Upload folder using huggingface_hub

.gitattributes

@@ -50,3 +50,6 @@ model/Qwen3-0.6B_finetuned_20250729_172802/tokenizer.json filter=lfs diff=lfs me
 model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_173318/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_173318/merged_16bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_173318/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+library_name: peft
+model_name: Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505
+tags:
+- base_model:adapter:unsloth/qwen3-0.6b-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505
+
+This model is a fine-tuned version of [unsloth/qwen3-0.6b-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-0.6b-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.20.0
+- Transformers: 4.54.1
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9249a5268b71c34e69d1aef84b785a6dd139543d978129242907120ff0354b
+size 40422168

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/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
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-0.6b-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9249a5268b71c34e69d1aef84b785a6dd139543d978129242907120ff0354b
+size 40422168

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/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
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d346ff8c72df2c9b31ce9d0bf1682a7964995603557d9902e9c79cf6d964b320
+size 20958981

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716d83e48b4ef0ecc739db256420344d8764b568cd2fec53ea128d8653e43804
+size 14645

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88a70f83ca592a7838eb4a3d66823c7f6c02bdad677beb6fe30c7ece2333715
+size 1465

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/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
+  }
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/tokenizer.json

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

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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,
+  "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
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0415541242468315,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00041554124246831497,
+      "grad_norm": 28.64969253540039,
+      "learning_rate": 0.0,
+      "loss": 5.6148,
+      "step": 1
+    },
+    {
+      "epoch": 0.0008310824849366299,
+      "grad_norm": 28.64969253540039,
+      "learning_rate": 4e-05,
+      "loss": 5.6148,
+      "step": 2
+    },
+    {
+      "epoch": 0.001246623727404945,
+      "grad_norm": 18.797611236572266,
+      "learning_rate": 8e-05,
+      "loss": 4.9314,
+      "step": 3
+    },
+    {
+      "epoch": 0.0016621649698732599,
+      "grad_norm": 8.891189575195312,
+      "learning_rate": 0.00012,
+      "loss": 4.1451,
+      "step": 4
+    },
+    {
+      "epoch": 0.002077706212341575,
+      "grad_norm": 7.788501739501953,
+      "learning_rate": 0.00016,
+      "loss": 3.5155,
+      "step": 5
+    },
+    {
+      "epoch": 0.00249324745480989,
+      "grad_norm": 7.208379745483398,
+      "learning_rate": 0.0002,
+      "loss": 2.8816,
+      "step": 6
+    },
+    {
+      "epoch": 0.002908788697278205,
+      "grad_norm": 7.199682235717773,
+      "learning_rate": 0.00019789473684210526,
+      "loss": 2.1359,
+      "step": 7
+    },
+    {
+      "epoch": 0.0033243299397465197,
+      "grad_norm": 6.998970031738281,
+      "learning_rate": 0.00019578947368421054,
+      "loss": 1.4612,
+      "step": 8
+    },
+    {
+      "epoch": 0.003739871182214835,
+      "grad_norm": 8.041845321655273,
+      "learning_rate": 0.0001936842105263158,
+      "loss": 0.956,
+      "step": 9
+    },
+    {
+      "epoch": 0.00415541242468315,
+      "grad_norm": 4.127288818359375,
+      "learning_rate": 0.00019157894736842104,
+      "loss": 0.662,
+      "step": 10
+    },
+    {
+      "epoch": 0.004570953667151465,
+      "grad_norm": 3.5372495651245117,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 0.4934,
+      "step": 11
+    },
+    {
+      "epoch": 0.00498649490961978,
+      "grad_norm": 3.451491117477417,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.3537,
+      "step": 12
+    },
+    {
+      "epoch": 0.0054020361520880945,
+      "grad_norm": 3.89812970161438,
+      "learning_rate": 0.00018526315789473685,
+      "loss": 0.1965,
+      "step": 13
+    },
+    {
+      "epoch": 0.00581757739455641,
+      "grad_norm": 4.1324238777160645,
+      "learning_rate": 0.0001831578947368421,
+      "loss": 0.0503,
+      "step": 14
+    },
+    {
+      "epoch": 0.006233118637024725,
+      "grad_norm": 2.4459030628204346,
+      "learning_rate": 0.00018105263157894739,
+      "loss": 0.0262,
+      "step": 15
+    },
+    {
+      "epoch": 0.0066486598794930395,
+      "grad_norm": 0.5439086556434631,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 0.0128,
+      "step": 16
+    },
+    {
+      "epoch": 0.007064201121961355,
+      "grad_norm": 0.40072309970855713,
+      "learning_rate": 0.0001768421052631579,
+      "loss": 0.0084,
+      "step": 17
+    },
+    {
+      "epoch": 0.00747974236442967,
+      "grad_norm": 0.14579936861991882,
+      "learning_rate": 0.00017473684210526317,
+      "loss": 0.004,
+      "step": 18
+    },
+    {
+      "epoch": 0.007895283606897984,
+      "grad_norm": 0.10983546078205109,
+      "learning_rate": 0.00017263157894736842,
+      "loss": 0.0026,
+      "step": 19
+    },
+    {
+      "epoch": 0.0083108248493663,
+      "grad_norm": 0.06975521892309189,
+      "learning_rate": 0.0001705263157894737,
+      "loss": 0.0018,
+      "step": 20
+    },
+    {
+      "epoch": 0.008726366091834614,
+      "grad_norm": 0.05262838304042816,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 0.0014,
+      "step": 21
+    },
+    {
+      "epoch": 0.00914190733430293,
+      "grad_norm": 0.0474303737282753,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.0013,
+      "step": 22
+    },
+    {
+      "epoch": 0.009557448576771245,
+      "grad_norm": 0.0563424751162529,
+      "learning_rate": 0.00016421052631578948,
+      "loss": 0.0013,
+      "step": 23
+    },
+    {
+      "epoch": 0.00997298981923956,
+      "grad_norm": 0.08237738907337189,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 0.0014,
+      "step": 24
+    },
+    {
+      "epoch": 0.010388531061707874,
+      "grad_norm": 0.08790373057126999,
+      "learning_rate": 0.00016,
+      "loss": 0.0014,
+      "step": 25
+    },
+    {
+      "epoch": 0.010804072304176189,
+      "grad_norm": 0.0720975324511528,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.0012,
+      "step": 26
+    },
+    {
+      "epoch": 0.011219613546644504,
+      "grad_norm": 0.044871218502521515,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 0.0009,
+      "step": 27
+    },
+    {
+      "epoch": 0.01163515478911282,
+      "grad_norm": 0.030363507568836212,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 0.0007,
+      "step": 28
+    },
+    {
+      "epoch": 0.012050696031581135,
+      "grad_norm": 0.022570375353097916,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.01246623727404945,
+      "grad_norm": 0.01790735498070717,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 0.0004,
+      "step": 30
+    },
+    {
+      "epoch": 0.012881778516517764,
+      "grad_norm": 0.014839502982795238,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 0.0004,
+      "step": 31
+    },
+    {
+      "epoch": 0.013297319758986079,
+      "grad_norm": 0.01251253206282854,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.013712861001454394,
+      "grad_norm": 0.010710136964917183,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.01412840224392271,
+      "grad_norm": 0.009633295238018036,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 0.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.014543943486391025,
+      "grad_norm": 0.008616195060312748,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.01495948472885934,
+      "grad_norm": 0.007750109303742647,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.015375025971327654,
+      "grad_norm": 0.006997754797339439,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.01579056721379597,
+      "grad_norm": 0.006447326857596636,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 0.0002,
+      "step": 38
+    },
+    {
+      "epoch": 0.016206108456264284,
+      "grad_norm": 0.00599507475271821,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.0166216496987326,
+      "grad_norm": 0.005462392698973417,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.017037190941200913,
+      "grad_norm": 0.005158347077667713,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.017452732183669228,
+      "grad_norm": 0.0048068431206047535,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.017868273426137546,
+      "grad_norm": 0.004522533621639013,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.01828381466860586,
+      "grad_norm": 0.004196793306618929,
+      "learning_rate": 0.00012,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.018699355911074175,
+      "grad_norm": 0.003982214257121086,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.01911489715354249,
+      "grad_norm": 0.003827708540484309,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.019530438396010805,
+      "grad_norm": 0.0036355017218738794,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.01994597963847912,
+      "grad_norm": 0.003501433879137039,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.020361520880947434,
+      "grad_norm": 0.003282280405983329,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 0.0001,
+      "step": 49
+    },
+    {
+      "epoch": 0.02077706212341575,
+      "grad_norm": 0.0031591353472322226,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.021192603365884063,
+      "grad_norm": 0.0030282808002084494,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.0001,
+      "step": 51
+    },
+    {
+      "epoch": 0.021608144608352378,
+      "grad_norm": 0.0029747660737484694,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.0001,
+      "step": 52
+    },
+    {
+      "epoch": 0.022023685850820693,
+      "grad_norm": 0.0028304217848926783,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 0.0001,
+      "step": 53
+    },
+    {
+      "epoch": 0.022439227093289008,
+      "grad_norm": 0.002745267003774643,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 0.0001,
+      "step": 54
+    },
+    {
+      "epoch": 0.022854768335757322,
+      "grad_norm": 0.002690468681976199,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 0.0001,
+      "step": 55
+    },
+    {
+      "epoch": 0.02327030957822564,
+      "grad_norm": 0.0026687898207455873,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.0001,
+      "step": 56
+    },
+    {
+      "epoch": 0.023685850820693955,
+      "grad_norm": 0.0025552893057465553,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 0.0001,
+      "step": 57
+    },
+    {
+      "epoch": 0.02410139206316227,
+      "grad_norm": 0.002527459291741252,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 0.0001,
+      "step": 58
+    },
+    {
+      "epoch": 0.024516933305630585,
+      "grad_norm": 0.0024460742715746164,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 0.0001,
+      "step": 59
+    },
+    {
+      "epoch": 0.0249324745480989,
+      "grad_norm": 0.0023703533224761486,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 0.0001,
+      "step": 60
+    },
+    {
+      "epoch": 0.025348015790567214,
+      "grad_norm": 0.0023257662542164326,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 0.0001,
+      "step": 61
+    },
+    {
+      "epoch": 0.02576355703303553,
+      "grad_norm": 0.0023002061061561108,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.0001,
+      "step": 62
+    },
+    {
+      "epoch": 0.026179098275503843,
+      "grad_norm": 0.0022338293492794037,
+      "learning_rate": 8e-05,
+      "loss": 0.0001,
+      "step": 63
+    },
+    {
+      "epoch": 0.026594639517972158,
+      "grad_norm": 0.002179167466238141,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.0001,
+      "step": 64
+    },
+    {
+      "epoch": 0.027010180760440473,
+      "grad_norm": 0.0021637778263539076,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.0001,
+      "step": 65
+    },
+    {
+      "epoch": 0.027425722002908787,
+      "grad_norm": 0.002151819644495845,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.0001,
+      "step": 66
+    },
+    {
+      "epoch": 0.027841263245377102,
+      "grad_norm": 0.0020999617408961058,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 0.0001,
+      "step": 67
+    },
+    {
+      "epoch": 0.02825680448784542,
+      "grad_norm": 0.002028311137109995,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 0.0001,
+      "step": 68
+    },
+    {
+      "epoch": 0.028672345730313735,
+      "grad_norm": 0.0020358797628432512,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 0.0001,
+      "step": 69
+    },
+    {
+      "epoch": 0.02908788697278205,
+      "grad_norm": 0.0020396795589476824,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 0.029503428215250364,
+      "grad_norm": 0.00197698175907135,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.0001,
+      "step": 71
+    },
+    {
+      "epoch": 0.02991896945771868,
+      "grad_norm": 0.0019586223643273115,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.0001,
+      "step": 72
+    },
+    {
+      "epoch": 0.030334510700186994,
+      "grad_norm": 0.0019408479565754533,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 0.0001,
+      "step": 73
+    },
+    {
+      "epoch": 0.03075005194265531,
+      "grad_norm": 0.0019137656781822443,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 0.0001,
+      "step": 74
+    },
+    {
+      "epoch": 0.031165593185123623,
+      "grad_norm": 0.001903255470097065,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.0001,
+      "step": 75
+    },
+    {
+      "epoch": 0.03158113442759194,
+      "grad_norm": 0.001851561013609171,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 0.0001,
+      "step": 76
+    },
+    {
+      "epoch": 0.03199667567006025,
+      "grad_norm": 0.001875043148174882,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 0.0001,
+      "step": 77
+    },
+    {
+      "epoch": 0.03241221691252857,
+      "grad_norm": 0.0018571719992905855,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 0.0001,
+      "step": 78
+    },
+    {
+      "epoch": 0.03282775815499688,
+      "grad_norm": 0.001821806887164712,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 0.0001,
+      "step": 79
+    },
+    {
+      "epoch": 0.0332432993974652,
+      "grad_norm": 0.001805800013244152,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 0.0001,
+      "step": 80
+    },
+    {
+      "epoch": 0.03365884063993351,
+      "grad_norm": 0.0018191809067502618,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.0001,
+      "step": 81
+    },
+    {
+      "epoch": 0.034074381882401826,
+      "grad_norm": 0.0018027713522315025,
+      "learning_rate": 4e-05,
+      "loss": 0.0001,
+      "step": 82
+    },
+    {
+      "epoch": 0.03448992312487014,
+      "grad_norm": 0.001802858547307551,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 0.0001,
+      "step": 83
+    },
+    {
+      "epoch": 0.034905464367338455,
+      "grad_norm": 0.0017742045456543565,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 0.0001,
+      "step": 84
+    },
+    {
+      "epoch": 0.03532100560980677,
+      "grad_norm": 0.0017400867072865367,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.03573654685227509,
+      "grad_norm": 0.0017318513710051775,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.036152088094743406,
+      "grad_norm": 0.0017047242727130651,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.03656762933721172,
+      "grad_norm": 0.0017478257650509477,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.036983170579680036,
+      "grad_norm": 0.0017005882691591978,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.03739871182214835,
+      "grad_norm": 0.0017056586220860481,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.037814253064616665,
+      "grad_norm": 0.0017013821052387357,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.03822979430708498,
+      "grad_norm": 0.0016793196555227041,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.038645335549553295,
+      "grad_norm": 0.0017003455432131886,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.03906087679202161,
+      "grad_norm": 0.0016800183802843094,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.039476418034489924,
+      "grad_norm": 0.0016582480166107416,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.03989195927695824,
+      "grad_norm": 0.00167914351914078,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.04030750051942655,
+      "grad_norm": 0.0016734959790483117,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.04072304176189487,
+      "grad_norm": 0.0016593442996963859,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.04113858300436318,
+      "grad_norm": 0.0016803013859316707,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.0415541242468315,
+      "grad_norm": 0.0016863644123077393,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 54067200000000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164a19f9afe68f209da99d3c25cd07bc4773f02bc23165a1068c7edef727ab20
+size 6225

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/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
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/chat_template.jinja

@@ -0,0 +1,99 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/config.json

@@ -0,0 +1,62 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 40960,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float16",
+    "transformers_version": "4.54.1",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.7.11",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 40960,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.54.1"
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e847c855ba4bdbee8474a60ddafa1cf4527bd974c71c341c4f9604a830872bc2
+size 1192134848

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/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
+  }
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/tokenizer.json

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

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/merged_16bit/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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,
+  "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
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/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
+  }
+}

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/tokenizer.json

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

model/Qwen3_0_6B_OpenMathReasoning_finetuned_20250729_180505/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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,
+  "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
+}