      "step": 112
+    },
+    {
+      "epoch": 2.1320754716981134,
+      "grad_norm": 2.9551656246185303,
+      "learning_rate": 0.00012764175989367718,
+      "loss": 0.7605,
+      "step": 113
+    },
+    {
+      "epoch": 2.150943396226415,
+      "grad_norm": 4.102267742156982,
+      "learning_rate": 0.00012646951139123934,
+      "loss": 0.907,
+      "step": 114
+    },
+    {
+      "epoch": 2.169811320754717,
+      "grad_norm": 4.0557026863098145,
+      "learning_rate": 0.00012529333823916807,
+      "loss": 0.9109,
+      "step": 115
+    },
+    {
+      "epoch": 2.188679245283019,
+      "grad_norm": 3.8453004360198975,
+      "learning_rate": 0.0001241134148293311,
+      "loss": 0.7561,
+      "step": 116
+    },
+    {
+      "epoch": 2.207547169811321,
+      "grad_norm": 5.24804162979126,
+      "learning_rate": 0.00012292991610964903,
+      "loss": 0.9191,
+      "step": 117
+    },
+    {
+      "epoch": 2.2264150943396226,
+      "grad_norm": 4.6383795738220215,
+      "learning_rate": 0.00012174301755815571,
+      "loss": 0.8057,
+      "step": 118
+    },
+    {
+      "epoch": 2.2452830188679247,
+      "grad_norm": 4.45780086517334,
+      "learning_rate": 0.00012055289515698007,
+      "loss": 0.895,
+      "step": 119
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 4.987161636352539,
+      "learning_rate": 0.00011935972536625302,
+      "loss": 0.8043,
+      "step": 120
+    },
+    {
+      "epoch": 2.2830188679245285,
+      "grad_norm": 3.0627079010009766,
+      "learning_rate": 0.00011816368509794364,
+      "loss": 0.7107,
+      "step": 121
+    },
+    {
+      "epoch": 2.30188679245283,
+      "grad_norm": 3.219001293182373,
+      "learning_rate": 0.00011696495168962847,
+      "loss": 0.7408,
+      "step": 122
+    },
+    {
+      "epoch": 2.3207547169811322,
+      "grad_norm": 3.5602636337280273,
+      "learning_rate": 0.00011576370287819736,
+      "loss": 0.748,
+      "step": 123
+    },
+    {
+      "epoch": 2.339622641509434,
+      "grad_norm": 4.614081382751465,
+      "learning_rate": 0.00011456011677350051,
+      "loss": 0.7347,
+      "step": 124
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 3.4051380157470703,
+      "learning_rate": 0.0001133543718319398,
+      "loss": 0.6849,
+      "step": 125
+    },
+    {
+      "epoch": 2.3773584905660377,
+      "grad_norm": 4.593987464904785,
+      "learning_rate": 0.00011214664683000927,
+      "loss": 0.811,
+      "step": 126
+    },
+    {
+      "epoch": 2.3962264150943398,
+      "grad_norm": 3.460425853729248,
+      "learning_rate": 0.00011093712083778746,
+      "loss": 0.7217,
+      "step": 127
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 4.334282875061035,
+      "learning_rate": 0.0001097259731923869,
+      "loss": 0.9764,
+      "step": 128
+    },
+    {
+      "epoch": 2.4339622641509435,
+      "grad_norm": 4.153921127319336,
+      "learning_rate": 0.00010851338347136357,
+      "loss": 0.755,
+      "step": 129
+    },
+    {
+      "epoch": 2.452830188679245,
+      "grad_norm": 3.751748561859131,
+      "learning_rate": 0.00010729953146609076,
+      "loss": 0.7872,
+      "step": 130
+    },
+    {
+      "epoch": 2.4716981132075473,
+      "grad_norm": 3.157301664352417,
+      "learning_rate": 0.00010608459715510139,
+      "loss": 0.6977,
+      "step": 131
+    },
+    {
+      "epoch": 2.490566037735849,
+      "grad_norm": 3.9355554580688477,
+      "learning_rate": 0.00010486876067740252,
+      "loss": 0.6962,
+      "step": 132
+    },
+    {
+      "epoch": 2.509433962264151,
+      "grad_norm": 3.7606890201568604,
+      "learning_rate": 0.0001036522023057659,
+      "loss": 0.7766,
+      "step": 133
+    },
+    {
+      "epoch": 2.5283018867924527,
+      "grad_norm": 3.3978798389434814,
+      "learning_rate": 0.00010243510241999899,
+      "loss": 0.7456,
+      "step": 134
+    },
+    {
+      "epoch": 2.547169811320755,
+      "grad_norm": 4.373416423797607,
+      "learning_rate": 0.00010121764148019976,
+      "loss": 0.7904,
+      "step": 135
+    },
+    {
+      "epoch": 2.5660377358490565,
+      "grad_norm": 3.233684539794922,
+      "learning_rate": 0.0001,
+      "loss": 0.6922,
+      "step": 136
+    },
+    {
+      "epoch": 2.5849056603773586,
+      "grad_norm": 2.8673453330993652,
+      "learning_rate": 9.878235851980025e-05,
+      "loss": 0.755,
+      "step": 137
+    },
+    {
+      "epoch": 2.6037735849056602,
+      "grad_norm": 4.115866661071777,
+      "learning_rate": 9.756489758000105e-05,
+      "loss": 0.8105,
+      "step": 138
+    },
+    {
+      "epoch": 2.6226415094339623,
+      "grad_norm": 4.364792823791504,
+      "learning_rate": 9.63477976942341e-05,
+      "loss": 0.8063,
+      "step": 139
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 3.319819927215576,
+      "learning_rate": 9.513123932259751e-05,
+      "loss": 0.7105,
+      "step": 140
+    },
+    {
+      "epoch": 2.660377358490566,
+      "grad_norm": 3.4825072288513184,
+      "learning_rate": 9.391540284489862e-05,
+      "loss": 0.6319,
+      "step": 141
+    },
+    {
+      "epoch": 2.6792452830188678,
+      "grad_norm": 4.888297080993652,
+      "learning_rate": 9.270046853390925e-05,
+      "loss": 0.9002,
+      "step": 142
+    },
+    {
+      "epoch": 2.69811320754717,
+      "grad_norm": 3.9948232173919678,
+      "learning_rate": 9.148661652863642e-05,
+      "loss": 0.8127,
+      "step": 143
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 4.544849395751953,
+      "learning_rate": 9.027402680761309e-05,
+      "loss": 0.8186,
+      "step": 144
+    },
+    {
+      "epoch": 2.7358490566037736,
+      "grad_norm": 4.437803268432617,
+      "learning_rate": 8.906287916221259e-05,
+      "loss": 0.8359,
+      "step": 145
+    },
+    {
+      "epoch": 2.7547169811320753,
+      "grad_norm": 4.868703842163086,
+      "learning_rate": 8.785335316999078e-05,
+      "loss": 0.8483,
+      "step": 146
+    },
+    {
+      "epoch": 2.7735849056603774,
+      "grad_norm": 4.967810153961182,
+      "learning_rate": 8.664562816806022e-05,
+      "loss": 0.9694,
+      "step": 147
+    },
+    {
+      "epoch": 2.7924528301886795,
+      "grad_norm": 4.962375164031982,
+      "learning_rate": 8.543988322649954e-05,
+      "loss": 0.9566,
+      "step": 148
+    },
+    {
+      "epoch": 2.811320754716981,
+      "grad_norm": 3.4327187538146973,
+      "learning_rate": 8.423629712180265e-05,
+      "loss": 0.7338,
+      "step": 149
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 4.282032012939453,
+      "learning_rate": 8.303504831037154e-05,
+      "loss": 0.7555,
+      "step": 150
+    },
+    {
+      "epoch": 2.849056603773585,
+      "grad_norm": 2.7784788608551025,
+      "learning_rate": 8.183631490205637e-05,
+      "loss": 0.5799,
+      "step": 151
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 3.580303192138672,
+      "learning_rate": 8.064027463374702e-05,
+      "loss": 0.8267,
+      "step": 152
+    },
+    {
+      "epoch": 2.8867924528301887,
+      "grad_norm": 3.964838981628418,
+      "learning_rate": 7.944710484301995e-05,
+      "loss": 0.8239,
+      "step": 153
+    },
+    {
+      "epoch": 2.9056603773584904,
+      "grad_norm": 3.3083627223968506,
+      "learning_rate": 7.825698244184431e-05,
+      "loss": 0.6842,
+      "step": 154
+    },
+    {
+      "epoch": 2.9245283018867925,
+      "grad_norm": 3.5870604515075684,
+      "learning_rate": 7.707008389035101e-05,
+      "loss": 0.7782,
+      "step": 155
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "grad_norm": 3.623816728591919,
+      "learning_rate": 7.588658517066892e-05,
+      "loss": 0.7621,
+      "step": 156
+    },
+    {
+      "epoch": 2.9622641509433962,
+      "grad_norm": 3.9412410259246826,
+      "learning_rate": 7.470666176083192e-05,
+      "loss": 0.7291,
+      "step": 157
+    },
+    {
+      "epoch": 2.981132075471698,
+      "grad_norm": 3.9385383129119873,
+      "learning_rate": 7.353048860876064e-05,
+      "loss": 0.8624,
+      "step": 158
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.64533519744873,
+      "learning_rate": 7.235824010632283e-05,
+      "loss": 1.1187,
+      "step": 159
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2971747068084224e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-159/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b1f3cc06609e6c3214b2ec2bc88284bb9f2f0a116540d08a78d352d59fb1b5
+size 6456

checkpoint-212/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.14.0

checkpoint-212/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-212/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db162d01431fa376f4b6adab4d7add646d19632f8d00b6046f62e9ff3bbe6df2
+size 80792096

checkpoint-212/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-212/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb0ad58b59b77fdcf7063fc5ca47b636364b8581ce00d0559557d2376ac0a01
+size 41459700

checkpoint-212/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae634112524f00aab94b9287c62faec725f65f1226fe8acc8f18fd5068f77df
+size 14244

checkpoint-212/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff788ca797fa08b005a5d9c3b23526cc1b1fdfcdc4841b1e5e2666722b79ec9d
+size 1064

checkpoint-212/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-212/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-212/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-212/trainer_state.json

@@ -0,0 +1,1517 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018867924528301886,
+      "grad_norm": 1.115654468536377,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 4.156,
+      "step": 1
+    },
+    {
+      "epoch": 0.03773584905660377,
+      "grad_norm": 0.9932883381843567,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 3.7357,
+      "step": 2
+    },
+    {
+      "epoch": 0.05660377358490566,
+      "grad_norm": 0.8334120512008667,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 3.618,
+      "step": 3
+    },
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 1.4111299514770508,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 4.7022,
+      "step": 4
+    },
+    {
+      "epoch": 0.09433962264150944,
+      "grad_norm": 1.1680220365524292,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 4.2272,
+      "step": 5
+    },
+    {
+      "epoch": 0.11320754716981132,
+      "grad_norm": 1.3442370891571045,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 3.7404,
+      "step": 6
+    },
+    {
+      "epoch": 0.1320754716981132,
+      "grad_norm": 1.1529392004013062,
+      "learning_rate": 0.0002,
+      "loss": 3.4162,
+      "step": 7
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 1.2701945304870605,
+      "learning_rate": 0.00019999258647132646,
+      "loss": 3.1241,
+      "step": 8
+    },
+    {
+      "epoch": 0.16981132075471697,
+      "grad_norm": 1.121218204498291,
+      "learning_rate": 0.00019997034698451395,
+      "loss": 2.9459,
+      "step": 9
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.7760863304138184,
+      "learning_rate": 0.00019993328483702393,
+      "loss": 3.5142,
+      "step": 10
+    },
+    {
+      "epoch": 0.20754716981132076,
+      "grad_norm": 1.8232007026672363,
+      "learning_rate": 0.0001998814055240823,
+      "loss": 3.4311,
+      "step": 11
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 1.6853322982788086,
+      "learning_rate": 0.00019981471673786452,
+      "loss": 3.3544,
+      "step": 12
+    },
+    {
+      "epoch": 0.24528301886792453,
+      "grad_norm": 2.0504536628723145,
+      "learning_rate": 0.00019973322836635518,
+      "loss": 3.2197,
+      "step": 13
+    },
+    {
+      "epoch": 0.2641509433962264,
+      "grad_norm": 1.896530270576477,
+      "learning_rate": 0.00019963695249188183,
+      "loss": 2.8467,
+      "step": 14
+    },
+    {
+      "epoch": 0.2830188679245283,
+      "grad_norm": 2.1596853733062744,
+      "learning_rate": 0.00019952590338932356,
+      "loss": 2.7842,
+      "step": 15
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 1.9467144012451172,
+      "learning_rate": 0.0001994000975239946,
+      "loss": 2.899,
+      "step": 16
+    },
+    {
+      "epoch": 0.32075471698113206,
+      "grad_norm": 1.5376367568969727,
+      "learning_rate": 0.00019925955354920265,
+      "loss": 2.6298,
+      "step": 17
+    },
+    {
+      "epoch": 0.33962264150943394,
+      "grad_norm": 1.997107982635498,
+      "learning_rate": 0.00019910429230348347,
+      "loss": 2.6655,
+      "step": 18
+    },
+    {
+      "epoch": 0.3584905660377358,
+      "grad_norm": 1.7822234630584717,
+      "learning_rate": 0.00019893433680751103,
+      "loss": 2.5176,
+      "step": 19
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 1.6853346824645996,
+      "learning_rate": 0.00019874971226068415,
+      "loss": 2.5518,
+      "step": 20
+    },
+    {
+      "epoch": 0.39622641509433965,
+      "grad_norm": 1.7381702661514282,
+      "learning_rate": 0.0001985504460373903,
+      "loss": 2.4681,
+      "step": 21
+    },
+    {
+      "epoch": 0.41509433962264153,
+      "grad_norm": 2.258498191833496,
+      "learning_rate": 0.00019833656768294662,
+      "loss": 2.519,
+      "step": 22
+    },
+    {
+      "epoch": 0.4339622641509434,
+      "grad_norm": 2.1127548217773438,
+      "learning_rate": 0.00019810810890921943,
+      "loss": 2.3028,
+      "step": 23
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 2.1267170906066895,
+      "learning_rate": 0.00019786510358992213,
+      "loss": 2.6239,
+      "step": 24
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 2.239455223083496,
+      "learning_rate": 0.00019760758775559274,
+      "loss": 2.5443,
+      "step": 25
+    },
+    {
+      "epoch": 0.49056603773584906,
+      "grad_norm": 2.42448353767395,
+      "learning_rate": 0.00019733559958825167,
+      "loss": 2.3706,
+      "step": 26
+    },
+    {
+      "epoch": 0.5094339622641509,
+      "grad_norm": 7.652919769287109,
+      "learning_rate": 0.00019704917941574051,
+      "loss": 2.3151,
+      "step": 27
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 2.243516683578491,
+      "learning_rate": 0.00019674836970574254,
+      "loss": 2.3693,
+      "step": 28
+    },
+    {
+      "epoch": 0.5471698113207547,
+      "grad_norm": 1.7010178565979004,
+      "learning_rate": 0.00019643321505948585,
+      "loss": 2.3783,
+      "step": 29
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 2.033024311065674,
+      "learning_rate": 0.00019610376220513068,
+      "loss": 2.2247,
+      "step": 30
+    },
+    {
+      "epoch": 0.5849056603773585,
+      "grad_norm": 2.2775955200195312,
+      "learning_rate": 0.0001957600599908406,
+      "loss": 2.3057,
+      "step": 31
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 1.7552495002746582,
+      "learning_rate": 0.00019540215937754007,
+      "loss": 2.4025,
+      "step": 32
+    },
+    {
+      "epoch": 0.6226415094339622,
+      "grad_norm": 2.3164401054382324,
+      "learning_rate": 0.00019503011343135825,
+      "loss": 2.5287,
+      "step": 33
+    },
+    {
+      "epoch": 0.6415094339622641,
+      "grad_norm": 1.6297874450683594,
+      "learning_rate": 0.00019464397731576094,
+      "loss": 2.3998,
+      "step": 34
+    },
+    {
+      "epoch": 0.660377358490566,
+      "grad_norm": 2.4134299755096436,
+      "learning_rate": 0.00019424380828337144,
+      "loss": 2.7639,
+      "step": 35
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 2.0522265434265137,
+      "learning_rate": 0.00019382966566748168,
+      "loss": 2.3176,
+      "step": 36
+    },
+    {
+      "epoch": 0.6981132075471698,
+      "grad_norm": 1.6699758768081665,
+      "learning_rate": 0.0001934016108732548,
+      "loss": 2.22,
+      "step": 37
+    },
+    {
+      "epoch": 0.7169811320754716,
+      "grad_norm": 2.503006935119629,
+      "learning_rate": 0.00019295970736862064,
+      "loss": 2.2503,
+      "step": 38
+    },
+    {
+      "epoch": 0.7358490566037735,
+      "grad_norm": 1.6840308904647827,
+      "learning_rate": 0.00019250402067486522,
+      "loss": 2.1508,
+      "step": 39
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 1.8616701364517212,
+      "learning_rate": 0.00019203461835691594,
+      "loss": 2.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.7735849056603774,
+      "grad_norm": 2.4246277809143066,
+      "learning_rate": 0.00019155157001332374,
+      "loss": 2.1372,
+      "step": 41
+    },
+    {
+      "epoch": 0.7924528301886793,
+      "grad_norm": 1.6494338512420654,
+      "learning_rate": 0.00019105494726594344,
+      "loss": 2.2013,
+      "step": 42
+    },
+    {
+      "epoch": 0.8113207547169812,
+      "grad_norm": 1.6298986673355103,
+      "learning_rate": 0.00019054482374931467,
+      "loss": 2.1511,
+      "step": 43
+    },
+    {
+      "epoch": 0.8301886792452831,
+      "grad_norm": 1.7853538990020752,
+      "learning_rate": 0.00019002127509974376,
+      "loss": 2.0782,
+      "step": 44
+    },
+    {
+      "epoch": 0.8490566037735849,
+      "grad_norm": 2.286972761154175,
+      "learning_rate": 0.00018948437894408918,
+      "loss": 1.9976,
+      "step": 45
+    },
+    {
+      "epoch": 0.8679245283018868,
+      "grad_norm": 2.409770965576172,
+      "learning_rate": 0.0001889342148882519,
+      "loss": 2.0205,
+      "step": 46
+    },
+    {
+      "epoch": 0.8867924528301887,
+      "grad_norm": 1.7730302810668945,
+      "learning_rate": 0.00018837086450537193,
+      "loss": 2.2549,
+      "step": 47
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 1.6488885879516602,
+      "learning_rate": 0.00018779441132373362,
+      "loss": 2.1286,
+      "step": 48
+    },
+    {
+      "epoch": 0.9245283018867925,
+      "grad_norm": 2.2842915058135986,
+      "learning_rate": 0.00018720494081438078,
+      "loss": 2.3106,
+      "step": 49
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 1.8777570724487305,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 2.0654,
+      "step": 50
+    },
+    {
+      "epoch": 0.9622641509433962,
+      "grad_norm": 1.8540980815887451,
+      "learning_rate": 0.000185987299334181,
+      "loss": 2.0328,
+      "step": 51
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 1.8285068273544312,
+      "learning_rate": 0.00018535930890373466,
+      "loss": 2.2068,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.4762396812438965,
+      "learning_rate": 0.00018471866219960602,
+      "loss": 1.9356,
+      "step": 53
+    },
+    {
+      "epoch": 1.0188679245283019,
+      "grad_norm": 2.077688455581665,
+      "learning_rate": 0.0001840654542108494,
+      "loss": 1.6721,
+      "step": 54
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 1.9822959899902344,
+      "learning_rate": 0.0001833997817889878,
+      "loss": 1.7122,
+      "step": 55
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 1.534433126449585,
+      "learning_rate": 0.000182721743633653,
+      "loss": 1.6987,
+      "step": 56
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 1.8601195812225342,
+      "learning_rate": 0.0001820314402779511,
+      "loss": 1.8424,
+      "step": 57
+    },
+    {
+      "epoch": 1.0943396226415094,
+      "grad_norm": 2.4600484371185303,
+      "learning_rate": 0.00018132897407355657,
+      "loss": 1.7138,
+      "step": 58
+    },
+    {
+      "epoch": 1.1132075471698113,
+      "grad_norm": 2.065377712249756,
+      "learning_rate": 0.00018061444917553629,
+      "loss": 1.5979,
+      "step": 59
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 2.640429973602295,
+      "learning_rate": 0.00017988797152690671,
+      "loss": 1.7678,
+      "step": 60
+    },
+    {
+      "epoch": 1.150943396226415,
+      "grad_norm": 3.0183305740356445,
+      "learning_rate": 0.00017914964884292544,
+      "loss": 1.9477,
+      "step": 61
+    },
+    {
+      "epoch": 1.169811320754717,
+      "grad_norm": 2.360927104949951,
+      "learning_rate": 0.00017839959059512016,
+      "loss": 1.4201,
+      "step": 62
+    },
+    {
+      "epoch": 1.1886792452830188,
+      "grad_norm": 2.2188379764556885,
+      "learning_rate": 0.00017763790799505747,
+      "loss": 1.5198,
+      "step": 63
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 2.1047656536102295,
+      "learning_rate": 0.0001768647139778532,
+      "loss": 1.6074,
+      "step": 64
+    },
+    {
+      "epoch": 1.2264150943396226,
+      "grad_norm": 2.154175043106079,
+      "learning_rate": 0.0001760801231854278,
+      "loss": 1.6812,
+      "step": 65
+    },
+    {
+      "epoch": 1.2452830188679245,
+      "grad_norm": 3.0521650314331055,
+      "learning_rate": 0.00017528425194950794,
+      "loss": 1.4974,
+      "step": 66
+    },
+    {
+      "epoch": 1.2641509433962264,
+      "grad_norm": 2.580881118774414,
+      "learning_rate": 0.0001744772182743782,
+      "loss": 1.541,
+      "step": 67
+    },
+    {
+      "epoch": 1.2830188679245282,
+      "grad_norm": 3.367107391357422,
+      "learning_rate": 0.0001736591418193844,
+      "loss": 1.4454,
+      "step": 68
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 3.1948163509368896,
+      "learning_rate": 0.00017283014388119159,
+      "loss": 1.4197,
+      "step": 69
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 3.0210657119750977,
+      "learning_rate": 0.0001719903473757996,
+      "loss": 1.5188,
+      "step": 70
+    },
+    {
+      "epoch": 1.3396226415094339,
+      "grad_norm": 3.215881586074829,
+      "learning_rate": 0.0001711398768203178,
+      "loss": 1.7274,
+      "step": 71
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "grad_norm": 3.664365530014038,
+      "learning_rate": 0.00017027885831450318,
+      "loss": 1.5503,
+      "step": 72
+    },
+    {
+      "epoch": 1.3773584905660377,
+      "grad_norm": 3.535518169403076,
+      "learning_rate": 0.0001694074195220634,
+      "loss": 1.5357,
+      "step": 73
+    },
+    {
+      "epoch": 1.3962264150943398,
+      "grad_norm": 3.6230850219726562,
+      "learning_rate": 0.00016852568965172791,
+      "loss": 1.8018,
+      "step": 74
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "grad_norm": 3.4955344200134277,
+      "learning_rate": 0.00016763379943809028,
+      "loss": 1.4862,
+      "step": 75
+    },
+    {
+      "epoch": 1.4339622641509435,
+      "grad_norm": 3.559926748275757,
+      "learning_rate": 0.00016673188112222394,
+      "loss": 1.6273,
+      "step": 76
+    },
+    {
+      "epoch": 1.4528301886792452,
+      "grad_norm": 2.655087947845459,
+      "learning_rate": 0.0001658200684320748,
+      "loss": 1.6323,
+      "step": 77
+    },
+    {
+      "epoch": 1.4716981132075473,
+      "grad_norm": 2.3575522899627686,
+      "learning_rate": 0.00016489849656263337,
+      "loss": 1.4034,
+      "step": 78
+    },
+    {
+      "epoch": 1.490566037735849,
+      "grad_norm": 3.3757848739624023,
+      "learning_rate": 0.00016396730215588915,
+      "loss": 1.4618,
+      "step": 79
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 3.6009631156921387,
+      "learning_rate": 0.00016302662328057088,
+      "loss": 1.5391,
+      "step": 80
+    },
+    {
+      "epoch": 1.5283018867924527,
+      "grad_norm": 3.2048425674438477,
+      "learning_rate": 0.00016207659941167485,
+      "loss": 1.7071,
+      "step": 81
+    },
+    {
+      "epoch": 1.5471698113207548,
+      "grad_norm": 3.4440090656280518,
+      "learning_rate": 0.00016111737140978494,
+      "loss": 1.7924,
+      "step": 82
+    },
+    {
+      "epoch": 1.5660377358490565,
+      "grad_norm": 3.539468288421631,
+      "learning_rate": 0.00016014908150018703,
+      "loss": 1.3348,
+      "step": 83
+    },
+    {
+      "epoch": 1.5849056603773586,
+      "grad_norm": 4.010547161102295,
+      "learning_rate": 0.00015917187325178138,
+      "loss": 1.4573,
+      "step": 84
+    },
+    {
+      "epoch": 1.6037735849056602,
+      "grad_norm": 3.605386734008789,
+      "learning_rate": 0.0001581858915557953,
+      "loss": 1.5987,
+      "step": 85
+    },
+    {
+      "epoch": 1.6226415094339623,
+      "grad_norm": 2.3369998931884766,
+      "learning_rate": 0.0001571912826043003,
+      "loss": 1.555,
+      "step": 86
+    },
+    {
+      "epoch": 1.641509433962264,
+      "grad_norm": 3.1403045654296875,
+      "learning_rate": 0.00015618819386853606,
+      "loss": 1.5138,
+      "step": 87
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "grad_norm": 3.0938310623168945,
+      "learning_rate": 0.0001551767740770446,
+      "loss": 1.444,
+      "step": 88
+    },
+    {
+      "epoch": 1.6792452830188678,
+      "grad_norm": 2.6411221027374268,
+      "learning_rate": 0.00015415717319361847,
+      "loss": 1.2681,
+      "step": 89
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 3.132369041442871,
+      "learning_rate": 0.00015312954239506533,
+      "loss": 1.6189,
+      "step": 90
+    },
+    {
+      "epoch": 1.7169811320754715,
+      "grad_norm": 2.8721351623535156,
+      "learning_rate": 0.00015209403404879303,
+      "loss": 1.351,
+      "step": 91
+    },
+    {
+      "epoch": 1.7358490566037736,
+      "grad_norm": 3.856358051300049,
+      "learning_rate": 0.0001510508016902179,
+      "loss": 1.5624,
+      "step": 92
+    },
+    {
+      "epoch": 1.7547169811320755,
+      "grad_norm": 3.9972498416900635,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.447,
+      "step": 93
+    },
+    {
+      "epoch": 1.7735849056603774,
+      "grad_norm": 2.7673652172088623,
+      "learning_rate": 0.00014894178478110857,
+      "loss": 1.4526,
+      "step": 94
+    },
+    {
+      "epoch": 1.7924528301886793,
+      "grad_norm": 3.1705822944641113,
+      "learning_rate": 0.00014787631293572092,
+      "loss": 1.2079,
+      "step": 95
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 2.8597121238708496,
+      "learning_rate": 0.0001468037424419586,
+      "loss": 1.1173,
+      "step": 96
+    },
+    {
+      "epoch": 1.830188679245283,
+      "grad_norm": 2.7988481521606445,
+      "learning_rate": 0.00014572423233046386,
+      "loss": 1.5903,
+      "step": 97
+    },
+    {
+      "epoch": 1.849056603773585,
+      "grad_norm": 2.7639687061309814,
+      "learning_rate": 0.00014463794266081993,
+      "loss": 1.2,
+      "step": 98
+    },
+    {
+      "epoch": 1.8679245283018868,
+      "grad_norm": 3.7310075759887695,
+      "learning_rate": 0.00014354503449781912,
+      "loss": 1.5971,
+      "step": 99
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 3.9048783779144287,
+      "learning_rate": 0.00014244566988758152,
+      "loss": 1.4054,
+      "step": 100
+    },
+    {
+      "epoch": 1.9056603773584906,
+      "grad_norm": 3.424018144607544,
+      "learning_rate": 0.00014134001183352832,
+      "loss": 1.4166,
+      "step": 101
+    },
+    {
+      "epoch": 1.9245283018867925,
+      "grad_norm": 3.7610878944396973,
+      "learning_rate": 0.00014022822427221324,
+      "loss": 1.3645,
+      "step": 102
+    },
+    {
+      "epoch": 1.9433962264150944,
+      "grad_norm": 3.938345193862915,
+      "learning_rate": 0.0001391104720490156,
+      "loss": 1.2987,
+      "step": 103
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 3.1331722736358643,
+      "learning_rate": 0.00013798692089369855,
+      "loss": 1.4195,
+      "step": 104
+    },
+    {
+      "epoch": 1.9811320754716981,
+      "grad_norm": 3.347231388092041,
+      "learning_rate": 0.00013685773739583617,
+      "loss": 1.4004,
+      "step": 105
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.958104610443115,
+      "learning_rate": 0.0001357230889801133,
+      "loss": 1.295,
+      "step": 106
+    },
+    {
+      "epoch": 2.018867924528302,
+      "grad_norm": 2.7938392162323,
+      "learning_rate": 0.00013458314388150114,
+      "loss": 0.8655,
+      "step": 107
+    },
+    {
+      "epoch": 2.0377358490566038,
+      "grad_norm": 3.1623213291168213,
+      "learning_rate": 0.00013343807112031327,
+      "loss": 0.8786,
+      "step": 108
+    },
+    {
+      "epoch": 2.056603773584906,
+      "grad_norm": 2.9963018894195557,
+      "learning_rate": 0.00013228804047714463,
+      "loss": 0.8819,
+      "step": 109
+    },
+    {
+      "epoch": 2.0754716981132075,
+      "grad_norm": 2.4673538208007812,
+      "learning_rate": 0.00013113322246769817,
+      "loss": 0.8189,
+      "step": 110
+    },
+    {
+      "epoch": 2.0943396226415096,
+      "grad_norm": 3.187716245651245,
+      "learning_rate": 0.00012997378831750242,
+      "loss": 0.8267,
+      "step": 111
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 2.730367422103882,
+      "learning_rate": 0.00012880990993652377,
+      "loss": 0.7693,
+      "step": 112
+    },
+    {
+      "epoch": 2.1320754716981134,
+      "grad_norm": 2.9551656246185303,
+      "learning_rate": 0.00012764175989367718,
+      "loss": 0.7605,
+      "step": 113
+    },
+    {
+      "epoch": 2.150943396226415,
+      "grad_norm": 4.102267742156982,
+      "learning_rate": 0.00012646951139123934,
+      "loss": 0.907,
+      "step": 114
+    },
+    {
+      "epoch": 2.169811320754717,
+      "grad_norm": 4.0557026863098145,
+      "learning_rate": 0.00012529333823916807,
+      "loss": 0.9109,
+      "step": 115
+    },
+    {
+      "epoch": 2.188679245283019,
+      "grad_norm": 3.8453004360198975,
+      "learning_rate": 0.0001241134148293311,
+      "loss": 0.7561,
+      "step": 116
+    },
+    {
+      "epoch": 2.207547169811321,
+      "grad_norm": 5.24804162979126,
+      "learning_rate": 0.00012292991610964903,
+      "loss": 0.9191,
+      "step": 117
+    },
+    {
+      "epoch": 2.2264150943396226,
+      "grad_norm": 4.6383795738220215,
+      "learning_rate": 0.00012174301755815571,
+      "loss": 0.8057,
+      "step": 118
+    },
+    {
+      "epoch": 2.2452830188679247,
+      "grad_norm": 4.45780086517334,
+      "learning_rate": 0.00012055289515698007,
+      "loss": 0.895,
+      "step": 119
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 4.987161636352539,
+      "learning_rate": 0.00011935972536625302,
+      "loss": 0.8043,
+      "step": 120
+    },
+    {
+      "epoch": 2.2830188679245285,
+      "grad_norm": 3.0627079010009766,
+      "learning_rate": 0.00011816368509794364,
+      "loss": 0.7107,
+      "step": 121
+    },
+    {
+      "epoch": 2.30188679245283,
+      "grad_norm": 3.219001293182373,
+      "learning_rate": 0.00011696495168962847,
+      "loss": 0.7408,
+      "step": 122
+    },
+    {
+      "epoch": 2.3207547169811322,
+      "grad_norm": 3.5602636337280273,
+      "learning_rate": 0.00011576370287819736,
+      "loss": 0.748,
+      "step": 123
+    },
+    {
+      "epoch": 2.339622641509434,
+      "grad_norm": 4.614081382751465,
+      "learning_rate": 0.00011456011677350051,
+      "loss": 0.7347,
+      "step": 124
+    },
+    {
+      "epoch": 2.358490566037736,
+      "grad_norm": 3.4051380157470703,
+      "learning_rate": 0.0001133543718319398,
+      "loss": 0.6849,
+      "step": 125
+    },
+    {
+      "epoch": 2.3773584905660377,
+      "grad_norm": 4.593987464904785,
+      "learning_rate": 0.00011214664683000927,
+      "loss": 0.811,
+      "step": 126
+    },
+    {
+      "epoch": 2.3962264150943398,
+      "grad_norm": 3.460425853729248,
+      "learning_rate": 0.00011093712083778746,
+      "loss": 0.7217,
+      "step": 127
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 4.334282875061035,
+      "learning_rate": 0.0001097259731923869,
+      "loss": 0.9764,
+      "step": 128
+    },
+    {
+      "epoch": 2.4339622641509435,
+      "grad_norm": 4.153921127319336,
+      "learning_rate": 0.00010851338347136357,
+      "loss": 0.755,
+      "step": 129
+    },
+    {
+      "epoch": 2.452830188679245,
+      "grad_norm": 3.751748561859131,
+      "learning_rate": 0.00010729953146609076,
+      "loss": 0.7872,
+      "step": 130
+    },
+    {
+      "epoch": 2.4716981132075473,
+      "grad_norm": 3.157301664352417,
+      "learning_rate": 0.00010608459715510139,
+      "loss": 0.6977,
+      "step": 131
+    },
+    {
+      "epoch": 2.490566037735849,
+      "grad_norm": 3.9355554580688477,
+      "learning_rate": 0.00010486876067740252,
+      "loss": 0.6962,
+      "step": 132
+    },
+    {
+      "epoch": 2.509433962264151,
+      "grad_norm": 3.7606890201568604,
+      "learning_rate": 0.0001036522023057659,
+      "loss": 0.7766,
+      "step": 133
+    },
+    {
+      "epoch": 2.5283018867924527,
+      "grad_norm": 3.3978798389434814,
+      "learning_rate": 0.00010243510241999899,
+      "loss": 0.7456,
+      "step": 134
+    },
+    {
+      "epoch": 2.547169811320755,
+      "grad_norm": 4.373416423797607,
+      "learning_rate": 0.00010121764148019976,
+      "loss": 0.7904,
+      "step": 135
+    },
+    {
+      "epoch": 2.5660377358490565,
+      "grad_norm": 3.233684539794922,
+      "learning_rate": 0.0001,
+      "loss": 0.6922,
+      "step": 136
+    },
+    {
+      "epoch": 2.5849056603773586,
+      "grad_norm": 2.8673453330993652,
+      "learning_rate": 9.878235851980025e-05,
+      "loss": 0.755,
+      "step": 137
+    },
+    {
+      "epoch": 2.6037735849056602,
+      "grad_norm": 4.115866661071777,
+      "learning_rate": 9.756489758000105e-05,
+      "loss": 0.8105,
+      "step": 138
+    },
+    {
+      "epoch": 2.6226415094339623,
+      "grad_norm": 4.364792823791504,
+      "learning_rate": 9.63477976942341e-05,
+      "loss": 0.8063,
+      "step": 139
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 3.319819927215576,
+      "learning_rate": 9.513123932259751e-05,
+      "loss": 0.7105,
+      "step": 140
+    },
+    {
+      "epoch": 2.660377358490566,
+      "grad_norm": 3.4825072288513184,
+      "learning_rate": 9.391540284489862e-05,
+      "loss": 0.6319,
+      "step": 141
+    },
+    {
+      "epoch": 2.6792452830188678,
+      "grad_norm": 4.888297080993652,
+      "learning_rate": 9.270046853390925e-05,
+      "loss": 0.9002,
+      "step": 142
+    },
+    {
+      "epoch": 2.69811320754717,
+      "grad_norm": 3.9948232173919678,
+      "learning_rate": 9.148661652863642e-05,
+      "loss": 0.8127,
+      "step": 143
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 4.544849395751953,
+      "learning_rate": 9.027402680761309e-05,
+      "loss": 0.8186,
+      "step": 144
+    },
+    {
+      "epoch": 2.7358490566037736,
+      "grad_norm": 4.437803268432617,
+      "learning_rate": 8.906287916221259e-05,
+      "loss": 0.8359,
+      "step": 145
+    },
+    {
+      "epoch": 2.7547169811320753,
+      "grad_norm": 4.868703842163086,
+      "learning_rate": 8.785335316999078e-05,
+      "loss": 0.8483,
+      "step": 146
+    },
+    {
+      "epoch": 2.7735849056603774,
+      "grad_norm": 4.967810153961182,
+      "learning_rate": 8.664562816806022e-05,
+      "loss": 0.9694,
+      "step": 147
+    },
+    {
+      "epoch": 2.7924528301886795,
+      "grad_norm": 4.962375164031982,
+      "learning_rate": 8.543988322649954e-05,
+      "loss": 0.9566,
+      "step": 148
+    },
+    {
+      "epoch": 2.811320754716981,
+      "grad_norm": 3.4327187538146973,
+      "learning_rate": 8.423629712180265e-05,
+      "loss": 0.7338,
+      "step": 149
+    },
+    {
+      "epoch": 2.830188679245283,
+      "grad_norm": 4.282032012939453,
+      "learning_rate": 8.303504831037154e-05,
+      "loss": 0.7555,
+      "step": 150
+    },
+    {
+      "epoch": 2.849056603773585,
+      "grad_norm": 2.7784788608551025,
+      "learning_rate": 8.183631490205637e-05,
+      "loss": 0.5799,
+      "step": 151
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 3.580303192138672,
+      "learning_rate": 8.064027463374702e-05,
+      "loss": 0.8267,
+      "step": 152
+    },
+    {
+      "epoch": 2.8867924528301887,
+      "grad_norm": 3.964838981628418,
+      "learning_rate": 7.944710484301995e-05,
+      "loss": 0.8239,
+      "step": 153
+    },
+    {
+      "epoch": 2.9056603773584904,
+      "grad_norm": 3.3083627223968506,
+      "learning_rate": 7.825698244184431e-05,
+      "loss": 0.6842,
+      "step": 154
+    },
+    {
+      "epoch": 2.9245283018867925,
+      "grad_norm": 3.5870604515075684,
+      "learning_rate": 7.707008389035101e-05,
+      "loss": 0.7782,
+      "step": 155
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "grad_norm": 3.623816728591919,
+      "learning_rate": 7.588658517066892e-05,
+      "loss": 0.7621,
+      "step": 156
+    },
+    {
+      "epoch": 2.9622641509433962,
+      "grad_norm": 3.9412410259246826,
+      "learning_rate": 7.470666176083192e-05,
+      "loss": 0.7291,
+      "step": 157
+    },
+    {
+      "epoch": 2.981132075471698,
+      "grad_norm": 3.9385383129119873,
+      "learning_rate": 7.353048860876064e-05,
+      "loss": 0.8624,
+      "step": 158
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.64533519744873,
+      "learning_rate": 7.235824010632283e-05,
+      "loss": 1.1187,
+      "step": 159
+    },
+    {
+      "epoch": 3.018867924528302,
+      "grad_norm": 2.421513080596924,
+      "learning_rate": 7.119009006347625e-05,
+      "loss": 0.5056,
+      "step": 160
+    },
+    {
+      "epoch": 3.0377358490566038,
+      "grad_norm": 3.147653102874756,
+      "learning_rate": 7.002621168249759e-05,
+      "loss": 0.5471,
+      "step": 161
+    },
+    {
+      "epoch": 3.056603773584906,
+      "grad_norm": 2.8054962158203125,
+      "learning_rate": 6.886677753230184e-05,
+      "loss": 0.5752,
+      "step": 162
+    },
+    {
+      "epoch": 3.0754716981132075,
+      "grad_norm": 2.7173664569854736,
+      "learning_rate": 6.77119595228554e-05,
+      "loss": 0.5369,
+      "step": 163
+    },
+    {
+      "epoch": 3.0943396226415096,
+      "grad_norm": 3.901042938232422,
+      "learning_rate": 6.656192887968675e-05,
+      "loss": 0.4626,
+      "step": 164
+    },
+    {
+      "epoch": 3.1132075471698113,
+      "grad_norm": 2.6537182331085205,
+      "learning_rate": 6.541685611849887e-05,
+      "loss": 0.5124,
+      "step": 165
+    },
+    {
+      "epoch": 3.1320754716981134,
+      "grad_norm": 2.607658863067627,
+      "learning_rate": 6.427691101988673e-05,
+      "loss": 0.5035,
+      "step": 166
+    },
+    {
+      "epoch": 3.150943396226415,
+      "grad_norm": 3.2988381385803223,
+      "learning_rate": 6.314226260416382e-05,
+      "loss": 0.5092,
+      "step": 167
+    },
+    {
+      "epoch": 3.169811320754717,
+      "grad_norm": 2.6154379844665527,
+      "learning_rate": 6.201307910630146e-05,
+      "loss": 0.3957,
+      "step": 168
+    },
+    {
+      "epoch": 3.188679245283019,
+      "grad_norm": 2.4007461071014404,
+      "learning_rate": 6.0889527950984416e-05,
+      "loss": 0.3623,
+      "step": 169
+    },
+    {
+      "epoch": 3.207547169811321,
+      "grad_norm": 2.508924722671509,
+      "learning_rate": 5.977177572778678e-05,
+      "loss": 0.3206,
+      "step": 170
+    },
+    {
+      "epoch": 3.2264150943396226,
+      "grad_norm": 3.345323085784912,
+      "learning_rate": 5.865998816647171e-05,
+      "loss": 0.5237,
+      "step": 171
+    },
+    {
+      "epoch": 3.2452830188679247,
+      "grad_norm": 3.6217191219329834,
+      "learning_rate": 5.755433011241851e-05,
+      "loss": 0.4244,
+      "step": 172
+    },
+    {
+      "epoch": 3.2641509433962264,
+      "grad_norm": 2.2621614933013916,
+      "learning_rate": 5.645496550218089e-05,
+      "loss": 0.3281,
+      "step": 173
+    },
+    {
+      "epoch": 3.2830188679245285,
+      "grad_norm": 2.162639617919922,
+      "learning_rate": 5.536205733918007e-05,
+      "loss": 0.2759,
+      "step": 174
+    },
+    {
+      "epoch": 3.30188679245283,
+      "grad_norm": 3.1658148765563965,
+      "learning_rate": 5.4275767669536146e-05,
+      "loss": 0.3728,
+      "step": 175
+    },
+    {
+      "epoch": 3.3207547169811322,
+      "grad_norm": 4.21240234375,
+      "learning_rate": 5.3196257558041386e-05,
+      "loss": 0.4965,
+      "step": 176
+    },
+    {
+      "epoch": 3.339622641509434,
+      "grad_norm": 2.725277900695801,
+      "learning_rate": 5.212368706427912e-05,
+      "loss": 0.2835,
+      "step": 177
+    },
+    {
+      "epoch": 3.358490566037736,
+      "grad_norm": 3.9107651710510254,
+      "learning_rate": 5.105821521889147e-05,
+      "loss": 0.4181,
+      "step": 178
+    },
+    {
+      "epoch": 3.3773584905660377,
+      "grad_norm": 3.5245237350463867,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4086,
+      "step": 179
+    },
+    {
+      "epoch": 3.3962264150943398,
+      "grad_norm": 4.99196195602417,
+      "learning_rate": 4.894919830978212e-05,
+      "loss": 0.5434,
+      "step": 180
+    },
+    {
+      "epoch": 3.4150943396226414,
+      "grad_norm": 4.471066474914551,
+      "learning_rate": 4.790596595120699e-05,
+      "loss": 0.5829,
+      "step": 181
+    },
+    {
+      "epoch": 3.4339622641509435,
+      "grad_norm": 4.952585697174072,
+      "learning_rate": 4.687045760493468e-05,
+      "loss": 0.5025,
+      "step": 182
+    },
+    {
+      "epoch": 3.452830188679245,
+      "grad_norm": 3.4417154788970947,
+      "learning_rate": 4.5842826806381544e-05,
+      "loss": 0.3641,
+      "step": 183
+    },
+    {
+      "epoch": 3.4716981132075473,
+      "grad_norm": 4.35126256942749,
+      "learning_rate": 4.48232259229554e-05,
+      "loss": 0.4988,
+      "step": 184
+    },
+    {
+      "epoch": 3.490566037735849,
+      "grad_norm": 4.080723285675049,
+      "learning_rate": 4.381180613146395e-05,
+      "loss": 0.4638,
+      "step": 185
+    },
+    {
+      "epoch": 3.509433962264151,
+      "grad_norm": 3.815850019454956,
+      "learning_rate": 4.280871739569972e-05,
+      "loss": 0.4974,
+      "step": 186
+    },
+    {
+      "epoch": 3.5283018867924527,
+      "grad_norm": 2.9292290210723877,
+      "learning_rate": 4.181410844420474e-05,
+      "loss": 0.3731,
+      "step": 187
+    },
+    {
+      "epoch": 3.547169811320755,
+      "grad_norm": 3.3885891437530518,
+      "learning_rate": 4.0828126748218654e-05,
+      "loss": 0.4534,
+      "step": 188
+    },
+    {
+      "epoch": 3.5660377358490565,
+      "grad_norm": 2.7148234844207764,
+      "learning_rate": 3.985091849981297e-05,
+      "loss": 0.3466,
+      "step": 189
+    },
+    {
+      "epoch": 3.5849056603773586,
+      "grad_norm": 3.8354432582855225,
+      "learning_rate": 3.8882628590215074e-05,
+      "loss": 0.4904,
+      "step": 190
+    },
+    {
+      "epoch": 3.6037735849056602,
+      "grad_norm": 3.343653678894043,
+      "learning_rate": 3.7923400588325155e-05,
+      "loss": 0.4574,
+      "step": 191
+    },
+    {
+      "epoch": 3.6226415094339623,
+      "grad_norm": 2.6676838397979736,
+      "learning_rate": 3.697337671942913e-05,
+      "loss": 0.3529,
+      "step": 192
+    },
+    {
+      "epoch": 3.641509433962264,
+      "grad_norm": 3.5791468620300293,
+      "learning_rate": 3.60326978441109e-05,
+      "loss": 0.4859,
+      "step": 193
+    },
+    {
+      "epoch": 3.660377358490566,
+      "grad_norm": 3.582289695739746,
+      "learning_rate": 3.510150343736668e-05,
+      "loss": 0.5873,
+      "step": 194
+    },
+    {
+      "epoch": 3.6792452830188678,
+      "grad_norm": 3.2222278118133545,
+      "learning_rate": 3.4179931567925216e-05,
+      "loss": 0.4527,
+      "step": 195
+    },
+    {
+      "epoch": 3.69811320754717,
+      "grad_norm": 5.0612616539001465,
+      "learning_rate": 3.3268118877776066e-05,
+      "loss": 0.5701,
+      "step": 196
+    },
+    {
+      "epoch": 3.7169811320754715,
+      "grad_norm": 4.360406875610352,
+      "learning_rate": 3.236620056190972e-05,
+      "loss": 0.5906,
+      "step": 197
+    },
+    {
+      "epoch": 3.7358490566037736,
+      "grad_norm": 3.25287127494812,
+      "learning_rate": 3.147431034827208e-05,
+      "loss": 0.4554,
+      "step": 198
+    },
+    {
+      "epoch": 3.7547169811320753,
+      "grad_norm": 2.8619189262390137,
+      "learning_rate": 3.059258047793661e-05,
+      "loss": 0.4203,
+      "step": 199
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "grad_norm": 4.216496467590332,
+      "learning_rate": 2.9721141685496823e-05,
+      "loss": 0.5493,
+      "step": 200
+    },
+    {
+      "epoch": 3.7924528301886795,
+      "grad_norm": 4.07708215713501,
+      "learning_rate": 2.8860123179682242e-05,
+      "loss": 0.5709,
+      "step": 201
+    },
+    {
+      "epoch": 3.811320754716981,
+      "grad_norm": 3.971759796142578,
+      "learning_rate": 2.800965262420043e-05,
+      "loss": 0.5874,
+      "step": 202
+    },
+    {
+      "epoch": 3.830188679245283,
+      "grad_norm": 2.842815399169922,
+      "learning_rate": 2.716985611880841e-05,
+      "loss": 0.3789,
+      "step": 203
+    },
+    {
+      "epoch": 3.849056603773585,
+      "grad_norm": 2.8079545497894287,
+      "learning_rate": 2.6340858180615646e-05,
+      "loss": 0.4352,
+      "step": 204
+    },
+    {
+      "epoch": 3.867924528301887,
+      "grad_norm": 3.446413516998291,
+      "learning_rate": 2.5522781725621813e-05,
+      "loss": 0.503,
+      "step": 205
+    },
+    {
+      "epoch": 3.8867924528301887,
+      "grad_norm": 4.122068405151367,
+      "learning_rate": 2.471574805049206e-05,
+      "loss": 0.6232,
+      "step": 206
+    },
+    {
+      "epoch": 3.9056603773584904,
+      "grad_norm": 3.0119433403015137,
+      "learning_rate": 2.3919876814572194e-05,
+      "loss": 0.4132,
+      "step": 207
+    },
+    {
+      "epoch": 3.9245283018867925,
+      "grad_norm": 2.8748209476470947,
+      "learning_rate": 2.3135286022146785e-05,
+      "loss": 0.4116,
+      "step": 208
+    },
+    {
+      "epoch": 3.9433962264150946,
+      "grad_norm": 2.9952023029327393,
+      "learning_rate": 2.236209200494258e-05,
+      "loss": 0.4076,
+      "step": 209
+    },
+    {
+      "epoch": 3.9622641509433962,
+      "grad_norm": 3.554006814956665,
+      "learning_rate": 2.1600409404879874e-05,
+      "loss": 0.5219,
+      "step": 210
+    },
+    {
+      "epoch": 3.981132075471698,
+      "grad_norm": 3.578646659851074,
+      "learning_rate": 2.0850351157074598e-05,
+      "loss": 0.6189,
+      "step": 211
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.404101848602295,
+      "learning_rate": 2.011202847309329e-05,
+      "loss": 0.4517,
+      "step": 212
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7382794559750144e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-212/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b1f3cc06609e6c3214b2ec2bc88284bb9f2f0a116540d08a78d352d59fb1b5
+size 6456

checkpoint-265/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.14.0

checkpoint-265/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-265/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1626c27c148d75be565ca192cd6f82889d748d4dba5ef6c4270fbfb973ff4c6
+size 80792096