Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,106 @@
+---
+license: mit
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+tags:
+  - video-language-model
+  - pet-detection
+  - lora
+  - qwen2-vl
+datasets:
+  - Raullen/petvlm-data
+pipeline_tag: video-text-to-text
+---
+
+# PetVLM - Sherlock Pet
+
+A LoRA adapter for Qwen2-VL-2B-Instruct, fine-tuned to detect naughty vs nice pet behavior with a sarcastic pet detective persona.
+
+## Model Description
+
+- **Base Model**: [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct)
+- **Fine-tuning**: LoRA (rank=16, alpha=32, dropout=0.05)
+- **Training Data**: [Raullen/petvlm-data](https://huggingface.co/datasets/Raullen/petvlm-data) (40 labeled pet videos)
+
+## Output Format
+
+- **ALERT!** - Naughty behavior detected (climbing, scratching furniture, stealing food, etc.)
+- **All Clear** - Good behavior (sleeping, eating properly, playing nicely)
+
+## Usage
+
+```python
+import torch
+from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
+from peft import PeftModel
+from qwen_vl_utils import process_vision_info
+
+# Load base model
+base_model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(base_model, "Raullen/petvlm")
+model.eval()
+
+processor = AutoProcessor.from_pretrained("Raullen/petvlm")
+
+# Analyze a video
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "video", "video": "path/to/video.mp4", "nframes": 8},
+            {"type": "text", "text": "What is the pet doing?"}
+        ]
+    }
+]
+
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+image_inputs, video_inputs = process_vision_info(messages)
+
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt"
+).to(model.device)
+
+with torch.no_grad():
+    output = model.generate(**inputs, max_new_tokens=256)
+
+response = processor.batch_decode(output[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0]
+print(response)
+```
+
+## Training Parameters
+
+| Parameter | Value |
+|-----------|-------|
+| LoRA rank | 16 |
+| LoRA alpha | 32 |
+| LoRA dropout | 0.05 |
+| Learning rate | 2e-4 |
+| Epochs | 30 |
+| Batch size | 1 |
+
+## Sample Outputs
+
+**Naughty:**
+> "ALERT! The acrobatic menace has achieved full Spider-Cat mode, scaling kitchen cabinets like it's an Olympic sport. Recommend securing all elevated surfaces immediately."
+
+**Nice:**
+> "All Clear. The suspect is peacefully napping by the fireplace like a perfect little angel. Don't be fooled though - this is just the calm before the zoomies."
+
+## Links
+
+- **Code**: [github.com/raullenchai/petvlm](https://github.com/raullenchai/petvlm)
+- **Dataset**: [Raullen/petvlm-data](https://huggingface.co/datasets/Raullen/petvlm-data)
+
+## License
+
+MIT

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1dd27a313df49d8699dc96b4aa1f47241b6125d126ab2cc20d4d0da9b451aa7
+size 73916992

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "total_flos": 5518966123560960.0,
+    "train_loss": 0.2944723299946054,
+    "train_runtime": 391.3174,
+    "train_samples_per_second": 3.067,
+    "train_steps_per_second": 3.067
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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 %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

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": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "total_flos": 5518966123560960.0,
+    "train_loss": 0.2944723299946054,
+    "train_runtime": 391.3174,
+    "train_samples_per_second": 3.067,
+    "train_steps_per_second": 3.067
+}

trainer_state.json

@@ -0,0 +1,883 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.778720378875732,
+      "learning_rate": 1.5e-05,
+      "loss": 4.1831,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.072098255157471,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 4.1488,
+      "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.428645133972168,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 3.7577,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.028885364532471,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 2.9842,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 5.070592403411865,
+      "learning_rate": 8.166666666666667e-05,
+      "loss": 2.3977,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.642765522003174,
+      "learning_rate": 9.833333333333333e-05,
+      "loss": 2.3892,
+      "step": 60
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 6.417508602142334,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 2.224,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.406721115112305,
+      "learning_rate": 0.00013166666666666668,
+      "loss": 1.9902,
+      "step": 80
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 10.698479652404785,
+      "learning_rate": 0.00014833333333333335,
+      "loss": 1.4379,
+      "step": 90
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 7.168300628662109,
+      "learning_rate": 0.000165,
+      "loss": 1.3657,
+      "step": 100
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 8.622518539428711,
+      "learning_rate": 0.00018166666666666667,
+      "loss": 1.1024,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.159564018249512,
+      "learning_rate": 0.00019833333333333335,
+      "loss": 1.4106,
+      "step": 120
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 4.976837158203125,
+      "learning_rate": 0.00019996573249755572,
+      "loss": 0.5826,
+      "step": 130
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 11.353582382202148,
+      "learning_rate": 0.00019984730708473114,
+      "loss": 0.6382,
+      "step": 140
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 5.605244159698486,
+      "learning_rate": 0.00019964440088179717,
+      "loss": 0.6091,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.121719837188721,
+      "learning_rate": 0.00019935718556765876,
+      "loss": 0.6703,
+      "step": 160
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 4.879727363586426,
+      "learning_rate": 0.00019898590415514598,
+      "loss": 0.2784,
+      "step": 170
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 4.103272914886475,
+      "learning_rate": 0.00019853087078540096,
+      "loss": 0.3594,
+      "step": 180
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 1.8382512331008911,
+      "learning_rate": 0.00019799247046208297,
+      "loss": 0.2317,
+      "step": 190
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.743032932281494,
+      "learning_rate": 0.0001973711587256171,
+      "loss": 0.3543,
+      "step": 200
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 4.488682746887207,
+      "learning_rate": 0.0001966674612677614,
+      "loss": 0.1764,
+      "step": 210
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 2.1697070598602295,
+      "learning_rate": 0.0001958819734868193,
+      "loss": 0.1821,
+      "step": 220
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 7.363753795623779,
+      "learning_rate": 0.00019501535998387313,
+      "loss": 0.203,
+      "step": 230
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.7093255519866943,
+      "learning_rate": 0.0001940683540004652,
+      "loss": 0.1724,
+      "step": 240
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 4.128848075866699,
+      "learning_rate": 0.00019304175679820247,
+      "loss": 0.0644,
+      "step": 250
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 3.6359198093414307,
+      "learning_rate": 0.00019193643698080893,
+      "loss": 0.1838,
+      "step": 260
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 3.275486469268799,
+      "learning_rate": 0.00019075332975920038,
+      "loss": 0.1627,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.216045379638672,
+      "learning_rate": 0.00018949343616020252,
+      "loss": 0.1454,
+      "step": 280
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 0.677476704120636,
+      "learning_rate": 0.00018815782217958233,
+      "loss": 0.0368,
+      "step": 290
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 8.758004188537598,
+      "learning_rate": 0.00018674761788010927,
+      "loss": 0.1259,
+      "step": 300
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 0.6607072353363037,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.0559,
+      "step": 310
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.017343521118164,
+      "learning_rate": 0.0001837082731204207,
+      "loss": 0.0662,
+      "step": 320
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 0.03981485217809677,
+      "learning_rate": 0.00018208170424930672,
+      "loss": 0.0237,
+      "step": 330
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 9.23737907409668,
+      "learning_rate": 0.00018038568606172173,
+      "loss": 0.1403,
+      "step": 340
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.65294349193573,
+      "learning_rate": 0.00017862165355837542,
+      "loss": 0.0689,
+      "step": 350
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.08593683689832687,
+      "learning_rate": 0.00017679109928687886,
+      "loss": 0.0896,
+      "step": 360
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 0.13523679971694946,
+      "learning_rate": 0.00017489557207890023,
+      "loss": 0.0232,
+      "step": 370
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 3.196052074432373,
+      "learning_rate": 0.00017293667573969854,
+      "loss": 0.0178,
+      "step": 380
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 2.6995441913604736,
+      "learning_rate": 0.00017091606769114437,
+      "loss": 0.0204,
+      "step": 390
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.18581485748291,
+      "learning_rate": 0.0001688354575693754,
+      "loss": 0.1131,
+      "step": 400
+    },
+    {
+      "epoch": 10.25,
+      "grad_norm": 0.39052364230155945,
+      "learning_rate": 0.00016669660577827363,
+      "loss": 0.0048,
+      "step": 410
+    },
+    {
+      "epoch": 10.5,
+      "grad_norm": 0.021380405873060226,
+      "learning_rate": 0.00016450132199998785,
+      "loss": 0.0189,
+      "step": 420
+    },
+    {
+      "epoch": 10.75,
+      "grad_norm": 0.06276793032884598,
+      "learning_rate": 0.00016225146366376198,
+      "loss": 0.0068,
+      "step": 430
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.017770862206816673,
+      "learning_rate": 0.0001599489343743644,
+      "loss": 0.0308,
+      "step": 440
+    },
+    {
+      "epoch": 11.25,
+      "grad_norm": 0.02739694155752659,
+      "learning_rate": 0.00015759568230144834,
+      "loss": 0.0009,
+      "step": 450
+    },
+    {
+      "epoch": 11.5,
+      "grad_norm": 0.01998838223516941,
+      "learning_rate": 0.0001551936985312058,
+      "loss": 0.0187,
+      "step": 460
+    },
+    {
+      "epoch": 11.75,
+      "grad_norm": 0.06585182994604111,
+      "learning_rate": 0.00015274501538171,
+      "loss": 0.0036,
+      "step": 470
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.4273861646652222,
+      "learning_rate": 0.000150251704683371,
+      "loss": 0.0022,
+      "step": 480
+    },
+    {
+      "epoch": 12.25,
+      "grad_norm": 0.01527713518589735,
+      "learning_rate": 0.00014771587602596084,
+      "loss": 0.0007,
+      "step": 490
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.027245204895734787,
+      "learning_rate": 0.0001451396749736897,
+      "loss": 0.0419,
+      "step": 500
+    },
+    {
+      "epoch": 12.75,
+      "grad_norm": 0.012291381135582924,
+      "learning_rate": 0.00014252528124984433,
+      "loss": 0.0007,
+      "step": 510
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.02366398088634014,
+      "learning_rate": 0.00013987490689252463,
+      "loss": 0.0011,
+      "step": 520
+    },
+    {
+      "epoch": 13.25,
+      "grad_norm": 0.010158264078199863,
+      "learning_rate": 0.00013719079438303866,
+      "loss": 0.0006,
+      "step": 530
+    },
+    {
+      "epoch": 13.5,
+      "grad_norm": 0.013381893746554852,
+      "learning_rate": 0.00013447521474853943,
+      "loss": 0.0006,
+      "step": 540
+    },
+    {
+      "epoch": 13.75,
+      "grad_norm": 0.013267560862004757,
+      "learning_rate": 0.00013173046564050924,
+      "loss": 0.0005,
+      "step": 550
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.00924230832606554,
+      "learning_rate": 0.0001289588693907171,
+      "loss": 0.0005,
+      "step": 560
+    },
+    {
+      "epoch": 14.25,
+      "grad_norm": 0.012411078438162804,
+      "learning_rate": 0.00012616277104629436,
+      "loss": 0.0005,
+      "step": 570
+    },
+    {
+      "epoch": 14.5,
+      "grad_norm": 0.010797705501317978,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0004,
+      "step": 580
+    },
+    {
+      "epoch": 14.75,
+      "grad_norm": 0.011653212830424309,
+      "learning_rate": 0.00012050654991648877,
+      "loss": 0.0004,
+      "step": 590
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.010719945654273033,
+      "learning_rate": 0.00011765121285887392,
+      "loss": 0.0004,
+      "step": 600
+    },
+    {
+      "epoch": 15.25,
+      "grad_norm": 0.009023563005030155,
+      "learning_rate": 0.00011478094111296109,
+      "loss": 0.0004,
+      "step": 610
+    },
+    {
+      "epoch": 15.5,
+      "grad_norm": 0.007160203997045755,
+      "learning_rate": 0.00011189816321520255,
+      "loss": 0.0004,
+      "step": 620
+    },
+    {
+      "epoch": 15.75,
+      "grad_norm": 0.010033920407295227,
+      "learning_rate": 0.00010900531828350374,
+      "loss": 0.0004,
+      "step": 630
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.006705187261104584,
+      "learning_rate": 0.00010610485395348571,
+      "loss": 0.0003,
+      "step": 640
+    },
+    {
+      "epoch": 16.25,
+      "grad_norm": 0.007724540773779154,
+      "learning_rate": 0.0001031992243075413,
+      "loss": 0.0003,
+      "step": 650
+    },
+    {
+      "epoch": 16.5,
+      "grad_norm": 0.007002962753176689,
+      "learning_rate": 0.00010029088779843621,
+      "loss": 0.0003,
+      "step": 660
+    },
+    {
+      "epoch": 16.75,
+      "grad_norm": 0.007640474010258913,
+      "learning_rate": 9.73823051692127e-05,
+      "loss": 0.0003,
+      "step": 670
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.008249858394265175,
+      "learning_rate": 9.447593737115516e-05,
+      "loss": 0.0003,
+      "step": 680
+    },
+    {
+      "epoch": 17.25,
+      "grad_norm": 0.005113428458571434,
+      "learning_rate": 9.157424348157972e-05,
+      "loss": 0.0003,
+      "step": 690
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 0.007044928148388863,
+      "learning_rate": 8.867967862320934e-05,
+      "loss": 0.0003,
+      "step": 700
+    },
+    {
+      "epoch": 17.75,
+      "grad_norm": 0.0062586585991084576,
+      "learning_rate": 8.579469188689475e-05,
+      "loss": 0.0003,
+      "step": 710
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.0065957107581198215,
+      "learning_rate": 8.292172425943934e-05,
+      "loss": 0.0003,
+      "step": 720
+    },
+    {
+      "epoch": 18.25,
+      "grad_norm": 0.004304594825953245,
+      "learning_rate": 8.00632065582803e-05,
+      "loss": 0.0002,
+      "step": 730
+    },
+    {
+      "epoch": 18.5,
+      "grad_norm": 0.004898569546639919,
+      "learning_rate": 7.722155737477466e-05,
+      "loss": 0.0003,
+      "step": 740
+    },
+    {
+      "epoch": 18.75,
+      "grad_norm": 0.006634353660047054,
+      "learning_rate": 7.439918102782944e-05,
+      "loss": 0.0003,
+      "step": 750
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.0058410619385540485,
+      "learning_rate": 7.159846552960774e-05,
+      "loss": 0.0003,
+      "step": 760
+    },
+    {
+      "epoch": 19.25,
+      "grad_norm": 0.00621160538867116,
+      "learning_rate": 6.88217805650322e-05,
+      "loss": 0.0003,
+      "step": 770
+    },
+    {
+      "epoch": 19.5,
+      "grad_norm": 0.005199102684855461,
+      "learning_rate": 6.60714754867949e-05,
+      "loss": 0.0002,
+      "step": 780
+    },
+    {
+      "epoch": 19.75,
+      "grad_norm": 0.005410065874457359,
+      "learning_rate": 6.334987732757029e-05,
+      "loss": 0.0003,
+      "step": 790
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.006572461687028408,
+      "learning_rate": 6.0659288831113516e-05,
+      "loss": 0.0003,
+      "step": 800
+    },
+    {
+      "epoch": 20.25,
+      "grad_norm": 0.004044756293296814,
+      "learning_rate": 5.8001986503909055e-05,
+      "loss": 0.0002,
+      "step": 810
+    },
+    {
+      "epoch": 20.5,
+      "grad_norm": 0.0064803618006408215,
+      "learning_rate": 5.5380218689019125e-05,
+      "loss": 0.0002,
+      "step": 820
+    },
+    {
+      "epoch": 20.75,
+      "grad_norm": 0.006396050099283457,
+      "learning_rate": 5.27962036637609e-05,
+      "loss": 0.0003,
+      "step": 830
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.004065022338181734,
+      "learning_rate": 5.0252127762822375e-05,
+      "loss": 0.0002,
+      "step": 840
+    },
+    {
+      "epoch": 21.25,
+      "grad_norm": 0.005657975561916828,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0002,
+      "step": 850
+    },
+    {
+      "epoch": 21.5,
+      "grad_norm": 0.005015597678720951,
+      "learning_rate": 4.529236788895854e-05,
+      "loss": 0.0002,
+      "step": 860
+    },
+    {
+      "epoch": 21.75,
+      "grad_norm": 0.006195488385856152,
+      "learning_rate": 4.288088036804713e-05,
+      "loss": 0.0002,
+      "step": 870
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.005124359857290983,
+      "learning_rate": 4.0517721324865884e-05,
+      "loss": 0.0002,
+      "step": 880
+    },
+    {
+      "epoch": 22.25,
+      "grad_norm": 0.005272749345749617,
+      "learning_rate": 3.8204890227892686e-05,
+      "loss": 0.0002,
+      "step": 890
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 0.0042186155915260315,
+      "learning_rate": 3.594434396313848e-05,
+      "loss": 0.0002,
+      "step": 900
+    },
+    {
+      "epoch": 22.75,
+      "grad_norm": 0.004914261866360903,
+      "learning_rate": 3.373799517842627e-05,
+      "loss": 0.0002,
+      "step": 910
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.004066417925059795,
+      "learning_rate": 3.1587710665100024e-05,
+      "loss": 0.0002,
+      "step": 920
+    },
+    {
+      "epoch": 23.25,
+      "grad_norm": 0.0054823365062475204,
+      "learning_rate": 2.9495309778532966e-05,
+      "loss": 0.0002,
+      "step": 930
+    },
+    {
+      "epoch": 23.5,
+      "grad_norm": 0.004470289219170809,
+      "learning_rate": 2.746256289877126e-05,
+      "loss": 0.0002,
+      "step": 940
+    },
+    {
+      "epoch": 23.75,
+      "grad_norm": 0.005384424235671759,
+      "learning_rate": 2.5491189932615646e-05,
+      "loss": 0.0002,
+      "step": 950
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.004562985617667437,
+      "learning_rate": 2.3582858858408684e-05,
+      "loss": 0.0002,
+      "step": 960
+    },
+    {
+      "epoch": 24.25,
+      "grad_norm": 0.0052340407855808735,
+      "learning_rate": 2.173918431475861e-05,
+      "loss": 0.0002,
+      "step": 970
+    },
+    {
+      "epoch": 24.5,
+      "grad_norm": 0.004082779865711927,
+      "learning_rate": 1.996172623439363e-05,
+      "loss": 0.0002,
+      "step": 980
+    },
+    {
+      "epoch": 24.75,
+      "grad_norm": 0.004965928383171558,
+      "learning_rate": 1.8251988524303363e-05,
+      "loss": 0.0002,
+      "step": 990
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.005955494940280914,
+      "learning_rate": 1.661141779328319e-05,
+      "loss": 0.0002,
+      "step": 1000
+    },
+    {
+      "epoch": 25.25,
+      "grad_norm": 0.004189318045973778,
+      "learning_rate": 1.5041402127958948e-05,
+      "loss": 0.0002,
+      "step": 1010
+    },
+    {
+      "epoch": 25.5,
+      "grad_norm": 0.0051079061813652515,
+      "learning_rate": 1.3543269918326961e-05,
+      "loss": 0.0002,
+      "step": 1020
+    },
+    {
+      "epoch": 25.75,
+      "grad_norm": 0.004737610928714275,
+      "learning_rate": 1.2118288733803473e-05,
+      "loss": 0.0002,
+      "step": 1030
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.005510413553565741,
+      "learning_rate": 1.0767664250734466e-05,
+      "loss": 0.0002,
+      "step": 1040
+    },
+    {
+      "epoch": 26.25,
+      "grad_norm": 0.003644640324637294,
+      "learning_rate": 9.492539232273001e-06,
+      "loss": 0.0002,
+      "step": 1050
+    },
+    {
+      "epoch": 26.5,
+      "grad_norm": 0.005952645093202591,
+      "learning_rate": 8.293992561487596e-06,
+      "loss": 0.0002,
+      "step": 1060
+    },
+    {
+      "epoch": 26.75,
+      "grad_norm": 0.0034450222738087177,
+      "learning_rate": 7.173038328519344e-06,
+      "loss": 0.0002,
+      "step": 1070
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.0034657688811421394,
+      "learning_rate": 6.130624972560461e-06,
+      "loss": 0.0002,
+      "step": 1080
+    },
+    {
+      "epoch": 27.25,
+      "grad_norm": 0.006222739350050688,
+      "learning_rate": 5.167634479380068e-06,
+      "loss": 0.0002,
+      "step": 1090
+    },
+    {
+      "epoch": 27.5,
+      "grad_norm": 0.006043997593224049,
+      "learning_rate": 4.284881635076132e-06,
+      "loss": 0.0002,
+      "step": 1100
+    },
+    {
+      "epoch": 27.75,
+      "grad_norm": 0.00470092985779047,
+      "learning_rate": 3.4831133366850623e-06,
+      "loss": 0.0002,
+      "step": 1110
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.004548701923340559,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0002,
+      "step": 1120
+    },
+    {
+      "epoch": 28.25,
+      "grad_norm": 0.004792294930666685,
+      "learning_rate": 2.125174786758599e-06,
+      "loss": 0.0002,
+      "step": 1130
+    },
+    {
+      "epoch": 28.5,
+      "grad_norm": 0.004103948827832937,
+      "learning_rate": 1.5701534868070355e-06,
+      "loss": 0.0002,
+      "step": 1140
+    },
+    {
+      "epoch": 28.75,
+      "grad_norm": 0.00405226880684495,
+      "learning_rate": 1.0984136638083177e-06,
+      "loss": 0.0002,
+      "step": 1150
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 0.003278164891526103,
+      "learning_rate": 7.103544567491071e-07,
+      "loss": 0.0002,
+      "step": 1160
+    },
+    {
+      "epoch": 29.25,
+      "grad_norm": 0.005859719589352608,
+      "learning_rate": 4.0630420246071665e-07,
+      "loss": 0.0002,
+      "step": 1170
+    },
+    {
+      "epoch": 29.5,
+      "grad_norm": 0.00393211143091321,
+      "learning_rate": 1.86520157813308e-07,
+      "loss": 0.0002,
+      "step": 1180
+    },
+    {
+      "epoch": 29.75,
+      "grad_norm": 0.004771947395056486,
+      "learning_rate": 5.1188282050906864e-08,
+      "loss": 0.0002,
+      "step": 1190
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.003914570435881615,
+      "learning_rate": 4.2307945137265435e-10,
+      "loss": 0.0002,
+      "step": 1200
+    },
+    {
+      "epoch": 30.0,
+      "step": 1200,
+      "total_flos": 5518966123560960.0,
+      "train_loss": 0.2944723299946054,
+      "train_runtime": 391.3174,
+      "train_samples_per_second": 3.067,
+      "train_steps_per_second": 3.067
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5518966123560960.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "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": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}