| [INFO|2025-02-10 15:14:00] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 15:14:00] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-AWQ", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file vocab.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/vocab.json | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file merges.txt from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/merges.txt | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file tokenizer.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/tokenizer.json | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file added_tokens.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/added_tokens.json | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file special_tokens_map.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/special_tokens_map.json | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file tokenizer_config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/tokenizer_config.json | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2030 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-02-10 15:14:01] tokenization_utils_base.py:2300 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|2025-02-10 15:14:02] image_processing_base.py:378 >> loading configuration file preprocessor_config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/preprocessor_config.json | |
| [INFO|2025-02-10 15:14:02] image_processing_base.py:378 >> loading configuration file preprocessor_config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/preprocessor_config.json | |
| [INFO|2025-02-10 15:14:02] image_processing_base.py:432 >> 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": 1003520, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "max_pixels": 1003520, | |
| "min_pixels": 3136 | |
| }, | |
| "temporal_patch_size": 2, | |
| "vision_token_id": 151654 | |
| } | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file vocab.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/vocab.json | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file merges.txt from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/merges.txt | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file tokenizer.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/tokenizer.json | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file added_tokens.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/added_tokens.json | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file special_tokens_map.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/special_tokens_map.json | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file tokenizer_config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/tokenizer_config.json | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2030 >> loading file chat_template.jinja from cache at None | |
| [INFO|2025-02-10 15:14:02] tokenization_utils_base.py:2300 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|2025-02-10 15:14:03] processing_utils.py:780 >> 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": 1003520, | |
| "merge_size": 2, | |
| "min_pixels": 3136, | |
| "patch_size": 14, | |
| "processor_class": "Qwen2VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "max_pixels": 1003520, | |
| "min_pixels": 3136 | |
| }, | |
| "temporal_patch_size": 2, | |
| "vision_token_id": 151654 | |
| } | |
| - tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2-VL-2B-Instruct-AWQ', 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|2025-02-10 15:14:03] logging.py:157 >> Add <|im_end|> to stop words. | |
| [INFO|2025-02-10 15:14:03] logging.py:157 >> Loading dataset qwen2_vl_dora.json... | |
| [INFO|2025-02-10 15:14:17] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 15:14:17] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-AWQ", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 15:14:17] logging.py:157 >> Loading 4-bit AWQ-quantized model. | |
| [INFO|2025-02-10 15:16:00] modeling_utils.py:3953 >> loading weights file model.safetensors from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/model.safetensors | |
| [INFO|2025-02-10 15:16:00] modeling_utils.py:1641 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.float16. | |
| [INFO|2025-02-10 15:16:00] configuration_utils.py:1140 >> Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645 | |
| } | |
| [INFO|2025-02-10 15:16:00] modeling_utils.py:1641 >> Instantiating Qwen2VisionTransformerPretrainedModel model under default dtype torch.float16. | |
| [WARNING|2025-02-10 15:16:00] logging.py:328 >> `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|2025-02-10 15:16:02] modeling_utils.py:4849 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration. | |
| [INFO|2025-02-10 15:16:02] modeling_utils.py:4857 >> All the weights of Qwen2VLForConditionalGeneration were initialized from the model checkpoint at Qwen/Qwen2-VL-2B-Instruct-AWQ. | |
| 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|2025-02-10 15:16:02] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/generation_config.json | |
| [INFO|2025-02-10 15:16:02] configuration_utils.py:1140 >> 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|2025-02-10 15:16:02] logging.py:157 >> Gradient checkpointing enabled. | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Casting multimodal projector outputs in torch.float16. | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Using torch SDPA for faster training and inference. | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Upcasting trainable params to float32. | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Fine-tuning method: LoRA | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Found linear modules: q_proj,v_proj,k_proj,o_proj,up_proj,down_proj,gate_proj | |
| [INFO|2025-02-10 15:16:02] logging.py:157 >> Set vision model not trainable: ['visual.patch_embed', 'visual.blocks']. | |
| [INFO|2025-02-10 15:16:03] logging.py:157 >> trainable params: 9,232,384 || all params: 907,964,928 || trainable%: 1.0168 | |
| [INFO|2025-02-10 15:16:03] trainer.py:734 >> Using auto half precision backend | |
| [INFO|2025-02-10 15:16:03] trainer.py:2362 >> ***** Running training ***** | |
| [INFO|2025-02-10 15:16:03] trainer.py:2363 >> Num examples = 565 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2364 >> Num Epochs = 3 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2365 >> Instantaneous batch size per device = 2 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2368 >> Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2369 >> Gradient Accumulation steps = 8 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2370 >> Total optimization steps = 105 | |
| [INFO|2025-02-10 15:16:03] trainer.py:2371 >> Number of trainable parameters = 9,232,384 | |
| [INFO|2025-02-10 15:18:30] logging.py:157 >> {'loss': 4.3219, 'learning_rate': 4.9721e-05, 'epoch': 0.14, 'throughput': 610.23} | |
| [INFO|2025-02-10 15:20:41] logging.py:157 >> {'loss': 2.7795, 'learning_rate': 4.8889e-05, 'epoch': 0.28, 'throughput': 625.65} | |
| [INFO|2025-02-10 15:22:49] logging.py:157 >> {'loss': 3.1788, 'learning_rate': 4.7839e-05, 'epoch': 0.42, 'throughput': 631.57} | |
| [INFO|2025-02-10 15:25:25] logging.py:157 >> {'loss': 2.8887, 'learning_rate': 4.6068e-05, 'epoch': 0.57, 'throughput': 630.67} | |
| [INFO|2025-02-10 15:27:48] logging.py:157 >> {'loss': 2.5454, 'learning_rate': 4.3827e-05, 'epoch': 0.71, 'throughput': 631.72} | |
| [INFO|2025-02-10 15:30:11] logging.py:157 >> {'loss': 2.2010, 'learning_rate': 4.1165e-05, 'epoch': 0.85, 'throughput': 632.41} | |
| [INFO|2025-02-10 15:32:29] logging.py:157 >> {'loss': 1.3345, 'learning_rate': 3.8142e-05, 'epoch': 0.99, 'throughput': 630.92} | |
| [INFO|2025-02-10 15:34:37] logging.py:157 >> {'loss': 0.9507, 'learning_rate': 3.4826e-05, 'epoch': 1.11, 'throughput': 631.24} | |
| [INFO|2025-02-10 15:37:03] logging.py:157 >> {'loss': 0.6257, 'learning_rate': 3.1290e-05, 'epoch': 1.25, 'throughput': 631.56} | |
| [INFO|2025-02-10 15:39:22] logging.py:157 >> {'loss': 1.9766, 'learning_rate': 2.7613e-05, 'epoch': 1.40, 'throughput': 629.20} | |
| [INFO|2025-02-10 15:39:22] trainer.py:3887 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50 | |
| [INFO|2025-02-10 15:39:22] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 15:39:22] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-319", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 15:39:22] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/tokenizer_config.json | |
| [INFO|2025-02-10 15:39:22] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/special_tokens_map.json | |
| [INFO|2025-02-10 15:39:23] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/preprocessor_config.json | |
| [INFO|2025-02-10 15:39:23] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/tokenizer_config.json | |
| [INFO|2025-02-10 15:39:23] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/special_tokens_map.json | |
| [INFO|2025-02-10 15:39:23] processing_utils.py:546 >> chat template saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-50/chat_template.json | |
| [INFO|2025-02-10 15:41:43] logging.py:157 >> {'loss': 1.0377, 'learning_rate': 2.3878e-05, 'epoch': 1.54, 'throughput': 629.38} | |
| [INFO|2025-02-10 15:44:11] logging.py:157 >> {'loss': 1.5486, 'learning_rate': 2.0169e-05, 'epoch': 1.68, 'throughput': 627.11} | |
| [INFO|2025-02-10 15:46:23] logging.py:157 >> {'loss': 0.7542, 'learning_rate': 1.6567e-05, 'epoch': 1.82, 'throughput': 628.22} | |
| [INFO|2025-02-10 15:48:46] logging.py:157 >> {'loss': 0.7561, 'learning_rate': 1.3153e-05, 'epoch': 1.96, 'throughput': 628.73} | |
| [INFO|2025-02-10 15:50:33] logging.py:157 >> {'loss': 0.7300, 'learning_rate': 1.0004e-05, 'epoch': 2.08, 'throughput': 629.72} | |
| [INFO|2025-02-10 15:52:41] logging.py:157 >> {'loss': 0.5124, 'learning_rate': 7.1906e-06, 'epoch': 2.23, 'throughput': 630.55} | |
| [INFO|2025-02-10 15:55:04] logging.py:157 >> {'loss': 0.7801, 'learning_rate': 4.7746e-06, 'epoch': 2.37, 'throughput': 630.83} | |
| [INFO|2025-02-10 15:57:38] logging.py:157 >> {'loss': 0.3849, 'learning_rate': 2.8104e-06, 'epoch': 2.51, 'throughput': 629.03} | |
| [INFO|2025-02-10 15:59:56] logging.py:157 >> {'loss': 0.4539, 'learning_rate': 1.3418e-06, 'epoch': 2.65, 'throughput': 629.45} | |
| [INFO|2025-02-10 16:02:20] logging.py:157 >> {'loss': 1.1474, 'learning_rate': 4.0176e-07, 'epoch': 2.79, 'throughput': 628.90} | |
| [INFO|2025-02-10 16:02:20] trainer.py:3887 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100 | |
| [INFO|2025-02-10 16:02:21] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 16:02:21] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-319", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 16:02:21] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/tokenizer_config.json | |
| [INFO|2025-02-10 16:02:21] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/special_tokens_map.json | |
| [INFO|2025-02-10 16:02:21] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/preprocessor_config.json | |
| [INFO|2025-02-10 16:02:21] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/tokenizer_config.json | |
| [INFO|2025-02-10 16:02:21] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/special_tokens_map.json | |
| [INFO|2025-02-10 16:02:22] processing_utils.py:546 >> chat template saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-100/chat_template.json | |
| [INFO|2025-02-10 16:04:55] logging.py:157 >> {'loss': 0.7139, 'learning_rate': 1.1189e-08, 'epoch': 2.93, 'throughput': 627.96} | |
| [INFO|2025-02-10 16:04:55] trainer.py:3887 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105 | |
| [INFO|2025-02-10 16:04:55] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 16:04:55] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-319", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 16:04:55] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/tokenizer_config.json | |
| [INFO|2025-02-10 16:04:55] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/special_tokens_map.json | |
| [INFO|2025-02-10 16:04:56] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/preprocessor_config.json | |
| [INFO|2025-02-10 16:04:56] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/tokenizer_config.json | |
| [INFO|2025-02-10 16:04:56] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/special_tokens_map.json | |
| [INFO|2025-02-10 16:04:56] processing_utils.py:546 >> chat template saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/checkpoint-105/chat_template.json | |
| [INFO|2025-02-10 16:04:56] trainer.py:2636 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|2025-02-10 16:04:56] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/preprocessor_config.json | |
| [INFO|2025-02-10 16:04:56] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/tokenizer_config.json | |
| [INFO|2025-02-10 16:04:56] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/special_tokens_map.json | |
| [INFO|2025-02-10 16:04:57] processing_utils.py:546 >> chat template saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/chat_template.json | |
| [INFO|2025-02-10 16:04:57] trainer.py:3887 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ | |
| [INFO|2025-02-10 16:04:57] configuration_utils.py:695 >> loading configuration file config.json from cache at /home/intern01/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct-AWQ/snapshots/4f6ea6d22fcf0f8c1ed64d1d2a3d722d4d7bbcea/config.json | |
| [INFO|2025-02-10 16:04:57] configuration_utils.py:762 >> Model config Qwen2VLConfig { | |
| "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct-319", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": [ | |
| "visual" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "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": "float16", | |
| "transformers_version": "4.47.1", | |
| "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|2025-02-10 16:04:57] tokenization_utils_base.py:2485 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/tokenizer_config.json | |
| [INFO|2025-02-10 16:04:57] tokenization_utils_base.py:2494 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct-AWQ/lora/250210_Abroad_LoRA_2B_AWQ/special_tokens_map.json | |
| [WARNING|2025-02-10 16:04:58] logging.py:162 >> No metric eval_loss to plot. | |
| [WARNING|2025-02-10 16:04:58] logging.py:162 >> No metric eval_accuracy to plot. | |
| [INFO|2025-02-10 16:04:58] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |