File size: 28,013 Bytes
7416041 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 |
Microsoft Windows [ηζ¬ 10.0.19045.4170]
(c) Microsoft CorporationγδΏηζζζε©γ
C:\Users\Lenovo>cd C:\Users\Lenovo\Desktop\wxy\CPT-master\finetune\generation
C:\Users\Lenovo\Desktop\wxy\CPT-master\finetune\generation>python run_gen.py --model_path C:\Users\Lenovo\.cache\huggingface\hub\models--fnlp--cpt-large\snapshots\f07323ad5818364d47fc17cc4088072cd2f5f46d --dataset adgen --data_dir demo_data
train
validation
test
03/22/2024 09:51:20 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
03/22/2024 09:51:20 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True},
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
dataloader_prefetch_factor=None,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
dispatch_batches=None,
do_eval=True,
do_predict=True,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=epoch,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=1,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=2e-05,
length_column_name=length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=output/adgen/6\runs\Mar22_09-51-19_DESKTOP-PC6Q6P1,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=10.0,
optim=adamw_torch,
optim_args=None,
output_dir=output/adgen/6,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=6,
per_device_train_batch_size=6,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=output/adgen/6,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=500,
save_strategy=no,
save_total_limit=None,
seed=6000,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=None,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
loading file vocab.txt
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.json
loading configuration file C:\Users\Lenovo\.cache\huggingface\hub\models--fnlp--cpt-large\snapshots\f07323ad5818364d47fc17cc4088072cd2f5f46d\config.json
Model config BartConfig {
"_name_or_path": "C:\\Users\\Lenovo\\.cache\\huggingface\\hub\\models--fnlp--cpt-large\\snapshots\\f07323ad5818364d47fc17cc4088072cd2f5f46d",
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 101,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 4,
"decoder_start_token_id": 102,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 24,
"eos_token_id": 102,
"forced_eos_token_id": 102,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 1024,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"normalize_embedding": true,
"num_beams": 4,
"num_hidden_layers": 24,
"pad_token_id": 0,
"scale_embedding": false,
"task_specific_params": {
"summarization": {
"length_penalty": 1.0,
"max_length": 128,
"min_length": 12,
"num_beams": 4
},
"summarization_cnn": {
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"num_beams": 4
},
"summarization_xsum": {
"length_penalty": 1.0,
"max_length": 62,
"min_length": 11,
"num_beams": 6
}
},
"tokenizer_class": "BertTokenizer",
"transformers_version": "4.38.1",
"use_cache": true,
"vocab_size": 51271
}
loading configuration file C:\Users\Lenovo\.cache\huggingface\hub\models--fnlp--cpt-large\snapshots\f07323ad5818364d47fc17cc4088072cd2f5f46d\config.json
Model config BartConfig {
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 101,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 4,
"decoder_start_token_id": 102,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 24,
"eos_token_id": 102,
"forced_eos_token_id": 102,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 1024,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"normalize_embedding": true,
"num_beams": 4,
"num_hidden_layers": 24,
"pad_token_id": 0,
"scale_embedding": false,
"task_specific_params": {
"summarization": {
"length_penalty": 1.0,
"max_length": 128,
"min_length": 12,
"num_beams": 4
},
"summarization_cnn": {
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"num_beams": 4
},
"summarization_xsum": {
"length_penalty": 1.0,
"max_length": 62,
"min_length": 11,
"num_beams": 6
}
},
"tokenizer_class": "BertTokenizer",
"transformers_version": "4.38.1",
"use_cache": true,
"vocab_size": 51271
}
loading weights file C:\Users\Lenovo\.cache\huggingface\hub\models--fnlp--cpt-large\snapshots\f07323ad5818364d47fc17cc4088072cd2f5f46d\model.safetensors
Generate config GenerationConfig {
"bos_token_id": 101,
"decoder_start_token_id": 102,
"early_stopping": true,
"eos_token_id": 102,
"forced_eos_token_id": 102,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"pad_token_id": 0
}
All model checkpoint weights were used when initializing CPTForConditionalGeneration.
All the weights of CPTForConditionalGeneration were initialized from the model checkpoint at C:\Users\Lenovo\.cache\huggingface\hub\models--fnlp--cpt-large\snapshots\f07323ad5818364d47fc17cc4088072cd2f5f46d.
If your task is similar to the task the model of the checkpoint was trained on, you can already use CPTForConditionalGeneration for predictions without further training.
Generation config file not found, using a generation config created from the model config.
Map: 0%| | 0/3290 [00:00<?, ? examples/s]D:\Python\lib\site-packages\transformers\tokenization_utils_base.py:3892: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
warnings.warn(
Map: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 3290/3290 [00:11<00:00, 274.45 examples/s]
Map: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 1098/1098 [00:03<00:00, 293.11 examples/s]
Map: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 1100/1100 [00:03<00:00, 284.09 examples/s]
The following columns in the training set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running training *****
Num examples = 3,290
Num Epochs = 10
Instantaneous batch size per device = 6
Total train batch size (w. parallel, distributed & accumulation) = 6
Gradient Accumulation steps = 1
Total optimization steps = 5,490
Number of trainable parameters = 424,102,912
{'loss': 1.1409, 'grad_norm': 2.757542133331299, 'learning_rate': 1.817850637522769e-05, 'epoch': 0.91}
10%|ββββββββ | 549/5490 [05:02<38:38, 2.13it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
Generate config GenerationConfig {
"bos_token_id": 101,
"decoder_start_token_id": 102,
"early_stopping": true,
"eos_token_id": 102,
"forced_eos_token_id": 102,
"max_length": 512,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"pad_token_id": 0
}
D:\Python\lib\site-packages\transformers\generation\utils.py:1339: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use and modify the model generation configuration (see https://huggingface.co/docs/transformers/generation_strategies#default-text-generation-configuration )
warnings.warn(
{'eval_loss': 0.6597685217857361, 'eval_rouge-1': 46.5406, 'eval_rouge-2': 22.9769, 'eval_rouge-l': 32.9451, 'eval_gen_len': 140.5492, 'eval_runtime': 2725.7664, 'eval_samples_per_second': 0.403, 'eval_steps_per_second': 0.067, 'epoch': 1.0}
10%|ββββββββ | 549/5490 [50:28<38:38, 2.13it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.6419, 'grad_norm': 3.1357340812683105, 'learning_rate': 1.6357012750455374e-05, 'epoch': 1.82}
20%|ββββββββββββββββ | 1098/5490 [1:41:48<35:16, 2.08it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.5546132922172546, 'eval_rouge-1': 48.0276, 'eval_rouge-2': 22.0229, 'eval_rouge-l': 32.1636, 'eval_gen_len': 196.4153, 'eval_runtime': 3772.7644, 'eval_samples_per_second': 0.291, 'eval_steps_per_second': 0.049, 'epoch': 2.0}
20%|ββββββββββββββββ | 1098/5490 [2:44:41<35:16, 2.08it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.5212, 'grad_norm': 1.975117802619934, 'learning_rate': 1.4535519125683062e-05, 'epoch': 2.73}
30%|βββββββββββββββββββββββ | 1647/5490 [3:53:14<29:42, 2.16it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.5185256004333496, 'eval_rouge-1': 50.9653, 'eval_rouge-2': 25.9311, 'eval_rouge-l': 35.8033, 'eval_gen_len': 159.2368, 'eval_runtime': 2838.4663, 'eval_samples_per_second': 0.387, 'eval_steps_per_second': 0.064, 'epoch': 3.0}
30%|βββββββββββββββββββββββ | 1647/5490 [4:40:33<29:42, 2.16it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.4477, 'grad_norm': 2.144341468811035, 'learning_rate': 1.2714025500910747e-05, 'epoch': 3.64}
40%|βββββββββββββββββββββββββββββββ | 2196/5490 [5:33:59<26:57, 2.04it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.49395063519477844, 'eval_rouge-1': 48.9221, 'eval_rouge-2': 23.9901, 'eval_rouge-l': 33.7623, 'eval_gen_len': 168.326, 'eval_runtime': 3077.747, 'eval_samples_per_second': 0.357, 'eval_steps_per_second': 0.059, 'epoch': 4.0}
40%|βββββββββββββββββββββββββββββββ | 2196/5490 [6:25:17<26:57, 2.04it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.3979, 'grad_norm': 2.392031669616699, 'learning_rate': 1.0892531876138435e-05, 'epoch': 4.55}
50%|ββββββββββββββββββββββββββββββββββββββ | 2745/5490 [7:21:08<22:34, 2.03it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.4893759787082672, 'eval_rouge-1': 50.0387, 'eval_rouge-2': 24.3981, 'eval_rouge-l': 34.4437, 'eval_gen_len': 175.8224, 'eval_runtime': 3577.8144, 'eval_samples_per_second': 0.307, 'eval_steps_per_second': 0.051, 'epoch': 5.0}
50%|ββββββββββββββββββββββββββββββββββββββ | 2745/5490 [8:20:46<22:34, 2.03it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.3643, 'grad_norm': 2.4226653575897217, 'learning_rate': 9.071038251366122e-06, 'epoch': 5.46}
60%|ββββββββββββββββββββββββββββββββββββββββββββββ | 3294/5490 [9:25:41<16:56, 2.16it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.48532548546791077, 'eval_rouge-1': 49.8422, 'eval_rouge-2': 25.0516, 'eval_rouge-l': 34.9932, 'eval_gen_len': 164.6248, 'eval_runtime': 3032.1092, 'eval_samples_per_second': 0.362, 'eval_steps_per_second': 0.06, 'epoch': 6.0}
60%|βββββββββββββββββββββββββββββββββββββββββββββ | 3294/5490 [10:16:13<16:56, 2.16it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.3238, 'grad_norm': 2.65415620803833, 'learning_rate': 7.249544626593807e-06, 'epoch': 6.38}
70%|βββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3843/5490 [11:08:06<12:34, 2.18it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.4873065650463104, 'eval_rouge-1': 50.8821, 'eval_rouge-2': 26.3218, 'eval_rouge-l': 36.3449, 'eval_gen_len': 160.2577, 'eval_runtime': 2730.9734, 'eval_samples_per_second': 0.402, 'eval_steps_per_second': 0.067, 'epoch': 7.0}
70%|βββββββββββββββββββββββββββββββββββββββββββββββββββββ | 3843/5490 [11:53:37<12:34, 2.18it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.2993, 'grad_norm': 3.1916089057922363, 'learning_rate': 5.428051001821493e-06, 'epoch': 7.29}
80%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4392/5490 [12:45:34<08:18, 2.20it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.4905695617198944, 'eval_rouge-1': 50.4851, 'eval_rouge-2': 25.7187, 'eval_rouge-l': 35.9106, 'eval_gen_len': 166.0501, 'eval_runtime': 2922.2897, 'eval_samples_per_second': 0.376, 'eval_steps_per_second': 0.063, 'epoch': 8.0}
80%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4392/5490 [13:34:16<08:18, 2.20it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.2735, 'grad_norm': 2.4203264713287354, 'learning_rate': 3.6065573770491806e-06, 'epoch': 8.2}
90%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4941/5490 [14:28:33<04:10, 2.19it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.4907337725162506, 'eval_rouge-1': 51.017, 'eval_rouge-2': 26.0933, 'eval_rouge-l': 36.1259, 'eval_gen_len': 167.5301, 'eval_runtime': 3054.2577, 'eval_samples_per_second': 0.359, 'eval_steps_per_second': 0.06, 'epoch': 9.0}
90%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | 4941/5490 [15:19:27<04:10, 2.19it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
{'loss': 0.2645, 'grad_norm': 3.681400775909424, 'learning_rate': 1.7850637522768672e-06, 'epoch': 9.11}
100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 5490/5490 [16:15:41<00:00, 2.20it/s]The following columns in the evaluation set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Evaluation *****
Num examples = 1098
Batch size = 6
{'eval_loss': 0.4916660189628601, 'eval_rouge-1': 51.2775, 'eval_rouge-2': 26.6234, 'eval_rouge-l': 36.7381, 'eval_gen_len': 163.3725, 'eval_runtime': 2893.3367, 'eval_samples_per_second': 0.379, 'eval_steps_per_second': 0.063, 'epoch': 10.0}
100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 5490/5490 [17:03:54<00:00, 2.20it/s]The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
Training completed. Do not forget to share your model on huggingface.co/models =)
{'train_runtime': 64358.151, 'train_samples_per_second': 0.511, 'train_steps_per_second': 0.085, 'train_loss': 0.4479398911550831, 'epoch': 10.0}
100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 5490/5490 [17:52:38<00:00, 11.72s/it]
Saving model checkpoint to output/adgen/6
Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 512, 'early_stopping': True, 'num_beams': 4, 'no_repeat_ngram_size': 3, 'forced_eos_token_id': 102}
Configuration saved in output/adgen/6\config.json
Configuration saved in output/adgen/6\generation_config.json
Removed shared tensor {'model.shared.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
Model weights saved in output/adgen/6\model.safetensors
tokenizer config file saved in output/adgen/6\tokenizer_config.json
Special tokens file saved in output/adgen/6\special_tokens_map.json
***** train metrics *****
epoch = 10.0
train_loss = 0.4479
train_runtime = 17:52:38.15
train_samples = 3290
train_samples_per_second = 0.511
train_steps_per_second = 0.085
The following columns in the test set don't have a corresponding argument in `CPTForConditionalGeneration.forward` and have been ignored: token_type_ids. If token_type_ids are not expected by `CPTForConditionalGeneration.forward`, you can safely ignore this message.
***** Running Prediction *****
Num examples = 1100
Batch size = 6
100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 184/184 [48:39<00:00, 15.87s/it]
C:\Users\Lenovo\Desktop\wxy\CPT-master\finetune\generation> |