| [INFO|configuration_utils.py:675] 2024-10-08 13:12:28,228 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:12:28,231 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,465 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/vocab.json | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,466 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/merges.txt | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,466 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer.json | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,466 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,466 >> loading file special_tokens_map.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:28,466 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2470] 2024-10-08 13:12:28,839 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|image_processing_base.py:375] 2024-10-08 13:12:29,629 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/preprocessor_config.json | |
| [INFO|image_processing_base.py:375] 2024-10-08 13:12:29,862 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/preprocessor_config.json | |
| [INFO|image_processing_base.py:429] 2024-10-08 13:12:29,863 >> Image processor Qwen2VLImageProcessor { | |
| "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 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,096 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/vocab.json | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,097 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/merges.txt | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,097 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer.json | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,097 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,097 >> loading file special_tokens_map.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-08 13:12:30,097 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2470] 2024-10-08 13:12:30,479 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|processing_utils.py:744] 2024-10-08 13:12:31,621 >> Processor Qwen2VLProcessor: | |
| - image_processor: Qwen2VLImageProcessor { | |
| "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 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |
| - tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2-VL-2B-Instruct', vocab_size=151643, model_max_length=32768, is_fast=True, padding_side='left', 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), | |
| } | |
| { | |
| "processor_class": "Qwen2VLProcessor" | |
| } | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:12:32,821 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:12:32,822 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/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": true, | |
| "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 | |
| } | |
| [INFO|modeling_utils.py:3732] 2024-10-08 13:12:32,836 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/model.safetensors.index.json | |
| [INFO|modeling_utils.py:1622] 2024-10-08 13:12:32,837 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.bfloat16. | |
| [INFO|configuration_utils.py:1099] 2024-10-08 13:12:32,838 >> Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645 | |
| } | |
| [WARNING|logging.py:328] 2024-10-08 13:12:32,862 >> `Qwen2VLRotaryEmbedding` can now be fully parameterized by passing the model config through the `config` argument. All other arguments will be removed in v4.46 | |
| [INFO|modeling_utils.py:4574] 2024-10-08 13:12:35,139 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration. | |
| [INFO|modeling_utils.py:4582] 2024-10-08 13:12:35,139 >> All the weights of Qwen2VLForConditionalGeneration were initialized from the model checkpoint at Qwen/Qwen2-VL-2B-Instruct. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2VLForConditionalGeneration for predictions without further training. | |
| [INFO|configuration_utils.py:1054] 2024-10-08 13:12:35,374 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/generation_config.json | |
| [INFO|configuration_utils.py:1099] 2024-10-08 13:12:35,374 >> Generate config GenerationConfig { | |
| "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 | |
| } | |
| [INFO|trainer.py:667] 2024-10-08 13:12:35,844 >> Using auto half precision backend | |
| [INFO|trainer.py:2243] 2024-10-08 13:12:36,413 >> ***** Running training ***** | |
| [INFO|trainer.py:2244] 2024-10-08 13:12:36,413 >> Num examples = 28,299 | |
| [INFO|trainer.py:2245] 2024-10-08 13:12:36,413 >> Num Epochs = 2 | |
| [INFO|trainer.py:2246] 2024-10-08 13:12:36,413 >> Instantaneous batch size per device = 2 | |
| [INFO|trainer.py:2249] 2024-10-08 13:12:36,414 >> Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| [INFO|trainer.py:2250] 2024-10-08 13:12:36,414 >> Gradient Accumulation steps = 8 | |
| [INFO|trainer.py:2251] 2024-10-08 13:12:36,414 >> Total optimization steps = 3,536 | |
| [INFO|trainer.py:2252] 2024-10-08 13:12:36,420 >> Number of trainable parameters = 9,232,384 | |
| [INFO|trainer.py:3705] 2024-10-08 13:20:36,530 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-100 | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:20:37,113 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:20:37,115 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 13:20:37,195 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 13:20:37,195 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 13:20:37,571 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 13:28:37,870 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-200 | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:28:38,362 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:28:38,364 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 13:28:38,442 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 13:28:38,443 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 13:28:38,840 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 13:36:40,245 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-300 | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:36:40,753 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:36:40,755 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 13:36:40,844 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 13:36:40,845 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 13:36:41,255 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 13:44:40,299 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-400 | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:44:40,804 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:44:40,806 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 13:44:40,887 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 13:44:40,887 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 13:44:41,291 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 13:52:43,216 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-500 | |
| [INFO|configuration_utils.py:675] 2024-10-08 13:52:43,727 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 13:52:43,728 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 13:52:43,808 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 13:52:43,809 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 13:52:44,206 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:00:42,108 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-600 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:00:42,640 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:00:42,642 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:00:42,720 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:00:42,720 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:00:43,111 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:08:43,399 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-700 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:08:43,915 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:08:43,917 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:08:43,996 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-700/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:08:43,997 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-700/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:08:44,383 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-700/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:16:43,300 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-800 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:16:43,801 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:16:43,803 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:16:43,882 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-800/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:16:43,882 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-800/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:16:44,277 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-800/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:24:44,545 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-900 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:24:45,056 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:24:45,058 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:24:45,135 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-900/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:24:45,136 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-900/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:24:45,515 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-900/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:32:43,816 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1000 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:32:44,539 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:32:44,541 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:32:44,619 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1000/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:32:44,620 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1000/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:32:45,008 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1000/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:40:44,092 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1100 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:40:44,623 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:40:44,625 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:40:44,704 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:40:44,704 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:40:45,088 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:48:44,238 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1200 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:48:44,752 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:48:44,754 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:48:44,834 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:48:44,834 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:48:45,216 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 14:56:45,544 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1300 | |
| [INFO|configuration_utils.py:675] 2024-10-08 14:56:46,061 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 14:56:46,063 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 14:56:46,142 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 14:56:46,142 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 14:56:46,522 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:04:43,671 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1400 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:04:44,208 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:04:44,210 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:04:44,291 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:04:44,291 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:04:44,667 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:12:42,210 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1500 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:12:43,006 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:12:43,007 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:12:43,088 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:12:43,089 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:12:43,473 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:20:40,861 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1600 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:20:41,376 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:20:41,378 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:20:41,457 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:20:41,458 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:20:41,836 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:28:39,662 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1700 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:28:40,179 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:28:40,181 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:28:40,260 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1700/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:28:40,260 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1700/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:28:40,651 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1700/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:36:40,815 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1800 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:36:41,314 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:36:41,315 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:36:41,395 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1800/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:36:41,396 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1800/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:36:41,785 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1800/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:44:39,876 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1900 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:44:40,826 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:44:40,828 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:44:40,906 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1900/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:44:40,906 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1900/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:44:41,301 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-1900/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 15:52:40,583 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2000 | |
| [INFO|configuration_utils.py:675] 2024-10-08 15:52:41,107 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 15:52:41,109 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 15:52:41,189 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2000/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 15:52:41,189 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2000/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 15:52:41,587 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2000/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:00:42,963 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2100 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:00:43,570 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:00:43,572 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:00:43,651 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:00:43,651 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:00:44,032 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:08:42,712 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2200 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:08:43,246 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:08:43,248 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:08:43,325 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:08:43,326 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:08:43,706 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:16:44,504 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2300 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:16:45,031 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:16:45,033 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:16:45,111 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:16:45,111 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:16:45,523 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:24:43,314 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2400 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:24:43,895 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:24:43,898 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:24:43,977 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:24:43,978 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:24:44,387 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:32:41,991 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2500 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:32:42,482 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:32:42,484 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:32:42,563 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:32:42,564 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:32:42,952 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:40:45,982 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2600 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:40:46,487 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:40:46,489 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:40:46,568 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:40:46,569 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:40:46,982 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:48:48,915 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2700 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:48:49,600 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:48:49,602 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:48:49,680 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2700/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:48:49,681 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2700/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:48:50,057 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2700/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 16:56:47,466 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2800 | |
| [INFO|configuration_utils.py:675] 2024-10-08 16:56:47,964 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 16:56:47,966 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 16:56:48,044 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2800/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 16:56:48,045 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2800/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 16:56:48,449 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2800/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:04:44,314 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2900 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:04:44,815 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:04:44,816 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:04:44,894 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2900/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:04:44,895 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2900/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:04:45,280 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-2900/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:12:42,327 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3000 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:12:42,820 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:12:42,822 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:12:42,901 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3000/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:12:42,902 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3000/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:12:43,286 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3000/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:20:38,760 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3100 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:20:39,276 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:20:39,278 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:20:39,355 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:20:39,356 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:20:39,756 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:28:37,513 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3200 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:28:38,044 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:28:38,046 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:28:38,126 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:28:38,126 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:28:38,521 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:36:37,328 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3300 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:36:37,831 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:36:37,833 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:36:37,913 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:36:37,913 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:36:38,305 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:44:36,588 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3400 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:44:37,156 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:44:37,158 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:44:37,236 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:44:37,236 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:44:37,635 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:52:36,896 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3500 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:52:37,389 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:52:37,390 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:52:37,468 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:52:37,468 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:52:37,856 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:55:30,913 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3536 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:55:31,403 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:55:31,405 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:55:31,484 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3536/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:55:31,485 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3536/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:55:31,884 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/checkpoint-3536/preprocessor_config.json | |
| [INFO|trainer.py:2505] 2024-10-08 17:55:31,885 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|image_processing_base.py:258] 2024-10-08 17:55:31,887 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-08 17:55:31,888 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54 | |
| [INFO|configuration_utils.py:675] 2024-10-08 17:55:32,377 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json | |
| [INFO|configuration_utils.py:742] 2024-10-08 17:55:32,379 >> Model config Qwen2VLConfig { | |
| "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": true, | |
| "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 | |
| } | |
| [INFO|tokenization_utils_base.py:2641] 2024-10-08 17:55:32,458 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-08 17:55:32,459 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-08-13-11-54/special_tokens_map.json | |
| [INFO|modelcard.py:449] 2024-10-08 17:55:32,848 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |