Add files using upload-large-folder tool

.gitattributes

@@ -45,3 +45,7 @@ checkpoint-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3087/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4410/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: Qwen-3-0.6B-it-Medical-LoRA
 tags:
 - generated_from_trainer
-- unsloth
-- sft
 - trl
+- sft
+- unsloth
 licence: license
 ---
 

checkpoint-4200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+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-4200/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc7771c72a0313706c909ca821cc832bc940a1553cdc0afd7bc06892beb0857
+size 40422168

checkpoint-4200/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-4200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92171c9d2a5dbb24a0573b64b9ee20fabbd327695904eaaad55f24bd0e1542e9
+size 21979091

checkpoint-4200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c8e01d63a3f5ec37577c8a512fbaa724203e22c133d4c4fd0214726b44c371
+size 14645

checkpoint-4200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0563f0c122c10b3bb9fb8ef7a029cf4fe15b88c3307945ff50155d3485ee7edd
+size 1383

checkpoint-4200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8438284aa8d7b77e17d11df209ee1f04e8e880a3f086b6085176725c5b2cea
+size 1465

checkpoint-4200/special_tokens_map.json

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

checkpoint-4200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
+size 11422753

checkpoint-4200/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- set message = messages[index] %}\n    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}\n    {%- set tool_start = '<tool_response>' %}\n    {%- set tool_start_length = tool_start|length %}\n    {%- set start_of_message = current_content[:tool_start_length] %}\n    {%- set tool_end = '</tool_response>' %}\n    {%- set tool_end_length = tool_end|length %}\n    {%- set start_pos = (current_content|length) - tool_end_length %}\n    {%- if start_pos < 0 %}\n        {%- set start_pos = 0 %}\n    {%- endif %}\n    {%- set end_of_message = current_content[start_pos:] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}\n        {%- set content = m_content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in m_content %}\n                {%- set content = (m_content.split('</think>')|last).lstrip('\\n') %}\n                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\\n') %}\n                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-4200/trainer_state.json

@@ -0,0 +1,958 @@
+{
+  "best_global_step": 4200,
+  "best_metric": 0.8649076223373413,
+  "best_model_checkpoint": "Qwen-3-0.6B-it-Medical-LoRA/checkpoint-4200",
+  "epoch": 9.52321630804077,
+  "eval_steps": 100,
+  "global_step": 4200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11325028312570781,
+      "grad_norm": 0.3080866038799286,
+      "learning_rate": 0.00019075425790754258,
+      "loss": 1.8711,
+      "step": 50
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "grad_norm": 0.28974413871765137,
+      "learning_rate": 0.0001664233576642336,
+      "loss": 1.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "eval_loss": 1.3033037185668945,
+      "eval_runtime": 217.1489,
+      "eval_samples_per_second": 7.225,
+      "eval_steps_per_second": 0.907,
+      "step": 100
+    },
+    {
+      "epoch": 0.33975084937712347,
+      "grad_norm": 0.3371483385562897,
+      "learning_rate": 0.0001420924574209246,
+      "loss": 1.2923,
+      "step": 150
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "grad_norm": 0.35730767250061035,
+      "learning_rate": 0.00011776155717761557,
+      "loss": 1.2703,
+      "step": 200
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "eval_loss": 1.2490053176879883,
+      "eval_runtime": 217.4793,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 200
+    },
+    {
+      "epoch": 0.5662514156285391,
+      "grad_norm": 0.35110780596733093,
+      "learning_rate": 9.343065693430657e-05,
+      "loss": 1.2397,
+      "step": 250
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "grad_norm": 0.35077276825904846,
+      "learning_rate": 6.909975669099758e-05,
+      "loss": 1.232,
+      "step": 300
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "eval_loss": 1.2211977243423462,
+      "eval_runtime": 217.5364,
+      "eval_samples_per_second": 7.213,
+      "eval_steps_per_second": 0.906,
+      "step": 300
+    },
+    {
+      "epoch": 0.7927519818799547,
+      "grad_norm": 0.3939191699028015,
+      "learning_rate": 4.476885644768857e-05,
+      "loss": 1.2241,
+      "step": 350
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "grad_norm": 0.366871178150177,
+      "learning_rate": 2.0437956204379563e-05,
+      "loss": 1.2078,
+      "step": 400
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "eval_loss": 1.2062289714813232,
+      "eval_runtime": 217.4838,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 400
+    },
+    {
+      "epoch": 1.0203850509626273,
+      "grad_norm": 0.3808969259262085,
+      "learning_rate": 0.00010164319248826291,
+      "loss": 1.1819,
+      "step": 450
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "grad_norm": 0.43216949701309204,
+      "learning_rate": 8.990610328638498e-05,
+      "loss": 1.19,
+      "step": 500
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "eval_loss": 1.1994948387145996,
+      "eval_runtime": 217.3626,
+      "eval_samples_per_second": 7.218,
+      "eval_steps_per_second": 0.906,
+      "step": 500
+    },
+    {
+      "epoch": 1.246885617214043,
+      "grad_norm": 0.4280295968055725,
+      "learning_rate": 7.816901408450704e-05,
+      "loss": 1.1971,
+      "step": 550
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "grad_norm": 0.4056779146194458,
+      "learning_rate": 6.643192488262912e-05,
+      "loss": 1.1771,
+      "step": 600
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "eval_loss": 1.1834282875061035,
+      "eval_runtime": 217.4514,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 0.906,
+      "step": 600
+    },
+    {
+      "epoch": 1.4733861834654587,
+      "grad_norm": 0.4397243857383728,
+      "learning_rate": 5.469483568075118e-05,
+      "loss": 1.1544,
+      "step": 650
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "grad_norm": 0.4214654862880707,
+      "learning_rate": 4.295774647887324e-05,
+      "loss": 1.1789,
+      "step": 700
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "eval_loss": 1.1712530851364136,
+      "eval_runtime": 217.6023,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.905,
+      "step": 700
+    },
+    {
+      "epoch": 1.6998867497168741,
+      "grad_norm": 0.43076109886169434,
+      "learning_rate": 3.1220657276995305e-05,
+      "loss": 1.1522,
+      "step": 750
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "grad_norm": 0.4253358244895935,
+      "learning_rate": 1.9483568075117372e-05,
+      "loss": 1.1508,
+      "step": 800
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "eval_loss": 1.1622345447540283,
+      "eval_runtime": 217.3951,
+      "eval_samples_per_second": 7.217,
+      "eval_steps_per_second": 0.906,
+      "step": 800
+    },
+    {
+      "epoch": 1.9263873159682898,
+      "grad_norm": 0.4359077215194702,
+      "learning_rate": 7.746478873239436e-06,
+      "loss": 1.1422,
+      "step": 850
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "grad_norm": 0.4511992633342743,
+      "learning_rate": 0.00014314687602224403,
+      "loss": 1.149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "eval_loss": 1.167581558227539,
+      "eval_runtime": 218.6888,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 0.901,
+      "step": 900
+    },
+    {
+      "epoch": 2.1540203850509627,
+      "grad_norm": 0.47519659996032715,
+      "learning_rate": 0.00013987569512594048,
+      "loss": 1.1498,
+      "step": 950
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "grad_norm": 0.4559363126754761,
+      "learning_rate": 0.00013660451422963692,
+      "loss": 1.1469,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "eval_loss": 1.1536333560943604,
+      "eval_runtime": 218.921,
+      "eval_samples_per_second": 7.167,
+      "eval_steps_per_second": 0.9,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3805209513023784,
+      "grad_norm": 0.49805569648742676,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.123,
+      "step": 1050
+    },
+    {
+      "epoch": 2.493771234428086,
+      "grad_norm": 0.4767671823501587,
+      "learning_rate": 0.00013006215243702978,
+      "loss": 1.1119,
+      "step": 1100
+    },
+    {
+      "epoch": 2.493771234428086,
+      "eval_loss": 1.1321617364883423,
+      "eval_runtime": 218.8468,
+      "eval_samples_per_second": 7.169,
+      "eval_steps_per_second": 0.9,
+      "step": 1100
+    },
+    {
+      "epoch": 2.607021517553794,
+      "grad_norm": 0.4313490688800812,
+      "learning_rate": 0.0001267909715407262,
+      "loss": 1.1096,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "grad_norm": 0.46401792764663696,
+      "learning_rate": 0.00012351979064442265,
+      "loss": 1.0929,
+      "step": 1200
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "eval_loss": 1.1138092279434204,
+      "eval_runtime": 219.2403,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8335220838052093,
+      "grad_norm": 0.46533071994781494,
+      "learning_rate": 0.00012024860974811907,
+      "loss": 1.0894,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "grad_norm": 0.42782357335090637,
+      "learning_rate": 0.00011697742885181551,
+      "loss": 1.072,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "eval_loss": 1.0986168384552002,
+      "eval_runtime": 219.0662,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 1300
+    },
+    {
+      "epoch": 3.061155152887882,
+      "grad_norm": 0.46029889583587646,
+      "learning_rate": 0.00011370624795551194,
+      "loss": 1.0936,
+      "step": 1350
+    },
+    {
+      "epoch": 3.17440543601359,
+      "grad_norm": 0.5067735314369202,
+      "learning_rate": 0.00011043506705920839,
+      "loss": 1.0304,
+      "step": 1400
+    },
+    {
+      "epoch": 3.17440543601359,
+      "eval_loss": 1.0839864015579224,
+      "eval_runtime": 219.2396,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1400
+    },
+    {
+      "epoch": 3.287655719139298,
+      "grad_norm": 0.46760454773902893,
+      "learning_rate": 0.0001071638861629048,
+      "loss": 1.0361,
+      "step": 1450
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "grad_norm": 0.5199077129364014,
+      "learning_rate": 0.00010389270526660124,
+      "loss": 1.0304,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "eval_loss": 1.070657730102539,
+      "eval_runtime": 219.1222,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1500
+    },
+    {
+      "epoch": 3.5141562853907136,
+      "grad_norm": 0.496124267578125,
+      "learning_rate": 0.00010062152437029768,
+      "loss": 1.0202,
+      "step": 1550
+    },
+    {
+      "epoch": 3.627406568516421,
+      "grad_norm": 0.5154497623443604,
+      "learning_rate": 9.735034347399413e-05,
+      "loss": 1.007,
+      "step": 1600
+    },
+    {
+      "epoch": 3.627406568516421,
+      "eval_loss": 1.0554137229919434,
+      "eval_runtime": 219.2648,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.898,
+      "step": 1600
+    },
+    {
+      "epoch": 3.7406568516421292,
+      "grad_norm": 0.4881006181240082,
+      "learning_rate": 9.407916257769055e-05,
+      "loss": 0.9934,
+      "step": 1650
+    },
+    {
+      "epoch": 3.853907134767837,
+      "grad_norm": 0.5507743954658508,
+      "learning_rate": 9.080798168138699e-05,
+      "loss": 0.9894,
+      "step": 1700
+    },
+    {
+      "epoch": 3.853907134767837,
+      "eval_loss": 1.0418345928192139,
+      "eval_runtime": 219.154,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 1700
+    },
+    {
+      "epoch": 3.967157417893545,
+      "grad_norm": 0.5333808064460754,
+      "learning_rate": 8.753680078508342e-05,
+      "loss": 0.9795,
+      "step": 1750
+    },
+    {
+      "epoch": 4.081540203850509,
+      "grad_norm": 0.551164448261261,
+      "learning_rate": 8.426561988877985e-05,
+      "loss": 0.974,
+      "step": 1800
+    },
+    {
+      "epoch": 4.081540203850509,
+      "eval_loss": 1.0327671766281128,
+      "eval_runtime": 219.1392,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1800
+    },
+    {
+      "epoch": 4.194790486976218,
+      "grad_norm": 0.5678717494010925,
+      "learning_rate": 8.099443899247629e-05,
+      "loss": 0.9204,
+      "step": 1850
+    },
+    {
+      "epoch": 4.308040770101925,
+      "grad_norm": 0.5472707152366638,
+      "learning_rate": 7.772325809617273e-05,
+      "loss": 0.9341,
+      "step": 1900
+    },
+    {
+      "epoch": 4.308040770101925,
+      "eval_loss": 1.0188047885894775,
+      "eval_runtime": 219.1338,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1900
+    },
+    {
+      "epoch": 4.421291053227633,
+      "grad_norm": 0.5799363255500793,
+      "learning_rate": 7.445207719986915e-05,
+      "loss": 0.9313,
+      "step": 1950
+    },
+    {
+      "epoch": 4.534541336353341,
+      "grad_norm": 0.6046631336212158,
+      "learning_rate": 7.11808963035656e-05,
+      "loss": 0.9325,
+      "step": 2000
+    },
+    {
+      "epoch": 4.534541336353341,
+      "eval_loss": 1.004631519317627,
+      "eval_runtime": 219.1114,
+      "eval_samples_per_second": 7.161,
+      "eval_steps_per_second": 0.899,
+      "step": 2000
+    },
+    {
+      "epoch": 4.647791619479049,
+      "grad_norm": 0.5897740721702576,
+      "learning_rate": 6.790971540726203e-05,
+      "loss": 0.9213,
+      "step": 2050
+    },
+    {
+      "epoch": 4.761041902604757,
+      "grad_norm": 0.583991289138794,
+      "learning_rate": 6.463853451095846e-05,
+      "loss": 0.9039,
+      "step": 2100
+    },
+    {
+      "epoch": 4.761041902604757,
+      "eval_loss": 0.9938989877700806,
+      "eval_runtime": 219.0293,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 2100
+    },
+    {
+      "epoch": 4.874292185730464,
+      "grad_norm": 0.6264305710792542,
+      "learning_rate": 6.13673536146549e-05,
+      "loss": 0.9028,
+      "step": 2150
+    },
+    {
+      "epoch": 4.987542468856172,
+      "grad_norm": 0.6474761962890625,
+      "learning_rate": 5.809617271835133e-05,
+      "loss": 0.9053,
+      "step": 2200
+    },
+    {
+      "epoch": 4.987542468856172,
+      "eval_loss": 0.9845430254936218,
+      "eval_runtime": 219.2502,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.899,
+      "step": 2200
+    },
+    {
+      "epoch": 5.101925254813137,
+      "grad_norm": 0.6595875024795532,
+      "learning_rate": 5.4824991822047765e-05,
+      "loss": 0.882,
+      "step": 2250
+    },
+    {
+      "epoch": 5.215175537938845,
+      "grad_norm": 0.6405232548713684,
+      "learning_rate": 5.15538109257442e-05,
+      "loss": 0.8471,
+      "step": 2300
+    },
+    {
+      "epoch": 5.215175537938845,
+      "eval_loss": 0.9782047867774963,
+      "eval_runtime": 219.0751,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2300
+    },
+    {
+      "epoch": 5.3284258210645525,
+      "grad_norm": 0.6547350287437439,
+      "learning_rate": 4.828263002944063e-05,
+      "loss": 0.8602,
+      "step": 2350
+    },
+    {
+      "epoch": 5.44167610419026,
+      "grad_norm": 0.7046269178390503,
+      "learning_rate": 4.501144913313706e-05,
+      "loss": 0.8404,
+      "step": 2400
+    },
+    {
+      "epoch": 5.44167610419026,
+      "eval_loss": 0.9688066244125366,
+      "eval_runtime": 219.0622,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2400
+    },
+    {
+      "epoch": 5.554926387315969,
+      "grad_norm": 0.6331756114959717,
+      "learning_rate": 4.17402682368335e-05,
+      "loss": 0.8286,
+      "step": 2450
+    },
+    {
+      "epoch": 5.668176670441676,
+      "grad_norm": 0.7212900519371033,
+      "learning_rate": 3.846908734052994e-05,
+      "loss": 0.8382,
+      "step": 2500
+    },
+    {
+      "epoch": 5.668176670441676,
+      "eval_loss": 0.9589976668357849,
+      "eval_runtime": 219.1257,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2500
+    },
+    {
+      "epoch": 5.781426953567384,
+      "grad_norm": 0.6771254539489746,
+      "learning_rate": 3.519790644422637e-05,
+      "loss": 0.8359,
+      "step": 2550
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "grad_norm": 0.7171376943588257,
+      "learning_rate": 3.19267255479228e-05,
+      "loss": 0.832,
+      "step": 2600
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "eval_loss": 0.9501948952674866,
+      "eval_runtime": 219.0768,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2600
+    },
+    {
+      "epoch": 6.009060022650057,
+      "grad_norm": 0.6734739542007446,
+      "learning_rate": 2.865554465161924e-05,
+      "loss": 0.8437,
+      "step": 2650
+    },
+    {
+      "epoch": 6.122310305775764,
+      "grad_norm": 0.697407603263855,
+      "learning_rate": 2.538436375531567e-05,
+      "loss": 0.7937,
+      "step": 2700
+    },
+    {
+      "epoch": 6.122310305775764,
+      "eval_loss": 0.9480313658714294,
+      "eval_runtime": 218.949,
+      "eval_samples_per_second": 7.166,
+      "eval_steps_per_second": 0.9,
+      "step": 2700
+    },
+    {
+      "epoch": 6.235560588901472,
+      "grad_norm": 0.7092292904853821,
+      "learning_rate": 2.2113182859012105e-05,
+      "loss": 0.7804,
+      "step": 2750
+    },
+    {
+      "epoch": 6.34881087202718,
+      "grad_norm": 0.7284964919090271,
+      "learning_rate": 1.884200196270854e-05,
+      "loss": 0.7861,
+      "step": 2800
+    },
+    {
+      "epoch": 6.34881087202718,
+      "eval_loss": 0.942541241645813,
+      "eval_runtime": 219.1707,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 2800
+    },
+    {
+      "epoch": 6.462061155152888,
+      "grad_norm": 0.7725135087966919,
+      "learning_rate": 1.557082106640497e-05,
+      "loss": 0.776,
+      "step": 2850
+    },
+    {
+      "epoch": 6.575311438278596,
+      "grad_norm": 0.7266800403594971,
+      "learning_rate": 1.2299640170101408e-05,
+      "loss": 0.7812,
+      "step": 2900
+    },
+    {
+      "epoch": 6.575311438278596,
+      "eval_loss": 0.939509928226471,
+      "eval_runtime": 219.1206,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2900
+    },
+    {
+      "epoch": 6.688561721404303,
+      "grad_norm": 0.7308298349380493,
+      "learning_rate": 9.028459273797842e-06,
+      "loss": 0.7827,
+      "step": 2950
+    },
+    {
+      "epoch": 6.801812004530011,
+      "grad_norm": 0.7362912893295288,
+      "learning_rate": 5.757278377494276e-06,
+      "loss": 0.7917,
+      "step": 3000
+    },
+    {
+      "epoch": 6.801812004530011,
+      "eval_loss": 0.9356247782707214,
+      "eval_runtime": 219.052,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 3000
+    },
+    {
+      "epoch": 6.9150622876557195,
+      "grad_norm": 0.7543765902519226,
+      "learning_rate": 2.4860974811907098e-06,
+      "loss": 0.7738,
+      "step": 3050
+    },
+    {
+      "epoch": 7.029445073612684,
+      "grad_norm": 0.7134389877319336,
+      "learning_rate": 5.986301369863014e-05,
+      "loss": 0.7481,
+      "step": 3100
+    },
+    {
+      "epoch": 7.029445073612684,
+      "eval_loss": 0.9381225109100342,
+      "eval_runtime": 218.2269,
+      "eval_samples_per_second": 7.19,
+      "eval_steps_per_second": 0.903,
+      "step": 3100
+    },
+    {
+      "epoch": 7.1426953567383915,
+      "grad_norm": 0.8131405711174011,
+      "learning_rate": 5.757990867579909e-05,
+      "loss": 0.7725,
+      "step": 3150
+    },
+    {
+      "epoch": 7.2559456398641,
+      "grad_norm": 0.8759368062019348,
+      "learning_rate": 5.529680365296805e-05,
+      "loss": 0.7752,
+      "step": 3200
+    },
+    {
+      "epoch": 7.2559456398641,
+      "eval_loss": 0.9386877417564392,
+      "eval_runtime": 218.4203,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3200
+    },
+    {
+      "epoch": 7.369195922989808,
+      "grad_norm": 0.8374108076095581,
+      "learning_rate": 5.3013698630136986e-05,
+      "loss": 0.7765,
+      "step": 3250
+    },
+    {
+      "epoch": 7.482446206115515,
+      "grad_norm": 0.8505973815917969,
+      "learning_rate": 5.0730593607305946e-05,
+      "loss": 0.7791,
+      "step": 3300
+    },
+    {
+      "epoch": 7.482446206115515,
+      "eval_loss": 0.9266760349273682,
+      "eval_runtime": 218.4773,
+      "eval_samples_per_second": 7.182,
+      "eval_steps_per_second": 0.902,
+      "step": 3300
+    },
+    {
+      "epoch": 7.595696489241223,
+      "grad_norm": 0.8420349359512329,
+      "learning_rate": 4.8447488584474886e-05,
+      "loss": 0.7721,
+      "step": 3350
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "grad_norm": 0.892084002494812,
+      "learning_rate": 4.616438356164384e-05,
+      "loss": 0.7626,
+      "step": 3400
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "eval_loss": 0.9153051376342773,
+      "eval_runtime": 218.391,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 0.902,
+      "step": 3400
+    },
+    {
+      "epoch": 7.822197055492639,
+      "grad_norm": 1.0072320699691772,
+      "learning_rate": 4.3881278538812785e-05,
+      "loss": 0.7578,
+      "step": 3450
+    },
+    {
+      "epoch": 7.935447338618347,
+      "grad_norm": 0.841740608215332,
+      "learning_rate": 4.159817351598174e-05,
+      "loss": 0.755,
+      "step": 3500
+    },
+    {
+      "epoch": 7.935447338618347,
+      "eval_loss": 0.9030627012252808,
+      "eval_runtime": 218.5627,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3500
+    },
+    {
+      "epoch": 8.049830124575312,
+      "grad_norm": 0.9417058825492859,
+      "learning_rate": 3.9315068493150684e-05,
+      "loss": 0.7419,
+      "step": 3550
+    },
+    {
+      "epoch": 8.163080407701019,
+      "grad_norm": 0.8208181858062744,
+      "learning_rate": 3.703196347031964e-05,
+      "loss": 0.7079,
+      "step": 3600
+    },
+    {
+      "epoch": 8.163080407701019,
+      "eval_loss": 0.9004995226860046,
+      "eval_runtime": 218.599,
+      "eval_samples_per_second": 7.178,
+      "eval_steps_per_second": 0.901,
+      "step": 3600
+    },
+    {
+      "epoch": 8.276330690826727,
+      "grad_norm": 0.8969956040382385,
+      "learning_rate": 3.4748858447488584e-05,
+      "loss": 0.7184,
+      "step": 3650
+    },
+    {
+      "epoch": 8.389580973952436,
+      "grad_norm": 0.9903959631919861,
+      "learning_rate": 3.246575342465754e-05,
+      "loss": 0.6977,
+      "step": 3700
+    },
+    {
+      "epoch": 8.389580973952436,
+      "eval_loss": 0.895404577255249,
+      "eval_runtime": 218.551,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3700
+    },
+    {
+      "epoch": 8.502831257078142,
+      "grad_norm": 0.8987964391708374,
+      "learning_rate": 3.0182648401826487e-05,
+      "loss": 0.6981,
+      "step": 3750
+    },
+    {
+      "epoch": 8.61608154020385,
+      "grad_norm": 0.9351384043693542,
+      "learning_rate": 2.7899543378995436e-05,
+      "loss": 0.6985,
+      "step": 3800
+    },
+    {
+      "epoch": 8.61608154020385,
+      "eval_loss": 0.8867019414901733,
+      "eval_runtime": 218.5395,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3800
+    },
+    {
+      "epoch": 8.729331823329558,
+      "grad_norm": 0.9520925283432007,
+      "learning_rate": 2.5616438356164386e-05,
+      "loss": 0.7041,
+      "step": 3850
+    },
+    {
+      "epoch": 8.842582106455266,
+      "grad_norm": 0.9150193333625793,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.6946,
+      "step": 3900
+    },
+    {
+      "epoch": 8.842582106455266,
+      "eval_loss": 0.8767301440238953,
+      "eval_runtime": 218.4183,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3900
+    },
+    {
+      "epoch": 8.955832389580975,
+      "grad_norm": 0.9718352556228638,
+      "learning_rate": 2.1050228310502286e-05,
+      "loss": 0.6837,
+      "step": 3950
+    },
+    {
+      "epoch": 9.070215175537939,
+      "grad_norm": 0.9025393724441528,
+      "learning_rate": 1.8767123287671235e-05,
+      "loss": 0.6821,
+      "step": 4000
+    },
+    {
+      "epoch": 9.070215175537939,
+      "eval_loss": 0.8735217452049255,
+      "eval_runtime": 218.5455,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 4000
+    },
+    {
+      "epoch": 9.183465458663647,
+      "grad_norm": 0.9804911017417908,
+      "learning_rate": 1.6484018264840185e-05,
+      "loss": 0.6533,
+      "step": 4050
+    },
+    {
+      "epoch": 9.296715741789354,
+      "grad_norm": 0.8889093399047852,
+      "learning_rate": 1.4200913242009135e-05,
+      "loss": 0.6549,
+      "step": 4100
+    },
+    {
+      "epoch": 9.296715741789354,
+      "eval_loss": 0.8693042993545532,
+      "eval_runtime": 218.4928,
+      "eval_samples_per_second": 7.181,
+      "eval_steps_per_second": 0.902,
+      "step": 4100
+    },
+    {
+      "epoch": 9.409966024915063,
+      "grad_norm": 0.9306142926216125,
+      "learning_rate": 1.1917808219178083e-05,
+      "loss": 0.643,
+      "step": 4150
+    },
+    {
+      "epoch": 9.52321630804077,
+      "grad_norm": 1.0180792808532715,
+      "learning_rate": 9.634703196347032e-06,
+      "loss": 0.6498,
+      "step": 4200
+    },
+    {
+      "epoch": 9.52321630804077,
+      "eval_loss": 0.8649076223373413,
+      "eval_runtime": 218.6148,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.901,
+      "step": 4200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4410,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1264290217984e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e998421db5fda141692eec9c9e597100acac3199364228e123959379525e09ed
+size 6161

checkpoint-4300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+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-4300/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8795f2034a6168c166f9982c8d3159b813490f0668aa404d2dd4652999dbd19a
+size 40422168

checkpoint-4300/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-4300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee6d3ed35198afddca44c02c3289e3ee6d5ab0496ee70b79a80562d885cc7e3
+size 21979091

checkpoint-4300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532826bfd6ab0d9c120628c9ba8dbb5c027e661038baccc2d23e0946927a6e4b
+size 14645

checkpoint-4300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b77bb946ed44eb6ecccc838f29d11ac7bdbf77de8b5138f44cbff526a9c81a4
+size 1383

checkpoint-4300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ef7efe1670c68497f5b5d4837fbc34f151e7f0b13d3b368644fa5501dd9580
+size 1465

checkpoint-4300/special_tokens_map.json

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

checkpoint-4300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
+size 11422753

checkpoint-4300/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- set message = messages[index] %}\n    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}\n    {%- set tool_start = '<tool_response>' %}\n    {%- set tool_start_length = tool_start|length %}\n    {%- set start_of_message = current_content[:tool_start_length] %}\n    {%- set tool_end = '</tool_response>' %}\n    {%- set tool_end_length = tool_end|length %}\n    {%- set start_pos = (current_content|length) - tool_end_length %}\n    {%- if start_pos < 0 %}\n        {%- set start_pos = 0 %}\n    {%- endif %}\n    {%- set end_of_message = current_content[start_pos:] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}\n        {%- set content = m_content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in m_content %}\n                {%- set content = (m_content.split('</think>')|last).lstrip('\\n') %}\n                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\\n') %}\n                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-4300/trainer_state.json

@@ -0,0 +1,980 @@
+{
+  "best_global_step": 4300,
+  "best_metric": 0.8624854683876038,
+  "best_model_checkpoint": "Qwen-3-0.6B-it-Medical-LoRA/checkpoint-4300",
+  "epoch": 9.749716874292186,
+  "eval_steps": 100,
+  "global_step": 4300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11325028312570781,
+      "grad_norm": 0.3080866038799286,
+      "learning_rate": 0.00019075425790754258,
+      "loss": 1.8711,
+      "step": 50
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "grad_norm": 0.28974413871765137,
+      "learning_rate": 0.0001664233576642336,
+      "loss": 1.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "eval_loss": 1.3033037185668945,
+      "eval_runtime": 217.1489,
+      "eval_samples_per_second": 7.225,
+      "eval_steps_per_second": 0.907,
+      "step": 100
+    },
+    {
+      "epoch": 0.33975084937712347,
+      "grad_norm": 0.3371483385562897,
+      "learning_rate": 0.0001420924574209246,
+      "loss": 1.2923,
+      "step": 150
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "grad_norm": 0.35730767250061035,
+      "learning_rate": 0.00011776155717761557,
+      "loss": 1.2703,
+      "step": 200
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "eval_loss": 1.2490053176879883,
+      "eval_runtime": 217.4793,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 200
+    },
+    {
+      "epoch": 0.5662514156285391,
+      "grad_norm": 0.35110780596733093,
+      "learning_rate": 9.343065693430657e-05,
+      "loss": 1.2397,
+      "step": 250
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "grad_norm": 0.35077276825904846,
+      "learning_rate": 6.909975669099758e-05,
+      "loss": 1.232,
+      "step": 300
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "eval_loss": 1.2211977243423462,
+      "eval_runtime": 217.5364,
+      "eval_samples_per_second": 7.213,
+      "eval_steps_per_second": 0.906,
+      "step": 300
+    },
+    {
+      "epoch": 0.7927519818799547,
+      "grad_norm": 0.3939191699028015,
+      "learning_rate": 4.476885644768857e-05,
+      "loss": 1.2241,
+      "step": 350
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "grad_norm": 0.366871178150177,
+      "learning_rate": 2.0437956204379563e-05,
+      "loss": 1.2078,
+      "step": 400
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "eval_loss": 1.2062289714813232,
+      "eval_runtime": 217.4838,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 400
+    },
+    {
+      "epoch": 1.0203850509626273,
+      "grad_norm": 0.3808969259262085,
+      "learning_rate": 0.00010164319248826291,
+      "loss": 1.1819,
+      "step": 450
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "grad_norm": 0.43216949701309204,
+      "learning_rate": 8.990610328638498e-05,
+      "loss": 1.19,
+      "step": 500
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "eval_loss": 1.1994948387145996,
+      "eval_runtime": 217.3626,
+      "eval_samples_per_second": 7.218,
+      "eval_steps_per_second": 0.906,
+      "step": 500
+    },
+    {
+      "epoch": 1.246885617214043,
+      "grad_norm": 0.4280295968055725,
+      "learning_rate": 7.816901408450704e-05,
+      "loss": 1.1971,
+      "step": 550
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "grad_norm": 0.4056779146194458,
+      "learning_rate": 6.643192488262912e-05,
+      "loss": 1.1771,
+      "step": 600
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "eval_loss": 1.1834282875061035,
+      "eval_runtime": 217.4514,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 0.906,
+      "step": 600
+    },
+    {
+      "epoch": 1.4733861834654587,
+      "grad_norm": 0.4397243857383728,
+      "learning_rate": 5.469483568075118e-05,
+      "loss": 1.1544,
+      "step": 650
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "grad_norm": 0.4214654862880707,
+      "learning_rate": 4.295774647887324e-05,
+      "loss": 1.1789,
+      "step": 700
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "eval_loss": 1.1712530851364136,
+      "eval_runtime": 217.6023,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.905,
+      "step": 700
+    },
+    {
+      "epoch": 1.6998867497168741,
+      "grad_norm": 0.43076109886169434,
+      "learning_rate": 3.1220657276995305e-05,
+      "loss": 1.1522,
+      "step": 750
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "grad_norm": 0.4253358244895935,
+      "learning_rate": 1.9483568075117372e-05,
+      "loss": 1.1508,
+      "step": 800
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "eval_loss": 1.1622345447540283,
+      "eval_runtime": 217.3951,
+      "eval_samples_per_second": 7.217,
+      "eval_steps_per_second": 0.906,
+      "step": 800
+    },
+    {
+      "epoch": 1.9263873159682898,
+      "grad_norm": 0.4359077215194702,
+      "learning_rate": 7.746478873239436e-06,
+      "loss": 1.1422,
+      "step": 850
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "grad_norm": 0.4511992633342743,
+      "learning_rate": 0.00014314687602224403,
+      "loss": 1.149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "eval_loss": 1.167581558227539,
+      "eval_runtime": 218.6888,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 0.901,
+      "step": 900
+    },
+    {
+      "epoch": 2.1540203850509627,
+      "grad_norm": 0.47519659996032715,
+      "learning_rate": 0.00013987569512594048,
+      "loss": 1.1498,
+      "step": 950
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "grad_norm": 0.4559363126754761,
+      "learning_rate": 0.00013660451422963692,
+      "loss": 1.1469,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "eval_loss": 1.1536333560943604,
+      "eval_runtime": 218.921,
+      "eval_samples_per_second": 7.167,
+      "eval_steps_per_second": 0.9,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3805209513023784,
+      "grad_norm": 0.49805569648742676,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.123,
+      "step": 1050
+    },
+    {
+      "epoch": 2.493771234428086,
+      "grad_norm": 0.4767671823501587,
+      "learning_rate": 0.00013006215243702978,
+      "loss": 1.1119,
+      "step": 1100
+    },
+    {
+      "epoch": 2.493771234428086,
+      "eval_loss": 1.1321617364883423,
+      "eval_runtime": 218.8468,
+      "eval_samples_per_second": 7.169,
+      "eval_steps_per_second": 0.9,
+      "step": 1100
+    },
+    {
+      "epoch": 2.607021517553794,
+      "grad_norm": 0.4313490688800812,
+      "learning_rate": 0.0001267909715407262,
+      "loss": 1.1096,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "grad_norm": 0.46401792764663696,
+      "learning_rate": 0.00012351979064442265,
+      "loss": 1.0929,
+      "step": 1200
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "eval_loss": 1.1138092279434204,
+      "eval_runtime": 219.2403,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8335220838052093,
+      "grad_norm": 0.46533071994781494,
+      "learning_rate": 0.00012024860974811907,
+      "loss": 1.0894,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "grad_norm": 0.42782357335090637,
+      "learning_rate": 0.00011697742885181551,
+      "loss": 1.072,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "eval_loss": 1.0986168384552002,
+      "eval_runtime": 219.0662,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 1300
+    },
+    {
+      "epoch": 3.061155152887882,
+      "grad_norm": 0.46029889583587646,
+      "learning_rate": 0.00011370624795551194,
+      "loss": 1.0936,
+      "step": 1350
+    },
+    {
+      "epoch": 3.17440543601359,
+      "grad_norm": 0.5067735314369202,
+      "learning_rate": 0.00011043506705920839,
+      "loss": 1.0304,
+      "step": 1400
+    },
+    {
+      "epoch": 3.17440543601359,
+      "eval_loss": 1.0839864015579224,
+      "eval_runtime": 219.2396,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1400
+    },
+    {
+      "epoch": 3.287655719139298,
+      "grad_norm": 0.46760454773902893,
+      "learning_rate": 0.0001071638861629048,
+      "loss": 1.0361,
+      "step": 1450
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "grad_norm": 0.5199077129364014,
+      "learning_rate": 0.00010389270526660124,
+      "loss": 1.0304,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "eval_loss": 1.070657730102539,
+      "eval_runtime": 219.1222,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1500
+    },
+    {
+      "epoch": 3.5141562853907136,
+      "grad_norm": 0.496124267578125,
+      "learning_rate": 0.00010062152437029768,
+      "loss": 1.0202,
+      "step": 1550
+    },
+    {
+      "epoch": 3.627406568516421,
+      "grad_norm": 0.5154497623443604,
+      "learning_rate": 9.735034347399413e-05,
+      "loss": 1.007,
+      "step": 1600
+    },
+    {
+      "epoch": 3.627406568516421,
+      "eval_loss": 1.0554137229919434,
+      "eval_runtime": 219.2648,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.898,
+      "step": 1600
+    },
+    {
+      "epoch": 3.7406568516421292,
+      "grad_norm": 0.4881006181240082,
+      "learning_rate": 9.407916257769055e-05,
+      "loss": 0.9934,
+      "step": 1650
+    },
+    {
+      "epoch": 3.853907134767837,
+      "grad_norm": 0.5507743954658508,
+      "learning_rate": 9.080798168138699e-05,
+      "loss": 0.9894,
+      "step": 1700
+    },
+    {
+      "epoch": 3.853907134767837,
+      "eval_loss": 1.0418345928192139,
+      "eval_runtime": 219.154,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 1700
+    },
+    {
+      "epoch": 3.967157417893545,
+      "grad_norm": 0.5333808064460754,
+      "learning_rate": 8.753680078508342e-05,
+      "loss": 0.9795,
+      "step": 1750
+    },
+    {
+      "epoch": 4.081540203850509,
+      "grad_norm": 0.551164448261261,
+      "learning_rate": 8.426561988877985e-05,
+      "loss": 0.974,
+      "step": 1800
+    },
+    {
+      "epoch": 4.081540203850509,
+      "eval_loss": 1.0327671766281128,
+      "eval_runtime": 219.1392,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1800
+    },
+    {
+      "epoch": 4.194790486976218,
+      "grad_norm": 0.5678717494010925,
+      "learning_rate": 8.099443899247629e-05,
+      "loss": 0.9204,
+      "step": 1850
+    },
+    {
+      "epoch": 4.308040770101925,
+      "grad_norm": 0.5472707152366638,
+      "learning_rate": 7.772325809617273e-05,
+      "loss": 0.9341,
+      "step": 1900
+    },
+    {
+      "epoch": 4.308040770101925,
+      "eval_loss": 1.0188047885894775,
+      "eval_runtime": 219.1338,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1900
+    },
+    {
+      "epoch": 4.421291053227633,
+      "grad_norm": 0.5799363255500793,
+      "learning_rate": 7.445207719986915e-05,
+      "loss": 0.9313,
+      "step": 1950
+    },
+    {
+      "epoch": 4.534541336353341,
+      "grad_norm": 0.6046631336212158,
+      "learning_rate": 7.11808963035656e-05,
+      "loss": 0.9325,
+      "step": 2000
+    },
+    {
+      "epoch": 4.534541336353341,
+      "eval_loss": 1.004631519317627,
+      "eval_runtime": 219.1114,
+      "eval_samples_per_second": 7.161,
+      "eval_steps_per_second": 0.899,
+      "step": 2000
+    },
+    {
+      "epoch": 4.647791619479049,
+      "grad_norm": 0.5897740721702576,
+      "learning_rate": 6.790971540726203e-05,
+      "loss": 0.9213,
+      "step": 2050
+    },
+    {
+      "epoch": 4.761041902604757,
+      "grad_norm": 0.583991289138794,
+      "learning_rate": 6.463853451095846e-05,
+      "loss": 0.9039,
+      "step": 2100
+    },
+    {
+      "epoch": 4.761041902604757,
+      "eval_loss": 0.9938989877700806,
+      "eval_runtime": 219.0293,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 2100
+    },
+    {
+      "epoch": 4.874292185730464,
+      "grad_norm": 0.6264305710792542,
+      "learning_rate": 6.13673536146549e-05,
+      "loss": 0.9028,
+      "step": 2150
+    },
+    {
+      "epoch": 4.987542468856172,
+      "grad_norm": 0.6474761962890625,
+      "learning_rate": 5.809617271835133e-05,
+      "loss": 0.9053,
+      "step": 2200
+    },
+    {
+      "epoch": 4.987542468856172,
+      "eval_loss": 0.9845430254936218,
+      "eval_runtime": 219.2502,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.899,
+      "step": 2200
+    },
+    {
+      "epoch": 5.101925254813137,
+      "grad_norm": 0.6595875024795532,
+      "learning_rate": 5.4824991822047765e-05,
+      "loss": 0.882,
+      "step": 2250
+    },
+    {
+      "epoch": 5.215175537938845,
+      "grad_norm": 0.6405232548713684,
+      "learning_rate": 5.15538109257442e-05,
+      "loss": 0.8471,
+      "step": 2300
+    },
+    {
+      "epoch": 5.215175537938845,
+      "eval_loss": 0.9782047867774963,
+      "eval_runtime": 219.0751,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2300
+    },
+    {
+      "epoch": 5.3284258210645525,
+      "grad_norm": 0.6547350287437439,
+      "learning_rate": 4.828263002944063e-05,
+      "loss": 0.8602,
+      "step": 2350
+    },
+    {
+      "epoch": 5.44167610419026,
+      "grad_norm": 0.7046269178390503,
+      "learning_rate": 4.501144913313706e-05,
+      "loss": 0.8404,
+      "step": 2400
+    },
+    {
+      "epoch": 5.44167610419026,
+      "eval_loss": 0.9688066244125366,
+      "eval_runtime": 219.0622,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2400
+    },
+    {
+      "epoch": 5.554926387315969,
+      "grad_norm": 0.6331756114959717,
+      "learning_rate": 4.17402682368335e-05,
+      "loss": 0.8286,
+      "step": 2450
+    },
+    {
+      "epoch": 5.668176670441676,
+      "grad_norm": 0.7212900519371033,
+      "learning_rate": 3.846908734052994e-05,
+      "loss": 0.8382,
+      "step": 2500
+    },
+    {
+      "epoch": 5.668176670441676,
+      "eval_loss": 0.9589976668357849,
+      "eval_runtime": 219.1257,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2500
+    },
+    {
+      "epoch": 5.781426953567384,
+      "grad_norm": 0.6771254539489746,
+      "learning_rate": 3.519790644422637e-05,
+      "loss": 0.8359,
+      "step": 2550
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "grad_norm": 0.7171376943588257,
+      "learning_rate": 3.19267255479228e-05,
+      "loss": 0.832,
+      "step": 2600
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "eval_loss": 0.9501948952674866,
+      "eval_runtime": 219.0768,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2600
+    },
+    {
+      "epoch": 6.009060022650057,
+      "grad_norm": 0.6734739542007446,
+      "learning_rate": 2.865554465161924e-05,
+      "loss": 0.8437,
+      "step": 2650
+    },
+    {
+      "epoch": 6.122310305775764,
+      "grad_norm": 0.697407603263855,
+      "learning_rate": 2.538436375531567e-05,
+      "loss": 0.7937,
+      "step": 2700
+    },
+    {
+      "epoch": 6.122310305775764,
+      "eval_loss": 0.9480313658714294,
+      "eval_runtime": 218.949,
+      "eval_samples_per_second": 7.166,
+      "eval_steps_per_second": 0.9,
+      "step": 2700
+    },
+    {
+      "epoch": 6.235560588901472,
+      "grad_norm": 0.7092292904853821,
+      "learning_rate": 2.2113182859012105e-05,
+      "loss": 0.7804,
+      "step": 2750
+    },
+    {
+      "epoch": 6.34881087202718,
+      "grad_norm": 0.7284964919090271,
+      "learning_rate": 1.884200196270854e-05,
+      "loss": 0.7861,
+      "step": 2800
+    },
+    {
+      "epoch": 6.34881087202718,
+      "eval_loss": 0.942541241645813,
+      "eval_runtime": 219.1707,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 2800
+    },
+    {
+      "epoch": 6.462061155152888,
+      "grad_norm": 0.7725135087966919,
+      "learning_rate": 1.557082106640497e-05,
+      "loss": 0.776,
+      "step": 2850
+    },
+    {
+      "epoch": 6.575311438278596,
+      "grad_norm": 0.7266800403594971,
+      "learning_rate": 1.2299640170101408e-05,
+      "loss": 0.7812,
+      "step": 2900
+    },
+    {
+      "epoch": 6.575311438278596,
+      "eval_loss": 0.939509928226471,
+      "eval_runtime": 219.1206,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2900
+    },
+    {
+      "epoch": 6.688561721404303,
+      "grad_norm": 0.7308298349380493,
+      "learning_rate": 9.028459273797842e-06,
+      "loss": 0.7827,
+      "step": 2950
+    },
+    {
+      "epoch": 6.801812004530011,
+      "grad_norm": 0.7362912893295288,
+      "learning_rate": 5.757278377494276e-06,
+      "loss": 0.7917,
+      "step": 3000
+    },
+    {
+      "epoch": 6.801812004530011,
+      "eval_loss": 0.9356247782707214,
+      "eval_runtime": 219.052,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 3000
+    },
+    {
+      "epoch": 6.9150622876557195,
+      "grad_norm": 0.7543765902519226,
+      "learning_rate": 2.4860974811907098e-06,
+      "loss": 0.7738,
+      "step": 3050
+    },
+    {
+      "epoch": 7.029445073612684,
+      "grad_norm": 0.7134389877319336,
+      "learning_rate": 5.986301369863014e-05,
+      "loss": 0.7481,
+      "step": 3100
+    },
+    {
+      "epoch": 7.029445073612684,
+      "eval_loss": 0.9381225109100342,
+      "eval_runtime": 218.2269,
+      "eval_samples_per_second": 7.19,
+      "eval_steps_per_second": 0.903,
+      "step": 3100
+    },
+    {
+      "epoch": 7.1426953567383915,
+      "grad_norm": 0.8131405711174011,
+      "learning_rate": 5.757990867579909e-05,
+      "loss": 0.7725,
+      "step": 3150
+    },
+    {
+      "epoch": 7.2559456398641,
+      "grad_norm": 0.8759368062019348,
+      "learning_rate": 5.529680365296805e-05,
+      "loss": 0.7752,
+      "step": 3200
+    },
+    {
+      "epoch": 7.2559456398641,
+      "eval_loss": 0.9386877417564392,
+      "eval_runtime": 218.4203,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3200
+    },
+    {
+      "epoch": 7.369195922989808,
+      "grad_norm": 0.8374108076095581,
+      "learning_rate": 5.3013698630136986e-05,
+      "loss": 0.7765,
+      "step": 3250
+    },
+    {
+      "epoch": 7.482446206115515,
+      "grad_norm": 0.8505973815917969,
+      "learning_rate": 5.0730593607305946e-05,
+      "loss": 0.7791,
+      "step": 3300
+    },
+    {
+      "epoch": 7.482446206115515,
+      "eval_loss": 0.9266760349273682,
+      "eval_runtime": 218.4773,
+      "eval_samples_per_second": 7.182,
+      "eval_steps_per_second": 0.902,
+      "step": 3300
+    },
+    {
+      "epoch": 7.595696489241223,
+      "grad_norm": 0.8420349359512329,
+      "learning_rate": 4.8447488584474886e-05,
+      "loss": 0.7721,
+      "step": 3350
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "grad_norm": 0.892084002494812,
+      "learning_rate": 4.616438356164384e-05,
+      "loss": 0.7626,
+      "step": 3400
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "eval_loss": 0.9153051376342773,
+      "eval_runtime": 218.391,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 0.902,
+      "step": 3400
+    },
+    {
+      "epoch": 7.822197055492639,
+      "grad_norm": 1.0072320699691772,
+      "learning_rate": 4.3881278538812785e-05,
+      "loss": 0.7578,
+      "step": 3450
+    },
+    {
+      "epoch": 7.935447338618347,
+      "grad_norm": 0.841740608215332,
+      "learning_rate": 4.159817351598174e-05,
+      "loss": 0.755,
+      "step": 3500
+    },
+    {
+      "epoch": 7.935447338618347,
+      "eval_loss": 0.9030627012252808,
+      "eval_runtime": 218.5627,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3500
+    },
+    {
+      "epoch": 8.049830124575312,
+      "grad_norm": 0.9417058825492859,
+      "learning_rate": 3.9315068493150684e-05,
+      "loss": 0.7419,
+      "step": 3550
+    },
+    {
+      "epoch": 8.163080407701019,
+      "grad_norm": 0.8208181858062744,
+      "learning_rate": 3.703196347031964e-05,
+      "loss": 0.7079,
+      "step": 3600
+    },
+    {
+      "epoch": 8.163080407701019,
+      "eval_loss": 0.9004995226860046,
+      "eval_runtime": 218.599,
+      "eval_samples_per_second": 7.178,
+      "eval_steps_per_second": 0.901,
+      "step": 3600
+    },
+    {
+      "epoch": 8.276330690826727,
+      "grad_norm": 0.8969956040382385,
+      "learning_rate": 3.4748858447488584e-05,
+      "loss": 0.7184,
+      "step": 3650
+    },
+    {
+      "epoch": 8.389580973952436,
+      "grad_norm": 0.9903959631919861,
+      "learning_rate": 3.246575342465754e-05,
+      "loss": 0.6977,
+      "step": 3700
+    },
+    {
+      "epoch": 8.389580973952436,
+      "eval_loss": 0.895404577255249,
+      "eval_runtime": 218.551,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3700
+    },
+    {
+      "epoch": 8.502831257078142,
+      "grad_norm": 0.8987964391708374,
+      "learning_rate": 3.0182648401826487e-05,
+      "loss": 0.6981,
+      "step": 3750
+    },
+    {
+      "epoch": 8.61608154020385,
+      "grad_norm": 0.9351384043693542,
+      "learning_rate": 2.7899543378995436e-05,
+      "loss": 0.6985,
+      "step": 3800
+    },
+    {
+      "epoch": 8.61608154020385,
+      "eval_loss": 0.8867019414901733,
+      "eval_runtime": 218.5395,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3800
+    },
+    {
+      "epoch": 8.729331823329558,
+      "grad_norm": 0.9520925283432007,
+      "learning_rate": 2.5616438356164386e-05,
+      "loss": 0.7041,
+      "step": 3850
+    },
+    {
+      "epoch": 8.842582106455266,
+      "grad_norm": 0.9150193333625793,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.6946,
+      "step": 3900
+    },
+    {
+      "epoch": 8.842582106455266,
+      "eval_loss": 0.8767301440238953,
+      "eval_runtime": 218.4183,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3900
+    },
+    {
+      "epoch": 8.955832389580975,
+      "grad_norm": 0.9718352556228638,
+      "learning_rate": 2.1050228310502286e-05,
+      "loss": 0.6837,
+      "step": 3950
+    },
+    {
+      "epoch": 9.070215175537939,
+      "grad_norm": 0.9025393724441528,
+      "learning_rate": 1.8767123287671235e-05,
+      "loss": 0.6821,
+      "step": 4000
+    },
+    {
+      "epoch": 9.070215175537939,
+      "eval_loss": 0.8735217452049255,
+      "eval_runtime": 218.5455,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 4000
+    },
+    {
+      "epoch": 9.183465458663647,
+      "grad_norm": 0.9804911017417908,
+      "learning_rate": 1.6484018264840185e-05,
+      "loss": 0.6533,
+      "step": 4050
+    },
+    {
+      "epoch": 9.296715741789354,
+      "grad_norm": 0.8889093399047852,
+      "learning_rate": 1.4200913242009135e-05,
+      "loss": 0.6549,
+      "step": 4100
+    },
+    {
+      "epoch": 9.296715741789354,
+      "eval_loss": 0.8693042993545532,
+      "eval_runtime": 218.4928,
+      "eval_samples_per_second": 7.181,
+      "eval_steps_per_second": 0.902,
+      "step": 4100
+    },
+    {
+      "epoch": 9.409966024915063,
+      "grad_norm": 0.9306142926216125,
+      "learning_rate": 1.1917808219178083e-05,
+      "loss": 0.643,
+      "step": 4150
+    },
+    {
+      "epoch": 9.52321630804077,
+      "grad_norm": 1.0180792808532715,
+      "learning_rate": 9.634703196347032e-06,
+      "loss": 0.6498,
+      "step": 4200
+    },
+    {
+      "epoch": 9.52321630804077,
+      "eval_loss": 0.8649076223373413,
+      "eval_runtime": 218.6148,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.901,
+      "step": 4200
+    },
+    {
+      "epoch": 9.636466591166478,
+      "grad_norm": 1.038870930671692,
+      "learning_rate": 7.351598173515982e-06,
+      "loss": 0.6633,
+      "step": 4250
+    },
+    {
+      "epoch": 9.749716874292186,
+      "grad_norm": 0.9064520001411438,
+      "learning_rate": 5.068493150684932e-06,
+      "loss": 0.6503,
+      "step": 4300
+    },
+    {
+      "epoch": 9.749716874292186,
+      "eval_loss": 0.8624854683876038,
+      "eval_runtime": 218.607,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.901,
+      "step": 4300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4410,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.177033109504e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e998421db5fda141692eec9c9e597100acac3199364228e123959379525e09ed
+size 6161

checkpoint-4400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+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-4400/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c97974ece4e8227ac60156c3d79495726f59fc34707b450a2577af64da68b5
+size 40422168

checkpoint-4400/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-4400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f697d4b7a1e261d24cb9eadb5b3ab14b3eedd963f19a05822d7b5f4bf9dc5d
+size 21979091

checkpoint-4400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1bc75e2fb0afb4cdce6286143bee936f37febf68cc744d52dbaaafbfa7bcf7
+size 14645

checkpoint-4400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa01c0faab1a39c11ceba075e1e73b81a5689cfd1ac0d27ee7fece150d320be6
+size 1383

checkpoint-4400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aceee74b8becaf878df00125a7c4a8aa25c0878cc5261eb748e0732302bc81f9
+size 1465

checkpoint-4400/special_tokens_map.json

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

checkpoint-4400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
+size 11422753

checkpoint-4400/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- set message = messages[index] %}\n    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}\n    {%- set tool_start = '<tool_response>' %}\n    {%- set tool_start_length = tool_start|length %}\n    {%- set start_of_message = current_content[:tool_start_length] %}\n    {%- set tool_end = '</tool_response>' %}\n    {%- set tool_end_length = tool_end|length %}\n    {%- set start_pos = (current_content|length) - tool_end_length %}\n    {%- if start_pos < 0 %}\n        {%- set start_pos = 0 %}\n    {%- endif %}\n    {%- set end_of_message = current_content[start_pos:] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}\n        {%- set content = m_content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in m_content %}\n                {%- set content = (m_content.split('</think>')|last).lstrip('\\n') %}\n                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\\n') %}\n                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-4400/trainer_state.json

@@ -0,0 +1,1002 @@
+{
+  "best_global_step": 4400,
+  "best_metric": 0.8610817790031433,
+  "best_model_checkpoint": "Qwen-3-0.6B-it-Medical-LoRA/checkpoint-4400",
+  "epoch": 9.976217440543602,
+  "eval_steps": 100,
+  "global_step": 4400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11325028312570781,
+      "grad_norm": 0.3080866038799286,
+      "learning_rate": 0.00019075425790754258,
+      "loss": 1.8711,
+      "step": 50
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "grad_norm": 0.28974413871765137,
+      "learning_rate": 0.0001664233576642336,
+      "loss": 1.338,
+      "step": 100
+    },
+    {
+      "epoch": 0.22650056625141562,
+      "eval_loss": 1.3033037185668945,
+      "eval_runtime": 217.1489,
+      "eval_samples_per_second": 7.225,
+      "eval_steps_per_second": 0.907,
+      "step": 100
+    },
+    {
+      "epoch": 0.33975084937712347,
+      "grad_norm": 0.3371483385562897,
+      "learning_rate": 0.0001420924574209246,
+      "loss": 1.2923,
+      "step": 150
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "grad_norm": 0.35730767250061035,
+      "learning_rate": 0.00011776155717761557,
+      "loss": 1.2703,
+      "step": 200
+    },
+    {
+      "epoch": 0.45300113250283125,
+      "eval_loss": 1.2490053176879883,
+      "eval_runtime": 217.4793,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 200
+    },
+    {
+      "epoch": 0.5662514156285391,
+      "grad_norm": 0.35110780596733093,
+      "learning_rate": 9.343065693430657e-05,
+      "loss": 1.2397,
+      "step": 250
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "grad_norm": 0.35077276825904846,
+      "learning_rate": 6.909975669099758e-05,
+      "loss": 1.232,
+      "step": 300
+    },
+    {
+      "epoch": 0.6795016987542469,
+      "eval_loss": 1.2211977243423462,
+      "eval_runtime": 217.5364,
+      "eval_samples_per_second": 7.213,
+      "eval_steps_per_second": 0.906,
+      "step": 300
+    },
+    {
+      "epoch": 0.7927519818799547,
+      "grad_norm": 0.3939191699028015,
+      "learning_rate": 4.476885644768857e-05,
+      "loss": 1.2241,
+      "step": 350
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "grad_norm": 0.366871178150177,
+      "learning_rate": 2.0437956204379563e-05,
+      "loss": 1.2078,
+      "step": 400
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "eval_loss": 1.2062289714813232,
+      "eval_runtime": 217.4838,
+      "eval_samples_per_second": 7.214,
+      "eval_steps_per_second": 0.906,
+      "step": 400
+    },
+    {
+      "epoch": 1.0203850509626273,
+      "grad_norm": 0.3808969259262085,
+      "learning_rate": 0.00010164319248826291,
+      "loss": 1.1819,
+      "step": 450
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "grad_norm": 0.43216949701309204,
+      "learning_rate": 8.990610328638498e-05,
+      "loss": 1.19,
+      "step": 500
+    },
+    {
+      "epoch": 1.1336353340883352,
+      "eval_loss": 1.1994948387145996,
+      "eval_runtime": 217.3626,
+      "eval_samples_per_second": 7.218,
+      "eval_steps_per_second": 0.906,
+      "step": 500
+    },
+    {
+      "epoch": 1.246885617214043,
+      "grad_norm": 0.4280295968055725,
+      "learning_rate": 7.816901408450704e-05,
+      "loss": 1.1971,
+      "step": 550
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "grad_norm": 0.4056779146194458,
+      "learning_rate": 6.643192488262912e-05,
+      "loss": 1.1771,
+      "step": 600
+    },
+    {
+      "epoch": 1.3601359003397508,
+      "eval_loss": 1.1834282875061035,
+      "eval_runtime": 217.4514,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 0.906,
+      "step": 600
+    },
+    {
+      "epoch": 1.4733861834654587,
+      "grad_norm": 0.4397243857383728,
+      "learning_rate": 5.469483568075118e-05,
+      "loss": 1.1544,
+      "step": 650
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "grad_norm": 0.4214654862880707,
+      "learning_rate": 4.295774647887324e-05,
+      "loss": 1.1789,
+      "step": 700
+    },
+    {
+      "epoch": 1.5866364665911665,
+      "eval_loss": 1.1712530851364136,
+      "eval_runtime": 217.6023,
+      "eval_samples_per_second": 7.21,
+      "eval_steps_per_second": 0.905,
+      "step": 700
+    },
+    {
+      "epoch": 1.6998867497168741,
+      "grad_norm": 0.43076109886169434,
+      "learning_rate": 3.1220657276995305e-05,
+      "loss": 1.1522,
+      "step": 750
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "grad_norm": 0.4253358244895935,
+      "learning_rate": 1.9483568075117372e-05,
+      "loss": 1.1508,
+      "step": 800
+    },
+    {
+      "epoch": 1.8131370328425822,
+      "eval_loss": 1.1622345447540283,
+      "eval_runtime": 217.3951,
+      "eval_samples_per_second": 7.217,
+      "eval_steps_per_second": 0.906,
+      "step": 800
+    },
+    {
+      "epoch": 1.9263873159682898,
+      "grad_norm": 0.4359077215194702,
+      "learning_rate": 7.746478873239436e-06,
+      "loss": 1.1422,
+      "step": 850
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "grad_norm": 0.4511992633342743,
+      "learning_rate": 0.00014314687602224403,
+      "loss": 1.149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0407701019252547,
+      "eval_loss": 1.167581558227539,
+      "eval_runtime": 218.6888,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 0.901,
+      "step": 900
+    },
+    {
+      "epoch": 2.1540203850509627,
+      "grad_norm": 0.47519659996032715,
+      "learning_rate": 0.00013987569512594048,
+      "loss": 1.1498,
+      "step": 950
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "grad_norm": 0.4559363126754761,
+      "learning_rate": 0.00013660451422963692,
+      "loss": 1.1469,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2672706681766703,
+      "eval_loss": 1.1536333560943604,
+      "eval_runtime": 218.921,
+      "eval_samples_per_second": 7.167,
+      "eval_steps_per_second": 0.9,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3805209513023784,
+      "grad_norm": 0.49805569648742676,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.123,
+      "step": 1050
+    },
+    {
+      "epoch": 2.493771234428086,
+      "grad_norm": 0.4767671823501587,
+      "learning_rate": 0.00013006215243702978,
+      "loss": 1.1119,
+      "step": 1100
+    },
+    {
+      "epoch": 2.493771234428086,
+      "eval_loss": 1.1321617364883423,
+      "eval_runtime": 218.8468,
+      "eval_samples_per_second": 7.169,
+      "eval_steps_per_second": 0.9,
+      "step": 1100
+    },
+    {
+      "epoch": 2.607021517553794,
+      "grad_norm": 0.4313490688800812,
+      "learning_rate": 0.0001267909715407262,
+      "loss": 1.1096,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "grad_norm": 0.46401792764663696,
+      "learning_rate": 0.00012351979064442265,
+      "loss": 1.0929,
+      "step": 1200
+    },
+    {
+      "epoch": 2.7202718006795017,
+      "eval_loss": 1.1138092279434204,
+      "eval_runtime": 219.2403,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8335220838052093,
+      "grad_norm": 0.46533071994781494,
+      "learning_rate": 0.00012024860974811907,
+      "loss": 1.0894,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "grad_norm": 0.42782357335090637,
+      "learning_rate": 0.00011697742885181551,
+      "loss": 1.072,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9467723669309174,
+      "eval_loss": 1.0986168384552002,
+      "eval_runtime": 219.0662,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 1300
+    },
+    {
+      "epoch": 3.061155152887882,
+      "grad_norm": 0.46029889583587646,
+      "learning_rate": 0.00011370624795551194,
+      "loss": 1.0936,
+      "step": 1350
+    },
+    {
+      "epoch": 3.17440543601359,
+      "grad_norm": 0.5067735314369202,
+      "learning_rate": 0.00011043506705920839,
+      "loss": 1.0304,
+      "step": 1400
+    },
+    {
+      "epoch": 3.17440543601359,
+      "eval_loss": 1.0839864015579224,
+      "eval_runtime": 219.2396,
+      "eval_samples_per_second": 7.157,
+      "eval_steps_per_second": 0.899,
+      "step": 1400
+    },
+    {
+      "epoch": 3.287655719139298,
+      "grad_norm": 0.46760454773902893,
+      "learning_rate": 0.0001071638861629048,
+      "loss": 1.0361,
+      "step": 1450
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "grad_norm": 0.5199077129364014,
+      "learning_rate": 0.00010389270526660124,
+      "loss": 1.0304,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4009060022650055,
+      "eval_loss": 1.070657730102539,
+      "eval_runtime": 219.1222,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1500
+    },
+    {
+      "epoch": 3.5141562853907136,
+      "grad_norm": 0.496124267578125,
+      "learning_rate": 0.00010062152437029768,
+      "loss": 1.0202,
+      "step": 1550
+    },
+    {
+      "epoch": 3.627406568516421,
+      "grad_norm": 0.5154497623443604,
+      "learning_rate": 9.735034347399413e-05,
+      "loss": 1.007,
+      "step": 1600
+    },
+    {
+      "epoch": 3.627406568516421,
+      "eval_loss": 1.0554137229919434,
+      "eval_runtime": 219.2648,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.898,
+      "step": 1600
+    },
+    {
+      "epoch": 3.7406568516421292,
+      "grad_norm": 0.4881006181240082,
+      "learning_rate": 9.407916257769055e-05,
+      "loss": 0.9934,
+      "step": 1650
+    },
+    {
+      "epoch": 3.853907134767837,
+      "grad_norm": 0.5507743954658508,
+      "learning_rate": 9.080798168138699e-05,
+      "loss": 0.9894,
+      "step": 1700
+    },
+    {
+      "epoch": 3.853907134767837,
+      "eval_loss": 1.0418345928192139,
+      "eval_runtime": 219.154,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 1700
+    },
+    {
+      "epoch": 3.967157417893545,
+      "grad_norm": 0.5333808064460754,
+      "learning_rate": 8.753680078508342e-05,
+      "loss": 0.9795,
+      "step": 1750
+    },
+    {
+      "epoch": 4.081540203850509,
+      "grad_norm": 0.551164448261261,
+      "learning_rate": 8.426561988877985e-05,
+      "loss": 0.974,
+      "step": 1800
+    },
+    {
+      "epoch": 4.081540203850509,
+      "eval_loss": 1.0327671766281128,
+      "eval_runtime": 219.1392,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1800
+    },
+    {
+      "epoch": 4.194790486976218,
+      "grad_norm": 0.5678717494010925,
+      "learning_rate": 8.099443899247629e-05,
+      "loss": 0.9204,
+      "step": 1850
+    },
+    {
+      "epoch": 4.308040770101925,
+      "grad_norm": 0.5472707152366638,
+      "learning_rate": 7.772325809617273e-05,
+      "loss": 0.9341,
+      "step": 1900
+    },
+    {
+      "epoch": 4.308040770101925,
+      "eval_loss": 1.0188047885894775,
+      "eval_runtime": 219.1338,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 1900
+    },
+    {
+      "epoch": 4.421291053227633,
+      "grad_norm": 0.5799363255500793,
+      "learning_rate": 7.445207719986915e-05,
+      "loss": 0.9313,
+      "step": 1950
+    },
+    {
+      "epoch": 4.534541336353341,
+      "grad_norm": 0.6046631336212158,
+      "learning_rate": 7.11808963035656e-05,
+      "loss": 0.9325,
+      "step": 2000
+    },
+    {
+      "epoch": 4.534541336353341,
+      "eval_loss": 1.004631519317627,
+      "eval_runtime": 219.1114,
+      "eval_samples_per_second": 7.161,
+      "eval_steps_per_second": 0.899,
+      "step": 2000
+    },
+    {
+      "epoch": 4.647791619479049,
+      "grad_norm": 0.5897740721702576,
+      "learning_rate": 6.790971540726203e-05,
+      "loss": 0.9213,
+      "step": 2050
+    },
+    {
+      "epoch": 4.761041902604757,
+      "grad_norm": 0.583991289138794,
+      "learning_rate": 6.463853451095846e-05,
+      "loss": 0.9039,
+      "step": 2100
+    },
+    {
+      "epoch": 4.761041902604757,
+      "eval_loss": 0.9938989877700806,
+      "eval_runtime": 219.0293,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 2100
+    },
+    {
+      "epoch": 4.874292185730464,
+      "grad_norm": 0.6264305710792542,
+      "learning_rate": 6.13673536146549e-05,
+      "loss": 0.9028,
+      "step": 2150
+    },
+    {
+      "epoch": 4.987542468856172,
+      "grad_norm": 0.6474761962890625,
+      "learning_rate": 5.809617271835133e-05,
+      "loss": 0.9053,
+      "step": 2200
+    },
+    {
+      "epoch": 4.987542468856172,
+      "eval_loss": 0.9845430254936218,
+      "eval_runtime": 219.2502,
+      "eval_samples_per_second": 7.156,
+      "eval_steps_per_second": 0.899,
+      "step": 2200
+    },
+    {
+      "epoch": 5.101925254813137,
+      "grad_norm": 0.6595875024795532,
+      "learning_rate": 5.4824991822047765e-05,
+      "loss": 0.882,
+      "step": 2250
+    },
+    {
+      "epoch": 5.215175537938845,
+      "grad_norm": 0.6405232548713684,
+      "learning_rate": 5.15538109257442e-05,
+      "loss": 0.8471,
+      "step": 2300
+    },
+    {
+      "epoch": 5.215175537938845,
+      "eval_loss": 0.9782047867774963,
+      "eval_runtime": 219.0751,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2300
+    },
+    {
+      "epoch": 5.3284258210645525,
+      "grad_norm": 0.6547350287437439,
+      "learning_rate": 4.828263002944063e-05,
+      "loss": 0.8602,
+      "step": 2350
+    },
+    {
+      "epoch": 5.44167610419026,
+      "grad_norm": 0.7046269178390503,
+      "learning_rate": 4.501144913313706e-05,
+      "loss": 0.8404,
+      "step": 2400
+    },
+    {
+      "epoch": 5.44167610419026,
+      "eval_loss": 0.9688066244125366,
+      "eval_runtime": 219.0622,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2400
+    },
+    {
+      "epoch": 5.554926387315969,
+      "grad_norm": 0.6331756114959717,
+      "learning_rate": 4.17402682368335e-05,
+      "loss": 0.8286,
+      "step": 2450
+    },
+    {
+      "epoch": 5.668176670441676,
+      "grad_norm": 0.7212900519371033,
+      "learning_rate": 3.846908734052994e-05,
+      "loss": 0.8382,
+      "step": 2500
+    },
+    {
+      "epoch": 5.668176670441676,
+      "eval_loss": 0.9589976668357849,
+      "eval_runtime": 219.1257,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2500
+    },
+    {
+      "epoch": 5.781426953567384,
+      "grad_norm": 0.6771254539489746,
+      "learning_rate": 3.519790644422637e-05,
+      "loss": 0.8359,
+      "step": 2550
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "grad_norm": 0.7171376943588257,
+      "learning_rate": 3.19267255479228e-05,
+      "loss": 0.832,
+      "step": 2600
+    },
+    {
+      "epoch": 5.8946772366930915,
+      "eval_loss": 0.9501948952674866,
+      "eval_runtime": 219.0768,
+      "eval_samples_per_second": 7.162,
+      "eval_steps_per_second": 0.899,
+      "step": 2600
+    },
+    {
+      "epoch": 6.009060022650057,
+      "grad_norm": 0.6734739542007446,
+      "learning_rate": 2.865554465161924e-05,
+      "loss": 0.8437,
+      "step": 2650
+    },
+    {
+      "epoch": 6.122310305775764,
+      "grad_norm": 0.697407603263855,
+      "learning_rate": 2.538436375531567e-05,
+      "loss": 0.7937,
+      "step": 2700
+    },
+    {
+      "epoch": 6.122310305775764,
+      "eval_loss": 0.9480313658714294,
+      "eval_runtime": 218.949,
+      "eval_samples_per_second": 7.166,
+      "eval_steps_per_second": 0.9,
+      "step": 2700
+    },
+    {
+      "epoch": 6.235560588901472,
+      "grad_norm": 0.7092292904853821,
+      "learning_rate": 2.2113182859012105e-05,
+      "loss": 0.7804,
+      "step": 2750
+    },
+    {
+      "epoch": 6.34881087202718,
+      "grad_norm": 0.7284964919090271,
+      "learning_rate": 1.884200196270854e-05,
+      "loss": 0.7861,
+      "step": 2800
+    },
+    {
+      "epoch": 6.34881087202718,
+      "eval_loss": 0.942541241645813,
+      "eval_runtime": 219.1707,
+      "eval_samples_per_second": 7.159,
+      "eval_steps_per_second": 0.899,
+      "step": 2800
+    },
+    {
+      "epoch": 6.462061155152888,
+      "grad_norm": 0.7725135087966919,
+      "learning_rate": 1.557082106640497e-05,
+      "loss": 0.776,
+      "step": 2850
+    },
+    {
+      "epoch": 6.575311438278596,
+      "grad_norm": 0.7266800403594971,
+      "learning_rate": 1.2299640170101408e-05,
+      "loss": 0.7812,
+      "step": 2900
+    },
+    {
+      "epoch": 6.575311438278596,
+      "eval_loss": 0.939509928226471,
+      "eval_runtime": 219.1206,
+      "eval_samples_per_second": 7.16,
+      "eval_steps_per_second": 0.899,
+      "step": 2900
+    },
+    {
+      "epoch": 6.688561721404303,
+      "grad_norm": 0.7308298349380493,
+      "learning_rate": 9.028459273797842e-06,
+      "loss": 0.7827,
+      "step": 2950
+    },
+    {
+      "epoch": 6.801812004530011,
+      "grad_norm": 0.7362912893295288,
+      "learning_rate": 5.757278377494276e-06,
+      "loss": 0.7917,
+      "step": 3000
+    },
+    {
+      "epoch": 6.801812004530011,
+      "eval_loss": 0.9356247782707214,
+      "eval_runtime": 219.052,
+      "eval_samples_per_second": 7.163,
+      "eval_steps_per_second": 0.899,
+      "step": 3000
+    },
+    {
+      "epoch": 6.9150622876557195,
+      "grad_norm": 0.7543765902519226,
+      "learning_rate": 2.4860974811907098e-06,
+      "loss": 0.7738,
+      "step": 3050
+    },
+    {
+      "epoch": 7.029445073612684,
+      "grad_norm": 0.7134389877319336,
+      "learning_rate": 5.986301369863014e-05,
+      "loss": 0.7481,
+      "step": 3100
+    },
+    {
+      "epoch": 7.029445073612684,
+      "eval_loss": 0.9381225109100342,
+      "eval_runtime": 218.2269,
+      "eval_samples_per_second": 7.19,
+      "eval_steps_per_second": 0.903,
+      "step": 3100
+    },
+    {
+      "epoch": 7.1426953567383915,
+      "grad_norm": 0.8131405711174011,
+      "learning_rate": 5.757990867579909e-05,
+      "loss": 0.7725,
+      "step": 3150
+    },
+    {
+      "epoch": 7.2559456398641,
+      "grad_norm": 0.8759368062019348,
+      "learning_rate": 5.529680365296805e-05,
+      "loss": 0.7752,
+      "step": 3200
+    },
+    {
+      "epoch": 7.2559456398641,
+      "eval_loss": 0.9386877417564392,
+      "eval_runtime": 218.4203,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3200
+    },
+    {
+      "epoch": 7.369195922989808,
+      "grad_norm": 0.8374108076095581,
+      "learning_rate": 5.3013698630136986e-05,
+      "loss": 0.7765,
+      "step": 3250
+    },
+    {
+      "epoch": 7.482446206115515,
+      "grad_norm": 0.8505973815917969,
+      "learning_rate": 5.0730593607305946e-05,
+      "loss": 0.7791,
+      "step": 3300
+    },
+    {
+      "epoch": 7.482446206115515,
+      "eval_loss": 0.9266760349273682,
+      "eval_runtime": 218.4773,
+      "eval_samples_per_second": 7.182,
+      "eval_steps_per_second": 0.902,
+      "step": 3300
+    },
+    {
+      "epoch": 7.595696489241223,
+      "grad_norm": 0.8420349359512329,
+      "learning_rate": 4.8447488584474886e-05,
+      "loss": 0.7721,
+      "step": 3350
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "grad_norm": 0.892084002494812,
+      "learning_rate": 4.616438356164384e-05,
+      "loss": 0.7626,
+      "step": 3400
+    },
+    {
+      "epoch": 7.7089467723669305,
+      "eval_loss": 0.9153051376342773,
+      "eval_runtime": 218.391,
+      "eval_samples_per_second": 7.184,
+      "eval_steps_per_second": 0.902,
+      "step": 3400
+    },
+    {
+      "epoch": 7.822197055492639,
+      "grad_norm": 1.0072320699691772,
+      "learning_rate": 4.3881278538812785e-05,
+      "loss": 0.7578,
+      "step": 3450
+    },
+    {
+      "epoch": 7.935447338618347,
+      "grad_norm": 0.841740608215332,
+      "learning_rate": 4.159817351598174e-05,
+      "loss": 0.755,
+      "step": 3500
+    },
+    {
+      "epoch": 7.935447338618347,
+      "eval_loss": 0.9030627012252808,
+      "eval_runtime": 218.5627,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3500
+    },
+    {
+      "epoch": 8.049830124575312,
+      "grad_norm": 0.9417058825492859,
+      "learning_rate": 3.9315068493150684e-05,
+      "loss": 0.7419,
+      "step": 3550
+    },
+    {
+      "epoch": 8.163080407701019,
+      "grad_norm": 0.8208181858062744,
+      "learning_rate": 3.703196347031964e-05,
+      "loss": 0.7079,
+      "step": 3600
+    },
+    {
+      "epoch": 8.163080407701019,
+      "eval_loss": 0.9004995226860046,
+      "eval_runtime": 218.599,
+      "eval_samples_per_second": 7.178,
+      "eval_steps_per_second": 0.901,
+      "step": 3600
+    },
+    {
+      "epoch": 8.276330690826727,
+      "grad_norm": 0.8969956040382385,
+      "learning_rate": 3.4748858447488584e-05,
+      "loss": 0.7184,
+      "step": 3650
+    },
+    {
+      "epoch": 8.389580973952436,
+      "grad_norm": 0.9903959631919861,
+      "learning_rate": 3.246575342465754e-05,
+      "loss": 0.6977,
+      "step": 3700
+    },
+    {
+      "epoch": 8.389580973952436,
+      "eval_loss": 0.895404577255249,
+      "eval_runtime": 218.551,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3700
+    },
+    {
+      "epoch": 8.502831257078142,
+      "grad_norm": 0.8987964391708374,
+      "learning_rate": 3.0182648401826487e-05,
+      "loss": 0.6981,
+      "step": 3750
+    },
+    {
+      "epoch": 8.61608154020385,
+      "grad_norm": 0.9351384043693542,
+      "learning_rate": 2.7899543378995436e-05,
+      "loss": 0.6985,
+      "step": 3800
+    },
+    {
+      "epoch": 8.61608154020385,
+      "eval_loss": 0.8867019414901733,
+      "eval_runtime": 218.5395,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 3800
+    },
+    {
+      "epoch": 8.729331823329558,
+      "grad_norm": 0.9520925283432007,
+      "learning_rate": 2.5616438356164386e-05,
+      "loss": 0.7041,
+      "step": 3850
+    },
+    {
+      "epoch": 8.842582106455266,
+      "grad_norm": 0.9150193333625793,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.6946,
+      "step": 3900
+    },
+    {
+      "epoch": 8.842582106455266,
+      "eval_loss": 0.8767301440238953,
+      "eval_runtime": 218.4183,
+      "eval_samples_per_second": 7.183,
+      "eval_steps_per_second": 0.902,
+      "step": 3900
+    },
+    {
+      "epoch": 8.955832389580975,
+      "grad_norm": 0.9718352556228638,
+      "learning_rate": 2.1050228310502286e-05,
+      "loss": 0.6837,
+      "step": 3950
+    },
+    {
+      "epoch": 9.070215175537939,
+      "grad_norm": 0.9025393724441528,
+      "learning_rate": 1.8767123287671235e-05,
+      "loss": 0.6821,
+      "step": 4000
+    },
+    {
+      "epoch": 9.070215175537939,
+      "eval_loss": 0.8735217452049255,
+      "eval_runtime": 218.5455,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.901,
+      "step": 4000
+    },
+    {
+      "epoch": 9.183465458663647,
+      "grad_norm": 0.9804911017417908,
+      "learning_rate": 1.6484018264840185e-05,
+      "loss": 0.6533,
+      "step": 4050
+    },
+    {
+      "epoch": 9.296715741789354,
+      "grad_norm": 0.8889093399047852,
+      "learning_rate": 1.4200913242009135e-05,
+      "loss": 0.6549,
+      "step": 4100
+    },
+    {
+      "epoch": 9.296715741789354,
+      "eval_loss": 0.8693042993545532,
+      "eval_runtime": 218.4928,
+      "eval_samples_per_second": 7.181,
+      "eval_steps_per_second": 0.902,
+      "step": 4100
+    },
+    {
+      "epoch": 9.409966024915063,
+      "grad_norm": 0.9306142926216125,
+      "learning_rate": 1.1917808219178083e-05,
+      "loss": 0.643,
+      "step": 4150
+    },
+    {
+      "epoch": 9.52321630804077,
+      "grad_norm": 1.0180792808532715,
+      "learning_rate": 9.634703196347032e-06,
+      "loss": 0.6498,
+      "step": 4200
+    },
+    {
+      "epoch": 9.52321630804077,
+      "eval_loss": 0.8649076223373413,
+      "eval_runtime": 218.6148,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.901,
+      "step": 4200
+    },
+    {
+      "epoch": 9.636466591166478,
+      "grad_norm": 1.038870930671692,
+      "learning_rate": 7.351598173515982e-06,
+      "loss": 0.6633,
+      "step": 4250
+    },
+    {
+      "epoch": 9.749716874292186,
+      "grad_norm": 0.9064520001411438,
+      "learning_rate": 5.068493150684932e-06,
+      "loss": 0.6503,
+      "step": 4300
+    },
+    {
+      "epoch": 9.749716874292186,
+      "eval_loss": 0.8624854683876038,
+      "eval_runtime": 218.607,
+      "eval_samples_per_second": 7.177,
+      "eval_steps_per_second": 0.901,
+      "step": 4300
+    },
+    {
+      "epoch": 9.862967157417893,
+      "grad_norm": 0.9673233032226562,
+      "learning_rate": 2.7853881278538815e-06,
+      "loss": 0.6439,
+      "step": 4350
+    },
+    {
+      "epoch": 9.976217440543602,
+      "grad_norm": 0.9512138366699219,
+      "learning_rate": 5.022831050228311e-07,
+      "loss": 0.6427,
+      "step": 4400
+    },
+    {
+      "epoch": 9.976217440543602,
+      "eval_loss": 0.8610817790031433,
+      "eval_runtime": 218.4692,
+      "eval_samples_per_second": 7.182,
+      "eval_steps_per_second": 0.902,
+      "step": 4400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4410,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2268623060992e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e998421db5fda141692eec9c9e597100acac3199364228e123959379525e09ed
+size 6161

checkpoint-4410/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+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-4410/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4410/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66831d119e2993c301b568560185fbc36137845ac54889a561a801b295a025b
+size 40422168