Upload LoRA Adapter

.gitattributes

@@ -33,3 +33,7 @@ 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-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,93 @@
+---
+language:
+- en
+- hi
+- bn
+- ta
+- te
+- gu
+- kn
+- ml
+- mr
+- or
+- pa
+- ur
+- as
+- brx
+- doi
+- gom
+- kas
+- mai
+- mni
+- ne
+- sa
+- sat
+- sd
+license: apache-2.0
+base_model: Qwen/Qwen3-VL-4B-Instruct
+tags:
+- vision
+- multilingual
+- indic-languages
+- lora
+- translation
+- document-understanding
+- fine-tuned
+datasets:
+- ai4bharat/BPCC
+- ai4bharat/Pralekha
+- ai4bharat/indicdlp
+- lmms-lab/DocVQA
+pipeline_tag: image-text-to-text
+---
+
+# Sarvam-1-VL-4B-Instruct - LoRA Adapter
+
+## Model Description
+
+Fine-tuned vision-language model for Indic languages based on Qwen3-VL-4B-Instruct. This is the **LoRA adapter** that needs to be merged with the base model.
+
+## Training Details
+
+- **Base Model:** Qwen/Qwen3-VL-4B-Instruct
+- **Training Method:** LoRA (Rank 128, Alpha 256)
+- **Training Steps:** 2,000
+- **Training Time:** ~8.9 hours
+- **Final Loss:** 6.25
+- **Effective Batch Size:** 16
+
+## Datasets
+
+Trained on 4 datasets covering:
+- **Translation** (40%): BPCC - 22 Indic languages ↔ English
+- **Instruction Following** (20%): Pralekha - 11 language pairs
+- **Document Layout** (30%): IndicDLP - Document understanding
+- **Visual QA** (10%): DocVQA - Question answering
+
+## Supported Languages
+
+Assamese, Bengali, Bodo, Dogri, Gujarati, Hindi, Kannada, Kashmiri, Konkani, Maithili, Malayalam, Marathi, Manipuri, Nepali, Odia, Punjabi, Sanskrit, Santali, Sindhi, Tamil, Telugu, Urdu, English
+
+## Usage
+
+```python
+from unsloth import FastVisionModel
+
+model, tokenizer = FastVisionModel.from_pretrained(
+    "Qwen/Qwen3-VL-4B-Instruct",
+    load_in_4bit=True,
+)
+
+# Load LoRA adapter
+model.load_adapter("mashriram/Sarvam-1-VL-4B-Instruct")
+
+# Use for inference
+```
+
+## License
+
+Apache 2.0
+
+## Citation
+
+If you use this model, please cite the original Qwen3-VL paper and the datasets used.

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_vl.modeling_qwen3_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_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:c47252852003986fb27279b60c97484471343f06ad5a80d1c1e670c1d6d731e7
+size 1258394608

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_vl.modeling_qwen3_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_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 sha256:8213db70d73ffce571b56fc27bd07a8b554b0446427486d4155aada684d27f24
+size 1258394608

checkpoint-1000/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473ac045af7f8a7283fd70b5bc8a580e88df3dd51043deccfdf08d323c586a86
+size 537334341

checkpoint-1000/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba19b3e96dd5de11496b64869771cfd85846e934713126a99458f90e1230e6b
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b1a1646b68187cbdd7d177c46067eb2219e6803b28c49bd72cb9963adb10c7
+size 1465

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af560c5e5807192776a9f72a0ea33c9331816d9c59af61e02bdf766f8a2a97fb
+size 11422922

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 53.94755554199219,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 26.115,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 11.3975191116333,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 12.5099,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 13.352740287780762,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 11.5997,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.22486400604248,
+      "learning_rate": 0.000117,
+      "loss": 11.0894,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 6.599037170410156,
+      "learning_rate": 0.000147,
+      "loss": 10.2273,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 12.686646461486816,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 9.5605,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 9.526597023010254,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 9.3932,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.044199466705322,
+      "learning_rate": 0.000237,
+      "loss": 9.8737,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 7.538876056671143,
+      "learning_rate": 0.000267,
+      "loss": 10.0198,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 10.840659141540527,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 10.4149,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 9.758448600769043,
+      "learning_rate": 0.00029857894736842104,
+      "loss": 10.4368,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.318181037902832,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 8.3996,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 13.915440559387207,
+      "learning_rate": 0.0002954210526315789,
+      "loss": 8.8513,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 9.88852310180664,
+      "learning_rate": 0.00029384210526315783,
+      "loss": 9.4877,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.668610095977783,
+      "learning_rate": 0.00029226315789473685,
+      "loss": 8.1337,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 29.449243545532227,
+      "learning_rate": 0.00029068421052631577,
+      "loss": 9.273,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 6.467507839202881,
+      "learning_rate": 0.00028910526315789473,
+      "loss": 8.8419,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 19.543132781982422,
+      "learning_rate": 0.00028752631578947364,
+      "loss": 8.3971,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 13.156903266906738,
+      "learning_rate": 0.0002859473684210526,
+      "loss": 9.5291,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.885478019714355,
+      "learning_rate": 0.0002843684210526315,
+      "loss": 7.7914,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 11.896453857421875,
+      "learning_rate": 0.0002827894736842105,
+      "loss": 9.8313,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.915274620056152,
+      "learning_rate": 0.00028121052631578945,
+      "loss": 8.8191,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 7.6407856941223145,
+      "learning_rate": 0.0002796315789473684,
+      "loss": 6.8206,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 12.518260955810547,
+      "learning_rate": 0.00027805263157894733,
+      "loss": 8.636,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 11.432880401611328,
+      "learning_rate": 0.0002764736842105263,
+      "loss": 7.1465,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 8.826226234436035,
+      "learning_rate": 0.0002748947368421052,
+      "loss": 7.1283,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.593420505523682,
+      "learning_rate": 0.0002733157894736842,
+      "loss": 7.6144,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.628589630126953,
+      "learning_rate": 0.00027173684210526314,
+      "loss": 7.6943,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 56.44780349731445,
+      "learning_rate": 0.0002701578947368421,
+      "loss": 9.6015,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 10.86131763458252,
+      "learning_rate": 0.000268578947368421,
+      "loss": 8.1787,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 20.813161849975586,
+      "learning_rate": 0.000267,
+      "loss": 7.7316,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 55.12717056274414,
+      "learning_rate": 0.0002654210526315789,
+      "loss": 7.5353,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 10.096261024475098,
+      "learning_rate": 0.00026384210526315786,
+      "loss": 7.3492,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.356606483459473,
+      "learning_rate": 0.00026226315789473683,
+      "loss": 7.0889,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 9.701301574707031,
+      "learning_rate": 0.00026068421052631574,
+      "loss": 6.9922,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.172627925872803,
+      "learning_rate": 0.0002591052631578947,
+      "loss": 7.3025,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 10.241826057434082,
+      "learning_rate": 0.00025752631578947367,
+      "loss": 6.6179,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 6.638657569885254,
+      "learning_rate": 0.00025594736842105264,
+      "loss": 8.2226,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 11.518302917480469,
+      "learning_rate": 0.00025436842105263155,
+      "loss": 6.3692,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.524480819702148,
+      "learning_rate": 0.0002527894736842105,
+      "loss": 8.131,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 10.748291969299316,
+      "learning_rate": 0.00025121052631578943,
+      "loss": 8.4304,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 12.697006225585938,
+      "learning_rate": 0.0002496315789473684,
+      "loss": 6.512,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 7.661844730377197,
+      "learning_rate": 0.00024805263157894736,
+      "loss": 7.6016,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 11.028185844421387,
+      "learning_rate": 0.0002464736842105263,
+      "loss": 6.144,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 10.651000022888184,
+      "learning_rate": 0.00024489473684210524,
+      "loss": 5.9826,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 9.832489013671875,
+      "learning_rate": 0.00024331578947368418,
+      "loss": 6.3437,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 11.302276611328125,
+      "learning_rate": 0.00024173684210526312,
+      "loss": 6.6576,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.565763473510742,
+      "learning_rate": 0.00024015789473684208,
+      "loss": 5.7402,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 11.632065773010254,
+      "learning_rate": 0.00023857894736842105,
+      "loss": 6.4514,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.037233352661133,
+      "learning_rate": 0.000237,
+      "loss": 6.7493,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 13.482627868652344,
+      "learning_rate": 0.00023542105263157893,
+      "loss": 5.6632,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.946409225463867,
+      "learning_rate": 0.00023384210526315787,
+      "loss": 6.1602,
+      "step": 520
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 10.61089038848877,
+      "learning_rate": 0.0002322631578947368,
+      "loss": 7.3882,
+      "step": 530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 11.012020111083984,
+      "learning_rate": 0.00023068421052631577,
+      "loss": 6.7398,
+      "step": 540
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 8.845987319946289,
+      "learning_rate": 0.0002291052631578947,
+      "loss": 7.0205,
+      "step": 550
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.243446350097656,
+      "learning_rate": 0.00022752631578947368,
+      "loss": 5.535,
+      "step": 560
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 6.976236820220947,
+      "learning_rate": 0.00022594736842105261,
+      "loss": 6.3107,
+      "step": 570
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 11.282112121582031,
+      "learning_rate": 0.00022436842105263155,
+      "loss": 6.4338,
+      "step": 580
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 12.507245063781738,
+      "learning_rate": 0.00022278947368421052,
+      "loss": 6.2523,
+      "step": 590
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9.16707992553711,
+      "learning_rate": 0.00022121052631578946,
+      "loss": 5.1103,
+      "step": 600
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 6.331278324127197,
+      "learning_rate": 0.0002196315789473684,
+      "loss": 6.561,
+      "step": 610
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 9.432160377502441,
+      "learning_rate": 0.00021805263157894734,
+      "loss": 7.2152,
+      "step": 620
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 10.932201385498047,
+      "learning_rate": 0.0002164736842105263,
+      "loss": 6.3478,
+      "step": 630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.170024871826172,
+      "learning_rate": 0.00021489473684210524,
+      "loss": 7.1665,
+      "step": 640
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 12.445239067077637,
+      "learning_rate": 0.0002133157894736842,
+      "loss": 5.9956,
+      "step": 650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 12.555913925170898,
+      "learning_rate": 0.00021173684210526315,
+      "loss": 6.7039,
+      "step": 660
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 10.212902069091797,
+      "learning_rate": 0.00021015789473684208,
+      "loss": 6.3633,
+      "step": 670
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.006694793701172,
+      "learning_rate": 0.00020857894736842102,
+      "loss": 7.2624,
+      "step": 680
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 9.131366729736328,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 6.1719,
+      "step": 690
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 15.563868522644043,
+      "learning_rate": 0.00020542105263157893,
+      "loss": 5.8857,
+      "step": 700
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 9.895964622497559,
+      "learning_rate": 0.0002038421052631579,
+      "loss": 6.6569,
+      "step": 710
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.801018714904785,
+      "learning_rate": 0.00020226315789473683,
+      "loss": 6.4785,
+      "step": 720
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 8.72229290008545,
+      "learning_rate": 0.00020068421052631577,
+      "loss": 5.3763,
+      "step": 730
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 8.640310287475586,
+      "learning_rate": 0.0001991052631578947,
+      "loss": 5.7271,
+      "step": 740
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 13.315818786621094,
+      "learning_rate": 0.00019752631578947365,
+      "loss": 6.2416,
+      "step": 750
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.7069995403289795,
+      "learning_rate": 0.00019594736842105264,
+      "loss": 6.0895,
+      "step": 760
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 11.817346572875977,
+      "learning_rate": 0.00019436842105263158,
+      "loss": 6.4639,
+      "step": 770
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.935391426086426,
+      "learning_rate": 0.00019278947368421052,
+      "loss": 6.9848,
+      "step": 780
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 4.711079120635986,
+      "learning_rate": 0.00019121052631578946,
+      "loss": 5.5295,
+      "step": 790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8401641845703125,
+      "learning_rate": 0.0001896315789473684,
+      "loss": 5.6227,
+      "step": 800
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 10.418253898620605,
+      "learning_rate": 0.00018805263157894734,
+      "loss": 6.1825,
+      "step": 810
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 7.468499660491943,
+      "learning_rate": 0.00018647368421052628,
+      "loss": 6.9214,
+      "step": 820
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 8.36676025390625,
+      "learning_rate": 0.00018489473684210527,
+      "loss": 5.6362,
+      "step": 830
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.0770392417907715,
+      "learning_rate": 0.0001833157894736842,
+      "loss": 6.571,
+      "step": 840
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 15.624354362487793,
+      "learning_rate": 0.00018173684210526315,
+      "loss": 7.6336,
+      "step": 850
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 15.162675857543945,
+      "learning_rate": 0.0001801578947368421,
+      "loss": 6.7955,
+      "step": 860
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 9.743088722229004,
+      "learning_rate": 0.00017857894736842103,
+      "loss": 5.4599,
+      "step": 870
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.73693561553955,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 6.0081,
+      "step": 880
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 5.465635776519775,
+      "learning_rate": 0.0001754210526315789,
+      "loss": 7.0656,
+      "step": 890
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.205047369003296,
+      "learning_rate": 0.0001738421052631579,
+      "loss": 5.9353,
+      "step": 900
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 9.32066535949707,
+      "learning_rate": 0.00017226315789473684,
+      "loss": 7.1441,
+      "step": 910
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 12.949300765991211,
+      "learning_rate": 0.00017068421052631578,
+      "loss": 6.4508,
+      "step": 920
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 8.177252769470215,
+      "learning_rate": 0.00016910526315789471,
+      "loss": 6.0847,
+      "step": 930
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.945886135101318,
+      "learning_rate": 0.00016752631578947365,
+      "loss": 5.7599,
+      "step": 940
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.926685810089111,
+      "learning_rate": 0.00016594736842105262,
+      "loss": 7.261,
+      "step": 950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.434368133544922,
+      "learning_rate": 0.00016436842105263156,
+      "loss": 6.7638,
+      "step": 960
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 9.134793281555176,
+      "learning_rate": 0.00016278947368421052,
+      "loss": 7.0167,
+      "step": 970
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 10.619525909423828,
+      "learning_rate": 0.00016121052631578946,
+      "loss": 6.9734,
+      "step": 980
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 10.44985580444336,
+      "learning_rate": 0.0001596315789473684,
+      "loss": 5.5139,
+      "step": 990
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 9.743708610534668,
+      "learning_rate": 0.00015805263157894734,
+      "loss": 6.2291,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2642853988974387e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9913fb8beabab987d7476f77493deae7d2a6ad5f13e62f85ecebf447bbb181fc
+size 6225

checkpoint-1000/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

checkpoint-1500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_vl.modeling_qwen3_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_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:c89a1f3878d11f9d11e89920be7cf10c5dcec5ad1ca5b0646fc0d1ccfa705aa7
+size 1258394608

checkpoint-1500/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af22c5513e9295d51ae3c1f6211b35d6524ecf5e28ab317d76f072ea7a5bb9e
+size 537334341

checkpoint-1500/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495803c2d2aa114a47baba14c0e9045cc449ab80828a8185938ddf1a57696727
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b91a0f737d278cd2a9aa1b218b9ccf1117af8f6516a48553819369a4618abc6
+size 1465

checkpoint-1500/special_tokens_map.json

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

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af560c5e5807192776a9f72a0ea33c9331816d9c59af61e02bdf766f8a2a97fb
+size 11422922

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.75,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 53.94755554199219,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 26.115,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 11.3975191116333,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 12.5099,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 13.352740287780762,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 11.5997,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.22486400604248,
+      "learning_rate": 0.000117,
+      "loss": 11.0894,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 6.599037170410156,
+      "learning_rate": 0.000147,
+      "loss": 10.2273,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 12.686646461486816,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 9.5605,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 9.526597023010254,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 9.3932,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 7.044199466705322,
+      "learning_rate": 0.000237,
+      "loss": 9.8737,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 7.538876056671143,
+      "learning_rate": 0.000267,
+      "loss": 10.0198,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 10.840659141540527,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 10.4149,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 9.758448600769043,
+      "learning_rate": 0.00029857894736842104,
+      "loss": 10.4368,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.318181037902832,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 8.3996,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 13.915440559387207,
+      "learning_rate": 0.0002954210526315789,
+      "loss": 8.8513,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 9.88852310180664,
+      "learning_rate": 0.00029384210526315783,
+      "loss": 9.4877,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.668610095977783,
+      "learning_rate": 0.00029226315789473685,
+      "loss": 8.1337,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 29.449243545532227,
+      "learning_rate": 0.00029068421052631577,
+      "loss": 9.273,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 6.467507839202881,
+      "learning_rate": 0.00028910526315789473,
+      "loss": 8.8419,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 19.543132781982422,
+      "learning_rate": 0.00028752631578947364,
+      "loss": 8.3971,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 13.156903266906738,
+      "learning_rate": 0.0002859473684210526,
+      "loss": 9.5291,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.885478019714355,
+      "learning_rate": 0.0002843684210526315,
+      "loss": 7.7914,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 11.896453857421875,
+      "learning_rate": 0.0002827894736842105,
+      "loss": 9.8313,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.915274620056152,
+      "learning_rate": 0.00028121052631578945,
+      "loss": 8.8191,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 7.6407856941223145,
+      "learning_rate": 0.0002796315789473684,
+      "loss": 6.8206,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 12.518260955810547,
+      "learning_rate": 0.00027805263157894733,
+      "loss": 8.636,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 11.432880401611328,
+      "learning_rate": 0.0002764736842105263,
+      "loss": 7.1465,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 8.826226234436035,
+      "learning_rate": 0.0002748947368421052,
+      "loss": 7.1283,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.593420505523682,
+      "learning_rate": 0.0002733157894736842,
+      "loss": 7.6144,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.628589630126953,
+      "learning_rate": 0.00027173684210526314,
+      "loss": 7.6943,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 56.44780349731445,
+      "learning_rate": 0.0002701578947368421,
+      "loss": 9.6015,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 10.86131763458252,
+      "learning_rate": 0.000268578947368421,
+      "loss": 8.1787,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 20.813161849975586,
+      "learning_rate": 0.000267,
+      "loss": 7.7316,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 55.12717056274414,
+      "learning_rate": 0.0002654210526315789,
+      "loss": 7.5353,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 10.096261024475098,
+      "learning_rate": 0.00026384210526315786,
+      "loss": 7.3492,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.356606483459473,
+      "learning_rate": 0.00026226315789473683,
+      "loss": 7.0889,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 9.701301574707031,
+      "learning_rate": 0.00026068421052631574,
+      "loss": 6.9922,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.172627925872803,
+      "learning_rate": 0.0002591052631578947,
+      "loss": 7.3025,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 10.241826057434082,
+      "learning_rate": 0.00025752631578947367,
+      "loss": 6.6179,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 6.638657569885254,
+      "learning_rate": 0.00025594736842105264,
+      "loss": 8.2226,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 11.518302917480469,
+      "learning_rate": 0.00025436842105263155,
+      "loss": 6.3692,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.524480819702148,
+      "learning_rate": 0.0002527894736842105,
+      "loss": 8.131,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 10.748291969299316,
+      "learning_rate": 0.00025121052631578943,
+      "loss": 8.4304,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 12.697006225585938,
+      "learning_rate": 0.0002496315789473684,
+      "loss": 6.512,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 7.661844730377197,
+      "learning_rate": 0.00024805263157894736,
+      "loss": 7.6016,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 11.028185844421387,
+      "learning_rate": 0.0002464736842105263,
+      "loss": 6.144,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 10.651000022888184,
+      "learning_rate": 0.00024489473684210524,
+      "loss": 5.9826,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 9.832489013671875,
+      "learning_rate": 0.00024331578947368418,
+      "loss": 6.3437,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 11.302276611328125,
+      "learning_rate": 0.00024173684210526312,
+      "loss": 6.6576,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.565763473510742,
+      "learning_rate": 0.00024015789473684208,
+      "loss": 5.7402,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 11.632065773010254,
+      "learning_rate": 0.00023857894736842105,
+      "loss": 6.4514,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.037233352661133,
+      "learning_rate": 0.000237,
+      "loss": 6.7493,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 13.482627868652344,
+      "learning_rate": 0.00023542105263157893,
+      "loss": 5.6632,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.946409225463867,
+      "learning_rate": 0.00023384210526315787,
+      "loss": 6.1602,
+      "step": 520
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 10.61089038848877,
+      "learning_rate": 0.0002322631578947368,
+      "loss": 7.3882,
+      "step": 530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 11.012020111083984,
+      "learning_rate": 0.00023068421052631577,
+      "loss": 6.7398,
+      "step": 540
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 8.845987319946289,
+      "learning_rate": 0.0002291052631578947,
+      "loss": 7.0205,
+      "step": 550
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.243446350097656,
+      "learning_rate": 0.00022752631578947368,
+      "loss": 5.535,
+      "step": 560
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 6.976236820220947,
+      "learning_rate": 0.00022594736842105261,
+      "loss": 6.3107,
+      "step": 570
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 11.282112121582031,
+      "learning_rate": 0.00022436842105263155,
+      "loss": 6.4338,
+      "step": 580
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 12.507245063781738,
+      "learning_rate": 0.00022278947368421052,
+      "loss": 6.2523,
+      "step": 590
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 9.16707992553711,
+      "learning_rate": 0.00022121052631578946,
+      "loss": 5.1103,
+      "step": 600
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 6.331278324127197,
+      "learning_rate": 0.0002196315789473684,
+      "loss": 6.561,
+      "step": 610
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 9.432160377502441,
+      "learning_rate": 0.00021805263157894734,
+      "loss": 7.2152,
+      "step": 620
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 10.932201385498047,
+      "learning_rate": 0.0002164736842105263,
+      "loss": 6.3478,
+      "step": 630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.170024871826172,
+      "learning_rate": 0.00021489473684210524,
+      "loss": 7.1665,
+      "step": 640
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 12.445239067077637,
+      "learning_rate": 0.0002133157894736842,
+      "loss": 5.9956,
+      "step": 650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 12.555913925170898,
+      "learning_rate": 0.00021173684210526315,
+      "loss": 6.7039,
+      "step": 660
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 10.212902069091797,
+      "learning_rate": 0.00021015789473684208,
+      "loss": 6.3633,
+      "step": 670
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.006694793701172,
+      "learning_rate": 0.00020857894736842102,
+      "loss": 7.2624,
+      "step": 680
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 9.131366729736328,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 6.1719,
+      "step": 690
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 15.563868522644043,
+      "learning_rate": 0.00020542105263157893,
+      "loss": 5.8857,
+      "step": 700
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 9.895964622497559,
+      "learning_rate": 0.0002038421052631579,
+      "loss": 6.6569,
+      "step": 710
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.801018714904785,
+      "learning_rate": 0.00020226315789473683,
+      "loss": 6.4785,
+      "step": 720
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 8.72229290008545,
+      "learning_rate": 0.00020068421052631577,
+      "loss": 5.3763,
+      "step": 730
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 8.640310287475586,
+      "learning_rate": 0.0001991052631578947,
+      "loss": 5.7271,
+      "step": 740
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 13.315818786621094,
+      "learning_rate": 0.00019752631578947365,
+      "loss": 6.2416,
+      "step": 750
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.7069995403289795,
+      "learning_rate": 0.00019594736842105264,
+      "loss": 6.0895,
+      "step": 760
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 11.817346572875977,
+      "learning_rate": 0.00019436842105263158,
+      "loss": 6.4639,
+      "step": 770
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.935391426086426,
+      "learning_rate": 0.00019278947368421052,
+      "loss": 6.9848,
+      "step": 780
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 4.711079120635986,
+      "learning_rate": 0.00019121052631578946,
+      "loss": 5.5295,
+      "step": 790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8401641845703125,
+      "learning_rate": 0.0001896315789473684,
+      "loss": 5.6227,
+      "step": 800
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 10.418253898620605,
+      "learning_rate": 0.00018805263157894734,
+      "loss": 6.1825,
+      "step": 810
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 7.468499660491943,
+      "learning_rate": 0.00018647368421052628,
+      "loss": 6.9214,
+      "step": 820
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 8.36676025390625,
+      "learning_rate": 0.00018489473684210527,
+      "loss": 5.6362,
+      "step": 830
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.0770392417907715,
+      "learning_rate": 0.0001833157894736842,
+      "loss": 6.571,
+      "step": 840
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 15.624354362487793,
+      "learning_rate": 0.00018173684210526315,
+      "loss": 7.6336,
+      "step": 850
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 15.162675857543945,
+      "learning_rate": 0.0001801578947368421,
+      "loss": 6.7955,
+      "step": 860
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 9.743088722229004,
+      "learning_rate": 0.00017857894736842103,
+      "loss": 5.4599,
+      "step": 870
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.73693561553955,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 6.0081,
+      "step": 880
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 5.465635776519775,
+      "learning_rate": 0.0001754210526315789,
+      "loss": 7.0656,
+      "step": 890
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.205047369003296,
+      "learning_rate": 0.0001738421052631579,
+      "loss": 5.9353,
+      "step": 900
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 9.32066535949707,
+      "learning_rate": 0.00017226315789473684,
+      "loss": 7.1441,
+      "step": 910
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 12.949300765991211,
+      "learning_rate": 0.00017068421052631578,
+      "loss": 6.4508,
+      "step": 920
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 8.177252769470215,
+      "learning_rate": 0.00016910526315789471,
+      "loss": 6.0847,
+      "step": 930
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.945886135101318,
+      "learning_rate": 0.00016752631578947365,
+      "loss": 5.7599,
+      "step": 940
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.926685810089111,
+      "learning_rate": 0.00016594736842105262,
+      "loss": 7.261,
+      "step": 950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.434368133544922,
+      "learning_rate": 0.00016436842105263156,
+      "loss": 6.7638,
+      "step": 960
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 9.134793281555176,
+      "learning_rate": 0.00016278947368421052,
+      "loss": 7.0167,
+      "step": 970
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 10.619525909423828,
+      "learning_rate": 0.00016121052631578946,
+      "loss": 6.9734,
+      "step": 980
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 10.44985580444336,
+      "learning_rate": 0.0001596315789473684,
+      "loss": 5.5139,
+      "step": 990
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 9.743708610534668,
+      "learning_rate": 0.00015805263157894734,
+      "loss": 6.2291,
+      "step": 1000
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 4.079898834228516,
+      "learning_rate": 0.0001564736842105263,
+      "loss": 5.7743,
+      "step": 1010
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 15.110444068908691,
+      "learning_rate": 0.00015489473684210525,
+      "loss": 6.4432,
+      "step": 1020
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 9.87468433380127,
+      "learning_rate": 0.00015331578947368419,
+      "loss": 6.4737,
+      "step": 1030
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.487386703491211,
+      "learning_rate": 0.00015173684210526315,
+      "loss": 6.8038,
+      "step": 1040
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 13.89244270324707,
+      "learning_rate": 0.0001501578947368421,
+      "loss": 5.861,
+      "step": 1050
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.0271711349487305,
+      "learning_rate": 0.00014857894736842103,
+      "loss": 6.0973,
+      "step": 1060
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 13.944864273071289,
+      "learning_rate": 0.000147,
+      "loss": 7.2229,
+      "step": 1070
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 11.327110290527344,
+      "learning_rate": 0.00014542105263157893,
+      "loss": 5.645,
+      "step": 1080
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 11.51246452331543,
+      "learning_rate": 0.00014384210526315787,
+      "loss": 4.5969,
+      "step": 1090
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.9547624588012695,
+      "learning_rate": 0.00014226315789473684,
+      "loss": 5.3187,
+      "step": 1100
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 4.5951995849609375,
+      "learning_rate": 0.00014068421052631578,
+      "loss": 5.4452,
+      "step": 1110
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 7.044490337371826,
+      "learning_rate": 0.00013910526315789474,
+      "loss": 5.8196,
+      "step": 1120
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 5.957108497619629,
+      "learning_rate": 0.00013752631578947368,
+      "loss": 6.1073,
+      "step": 1130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 8.093610763549805,
+      "learning_rate": 0.00013594736842105262,
+      "loss": 5.5731,
+      "step": 1140
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 11.078412055969238,
+      "learning_rate": 0.0001343684210526316,
+      "loss": 6.7678,
+      "step": 1150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.7904133796691895,
+      "learning_rate": 0.00013278947368421053,
+      "loss": 5.5891,
+      "step": 1160
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 6.466845512390137,
+      "learning_rate": 0.00013121052631578947,
+      "loss": 5.8488,
+      "step": 1170
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 6.9840922355651855,
+      "learning_rate": 0.0001296315789473684,
+      "loss": 6.2465,
+      "step": 1180
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 9.122848510742188,
+      "learning_rate": 0.00012805263157894737,
+      "loss": 7.0481,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.476122856140137,
+      "learning_rate": 0.0001264736842105263,
+      "loss": 6.6299,
+      "step": 1200
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 4.769547462463379,
+      "learning_rate": 0.00012489473684210525,
+      "loss": 4.4049,
+      "step": 1210
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 11.937010765075684,
+      "learning_rate": 0.00012331578947368421,
+      "loss": 5.7009,
+      "step": 1220
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 5.662721633911133,
+      "learning_rate": 0.00012173684210526315,
+      "loss": 6.8112,
+      "step": 1230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 8.745271682739258,
+      "learning_rate": 0.00012015789473684209,
+      "loss": 5.956,
+      "step": 1240
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 11.694770812988281,
+      "learning_rate": 0.00011857894736842103,
+      "loss": 5.635,
+      "step": 1250
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 12.576383590698242,
+      "learning_rate": 0.000117,
+      "loss": 6.6435,
+      "step": 1260
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 11.117959976196289,
+      "learning_rate": 0.00011542105263157894,
+      "loss": 5.6533,
+      "step": 1270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.086808681488037,
+      "learning_rate": 0.00011384210526315788,
+      "loss": 6.147,
+      "step": 1280
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 5.031323432922363,
+      "learning_rate": 0.00011226315789473684,
+      "loss": 6.0361,
+      "step": 1290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 10.029598236083984,
+      "learning_rate": 0.00011068421052631578,
+      "loss": 6.1938,
+      "step": 1300
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 9.102313041687012,
+      "learning_rate": 0.00010910526315789472,
+      "loss": 5.7654,
+      "step": 1310
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 8.28632926940918,
+      "learning_rate": 0.00010752631578947369,
+      "loss": 6.2164,
+      "step": 1320
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 7.555177688598633,
+      "learning_rate": 0.00010594736842105262,
+      "loss": 6.2955,
+      "step": 1330
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 7.858890533447266,
+      "learning_rate": 0.00010436842105263156,
+      "loss": 5.4419,
+      "step": 1340
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 9.47352123260498,
+      "learning_rate": 0.00010278947368421052,
+      "loss": 5.878,
+      "step": 1350
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.735633373260498,
+      "learning_rate": 0.00010121052631578947,
+      "loss": 5.2803,
+      "step": 1360
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 5.728670597076416,
+      "learning_rate": 9.963157894736841e-05,
+      "loss": 5.9334,
+      "step": 1370
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 9.471277236938477,
+      "learning_rate": 9.805263157894736e-05,
+      "loss": 6.172,
+      "step": 1380
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 10.102209091186523,
+      "learning_rate": 9.647368421052631e-05,
+      "loss": 5.4889,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 8.452800750732422,
+      "learning_rate": 9.489473684210525e-05,
+      "loss": 6.0632,
+      "step": 1400
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 6.8025898933410645,
+      "learning_rate": 9.33157894736842e-05,
+      "loss": 5.6116,
+      "step": 1410
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 6.024433612823486,
+      "learning_rate": 9.173684210526314e-05,
+      "loss": 5.6093,
+      "step": 1420
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 6.203394889831543,
+      "learning_rate": 9.01578947368421e-05,
+      "loss": 4.9379,
+      "step": 1430
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.7379953861236572,
+      "learning_rate": 8.857894736842105e-05,
+      "loss": 5.1323,
+      "step": 1440
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 11.372900009155273,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 4.727,
+      "step": 1450
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 9.120123863220215,
+      "learning_rate": 8.542105263157894e-05,
+      "loss": 5.387,
+      "step": 1460
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 6.839603424072266,
+      "learning_rate": 8.384210526315789e-05,
+      "loss": 5.794,
+      "step": 1470
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 9.580937385559082,
+      "learning_rate": 8.226315789473683e-05,
+      "loss": 6.2431,
+      "step": 1480
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 6.182724952697754,
+      "learning_rate": 8.068421052631578e-05,
+      "loss": 5.729,
+      "step": 1490
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 11.157108306884766,
+      "learning_rate": 7.910526315789474e-05,
+      "loss": 5.7552,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.866970968076585e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9913fb8beabab987d7476f77493deae7d2a6ad5f13e62f85ecebf447bbb181fc
+size 6225

checkpoint-1500/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

checkpoint-2000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-2000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3VLForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_vl.modeling_qwen3_vl",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47252852003986fb27279b60c97484471343f06ad5a80d1c1e670c1d6d731e7
+size 1258394608

checkpoint-2000/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff756efdc8b8415a96c5912e0d9ad0431d4f9ffa52bc974f713cfe15cf127c5
+size 537334341

checkpoint-2000/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "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
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b64ebdf87f5e7a444aaa05d9c87f2ef9dffc2627e7343a974b4e36571bb1871
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e994df2db06cf21b94a8d5eb2d1526ded950d85b50f20125124d25b8720c6a
+size 1465