File size: 15,847 Bytes
4550ffa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 |
[INFO|configuration_utils.py:672] 2024-10-07 10:46:19,862 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
[WARNING|modeling_rope_utils.py:379] 2024-10-07 10:46:19,863 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
[INFO|configuration_utils.py:739] 2024-10-07 10:46:19,865 >> 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": "4.45.0",
"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:2214] 2024-10-07 10:46:24,575 >> 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:2214] 2024-10-07 10:46:24,576 >> 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:2214] 2024-10-07 10:46:24,576 >> 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:2214] 2024-10-07 10:46:24,576 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2214] 2024-10-07 10:46:24,576 >> loading file special_tokens_map.json from cache at None
[INFO|tokenization_utils_base.py:2214] 2024-10-07 10:46:24,576 >> 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:2478] 2024-10-07 10:46:24,943 >> 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] 2024-10-07 10:46:25,869 >> 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] 2024-10-07 10:46:26,105 >> 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] 2024-10-07 10:46:26,105 >> 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:2214] 2024-10-07 10:46:26,342 >> 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:2214] 2024-10-07 10:46:26,342 >> 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:2214] 2024-10-07 10:46:26,342 >> 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:2214] 2024-10-07 10:46:26,342 >> loading file added_tokens.json from cache at None
[INFO|tokenization_utils_base.py:2214] 2024-10-07 10:46:26,342 >> loading file special_tokens_map.json from cache at None
[INFO|tokenization_utils_base.py:2214] 2024-10-07 10:46:26,342 >> 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:2478] 2024-10-07 10:46:26,691 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|processing_utils.py:744] 2024-10-07 10:46:27,998 >> 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:672] 2024-10-07 10:46:33,485 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-2B-Instruct/snapshots/aca78372505e6cb469c4fa6a35c60265b00ff5a4/config.json
[WARNING|modeling_rope_utils.py:379] 2024-10-07 10:46:33,486 >> Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
[INFO|configuration_utils.py:739] 2024-10-07 10:46:33,488 >> 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": "4.45.0",
"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:3726] 2024-10-07 10:46:34,699 >> 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] 2024-10-07 10:46:49,097 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.bfloat16.
[INFO|configuration_utils.py:1099] 2024-10-07 10:46:49,099 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
[WARNING|logging.py:328] 2024-10-07 10:46:49,381 >> `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:4568] 2024-10-07 10:46:51,825 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration.
[INFO|modeling_utils.py:4576] 2024-10-07 10:46:51,825 >> 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] 2024-10-07 10:46:52,385 >> 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] 2024-10-07 10:46:52,385 >> 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] 2024-10-07 10:46:52,481 >> Using auto half precision backend
[INFO|trainer.py:2243] 2024-10-07 10:46:53,044 >> ***** Running training *****
[INFO|trainer.py:2244] 2024-10-07 10:46:53,044 >> Num examples = 100
[INFO|trainer.py:2245] 2024-10-07 10:46:53,044 >> Num Epochs = 3
[INFO|trainer.py:2246] 2024-10-07 10:46:53,044 >> Instantaneous batch size per device = 2
[INFO|trainer.py:2249] 2024-10-07 10:46:53,045 >> Total train batch size (w. parallel, distributed & accumulation) = 16
[INFO|trainer.py:2250] 2024-10-07 10:46:53,045 >> Gradient Accumulation steps = 8
[INFO|trainer.py:2251] 2024-10-07 10:46:53,045 >> Total optimization steps = 18
[INFO|trainer.py:2252] 2024-10-07 10:46:53,047 >> Number of trainable parameters = 1,543,714,304
[INFO|trainer.py:3705] 2024-10-07 10:47:41,126 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18
[INFO|configuration_utils.py:407] 2024-10-07 10:47:41,128 >> Configuration saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/config.json
[INFO|configuration_utils.py:868] 2024-10-07 10:47:41,129 >> Configuration saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/generation_config.json
[INFO|modeling_utils.py:2838] 2024-10-07 10:48:08,436 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2649] 2024-10-07 10:48:08,438 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/tokenizer_config.json
[INFO|tokenization_utils_base.py:2658] 2024-10-07 10:48:08,439 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/special_tokens_map.json
[INFO|image_processing_base.py:258] 2024-10-07 10:48:52,717 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/checkpoint-18/preprocessor_config.json
[INFO|trainer.py:2505] 2024-10-07 10:48:52,717 >>
Training completed. Do not forget to share your model on huggingface.co/models =)
[INFO|image_processing_base.py:258] 2024-10-07 10:48:52,720 >> Image processor saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/preprocessor_config.json
[INFO|trainer.py:3705] 2024-10-07 10:48:52,720 >> Saving model checkpoint to saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38
[INFO|configuration_utils.py:407] 2024-10-07 10:48:52,723 >> Configuration saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/config.json
[INFO|configuration_utils.py:868] 2024-10-07 10:48:52,723 >> Configuration saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/generation_config.json
[INFO|modeling_utils.py:2838] 2024-10-07 10:49:26,625 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2649] 2024-10-07 10:49:26,627 >> tokenizer config file saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/tokenizer_config.json
[INFO|tokenization_utils_base.py:2658] 2024-10-07 10:49:26,628 >> Special tokens file saved in saves/Qwen2-VL-2B-Instruct/full/train_2024-10-07-10-45-38/special_tokens_map.json
[INFO|modelcard.py:449] 2024-10-07 10:49:26,987 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|