Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1638/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+model_name: km_full_model
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for km_full_model
+
+This model is a fine-tuned version of [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B).
+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 0.18.1
+- TRL: 0.24.0
+- Transformers: 5.2.0
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## 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}}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae7c6d0daab67837abb33f93468f20937e3666d8f09a8ea2decd15b8e7c76ab
+size 84972248

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- 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 0.18.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b767baac65782780ee33853bf9be44bf627a24033838b00082417abd536180
+size 84972248

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf457645153c16cc8c9e1ece00490c651f215adf22ed1062cf0554c765f7352b
+size 43434405

checkpoint-1000/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75b69f57bec77f6eb803b4451664f594e6da317e27b8e1452ada7d5843e7e09
+size 1465

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.832263978001833,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01833180568285976,
+      "grad_norm": 0.6833510994911194,
+      "learning_rate": 0.00018,
+      "loss": 1.8247451782226562,
+      "step": 10
+    },
+    {
+      "epoch": 0.03666361136571952,
+      "grad_norm": 0.9012069702148438,
+      "learning_rate": 0.0001988943488943489,
+      "loss": 1.4739965438842773,
+      "step": 20
+    },
+    {
+      "epoch": 0.054995417048579284,
+      "grad_norm": 0.8267062306404114,
+      "learning_rate": 0.00019766584766584767,
+      "loss": 1.3358205795288085,
+      "step": 30
+    },
+    {
+      "epoch": 0.07332722273143905,
+      "grad_norm": 0.7565646767616272,
+      "learning_rate": 0.00019643734643734644,
+      "loss": 1.2644735336303712,
+      "step": 40
+    },
+    {
+      "epoch": 0.09165902841429881,
+      "grad_norm": 0.8591431975364685,
+      "learning_rate": 0.0001952088452088452,
+      "loss": 1.244968318939209,
+      "step": 50
+    },
+    {
+      "epoch": 0.10999083409715857,
+      "grad_norm": 0.8081830143928528,
+      "learning_rate": 0.000193980343980344,
+      "loss": 1.209956455230713,
+      "step": 60
+    },
+    {
+      "epoch": 0.12832263978001834,
+      "grad_norm": 0.8808525800704956,
+      "learning_rate": 0.00019275184275184277,
+      "loss": 1.1500988960266114,
+      "step": 70
+    },
+    {
+      "epoch": 0.1466544454628781,
+      "grad_norm": 0.82117760181427,
+      "learning_rate": 0.00019152334152334154,
+      "loss": 1.1469905853271485,
+      "step": 80
+    },
+    {
+      "epoch": 0.16498625114573787,
+      "grad_norm": 0.8583332896232605,
+      "learning_rate": 0.0001902948402948403,
+      "loss": 1.1948189735412598,
+      "step": 90
+    },
+    {
+      "epoch": 0.18331805682859761,
+      "grad_norm": 0.6712405681610107,
+      "learning_rate": 0.00018906633906633907,
+      "loss": 1.1391284942626954,
+      "step": 100
+    },
+    {
+      "epoch": 0.2016498625114574,
+      "grad_norm": 0.8613548874855042,
+      "learning_rate": 0.00018783783783783784,
+      "loss": 1.1040291786193848,
+      "step": 110
+    },
+    {
+      "epoch": 0.21998166819431714,
+      "grad_norm": 0.8608964085578918,
+      "learning_rate": 0.0001866093366093366,
+      "loss": 1.1578070640563964,
+      "step": 120
+    },
+    {
+      "epoch": 0.2383134738771769,
+      "grad_norm": 0.8638626337051392,
+      "learning_rate": 0.0001853808353808354,
+      "loss": 1.1500712394714356,
+      "step": 130
+    },
+    {
+      "epoch": 0.2566452795600367,
+      "grad_norm": 0.8131710886955261,
+      "learning_rate": 0.00018415233415233417,
+      "loss": 1.0960933685302734,
+      "step": 140
+    },
+    {
+      "epoch": 0.27497708524289644,
+      "grad_norm": 1.023303508758545,
+      "learning_rate": 0.00018292383292383292,
+      "loss": 1.106197452545166,
+      "step": 150
+    },
+    {
+      "epoch": 0.2933088909257562,
+      "grad_norm": 0.7958722114562988,
+      "learning_rate": 0.0001816953316953317,
+      "loss": 1.1257465362548829,
+      "step": 160
+    },
+    {
+      "epoch": 0.31164069660861593,
+      "grad_norm": 0.8529394865036011,
+      "learning_rate": 0.00018046683046683048,
+      "loss": 1.062838077545166,
+      "step": 170
+    },
+    {
+      "epoch": 0.32997250229147573,
+      "grad_norm": 0.8443934917449951,
+      "learning_rate": 0.00017923832923832925,
+      "loss": 1.023012638092041,
+      "step": 180
+    },
+    {
+      "epoch": 0.3483043079743355,
+      "grad_norm": 0.8035740852355957,
+      "learning_rate": 0.00017800982800982802,
+      "loss": 1.0435395240783691,
+      "step": 190
+    },
+    {
+      "epoch": 0.36663611365719523,
+      "grad_norm": 0.8863442540168762,
+      "learning_rate": 0.00017678132678132678,
+      "loss": 1.0918319702148438,
+      "step": 200
+    },
+    {
+      "epoch": 0.384967919340055,
+      "grad_norm": 0.8198781609535217,
+      "learning_rate": 0.00017555282555282555,
+      "loss": 1.0226572036743165,
+      "step": 210
+    },
+    {
+      "epoch": 0.4032997250229148,
+      "grad_norm": 0.9801501035690308,
+      "learning_rate": 0.00017432432432432432,
+      "loss": 1.0847922325134278,
+      "step": 220
+    },
+    {
+      "epoch": 0.4216315307057745,
+      "grad_norm": 0.6737959980964661,
+      "learning_rate": 0.00017309582309582312,
+      "loss": 1.0508249282836915,
+      "step": 230
+    },
+    {
+      "epoch": 0.4399633363886343,
+      "grad_norm": 0.7932195067405701,
+      "learning_rate": 0.00017186732186732188,
+      "loss": 1.042081069946289,
+      "step": 240
+    },
+    {
+      "epoch": 0.458295142071494,
+      "grad_norm": 0.864284873008728,
+      "learning_rate": 0.00017063882063882065,
+      "loss": 1.0485817909240722,
+      "step": 250
+    },
+    {
+      "epoch": 0.4766269477543538,
+      "grad_norm": 0.8705862164497375,
+      "learning_rate": 0.00016941031941031942,
+      "loss": 1.0782199859619142,
+      "step": 260
+    },
+    {
+      "epoch": 0.49495875343721357,
+      "grad_norm": 0.8180854916572571,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 1.075644302368164,
+      "step": 270
+    },
+    {
+      "epoch": 0.5132905591200734,
+      "grad_norm": 0.8689812421798706,
+      "learning_rate": 0.00016695331695331696,
+      "loss": 1.0431486129760743,
+      "step": 280
+    },
+    {
+      "epoch": 0.5316223648029331,
+      "grad_norm": 0.7797616720199585,
+      "learning_rate": 0.00016572481572481573,
+      "loss": 1.019082736968994,
+      "step": 290
+    },
+    {
+      "epoch": 0.5499541704857929,
+      "grad_norm": 0.9403369426727295,
+      "learning_rate": 0.0001644963144963145,
+      "loss": 1.0104355812072754,
+      "step": 300
+    },
+    {
+      "epoch": 0.5682859761686526,
+      "grad_norm": 0.8061522245407104,
+      "learning_rate": 0.0001632678132678133,
+      "loss": 1.015712833404541,
+      "step": 310
+    },
+    {
+      "epoch": 0.5866177818515124,
+      "grad_norm": 1.0389378070831299,
+      "learning_rate": 0.00016203931203931203,
+      "loss": 0.983332347869873,
+      "step": 320
+    },
+    {
+      "epoch": 0.6049495875343721,
+      "grad_norm": 0.8335319757461548,
+      "learning_rate": 0.00016081081081081083,
+      "loss": 1.0035177230834962,
+      "step": 330
+    },
+    {
+      "epoch": 0.6232813932172319,
+      "grad_norm": 0.8039399981498718,
+      "learning_rate": 0.0001595823095823096,
+      "loss": 1.0274381637573242,
+      "step": 340
+    },
+    {
+      "epoch": 0.6416131989000916,
+      "grad_norm": 0.777919352054596,
+      "learning_rate": 0.00015835380835380836,
+      "loss": 1.0467321395874023,
+      "step": 350
+    },
+    {
+      "epoch": 0.6599450045829515,
+      "grad_norm": 0.8876609802246094,
+      "learning_rate": 0.00015712530712530713,
+      "loss": 0.9848588943481446,
+      "step": 360
+    },
+    {
+      "epoch": 0.6782768102658112,
+      "grad_norm": 0.8413349986076355,
+      "learning_rate": 0.0001558968058968059,
+      "loss": 1.0367840766906737,
+      "step": 370
+    },
+    {
+      "epoch": 0.696608615948671,
+      "grad_norm": 0.9921192526817322,
+      "learning_rate": 0.0001546683046683047,
+      "loss": 1.0018555641174316,
+      "step": 380
+    },
+    {
+      "epoch": 0.7149404216315307,
+      "grad_norm": 0.8272864818572998,
+      "learning_rate": 0.00015343980343980344,
+      "loss": 1.0093633651733398,
+      "step": 390
+    },
+    {
+      "epoch": 0.7332722273143905,
+      "grad_norm": 0.7949515581130981,
+      "learning_rate": 0.00015221130221130223,
+      "loss": 1.0220769882202148,
+      "step": 400
+    },
+    {
+      "epoch": 0.7516040329972502,
+      "grad_norm": 0.8337849378585815,
+      "learning_rate": 0.000150982800982801,
+      "loss": 0.9723053932189941,
+      "step": 410
+    },
+    {
+      "epoch": 0.76993583868011,
+      "grad_norm": 0.9521737694740295,
+      "learning_rate": 0.00014975429975429974,
+      "loss": 1.0630863189697266,
+      "step": 420
+    },
+    {
+      "epoch": 0.7882676443629697,
+      "grad_norm": 0.8320823311805725,
+      "learning_rate": 0.00014852579852579854,
+      "loss": 0.9916687965393066,
+      "step": 430
+    },
+    {
+      "epoch": 0.8065994500458296,
+      "grad_norm": 0.903413712978363,
+      "learning_rate": 0.0001472972972972973,
+      "loss": 0.9519875526428223,
+      "step": 440
+    },
+    {
+      "epoch": 0.8249312557286893,
+      "grad_norm": 0.8783673048019409,
+      "learning_rate": 0.00014606879606879607,
+      "loss": 1.0056891441345215,
+      "step": 450
+    },
+    {
+      "epoch": 0.843263061411549,
+      "grad_norm": 0.8581491708755493,
+      "learning_rate": 0.00014484029484029484,
+      "loss": 1.0211298942565918,
+      "step": 460
+    },
+    {
+      "epoch": 0.8615948670944088,
+      "grad_norm": 0.7977339029312134,
+      "learning_rate": 0.0001436117936117936,
+      "loss": 0.9528703689575195,
+      "step": 470
+    },
+    {
+      "epoch": 0.8799266727772685,
+      "grad_norm": 0.8142527937889099,
+      "learning_rate": 0.0001423832923832924,
+      "loss": 1.0111416816711425,
+      "step": 480
+    },
+    {
+      "epoch": 0.8982584784601283,
+      "grad_norm": 0.865929126739502,
+      "learning_rate": 0.00014115479115479115,
+      "loss": 0.978369140625,
+      "step": 490
+    },
+    {
+      "epoch": 0.916590284142988,
+      "grad_norm": 0.7955005764961243,
+      "learning_rate": 0.00013992628992628994,
+      "loss": 0.998965835571289,
+      "step": 500
+    },
+    {
+      "epoch": 0.9349220898258478,
+      "grad_norm": 0.7812423706054688,
+      "learning_rate": 0.0001386977886977887,
+      "loss": 0.9544276237487793,
+      "step": 510
+    },
+    {
+      "epoch": 0.9532538955087076,
+      "grad_norm": 0.817484974861145,
+      "learning_rate": 0.00013746928746928748,
+      "loss": 0.9699355125427246,
+      "step": 520
+    },
+    {
+      "epoch": 0.9715857011915674,
+      "grad_norm": 0.875234842300415,
+      "learning_rate": 0.00013624078624078625,
+      "loss": 0.9715826034545898,
+      "step": 530
+    },
+    {
+      "epoch": 0.9899175068744271,
+      "grad_norm": 0.7700145244598389,
+      "learning_rate": 0.00013501228501228501,
+      "loss": 0.9811925888061523,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073327222731439,
+      "grad_norm": 0.7260869145393372,
+      "learning_rate": 0.0001337837837837838,
+      "loss": 0.882848072052002,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256645279560037,
+      "grad_norm": 0.7263541221618652,
+      "learning_rate": 0.00013255528255528255,
+      "loss": 0.8015734672546386,
+      "step": 560
+    },
+    {
+      "epoch": 1.0439963336388633,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 0.00013132678132678135,
+      "loss": 0.778080940246582,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623281393217232,
+      "grad_norm": 0.8094732165336609,
+      "learning_rate": 0.00013009828009828011,
+      "loss": 0.7774394989013672,
+      "step": 580
+    },
+    {
+      "epoch": 1.0806599450045828,
+      "grad_norm": 0.8383634686470032,
+      "learning_rate": 0.00012886977886977886,
+      "loss": 0.7659544944763184,
+      "step": 590
+    },
+    {
+      "epoch": 1.0989917506874427,
+      "grad_norm": 0.9429551959037781,
+      "learning_rate": 0.00012764127764127765,
+      "loss": 0.7822256565093995,
+      "step": 600
+    },
+    {
+      "epoch": 1.1173235563703026,
+      "grad_norm": 0.8432884812355042,
+      "learning_rate": 0.00012641277641277642,
+      "loss": 0.7877971649169921,
+      "step": 610
+    },
+    {
+      "epoch": 1.1356553620531622,
+      "grad_norm": 0.9461238384246826,
+      "learning_rate": 0.0001251842751842752,
+      "loss": 0.8412753105163574,
+      "step": 620
+    },
+    {
+      "epoch": 1.153987167736022,
+      "grad_norm": 0.9495576620101929,
+      "learning_rate": 0.00012395577395577396,
+      "loss": 0.7389075279235839,
+      "step": 630
+    },
+    {
+      "epoch": 1.1723189734188817,
+      "grad_norm": 0.8137982487678528,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 0.7511651992797852,
+      "step": 640
+    },
+    {
+      "epoch": 1.1906507791017416,
+      "grad_norm": 0.9718158841133118,
+      "learning_rate": 0.00012149877149877152,
+      "loss": 0.7982583999633789,
+      "step": 650
+    },
+    {
+      "epoch": 1.2089825847846012,
+      "grad_norm": 1.0837777853012085,
+      "learning_rate": 0.00012027027027027027,
+      "loss": 0.762714433670044,
+      "step": 660
+    },
+    {
+      "epoch": 1.227314390467461,
+      "grad_norm": 0.9882314801216125,
+      "learning_rate": 0.00011904176904176904,
+      "loss": 0.7749518871307373,
+      "step": 670
+    },
+    {
+      "epoch": 1.2456461961503207,
+      "grad_norm": 0.9463419914245605,
+      "learning_rate": 0.00011781326781326782,
+      "loss": 0.7641645908355713,
+      "step": 680
+    },
+    {
+      "epoch": 1.2639780018331805,
+      "grad_norm": 0.9794511198997498,
+      "learning_rate": 0.00011658476658476658,
+      "loss": 0.8050010681152344,
+      "step": 690
+    },
+    {
+      "epoch": 1.2823098075160404,
+      "grad_norm": 1.1002216339111328,
+      "learning_rate": 0.00011535626535626536,
+      "loss": 0.793759822845459,
+      "step": 700
+    },
+    {
+      "epoch": 1.3006416131989,
+      "grad_norm": 0.9648078083992004,
+      "learning_rate": 0.00011412776412776414,
+      "loss": 0.7668623447418212,
+      "step": 710
+    },
+    {
+      "epoch": 1.31897341888176,
+      "grad_norm": 1.0727074146270752,
+      "learning_rate": 0.00011289926289926291,
+      "loss": 0.8029165267944336,
+      "step": 720
+    },
+    {
+      "epoch": 1.3373052245646195,
+      "grad_norm": 0.9617047905921936,
+      "learning_rate": 0.00011167076167076167,
+      "loss": 0.7798116683959961,
+      "step": 730
+    },
+    {
+      "epoch": 1.3556370302474794,
+      "grad_norm": 0.8710028529167175,
+      "learning_rate": 0.00011044226044226045,
+      "loss": 0.7962553977966309,
+      "step": 740
+    },
+    {
+      "epoch": 1.3739688359303392,
+      "grad_norm": 0.8409777283668518,
+      "learning_rate": 0.00010921375921375923,
+      "loss": 0.7403414726257325,
+      "step": 750
+    },
+    {
+      "epoch": 1.3923006416131989,
+      "grad_norm": 1.029362440109253,
+      "learning_rate": 0.00010798525798525798,
+      "loss": 0.7815125465393067,
+      "step": 760
+    },
+    {
+      "epoch": 1.4106324472960587,
+      "grad_norm": 0.9566736221313477,
+      "learning_rate": 0.00010675675675675677,
+      "loss": 0.7839052200317382,
+      "step": 770
+    },
+    {
+      "epoch": 1.4289642529789184,
+      "grad_norm": 0.975339949131012,
+      "learning_rate": 0.00010552825552825553,
+      "loss": 0.749812650680542,
+      "step": 780
+    },
+    {
+      "epoch": 1.4472960586617782,
+      "grad_norm": 1.1521857976913452,
+      "learning_rate": 0.00010429975429975432,
+      "loss": 0.7797944068908691,
+      "step": 790
+    },
+    {
+      "epoch": 1.4656278643446379,
+      "grad_norm": 0.8301038146018982,
+      "learning_rate": 0.00010307125307125307,
+      "loss": 0.7280281543731689,
+      "step": 800
+    },
+    {
+      "epoch": 1.4839596700274977,
+      "grad_norm": 0.9730615615844727,
+      "learning_rate": 0.00010184275184275185,
+      "loss": 0.7437058448791504,
+      "step": 810
+    },
+    {
+      "epoch": 1.5022914757103574,
+      "grad_norm": 1.0270700454711914,
+      "learning_rate": 0.00010061425061425062,
+      "loss": 0.7848101615905761,
+      "step": 820
+    },
+    {
+      "epoch": 1.5206232813932172,
+      "grad_norm": 1.2335196733474731,
+      "learning_rate": 9.938574938574939e-05,
+      "loss": 0.7896716117858886,
+      "step": 830
+    },
+    {
+      "epoch": 1.538955087076077,
+      "grad_norm": 0.968611478805542,
+      "learning_rate": 9.815724815724816e-05,
+      "loss": 0.7918240070343018,
+      "step": 840
+    },
+    {
+      "epoch": 1.5572868927589367,
+      "grad_norm": 0.9463298320770264,
+      "learning_rate": 9.692874692874694e-05,
+      "loss": 0.7453035354614258,
+      "step": 850
+    },
+    {
+      "epoch": 1.5756186984417964,
+      "grad_norm": 1.004184603691101,
+      "learning_rate": 9.570024570024571e-05,
+      "loss": 0.8125950813293457,
+      "step": 860
+    },
+    {
+      "epoch": 1.5939505041246562,
+      "grad_norm": 1.1150691509246826,
+      "learning_rate": 9.447174447174448e-05,
+      "loss": 0.7995445251464843,
+      "step": 870
+    },
+    {
+      "epoch": 1.612282309807516,
+      "grad_norm": 1.060056447982788,
+      "learning_rate": 9.324324324324324e-05,
+      "loss": 0.7746751785278321,
+      "step": 880
+    },
+    {
+      "epoch": 1.630614115490376,
+      "grad_norm": 1.0525883436203003,
+      "learning_rate": 9.201474201474201e-05,
+      "loss": 0.7861367225646972,
+      "step": 890
+    },
+    {
+      "epoch": 1.6489459211732356,
+      "grad_norm": 0.9495214223861694,
+      "learning_rate": 9.07862407862408e-05,
+      "loss": 0.8055791854858398,
+      "step": 900
+    },
+    {
+      "epoch": 1.6672777268560952,
+      "grad_norm": 0.8876036405563354,
+      "learning_rate": 8.955773955773956e-05,
+      "loss": 0.736152982711792,
+      "step": 910
+    },
+    {
+      "epoch": 1.685609532538955,
+      "grad_norm": 1.0228347778320312,
+      "learning_rate": 8.832923832923833e-05,
+      "loss": 0.7859257698059082,
+      "step": 920
+    },
+    {
+      "epoch": 1.703941338221815,
+      "grad_norm": 1.2196885347366333,
+      "learning_rate": 8.710073710073711e-05,
+      "loss": 0.7442365169525147,
+      "step": 930
+    },
+    {
+      "epoch": 1.7222731439046746,
+      "grad_norm": 1.1201367378234863,
+      "learning_rate": 8.587223587223587e-05,
+      "loss": 0.7933924674987793,
+      "step": 940
+    },
+    {
+      "epoch": 1.7406049495875344,
+      "grad_norm": 1.0457044839859009,
+      "learning_rate": 8.464373464373465e-05,
+      "loss": 0.7594408512115478,
+      "step": 950
+    },
+    {
+      "epoch": 1.758936755270394,
+      "grad_norm": 1.2219468355178833,
+      "learning_rate": 8.341523341523342e-05,
+      "loss": 0.725389051437378,
+      "step": 960
+    },
+    {
+      "epoch": 1.777268560953254,
+      "grad_norm": 1.0098403692245483,
+      "learning_rate": 8.21867321867322e-05,
+      "loss": 0.7753002166748046,
+      "step": 970
+    },
+    {
+      "epoch": 1.7956003666361138,
+      "grad_norm": 1.020544409751892,
+      "learning_rate": 8.095823095823097e-05,
+      "loss": 0.7580110549926757,
+      "step": 980
+    },
+    {
+      "epoch": 1.8139321723189734,
+      "grad_norm": 0.9121679067611694,
+      "learning_rate": 7.972972972972974e-05,
+      "loss": 0.7329069614410401,
+      "step": 990
+    },
+    {
+      "epoch": 1.832263978001833,
+      "grad_norm": 1.1305643320083618,
+      "learning_rate": 7.85012285012285e-05,
+      "loss": 0.7436663150787354,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1638,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.734059628397261e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85e9413c7636d9fff8558d114d2112dff5238aa624b3ebdad9a7bde187c0bf2
+size 5713

checkpoint-1500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- 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 0.18.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2273f4b1d0643882baac5049c9004b1eed74ac50ac2bb70430b06145ac6436a5
+size 84972248

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0264ddc8590e4c498cd75dff8cb9af42a735ebd6211196b5227803b287a2c60
+size 43434405

checkpoint-1500/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0931eefd71a9398394398348a2f58bb240814c4c660a1ff40d26a4b95bd14260
+size 1465

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7479376718606785,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01833180568285976,
+      "grad_norm": 0.6833510994911194,
+      "learning_rate": 0.00018,
+      "loss": 1.8247451782226562,
+      "step": 10
+    },
+    {
+      "epoch": 0.03666361136571952,
+      "grad_norm": 0.9012069702148438,
+      "learning_rate": 0.0001988943488943489,
+      "loss": 1.4739965438842773,
+      "step": 20
+    },
+    {
+      "epoch": 0.054995417048579284,
+      "grad_norm": 0.8267062306404114,
+      "learning_rate": 0.00019766584766584767,
+      "loss": 1.3358205795288085,
+      "step": 30
+    },
+    {
+      "epoch": 0.07332722273143905,
+      "grad_norm": 0.7565646767616272,
+      "learning_rate": 0.00019643734643734644,
+      "loss": 1.2644735336303712,
+      "step": 40
+    },
+    {
+      "epoch": 0.09165902841429881,
+      "grad_norm": 0.8591431975364685,
+      "learning_rate": 0.0001952088452088452,
+      "loss": 1.244968318939209,
+      "step": 50
+    },
+    {
+      "epoch": 0.10999083409715857,
+      "grad_norm": 0.8081830143928528,
+      "learning_rate": 0.000193980343980344,
+      "loss": 1.209956455230713,
+      "step": 60
+    },
+    {
+      "epoch": 0.12832263978001834,
+      "grad_norm": 0.8808525800704956,
+      "learning_rate": 0.00019275184275184277,
+      "loss": 1.1500988960266114,
+      "step": 70
+    },
+    {
+      "epoch": 0.1466544454628781,
+      "grad_norm": 0.82117760181427,
+      "learning_rate": 0.00019152334152334154,
+      "loss": 1.1469905853271485,
+      "step": 80
+    },
+    {
+      "epoch": 0.16498625114573787,
+      "grad_norm": 0.8583332896232605,
+      "learning_rate": 0.0001902948402948403,
+      "loss": 1.1948189735412598,
+      "step": 90
+    },
+    {
+      "epoch": 0.18331805682859761,
+      "grad_norm": 0.6712405681610107,
+      "learning_rate": 0.00018906633906633907,
+      "loss": 1.1391284942626954,
+      "step": 100
+    },
+    {
+      "epoch": 0.2016498625114574,
+      "grad_norm": 0.8613548874855042,
+      "learning_rate": 0.00018783783783783784,
+      "loss": 1.1040291786193848,
+      "step": 110
+    },
+    {
+      "epoch": 0.21998166819431714,
+      "grad_norm": 0.8608964085578918,
+      "learning_rate": 0.0001866093366093366,
+      "loss": 1.1578070640563964,
+      "step": 120
+    },
+    {
+      "epoch": 0.2383134738771769,
+      "grad_norm": 0.8638626337051392,
+      "learning_rate": 0.0001853808353808354,
+      "loss": 1.1500712394714356,
+      "step": 130
+    },
+    {
+      "epoch": 0.2566452795600367,
+      "grad_norm": 0.8131710886955261,
+      "learning_rate": 0.00018415233415233417,
+      "loss": 1.0960933685302734,
+      "step": 140
+    },
+    {
+      "epoch": 0.27497708524289644,
+      "grad_norm": 1.023303508758545,
+      "learning_rate": 0.00018292383292383292,
+      "loss": 1.106197452545166,
+      "step": 150
+    },
+    {
+      "epoch": 0.2933088909257562,
+      "grad_norm": 0.7958722114562988,
+      "learning_rate": 0.0001816953316953317,
+      "loss": 1.1257465362548829,
+      "step": 160
+    },
+    {
+      "epoch": 0.31164069660861593,
+      "grad_norm": 0.8529394865036011,
+      "learning_rate": 0.00018046683046683048,
+      "loss": 1.062838077545166,
+      "step": 170
+    },
+    {
+      "epoch": 0.32997250229147573,
+      "grad_norm": 0.8443934917449951,
+      "learning_rate": 0.00017923832923832925,
+      "loss": 1.023012638092041,
+      "step": 180
+    },
+    {
+      "epoch": 0.3483043079743355,
+      "grad_norm": 0.8035740852355957,
+      "learning_rate": 0.00017800982800982802,
+      "loss": 1.0435395240783691,
+      "step": 190
+    },
+    {
+      "epoch": 0.36663611365719523,
+      "grad_norm": 0.8863442540168762,
+      "learning_rate": 0.00017678132678132678,
+      "loss": 1.0918319702148438,
+      "step": 200
+    },
+    {
+      "epoch": 0.384967919340055,
+      "grad_norm": 0.8198781609535217,
+      "learning_rate": 0.00017555282555282555,
+      "loss": 1.0226572036743165,
+      "step": 210
+    },
+    {
+      "epoch": 0.4032997250229148,
+      "grad_norm": 0.9801501035690308,
+      "learning_rate": 0.00017432432432432432,
+      "loss": 1.0847922325134278,
+      "step": 220
+    },
+    {
+      "epoch": 0.4216315307057745,
+      "grad_norm": 0.6737959980964661,
+      "learning_rate": 0.00017309582309582312,
+      "loss": 1.0508249282836915,
+      "step": 230
+    },
+    {
+      "epoch": 0.4399633363886343,
+      "grad_norm": 0.7932195067405701,
+      "learning_rate": 0.00017186732186732188,
+      "loss": 1.042081069946289,
+      "step": 240
+    },
+    {
+      "epoch": 0.458295142071494,
+      "grad_norm": 0.864284873008728,
+      "learning_rate": 0.00017063882063882065,
+      "loss": 1.0485817909240722,
+      "step": 250
+    },
+    {
+      "epoch": 0.4766269477543538,
+      "grad_norm": 0.8705862164497375,
+      "learning_rate": 0.00016941031941031942,
+      "loss": 1.0782199859619142,
+      "step": 260
+    },
+    {
+      "epoch": 0.49495875343721357,
+      "grad_norm": 0.8180854916572571,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 1.075644302368164,
+      "step": 270
+    },
+    {
+      "epoch": 0.5132905591200734,
+      "grad_norm": 0.8689812421798706,
+      "learning_rate": 0.00016695331695331696,
+      "loss": 1.0431486129760743,
+      "step": 280
+    },
+    {
+      "epoch": 0.5316223648029331,
+      "grad_norm": 0.7797616720199585,
+      "learning_rate": 0.00016572481572481573,
+      "loss": 1.019082736968994,
+      "step": 290
+    },
+    {
+      "epoch": 0.5499541704857929,
+      "grad_norm": 0.9403369426727295,
+      "learning_rate": 0.0001644963144963145,
+      "loss": 1.0104355812072754,
+      "step": 300
+    },
+    {
+      "epoch": 0.5682859761686526,
+      "grad_norm": 0.8061522245407104,
+      "learning_rate": 0.0001632678132678133,
+      "loss": 1.015712833404541,
+      "step": 310
+    },
+    {
+      "epoch": 0.5866177818515124,
+      "grad_norm": 1.0389378070831299,
+      "learning_rate": 0.00016203931203931203,
+      "loss": 0.983332347869873,
+      "step": 320
+    },
+    {
+      "epoch": 0.6049495875343721,
+      "grad_norm": 0.8335319757461548,
+      "learning_rate": 0.00016081081081081083,
+      "loss": 1.0035177230834962,
+      "step": 330
+    },
+    {
+      "epoch": 0.6232813932172319,
+      "grad_norm": 0.8039399981498718,
+      "learning_rate": 0.0001595823095823096,
+      "loss": 1.0274381637573242,
+      "step": 340
+    },
+    {
+      "epoch": 0.6416131989000916,
+      "grad_norm": 0.777919352054596,
+      "learning_rate": 0.00015835380835380836,
+      "loss": 1.0467321395874023,
+      "step": 350
+    },
+    {
+      "epoch": 0.6599450045829515,
+      "grad_norm": 0.8876609802246094,
+      "learning_rate": 0.00015712530712530713,
+      "loss": 0.9848588943481446,
+      "step": 360
+    },
+    {
+      "epoch": 0.6782768102658112,
+      "grad_norm": 0.8413349986076355,
+      "learning_rate": 0.0001558968058968059,
+      "loss": 1.0367840766906737,
+      "step": 370
+    },
+    {
+      "epoch": 0.696608615948671,
+      "grad_norm": 0.9921192526817322,
+      "learning_rate": 0.0001546683046683047,
+      "loss": 1.0018555641174316,
+      "step": 380
+    },
+    {
+      "epoch": 0.7149404216315307,
+      "grad_norm": 0.8272864818572998,
+      "learning_rate": 0.00015343980343980344,
+      "loss": 1.0093633651733398,
+      "step": 390
+    },
+    {
+      "epoch": 0.7332722273143905,
+      "grad_norm": 0.7949515581130981,
+      "learning_rate": 0.00015221130221130223,
+      "loss": 1.0220769882202148,
+      "step": 400
+    },
+    {
+      "epoch": 0.7516040329972502,
+      "grad_norm": 0.8337849378585815,
+      "learning_rate": 0.000150982800982801,
+      "loss": 0.9723053932189941,
+      "step": 410
+    },
+    {
+      "epoch": 0.76993583868011,
+      "grad_norm": 0.9521737694740295,
+      "learning_rate": 0.00014975429975429974,
+      "loss": 1.0630863189697266,
+      "step": 420
+    },
+    {
+      "epoch": 0.7882676443629697,
+      "grad_norm": 0.8320823311805725,
+      "learning_rate": 0.00014852579852579854,
+      "loss": 0.9916687965393066,
+      "step": 430
+    },
+    {
+      "epoch": 0.8065994500458296,
+      "grad_norm": 0.903413712978363,
+      "learning_rate": 0.0001472972972972973,
+      "loss": 0.9519875526428223,
+      "step": 440
+    },
+    {
+      "epoch": 0.8249312557286893,
+      "grad_norm": 0.8783673048019409,
+      "learning_rate": 0.00014606879606879607,
+      "loss": 1.0056891441345215,
+      "step": 450
+    },
+    {
+      "epoch": 0.843263061411549,
+      "grad_norm": 0.8581491708755493,
+      "learning_rate": 0.00014484029484029484,
+      "loss": 1.0211298942565918,
+      "step": 460
+    },
+    {
+      "epoch": 0.8615948670944088,
+      "grad_norm": 0.7977339029312134,
+      "learning_rate": 0.0001436117936117936,
+      "loss": 0.9528703689575195,
+      "step": 470
+    },
+    {
+      "epoch": 0.8799266727772685,
+      "grad_norm": 0.8142527937889099,
+      "learning_rate": 0.0001423832923832924,
+      "loss": 1.0111416816711425,
+      "step": 480
+    },
+    {
+      "epoch": 0.8982584784601283,
+      "grad_norm": 0.865929126739502,
+      "learning_rate": 0.00014115479115479115,
+      "loss": 0.978369140625,
+      "step": 490
+    },
+    {
+      "epoch": 0.916590284142988,
+      "grad_norm": 0.7955005764961243,
+      "learning_rate": 0.00013992628992628994,
+      "loss": 0.998965835571289,
+      "step": 500
+    },
+    {
+      "epoch": 0.9349220898258478,
+      "grad_norm": 0.7812423706054688,
+      "learning_rate": 0.0001386977886977887,
+      "loss": 0.9544276237487793,
+      "step": 510
+    },
+    {
+      "epoch": 0.9532538955087076,
+      "grad_norm": 0.817484974861145,
+      "learning_rate": 0.00013746928746928748,
+      "loss": 0.9699355125427246,
+      "step": 520
+    },
+    {
+      "epoch": 0.9715857011915674,
+      "grad_norm": 0.875234842300415,
+      "learning_rate": 0.00013624078624078625,
+      "loss": 0.9715826034545898,
+      "step": 530
+    },
+    {
+      "epoch": 0.9899175068744271,
+      "grad_norm": 0.7700145244598389,
+      "learning_rate": 0.00013501228501228501,
+      "loss": 0.9811925888061523,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073327222731439,
+      "grad_norm": 0.7260869145393372,
+      "learning_rate": 0.0001337837837837838,
+      "loss": 0.882848072052002,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256645279560037,
+      "grad_norm": 0.7263541221618652,
+      "learning_rate": 0.00013255528255528255,
+      "loss": 0.8015734672546386,
+      "step": 560
+    },
+    {
+      "epoch": 1.0439963336388633,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 0.00013132678132678135,
+      "loss": 0.778080940246582,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623281393217232,
+      "grad_norm": 0.8094732165336609,
+      "learning_rate": 0.00013009828009828011,
+      "loss": 0.7774394989013672,
+      "step": 580
+    },
+    {
+      "epoch": 1.0806599450045828,
+      "grad_norm": 0.8383634686470032,
+      "learning_rate": 0.00012886977886977886,
+      "loss": 0.7659544944763184,
+      "step": 590
+    },
+    {
+      "epoch": 1.0989917506874427,
+      "grad_norm": 0.9429551959037781,
+      "learning_rate": 0.00012764127764127765,
+      "loss": 0.7822256565093995,
+      "step": 600
+    },
+    {
+      "epoch": 1.1173235563703026,
+      "grad_norm": 0.8432884812355042,
+      "learning_rate": 0.00012641277641277642,
+      "loss": 0.7877971649169921,
+      "step": 610
+    },
+    {
+      "epoch": 1.1356553620531622,
+      "grad_norm": 0.9461238384246826,
+      "learning_rate": 0.0001251842751842752,
+      "loss": 0.8412753105163574,
+      "step": 620
+    },
+    {
+      "epoch": 1.153987167736022,
+      "grad_norm": 0.9495576620101929,
+      "learning_rate": 0.00012395577395577396,
+      "loss": 0.7389075279235839,
+      "step": 630
+    },
+    {
+      "epoch": 1.1723189734188817,
+      "grad_norm": 0.8137982487678528,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 0.7511651992797852,
+      "step": 640
+    },
+    {
+      "epoch": 1.1906507791017416,
+      "grad_norm": 0.9718158841133118,
+      "learning_rate": 0.00012149877149877152,
+      "loss": 0.7982583999633789,
+      "step": 650
+    },
+    {
+      "epoch": 1.2089825847846012,
+      "grad_norm": 1.0837777853012085,
+      "learning_rate": 0.00012027027027027027,
+      "loss": 0.762714433670044,
+      "step": 660
+    },
+    {
+      "epoch": 1.227314390467461,
+      "grad_norm": 0.9882314801216125,
+      "learning_rate": 0.00011904176904176904,
+      "loss": 0.7749518871307373,
+      "step": 670
+    },
+    {
+      "epoch": 1.2456461961503207,
+      "grad_norm": 0.9463419914245605,
+      "learning_rate": 0.00011781326781326782,
+      "loss": 0.7641645908355713,
+      "step": 680
+    },
+    {
+      "epoch": 1.2639780018331805,
+      "grad_norm": 0.9794511198997498,
+      "learning_rate": 0.00011658476658476658,
+      "loss": 0.8050010681152344,
+      "step": 690
+    },
+    {
+      "epoch": 1.2823098075160404,
+      "grad_norm": 1.1002216339111328,
+      "learning_rate": 0.00011535626535626536,
+      "loss": 0.793759822845459,
+      "step": 700
+    },
+    {
+      "epoch": 1.3006416131989,
+      "grad_norm": 0.9648078083992004,
+      "learning_rate": 0.00011412776412776414,
+      "loss": 0.7668623447418212,
+      "step": 710
+    },
+    {
+      "epoch": 1.31897341888176,
+      "grad_norm": 1.0727074146270752,
+      "learning_rate": 0.00011289926289926291,
+      "loss": 0.8029165267944336,
+      "step": 720
+    },
+    {
+      "epoch": 1.3373052245646195,
+      "grad_norm": 0.9617047905921936,
+      "learning_rate": 0.00011167076167076167,
+      "loss": 0.7798116683959961,
+      "step": 730
+    },
+    {
+      "epoch": 1.3556370302474794,
+      "grad_norm": 0.8710028529167175,
+      "learning_rate": 0.00011044226044226045,
+      "loss": 0.7962553977966309,
+      "step": 740
+    },
+    {
+      "epoch": 1.3739688359303392,
+      "grad_norm": 0.8409777283668518,
+      "learning_rate": 0.00010921375921375923,
+      "loss": 0.7403414726257325,
+      "step": 750
+    },
+    {
+      "epoch": 1.3923006416131989,
+      "grad_norm": 1.029362440109253,
+      "learning_rate": 0.00010798525798525798,
+      "loss": 0.7815125465393067,
+      "step": 760
+    },
+    {
+      "epoch": 1.4106324472960587,
+      "grad_norm": 0.9566736221313477,
+      "learning_rate": 0.00010675675675675677,
+      "loss": 0.7839052200317382,
+      "step": 770
+    },
+    {
+      "epoch": 1.4289642529789184,
+      "grad_norm": 0.975339949131012,
+      "learning_rate": 0.00010552825552825553,
+      "loss": 0.749812650680542,
+      "step": 780
+    },
+    {
+      "epoch": 1.4472960586617782,
+      "grad_norm": 1.1521857976913452,
+      "learning_rate": 0.00010429975429975432,
+      "loss": 0.7797944068908691,
+      "step": 790
+    },
+    {
+      "epoch": 1.4656278643446379,
+      "grad_norm": 0.8301038146018982,
+      "learning_rate": 0.00010307125307125307,
+      "loss": 0.7280281543731689,
+      "step": 800
+    },
+    {
+      "epoch": 1.4839596700274977,
+      "grad_norm": 0.9730615615844727,
+      "learning_rate": 0.00010184275184275185,
+      "loss": 0.7437058448791504,
+      "step": 810
+    },
+    {
+      "epoch": 1.5022914757103574,
+      "grad_norm": 1.0270700454711914,
+      "learning_rate": 0.00010061425061425062,
+      "loss": 0.7848101615905761,
+      "step": 820
+    },
+    {
+      "epoch": 1.5206232813932172,
+      "grad_norm": 1.2335196733474731,
+      "learning_rate": 9.938574938574939e-05,
+      "loss": 0.7896716117858886,
+      "step": 830
+    },
+    {
+      "epoch": 1.538955087076077,
+      "grad_norm": 0.968611478805542,
+      "learning_rate": 9.815724815724816e-05,
+      "loss": 0.7918240070343018,
+      "step": 840
+    },
+    {
+      "epoch": 1.5572868927589367,
+      "grad_norm": 0.9463298320770264,
+      "learning_rate": 9.692874692874694e-05,
+      "loss": 0.7453035354614258,
+      "step": 850
+    },
+    {
+      "epoch": 1.5756186984417964,
+      "grad_norm": 1.004184603691101,
+      "learning_rate": 9.570024570024571e-05,
+      "loss": 0.8125950813293457,
+      "step": 860
+    },
+    {
+      "epoch": 1.5939505041246562,
+      "grad_norm": 1.1150691509246826,
+      "learning_rate": 9.447174447174448e-05,
+      "loss": 0.7995445251464843,
+      "step": 870
+    },
+    {
+      "epoch": 1.612282309807516,
+      "grad_norm": 1.060056447982788,
+      "learning_rate": 9.324324324324324e-05,
+      "loss": 0.7746751785278321,
+      "step": 880
+    },
+    {
+      "epoch": 1.630614115490376,
+      "grad_norm": 1.0525883436203003,
+      "learning_rate": 9.201474201474201e-05,
+      "loss": 0.7861367225646972,
+      "step": 890
+    },
+    {
+      "epoch": 1.6489459211732356,
+      "grad_norm": 0.9495214223861694,
+      "learning_rate": 9.07862407862408e-05,
+      "loss": 0.8055791854858398,
+      "step": 900
+    },
+    {
+      "epoch": 1.6672777268560952,
+      "grad_norm": 0.8876036405563354,
+      "learning_rate": 8.955773955773956e-05,
+      "loss": 0.736152982711792,
+      "step": 910
+    },
+    {
+      "epoch": 1.685609532538955,
+      "grad_norm": 1.0228347778320312,
+      "learning_rate": 8.832923832923833e-05,
+      "loss": 0.7859257698059082,
+      "step": 920
+    },
+    {
+      "epoch": 1.703941338221815,
+      "grad_norm": 1.2196885347366333,
+      "learning_rate": 8.710073710073711e-05,
+      "loss": 0.7442365169525147,
+      "step": 930
+    },
+    {
+      "epoch": 1.7222731439046746,
+      "grad_norm": 1.1201367378234863,
+      "learning_rate": 8.587223587223587e-05,
+      "loss": 0.7933924674987793,
+      "step": 940
+    },
+    {
+      "epoch": 1.7406049495875344,
+      "grad_norm": 1.0457044839859009,
+      "learning_rate": 8.464373464373465e-05,
+      "loss": 0.7594408512115478,
+      "step": 950
+    },
+    {
+      "epoch": 1.758936755270394,
+      "grad_norm": 1.2219468355178833,
+      "learning_rate": 8.341523341523342e-05,
+      "loss": 0.725389051437378,
+      "step": 960
+    },
+    {
+      "epoch": 1.777268560953254,
+      "grad_norm": 1.0098403692245483,
+      "learning_rate": 8.21867321867322e-05,
+      "loss": 0.7753002166748046,
+      "step": 970
+    },
+    {
+      "epoch": 1.7956003666361138,
+      "grad_norm": 1.020544409751892,
+      "learning_rate": 8.095823095823097e-05,
+      "loss": 0.7580110549926757,
+      "step": 980
+    },
+    {
+      "epoch": 1.8139321723189734,
+      "grad_norm": 0.9121679067611694,
+      "learning_rate": 7.972972972972974e-05,
+      "loss": 0.7329069614410401,
+      "step": 990
+    },
+    {
+      "epoch": 1.832263978001833,
+      "grad_norm": 1.1305643320083618,
+      "learning_rate": 7.85012285012285e-05,
+      "loss": 0.7436663150787354,
+      "step": 1000
+    },
+    {
+      "epoch": 1.850595783684693,
+      "grad_norm": 0.9970649480819702,
+      "learning_rate": 7.727272727272727e-05,
+      "loss": 0.7684538841247559,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8689275893675528,
+      "grad_norm": 1.0161981582641602,
+      "learning_rate": 7.604422604422605e-05,
+      "loss": 0.7405171394348145,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8872593950504126,
+      "grad_norm": 1.3399347066879272,
+      "learning_rate": 7.481572481572482e-05,
+      "loss": 0.780091667175293,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9055912007332723,
+      "grad_norm": 1.2579443454742432,
+      "learning_rate": 7.358722358722359e-05,
+      "loss": 0.6868968486785889,
+      "step": 1040
+    },
+    {
+      "epoch": 1.923923006416132,
+      "grad_norm": 1.0092531442642212,
+      "learning_rate": 7.235872235872236e-05,
+      "loss": 0.742798137664795,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9422548120989918,
+      "grad_norm": 1.121690273284912,
+      "learning_rate": 7.113022113022113e-05,
+      "loss": 0.8035343170166016,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9605866177818516,
+      "grad_norm": 1.0780940055847168,
+      "learning_rate": 6.990171990171991e-05,
+      "loss": 0.7256640911102294,
+      "step": 1070
+    },
+    {
+      "epoch": 1.9789184234647113,
+      "grad_norm": 1.0335768461227417,
+      "learning_rate": 6.867321867321868e-05,
+      "loss": 0.751814889907837,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9972502291475709,
+      "grad_norm": 1.0326813459396362,
+      "learning_rate": 6.744471744471746e-05,
+      "loss": 0.781493854522705,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0146654445462877,
+      "grad_norm": 0.9365840554237366,
+      "learning_rate": 6.621621621621621e-05,
+      "loss": 0.6172435760498047,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0329972502291476,
+      "grad_norm": 1.0775729417800903,
+      "learning_rate": 6.498771498771498e-05,
+      "loss": 0.5551021575927735,
+      "step": 1110
+    },
+    {
+      "epoch": 2.0513290559120074,
+      "grad_norm": 1.1233711242675781,
+      "learning_rate": 6.375921375921376e-05,
+      "loss": 0.530482006072998,
+      "step": 1120
+    },
+    {
+      "epoch": 2.0696608615948673,
+      "grad_norm": 0.9685810208320618,
+      "learning_rate": 6.253071253071253e-05,
+      "loss": 0.5284864902496338,
+      "step": 1130
+    },
+    {
+      "epoch": 2.0879926672777267,
+      "grad_norm": 1.3673559427261353,
+      "learning_rate": 6.130221130221131e-05,
+      "loss": 0.5300433158874511,
+      "step": 1140
+    },
+    {
+      "epoch": 2.1063244729605866,
+      "grad_norm": 1.291156530380249,
+      "learning_rate": 6.0073710073710075e-05,
+      "loss": 0.5388914585113526,
+      "step": 1150
+    },
+    {
+      "epoch": 2.1246562786434464,
+      "grad_norm": 1.0860686302185059,
+      "learning_rate": 5.8845208845208844e-05,
+      "loss": 0.5599504947662354,
+      "step": 1160
+    },
+    {
+      "epoch": 2.1429880843263063,
+      "grad_norm": 1.2297484874725342,
+      "learning_rate": 5.761670761670762e-05,
+      "loss": 0.5693662643432618,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1613198900091657,
+      "grad_norm": 1.3128403425216675,
+      "learning_rate": 5.638820638820639e-05,
+      "loss": 0.5087790012359619,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1796516956920255,
+      "grad_norm": 1.47864830493927,
+      "learning_rate": 5.515970515970517e-05,
+      "loss": 0.5520669460296631,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1979835013748854,
+      "grad_norm": 1.3533881902694702,
+      "learning_rate": 5.393120393120393e-05,
+      "loss": 0.5194924354553223,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2163153070577453,
+      "grad_norm": 1.0729988813400269,
+      "learning_rate": 5.27027027027027e-05,
+      "loss": 0.5386343955993652,
+      "step": 1210
+    },
+    {
+      "epoch": 2.234647112740605,
+      "grad_norm": 1.1851814985275269,
+      "learning_rate": 5.147420147420148e-05,
+      "loss": 0.5398934364318848,
+      "step": 1220
+    },
+    {
+      "epoch": 2.2529789184234645,
+      "grad_norm": 1.306754469871521,
+      "learning_rate": 5.024570024570024e-05,
+      "loss": 0.5412076473236084,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2713107241063244,
+      "grad_norm": 1.2561992406845093,
+      "learning_rate": 4.901719901719902e-05,
+      "loss": 0.555613899230957,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2896425297891843,
+      "grad_norm": 1.4935739040374756,
+      "learning_rate": 4.778869778869779e-05,
+      "loss": 0.560833215713501,
+      "step": 1250
+    },
+    {
+      "epoch": 2.307974335472044,
+      "grad_norm": 1.2064818143844604,
+      "learning_rate": 4.656019656019656e-05,
+      "loss": 0.5313505172729492,
+      "step": 1260
+    },
+    {
+      "epoch": 2.3263061411549035,
+      "grad_norm": 1.2250595092773438,
+      "learning_rate": 4.5331695331695335e-05,
+      "loss": 0.5530914306640625,
+      "step": 1270
+    },
+    {
+      "epoch": 2.3446379468377634,
+      "grad_norm": 1.249531865119934,
+      "learning_rate": 4.4103194103194104e-05,
+      "loss": 0.5281160831451416,
+      "step": 1280
+    },
+    {
+      "epoch": 2.3629697525206232,
+      "grad_norm": 1.1765642166137695,
+      "learning_rate": 4.287469287469288e-05,
+      "loss": 0.5416937351226807,
+      "step": 1290
+    },
+    {
+      "epoch": 2.381301558203483,
+      "grad_norm": 1.2973071336746216,
+      "learning_rate": 4.164619164619165e-05,
+      "loss": 0.5341888427734375,
+      "step": 1300
+    },
+    {
+      "epoch": 2.399633363886343,
+      "grad_norm": 1.3533828258514404,
+      "learning_rate": 4.0417690417690415e-05,
+      "loss": 0.5386404514312744,
+      "step": 1310
+    },
+    {
+      "epoch": 2.4179651695692024,
+      "grad_norm": 1.1323643922805786,
+      "learning_rate": 3.918918918918919e-05,
+      "loss": 0.5549521446228027,
+      "step": 1320
+    },
+    {
+      "epoch": 2.4362969752520622,
+      "grad_norm": 1.0967226028442383,
+      "learning_rate": 3.7960687960687965e-05,
+      "loss": 0.5668260097503662,
+      "step": 1330
+    },
+    {
+      "epoch": 2.454628780934922,
+      "grad_norm": 1.3874995708465576,
+      "learning_rate": 3.6732186732186734e-05,
+      "loss": 0.5530946254730225,
+      "step": 1340
+    },
+    {
+      "epoch": 2.472960586617782,
+      "grad_norm": 1.3139115571975708,
+      "learning_rate": 3.550368550368551e-05,
+      "loss": 0.544743013381958,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4912923923006414,
+      "grad_norm": 1.3629847764968872,
+      "learning_rate": 3.427518427518428e-05,
+      "loss": 0.5550421714782715,
+      "step": 1360
+    },
+    {
+      "epoch": 2.5096241979835012,
+      "grad_norm": 1.3279292583465576,
+      "learning_rate": 3.3046683046683045e-05,
+      "loss": 0.5361227035522461,
+      "step": 1370
+    },
+    {
+      "epoch": 2.527956003666361,
+      "grad_norm": 1.3736717700958252,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 0.5256178855895997,
+      "step": 1380
+    },
+    {
+      "epoch": 2.546287809349221,
+      "grad_norm": 1.2405906915664673,
+      "learning_rate": 3.058968058968059e-05,
+      "loss": 0.5551014900207519,
+      "step": 1390
+    },
+    {
+      "epoch": 2.564619615032081,
+      "grad_norm": 1.2711869478225708,
+      "learning_rate": 2.9361179361179364e-05,
+      "loss": 0.549025011062622,
+      "step": 1400
+    },
+    {
+      "epoch": 2.5829514207149407,
+      "grad_norm": 1.1510083675384521,
+      "learning_rate": 2.8132678132678135e-05,
+      "loss": 0.5108777046203613,
+      "step": 1410
+    },
+    {
+      "epoch": 2.6012832263978,
+      "grad_norm": 1.2585129737854004,
+      "learning_rate": 2.6904176904176904e-05,
+      "loss": 0.545832633972168,
+      "step": 1420
+    },
+    {
+      "epoch": 2.61961503208066,
+      "grad_norm": 1.2926920652389526,
+      "learning_rate": 2.5675675675675675e-05,
+      "loss": 0.531532621383667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.63794683776352,
+      "grad_norm": 1.1816222667694092,
+      "learning_rate": 2.4447174447174447e-05,
+      "loss": 0.4899789333343506,
+      "step": 1440
+    },
+    {
+      "epoch": 2.656278643446379,
+      "grad_norm": 1.3441561460494995,
+      "learning_rate": 2.3218673218673222e-05,
+      "loss": 0.5534125804901123,
+      "step": 1450
+    },
+    {
+      "epoch": 2.674610449129239,
+      "grad_norm": 1.5367056131362915,
+      "learning_rate": 2.199017199017199e-05,
+      "loss": 0.5469470500946045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.692942254812099,
+      "grad_norm": 1.292490005493164,
+      "learning_rate": 2.0761670761670762e-05,
+      "loss": 0.5418555259704589,
+      "step": 1470
+    },
+    {
+      "epoch": 2.711274060494959,
+      "grad_norm": 1.2457395792007446,
+      "learning_rate": 1.9533169533169534e-05,
+      "loss": 0.5272214889526368,
+      "step": 1480
+    },
+    {
+      "epoch": 2.7296058661778186,
+      "grad_norm": 1.3204960823059082,
+      "learning_rate": 1.8304668304668305e-05,
+      "loss": 0.5287877559661865,
+      "step": 1490
+    },
+    {
+      "epoch": 2.7479376718606785,
+      "grad_norm": 1.0838243961334229,
+      "learning_rate": 1.7076167076167077e-05,
+      "loss": 0.49266462326049804,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1638,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.100994127286784e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85e9413c7636d9fff8558d114d2112dff5238aa624b3ebdad9a7bde187c0bf2
+size 5713

checkpoint-1638/README.md

@@ -0,0 +1,210 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- 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 0.18.1

checkpoint-1638/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1638/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae7c6d0daab67837abb33f93468f20937e3666d8f09a8ea2decd15b8e7c76ab
+size 84972248

checkpoint-1638/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1638/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432ab2a4e17001ab352ca4740f00fd740468093ebd062aca664ad2de39bbf938
+size 43434405

checkpoint-1638/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-1638/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-1638/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30221d2371277d9c2ee0a99b44f86b7d2fe6174ffcee6c591737073fbc903359
+size 1465

checkpoint-1638/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

checkpoint-1638/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

checkpoint-1638/trainer_state.json

@@ -0,0 +1,1175 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1638,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01833180568285976,
+      "grad_norm": 0.6833510994911194,
+      "learning_rate": 0.00018,
+      "loss": 1.8247451782226562,
+      "step": 10
+    },
+    {
+      "epoch": 0.03666361136571952,
+      "grad_norm": 0.9012069702148438,
+      "learning_rate": 0.0001988943488943489,
+      "loss": 1.4739965438842773,
+      "step": 20
+    },
+    {
+      "epoch": 0.054995417048579284,
+      "grad_norm": 0.8267062306404114,
+      "learning_rate": 0.00019766584766584767,
+      "loss": 1.3358205795288085,
+      "step": 30
+    },
+    {
+      "epoch": 0.07332722273143905,
+      "grad_norm": 0.7565646767616272,
+      "learning_rate": 0.00019643734643734644,
+      "loss": 1.2644735336303712,
+      "step": 40
+    },
+    {
+      "epoch": 0.09165902841429881,
+      "grad_norm": 0.8591431975364685,
+      "learning_rate": 0.0001952088452088452,
+      "loss": 1.244968318939209,
+      "step": 50
+    },
+    {
+      "epoch": 0.10999083409715857,
+      "grad_norm": 0.8081830143928528,
+      "learning_rate": 0.000193980343980344,
+      "loss": 1.209956455230713,
+      "step": 60
+    },
+    {
+      "epoch": 0.12832263978001834,
+      "grad_norm": 0.8808525800704956,
+      "learning_rate": 0.00019275184275184277,
+      "loss": 1.1500988960266114,
+      "step": 70
+    },
+    {
+      "epoch": 0.1466544454628781,
+      "grad_norm": 0.82117760181427,
+      "learning_rate": 0.00019152334152334154,
+      "loss": 1.1469905853271485,
+      "step": 80
+    },
+    {
+      "epoch": 0.16498625114573787,
+      "grad_norm": 0.8583332896232605,
+      "learning_rate": 0.0001902948402948403,
+      "loss": 1.1948189735412598,
+      "step": 90
+    },
+    {
+      "epoch": 0.18331805682859761,
+      "grad_norm": 0.6712405681610107,
+      "learning_rate": 0.00018906633906633907,
+      "loss": 1.1391284942626954,
+      "step": 100
+    },
+    {
+      "epoch": 0.2016498625114574,
+      "grad_norm": 0.8613548874855042,
+      "learning_rate": 0.00018783783783783784,
+      "loss": 1.1040291786193848,
+      "step": 110
+    },
+    {
+      "epoch": 0.21998166819431714,
+      "grad_norm": 0.8608964085578918,
+      "learning_rate": 0.0001866093366093366,
+      "loss": 1.1578070640563964,
+      "step": 120
+    },
+    {
+      "epoch": 0.2383134738771769,
+      "grad_norm": 0.8638626337051392,
+      "learning_rate": 0.0001853808353808354,
+      "loss": 1.1500712394714356,
+      "step": 130
+    },
+    {
+      "epoch": 0.2566452795600367,
+      "grad_norm": 0.8131710886955261,
+      "learning_rate": 0.00018415233415233417,
+      "loss": 1.0960933685302734,
+      "step": 140
+    },
+    {
+      "epoch": 0.27497708524289644,
+      "grad_norm": 1.023303508758545,
+      "learning_rate": 0.00018292383292383292,
+      "loss": 1.106197452545166,
+      "step": 150
+    },
+    {
+      "epoch": 0.2933088909257562,
+      "grad_norm": 0.7958722114562988,
+      "learning_rate": 0.0001816953316953317,
+      "loss": 1.1257465362548829,
+      "step": 160
+    },
+    {
+      "epoch": 0.31164069660861593,
+      "grad_norm": 0.8529394865036011,
+      "learning_rate": 0.00018046683046683048,
+      "loss": 1.062838077545166,
+      "step": 170
+    },
+    {
+      "epoch": 0.32997250229147573,
+      "grad_norm": 0.8443934917449951,
+      "learning_rate": 0.00017923832923832925,
+      "loss": 1.023012638092041,
+      "step": 180
+    },
+    {
+      "epoch": 0.3483043079743355,
+      "grad_norm": 0.8035740852355957,
+      "learning_rate": 0.00017800982800982802,
+      "loss": 1.0435395240783691,
+      "step": 190
+    },
+    {
+      "epoch": 0.36663611365719523,
+      "grad_norm": 0.8863442540168762,
+      "learning_rate": 0.00017678132678132678,
+      "loss": 1.0918319702148438,
+      "step": 200
+    },
+    {
+      "epoch": 0.384967919340055,
+      "grad_norm": 0.8198781609535217,
+      "learning_rate": 0.00017555282555282555,
+      "loss": 1.0226572036743165,
+      "step": 210
+    },
+    {
+      "epoch": 0.4032997250229148,
+      "grad_norm": 0.9801501035690308,
+      "learning_rate": 0.00017432432432432432,
+      "loss": 1.0847922325134278,
+      "step": 220
+    },
+    {
+      "epoch": 0.4216315307057745,
+      "grad_norm": 0.6737959980964661,
+      "learning_rate": 0.00017309582309582312,
+      "loss": 1.0508249282836915,
+      "step": 230
+    },
+    {
+      "epoch": 0.4399633363886343,
+      "grad_norm": 0.7932195067405701,
+      "learning_rate": 0.00017186732186732188,
+      "loss": 1.042081069946289,
+      "step": 240
+    },
+    {
+      "epoch": 0.458295142071494,
+      "grad_norm": 0.864284873008728,
+      "learning_rate": 0.00017063882063882065,
+      "loss": 1.0485817909240722,
+      "step": 250
+    },
+    {
+      "epoch": 0.4766269477543538,
+      "grad_norm": 0.8705862164497375,
+      "learning_rate": 0.00016941031941031942,
+      "loss": 1.0782199859619142,
+      "step": 260
+    },
+    {
+      "epoch": 0.49495875343721357,
+      "grad_norm": 0.8180854916572571,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 1.075644302368164,
+      "step": 270
+    },
+    {
+      "epoch": 0.5132905591200734,
+      "grad_norm": 0.8689812421798706,
+      "learning_rate": 0.00016695331695331696,
+      "loss": 1.0431486129760743,
+      "step": 280
+    },
+    {
+      "epoch": 0.5316223648029331,
+      "grad_norm": 0.7797616720199585,
+      "learning_rate": 0.00016572481572481573,
+      "loss": 1.019082736968994,
+      "step": 290
+    },
+    {
+      "epoch": 0.5499541704857929,
+      "grad_norm": 0.9403369426727295,
+      "learning_rate": 0.0001644963144963145,
+      "loss": 1.0104355812072754,
+      "step": 300
+    },
+    {
+      "epoch": 0.5682859761686526,
+      "grad_norm": 0.8061522245407104,
+      "learning_rate": 0.0001632678132678133,
+      "loss": 1.015712833404541,
+      "step": 310
+    },
+    {
+      "epoch": 0.5866177818515124,
+      "grad_norm": 1.0389378070831299,
+      "learning_rate": 0.00016203931203931203,
+      "loss": 0.983332347869873,
+      "step": 320
+    },
+    {
+      "epoch": 0.6049495875343721,
+      "grad_norm": 0.8335319757461548,
+      "learning_rate": 0.00016081081081081083,
+      "loss": 1.0035177230834962,
+      "step": 330
+    },
+    {
+      "epoch": 0.6232813932172319,
+      "grad_norm": 0.8039399981498718,
+      "learning_rate": 0.0001595823095823096,
+      "loss": 1.0274381637573242,
+      "step": 340
+    },
+    {
+      "epoch": 0.6416131989000916,
+      "grad_norm": 0.777919352054596,
+      "learning_rate": 0.00015835380835380836,
+      "loss": 1.0467321395874023,
+      "step": 350
+    },
+    {
+      "epoch": 0.6599450045829515,
+      "grad_norm": 0.8876609802246094,
+      "learning_rate": 0.00015712530712530713,
+      "loss": 0.9848588943481446,
+      "step": 360
+    },
+    {
+      "epoch": 0.6782768102658112,
+      "grad_norm": 0.8413349986076355,
+      "learning_rate": 0.0001558968058968059,
+      "loss": 1.0367840766906737,
+      "step": 370
+    },
+    {
+      "epoch": 0.696608615948671,
+      "grad_norm": 0.9921192526817322,
+      "learning_rate": 0.0001546683046683047,
+      "loss": 1.0018555641174316,
+      "step": 380
+    },
+    {
+      "epoch": 0.7149404216315307,
+      "grad_norm": 0.8272864818572998,
+      "learning_rate": 0.00015343980343980344,
+      "loss": 1.0093633651733398,
+      "step": 390
+    },
+    {
+      "epoch": 0.7332722273143905,
+      "grad_norm": 0.7949515581130981,
+      "learning_rate": 0.00015221130221130223,
+      "loss": 1.0220769882202148,
+      "step": 400
+    },
+    {
+      "epoch": 0.7516040329972502,
+      "grad_norm": 0.8337849378585815,
+      "learning_rate": 0.000150982800982801,
+      "loss": 0.9723053932189941,
+      "step": 410
+    },
+    {
+      "epoch": 0.76993583868011,
+      "grad_norm": 0.9521737694740295,
+      "learning_rate": 0.00014975429975429974,
+      "loss": 1.0630863189697266,
+      "step": 420
+    },
+    {
+      "epoch": 0.7882676443629697,
+      "grad_norm": 0.8320823311805725,
+      "learning_rate": 0.00014852579852579854,
+      "loss": 0.9916687965393066,
+      "step": 430
+    },
+    {
+      "epoch": 0.8065994500458296,
+      "grad_norm": 0.903413712978363,
+      "learning_rate": 0.0001472972972972973,
+      "loss": 0.9519875526428223,
+      "step": 440
+    },
+    {
+      "epoch": 0.8249312557286893,
+      "grad_norm": 0.8783673048019409,
+      "learning_rate": 0.00014606879606879607,
+      "loss": 1.0056891441345215,
+      "step": 450
+    },
+    {
+      "epoch": 0.843263061411549,
+      "grad_norm": 0.8581491708755493,
+      "learning_rate": 0.00014484029484029484,
+      "loss": 1.0211298942565918,
+      "step": 460
+    },
+    {
+      "epoch": 0.8615948670944088,
+      "grad_norm": 0.7977339029312134,
+      "learning_rate": 0.0001436117936117936,
+      "loss": 0.9528703689575195,
+      "step": 470
+    },
+    {
+      "epoch": 0.8799266727772685,
+      "grad_norm": 0.8142527937889099,
+      "learning_rate": 0.0001423832923832924,
+      "loss": 1.0111416816711425,
+      "step": 480
+    },
+    {
+      "epoch": 0.8982584784601283,
+      "grad_norm": 0.865929126739502,
+      "learning_rate": 0.00014115479115479115,
+      "loss": 0.978369140625,
+      "step": 490
+    },
+    {
+      "epoch": 0.916590284142988,
+      "grad_norm": 0.7955005764961243,
+      "learning_rate": 0.00013992628992628994,
+      "loss": 0.998965835571289,
+      "step": 500
+    },
+    {
+      "epoch": 0.9349220898258478,
+      "grad_norm": 0.7812423706054688,
+      "learning_rate": 0.0001386977886977887,
+      "loss": 0.9544276237487793,
+      "step": 510
+    },
+    {
+      "epoch": 0.9532538955087076,
+      "grad_norm": 0.817484974861145,
+      "learning_rate": 0.00013746928746928748,
+      "loss": 0.9699355125427246,
+      "step": 520
+    },
+    {
+      "epoch": 0.9715857011915674,
+      "grad_norm": 0.875234842300415,
+      "learning_rate": 0.00013624078624078625,
+      "loss": 0.9715826034545898,
+      "step": 530
+    },
+    {
+      "epoch": 0.9899175068744271,
+      "grad_norm": 0.7700145244598389,
+      "learning_rate": 0.00013501228501228501,
+      "loss": 0.9811925888061523,
+      "step": 540
+    },
+    {
+      "epoch": 1.0073327222731439,
+      "grad_norm": 0.7260869145393372,
+      "learning_rate": 0.0001337837837837838,
+      "loss": 0.882848072052002,
+      "step": 550
+    },
+    {
+      "epoch": 1.0256645279560037,
+      "grad_norm": 0.7263541221618652,
+      "learning_rate": 0.00013255528255528255,
+      "loss": 0.8015734672546386,
+      "step": 560
+    },
+    {
+      "epoch": 1.0439963336388633,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 0.00013132678132678135,
+      "loss": 0.778080940246582,
+      "step": 570
+    },
+    {
+      "epoch": 1.0623281393217232,
+      "grad_norm": 0.8094732165336609,
+      "learning_rate": 0.00013009828009828011,
+      "loss": 0.7774394989013672,
+      "step": 580
+    },
+    {
+      "epoch": 1.0806599450045828,
+      "grad_norm": 0.8383634686470032,
+      "learning_rate": 0.00012886977886977886,
+      "loss": 0.7659544944763184,
+      "step": 590
+    },
+    {
+      "epoch": 1.0989917506874427,
+      "grad_norm": 0.9429551959037781,
+      "learning_rate": 0.00012764127764127765,
+      "loss": 0.7822256565093995,
+      "step": 600
+    },
+    {
+      "epoch": 1.1173235563703026,
+      "grad_norm": 0.8432884812355042,
+      "learning_rate": 0.00012641277641277642,
+      "loss": 0.7877971649169921,
+      "step": 610
+    },
+    {
+      "epoch": 1.1356553620531622,
+      "grad_norm": 0.9461238384246826,
+      "learning_rate": 0.0001251842751842752,
+      "loss": 0.8412753105163574,
+      "step": 620
+    },
+    {
+      "epoch": 1.153987167736022,
+      "grad_norm": 0.9495576620101929,
+      "learning_rate": 0.00012395577395577396,
+      "loss": 0.7389075279235839,
+      "step": 630
+    },
+    {
+      "epoch": 1.1723189734188817,
+      "grad_norm": 0.8137982487678528,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 0.7511651992797852,
+      "step": 640
+    },
+    {
+      "epoch": 1.1906507791017416,
+      "grad_norm": 0.9718158841133118,
+      "learning_rate": 0.00012149877149877152,
+      "loss": 0.7982583999633789,
+      "step": 650
+    },
+    {
+      "epoch": 1.2089825847846012,
+      "grad_norm": 1.0837777853012085,
+      "learning_rate": 0.00012027027027027027,
+      "loss": 0.762714433670044,
+      "step": 660
+    },
+    {
+      "epoch": 1.227314390467461,
+      "grad_norm": 0.9882314801216125,
+      "learning_rate": 0.00011904176904176904,
+      "loss": 0.7749518871307373,
+      "step": 670
+    },
+    {
+      "epoch": 1.2456461961503207,
+      "grad_norm": 0.9463419914245605,
+      "learning_rate": 0.00011781326781326782,
+      "loss": 0.7641645908355713,
+      "step": 680
+    },
+    {
+      "epoch": 1.2639780018331805,
+      "grad_norm": 0.9794511198997498,
+      "learning_rate": 0.00011658476658476658,
+      "loss": 0.8050010681152344,
+      "step": 690
+    },
+    {
+      "epoch": 1.2823098075160404,
+      "grad_norm": 1.1002216339111328,
+      "learning_rate": 0.00011535626535626536,
+      "loss": 0.793759822845459,
+      "step": 700
+    },
+    {
+      "epoch": 1.3006416131989,
+      "grad_norm": 0.9648078083992004,
+      "learning_rate": 0.00011412776412776414,
+      "loss": 0.7668623447418212,
+      "step": 710
+    },
+    {
+      "epoch": 1.31897341888176,
+      "grad_norm": 1.0727074146270752,
+      "learning_rate": 0.00011289926289926291,
+      "loss": 0.8029165267944336,
+      "step": 720
+    },
+    {
+      "epoch": 1.3373052245646195,
+      "grad_norm": 0.9617047905921936,
+      "learning_rate": 0.00011167076167076167,
+      "loss": 0.7798116683959961,
+      "step": 730
+    },
+    {
+      "epoch": 1.3556370302474794,
+      "grad_norm": 0.8710028529167175,
+      "learning_rate": 0.00011044226044226045,
+      "loss": 0.7962553977966309,
+      "step": 740
+    },
+    {
+      "epoch": 1.3739688359303392,
+      "grad_norm": 0.8409777283668518,
+      "learning_rate": 0.00010921375921375923,
+      "loss": 0.7403414726257325,
+      "step": 750
+    },
+    {
+      "epoch": 1.3923006416131989,
+      "grad_norm": 1.029362440109253,
+      "learning_rate": 0.00010798525798525798,
+      "loss": 0.7815125465393067,
+      "step": 760
+    },
+    {
+      "epoch": 1.4106324472960587,
+      "grad_norm": 0.9566736221313477,
+      "learning_rate": 0.00010675675675675677,
+      "loss": 0.7839052200317382,
+      "step": 770
+    },
+    {
+      "epoch": 1.4289642529789184,
+      "grad_norm": 0.975339949131012,
+      "learning_rate": 0.00010552825552825553,
+      "loss": 0.749812650680542,
+      "step": 780
+    },
+    {
+      "epoch": 1.4472960586617782,
+      "grad_norm": 1.1521857976913452,
+      "learning_rate": 0.00010429975429975432,
+      "loss": 0.7797944068908691,
+      "step": 790
+    },
+    {
+      "epoch": 1.4656278643446379,
+      "grad_norm": 0.8301038146018982,
+      "learning_rate": 0.00010307125307125307,
+      "loss": 0.7280281543731689,
+      "step": 800
+    },
+    {
+      "epoch": 1.4839596700274977,
+      "grad_norm": 0.9730615615844727,
+      "learning_rate": 0.00010184275184275185,
+      "loss": 0.7437058448791504,
+      "step": 810
+    },
+    {
+      "epoch": 1.5022914757103574,
+      "grad_norm": 1.0270700454711914,
+      "learning_rate": 0.00010061425061425062,
+      "loss": 0.7848101615905761,
+      "step": 820
+    },
+    {
+      "epoch": 1.5206232813932172,
+      "grad_norm": 1.2335196733474731,
+      "learning_rate": 9.938574938574939e-05,
+      "loss": 0.7896716117858886,
+      "step": 830
+    },
+    {
+      "epoch": 1.538955087076077,
+      "grad_norm": 0.968611478805542,
+      "learning_rate": 9.815724815724816e-05,
+      "loss": 0.7918240070343018,
+      "step": 840
+    },
+    {
+      "epoch": 1.5572868927589367,
+      "grad_norm": 0.9463298320770264,
+      "learning_rate": 9.692874692874694e-05,
+      "loss": 0.7453035354614258,
+      "step": 850
+    },
+    {
+      "epoch": 1.5756186984417964,
+      "grad_norm": 1.004184603691101,
+      "learning_rate": 9.570024570024571e-05,
+      "loss": 0.8125950813293457,
+      "step": 860
+    },
+    {
+      "epoch": 1.5939505041246562,
+      "grad_norm": 1.1150691509246826,
+      "learning_rate": 9.447174447174448e-05,
+      "loss": 0.7995445251464843,
+      "step": 870
+    },
+    {
+      "epoch": 1.612282309807516,
+      "grad_norm": 1.060056447982788,
+      "learning_rate": 9.324324324324324e-05,
+      "loss": 0.7746751785278321,
+      "step": 880
+    },
+    {
+      "epoch": 1.630614115490376,
+      "grad_norm": 1.0525883436203003,
+      "learning_rate": 9.201474201474201e-05,
+      "loss": 0.7861367225646972,
+      "step": 890
+    },
+    {
+      "epoch": 1.6489459211732356,
+      "grad_norm": 0.9495214223861694,
+      "learning_rate": 9.07862407862408e-05,
+      "loss": 0.8055791854858398,
+      "step": 900
+    },
+    {
+      "epoch": 1.6672777268560952,
+      "grad_norm": 0.8876036405563354,
+      "learning_rate": 8.955773955773956e-05,
+      "loss": 0.736152982711792,
+      "step": 910
+    },
+    {
+      "epoch": 1.685609532538955,
+      "grad_norm": 1.0228347778320312,
+      "learning_rate": 8.832923832923833e-05,
+      "loss": 0.7859257698059082,
+      "step": 920
+    },
+    {
+      "epoch": 1.703941338221815,
+      "grad_norm": 1.2196885347366333,
+      "learning_rate": 8.710073710073711e-05,
+      "loss": 0.7442365169525147,
+      "step": 930
+    },
+    {
+      "epoch": 1.7222731439046746,
+      "grad_norm": 1.1201367378234863,
+      "learning_rate": 8.587223587223587e-05,
+      "loss": 0.7933924674987793,
+      "step": 940
+    },
+    {
+      "epoch": 1.7406049495875344,
+      "grad_norm": 1.0457044839859009,
+      "learning_rate": 8.464373464373465e-05,
+      "loss": 0.7594408512115478,
+      "step": 950
+    },
+    {
+      "epoch": 1.758936755270394,
+      "grad_norm": 1.2219468355178833,
+      "learning_rate": 8.341523341523342e-05,
+      "loss": 0.725389051437378,
+      "step": 960
+    },
+    {
+      "epoch": 1.777268560953254,
+      "grad_norm": 1.0098403692245483,
+      "learning_rate": 8.21867321867322e-05,
+      "loss": 0.7753002166748046,
+      "step": 970
+    },
+    {
+      "epoch": 1.7956003666361138,
+      "grad_norm": 1.020544409751892,
+      "learning_rate": 8.095823095823097e-05,
+      "loss": 0.7580110549926757,
+      "step": 980
+    },
+    {
+      "epoch": 1.8139321723189734,
+      "grad_norm": 0.9121679067611694,
+      "learning_rate": 7.972972972972974e-05,
+      "loss": 0.7329069614410401,
+      "step": 990
+    },
+    {
+      "epoch": 1.832263978001833,
+      "grad_norm": 1.1305643320083618,
+      "learning_rate": 7.85012285012285e-05,
+      "loss": 0.7436663150787354,
+      "step": 1000
+    },
+    {
+      "epoch": 1.850595783684693,
+      "grad_norm": 0.9970649480819702,
+      "learning_rate": 7.727272727272727e-05,
+      "loss": 0.7684538841247559,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8689275893675528,
+      "grad_norm": 1.0161981582641602,
+      "learning_rate": 7.604422604422605e-05,
+      "loss": 0.7405171394348145,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8872593950504126,
+      "grad_norm": 1.3399347066879272,
+      "learning_rate": 7.481572481572482e-05,
+      "loss": 0.780091667175293,
+      "step": 1030
+    },
+    {
+      "epoch": 1.9055912007332723,
+      "grad_norm": 1.2579443454742432,
+      "learning_rate": 7.358722358722359e-05,
+      "loss": 0.6868968486785889,
+      "step": 1040
+    },
+    {
+      "epoch": 1.923923006416132,
+      "grad_norm": 1.0092531442642212,
+      "learning_rate": 7.235872235872236e-05,
+      "loss": 0.742798137664795,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9422548120989918,
+      "grad_norm": 1.121690273284912,
+      "learning_rate": 7.113022113022113e-05,
+      "loss": 0.8035343170166016,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9605866177818516,
+      "grad_norm": 1.0780940055847168,
+      "learning_rate": 6.990171990171991e-05,
+      "loss": 0.7256640911102294,
+      "step": 1070
+    },
+    {
+      "epoch": 1.9789184234647113,
+      "grad_norm": 1.0335768461227417,
+      "learning_rate": 6.867321867321868e-05,
+      "loss": 0.751814889907837,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9972502291475709,
+      "grad_norm": 1.0326813459396362,
+      "learning_rate": 6.744471744471746e-05,
+      "loss": 0.781493854522705,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0146654445462877,
+      "grad_norm": 0.9365840554237366,
+      "learning_rate": 6.621621621621621e-05,
+      "loss": 0.6172435760498047,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0329972502291476,
+      "grad_norm": 1.0775729417800903,
+      "learning_rate": 6.498771498771498e-05,
+      "loss": 0.5551021575927735,
+      "step": 1110
+    },
+    {
+      "epoch": 2.0513290559120074,
+      "grad_norm": 1.1233711242675781,
+      "learning_rate": 6.375921375921376e-05,
+      "loss": 0.530482006072998,
+      "step": 1120
+    },
+    {
+      "epoch": 2.0696608615948673,
+      "grad_norm": 0.9685810208320618,
+      "learning_rate": 6.253071253071253e-05,
+      "loss": 0.5284864902496338,
+      "step": 1130
+    },
+    {
+      "epoch": 2.0879926672777267,
+      "grad_norm": 1.3673559427261353,
+      "learning_rate": 6.130221130221131e-05,
+      "loss": 0.5300433158874511,
+      "step": 1140
+    },
+    {
+      "epoch": 2.1063244729605866,
+      "grad_norm": 1.291156530380249,
+      "learning_rate": 6.0073710073710075e-05,
+      "loss": 0.5388914585113526,
+      "step": 1150
+    },
+    {
+      "epoch": 2.1246562786434464,
+      "grad_norm": 1.0860686302185059,
+      "learning_rate": 5.8845208845208844e-05,
+      "loss": 0.5599504947662354,
+      "step": 1160
+    },
+    {
+      "epoch": 2.1429880843263063,
+      "grad_norm": 1.2297484874725342,
+      "learning_rate": 5.761670761670762e-05,
+      "loss": 0.5693662643432618,
+      "step": 1170
+    },
+    {
+      "epoch": 2.1613198900091657,
+      "grad_norm": 1.3128403425216675,
+      "learning_rate": 5.638820638820639e-05,
+      "loss": 0.5087790012359619,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1796516956920255,
+      "grad_norm": 1.47864830493927,
+      "learning_rate": 5.515970515970517e-05,
+      "loss": 0.5520669460296631,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1979835013748854,
+      "grad_norm": 1.3533881902694702,
+      "learning_rate": 5.393120393120393e-05,
+      "loss": 0.5194924354553223,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2163153070577453,
+      "grad_norm": 1.0729988813400269,
+      "learning_rate": 5.27027027027027e-05,
+      "loss": 0.5386343955993652,
+      "step": 1210
+    },
+    {
+      "epoch": 2.234647112740605,
+      "grad_norm": 1.1851814985275269,
+      "learning_rate": 5.147420147420148e-05,
+      "loss": 0.5398934364318848,
+      "step": 1220
+    },
+    {
+      "epoch": 2.2529789184234645,
+      "grad_norm": 1.306754469871521,
+      "learning_rate": 5.024570024570024e-05,
+      "loss": 0.5412076473236084,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2713107241063244,
+      "grad_norm": 1.2561992406845093,
+      "learning_rate": 4.901719901719902e-05,
+      "loss": 0.555613899230957,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2896425297891843,
+      "grad_norm": 1.4935739040374756,
+      "learning_rate": 4.778869778869779e-05,
+      "loss": 0.560833215713501,
+      "step": 1250
+    },
+    {
+      "epoch": 2.307974335472044,
+      "grad_norm": 1.2064818143844604,
+      "learning_rate": 4.656019656019656e-05,
+      "loss": 0.5313505172729492,
+      "step": 1260
+    },
+    {
+      "epoch": 2.3263061411549035,
+      "grad_norm": 1.2250595092773438,
+      "learning_rate": 4.5331695331695335e-05,
+      "loss": 0.5530914306640625,
+      "step": 1270
+    },
+    {
+      "epoch": 2.3446379468377634,
+      "grad_norm": 1.249531865119934,
+      "learning_rate": 4.4103194103194104e-05,
+      "loss": 0.5281160831451416,
+      "step": 1280
+    },
+    {
+      "epoch": 2.3629697525206232,
+      "grad_norm": 1.1765642166137695,
+      "learning_rate": 4.287469287469288e-05,
+      "loss": 0.5416937351226807,
+      "step": 1290
+    },
+    {
+      "epoch": 2.381301558203483,
+      "grad_norm": 1.2973071336746216,
+      "learning_rate": 4.164619164619165e-05,
+      "loss": 0.5341888427734375,
+      "step": 1300
+    },
+    {
+      "epoch": 2.399633363886343,
+      "grad_norm": 1.3533828258514404,
+      "learning_rate": 4.0417690417690415e-05,
+      "loss": 0.5386404514312744,
+      "step": 1310
+    },
+    {
+      "epoch": 2.4179651695692024,
+      "grad_norm": 1.1323643922805786,
+      "learning_rate": 3.918918918918919e-05,
+      "loss": 0.5549521446228027,
+      "step": 1320
+    },
+    {
+      "epoch": 2.4362969752520622,
+      "grad_norm": 1.0967226028442383,
+      "learning_rate": 3.7960687960687965e-05,
+      "loss": 0.5668260097503662,
+      "step": 1330
+    },
+    {
+      "epoch": 2.454628780934922,
+      "grad_norm": 1.3874995708465576,
+      "learning_rate": 3.6732186732186734e-05,
+      "loss": 0.5530946254730225,
+      "step": 1340
+    },
+    {
+      "epoch": 2.472960586617782,
+      "grad_norm": 1.3139115571975708,
+      "learning_rate": 3.550368550368551e-05,
+      "loss": 0.544743013381958,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4912923923006414,
+      "grad_norm": 1.3629847764968872,
+      "learning_rate": 3.427518427518428e-05,
+      "loss": 0.5550421714782715,
+      "step": 1360
+    },
+    {
+      "epoch": 2.5096241979835012,
+      "grad_norm": 1.3279292583465576,
+      "learning_rate": 3.3046683046683045e-05,
+      "loss": 0.5361227035522461,
+      "step": 1370
+    },
+    {
+      "epoch": 2.527956003666361,
+      "grad_norm": 1.3736717700958252,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 0.5256178855895997,
+      "step": 1380
+    },
+    {
+      "epoch": 2.546287809349221,
+      "grad_norm": 1.2405906915664673,
+      "learning_rate": 3.058968058968059e-05,
+      "loss": 0.5551014900207519,
+      "step": 1390
+    },
+    {
+      "epoch": 2.564619615032081,
+      "grad_norm": 1.2711869478225708,
+      "learning_rate": 2.9361179361179364e-05,
+      "loss": 0.549025011062622,
+      "step": 1400
+    },
+    {
+      "epoch": 2.5829514207149407,
+      "grad_norm": 1.1510083675384521,
+      "learning_rate": 2.8132678132678135e-05,
+      "loss": 0.5108777046203613,
+      "step": 1410
+    },
+    {
+      "epoch": 2.6012832263978,
+      "grad_norm": 1.2585129737854004,
+      "learning_rate": 2.6904176904176904e-05,
+      "loss": 0.545832633972168,
+      "step": 1420
+    },
+    {
+      "epoch": 2.61961503208066,
+      "grad_norm": 1.2926920652389526,
+      "learning_rate": 2.5675675675675675e-05,
+      "loss": 0.531532621383667,
+      "step": 1430
+    },
+    {
+      "epoch": 2.63794683776352,
+      "grad_norm": 1.1816222667694092,
+      "learning_rate": 2.4447174447174447e-05,
+      "loss": 0.4899789333343506,
+      "step": 1440
+    },
+    {
+      "epoch": 2.656278643446379,
+      "grad_norm": 1.3441561460494995,
+      "learning_rate": 2.3218673218673222e-05,
+      "loss": 0.5534125804901123,
+      "step": 1450
+    },
+    {
+      "epoch": 2.674610449129239,
+      "grad_norm": 1.5367056131362915,
+      "learning_rate": 2.199017199017199e-05,
+      "loss": 0.5469470500946045,
+      "step": 1460
+    },
+    {
+      "epoch": 2.692942254812099,
+      "grad_norm": 1.292490005493164,
+      "learning_rate": 2.0761670761670762e-05,
+      "loss": 0.5418555259704589,
+      "step": 1470
+    },
+    {
+      "epoch": 2.711274060494959,
+      "grad_norm": 1.2457395792007446,
+      "learning_rate": 1.9533169533169534e-05,
+      "loss": 0.5272214889526368,
+      "step": 1480
+    },
+    {
+      "epoch": 2.7296058661778186,
+      "grad_norm": 1.3204960823059082,
+      "learning_rate": 1.8304668304668305e-05,
+      "loss": 0.5287877559661865,
+      "step": 1490
+    },
+    {
+      "epoch": 2.7479376718606785,
+      "grad_norm": 1.0838243961334229,
+      "learning_rate": 1.7076167076167077e-05,
+      "loss": 0.49266462326049804,
+      "step": 1500
+    },
+    {
+      "epoch": 2.766269477543538,
+      "grad_norm": 1.3524028062820435,
+      "learning_rate": 1.584766584766585e-05,
+      "loss": 0.534552526473999,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7846012832263978,
+      "grad_norm": 1.2434245347976685,
+      "learning_rate": 1.4619164619164619e-05,
+      "loss": 0.5303339004516602,
+      "step": 1520
+    },
+    {
+      "epoch": 2.8029330889092576,
+      "grad_norm": 1.4432783126831055,
+      "learning_rate": 1.339066339066339e-05,
+      "loss": 0.5432450771331787,
+      "step": 1530
+    },
+    {
+      "epoch": 2.8212648945921175,
+      "grad_norm": 1.372916340827942,
+      "learning_rate": 1.2162162162162164e-05,
+      "loss": 0.5449412345886231,
+      "step": 1540
+    },
+    {
+      "epoch": 2.839596700274977,
+      "grad_norm": 1.3015090227127075,
+      "learning_rate": 1.0933660933660935e-05,
+      "loss": 0.5642722129821778,
+      "step": 1550
+    },
+    {
+      "epoch": 2.8579285059578368,
+      "grad_norm": 1.434592366218567,
+      "learning_rate": 9.705159705159705e-06,
+      "loss": 0.5404855728149414,
+      "step": 1560
+    },
+    {
+      "epoch": 2.8762603116406966,
+      "grad_norm": 2.344008445739746,
+      "learning_rate": 8.476658476658477e-06,
+      "loss": 0.5066645622253418,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8945921173235565,
+      "grad_norm": 1.0202550888061523,
+      "learning_rate": 7.2481572481572485e-06,
+      "loss": 0.5348256587982178,
+      "step": 1580
+    },
+    {
+      "epoch": 2.9129239230064163,
+      "grad_norm": 1.2149248123168945,
+      "learning_rate": 6.019656019656019e-06,
+      "loss": 0.4903108596801758,
+      "step": 1590
+    },
+    {
+      "epoch": 2.9312557286892758,
+      "grad_norm": 1.5240399837493896,
+      "learning_rate": 4.791154791154792e-06,
+      "loss": 0.5296618461608886,
+      "step": 1600
+    },
+    {
+      "epoch": 2.9495875343721356,
+      "grad_norm": 1.4258157014846802,
+      "learning_rate": 3.562653562653563e-06,
+      "loss": 0.49115524291992185,
+      "step": 1610
+    },
+    {
+      "epoch": 2.9679193400549955,
+      "grad_norm": 1.1255574226379395,
+      "learning_rate": 2.3341523341523343e-06,
+      "loss": 0.5161442279815673,
+      "step": 1620
+    },
+    {
+      "epoch": 2.9862511457378553,
+      "grad_norm": 1.365963101387024,
+      "learning_rate": 1.1056511056511056e-06,
+      "loss": 0.5332399368286133,
+      "step": 1630
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1638,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 4.469692570628813e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1638/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85e9413c7636d9fff8558d114d2112dff5238aa624b3ebdad9a7bde187c0bf2
+size 5713

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- 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 0.18.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f8036c0ba5f313b73cd89593e6a7b013359ebaa8d06e562eb93fbcd952b4bf
+size 84972248

checkpoint-500/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc88863efebd2a57f93104421dc52326c2a03e9d5ea0e6de71727e82d4dd68ec
+size 43434405

checkpoint-500/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52255f5f510483729853e9c8db34e229d7de0649af4856c1ece43967c1b7f0bf
+size 1465

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343