| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/vocab.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/merges.txt | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/tokenizer.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file special_tokens_map.json from cache at None | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/tokenizer_config.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2336 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|2025-09-10 08:36:51] image_processing_base.py:378 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/preprocessor_config.json | |
| [INFO|2025-09-10 08:36:51] image_processing_base.py:378 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/preprocessor_config.json | |
| [INFO|2025-09-10 08:36:51] image_processing_base.py:423 >> Image processor Qwen2VLImageProcessorFast { | |
| "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_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, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/vocab.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/merges.txt | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/tokenizer.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file special_tokens_map.json from cache at None | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/tokenizer_config.json | |
| [INFO|2025-09-10 08:36:51] tokenization_utils_base.py:2067 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-09-10 08:36:52] tokenization_utils_base.py:2336 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [WARNING|2025-09-10 08:36:52] logging.py:328 >> You have video processor config saved in `preprocessor.json` file which is deprecated. Video processor configs should be saved in their own `video_preprocessor.json` file. You can rename the file or load and save the processor back which renames it automatically. Loading from `preprocessor.json` will be removed in v5.0. | |
| [INFO|2025-09-10 08:36:52] video_processing_utils.py:720 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/preprocessor_config.json | |
| [INFO|2025-09-10 08:36:52] video_processing_utils.py:764 >> Video processor Qwen2VLVideoProcessor { | |
| "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_pad": null, | |
| "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, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "size_divisor": null, | |
| "temporal_patch_size": 2, | |
| "video_metadata": null, | |
| "video_processor_type": "Qwen2VLVideoProcessor" | |
| } | |
| [INFO|2025-09-10 08:36:53] processing_utils.py:1117 >> Processor Qwen2_5_VLProcessor: | |
| - image_processor: Qwen2VLImageProcessorFast { | |
| "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_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, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |
| - tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-VL-7B-Instruct', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', '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|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={ | |
| 151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), | |
| 151657: AddedToken("<tool_call>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151658: AddedToken("</tool_call>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151659: AddedToken("<|fim_prefix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151660: AddedToken("<|fim_middle|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151661: AddedToken("<|fim_suffix|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151662: AddedToken("<|fim_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151663: AddedToken("<|repo_name|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| 151664: AddedToken("<|file_sep|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=False), | |
| } | |
| ) | |
| - video_processor: Qwen2VLVideoProcessor { | |
| "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_pad": null, | |
| "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, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 12845056, | |
| "shortest_edge": 3136 | |
| }, | |
| "size_divisor": null, | |
| "temporal_patch_size": 2, | |
| "video_metadata": null, | |
| "video_processor_type": "Qwen2VLVideoProcessor" | |
| } | |
| { | |
| "processor_class": "Qwen2_5_VLProcessor" | |
| } | |
| [INFO|2025-09-10 08:36:53] logging.py:143 >> Loading dataset BsKIE3.json... | |
| [INFO|2025-09-10 08:40:28] configuration_utils.py:752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/config.json | |
| [INFO|2025-09-10 08:40:28] configuration_utils.py:817 >> Model config Qwen2_5_VLConfig { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |
| [INFO|2025-09-10 08:40:28] logging.py:143 >> KV cache is disabled during training. | |
| [INFO|2025-09-10 08:40:28] modeling_utils.py:1309 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/model.safetensors.index.json | |
| [INFO|2025-09-10 08:40:28] modeling_utils.py:2412 >> Instantiating Qwen2_5_VLForConditionalGeneration model under default dtype torch.bfloat16. | |
| [INFO|2025-09-10 08:40:28] configuration_utils.py:1098 >> Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "use_cache": false | |
| } | |
| [INFO|2025-09-10 08:40:28] modeling_utils.py:2412 >> Instantiating Qwen2_5_VisionTransformerPretrainedModel model under default dtype torch.bfloat16. | |
| [INFO|2025-09-10 08:40:28] modeling_utils.py:2412 >> Instantiating Qwen2_5_VLTextModel model under default dtype torch.bfloat16. | |
| [INFO|2025-09-10 08:40:39] modeling_utils.py:5614 >> All model checkpoint weights were used when initializing Qwen2_5_VLForConditionalGeneration. | |
| [INFO|2025-09-10 08:40:39] modeling_utils.py:5622 >> All the weights of Qwen2_5_VLForConditionalGeneration were initialized from the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2_5_VLForConditionalGeneration for predictions without further training. | |
| [INFO|2025-09-10 08:40:39] configuration_utils.py:1053 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/generation_config.json | |
| [INFO|2025-09-10 08:40:39] configuration_utils.py:1098 >> Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "temperature": 1e-06 | |
| } | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Gradient checkpointing enabled. | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Using torch SDPA for faster training and inference. | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Upcasting trainable params to float32. | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Fine-tuning method: LoRA | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Found linear modules: v_proj,o_proj,up_proj,k_proj,down_proj,q_proj,gate_proj | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Set vision model not trainable: ['visual.patch_embed', 'visual.blocks']. | |
| [INFO|2025-09-10 08:40:39] logging.py:143 >> Set multi model projector not trainable: visual.merger. | |
| [INFO|2025-09-10 08:40:40] logging.py:143 >> trainable params: 20,185,088 || all params: 8,312,351,744 || trainable%: 0.2428 | |
| [INFO|2025-09-10 08:40:40] trainer.py:757 >> Using auto half precision backend | |
| [INFO|2025-09-10 08:40:40] trainer.py:2433 >> ***** Running training ***** | |
| [INFO|2025-09-10 08:40:40] trainer.py:2434 >> Num examples = 1,495 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2435 >> Num Epochs = 3 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2436 >> Instantaneous batch size per device = 2 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2439 >> Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2440 >> Gradient Accumulation steps = 8 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2441 >> Total optimization steps = 282 | |
| [INFO|2025-09-10 08:40:40] trainer.py:2442 >> Number of trainable parameters = 20,185,088 | |
| [WARNING|2025-09-10 08:40:42] logging.py:328 >> `loss_type=None` was set in the config but it is unrecognised.Using the default loss: `ForCausalLMLoss`. | |
| [INFO|2025-09-10 08:42:11] logging.py:143 >> {'loss': 0.2185, 'learning_rate': 4.9975e-05, 'epoch': 0.05, 'throughput': 3058.36} | |
| [INFO|2025-09-10 08:43:45] logging.py:143 >> {'loss': 0.1329, 'learning_rate': 4.9874e-05, 'epoch': 0.11, 'throughput': 3055.20} | |
| [INFO|2025-09-10 08:45:23] logging.py:143 >> {'loss': 0.1124, 'learning_rate': 4.9697e-05, 'epoch': 0.16, 'throughput': 3042.04} | |
| [INFO|2025-09-10 08:46:59] logging.py:143 >> {'loss': 0.0841, 'learning_rate': 4.9442e-05, 'epoch': 0.21, 'throughput': 3046.79} | |
| [INFO|2025-09-10 08:48:31] logging.py:143 >> {'loss': 0.0670, 'learning_rate': 4.9112e-05, 'epoch': 0.27, 'throughput': 3053.41} | |
| [INFO|2025-09-10 08:50:03] logging.py:143 >> {'loss': 0.0633, 'learning_rate': 4.8707e-05, 'epoch': 0.32, 'throughput': 3059.39} | |
| [INFO|2025-09-10 08:51:36] logging.py:143 >> {'loss': 0.0508, 'learning_rate': 4.8228e-05, 'epoch': 0.37, 'throughput': 3062.17} | |
| [INFO|2025-09-10 08:53:08] logging.py:143 >> {'loss': 0.0452, 'learning_rate': 4.7677e-05, 'epoch': 0.43, 'throughput': 3064.58} | |
| [INFO|2025-09-10 08:54:41] logging.py:143 >> {'loss': 0.0401, 'learning_rate': 4.7056e-05, 'epoch': 0.48, 'throughput': 3064.56} | |
| [INFO|2025-09-10 08:56:14] logging.py:143 >> {'loss': 0.0418, 'learning_rate': 4.6367e-05, 'epoch': 0.53, 'throughput': 3066.16} | |
| [INFO|2025-09-10 08:57:50] logging.py:143 >> {'loss': 0.0468, 'learning_rate': 4.5611e-05, 'epoch': 0.59, 'throughput': 3063.56} | |
| [INFO|2025-09-10 08:59:22] logging.py:143 >> {'loss': 0.0421, 'learning_rate': 4.4791e-05, 'epoch': 0.64, 'throughput': 3065.33} | |
| [INFO|2025-09-10 09:00:55] logging.py:143 >> {'loss': 0.0400, 'learning_rate': 4.3910e-05, 'epoch': 0.70, 'throughput': 3065.66} | |
| [INFO|2025-09-10 09:02:28] logging.py:143 >> {'loss': 0.0279, 'learning_rate': 4.2971e-05, 'epoch': 0.75, 'throughput': 3066.01} | |
| [INFO|2025-09-10 09:04:00] logging.py:143 >> {'loss': 0.0322, 'learning_rate': 4.1975e-05, 'epoch': 0.80, 'throughput': 3067.38} | |
| [INFO|2025-09-10 09:05:32] logging.py:143 >> {'loss': 0.0340, 'learning_rate': 4.0927e-05, 'epoch': 0.86, 'throughput': 3068.16} | |
| [INFO|2025-09-10 09:07:02] logging.py:143 >> {'loss': 0.0388, 'learning_rate': 3.9829e-05, 'epoch': 0.91, 'throughput': 3070.18} | |
| [INFO|2025-09-10 09:08:29] logging.py:143 >> {'loss': 0.0395, 'learning_rate': 3.8686e-05, 'epoch': 0.96, 'throughput': 3073.05} | |
| [INFO|2025-09-10 09:09:56] logging.py:143 >> {'loss': 0.0300, 'learning_rate': 3.7500e-05, 'epoch': 1.01, 'throughput': 3070.50} | |
| [INFO|2025-09-10 09:11:31] logging.py:143 >> {'loss': 0.0282, 'learning_rate': 3.6275e-05, 'epoch': 1.06, 'throughput': 3070.00} | |
| [INFO|2025-09-10 09:11:31] trainer.py:4074 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100 | |
| [INFO|2025-09-10 09:11:31] configuration_utils.py:752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/config.json | |
| [INFO|2025-09-10 09:11:31] configuration_utils.py:817 >> Model config Qwen2_5_VLConfig { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |
| [INFO|2025-09-10 09:11:31] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/chat_template.jinja | |
| [INFO|2025-09-10 09:11:31] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/tokenizer_config.json | |
| [INFO|2025-09-10 09:11:31] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/special_tokens_map.json | |
| [INFO|2025-09-10 09:11:32] image_processing_base.py:258 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/preprocessor_config.json | |
| [INFO|2025-09-10 09:11:32] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/chat_template.jinja | |
| [INFO|2025-09-10 09:11:32] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/tokenizer_config.json | |
| [INFO|2025-09-10 09:11:32] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/special_tokens_map.json | |
| [INFO|2025-09-10 09:11:32] video_processing_utils.py:582 >> Video processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/video_preprocessor_config.json | |
| [INFO|2025-09-10 09:11:32] processing_utils.py:745 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-100/chat_template.jinja | |
| [INFO|2025-09-10 09:13:07] logging.py:143 >> {'loss': 0.0452, 'learning_rate': 3.5016e-05, 'epoch': 1.12, 'throughput': 3067.60} | |
| [INFO|2025-09-10 09:14:42] logging.py:143 >> {'loss': 0.0266, 'learning_rate': 3.3725e-05, 'epoch': 1.17, 'throughput': 3066.95} | |
| [INFO|2025-09-10 09:16:15] logging.py:143 >> {'loss': 0.0329, 'learning_rate': 3.2407e-05, 'epoch': 1.22, 'throughput': 3067.78} | |
| [INFO|2025-09-10 09:17:50] logging.py:143 >> {'loss': 0.0232, 'learning_rate': 3.1066e-05, 'epoch': 1.28, 'throughput': 3067.40} | |
| [INFO|2025-09-10 09:19:23] logging.py:143 >> {'loss': 0.0366, 'learning_rate': 2.9706e-05, 'epoch': 1.33, 'throughput': 3067.80} | |
| [INFO|2025-09-10 09:20:58] logging.py:143 >> {'loss': 0.0301, 'learning_rate': 2.8332e-05, 'epoch': 1.39, 'throughput': 3067.34} | |
| [INFO|2025-09-10 09:22:34] logging.py:143 >> {'loss': 0.0253, 'learning_rate': 2.6948e-05, 'epoch': 1.44, 'throughput': 3066.79} | |
| [INFO|2025-09-10 09:24:03] logging.py:143 >> {'loss': 0.0291, 'learning_rate': 2.5557e-05, 'epoch': 1.49, 'throughput': 3067.92} | |
| [INFO|2025-09-10 09:25:37] logging.py:143 >> {'loss': 0.0236, 'learning_rate': 2.4165e-05, 'epoch': 1.55, 'throughput': 3067.40} | |
| [INFO|2025-09-10 09:27:11] logging.py:143 >> {'loss': 0.0288, 'learning_rate': 2.2775e-05, 'epoch': 1.60, 'throughput': 3067.26} | |
| [INFO|2025-09-10 09:28:44] logging.py:143 >> {'loss': 0.0334, 'learning_rate': 2.1392e-05, 'epoch': 1.65, 'throughput': 3067.76} | |
| [INFO|2025-09-10 09:30:11] logging.py:143 >> {'loss': 0.0273, 'learning_rate': 2.0020e-05, 'epoch': 1.71, 'throughput': 3069.37} | |
| [INFO|2025-09-10 09:31:41] logging.py:143 >> {'loss': 0.0219, 'learning_rate': 1.8664e-05, 'epoch': 1.76, 'throughput': 3070.12} | |
| [INFO|2025-09-10 09:33:12] logging.py:143 >> {'loss': 0.0246, 'learning_rate': 1.7328e-05, 'epoch': 1.81, 'throughput': 3070.76} | |
| [INFO|2025-09-10 09:34:45] logging.py:143 >> {'loss': 0.0283, 'learning_rate': 1.6015e-05, 'epoch': 1.87, 'throughput': 3070.80} | |
| [INFO|2025-09-10 09:36:15] logging.py:143 >> {'loss': 0.0196, 'learning_rate': 1.4730e-05, 'epoch': 1.92, 'throughput': 3071.62} | |
| [INFO|2025-09-10 09:37:47] logging.py:143 >> {'loss': 0.0222, 'learning_rate': 1.3477e-05, 'epoch': 1.97, 'throughput': 3071.83} | |
| [INFO|2025-09-10 09:39:11] logging.py:143 >> {'loss': 0.0228, 'learning_rate': 1.2260e-05, 'epoch': 2.02, 'throughput': 3071.66} | |
| [INFO|2025-09-10 09:40:44] logging.py:143 >> {'loss': 0.0294, 'learning_rate': 1.1082e-05, 'epoch': 2.07, 'throughput': 3071.74} | |
| [INFO|2025-09-10 09:42:18] logging.py:143 >> {'loss': 0.0171, 'learning_rate': 9.9472e-06, 'epoch': 2.13, 'throughput': 3071.46} | |
| [INFO|2025-09-10 09:42:18] trainer.py:4074 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200 | |
| [INFO|2025-09-10 09:42:18] configuration_utils.py:752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/config.json | |
| [INFO|2025-09-10 09:42:18] configuration_utils.py:817 >> Model config Qwen2_5_VLConfig { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/chat_template.jinja | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/tokenizer_config.json | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/special_tokens_map.json | |
| [INFO|2025-09-10 09:42:18] image_processing_base.py:258 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/preprocessor_config.json | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/chat_template.jinja | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/tokenizer_config.json | |
| [INFO|2025-09-10 09:42:18] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/special_tokens_map.json | |
| [INFO|2025-09-10 09:42:18] video_processing_utils.py:582 >> Video processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/video_preprocessor_config.json | |
| [INFO|2025-09-10 09:42:19] processing_utils.py:745 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-200/chat_template.jinja | |
| [INFO|2025-09-10 09:43:49] logging.py:143 >> {'loss': 0.0199, 'learning_rate': 8.8593e-06, 'epoch': 2.18, 'throughput': 3071.28} | |
| [INFO|2025-09-10 09:45:21] logging.py:143 >> {'loss': 0.0250, 'learning_rate': 7.8215e-06, 'epoch': 2.24, 'throughput': 3071.79} | |
| [INFO|2025-09-10 09:46:55] logging.py:143 >> {'loss': 0.0191, 'learning_rate': 6.8369e-06, 'epoch': 2.29, 'throughput': 3071.27} | |
| [INFO|2025-09-10 09:48:30] logging.py:143 >> {'loss': 0.0276, 'learning_rate': 5.9087e-06, 'epoch': 2.34, 'throughput': 3070.96} | |
| [INFO|2025-09-10 09:50:02] logging.py:143 >> {'loss': 0.0299, 'learning_rate': 5.0397e-06, 'epoch': 2.40, 'throughput': 3071.27} | |
| [INFO|2025-09-10 09:51:36] logging.py:143 >> {'loss': 0.0230, 'learning_rate': 4.2326e-06, 'epoch': 2.45, 'throughput': 3071.07} | |
| [INFO|2025-09-10 09:53:10] logging.py:143 >> {'loss': 0.0224, 'learning_rate': 3.4900e-06, 'epoch': 2.50, 'throughput': 3071.01} | |
| [INFO|2025-09-10 09:54:41] logging.py:143 >> {'loss': 0.0246, 'learning_rate': 2.8140e-06, 'epoch': 2.56, 'throughput': 3071.67} | |
| [INFO|2025-09-10 09:56:10] logging.py:143 >> {'loss': 0.0249, 'learning_rate': 2.2069e-06, 'epoch': 2.61, 'throughput': 3072.55} | |
| [INFO|2025-09-10 09:57:42] logging.py:143 >> {'loss': 0.0226, 'learning_rate': 1.6705e-06, 'epoch': 2.66, 'throughput': 3072.70} | |
| [INFO|2025-09-10 09:59:15] logging.py:143 >> {'loss': 0.0188, 'learning_rate': 1.2064e-06, 'epoch': 2.72, 'throughput': 3072.67} | |
| [INFO|2025-09-10 10:00:47] logging.py:143 >> {'loss': 0.0222, 'learning_rate': 8.1619e-07, 'epoch': 2.77, 'throughput': 3072.99} | |
| [INFO|2025-09-10 10:02:19] logging.py:143 >> {'loss': 0.0230, 'learning_rate': 5.0096e-07, 'epoch': 2.82, 'throughput': 3073.21} | |
| [INFO|2025-09-10 10:03:57] logging.py:143 >> {'loss': 0.0211, 'learning_rate': 2.6172e-07, 'epoch': 2.88, 'throughput': 3072.52} | |
| [INFO|2025-09-10 10:05:32] logging.py:143 >> {'loss': 0.0306, 'learning_rate': 9.9221e-08, 'epoch': 2.93, 'throughput': 3072.24} | |
| [INFO|2025-09-10 10:07:04] logging.py:143 >> {'loss': 0.0195, 'learning_rate': 1.3961e-08, 'epoch': 2.98, 'throughput': 3072.67} | |
| [INFO|2025-09-10 10:07:30] trainer.py:4074 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282 | |
| [INFO|2025-09-10 10:07:30] configuration_utils.py:752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/config.json | |
| [INFO|2025-09-10 10:07:30] configuration_utils.py:817 >> Model config Qwen2_5_VLConfig { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/chat_template.jinja | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/tokenizer_config.json | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/special_tokens_map.json | |
| [INFO|2025-09-10 10:07:30] image_processing_base.py:258 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/preprocessor_config.json | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/chat_template.jinja | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/tokenizer_config.json | |
| [INFO|2025-09-10 10:07:30] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/special_tokens_map.json | |
| [INFO|2025-09-10 10:07:30] video_processing_utils.py:582 >> Video processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/video_preprocessor_config.json | |
| [INFO|2025-09-10 10:07:31] processing_utils.py:745 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/checkpoint-282/chat_template.jinja | |
| [INFO|2025-09-10 10:07:31] trainer.py:2718 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|2025-09-10 10:07:31] image_processing_base.py:258 >> Image processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/preprocessor_config.json | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/chat_template.jinja | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/tokenizer_config.json | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/special_tokens_map.json | |
| [INFO|2025-09-10 10:07:31] video_processing_utils.py:582 >> Video processor saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/video_preprocessor_config.json | |
| [INFO|2025-09-10 10:07:31] processing_utils.py:745 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/chat_template.jinja | |
| [INFO|2025-09-10 10:07:31] trainer.py:4074 >> Saving model checkpoint to saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54 | |
| [INFO|2025-09-10 10:07:31] configuration_utils.py:752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5/config.json | |
| [INFO|2025-09-10 10:07:31] configuration_utils.py:817 >> Model config Qwen2_5_VLConfig { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "text_config": { | |
| "architectures": [ | |
| "Qwen2_5_VLForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_5_vl_text", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": null, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_hidden_size": 3584, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 2, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/chat_template.jinja | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/tokenizer_config.json | |
| [INFO|2025-09-10 10:07:31] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen2.5-VL-7B-Instruct/lora/train_2025-09-10-08-35-54/special_tokens_map.json | |
| [WARNING|2025-09-10 10:07:32] logging.py:148 >> No metric eval_loss to plot. | |
| [WARNING|2025-09-10 10:07:32] logging.py:148 >> No metric eval_accuracy to plot. | |
| [INFO|2025-09-10 10:07:32] modelcard.py:456 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |