Upload folder using huggingface_hub

.gitattributes

@@ -174,3 +174,9 @@ not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit_aug_v0/fold_5/che
 not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit_aug_v0/fold_5/checkpoint-287/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit_aug_v0/fold_5/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit_aug_v0/fold_5/model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_1/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_2/checkpoint-110/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_3/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_4/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_5/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/README.md

@@ -0,0 +1,59 @@
+---
+base_model: unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit
+library_name: transformers
+model_name: fold_0
+tags:
+- generated_from_trainer
+- sft
+- unsloth
+- trl
+licence: license
+---
+
+# Model Card for fold_0
+
+This model is a fine-tuned version of [unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 4.57.3
+- Pytorch: 2.9.1
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-8B-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 0.18.0

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/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-8B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "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": true
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38e01f33f55fa5fc7408c4448481fee7920e06504b18739c988d0f8eeae4f2f
+size 821656768

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/added_tokens.json

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

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/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 %}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5935ccddf364748b8a4b16f7c9ffb2e5ef3b354c69871d2b351a60ed9e0a07f
+size 355225733

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b15d59b7d2f507771b26ca44b1603b8cdd22ee0992f3217d7e17b763986855
+size 14645

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b1ef7366c6c30d53737b169bbacb6895371d849f595f92403a403289227abf
+size 1465

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/special_tokens_map.json

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

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f3cad7255d8b75d5ceb46c9ee639981b038f1a97c1633437d0e2dad2e7823e
+size 11422923

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/trainer_state.json

@@ -0,0 +1,750 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.72,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 46.222320556640625,
+      "learning_rate": 0.0,
+      "loss": 3.7386,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 43.76449203491211,
+      "learning_rate": 1e-05,
+      "loss": 3.7519,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 36.74058532714844,
+      "learning_rate": 2e-05,
+      "loss": 3.2753,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.926800727844238,
+      "learning_rate": 3e-05,
+      "loss": 2.4082,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.70433521270752,
+      "learning_rate": 4e-05,
+      "loss": 1.8808,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.313986778259277,
+      "learning_rate": 5e-05,
+      "loss": 1.5675,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.439535617828369,
+      "learning_rate": 4.99921047320825e-05,
+      "loss": 1.2076,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.118196964263916,
+      "learning_rate": 4.996842391515044e-05,
+      "loss": 0.9051,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.740301609039307,
+      "learning_rate": 4.992897250651535e-05,
+      "loss": 0.6327,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.944699287414551,
+      "learning_rate": 4.987377542453251e-05,
+      "loss": 0.394,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7546186447143555,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.2702,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.2921996116638184,
+      "learning_rate": 4.971629361844785e-05,
+      "loss": 0.2078,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.328129291534424,
+      "learning_rate": 4.9614108363230135e-05,
+      "loss": 0.1636,
+      "step": 13
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.1561111211776733,
+      "learning_rate": 4.949637630960617e-05,
+      "loss": 0.1487,
+      "step": 14
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.5206750631332397,
+      "learning_rate": 4.9363171819664434e-05,
+      "loss": 0.1351,
+      "step": 15
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.1434717178344727,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.1093,
+      "step": 16
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.078804850578308,
+      "learning_rate": 4.905069178965215e-05,
+      "loss": 0.0896,
+      "step": 17
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.3894654512405396,
+      "learning_rate": 4.887161361866608e-05,
+      "loss": 0.0841,
+      "step": 18
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.0231529474258423,
+      "learning_rate": 4.867745762486861e-05,
+      "loss": 0.0813,
+      "step": 19
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.6194835901260376,
+      "learning_rate": 4.846834644134686e-05,
+      "loss": 0.0826,
+      "step": 20
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 1.1622838973999023,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.0765,
+      "step": 21
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.8758455514907837,
+      "learning_rate": 4.800579618414676e-05,
+      "loss": 0.0721,
+      "step": 22
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.993780791759491,
+      "learning_rate": 4.775264926712489e-05,
+      "loss": 0.0695,
+      "step": 23
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7119081020355225,
+      "learning_rate": 4.7485131289159276e-05,
+      "loss": 0.0537,
+      "step": 24
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7918580770492554,
+      "learning_rate": 4.720341122033862e-05,
+      "loss": 0.0575,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1798608303070068,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.6417698264122009,
+      "learning_rate": 4.659808542982088e-05,
+      "loss": 0.0484,
+      "step": 27
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.5201259851455688,
+      "learning_rate": 4.6274862044867304e-05,
+      "loss": 0.0485,
+      "step": 28
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7435464859008789,
+      "learning_rate": 4.593820100105355e-05,
+      "loss": 0.0547,
+      "step": 29
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.7111960649490356,
+      "learning_rate": 4.558831494071069e-05,
+      "loss": 0.0568,
+      "step": 30
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.7623787522315979,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.0582,
+      "step": 31
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5909068584442139,
+      "learning_rate": 4.484975996619589e-05,
+      "loss": 0.049,
+      "step": 32
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6174893379211426,
+      "learning_rate": 4.4461557539175594e-05,
+      "loss": 0.0475,
+      "step": 33
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.6622814536094666,
+      "learning_rate": 4.40610627752862e-05,
+      "loss": 0.0497,
+      "step": 34
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.6719883680343628,
+      "learning_rate": 4.3648528635604556e-05,
+      "loss": 0.0485,
+      "step": 35
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5630459785461426,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.0444,
+      "step": 36
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6010923385620117,
+      "learning_rate": 4.278839193023214e-05,
+      "loss": 0.0504,
+      "step": 37
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.6897675395011902,
+      "learning_rate": 4.234133264532012e-05,
+      "loss": 0.0482,
+      "step": 38
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6990064382553101,
+      "learning_rate": 4.188332020302561e-05,
+      "loss": 0.0357,
+      "step": 39
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.6793434619903564,
+      "learning_rate": 4.1414643893823914e-05,
+      "loss": 0.0422,
+      "step": 40
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.4914472997188568,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.0419,
+      "step": 41
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 0.6658065319061279,
+      "learning_rate": 4.044649032725836e-05,
+      "loss": 0.0395,
+      "step": 42
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.5577124357223511,
+      "learning_rate": 3.9947624576437975e-05,
+      "loss": 0.0413,
+      "step": 43
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.6956123113632202,
+      "learning_rate": 3.943931758555669e-05,
+      "loss": 0.0444,
+      "step": 44
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.48270997405052185,
+      "learning_rate": 3.8921890412204705e-05,
+      "loss": 0.0342,
+      "step": 45
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.5660143494606018,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.0411,
+      "step": 46
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.8836619257926941,
+      "learning_rate": 3.786098834453766e-05,
+      "loss": 0.0442,
+      "step": 47
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 0.43791842460632324,
+      "learning_rate": 3.731818353870729e-05,
+      "loss": 0.033,
+      "step": 48
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.5275256633758545,
+      "learning_rate": 3.6767598304133324e-05,
+      "loss": 0.0396,
+      "step": 49
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.5512613654136658,
+      "learning_rate": 3.6209580402250815e-05,
+      "loss": 0.0392,
+      "step": 50
+    },
+    {
+      "epoch": 3.88,
+      "eval_loss": 0.07899235934019089,
+      "eval_runtime": 137.9005,
+      "eval_samples_per_second": 0.856,
+      "eval_steps_per_second": 0.218,
+      "step": 50
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.5676145553588867,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 0.04,
+      "step": 51
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.835232138633728,
+      "learning_rate": 3.507266089284157e-05,
+      "loss": 0.0494,
+      "step": 52
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.5702734589576721,
+      "learning_rate": 3.4494477388045035e-05,
+      "loss": 0.0377,
+      "step": 53
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.6397337913513184,
+      "learning_rate": 3.3910296967831266e-05,
+      "loss": 0.0361,
+      "step": 54
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.4872088134288788,
+      "learning_rate": 3.332048861307467e-05,
+      "loss": 0.0394,
+      "step": 55
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.6632542014122009,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0366,
+      "step": 56
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.45951083302497864,
+      "learning_rate": 3.21254815617494e-05,
+      "loss": 0.0329,
+      "step": 57
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.5678207874298096,
+      "learning_rate": 3.152103765724743e-05,
+      "loss": 0.0391,
+      "step": 58
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.5014293789863586,
+      "learning_rate": 3.091247492559312e-05,
+      "loss": 0.0369,
+      "step": 59
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.48377713561058044,
+      "learning_rate": 3.0300177748051373e-05,
+      "loss": 0.0332,
+      "step": 60
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.5142446160316467,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 0.0325,
+      "step": 61
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.4637300670146942,
+      "learning_rate": 2.9065929129872094e-05,
+      "loss": 0.0355,
+      "step": 62
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.3928743302822113,
+      "learning_rate": 2.844475726711595e-05,
+      "loss": 0.0336,
+      "step": 63
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.4277777075767517,
+      "learning_rate": 2.782140962183704e-05,
+      "loss": 0.0373,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6836524605751038,
+      "learning_rate": 2.7196279913768584e-05,
+      "loss": 0.0357,
+      "step": 65
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 0.44082269072532654,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 0.46267983317375183,
+      "learning_rate": 2.594225456674837e-05,
+      "loss": 0.0333,
+      "step": 67
+    },
+    {
+      "epoch": 5.24,
+      "grad_norm": 0.45492178201675415,
+      "learning_rate": 2.531415099708382e-05,
+      "loss": 0.031,
+      "step": 68
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 0.4461764693260193,
+      "learning_rate": 2.4685849002916183e-05,
+      "loss": 0.0318,
+      "step": 69
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.5425416231155396,
+      "learning_rate": 2.4057745433251635e-05,
+      "loss": 0.028,
+      "step": 70
+    },
+    {
+      "epoch": 5.48,
+      "grad_norm": 0.46646848320961,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 0.0289,
+      "step": 71
+    },
+    {
+      "epoch": 5.5600000000000005,
+      "grad_norm": 0.4980866312980652,
+      "learning_rate": 2.280372008623142e-05,
+      "loss": 0.0321,
+      "step": 72
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 0.5860579013824463,
+      "learning_rate": 2.217859037816296e-05,
+      "loss": 0.0352,
+      "step": 73
+    },
+    {
+      "epoch": 5.72,
+      "grad_norm": 0.5109958648681641,
+      "learning_rate": 2.155524273288405e-05,
+      "loss": 0.0332,
+      "step": 74
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.5045474171638489,
+      "learning_rate": 2.0934070870127912e-05,
+      "loss": 0.0345,
+      "step": 75
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 0.4226977229118347,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 0.0293,
+      "step": 76
+    },
+    {
+      "epoch": 5.96,
+      "grad_norm": 0.6118741035461426,
+      "learning_rate": 1.969982225194864e-05,
+      "loss": 0.0345,
+      "step": 77
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5884000062942505,
+      "learning_rate": 1.908752507440689e-05,
+      "loss": 0.0256,
+      "step": 78
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 0.4448150396347046,
+      "learning_rate": 1.8478962342752583e-05,
+      "loss": 0.0268,
+      "step": 79
+    },
+    {
+      "epoch": 6.16,
+      "grad_norm": 0.5885403752326965,
+      "learning_rate": 1.7874518438250597e-05,
+      "loss": 0.0305,
+      "step": 80
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.437648743391037,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0249,
+      "step": 81
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.4628402888774872,
+      "learning_rate": 1.6679511386925337e-05,
+      "loss": 0.0306,
+      "step": 82
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.43142837285995483,
+      "learning_rate": 1.6089703032168733e-05,
+      "loss": 0.0259,
+      "step": 83
+    },
+    {
+      "epoch": 6.48,
+      "grad_norm": 0.5359015464782715,
+      "learning_rate": 1.5505522611954975e-05,
+      "loss": 0.0293,
+      "step": 84
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 0.4640922248363495,
+      "learning_rate": 1.4927339107158437e-05,
+      "loss": 0.026,
+      "step": 85
+    },
+    {
+      "epoch": 6.64,
+      "grad_norm": 0.5524070262908936,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 0.0294,
+      "step": 86
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 0.5265147686004639,
+      "learning_rate": 1.3790419597749199e-05,
+      "loss": 0.0301,
+      "step": 87
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.4640660285949707,
+      "learning_rate": 1.3232401695866687e-05,
+      "loss": 0.0253,
+      "step": 88
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.4505196213722229,
+      "learning_rate": 1.2681816461292715e-05,
+      "loss": 0.0242,
+      "step": 89
+    },
+    {
+      "epoch": 6.96,
+      "grad_norm": 0.4053988754749298,
+      "learning_rate": 1.2139011655462337e-05,
+      "loss": 0.0235,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8708481192588806,
+      "learning_rate": 1.1604330125525079e-05,
+      "loss": 0.0286,
+      "step": 91
+    },
+    {
+      "epoch": 7.08,
+      "grad_norm": 0.624153733253479,
+      "learning_rate": 1.107810958779531e-05,
+      "loss": 0.0213,
+      "step": 92
+    },
+    {
+      "epoch": 7.16,
+      "grad_norm": 0.48327621817588806,
+      "learning_rate": 1.0560682414443315e-05,
+      "loss": 0.0216,
+      "step": 93
+    },
+    {
+      "epoch": 7.24,
+      "grad_norm": 0.4970317780971527,
+      "learning_rate": 1.0052375423562038e-05,
+      "loss": 0.0233,
+      "step": 94
+    },
+    {
+      "epoch": 7.32,
+      "grad_norm": 0.43698397278785706,
+      "learning_rate": 9.553509672741645e-06,
+      "loss": 0.022,
+      "step": 95
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 0.5406357645988464,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 0.0234,
+      "step": 96
+    },
+    {
+      "epoch": 7.48,
+      "grad_norm": 0.47867053747177124,
+      "learning_rate": 8.585356106176094e-06,
+      "loss": 0.0221,
+      "step": 97
+    },
+    {
+      "epoch": 7.5600000000000005,
+      "grad_norm": 0.5372248291969299,
+      "learning_rate": 8.116679796974388e-06,
+      "loss": 0.0247,
+      "step": 98
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5064783692359924,
+      "learning_rate": 7.65866735467988e-06,
+      "loss": 0.0264,
+      "step": 99
+    },
+    {
+      "epoch": 7.72,
+      "grad_norm": 0.4860106110572815,
+      "learning_rate": 7.211608069767867e-06,
+      "loss": 0.0224,
+      "step": 100
+    },
+    {
+      "epoch": 7.72,
+      "eval_loss": 0.08931571990251541,
+      "eval_runtime": 133.0545,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.225,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8596986106414106e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ca8101e3dfcacdd990d5e60693232a28be62fabd58c940c63b5e3635ffdd57
+size 6417

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-100/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"
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-8B-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 0.18.0

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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-8B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "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": true
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e13fe5b0f2509f4a4bf6d5e580acd549dbaca6ebc8b7e7db530fc8d7aa6eb85
+size 821656768

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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 %}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b1074746b6f452b5e3db406854d5682774f90a0b63c852976c7287e23f51ce
+size 355225733

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f3e429ffab9361eb588f03657ab12e499db270bb2234e5408b66a7fc8b7a88
+size 14645

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1723a2a28d652f6c208711c02b0bd6d63c9bd2bcf166b51f5fe78301acdcd6
+size 1465

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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
+  }
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f3cad7255d8b75d5ceb46c9ee639981b038f1a97c1633437d0e2dad2e7823e
+size 11422923

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/trainer_state.json

@@ -0,0 +1,960 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 50,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 46.222320556640625,
+      "learning_rate": 0.0,
+      "loss": 3.7386,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 43.76449203491211,
+      "learning_rate": 1e-05,
+      "loss": 3.7519,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 36.74058532714844,
+      "learning_rate": 2e-05,
+      "loss": 3.2753,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.926800727844238,
+      "learning_rate": 3e-05,
+      "loss": 2.4082,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.70433521270752,
+      "learning_rate": 4e-05,
+      "loss": 1.8808,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.313986778259277,
+      "learning_rate": 5e-05,
+      "loss": 1.5675,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.439535617828369,
+      "learning_rate": 4.99921047320825e-05,
+      "loss": 1.2076,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.118196964263916,
+      "learning_rate": 4.996842391515044e-05,
+      "loss": 0.9051,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.740301609039307,
+      "learning_rate": 4.992897250651535e-05,
+      "loss": 0.6327,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.944699287414551,
+      "learning_rate": 4.987377542453251e-05,
+      "loss": 0.394,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7546186447143555,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.2702,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.2921996116638184,
+      "learning_rate": 4.971629361844785e-05,
+      "loss": 0.2078,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.328129291534424,
+      "learning_rate": 4.9614108363230135e-05,
+      "loss": 0.1636,
+      "step": 13
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.1561111211776733,
+      "learning_rate": 4.949637630960617e-05,
+      "loss": 0.1487,
+      "step": 14
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.5206750631332397,
+      "learning_rate": 4.9363171819664434e-05,
+      "loss": 0.1351,
+      "step": 15
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.1434717178344727,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.1093,
+      "step": 16
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.078804850578308,
+      "learning_rate": 4.905069178965215e-05,
+      "loss": 0.0896,
+      "step": 17
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.3894654512405396,
+      "learning_rate": 4.887161361866608e-05,
+      "loss": 0.0841,
+      "step": 18
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.0231529474258423,
+      "learning_rate": 4.867745762486861e-05,
+      "loss": 0.0813,
+      "step": 19
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.6194835901260376,
+      "learning_rate": 4.846834644134686e-05,
+      "loss": 0.0826,
+      "step": 20
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 1.1622838973999023,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.0765,
+      "step": 21
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.8758455514907837,
+      "learning_rate": 4.800579618414676e-05,
+      "loss": 0.0721,
+      "step": 22
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.993780791759491,
+      "learning_rate": 4.775264926712489e-05,
+      "loss": 0.0695,
+      "step": 23
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7119081020355225,
+      "learning_rate": 4.7485131289159276e-05,
+      "loss": 0.0537,
+      "step": 24
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7918580770492554,
+      "learning_rate": 4.720341122033862e-05,
+      "loss": 0.0575,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1798608303070068,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.6417698264122009,
+      "learning_rate": 4.659808542982088e-05,
+      "loss": 0.0484,
+      "step": 27
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.5201259851455688,
+      "learning_rate": 4.6274862044867304e-05,
+      "loss": 0.0485,
+      "step": 28
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7435464859008789,
+      "learning_rate": 4.593820100105355e-05,
+      "loss": 0.0547,
+      "step": 29
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.7111960649490356,
+      "learning_rate": 4.558831494071069e-05,
+      "loss": 0.0568,
+      "step": 30
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.7623787522315979,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.0582,
+      "step": 31
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5909068584442139,
+      "learning_rate": 4.484975996619589e-05,
+      "loss": 0.049,
+      "step": 32
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6174893379211426,
+      "learning_rate": 4.4461557539175594e-05,
+      "loss": 0.0475,
+      "step": 33
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.6622814536094666,
+      "learning_rate": 4.40610627752862e-05,
+      "loss": 0.0497,
+      "step": 34
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.6719883680343628,
+      "learning_rate": 4.3648528635604556e-05,
+      "loss": 0.0485,
+      "step": 35
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5630459785461426,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.0444,
+      "step": 36
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6010923385620117,
+      "learning_rate": 4.278839193023214e-05,
+      "loss": 0.0504,
+      "step": 37
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.6897675395011902,
+      "learning_rate": 4.234133264532012e-05,
+      "loss": 0.0482,
+      "step": 38
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6990064382553101,
+      "learning_rate": 4.188332020302561e-05,
+      "loss": 0.0357,
+      "step": 39
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.6793434619903564,
+      "learning_rate": 4.1414643893823914e-05,
+      "loss": 0.0422,
+      "step": 40
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.4914472997188568,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.0419,
+      "step": 41
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 0.6658065319061279,
+      "learning_rate": 4.044649032725836e-05,
+      "loss": 0.0395,
+      "step": 42
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.5577124357223511,
+      "learning_rate": 3.9947624576437975e-05,
+      "loss": 0.0413,
+      "step": 43
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.6956123113632202,
+      "learning_rate": 3.943931758555669e-05,
+      "loss": 0.0444,
+      "step": 44
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.48270997405052185,
+      "learning_rate": 3.8921890412204705e-05,
+      "loss": 0.0342,
+      "step": 45
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.5660143494606018,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.0411,
+      "step": 46
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.8836619257926941,
+      "learning_rate": 3.786098834453766e-05,
+      "loss": 0.0442,
+      "step": 47
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 0.43791842460632324,
+      "learning_rate": 3.731818353870729e-05,
+      "loss": 0.033,
+      "step": 48
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.5275256633758545,
+      "learning_rate": 3.6767598304133324e-05,
+      "loss": 0.0396,
+      "step": 49
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.5512613654136658,
+      "learning_rate": 3.6209580402250815e-05,
+      "loss": 0.0392,
+      "step": 50
+    },
+    {
+      "epoch": 3.88,
+      "eval_loss": 0.07899235934019089,
+      "eval_runtime": 137.9005,
+      "eval_samples_per_second": 0.856,
+      "eval_steps_per_second": 0.218,
+      "step": 50
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.5676145553588867,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 0.04,
+      "step": 51
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.835232138633728,
+      "learning_rate": 3.507266089284157e-05,
+      "loss": 0.0494,
+      "step": 52
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.5702734589576721,
+      "learning_rate": 3.4494477388045035e-05,
+      "loss": 0.0377,
+      "step": 53
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.6397337913513184,
+      "learning_rate": 3.3910296967831266e-05,
+      "loss": 0.0361,
+      "step": 54
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.4872088134288788,
+      "learning_rate": 3.332048861307467e-05,
+      "loss": 0.0394,
+      "step": 55
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.6632542014122009,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.0366,
+      "step": 56
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.45951083302497864,
+      "learning_rate": 3.21254815617494e-05,
+      "loss": 0.0329,
+      "step": 57
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.5678207874298096,
+      "learning_rate": 3.152103765724743e-05,
+      "loss": 0.0391,
+      "step": 58
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.5014293789863586,
+      "learning_rate": 3.091247492559312e-05,
+      "loss": 0.0369,
+      "step": 59
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.48377713561058044,
+      "learning_rate": 3.0300177748051373e-05,
+      "loss": 0.0332,
+      "step": 60
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.5142446160316467,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 0.0325,
+      "step": 61
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.4637300670146942,
+      "learning_rate": 2.9065929129872094e-05,
+      "loss": 0.0355,
+      "step": 62
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.3928743302822113,
+      "learning_rate": 2.844475726711595e-05,
+      "loss": 0.0336,
+      "step": 63
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.4277777075767517,
+      "learning_rate": 2.782140962183704e-05,
+      "loss": 0.0373,
+      "step": 64
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6836524605751038,
+      "learning_rate": 2.7196279913768584e-05,
+      "loss": 0.0357,
+      "step": 65
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 0.44082269072532654,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 0.0336,
+      "step": 66
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 0.46267983317375183,
+      "learning_rate": 2.594225456674837e-05,
+      "loss": 0.0333,
+      "step": 67
+    },
+    {
+      "epoch": 5.24,
+      "grad_norm": 0.45492178201675415,
+      "learning_rate": 2.531415099708382e-05,
+      "loss": 0.031,
+      "step": 68
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 0.4461764693260193,
+      "learning_rate": 2.4685849002916183e-05,
+      "loss": 0.0318,
+      "step": 69
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.5425416231155396,
+      "learning_rate": 2.4057745433251635e-05,
+      "loss": 0.028,
+      "step": 70
+    },
+    {
+      "epoch": 5.48,
+      "grad_norm": 0.46646848320961,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 0.0289,
+      "step": 71
+    },
+    {
+      "epoch": 5.5600000000000005,
+      "grad_norm": 0.4980866312980652,
+      "learning_rate": 2.280372008623142e-05,
+      "loss": 0.0321,
+      "step": 72
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 0.5860579013824463,
+      "learning_rate": 2.217859037816296e-05,
+      "loss": 0.0352,
+      "step": 73
+    },
+    {
+      "epoch": 5.72,
+      "grad_norm": 0.5109958648681641,
+      "learning_rate": 2.155524273288405e-05,
+      "loss": 0.0332,
+      "step": 74
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.5045474171638489,
+      "learning_rate": 2.0934070870127912e-05,
+      "loss": 0.0345,
+      "step": 75
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 0.4226977229118347,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 0.0293,
+      "step": 76
+    },
+    {
+      "epoch": 5.96,
+      "grad_norm": 0.6118741035461426,
+      "learning_rate": 1.969982225194864e-05,
+      "loss": 0.0345,
+      "step": 77
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5884000062942505,
+      "learning_rate": 1.908752507440689e-05,
+      "loss": 0.0256,
+      "step": 78
+    },
+    {
+      "epoch": 6.08,
+      "grad_norm": 0.4448150396347046,
+      "learning_rate": 1.8478962342752583e-05,
+      "loss": 0.0268,
+      "step": 79
+    },
+    {
+      "epoch": 6.16,
+      "grad_norm": 0.5885403752326965,
+      "learning_rate": 1.7874518438250597e-05,
+      "loss": 0.0305,
+      "step": 80
+    },
+    {
+      "epoch": 6.24,
+      "grad_norm": 0.437648743391037,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0249,
+      "step": 81
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.4628402888774872,
+      "learning_rate": 1.6679511386925337e-05,
+      "loss": 0.0306,
+      "step": 82
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.43142837285995483,
+      "learning_rate": 1.6089703032168733e-05,
+      "loss": 0.0259,
+      "step": 83
+    },
+    {
+      "epoch": 6.48,
+      "grad_norm": 0.5359015464782715,
+      "learning_rate": 1.5505522611954975e-05,
+      "loss": 0.0293,
+      "step": 84
+    },
+    {
+      "epoch": 6.5600000000000005,
+      "grad_norm": 0.4640922248363495,
+      "learning_rate": 1.4927339107158437e-05,
+      "loss": 0.026,
+      "step": 85
+    },
+    {
+      "epoch": 6.64,
+      "grad_norm": 0.5524070262908936,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 0.0294,
+      "step": 86
+    },
+    {
+      "epoch": 6.72,
+      "grad_norm": 0.5265147686004639,
+      "learning_rate": 1.3790419597749199e-05,
+      "loss": 0.0301,
+      "step": 87
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.4640660285949707,
+      "learning_rate": 1.3232401695866687e-05,
+      "loss": 0.0253,
+      "step": 88
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.4505196213722229,
+      "learning_rate": 1.2681816461292715e-05,
+      "loss": 0.0242,
+      "step": 89
+    },
+    {
+      "epoch": 6.96,
+      "grad_norm": 0.4053988754749298,
+      "learning_rate": 1.2139011655462337e-05,
+      "loss": 0.0235,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8708481192588806,
+      "learning_rate": 1.1604330125525079e-05,
+      "loss": 0.0286,
+      "step": 91
+    },
+    {
+      "epoch": 7.08,
+      "grad_norm": 0.624153733253479,
+      "learning_rate": 1.107810958779531e-05,
+      "loss": 0.0213,
+      "step": 92
+    },
+    {
+      "epoch": 7.16,
+      "grad_norm": 0.48327621817588806,
+      "learning_rate": 1.0560682414443315e-05,
+      "loss": 0.0216,
+      "step": 93
+    },
+    {
+      "epoch": 7.24,
+      "grad_norm": 0.4970317780971527,
+      "learning_rate": 1.0052375423562038e-05,
+      "loss": 0.0233,
+      "step": 94
+    },
+    {
+      "epoch": 7.32,
+      "grad_norm": 0.43698397278785706,
+      "learning_rate": 9.553509672741645e-06,
+      "loss": 0.022,
+      "step": 95
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 0.5406357645988464,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 0.0234,
+      "step": 96
+    },
+    {
+      "epoch": 7.48,
+      "grad_norm": 0.47867053747177124,
+      "learning_rate": 8.585356106176094e-06,
+      "loss": 0.0221,
+      "step": 97
+    },
+    {
+      "epoch": 7.5600000000000005,
+      "grad_norm": 0.5372248291969299,
+      "learning_rate": 8.116679796974388e-06,
+      "loss": 0.0247,
+      "step": 98
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.5064783692359924,
+      "learning_rate": 7.65866735467988e-06,
+      "loss": 0.0264,
+      "step": 99
+    },
+    {
+      "epoch": 7.72,
+      "grad_norm": 0.4860106110572815,
+      "learning_rate": 7.211608069767867e-06,
+      "loss": 0.0224,
+      "step": 100
+    },
+    {
+      "epoch": 7.72,
+      "eval_loss": 0.08931571990251541,
+      "eval_runtime": 133.0545,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.225,
+      "step": 100
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.48181092739105225,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 0.0242,
+      "step": 101
+    },
+    {
+      "epoch": 7.88,
+      "grad_norm": 0.5411723852157593,
+      "learning_rate": 6.3514713643954475e-06,
+      "loss": 0.0256,
+      "step": 102
+    },
+    {
+      "epoch": 7.96,
+      "grad_norm": 0.5460256338119507,
+      "learning_rate": 5.9389372247138e-06,
+      "loss": 0.0266,
+      "step": 103
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8071214556694031,
+      "learning_rate": 5.538442460824417e-06,
+      "loss": 0.0248,
+      "step": 104
+    },
+    {
+      "epoch": 8.08,
+      "grad_norm": 0.35192567110061646,
+      "learning_rate": 5.150240033804116e-06,
+      "loss": 0.019,
+      "step": 105
+    },
+    {
+      "epoch": 8.16,
+      "grad_norm": 0.40415850281715393,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0181,
+      "step": 106
+    },
+    {
+      "epoch": 8.24,
+      "grad_norm": 0.34627479314804077,
+      "learning_rate": 4.411685059289314e-06,
+      "loss": 0.0168,
+      "step": 107
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 0.4153834879398346,
+      "learning_rate": 4.061798998946459e-06,
+      "loss": 0.02,
+      "step": 108
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 0.4776570200920105,
+      "learning_rate": 3.725137955132707e-06,
+      "loss": 0.0204,
+      "step": 109
+    },
+    {
+      "epoch": 8.48,
+      "grad_norm": 0.447558730840683,
+      "learning_rate": 3.4019145701791184e-06,
+      "loss": 0.0228,
+      "step": 110
+    },
+    {
+      "epoch": 8.56,
+      "grad_norm": 0.4290669858455658,
+      "learning_rate": 3.092332998903416e-06,
+      "loss": 0.0211,
+      "step": 111
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 0.5055780410766602,
+      "learning_rate": 2.7965887796613884e-06,
+      "loss": 0.0241,
+      "step": 112
+    },
+    {
+      "epoch": 8.72,
+      "grad_norm": 0.4641125500202179,
+      "learning_rate": 2.514868710840723e-06,
+      "loss": 0.0215,
+      "step": 113
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.46760281920433044,
+      "learning_rate": 2.2473507328751086e-06,
+      "loss": 0.0211,
+      "step": 114
+    },
+    {
+      "epoch": 8.88,
+      "grad_norm": 0.5904353857040405,
+      "learning_rate": 1.9942038158532407e-06,
+      "loss": 0.0209,
+      "step": 115
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.3934815227985382,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 0.0207,
+      "step": 116
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6042241454124451,
+      "learning_rate": 1.5316535586531483e-06,
+      "loss": 0.0172,
+      "step": 117
+    },
+    {
+      "epoch": 9.08,
+      "grad_norm": 0.4118458330631256,
+      "learning_rate": 1.3225423751313942e-06,
+      "loss": 0.0187,
+      "step": 118
+    },
+    {
+      "epoch": 9.16,
+      "grad_norm": 0.46107548475265503,
+      "learning_rate": 1.1283863813339263e-06,
+      "loss": 0.0174,
+      "step": 119
+    },
+    {
+      "epoch": 9.24,
+      "grad_norm": 0.43782806396484375,
+      "learning_rate": 9.493082103478517e-07,
+      "loss": 0.0196,
+      "step": 120
+    },
+    {
+      "epoch": 9.32,
+      "grad_norm": 0.343911737203598,
+      "learning_rate": 7.854209717842231e-07,
+      "loss": 0.017,
+      "step": 121
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 0.4319242537021637,
+      "learning_rate": 6.368281803355691e-07,
+      "loss": 0.0169,
+      "step": 122
+    },
+    {
+      "epoch": 9.48,
+      "grad_norm": 0.41077643632888794,
+      "learning_rate": 5.036236903938285e-07,
+      "loss": 0.0199,
+      "step": 123
+    },
+    {
+      "epoch": 9.56,
+      "grad_norm": 0.518122136592865,
+      "learning_rate": 3.8589163676986674e-07,
+      "loss": 0.0235,
+      "step": 124
+    },
+    {
+      "epoch": 9.64,
+      "grad_norm": 0.41007891297340393,
+      "learning_rate": 2.8370638155215123e-07,
+      "loss": 0.019,
+      "step": 125
+    },
+    {
+      "epoch": 9.72,
+      "grad_norm": 0.40567460656166077,
+      "learning_rate": 1.9713246713805588e-07,
+      "loss": 0.0195,
+      "step": 126
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.45314908027648926,
+      "learning_rate": 1.2622457546749567e-07,
+      "loss": 0.022,
+      "step": 127
+    },
+    {
+      "epoch": 9.88,
+      "grad_norm": 0.4579121470451355,
+      "learning_rate": 7.102749348465165e-08,
+      "loss": 0.0191,
+      "step": 128
+    },
+    {
+      "epoch": 9.96,
+      "grad_norm": 0.40803587436676025,
+      "learning_rate": 3.157608484956332e-08,
+      "loss": 0.0192,
+      "step": 129
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5823314785957336,
+      "learning_rate": 7.895267917501504e-09,
+      "loss": 0.0132,
+      "step": 130
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.708476866992332e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ca8101e3dfcacdd990d5e60693232a28be62fabd58c940c63b5e3635ffdd57
+size 6417

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-130/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"
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-VL-8B-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 0.18.0

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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-8B-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "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": true
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11120992b491a04ccd2a4d2641de535599c37b9529fd97e284ac2cc1c6ea349c
+size 821656768

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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 %}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b40902873f2cd6ef0113802f8148bec9a984faaa2373939bd9c791f61f2b9a
+size 355225733

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89645f9f6a2a8823b334e0748e4f5ea683a27b3d02632f0a241397db55d82fad
+size 14645

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bdda34d0c74b4cdb40256da93a380b3cbf6d118eea8dffdc60a1970307254b
+size 1465

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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
+  }
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f3cad7255d8b75d5ceb46c9ee639981b038f1a97c1633437d0e2dad2e7823e
+size 11422923

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/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
+}

not_used_in_demo/unsloth_Qwen3-VL-8B-Instruct-unsloth-bnb-4bit/fold_0/checkpoint-50/trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.88,
+  "eval_steps": 50,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 46.222320556640625,
+      "learning_rate": 0.0,
+      "loss": 3.7386,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 43.76449203491211,
+      "learning_rate": 1e-05,
+      "loss": 3.7519,
+      "step": 2
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 36.74058532714844,
+      "learning_rate": 2e-05,
+      "loss": 3.2753,
+      "step": 3
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.926800727844238,
+      "learning_rate": 3e-05,
+      "loss": 2.4082,
+      "step": 4
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.70433521270752,
+      "learning_rate": 4e-05,
+      "loss": 1.8808,
+      "step": 5
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.313986778259277,
+      "learning_rate": 5e-05,
+      "loss": 1.5675,
+      "step": 6
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.439535617828369,
+      "learning_rate": 4.99921047320825e-05,
+      "loss": 1.2076,
+      "step": 7
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.118196964263916,
+      "learning_rate": 4.996842391515044e-05,
+      "loss": 0.9051,
+      "step": 8
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.740301609039307,
+      "learning_rate": 4.992897250651535e-05,
+      "loss": 0.6327,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.944699287414551,
+      "learning_rate": 4.987377542453251e-05,
+      "loss": 0.394,
+      "step": 10
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.7546186447143555,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.2702,
+      "step": 11
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.2921996116638184,
+      "learning_rate": 4.971629361844785e-05,
+      "loss": 0.2078,
+      "step": 12
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.328129291534424,
+      "learning_rate": 4.9614108363230135e-05,
+      "loss": 0.1636,
+      "step": 13
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.1561111211776733,
+      "learning_rate": 4.949637630960617e-05,
+      "loss": 0.1487,
+      "step": 14
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.5206750631332397,
+      "learning_rate": 4.9363171819664434e-05,
+      "loss": 0.1351,
+      "step": 15
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.1434717178344727,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.1093,
+      "step": 16
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.078804850578308,
+      "learning_rate": 4.905069178965215e-05,
+      "loss": 0.0896,
+      "step": 17
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.3894654512405396,
+      "learning_rate": 4.887161361866608e-05,
+      "loss": 0.0841,
+      "step": 18
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.0231529474258423,
+      "learning_rate": 4.867745762486861e-05,
+      "loss": 0.0813,
+      "step": 19
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.6194835901260376,
+      "learning_rate": 4.846834644134686e-05,
+      "loss": 0.0826,
+      "step": 20
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 1.1622838973999023,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.0765,
+      "step": 21
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.8758455514907837,
+      "learning_rate": 4.800579618414676e-05,
+      "loss": 0.0721,
+      "step": 22
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.993780791759491,
+      "learning_rate": 4.775264926712489e-05,
+      "loss": 0.0695,
+      "step": 23
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.7119081020355225,
+      "learning_rate": 4.7485131289159276e-05,
+      "loss": 0.0537,
+      "step": 24
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7918580770492554,
+      "learning_rate": 4.720341122033862e-05,
+      "loss": 0.0575,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1798608303070068,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.6417698264122009,
+      "learning_rate": 4.659808542982088e-05,
+      "loss": 0.0484,
+      "step": 27
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.5201259851455688,
+      "learning_rate": 4.6274862044867304e-05,
+      "loss": 0.0485,
+      "step": 28
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7435464859008789,
+      "learning_rate": 4.593820100105355e-05,
+      "loss": 0.0547,
+      "step": 29
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.7111960649490356,
+      "learning_rate": 4.558831494071069e-05,
+      "loss": 0.0568,
+      "step": 30
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.7623787522315979,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.0582,
+      "step": 31
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5909068584442139,
+      "learning_rate": 4.484975996619589e-05,
+      "loss": 0.049,
+      "step": 32
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6174893379211426,
+      "learning_rate": 4.4461557539175594e-05,
+      "loss": 0.0475,
+      "step": 33
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.6622814536094666,
+      "learning_rate": 4.40610627752862e-05,
+      "loss": 0.0497,
+      "step": 34
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.6719883680343628,
+      "learning_rate": 4.3648528635604556e-05,
+      "loss": 0.0485,
+      "step": 35
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5630459785461426,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.0444,
+      "step": 36
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6010923385620117,
+      "learning_rate": 4.278839193023214e-05,
+      "loss": 0.0504,
+      "step": 37
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.6897675395011902,
+      "learning_rate": 4.234133264532012e-05,
+      "loss": 0.0482,
+      "step": 38
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6990064382553101,
+      "learning_rate": 4.188332020302561e-05,
+      "loss": 0.0357,
+      "step": 39
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.6793434619903564,
+      "learning_rate": 4.1414643893823914e-05,
+      "loss": 0.0422,
+      "step": 40
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.4914472997188568,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.0419,
+      "step": 41
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 0.6658065319061279,
+      "learning_rate": 4.044649032725836e-05,
+      "loss": 0.0395,
+      "step": 42
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.5577124357223511,
+      "learning_rate": 3.9947624576437975e-05,
+      "loss": 0.0413,
+      "step": 43
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.6956123113632202,
+      "learning_rate": 3.943931758555669e-05,
+      "loss": 0.0444,
+      "step": 44
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.48270997405052185,
+      "learning_rate": 3.8921890412204705e-05,
+      "loss": 0.0342,
+      "step": 45
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.5660143494606018,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.0411,
+      "step": 46
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.8836619257926941,
+      "learning_rate": 3.786098834453766e-05,
+      "loss": 0.0442,
+      "step": 47
+    },
+    {
+      "epoch": 3.7199999999999998,
+      "grad_norm": 0.43791842460632324,
+      "learning_rate": 3.731818353870729e-05,
+      "loss": 0.033,
+      "step": 48
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.5275256633758545,
+      "learning_rate": 3.6767598304133324e-05,
+      "loss": 0.0396,
+      "step": 49
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.5512613654136658,
+      "learning_rate": 3.6209580402250815e-05,
+      "loss": 0.0392,
+      "step": 50
+    },
+    {
+      "epoch": 3.88,
+      "eval_loss": 0.07899235934019089,
+      "eval_runtime": 137.9005,
+      "eval_samples_per_second": 0.856,
+      "eval_steps_per_second": 0.218,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.44478369965581e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}