Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1063/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1063/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1063/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1063/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5472bbad318419ebf3b830cb9423f10bf194768289606ec1bfe02a4ed3496330
+size 755018656

checkpoint-1063/added_tokens.json

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

checkpoint-1063/chat_template.jinja

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

checkpoint-1063/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d43cd186a819f5bcd1e322d76d8c1b1199c56b88b5d146fd909e735fa03856
+size 1510197579

checkpoint-1063/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1063/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e0ae30d75a6f1bb9f51950040e9dc9396a660000a56d8d14711a80e859d867
+size 16325

checkpoint-1063/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bf405c3c1e26a3fbfbb975d6c256b109e00e5af1b105169ef4120ae6da1fc1
+size 16325

checkpoint-1063/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5946aa4182f6734614bb39f2cec62bfe5db663d5b7ec75525a5618cb21a73b58
+size 16325

checkpoint-1063/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b5e6958f2c398b8c7e5ec583d6825e0ea4db906b31b33f9c0cf286b9a0fd31
+size 16325

checkpoint-1063/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1069d6002b7337188af8cf67b447edf79fdab47195cfa8f9032f2a271790bfe8
+size 16325

checkpoint-1063/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b28264664bc38dbb49c5494d3d90dbb138c10246a9843d844ffd025dd3fc891
+size 16325

checkpoint-1063/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c5b9a7c1623105f2e6c88c5144556eca47d577bd97afa72e1de6cf730e921e
+size 16325

checkpoint-1063/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f3dace39c4b726127da888c9ea6e48c6271db2d7b13829b690059fee07b8eb
+size 16325

checkpoint-1063/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27271691c2f523caa57899540ef24dbeb6302bc9855b4e79fc9fc1895861164
+size 1465

checkpoint-1063/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1063/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1063/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1063/trainer_state.json

@@ -0,0 +1,834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1063,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval/E1/acc_on_CONSISTENT": 0.16435185185185186,
+      "eval/E1/acc_on_INCONSISTENT": 0.9875,
+      "eval/E1/accuracy": 0.29296875,
+      "eval/E1/f1_INC": 0.3038461538461539,
+      "eval/E1/precision_INC": 0.17954545454545454,
+      "eval/E1/recall_INC": 0.9875,
+      "eval/E2/acc_on_CONSISTENT": 0.6785714285714286,
+      "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594,
+      "eval/E2/accuracy": 0.759765625,
+      "eval/E2/f1_INC": 0.6977886977886979,
+      "eval/E2/precision_INC": 0.5482625482625483,
+      "eval/E2/recall_INC": 0.9594594594594594,
+      "eval/E3/acc_on_CONSISTENT": 0.07098765432098765,
+      "eval/E3/acc_on_INCONSISTENT": 0.9680851063829787,
+      "eval/E3/accuracy": 0.400390625,
+      "eval/E3/f1_INC": 0.5424739195230999,
+      "eval/E3/precision_INC": 0.37681159420289856,
+      "eval/E3/recall_INC": 0.9680851063829787,
+      "eval/E4/acc_on_CONSISTENT": 0.0529595015576324,
+      "eval/E4/acc_on_INCONSISTENT": 0.9476439790575916,
+      "eval/E4/accuracy": 0.38671875,
+      "eval/E4/f1_INC": 0.5355029585798816,
+      "eval/E4/precision_INC": 0.3731958762886598,
+      "eval/E4/recall_INC": 0.9476439790575916,
+      "eval/edge_macro_accuracy": 0.4599609375,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.08133971291866028,
+      "eval/overall/acc_on_INCONSISTENT": 0.966996699669967,
+      "eval/overall/accuracy": 0.60546875,
+      "eval/overall/f1_INC": 0.7436548223350254,
+      "eval/overall/precision_INC": 0.6041237113402061,
+      "eval/overall/recall_INC": 0.966996699669967,
+      "eval/overall_exact_match": 0.064453125,
+      "eval_label": "start",
+      "step": 0
+    },
+    {
+      "epoch": 0.01881467544684854,
+      "grad_norm": 0.13588111102581024,
+      "learning_rate": 5.9375e-05,
+      "loss": 0.0936,
+      "step": 20
+    },
+    {
+      "epoch": 0.03762935089369708,
+      "grad_norm": 0.15987196564674377,
+      "learning_rate": 9.932104752667314e-05,
+      "loss": 0.0348,
+      "step": 40
+    },
+    {
+      "epoch": 0.05644402634054563,
+      "grad_norm": 0.14962074160575867,
+      "learning_rate": 9.73811833171678e-05,
+      "loss": 0.0273,
+      "step": 60
+    },
+    {
+      "epoch": 0.07525870178739416,
+      "grad_norm": 0.1912640929222107,
+      "learning_rate": 9.544131910766246e-05,
+      "loss": 0.0248,
+      "step": 80
+    },
+    {
+      "epoch": 0.09407337723424271,
+      "eval/E1/acc_on_CONSISTENT": 0.8819444444444444,
+      "eval/E1/acc_on_INCONSISTENT": 0.4625,
+      "eval/E1/accuracy": 0.81640625,
+      "eval/E1/f1_INC": 0.44047619047619047,
+      "eval/E1/precision_INC": 0.42045454545454547,
+      "eval/E1/recall_INC": 0.4625,
+      "eval/E2/acc_on_CONSISTENT": 0.9752747252747253,
+      "eval/E2/acc_on_INCONSISTENT": 0.8243243243243243,
+      "eval/E2/accuracy": 0.931640625,
+      "eval/E2/f1_INC": 0.8745519713261649,
+      "eval/E2/precision_INC": 0.9312977099236641,
+      "eval/E2/recall_INC": 0.8243243243243243,
+      "eval/E3/acc_on_CONSISTENT": 0.8179012345679012,
+      "eval/E3/acc_on_INCONSISTENT": 0.6968085106382979,
+      "eval/E3/accuracy": 0.7734375,
+      "eval/E3/f1_INC": 0.6931216931216931,
+      "eval/E3/precision_INC": 0.6894736842105263,
+      "eval/E3/recall_INC": 0.6968085106382979,
+      "eval/E4/acc_on_CONSISTENT": 0.8629283489096573,
+      "eval/E4/acc_on_INCONSISTENT": 0.7068062827225131,
+      "eval/E4/accuracy": 0.8046875,
+      "eval/E4/f1_INC": 0.7297297297297297,
+      "eval/E4/precision_INC": 0.7541899441340782,
+      "eval/E4/recall_INC": 0.7068062827225131,
+      "eval/edge_macro_accuracy": 0.83154296875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8325358851674641,
+      "eval/overall/acc_on_INCONSISTENT": 0.7887788778877888,
+      "eval/overall/accuracy": 0.806640625,
+      "eval/overall/f1_INC": 0.82842287694974,
+      "eval/overall/precision_INC": 0.8722627737226277,
+      "eval/overall/recall_INC": 0.7887788778877888,
+      "eval/overall_exact_match": 0.576171875,
+      "eval_label": "step_100",
+      "step": 100
+    },
+    {
+      "epoch": 0.09407337723424271,
+      "grad_norm": 0.10156096518039703,
+      "learning_rate": 9.350145489815713e-05,
+      "loss": 0.0248,
+      "step": 100
+    },
+    {
+      "epoch": 0.11288805268109126,
+      "grad_norm": 0.15984299778938293,
+      "learning_rate": 9.15615906886518e-05,
+      "loss": 0.0241,
+      "step": 120
+    },
+    {
+      "epoch": 0.1317027281279398,
+      "grad_norm": 0.14268864691257477,
+      "learning_rate": 8.962172647914647e-05,
+      "loss": 0.0222,
+      "step": 140
+    },
+    {
+      "epoch": 0.15051740357478832,
+      "grad_norm": 0.09480800479650497,
+      "learning_rate": 8.768186226964112e-05,
+      "loss": 0.022,
+      "step": 160
+    },
+    {
+      "epoch": 0.16933207902163688,
+      "grad_norm": 0.09908359497785568,
+      "learning_rate": 8.57419980601358e-05,
+      "loss": 0.0205,
+      "step": 180
+    },
+    {
+      "epoch": 0.18814675446848542,
+      "eval/E1/acc_on_CONSISTENT": 0.9236111111111112,
+      "eval/E1/acc_on_INCONSISTENT": 0.4125,
+      "eval/E1/accuracy": 0.84375,
+      "eval/E1/f1_INC": 0.4520547945205479,
+      "eval/E1/precision_INC": 0.5,
+      "eval/E1/recall_INC": 0.4125,
+      "eval/E2/acc_on_CONSISTENT": 0.945054945054945,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.943359375,
+      "eval/E2/f1_INC": 0.9055374592833876,
+      "eval/E2/precision_INC": 0.8742138364779874,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.8703703703703703,
+      "eval/E3/acc_on_INCONSISTENT": 0.8191489361702128,
+      "eval/E3/accuracy": 0.8515625,
+      "eval/E3/f1_INC": 0.8020833333333333,
+      "eval/E3/precision_INC": 0.7857142857142857,
+      "eval/E3/recall_INC": 0.8191489361702128,
+      "eval/E4/acc_on_CONSISTENT": 0.8411214953271028,
+      "eval/E4/acc_on_INCONSISTENT": 0.7905759162303665,
+      "eval/E4/accuracy": 0.822265625,
+      "eval/E4/f1_INC": 0.7684478371501273,
+      "eval/E4/precision_INC": 0.7475247524752475,
+      "eval/E4/recall_INC": 0.7905759162303665,
+      "eval/edge_macro_accuracy": 0.865234375,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.7559808612440191,
+      "eval/overall/acc_on_INCONSISTENT": 0.8712871287128713,
+      "eval/overall/accuracy": 0.82421875,
+      "eval/overall/f1_INC": 0.854368932038835,
+      "eval/overall/precision_INC": 0.8380952380952381,
+      "eval/overall/recall_INC": 0.8712871287128713,
+      "eval/overall_exact_match": 0.63671875,
+      "eval_label": "step_200",
+      "step": 200
+    },
+    {
+      "epoch": 0.18814675446848542,
+      "grad_norm": 0.1302443891763687,
+      "learning_rate": 8.380213385063046e-05,
+      "loss": 0.0211,
+      "step": 200
+    },
+    {
+      "epoch": 0.20696142991533395,
+      "grad_norm": 0.14304408431053162,
+      "learning_rate": 8.186226964112513e-05,
+      "loss": 0.0187,
+      "step": 220
+    },
+    {
+      "epoch": 0.2257761053621825,
+      "grad_norm": 0.20394913852214813,
+      "learning_rate": 7.99224054316198e-05,
+      "loss": 0.0208,
+      "step": 240
+    },
+    {
+      "epoch": 0.24459078080903104,
+      "grad_norm": 0.11161988973617554,
+      "learning_rate": 7.798254122211446e-05,
+      "loss": 0.019,
+      "step": 260
+    },
+    {
+      "epoch": 0.2634054562558796,
+      "grad_norm": 0.11904545873403549,
+      "learning_rate": 7.604267701260912e-05,
+      "loss": 0.0204,
+      "step": 280
+    },
+    {
+      "epoch": 0.28222013170272814,
+      "eval/E1/acc_on_CONSISTENT": 0.9652777777777778,
+      "eval/E1/acc_on_INCONSISTENT": 0.3375,
+      "eval/E1/accuracy": 0.8671875,
+      "eval/E1/f1_INC": 0.4426229508196722,
+      "eval/E1/precision_INC": 0.6428571428571429,
+      "eval/E1/recall_INC": 0.3375,
+      "eval/E2/acc_on_CONSISTENT": 0.967032967032967,
+      "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325,
+      "eval/E2/accuracy": 0.95703125,
+      "eval/E2/f1_INC": 0.9261744966442953,
+      "eval/E2/precision_INC": 0.92,
+      "eval/E2/recall_INC": 0.9324324324324325,
+      "eval/E3/acc_on_CONSISTENT": 0.9382716049382716,
+      "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425,
+      "eval/E3/accuracy": 0.892578125,
+      "eval/E3/f1_INC": 0.8476454293628809,
+      "eval/E3/precision_INC": 0.884393063583815,
+      "eval/E3/recall_INC": 0.8138297872340425,
+      "eval/E4/acc_on_CONSISTENT": 0.8940809968847352,
+      "eval/E4/acc_on_INCONSISTENT": 0.8010471204188482,
+      "eval/E4/accuracy": 0.859375,
+      "eval/E4/f1_INC": 0.8095238095238095,
+      "eval/E4/precision_INC": 0.8181818181818182,
+      "eval/E4/recall_INC": 0.8010471204188482,
+      "eval/edge_macro_accuracy": 0.89404296875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8851674641148325,
+      "eval/overall/acc_on_INCONSISTENT": 0.8448844884488449,
+      "eval/overall/accuracy": 0.861328125,
+      "eval/overall/f1_INC": 0.8782161234991424,
+      "eval/overall/precision_INC": 0.9142857142857143,
+      "eval/overall/recall_INC": 0.8448844884488449,
+      "eval/overall_exact_match": 0.697265625,
+      "eval_label": "step_300",
+      "step": 300
+    },
+    {
+      "epoch": 0.28222013170272814,
+      "grad_norm": 0.1075235903263092,
+      "learning_rate": 7.410281280310378e-05,
+      "loss": 0.0212,
+      "step": 300
+    },
+    {
+      "epoch": 0.30103480714957664,
+      "grad_norm": 0.08106118440628052,
+      "learning_rate": 7.216294859359845e-05,
+      "loss": 0.0177,
+      "step": 320
+    },
+    {
+      "epoch": 0.3198494825964252,
+      "grad_norm": 0.07731106132268906,
+      "learning_rate": 7.022308438409312e-05,
+      "loss": 0.0182,
+      "step": 340
+    },
+    {
+      "epoch": 0.33866415804327377,
+      "grad_norm": 0.1482355296611786,
+      "learning_rate": 6.828322017458779e-05,
+      "loss": 0.0178,
+      "step": 360
+    },
+    {
+      "epoch": 0.35747883349012227,
+      "grad_norm": 0.07897721230983734,
+      "learning_rate": 6.634335596508244e-05,
+      "loss": 0.018,
+      "step": 380
+    },
+    {
+      "epoch": 0.37629350893697083,
+      "eval/E1/acc_on_CONSISTENT": 0.9722222222222222,
+      "eval/E1/acc_on_INCONSISTENT": 0.45,
+      "eval/E1/accuracy": 0.890625,
+      "eval/E1/f1_INC": 0.5625000000000001,
+      "eval/E1/precision_INC": 0.75,
+      "eval/E1/recall_INC": 0.45,
+      "eval/E2/acc_on_CONSISTENT": 0.9697802197802198,
+      "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325,
+      "eval/E2/accuracy": 0.958984375,
+      "eval/E2/f1_INC": 0.9292929292929293,
+      "eval/E2/precision_INC": 0.9261744966442953,
+      "eval/E2/recall_INC": 0.9324324324324325,
+      "eval/E3/acc_on_CONSISTENT": 0.9598765432098766,
+      "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425,
+      "eval/E3/accuracy": 0.90625,
+      "eval/E3/f1_INC": 0.8644067796610171,
+      "eval/E3/precision_INC": 0.9216867469879518,
+      "eval/E3/recall_INC": 0.8138297872340425,
+      "eval/E4/acc_on_CONSISTENT": 0.9096573208722741,
+      "eval/E4/acc_on_INCONSISTENT": 0.806282722513089,
+      "eval/E4/accuracy": 0.87109375,
+      "eval/E4/f1_INC": 0.823529411764706,
+      "eval/E4/precision_INC": 0.8415300546448088,
+      "eval/E4/recall_INC": 0.806282722513089,
+      "eval/edge_macro_accuracy": 0.90673828125,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9282296650717703,
+      "eval/overall/acc_on_INCONSISTENT": 0.8481848184818482,
+      "eval/overall/accuracy": 0.880859375,
+      "eval/overall/f1_INC": 0.8939130434782608,
+      "eval/overall/precision_INC": 0.9448529411764706,
+      "eval/overall/recall_INC": 0.8481848184818482,
+      "eval/overall_exact_match": 0.728515625,
+      "eval_label": "step_400",
+      "step": 400
+    },
+    {
+      "epoch": 0.37629350893697083,
+      "grad_norm": 0.1120094284415245,
+      "learning_rate": 6.440349175557712e-05,
+      "loss": 0.0168,
+      "step": 400
+    },
+    {
+      "epoch": 0.3951081843838194,
+      "grad_norm": 0.16071178019046783,
+      "learning_rate": 6.246362754607178e-05,
+      "loss": 0.016,
+      "step": 420
+    },
+    {
+      "epoch": 0.4139228598306679,
+      "grad_norm": 0.10165177285671234,
+      "learning_rate": 6.0523763336566445e-05,
+      "loss": 0.0159,
+      "step": 440
+    },
+    {
+      "epoch": 0.43273753527751646,
+      "grad_norm": 0.08946932107210159,
+      "learning_rate": 5.8583899127061106e-05,
+      "loss": 0.0167,
+      "step": 460
+    },
+    {
+      "epoch": 0.451552210724365,
+      "grad_norm": 0.07830841839313507,
+      "learning_rate": 5.664403491755578e-05,
+      "loss": 0.016,
+      "step": 480
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "eval/E1/acc_on_CONSISTENT": 0.9444444444444444,
+      "eval/E1/acc_on_INCONSISTENT": 0.575,
+      "eval/E1/accuracy": 0.88671875,
+      "eval/E1/f1_INC": 0.6133333333333333,
+      "eval/E1/precision_INC": 0.6571428571428571,
+      "eval/E1/recall_INC": 0.575,
+      "eval/E2/acc_on_CONSISTENT": 0.9285714285714286,
+      "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594,
+      "eval/E2/accuracy": 0.9375,
+      "eval/E2/f1_INC": 0.8987341772151899,
+      "eval/E2/precision_INC": 0.8452380952380952,
+      "eval/E2/recall_INC": 0.9594594594594594,
+      "eval/E3/acc_on_CONSISTENT": 0.8919753086419753,
+      "eval/E3/acc_on_INCONSISTENT": 0.8882978723404256,
+      "eval/E3/accuracy": 0.890625,
+      "eval/E3/f1_INC": 0.8564102564102564,
+      "eval/E3/precision_INC": 0.8267326732673267,
+      "eval/E3/recall_INC": 0.8882978723404256,
+      "eval/E4/acc_on_CONSISTENT": 0.8847352024922118,
+      "eval/E4/acc_on_INCONSISTENT": 0.8638743455497382,
+      "eval/E4/accuracy": 0.876953125,
+      "eval/E4/f1_INC": 0.8396946564885497,
+      "eval/E4/precision_INC": 0.8168316831683168,
+      "eval/E4/recall_INC": 0.8638743455497382,
+      "eval/edge_macro_accuracy": 0.89794921875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8325358851674641,
+      "eval/overall/acc_on_INCONSISTENT": 0.8976897689768977,
+      "eval/overall/accuracy": 0.87109375,
+      "eval/overall/f1_INC": 0.8918032786885246,
+      "eval/overall/precision_INC": 0.8859934853420195,
+      "eval/overall/recall_INC": 0.8976897689768977,
+      "eval/overall_exact_match": 0.71484375,
+      "eval_label": "step_500",
+      "step": 500
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "grad_norm": 0.23986610770225525,
+      "learning_rate": 5.470417070805044e-05,
+      "loss": 0.0168,
+      "step": 500
+    },
+    {
+      "epoch": 0.4891815616180621,
+      "grad_norm": 0.07184334099292755,
+      "learning_rate": 5.27643064985451e-05,
+      "loss": 0.0169,
+      "step": 520
+    },
+    {
+      "epoch": 0.5079962370649106,
+      "grad_norm": 0.0486169196665287,
+      "learning_rate": 5.0824442289039763e-05,
+      "loss": 0.0148,
+      "step": 540
+    },
+    {
+      "epoch": 0.5268109125117592,
+      "grad_norm": 0.11095824092626572,
+      "learning_rate": 4.888457807953444e-05,
+      "loss": 0.0173,
+      "step": 560
+    },
+    {
+      "epoch": 0.5456255879586077,
+      "grad_norm": 0.11410392075777054,
+      "learning_rate": 4.69447138700291e-05,
+      "loss": 0.0149,
+      "step": 580
+    },
+    {
+      "epoch": 0.5644402634054563,
+      "eval/E1/acc_on_CONSISTENT": 0.9722222222222222,
+      "eval/E1/acc_on_INCONSISTENT": 0.4375,
+      "eval/E1/accuracy": 0.888671875,
+      "eval/E1/f1_INC": 0.5511811023622046,
+      "eval/E1/precision_INC": 0.7446808510638298,
+      "eval/E1/recall_INC": 0.4375,
+      "eval/E2/acc_on_CONSISTENT": 0.978021978021978,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.966796875,
+      "eval/E2/f1_INC": 0.9423728813559321,
+      "eval/E2/precision_INC": 0.9455782312925171,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.9691358024691358,
+      "eval/E3/acc_on_INCONSISTENT": 0.75,
+      "eval/E3/accuracy": 0.888671875,
+      "eval/E3/f1_INC": 0.831858407079646,
+      "eval/E3/precision_INC": 0.9337748344370861,
+      "eval/E3/recall_INC": 0.75,
+      "eval/E4/acc_on_CONSISTENT": 0.956386292834891,
+      "eval/E4/acc_on_INCONSISTENT": 0.7801047120418848,
+      "eval/E4/accuracy": 0.890625,
+      "eval/E4/f1_INC": 0.8418079096045198,
+      "eval/E4/precision_INC": 0.9141104294478528,
+      "eval/E4/recall_INC": 0.7801047120418848,
+      "eval/edge_macro_accuracy": 0.90869140625,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9473684210526315,
+      "eval/overall/acc_on_INCONSISTENT": 0.8118811881188119,
+      "eval/overall/accuracy": 0.8671875,
+      "eval/overall/f1_INC": 0.8785714285714287,
+      "eval/overall/precision_INC": 0.9571984435797666,
+      "eval/overall/recall_INC": 0.8118811881188119,
+      "eval/overall_exact_match": 0.728515625,
+      "eval_label": "step_600",
+      "step": 600
+    },
+    {
+      "epoch": 0.5644402634054563,
+      "grad_norm": 0.13476960361003876,
+      "learning_rate": 4.500484966052377e-05,
+      "loss": 0.0159,
+      "step": 600
+    },
+    {
+      "epoch": 0.5832549388523048,
+      "grad_norm": 0.22448623180389404,
+      "learning_rate": 4.306498545101843e-05,
+      "loss": 0.0158,
+      "step": 620
+    },
+    {
+      "epoch": 0.6020696142991533,
+      "grad_norm": 0.3091525435447693,
+      "learning_rate": 4.1125121241513096e-05,
+      "loss": 0.0163,
+      "step": 640
+    },
+    {
+      "epoch": 0.6208842897460018,
+      "grad_norm": 0.06753229349851608,
+      "learning_rate": 3.9185257032007764e-05,
+      "loss": 0.0153,
+      "step": 660
+    },
+    {
+      "epoch": 0.6396989651928504,
+      "grad_norm": 0.16454404592514038,
+      "learning_rate": 3.724539282250243e-05,
+      "loss": 0.0137,
+      "step": 680
+    },
+    {
+      "epoch": 0.658513640639699,
+      "eval/E1/acc_on_CONSISTENT": 0.8958333333333334,
+      "eval/E1/acc_on_INCONSISTENT": 0.7,
+      "eval/E1/accuracy": 0.865234375,
+      "eval/E1/f1_INC": 0.6187845303867403,
+      "eval/E1/precision_INC": 0.5544554455445545,
+      "eval/E1/recall_INC": 0.7,
+      "eval/E2/acc_on_CONSISTENT": 0.9835164835164835,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.970703125,
+      "eval/E2/f1_INC": 0.9488054607508533,
+      "eval/E2/precision_INC": 0.9586206896551724,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.9444444444444444,
+      "eval/E3/acc_on_INCONSISTENT": 0.8563829787234043,
+      "eval/E3/accuracy": 0.912109375,
+      "eval/E3/f1_INC": 0.8773841961852861,
+      "eval/E3/precision_INC": 0.8994413407821229,
+      "eval/E3/recall_INC": 0.8563829787234043,
+      "eval/E4/acc_on_CONSISTENT": 0.9034267912772586,
+      "eval/E4/acc_on_INCONSISTENT": 0.8691099476439791,
+      "eval/E4/accuracy": 0.890625,
+      "eval/E4/f1_INC": 0.8556701030927836,
+      "eval/E4/precision_INC": 0.8426395939086294,
+      "eval/E4/recall_INC": 0.8691099476439791,
+      "eval/edge_macro_accuracy": 0.90966796875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8851674641148325,
+      "eval/overall/acc_on_INCONSISTENT": 0.8943894389438944,
+      "eval/overall/accuracy": 0.890625,
+      "eval/overall/f1_INC": 0.9063545150501673,
+      "eval/overall/precision_INC": 0.9186440677966101,
+      "eval/overall/recall_INC": 0.8943894389438944,
+      "eval/overall_exact_match": 0.736328125,
+      "eval_label": "step_700",
+      "step": 700
+    },
+    {
+      "epoch": 0.658513640639699,
+      "grad_norm": 0.10377257317304611,
+      "learning_rate": 3.530552861299709e-05,
+      "loss": 0.0159,
+      "step": 700
+    },
+    {
+      "epoch": 0.6773283160865475,
+      "grad_norm": 0.08269070833921432,
+      "learning_rate": 3.336566440349176e-05,
+      "loss": 0.0154,
+      "step": 720
+    },
+    {
+      "epoch": 0.6961429915333961,
+      "grad_norm": 0.13774652779102325,
+      "learning_rate": 3.142580019398642e-05,
+      "loss": 0.0164,
+      "step": 740
+    },
+    {
+      "epoch": 0.7149576669802445,
+      "grad_norm": 0.0529085136950016,
+      "learning_rate": 2.948593598448109e-05,
+      "loss": 0.0289,
+      "step": 760
+    },
+    {
+      "epoch": 0.7337723424270931,
+      "grad_norm": 0.07344073057174683,
+      "learning_rate": 2.754607177497575e-05,
+      "loss": 0.015,
+      "step": 780
+    },
+    {
+      "epoch": 0.7525870178739417,
+      "eval/E1/acc_on_CONSISTENT": 0.9722222222222222,
+      "eval/E1/acc_on_INCONSISTENT": 0.45,
+      "eval/E1/accuracy": 0.890625,
+      "eval/E1/f1_INC": 0.5625000000000001,
+      "eval/E1/precision_INC": 0.75,
+      "eval/E1/recall_INC": 0.45,
+      "eval/E2/acc_on_CONSISTENT": 0.9587912087912088,
+      "eval/E2/acc_on_INCONSISTENT": 0.9459459459459459,
+      "eval/E2/accuracy": 0.955078125,
+      "eval/E2/f1_INC": 0.9240924092409241,
+      "eval/E2/precision_INC": 0.9032258064516129,
+      "eval/E2/recall_INC": 0.9459459459459459,
+      "eval/E3/acc_on_CONSISTENT": 0.9598765432098766,
+      "eval/E3/acc_on_INCONSISTENT": 0.8404255319148937,
+      "eval/E3/accuracy": 0.916015625,
+      "eval/E3/f1_INC": 0.8802228412256267,
+      "eval/E3/precision_INC": 0.9239766081871345,
+      "eval/E3/recall_INC": 0.8404255319148937,
+      "eval/E4/acc_on_CONSISTENT": 0.9345794392523364,
+      "eval/E4/acc_on_INCONSISTENT": 0.837696335078534,
+      "eval/E4/accuracy": 0.8984375,
+      "eval/E4/f1_INC": 0.8602150537634408,
+      "eval/E4/precision_INC": 0.8839779005524862,
+      "eval/E4/recall_INC": 0.837696335078534,
+      "eval/edge_macro_accuracy": 0.9150390625,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9282296650717703,
+      "eval/overall/acc_on_INCONSISTENT": 0.8547854785478548,
+      "eval/overall/accuracy": 0.884765625,
+      "eval/overall/f1_INC": 0.8977469670710573,
+      "eval/overall/precision_INC": 0.9452554744525548,
+      "eval/overall/recall_INC": 0.8547854785478548,
+      "eval/overall_exact_match": 0.751953125,
+      "eval_label": "step_800",
+      "step": 800
+    },
+    {
+      "epoch": 0.7525870178739417,
+      "grad_norm": 0.07503994554281235,
+      "learning_rate": 2.560620756547042e-05,
+      "loss": 0.0146,
+      "step": 800
+    },
+    {
+      "epoch": 0.7714016933207902,
+      "grad_norm": 0.05603089556097984,
+      "learning_rate": 2.3666343355965083e-05,
+      "loss": 0.0142,
+      "step": 820
+    },
+    {
+      "epoch": 0.7902163687676388,
+      "grad_norm": 0.09725795686244965,
+      "learning_rate": 2.172647914645975e-05,
+      "loss": 0.0151,
+      "step": 840
+    },
+    {
+      "epoch": 0.8090310442144873,
+      "grad_norm": 0.13120990991592407,
+      "learning_rate": 1.9786614936954415e-05,
+      "loss": 0.0136,
+      "step": 860
+    },
+    {
+      "epoch": 0.8278457196613358,
+      "grad_norm": 0.09627928584814072,
+      "learning_rate": 1.784675072744908e-05,
+      "loss": 0.0121,
+      "step": 880
+    },
+    {
+      "epoch": 0.8466603951081844,
+      "eval/E1/acc_on_CONSISTENT": 0.9467592592592593,
+      "eval/E1/acc_on_INCONSISTENT": 0.575,
+      "eval/E1/accuracy": 0.888671875,
+      "eval/E1/f1_INC": 0.6174496644295301,
+      "eval/E1/precision_INC": 0.6666666666666666,
+      "eval/E1/recall_INC": 0.575,
+      "eval/E2/acc_on_CONSISTENT": 0.9752747252747253,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.96484375,
+      "eval/E2/f1_INC": 0.9391891891891891,
+      "eval/E2/precision_INC": 0.9391891891891891,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.941358024691358,
+      "eval/E3/acc_on_INCONSISTENT": 0.8297872340425532,
+      "eval/E3/accuracy": 0.900390625,
+      "eval/E3/f1_INC": 0.859504132231405,
+      "eval/E3/precision_INC": 0.8914285714285715,
+      "eval/E3/recall_INC": 0.8297872340425532,
+      "eval/E4/acc_on_CONSISTENT": 0.9127725856697819,
+      "eval/E4/acc_on_INCONSISTENT": 0.8638743455497382,
+      "eval/E4/accuracy": 0.89453125,
+      "eval/E4/f1_INC": 0.859375,
+      "eval/E4/precision_INC": 0.8549222797927462,
+      "eval/E4/recall_INC": 0.8638743455497382,
+      "eval/edge_macro_accuracy": 0.912109375,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8899521531100478,
+      "eval/overall/acc_on_INCONSISTENT": 0.8877887788778878,
+      "eval/overall/accuracy": 0.888671875,
+      "eval/overall/f1_INC": 0.9042016806722689,
+      "eval/overall/precision_INC": 0.9212328767123288,
+      "eval/overall/recall_INC": 0.8877887788778878,
+      "eval/overall_exact_match": 0.748046875,
+      "eval_label": "step_900",
+      "step": 900
+    },
+    {
+      "epoch": 0.8466603951081844,
+      "grad_norm": 0.07019995152950287,
+      "learning_rate": 1.5906886517943744e-05,
+      "loss": 0.0151,
+      "step": 900
+    },
+    {
+      "epoch": 0.8654750705550329,
+      "grad_norm": 0.09808464348316193,
+      "learning_rate": 1.396702230843841e-05,
+      "loss": 0.0146,
+      "step": 920
+    },
+    {
+      "epoch": 0.8842897460018815,
+      "grad_norm": 0.07016833871603012,
+      "learning_rate": 1.2027158098933075e-05,
+      "loss": 0.0143,
+      "step": 940
+    },
+    {
+      "epoch": 0.90310442144873,
+      "grad_norm": 0.060904502868652344,
+      "learning_rate": 1.008729388942774e-05,
+      "loss": 0.0147,
+      "step": 960
+    },
+    {
+      "epoch": 0.9219190968955786,
+      "grad_norm": 0.08607947826385498,
+      "learning_rate": 8.147429679922405e-06,
+      "loss": 0.0152,
+      "step": 980
+    },
+    {
+      "epoch": 0.940733772342427,
+      "eval/E1/acc_on_CONSISTENT": 0.9791666666666666,
+      "eval/E1/acc_on_INCONSISTENT": 0.45,
+      "eval/E1/accuracy": 0.896484375,
+      "eval/E1/f1_INC": 0.5760000000000001,
+      "eval/E1/precision_INC": 0.8,
+      "eval/E1/recall_INC": 0.45,
+      "eval/E2/acc_on_CONSISTENT": 0.9835164835164835,
+      "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325,
+      "eval/E2/accuracy": 0.96875,
+      "eval/E2/f1_INC": 0.9452054794520548,
+      "eval/E2/precision_INC": 0.9583333333333334,
+      "eval/E2/recall_INC": 0.9324324324324325,
+      "eval/E3/acc_on_CONSISTENT": 0.9598765432098766,
+      "eval/E3/acc_on_INCONSISTENT": 0.8191489361702128,
+      "eval/E3/accuracy": 0.908203125,
+      "eval/E3/f1_INC": 0.867605633802817,
+      "eval/E3/precision_INC": 0.9221556886227545,
+      "eval/E3/recall_INC": 0.8191489361702128,
+      "eval/E4/acc_on_CONSISTENT": 0.9252336448598131,
+      "eval/E4/acc_on_INCONSISTENT": 0.8638743455497382,
+      "eval/E4/accuracy": 0.90234375,
+      "eval/E4/f1_INC": 0.8684210526315789,
+      "eval/E4/precision_INC": 0.873015873015873,
+      "eval/E4/recall_INC": 0.8638743455497382,
+      "eval/edge_macro_accuracy": 0.9189453125,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9186602870813397,
+      "eval/overall/acc_on_INCONSISTENT": 0.8712871287128713,
+      "eval/overall/accuracy": 0.890625,
+      "eval/overall/f1_INC": 0.9041095890410958,
+      "eval/overall/precision_INC": 0.9395017793594306,
+      "eval/overall/recall_INC": 0.8712871287128713,
+      "eval/overall_exact_match": 0.751953125,
+      "eval_label": "step_1000",
+      "step": 1000
+    },
+    {
+      "epoch": 0.940733772342427,
+      "grad_norm": 0.05431496351957321,
+      "learning_rate": 6.207565470417071e-06,
+      "loss": 0.0151,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9595484477892756,
+      "grad_norm": 0.11394680291414261,
+      "learning_rate": 4.267701260911737e-06,
+      "loss": 0.0137,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9783631232361242,
+      "grad_norm": 0.06685776263475418,
+      "learning_rate": 2.327837051406402e-06,
+      "loss": 0.0135,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9971777986829727,
+      "grad_norm": 0.07160358875989914,
+      "learning_rate": 3.8797284190106696e-07,
+      "loss": 0.0124,
+      "step": 1060
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1063,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5483964464142746e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1063/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744ad00c8c00b9edc8e0bd33e72eaff717a24e6a1f81961a168c411d234137e9
+size 5905

checkpoint-1063/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

checkpoint-600/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-600/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3d55aca26cbd9fd5828f9c90f03d4d959629a3f90fff87356eb0ea2753dfc4
+size 755018656

checkpoint-600/added_tokens.json

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

checkpoint-600/chat_template.jinja

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

checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3012d70525c66df85beb427611e72ffe8d56d0b03482245c34426ba135cc75d3
+size 1510197579

checkpoint-600/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

checkpoint-600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419a8a6861381fa10f2c726f06e06a231f7d5b1e1955c980da2257eddb3c1727
+size 16325

checkpoint-600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1178ec7f8a778361075fbf8aa7e746031c4d092e59b171aa635079e6863968f0
+size 16325

checkpoint-600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c18fe5bf258da8c4dfbff363482f442a4fe43a418f5be795a79dc16fae6a61
+size 16325

checkpoint-600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a487e42142050b3fccd5f0f4f58b9372c21ada9fb4e3b2bca54a902cba4d4f3c
+size 16325

checkpoint-600/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e8955907b140db96aabb195ffc67cd5664a0bf1f1b98a35e078a895b1e7e3
+size 16325

checkpoint-600/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6cb4f53b9077371a08eafed9f4a72ab4db01f2bd8f4bc1e72ce685ad59cd58
+size 16325

checkpoint-600/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6653912c05df0e21e00e5fdcbb3d95eac67523709429264d729ef679fb8fb1f
+size 16325

checkpoint-600/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ea93fd75f3a1af4ebef90d2afbfa9e07430e07443655538feaff8258badf41
+size 16325

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28368687aefbb4027c7cc4796b1aca150a0fa02a25fd97a820bfa759c12f99d
+size 1465

checkpoint-600/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-600/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-600/trainer_state.json

@@ -0,0 +1,517 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5644402634054563,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval/E1/acc_on_CONSISTENT": 0.16435185185185186,
+      "eval/E1/acc_on_INCONSISTENT": 0.9875,
+      "eval/E1/accuracy": 0.29296875,
+      "eval/E1/f1_INC": 0.3038461538461539,
+      "eval/E1/precision_INC": 0.17954545454545454,
+      "eval/E1/recall_INC": 0.9875,
+      "eval/E2/acc_on_CONSISTENT": 0.6785714285714286,
+      "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594,
+      "eval/E2/accuracy": 0.759765625,
+      "eval/E2/f1_INC": 0.6977886977886979,
+      "eval/E2/precision_INC": 0.5482625482625483,
+      "eval/E2/recall_INC": 0.9594594594594594,
+      "eval/E3/acc_on_CONSISTENT": 0.07098765432098765,
+      "eval/E3/acc_on_INCONSISTENT": 0.9680851063829787,
+      "eval/E3/accuracy": 0.400390625,
+      "eval/E3/f1_INC": 0.5424739195230999,
+      "eval/E3/precision_INC": 0.37681159420289856,
+      "eval/E3/recall_INC": 0.9680851063829787,
+      "eval/E4/acc_on_CONSISTENT": 0.0529595015576324,
+      "eval/E4/acc_on_INCONSISTENT": 0.9476439790575916,
+      "eval/E4/accuracy": 0.38671875,
+      "eval/E4/f1_INC": 0.5355029585798816,
+      "eval/E4/precision_INC": 0.3731958762886598,
+      "eval/E4/recall_INC": 0.9476439790575916,
+      "eval/edge_macro_accuracy": 0.4599609375,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.08133971291866028,
+      "eval/overall/acc_on_INCONSISTENT": 0.966996699669967,
+      "eval/overall/accuracy": 0.60546875,
+      "eval/overall/f1_INC": 0.7436548223350254,
+      "eval/overall/precision_INC": 0.6041237113402061,
+      "eval/overall/recall_INC": 0.966996699669967,
+      "eval/overall_exact_match": 0.064453125,
+      "eval_label": "start",
+      "step": 0
+    },
+    {
+      "epoch": 0.01881467544684854,
+      "grad_norm": 0.13588111102581024,
+      "learning_rate": 5.9375e-05,
+      "loss": 0.0936,
+      "step": 20
+    },
+    {
+      "epoch": 0.03762935089369708,
+      "grad_norm": 0.15987196564674377,
+      "learning_rate": 9.932104752667314e-05,
+      "loss": 0.0348,
+      "step": 40
+    },
+    {
+      "epoch": 0.05644402634054563,
+      "grad_norm": 0.14962074160575867,
+      "learning_rate": 9.73811833171678e-05,
+      "loss": 0.0273,
+      "step": 60
+    },
+    {
+      "epoch": 0.07525870178739416,
+      "grad_norm": 0.1912640929222107,
+      "learning_rate": 9.544131910766246e-05,
+      "loss": 0.0248,
+      "step": 80
+    },
+    {
+      "epoch": 0.09407337723424271,
+      "eval/E1/acc_on_CONSISTENT": 0.8819444444444444,
+      "eval/E1/acc_on_INCONSISTENT": 0.4625,
+      "eval/E1/accuracy": 0.81640625,
+      "eval/E1/f1_INC": 0.44047619047619047,
+      "eval/E1/precision_INC": 0.42045454545454547,
+      "eval/E1/recall_INC": 0.4625,
+      "eval/E2/acc_on_CONSISTENT": 0.9752747252747253,
+      "eval/E2/acc_on_INCONSISTENT": 0.8243243243243243,
+      "eval/E2/accuracy": 0.931640625,
+      "eval/E2/f1_INC": 0.8745519713261649,
+      "eval/E2/precision_INC": 0.9312977099236641,
+      "eval/E2/recall_INC": 0.8243243243243243,
+      "eval/E3/acc_on_CONSISTENT": 0.8179012345679012,
+      "eval/E3/acc_on_INCONSISTENT": 0.6968085106382979,
+      "eval/E3/accuracy": 0.7734375,
+      "eval/E3/f1_INC": 0.6931216931216931,
+      "eval/E3/precision_INC": 0.6894736842105263,
+      "eval/E3/recall_INC": 0.6968085106382979,
+      "eval/E4/acc_on_CONSISTENT": 0.8629283489096573,
+      "eval/E4/acc_on_INCONSISTENT": 0.7068062827225131,
+      "eval/E4/accuracy": 0.8046875,
+      "eval/E4/f1_INC": 0.7297297297297297,
+      "eval/E4/precision_INC": 0.7541899441340782,
+      "eval/E4/recall_INC": 0.7068062827225131,
+      "eval/edge_macro_accuracy": 0.83154296875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8325358851674641,
+      "eval/overall/acc_on_INCONSISTENT": 0.7887788778877888,
+      "eval/overall/accuracy": 0.806640625,
+      "eval/overall/f1_INC": 0.82842287694974,
+      "eval/overall/precision_INC": 0.8722627737226277,
+      "eval/overall/recall_INC": 0.7887788778877888,
+      "eval/overall_exact_match": 0.576171875,
+      "eval_label": "step_100",
+      "step": 100
+    },
+    {
+      "epoch": 0.09407337723424271,
+      "grad_norm": 0.10156096518039703,
+      "learning_rate": 9.350145489815713e-05,
+      "loss": 0.0248,
+      "step": 100
+    },
+    {
+      "epoch": 0.11288805268109126,
+      "grad_norm": 0.15984299778938293,
+      "learning_rate": 9.15615906886518e-05,
+      "loss": 0.0241,
+      "step": 120
+    },
+    {
+      "epoch": 0.1317027281279398,
+      "grad_norm": 0.14268864691257477,
+      "learning_rate": 8.962172647914647e-05,
+      "loss": 0.0222,
+      "step": 140
+    },
+    {
+      "epoch": 0.15051740357478832,
+      "grad_norm": 0.09480800479650497,
+      "learning_rate": 8.768186226964112e-05,
+      "loss": 0.022,
+      "step": 160
+    },
+    {
+      "epoch": 0.16933207902163688,
+      "grad_norm": 0.09908359497785568,
+      "learning_rate": 8.57419980601358e-05,
+      "loss": 0.0205,
+      "step": 180
+    },
+    {
+      "epoch": 0.18814675446848542,
+      "eval/E1/acc_on_CONSISTENT": 0.9236111111111112,
+      "eval/E1/acc_on_INCONSISTENT": 0.4125,
+      "eval/E1/accuracy": 0.84375,
+      "eval/E1/f1_INC": 0.4520547945205479,
+      "eval/E1/precision_INC": 0.5,
+      "eval/E1/recall_INC": 0.4125,
+      "eval/E2/acc_on_CONSISTENT": 0.945054945054945,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.943359375,
+      "eval/E2/f1_INC": 0.9055374592833876,
+      "eval/E2/precision_INC": 0.8742138364779874,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.8703703703703703,
+      "eval/E3/acc_on_INCONSISTENT": 0.8191489361702128,
+      "eval/E3/accuracy": 0.8515625,
+      "eval/E3/f1_INC": 0.8020833333333333,
+      "eval/E3/precision_INC": 0.7857142857142857,
+      "eval/E3/recall_INC": 0.8191489361702128,
+      "eval/E4/acc_on_CONSISTENT": 0.8411214953271028,
+      "eval/E4/acc_on_INCONSISTENT": 0.7905759162303665,
+      "eval/E4/accuracy": 0.822265625,
+      "eval/E4/f1_INC": 0.7684478371501273,
+      "eval/E4/precision_INC": 0.7475247524752475,
+      "eval/E4/recall_INC": 0.7905759162303665,
+      "eval/edge_macro_accuracy": 0.865234375,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.7559808612440191,
+      "eval/overall/acc_on_INCONSISTENT": 0.8712871287128713,
+      "eval/overall/accuracy": 0.82421875,
+      "eval/overall/f1_INC": 0.854368932038835,
+      "eval/overall/precision_INC": 0.8380952380952381,
+      "eval/overall/recall_INC": 0.8712871287128713,
+      "eval/overall_exact_match": 0.63671875,
+      "eval_label": "step_200",
+      "step": 200
+    },
+    {
+      "epoch": 0.18814675446848542,
+      "grad_norm": 0.1302443891763687,
+      "learning_rate": 8.380213385063046e-05,
+      "loss": 0.0211,
+      "step": 200
+    },
+    {
+      "epoch": 0.20696142991533395,
+      "grad_norm": 0.14304408431053162,
+      "learning_rate": 8.186226964112513e-05,
+      "loss": 0.0187,
+      "step": 220
+    },
+    {
+      "epoch": 0.2257761053621825,
+      "grad_norm": 0.20394913852214813,
+      "learning_rate": 7.99224054316198e-05,
+      "loss": 0.0208,
+      "step": 240
+    },
+    {
+      "epoch": 0.24459078080903104,
+      "grad_norm": 0.11161988973617554,
+      "learning_rate": 7.798254122211446e-05,
+      "loss": 0.019,
+      "step": 260
+    },
+    {
+      "epoch": 0.2634054562558796,
+      "grad_norm": 0.11904545873403549,
+      "learning_rate": 7.604267701260912e-05,
+      "loss": 0.0204,
+      "step": 280
+    },
+    {
+      "epoch": 0.28222013170272814,
+      "eval/E1/acc_on_CONSISTENT": 0.9652777777777778,
+      "eval/E1/acc_on_INCONSISTENT": 0.3375,
+      "eval/E1/accuracy": 0.8671875,
+      "eval/E1/f1_INC": 0.4426229508196722,
+      "eval/E1/precision_INC": 0.6428571428571429,
+      "eval/E1/recall_INC": 0.3375,
+      "eval/E2/acc_on_CONSISTENT": 0.967032967032967,
+      "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325,
+      "eval/E2/accuracy": 0.95703125,
+      "eval/E2/f1_INC": 0.9261744966442953,
+      "eval/E2/precision_INC": 0.92,
+      "eval/E2/recall_INC": 0.9324324324324325,
+      "eval/E3/acc_on_CONSISTENT": 0.9382716049382716,
+      "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425,
+      "eval/E3/accuracy": 0.892578125,
+      "eval/E3/f1_INC": 0.8476454293628809,
+      "eval/E3/precision_INC": 0.884393063583815,
+      "eval/E3/recall_INC": 0.8138297872340425,
+      "eval/E4/acc_on_CONSISTENT": 0.8940809968847352,
+      "eval/E4/acc_on_INCONSISTENT": 0.8010471204188482,
+      "eval/E4/accuracy": 0.859375,
+      "eval/E4/f1_INC": 0.8095238095238095,
+      "eval/E4/precision_INC": 0.8181818181818182,
+      "eval/E4/recall_INC": 0.8010471204188482,
+      "eval/edge_macro_accuracy": 0.89404296875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8851674641148325,
+      "eval/overall/acc_on_INCONSISTENT": 0.8448844884488449,
+      "eval/overall/accuracy": 0.861328125,
+      "eval/overall/f1_INC": 0.8782161234991424,
+      "eval/overall/precision_INC": 0.9142857142857143,
+      "eval/overall/recall_INC": 0.8448844884488449,
+      "eval/overall_exact_match": 0.697265625,
+      "eval_label": "step_300",
+      "step": 300
+    },
+    {
+      "epoch": 0.28222013170272814,
+      "grad_norm": 0.1075235903263092,
+      "learning_rate": 7.410281280310378e-05,
+      "loss": 0.0212,
+      "step": 300
+    },
+    {
+      "epoch": 0.30103480714957664,
+      "grad_norm": 0.08106118440628052,
+      "learning_rate": 7.216294859359845e-05,
+      "loss": 0.0177,
+      "step": 320
+    },
+    {
+      "epoch": 0.3198494825964252,
+      "grad_norm": 0.07731106132268906,
+      "learning_rate": 7.022308438409312e-05,
+      "loss": 0.0182,
+      "step": 340
+    },
+    {
+      "epoch": 0.33866415804327377,
+      "grad_norm": 0.1482355296611786,
+      "learning_rate": 6.828322017458779e-05,
+      "loss": 0.0178,
+      "step": 360
+    },
+    {
+      "epoch": 0.35747883349012227,
+      "grad_norm": 0.07897721230983734,
+      "learning_rate": 6.634335596508244e-05,
+      "loss": 0.018,
+      "step": 380
+    },
+    {
+      "epoch": 0.37629350893697083,
+      "eval/E1/acc_on_CONSISTENT": 0.9722222222222222,
+      "eval/E1/acc_on_INCONSISTENT": 0.45,
+      "eval/E1/accuracy": 0.890625,
+      "eval/E1/f1_INC": 0.5625000000000001,
+      "eval/E1/precision_INC": 0.75,
+      "eval/E1/recall_INC": 0.45,
+      "eval/E2/acc_on_CONSISTENT": 0.9697802197802198,
+      "eval/E2/acc_on_INCONSISTENT": 0.9324324324324325,
+      "eval/E2/accuracy": 0.958984375,
+      "eval/E2/f1_INC": 0.9292929292929293,
+      "eval/E2/precision_INC": 0.9261744966442953,
+      "eval/E2/recall_INC": 0.9324324324324325,
+      "eval/E3/acc_on_CONSISTENT": 0.9598765432098766,
+      "eval/E3/acc_on_INCONSISTENT": 0.8138297872340425,
+      "eval/E3/accuracy": 0.90625,
+      "eval/E3/f1_INC": 0.8644067796610171,
+      "eval/E3/precision_INC": 0.9216867469879518,
+      "eval/E3/recall_INC": 0.8138297872340425,
+      "eval/E4/acc_on_CONSISTENT": 0.9096573208722741,
+      "eval/E4/acc_on_INCONSISTENT": 0.806282722513089,
+      "eval/E4/accuracy": 0.87109375,
+      "eval/E4/f1_INC": 0.823529411764706,
+      "eval/E4/precision_INC": 0.8415300546448088,
+      "eval/E4/recall_INC": 0.806282722513089,
+      "eval/edge_macro_accuracy": 0.90673828125,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9282296650717703,
+      "eval/overall/acc_on_INCONSISTENT": 0.8481848184818482,
+      "eval/overall/accuracy": 0.880859375,
+      "eval/overall/f1_INC": 0.8939130434782608,
+      "eval/overall/precision_INC": 0.9448529411764706,
+      "eval/overall/recall_INC": 0.8481848184818482,
+      "eval/overall_exact_match": 0.728515625,
+      "eval_label": "step_400",
+      "step": 400
+    },
+    {
+      "epoch": 0.37629350893697083,
+      "grad_norm": 0.1120094284415245,
+      "learning_rate": 6.440349175557712e-05,
+      "loss": 0.0168,
+      "step": 400
+    },
+    {
+      "epoch": 0.3951081843838194,
+      "grad_norm": 0.16071178019046783,
+      "learning_rate": 6.246362754607178e-05,
+      "loss": 0.016,
+      "step": 420
+    },
+    {
+      "epoch": 0.4139228598306679,
+      "grad_norm": 0.10165177285671234,
+      "learning_rate": 6.0523763336566445e-05,
+      "loss": 0.0159,
+      "step": 440
+    },
+    {
+      "epoch": 0.43273753527751646,
+      "grad_norm": 0.08946932107210159,
+      "learning_rate": 5.8583899127061106e-05,
+      "loss": 0.0167,
+      "step": 460
+    },
+    {
+      "epoch": 0.451552210724365,
+      "grad_norm": 0.07830841839313507,
+      "learning_rate": 5.664403491755578e-05,
+      "loss": 0.016,
+      "step": 480
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "eval/E1/acc_on_CONSISTENT": 0.9444444444444444,
+      "eval/E1/acc_on_INCONSISTENT": 0.575,
+      "eval/E1/accuracy": 0.88671875,
+      "eval/E1/f1_INC": 0.6133333333333333,
+      "eval/E1/precision_INC": 0.6571428571428571,
+      "eval/E1/recall_INC": 0.575,
+      "eval/E2/acc_on_CONSISTENT": 0.9285714285714286,
+      "eval/E2/acc_on_INCONSISTENT": 0.9594594594594594,
+      "eval/E2/accuracy": 0.9375,
+      "eval/E2/f1_INC": 0.8987341772151899,
+      "eval/E2/precision_INC": 0.8452380952380952,
+      "eval/E2/recall_INC": 0.9594594594594594,
+      "eval/E3/acc_on_CONSISTENT": 0.8919753086419753,
+      "eval/E3/acc_on_INCONSISTENT": 0.8882978723404256,
+      "eval/E3/accuracy": 0.890625,
+      "eval/E3/f1_INC": 0.8564102564102564,
+      "eval/E3/precision_INC": 0.8267326732673267,
+      "eval/E3/recall_INC": 0.8882978723404256,
+      "eval/E4/acc_on_CONSISTENT": 0.8847352024922118,
+      "eval/E4/acc_on_INCONSISTENT": 0.8638743455497382,
+      "eval/E4/accuracy": 0.876953125,
+      "eval/E4/f1_INC": 0.8396946564885497,
+      "eval/E4/precision_INC": 0.8168316831683168,
+      "eval/E4/recall_INC": 0.8638743455497382,
+      "eval/edge_macro_accuracy": 0.89794921875,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.8325358851674641,
+      "eval/overall/acc_on_INCONSISTENT": 0.8976897689768977,
+      "eval/overall/accuracy": 0.87109375,
+      "eval/overall/f1_INC": 0.8918032786885246,
+      "eval/overall/precision_INC": 0.8859934853420195,
+      "eval/overall/recall_INC": 0.8976897689768977,
+      "eval/overall_exact_match": 0.71484375,
+      "eval_label": "step_500",
+      "step": 500
+    },
+    {
+      "epoch": 0.4703668861712135,
+      "grad_norm": 0.23986610770225525,
+      "learning_rate": 5.470417070805044e-05,
+      "loss": 0.0168,
+      "step": 500
+    },
+    {
+      "epoch": 0.4891815616180621,
+      "grad_norm": 0.07184334099292755,
+      "learning_rate": 5.27643064985451e-05,
+      "loss": 0.0169,
+      "step": 520
+    },
+    {
+      "epoch": 0.5079962370649106,
+      "grad_norm": 0.0486169196665287,
+      "learning_rate": 5.0824442289039763e-05,
+      "loss": 0.0148,
+      "step": 540
+    },
+    {
+      "epoch": 0.5268109125117592,
+      "grad_norm": 0.11095824092626572,
+      "learning_rate": 4.888457807953444e-05,
+      "loss": 0.0173,
+      "step": 560
+    },
+    {
+      "epoch": 0.5456255879586077,
+      "grad_norm": 0.11410392075777054,
+      "learning_rate": 4.69447138700291e-05,
+      "loss": 0.0149,
+      "step": 580
+    },
+    {
+      "epoch": 0.5644402634054563,
+      "eval/E1/acc_on_CONSISTENT": 0.9722222222222222,
+      "eval/E1/acc_on_INCONSISTENT": 0.4375,
+      "eval/E1/accuracy": 0.888671875,
+      "eval/E1/f1_INC": 0.5511811023622046,
+      "eval/E1/precision_INC": 0.7446808510638298,
+      "eval/E1/recall_INC": 0.4375,
+      "eval/E2/acc_on_CONSISTENT": 0.978021978021978,
+      "eval/E2/acc_on_INCONSISTENT": 0.9391891891891891,
+      "eval/E2/accuracy": 0.966796875,
+      "eval/E2/f1_INC": 0.9423728813559321,
+      "eval/E2/precision_INC": 0.9455782312925171,
+      "eval/E2/recall_INC": 0.9391891891891891,
+      "eval/E3/acc_on_CONSISTENT": 0.9691358024691358,
+      "eval/E3/acc_on_INCONSISTENT": 0.75,
+      "eval/E3/accuracy": 0.888671875,
+      "eval/E3/f1_INC": 0.831858407079646,
+      "eval/E3/precision_INC": 0.9337748344370861,
+      "eval/E3/recall_INC": 0.75,
+      "eval/E4/acc_on_CONSISTENT": 0.956386292834891,
+      "eval/E4/acc_on_INCONSISTENT": 0.7801047120418848,
+      "eval/E4/accuracy": 0.890625,
+      "eval/E4/f1_INC": 0.8418079096045198,
+      "eval/E4/precision_INC": 0.9141104294478528,
+      "eval/E4/recall_INC": 0.7801047120418848,
+      "eval/edge_macro_accuracy": 0.90869140625,
+      "eval/malformed_rate": 0.0,
+      "eval/n_eval": 512.0,
+      "eval/overall/acc_on_CONSISTENT": 0.9473684210526315,
+      "eval/overall/acc_on_INCONSISTENT": 0.8118811881188119,
+      "eval/overall/accuracy": 0.8671875,
+      "eval/overall/f1_INC": 0.8785714285714287,
+      "eval/overall/precision_INC": 0.9571984435797666,
+      "eval/overall/recall_INC": 0.8118811881188119,
+      "eval/overall_exact_match": 0.728515625,
+      "eval_label": "step_600",
+      "step": 600
+    },
+    {
+      "epoch": 0.5644402634054563,
+      "grad_norm": 0.13476960361003876,
+      "learning_rate": 4.500484966052377e-05,
+      "loss": 0.0159,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1063,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.738632608964936e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744ad00c8c00b9edc8e0bd33e72eaff717a24e6a1f81961a168c411d234137e9
+size 5905

checkpoint-600/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

checkpoint-900/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.17.1