| [INFO|configuration_utils.py:675] 2024-10-09 12:45:03,028 >> 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] 2024-10-09 12:45:03,031 >> 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] 2024-10-09 12:45:04,989 >> 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] 2024-10-09 12:45:04,990 >> 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] 2024-10-09 12:45:04,990 >> 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] 2024-10-09 12:45:04,990 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-09 12:45:04,990 >> loading file special_tokens_map.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-09 12:45:04,990 >> 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] 2024-10-09 12:45:05,340 >> 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] 2024-10-09 12:45:05,687 >> 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] 2024-10-09 12:45:05,775 >> 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] 2024-10-09 12:45:05,776 >> 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] 2024-10-09 12:45:05,868 >> 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] 2024-10-09 12:45:05,868 >> 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] 2024-10-09 12:45:05,868 >> 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] 2024-10-09 12:45:05,868 >> loading file added_tokens.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-09 12:45:05,868 >> loading file special_tokens_map.json from cache at None | |
| [INFO|tokenization_utils_base.py:2206] 2024-10-09 12:45:05,868 >> 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] 2024-10-09 12:45:06,216 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|processing_utils.py:744] 2024-10-09 12:45:07,208 >> 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] 2024-10-09 12:46:22,901 >> 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] 2024-10-09 12:46:22,903 >> 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] 2024-10-09 12:46:23,276 >> 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] 2024-10-09 12:46:50,655 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.bfloat16. | |
| [INFO|configuration_utils.py:1099] 2024-10-09 12:46:50,657 >> Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645 | |
| } | |
| [WARNING|logging.py:328] 2024-10-09 12:46:50,909 >> `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] 2024-10-09 12:46:53,344 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration. | |
| [INFO|modeling_utils.py:4582] 2024-10-09 12:46:53,344 >> 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] 2024-10-09 12:46:53,525 >> 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] 2024-10-09 12:46:53,525 >> 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] 2024-10-09 12:46:54,254 >> Using auto half precision backend | |
| [INFO|trainer.py:2243] 2024-10-09 12:46:54,884 >> ***** Running training ***** | |
| [INFO|trainer.py:2244] 2024-10-09 12:46:54,884 >> Num examples = 21,224 | |
| [INFO|trainer.py:2245] 2024-10-09 12:46:54,884 >> Num Epochs = 2 | |
| [INFO|trainer.py:2246] 2024-10-09 12:46:54,884 >> Instantaneous batch size per device = 2 | |
| [INFO|trainer.py:2249] 2024-10-09 12:46:54,884 >> Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| [INFO|trainer.py:2250] 2024-10-09 12:46:54,884 >> Gradient Accumulation steps = 8 | |
| [INFO|trainer.py:2251] 2024-10-09 12:46:54,885 >> Total optimization steps = 2,652 | |
| [INFO|trainer.py:2252] 2024-10-09 12:46:54,890 >> Number of trainable parameters = 9,232,384 | |
| [INFO|trainer.py:3705] 2024-10-09 12:54:47,981 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-100 | |
| [INFO|configuration_utils.py:675] 2024-10-09 12:54:48,228 >> 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] 2024-10-09 12:54:48,230 >> 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] 2024-10-09 12:54:48,312 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 12:54:48,312 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 12:54:48,687 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:02:42,429 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-200 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:02:42,671 >> 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] 2024-10-09 13:02:42,673 >> 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] 2024-10-09 13:02:42,753 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:02:42,753 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:02:43,120 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:10:35,549 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-300 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:10:35,998 >> 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] 2024-10-09 13:10:36,000 >> 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] 2024-10-09 13:10:36,077 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:10:36,077 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:10:36,440 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:18:28,558 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-400 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:18:28,820 >> 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] 2024-10-09 13:18:28,821 >> 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] 2024-10-09 13:18:28,900 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:18:28,901 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:18:29,268 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:26:21,551 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-500 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:26:21,834 >> 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] 2024-10-09 13:26:21,836 >> 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] 2024-10-09 13:26:21,915 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:26:21,916 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:26:22,286 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:34:12,937 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-600 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:34:13,176 >> 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] 2024-10-09 13:34:13,178 >> 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] 2024-10-09 13:34:13,257 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:34:13,257 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:34:13,632 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:42:05,869 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-700 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:42:06,119 >> 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] 2024-10-09 13:42:06,122 >> 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] 2024-10-09 13:42:06,206 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-700/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:42:06,206 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-700/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:42:06,578 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-700/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:49:59,548 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-800 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:49:59,918 >> 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] 2024-10-09 13:49:59,920 >> 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] 2024-10-09 13:49:59,998 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-800/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:49:59,998 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-800/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:50:00,364 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-800/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 13:57:52,360 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-900 | |
| [INFO|configuration_utils.py:675] 2024-10-09 13:57:52,724 >> 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] 2024-10-09 13:57:52,726 >> 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] 2024-10-09 13:57:52,803 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-900/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 13:57:52,804 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-900/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 13:57:53,158 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-900/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:05:46,307 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1000 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:05:46,678 >> 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] 2024-10-09 14:05:46,680 >> 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] 2024-10-09 14:05:46,760 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1000/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:05:46,761 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1000/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:05:47,159 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1000/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:13:36,789 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1100 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:13:37,042 >> 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] 2024-10-09 14:13:37,044 >> 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] 2024-10-09 14:13:37,125 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:13:37,125 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:13:37,514 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:21:27,589 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1200 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:21:27,836 >> 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] 2024-10-09 14:21:27,837 >> 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] 2024-10-09 14:21:27,916 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:21:27,916 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:21:28,279 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:29:17,291 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1300 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:29:17,544 >> 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] 2024-10-09 14:29:17,546 >> 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] 2024-10-09 14:29:17,625 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:29:17,626 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:29:17,999 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:37:08,324 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1400 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:37:08,574 >> 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] 2024-10-09 14:37:08,576 >> 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] 2024-10-09 14:37:08,653 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:37:08,654 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:37:09,023 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:45:00,115 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1500 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:45:00,352 >> 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] 2024-10-09 14:45:00,354 >> 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] 2024-10-09 14:45:00,434 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:45:00,435 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:45:00,814 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 14:52:50,437 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1600 | |
| [INFO|configuration_utils.py:675] 2024-10-09 14:52:50,829 >> 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] 2024-10-09 14:52:50,831 >> 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] 2024-10-09 14:52:50,909 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 14:52:50,910 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 14:52:51,278 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:00:43,843 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1700 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:00:44,099 >> 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] 2024-10-09 15:00:44,101 >> 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] 2024-10-09 15:00:44,179 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1700/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:00:44,180 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1700/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:00:44,563 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1700/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:08:35,660 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1800 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:08:35,905 >> 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] 2024-10-09 15:08:35,907 >> 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] 2024-10-09 15:08:35,987 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1800/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:08:35,987 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1800/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:08:36,361 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1800/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:16:27,093 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1900 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:16:27,347 >> 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] 2024-10-09 15:16:27,350 >> 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] 2024-10-09 15:16:27,434 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1900/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:16:27,435 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1900/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:16:27,827 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-1900/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:24:17,107 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2000 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:24:17,356 >> 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] 2024-10-09 15:24:17,358 >> 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] 2024-10-09 15:24:17,437 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2000/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:24:17,438 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2000/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:24:17,834 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2000/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:32:07,838 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2100 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:32:08,083 >> 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] 2024-10-09 15:32:08,085 >> 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] 2024-10-09 15:32:08,162 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2100/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:32:08,163 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2100/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:32:08,564 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2100/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:39:57,441 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2200 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:39:57,712 >> 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] 2024-10-09 15:39:57,714 >> 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] 2024-10-09 15:39:57,792 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2200/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:39:57,793 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2200/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:39:58,162 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2200/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:47:48,947 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2300 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:47:49,189 >> 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] 2024-10-09 15:47:49,190 >> 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] 2024-10-09 15:47:49,270 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2300/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:47:49,270 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2300/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:47:49,662 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2300/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 15:55:43,626 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2400 | |
| [INFO|configuration_utils.py:675] 2024-10-09 15:55:44,004 >> 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] 2024-10-09 15:55:44,006 >> 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] 2024-10-09 15:55:44,085 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2400/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 15:55:44,085 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2400/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 15:55:44,485 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2400/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 16:03:36,647 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2500 | |
| [INFO|configuration_utils.py:675] 2024-10-09 16:03:36,905 >> 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] 2024-10-09 16:03:36,906 >> 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] 2024-10-09 16:03:36,984 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2500/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 16:03:36,985 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2500/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 16:03:37,373 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2500/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 16:11:28,270 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2600 | |
| [INFO|configuration_utils.py:675] 2024-10-09 16:11:28,651 >> 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] 2024-10-09 16:11:28,653 >> 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] 2024-10-09 16:11:28,731 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2600/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 16:11:28,731 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2600/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 16:11:29,100 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2600/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 16:15:32,206 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2652 | |
| [INFO|configuration_utils.py:675] 2024-10-09 16:15:32,458 >> 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] 2024-10-09 16:15:32,460 >> 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] 2024-10-09 16:15:32,539 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2652/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 16:15:32,539 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2652/special_tokens_map.json | |
| [INFO|image_processing_base.py:258] 2024-10-09 16:15:32,937 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/checkpoint-2652/preprocessor_config.json | |
| [INFO|trainer.py:2505] 2024-10-09 16:15:32,937 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|image_processing_base.py:258] 2024-10-09 16:15:32,939 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/preprocessor_config.json | |
| [INFO|trainer.py:3705] 2024-10-09 16:15:32,940 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31 | |
| [INFO|configuration_utils.py:675] 2024-10-09 16:15:33,140 >> 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] 2024-10-09 16:15:33,141 >> 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] 2024-10-09 16:15:33,221 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2650] 2024-10-09 16:15:33,221 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/lora/train_2024-10-09-12-44-31/special_tokens_map.json | |
| [INFO|modelcard.py:449] 2024-10-09 16:15:33,628 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |