Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ Qwen2-VL/Full/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen2-VL/Full/V7W/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen2-VL/Full/TextVQA/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen2-VL/Full/MathV/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-VL/Full/Fingerprint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen2-VL/Full/Fingerprint/README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Fingerprint
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Fingerprint
+
+This model is a fine-tuned version of [/data/xcw/model/Qwen2-VL-2B-Instruct/](https://huggingface.co//data/xcw/model/Qwen2-VL-2B-Instruct/) on the Fingerprint dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0792
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 12
+- total_eval_batch_size: 3
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.3.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

Qwen2-VL/Full/Fingerprint/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
+}

Qwen2-VL/Full/Fingerprint/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.545454545454545,
+    "eval_loss": 1.0792454481124878,
+    "eval_runtime": 3.048,
+    "eval_samples_per_second": 2.297,
+    "eval_steps_per_second": 0.984,
+    "total_flos": 3844425596928.0,
+    "train_loss": 0.29138397969305513,
+    "train_runtime": 173.6453,
+    "train_samples_per_second": 1.814,
+    "train_steps_per_second": 0.144
+}

Qwen2-VL/Full/Fingerprint/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

Qwen2-VL/Full/Fingerprint/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/data/xcw/model/Qwen2-VL-2B-Instruct/",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

Qwen2-VL/Full/Fingerprint/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.545454545454545,
+    "eval_loss": 1.0792454481124878,
+    "eval_runtime": 3.048,
+    "eval_samples_per_second": 2.297,
+    "eval_steps_per_second": 0.984
+}

Qwen2-VL/Full/Fingerprint/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.45.2"
+}

Qwen2-VL/Full/Fingerprint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac2572aa207cd22ec2eca4b1f171999fa22a6183f7b84400594fec972d3b635
+size 4418050848

Qwen2-VL/Full/Fingerprint/preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+    "size": {
+    "shortest_edge": 448,
+    "longest_edge": 448
+  },
+  "temporal_patch_size": 2
+}

Qwen2-VL/Full/Fingerprint/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
+  }
+}

Qwen2-VL/Full/Fingerprint/tokenizer.json

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

Qwen2-VL/Full/Fingerprint/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,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2-VL/Full/Fingerprint/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.545454545454545,
+    "total_flos": 3844425596928.0,
+    "train_loss": 0.29138397969305513,
+    "train_runtime": 173.6453,
+    "train_samples_per_second": 1.814,
+    "train_steps_per_second": 0.144
+}

Qwen2-VL/Full/Fingerprint/trainer_log.jsonl

@@ -0,0 +1 @@
+{"current_steps": 1, "total_steps": 20, "loss": 0.8204, "lr": 2e-05, "epoch": 0.25, "percentage": 5.0, "elapsed_time": "0:00:19", "remaining_time": "0:06:10"}

Qwen2-VL/Full/Fingerprint/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.545454545454545,
+  "eval_steps": 50000,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 4.741116192384917,
+      "learning_rate": 2e-05,
+      "loss": 0.7491,
+      "step": 1
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 7.737946469435016,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 1.0799,
+      "step": 2
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 7.825964084531432,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.7959,
+      "step": 3
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 6.276285352257505,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.8144,
+      "step": 4
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 5.7371220785691595,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.8349,
+      "step": 5
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 3.138888722035557,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 0.4229,
+      "step": 6
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 4.352418777488962,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.2988,
+      "step": 7
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 3.3132948553202226,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 0.3381,
+      "step": 8
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 3.1497519910420517,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.317,
+      "step": 9
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 4.76403502421096,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.284,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.723541436285857,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.3091,
+      "step": 11
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 4.246637756212984,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 0.1513,
+      "step": 12
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 3.187963215608874,
+      "learning_rate": 1e-05,
+      "loss": 0.1538,
+      "step": 13
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 2.00879349649311,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 0.0972,
+      "step": 14
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.5917835368972042,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.0809,
+      "step": 15
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 3.1942570614493184,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.1236,
+      "step": 16
+    },
+    {
+      "epoch": 3.090909090909091,
+      "grad_norm": 2.6620783111165625,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0682,
+      "step": 17
+    },
+    {
+      "epoch": 3.2727272727272725,
+      "grad_norm": 1.0650925087932157,
+      "learning_rate": 3.912385709912794e-06,
+      "loss": 0.0603,
+      "step": 18
+    },
+    {
+      "epoch": 3.4545454545454546,
+      "grad_norm": 0.9893390682796337,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.0277,
+      "step": 19
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 1.5893451823775342,
+      "learning_rate": 2.0664665970876496e-06,
+      "loss": 0.0286,
+      "step": 20
+    },
+    {
+      "epoch": 3.8181818181818183,
+      "grad_norm": 1.1313925852247455,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.0481,
+      "step": 21
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2724397721277956,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.0613,
+      "step": 22
+    },
+    {
+      "epoch": 4.181818181818182,
+      "grad_norm": 0.9456624994504107,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.0472,
+      "step": 23
+    },
+    {
+      "epoch": 4.363636363636363,
+      "grad_norm": 1.157671829911023,
+      "learning_rate": 8.555138626189619e-08,
+      "loss": 0.0506,
+      "step": 24
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.9301732922378104,
+      "learning_rate": 0.0,
+      "loss": 0.0419,
+      "step": 25
+    },
+    {
+      "epoch": 4.545454545454545,
+      "step": 25,
+      "total_flos": 3844425596928.0,
+      "train_loss": 0.29138397969305513,
+      "train_runtime": 173.6453,
+      "train_samples_per_second": 1.814,
+      "train_steps_per_second": 0.144
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3844425596928.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2-VL/Full/Fingerprint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100940988487b697cfedd4ac95948f7c2bfd555db1ec8f32712555b6260491d4
+size 7224