File size: 73,652 Bytes
9a2897a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 |
09/29/2023 23:17:38 - WARNING - __main__ - Process rank: -1, device: cuda, n_gpu: 1, distributed training: False, 16-bits training: False
09/29/2023 23:17:49 - INFO - __main__ - Training/evaluation parameters Namespace(train_file='../../../data/mcqa/atomic/train_atmc_2i_100k_name.jsonl', dev_file='../../../data/mcqa/atomic/dev_atmc_SyntheticQA_10k.jsonl', model_type='deberta-mlm', model_name_or_path='microsoft/deberta-v3-large', config_name='', tokenizer_name='', cache_dir='.cache', task_name='atomic', output_dir='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', second_train_file=None, second_dev_file=None, max_seq_length=128, max_words_to_mask=6, max_sequence_per_time=80, do_train=True, do_eval=True, do_ext_eval=True, evaluate_during_training=True, do_lower_case=False, per_gpu_train_batch_size=2, per_gpu_eval_batch_size=32, gradient_accumulation_steps=16, margin=1.0, learning_rate=5e-06, weight_decay=0.01, adam_epsilon=1e-06, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, warmup_steps=0, warmup_proportion=0.05, logging_steps=50, save_steps=200, logits_file='logits_test.txt', results_file='eval_results.txt', no_cuda=False, overwrite_output_dir=False, seed=101, fp16=False, fp16_opt_level='O1', local_rank=-1, server_ip='', server_port='', eval_output_dir='./eval_results', n_gpu=1, device=device(type='cuda'))
09/29/2023 23:17:58 - INFO - __main__ - ***** Running evaluation *****
09/29/2023 23:17:58 - INFO - __main__ - Num examples = 10000
09/29/2023 23:17:58 - INFO - __main__ - Batch size = 32
09/29/2023 23:22:13 - INFO - __main__ - ***** Eval results *****
09/29/2023 23:22:13 - INFO - __main__ - acc = 0.3356
09/29/2023 23:32:56 - INFO - __main__ - warm up steps = 916
09/29/2023 23:32:56 - INFO - __main__ - ***** Running training *****
09/29/2023 23:32:56 - INFO - __main__ - Num examples = 586778
09/29/2023 23:32:56 - INFO - __main__ - Num Epochs = 1
09/29/2023 23:32:56 - INFO - __main__ - Instantaneous batch size per GPU = 2
09/29/2023 23:32:56 - INFO - __main__ - Total train batch size (w. parallel, distributed & accumulation) = 32
09/29/2023 23:32:56 - INFO - __main__ - Gradient Accumulation steps = 16
09/29/2023 23:32:56 - INFO - __main__ - Total optimization steps = 18336
09/29/2023 23:36:55 - INFO - __main__ - global_step = 50, average loss = 0.6978485188353807
09/29/2023 23:41:05 - INFO - __main__ - global_step = 100, average loss = 0.6761001783981919
09/29/2023 23:45:18 - INFO - __main__ - global_step = 150, average loss = 0.6527128890505992
09/29/2023 23:49:15 - INFO - __main__ - global_step = 200, average loss = 0.6255776268531917
09/29/2023 23:49:16 - INFO - __main__ - ***** Running evaluation *****
09/29/2023 23:49:16 - INFO - __main__ - Num examples = 10000
09/29/2023 23:49:16 - INFO - __main__ - Batch size = 32
09/29/2023 23:53:34 - INFO - __main__ - ***** Eval results *****
09/29/2023 23:53:34 - INFO - __main__ - acc = 0.3839
09/29/2023 23:54:05 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/29/2023 23:58:03 - INFO - __main__ - global_step = 250, average loss = 0.5687153974524699
09/30/2023 00:02:07 - INFO - __main__ - global_step = 300, average loss = 0.4650766727951122
09/30/2023 00:06:15 - INFO - __main__ - global_step = 350, average loss = 0.344281620121983
09/30/2023 00:10:25 - INFO - __main__ - global_step = 400, average loss = 0.2641717765412432
09/30/2023 00:10:26 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 00:10:26 - INFO - __main__ - Num examples = 10000
09/30/2023 00:10:26 - INFO - __main__ - Batch size = 32
09/30/2023 00:14:45 - INFO - __main__ - ***** Eval results *****
09/30/2023 00:14:45 - INFO - __main__ - acc = 0.6657
09/30/2023 00:15:14 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 00:19:09 - INFO - __main__ - global_step = 450, average loss = 0.203622583138349
09/30/2023 00:23:15 - INFO - __main__ - global_step = 500, average loss = 0.19167841194193896
09/30/2023 00:27:33 - INFO - __main__ - global_step = 550, average loss = 0.1768511165331256
09/30/2023 00:31:46 - INFO - __main__ - global_step = 600, average loss = 0.17364913663874176
09/30/2023 00:31:47 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 00:31:47 - INFO - __main__ - Num examples = 10000
09/30/2023 00:31:47 - INFO - __main__ - Batch size = 32
09/30/2023 00:36:06 - INFO - __main__ - ***** Eval results *****
09/30/2023 00:36:06 - INFO - __main__ - acc = 0.7383
09/30/2023 00:36:35 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 00:40:35 - INFO - __main__ - global_step = 650, average loss = 0.16046627445422929
09/30/2023 00:44:50 - INFO - __main__ - global_step = 700, average loss = 0.15604460480608395
09/30/2023 00:49:12 - INFO - __main__ - global_step = 750, average loss = 0.16073274322843645
09/30/2023 00:53:44 - INFO - __main__ - global_step = 800, average loss = 0.15695772335122457
09/30/2023 00:53:44 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 00:53:44 - INFO - __main__ - Num examples = 10000
09/30/2023 00:53:44 - INFO - __main__ - Batch size = 32
09/30/2023 00:58:03 - INFO - __main__ - ***** Eval results *****
09/30/2023 00:58:03 - INFO - __main__ - acc = 0.7684
09/30/2023 00:58:33 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 01:02:32 - INFO - __main__ - global_step = 850, average loss = 0.14848782167286118
09/30/2023 01:06:57 - INFO - __main__ - global_step = 900, average loss = 0.12806821554375347
09/30/2023 01:11:28 - INFO - __main__ - global_step = 950, average loss = 0.1180885765995481
09/30/2023 01:15:52 - INFO - __main__ - global_step = 1000, average loss = 0.13545685631077503
09/30/2023 01:15:53 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 01:15:53 - INFO - __main__ - Num examples = 10000
09/30/2023 01:15:53 - INFO - __main__ - Batch size = 32
09/30/2023 01:20:11 - INFO - __main__ - ***** Eval results *****
09/30/2023 01:20:11 - INFO - __main__ - acc = 0.7644
09/30/2023 01:24:17 - INFO - __main__ - global_step = 1050, average loss = 0.11866092401789502
09/30/2023 01:28:20 - INFO - __main__ - global_step = 1100, average loss = 0.12610675325471676
09/30/2023 01:32:47 - INFO - __main__ - global_step = 1150, average loss = 0.10549746582400985
09/30/2023 01:37:16 - INFO - __main__ - global_step = 1200, average loss = 0.12280375221620489
09/30/2023 01:37:17 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 01:37:17 - INFO - __main__ - Num examples = 10000
09/30/2023 01:37:17 - INFO - __main__ - Batch size = 32
09/30/2023 01:41:35 - INFO - __main__ - ***** Eval results *****
09/30/2023 01:41:35 - INFO - __main__ - acc = 0.7802
09/30/2023 01:42:04 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 01:46:00 - INFO - __main__ - global_step = 1250, average loss = 0.11540970739923068
09/30/2023 01:50:18 - INFO - __main__ - global_step = 1300, average loss = 0.1098322441923665
09/30/2023 01:54:50 - INFO - __main__ - global_step = 1350, average loss = 0.12102181358681265
09/30/2023 01:59:20 - INFO - __main__ - global_step = 1400, average loss = 0.11920341529325014
09/30/2023 01:59:20 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 01:59:20 - INFO - __main__ - Num examples = 10000
09/30/2023 01:59:20 - INFO - __main__ - Batch size = 32
09/30/2023 02:03:40 - INFO - __main__ - ***** Eval results *****
09/30/2023 02:03:40 - INFO - __main__ - acc = 0.7991
09/30/2023 02:04:09 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 02:08:14 - INFO - __main__ - global_step = 1450, average loss = 0.12416476066496215
09/30/2023 02:12:18 - INFO - __main__ - global_step = 1500, average loss = 0.11171700998882443
09/30/2023 02:16:39 - INFO - __main__ - global_step = 1550, average loss = 0.11893717237122474
09/30/2023 02:21:18 - INFO - __main__ - global_step = 1600, average loss = 0.11236542866332457
09/30/2023 02:21:18 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 02:21:18 - INFO - __main__ - Num examples = 10000
09/30/2023 02:21:18 - INFO - __main__ - Batch size = 32
09/30/2023 02:25:38 - INFO - __main__ - ***** Eval results *****
09/30/2023 02:25:38 - INFO - __main__ - acc = 0.7998
09/30/2023 02:26:08 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 02:30:17 - INFO - __main__ - global_step = 1650, average loss = 0.11477049457775138
09/30/2023 02:34:26 - INFO - __main__ - global_step = 1700, average loss = 0.10185962059051235
09/30/2023 02:38:45 - INFO - __main__ - global_step = 1750, average loss = 0.08941184240770554
09/30/2023 02:43:11 - INFO - __main__ - global_step = 1800, average loss = 0.12326178842118679
09/30/2023 02:43:11 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 02:43:11 - INFO - __main__ - Num examples = 10000
09/30/2023 02:43:11 - INFO - __main__ - Batch size = 32
09/30/2023 02:47:30 - INFO - __main__ - ***** Eval results *****
09/30/2023 02:47:30 - INFO - __main__ - acc = 0.7949
09/30/2023 02:51:33 - INFO - __main__ - global_step = 1850, average loss = 0.1172889139153267
09/30/2023 02:55:34 - INFO - __main__ - global_step = 1900, average loss = 0.11077741613984472
09/30/2023 02:59:53 - INFO - __main__ - global_step = 1950, average loss = 0.11476122897045571
09/30/2023 03:04:26 - INFO - __main__ - global_step = 2000, average loss = 0.11272342270149238
09/30/2023 03:04:27 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 03:04:27 - INFO - __main__ - Num examples = 10000
09/30/2023 03:04:27 - INFO - __main__ - Batch size = 32
09/30/2023 03:08:46 - INFO - __main__ - ***** Eval results *****
09/30/2023 03:08:46 - INFO - __main__ - acc = 0.796
09/30/2023 03:12:55 - INFO - __main__ - global_step = 2050, average loss = 0.10859557473420864
09/30/2023 03:17:10 - INFO - __main__ - global_step = 2100, average loss = 0.09719053598862956
09/30/2023 03:21:26 - INFO - __main__ - global_step = 2150, average loss = 0.11492000469923369
09/30/2023 03:25:59 - INFO - __main__ - global_step = 2200, average loss = 0.09694181648810626
09/30/2023 03:25:59 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 03:25:59 - INFO - __main__ - Num examples = 10000
09/30/2023 03:25:59 - INFO - __main__ - Batch size = 32
09/30/2023 03:30:18 - INFO - __main__ - ***** Eval results *****
09/30/2023 03:30:18 - INFO - __main__ - acc = 0.7974
09/30/2023 03:34:20 - INFO - __main__ - global_step = 2250, average loss = 0.10450371610718548
09/30/2023 03:38:29 - INFO - __main__ - global_step = 2300, average loss = 0.09968944377507796
09/30/2023 03:42:35 - INFO - __main__ - global_step = 2350, average loss = 0.09726969640512834
09/30/2023 03:46:47 - INFO - __main__ - global_step = 2400, average loss = 0.10790286644703884
09/30/2023 03:46:48 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 03:46:48 - INFO - __main__ - Num examples = 10000
09/30/2023 03:46:48 - INFO - __main__ - Batch size = 32
09/30/2023 03:51:06 - INFO - __main__ - ***** Eval results *****
09/30/2023 03:51:06 - INFO - __main__ - acc = 0.8019
09/30/2023 03:51:36 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 03:55:37 - INFO - __main__ - global_step = 2450, average loss = 0.0904800341839109
09/30/2023 03:59:49 - INFO - __main__ - global_step = 2500, average loss = 0.09749648973207513
09/30/2023 04:04:09 - INFO - __main__ - global_step = 2550, average loss = 0.09015977876108082
09/30/2023 04:08:36 - INFO - __main__ - global_step = 2600, average loss = 0.11385933604056846
09/30/2023 04:08:37 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 04:08:37 - INFO - __main__ - Num examples = 10000
09/30/2023 04:08:37 - INFO - __main__ - Batch size = 32
09/30/2023 04:12:54 - INFO - __main__ - ***** Eval results *****
09/30/2023 04:12:54 - INFO - __main__ - acc = 0.8079
09/30/2023 04:13:24 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 04:17:30 - INFO - __main__ - global_step = 2650, average loss = 0.09506087936344557
09/30/2023 04:21:44 - INFO - __main__ - global_step = 2700, average loss = 0.09819057766188052
09/30/2023 04:25:56 - INFO - __main__ - global_step = 2750, average loss = 0.09318019706217456
09/30/2023 04:30:01 - INFO - __main__ - global_step = 2800, average loss = 0.08744580631115241
09/30/2023 04:30:02 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 04:30:02 - INFO - __main__ - Num examples = 10000
09/30/2023 04:30:02 - INFO - __main__ - Batch size = 32
09/30/2023 04:34:20 - INFO - __main__ - ***** Eval results *****
09/30/2023 04:34:20 - INFO - __main__ - acc = 0.8088
09/30/2023 04:34:50 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 04:39:07 - INFO - __main__ - global_step = 2850, average loss = 0.10302798340337177
09/30/2023 04:43:20 - INFO - __main__ - global_step = 2900, average loss = 0.09180921425198903
09/30/2023 04:47:38 - INFO - __main__ - global_step = 2950, average loss = 0.09286653973598731
09/30/2023 04:52:11 - INFO - __main__ - global_step = 3000, average loss = 0.09590554324422555
09/30/2023 04:52:12 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 04:52:12 - INFO - __main__ - Num examples = 10000
09/30/2023 04:52:12 - INFO - __main__ - Batch size = 32
09/30/2023 04:56:30 - INFO - __main__ - ***** Eval results *****
09/30/2023 04:56:30 - INFO - __main__ - acc = 0.8082
09/30/2023 05:00:20 - INFO - __main__ - global_step = 3050, average loss = 0.0994117746003758
09/30/2023 05:04:34 - INFO - __main__ - global_step = 3100, average loss = 0.08591548198470264
09/30/2023 05:09:00 - INFO - __main__ - global_step = 3150, average loss = 0.09913339292746969
09/30/2023 05:13:29 - INFO - __main__ - global_step = 3200, average loss = 0.09553639550766092
09/30/2023 05:13:29 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 05:13:29 - INFO - __main__ - Num examples = 10000
09/30/2023 05:13:29 - INFO - __main__ - Batch size = 32
09/30/2023 05:17:46 - INFO - __main__ - ***** Eval results *****
09/30/2023 05:17:46 - INFO - __main__ - acc = 0.8013
09/30/2023 05:21:55 - INFO - __main__ - global_step = 3250, average loss = 0.0932181820196638
09/30/2023 05:25:59 - INFO - __main__ - global_step = 3300, average loss = 0.08498929560689703
09/30/2023 05:30:21 - INFO - __main__ - global_step = 3350, average loss = 0.10022641647228739
09/30/2023 05:34:47 - INFO - __main__ - global_step = 3400, average loss = 0.08711659569285984
09/30/2023 05:34:47 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 05:34:47 - INFO - __main__ - Num examples = 10000
09/30/2023 05:34:47 - INFO - __main__ - Batch size = 32
09/30/2023 05:39:06 - INFO - __main__ - ***** Eval results *****
09/30/2023 05:39:06 - INFO - __main__ - acc = 0.8085
09/30/2023 05:43:04 - INFO - __main__ - global_step = 3450, average loss = 0.08860307957234909
09/30/2023 05:47:15 - INFO - __main__ - global_step = 3500, average loss = 0.09122671313540195
09/30/2023 05:51:40 - INFO - __main__ - global_step = 3550, average loss = 0.09726192618174537
09/30/2023 05:56:06 - INFO - __main__ - global_step = 3600, average loss = 0.09295479882246582
09/30/2023 05:56:07 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 05:56:07 - INFO - __main__ - Num examples = 10000
09/30/2023 05:56:07 - INFO - __main__ - Batch size = 32
09/30/2023 06:00:25 - INFO - __main__ - ***** Eval results *****
09/30/2023 06:00:25 - INFO - __main__ - acc = 0.7981
09/30/2023 06:04:25 - INFO - __main__ - global_step = 3650, average loss = 0.0850781474460382
09/30/2023 06:08:29 - INFO - __main__ - global_step = 3700, average loss = 0.08510007355012932
09/30/2023 06:12:45 - INFO - __main__ - global_step = 3750, average loss = 0.09091129492127947
09/30/2023 06:17:00 - INFO - __main__ - global_step = 3800, average loss = 0.08938177831689245
09/30/2023 06:17:01 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 06:17:01 - INFO - __main__ - Num examples = 10000
09/30/2023 06:17:01 - INFO - __main__ - Batch size = 32
09/30/2023 06:21:19 - INFO - __main__ - ***** Eval results *****
09/30/2023 06:21:19 - INFO - __main__ - acc = 0.8008
09/30/2023 06:25:31 - INFO - __main__ - global_step = 3850, average loss = 0.09504610720792699
09/30/2023 06:29:46 - INFO - __main__ - global_step = 3900, average loss = 0.0801623915314849
09/30/2023 06:34:06 - INFO - __main__ - global_step = 3950, average loss = 0.08579662030970212
09/30/2023 06:38:28 - INFO - __main__ - global_step = 4000, average loss = 0.09399219373066443
09/30/2023 06:38:29 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 06:38:29 - INFO - __main__ - Num examples = 10000
09/30/2023 06:38:29 - INFO - __main__ - Batch size = 32
09/30/2023 06:42:47 - INFO - __main__ - ***** Eval results *****
09/30/2023 06:42:47 - INFO - __main__ - acc = 0.8075
09/30/2023 06:46:50 - INFO - __main__ - global_step = 4050, average loss = 0.07777188256899535
09/30/2023 06:51:06 - INFO - __main__ - global_step = 4100, average loss = 0.09610467369071557
09/30/2023 06:55:28 - INFO - __main__ - global_step = 4150, average loss = 0.08811031442368403
09/30/2023 07:00:00 - INFO - __main__ - global_step = 4200, average loss = 0.08664546085885377
09/30/2023 07:00:01 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 07:00:01 - INFO - __main__ - Num examples = 10000
09/30/2023 07:00:01 - INFO - __main__ - Batch size = 32
09/30/2023 07:04:19 - INFO - __main__ - ***** Eval results *****
09/30/2023 07:04:19 - INFO - __main__ - acc = 0.8193
09/30/2023 07:04:50 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 07:09:00 - INFO - __main__ - global_step = 4250, average loss = 0.0982984783052234
09/30/2023 07:13:25 - INFO - __main__ - global_step = 4300, average loss = 0.08057821323724056
09/30/2023 07:17:51 - INFO - __main__ - global_step = 4350, average loss = 0.08660443297441817
09/30/2023 07:22:18 - INFO - __main__ - global_step = 4400, average loss = 0.09301655420538736
09/30/2023 07:22:19 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 07:22:19 - INFO - __main__ - Num examples = 10000
09/30/2023 07:22:19 - INFO - __main__ - Batch size = 32
09/30/2023 07:26:36 - INFO - __main__ - ***** Eval results *****
09/30/2023 07:26:36 - INFO - __main__ - acc = 0.8113
09/30/2023 07:30:33 - INFO - __main__ - global_step = 4450, average loss = 0.08599573986270116
09/30/2023 07:34:39 - INFO - __main__ - global_step = 4500, average loss = 0.08530666312639369
09/30/2023 07:38:48 - INFO - __main__ - global_step = 4550, average loss = 0.0846066818782856
09/30/2023 07:43:20 - INFO - __main__ - global_step = 4600, average loss = 0.0817996960383789
09/30/2023 07:43:21 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 07:43:21 - INFO - __main__ - Num examples = 10000
09/30/2023 07:43:21 - INFO - __main__ - Batch size = 32
09/30/2023 07:47:39 - INFO - __main__ - ***** Eval results *****
09/30/2023 07:47:39 - INFO - __main__ - acc = 0.82
09/30/2023 07:48:09 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 07:52:15 - INFO - __main__ - global_step = 4650, average loss = 0.09457363621040712
09/30/2023 07:56:34 - INFO - __main__ - global_step = 4700, average loss = 0.09125612366977293
09/30/2023 08:01:01 - INFO - __main__ - global_step = 4750, average loss = 0.08600258652179037
09/30/2023 08:05:26 - INFO - __main__ - global_step = 4800, average loss = 0.09128527461645718
09/30/2023 08:05:26 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 08:05:26 - INFO - __main__ - Num examples = 10000
09/30/2023 08:05:26 - INFO - __main__ - Batch size = 32
09/30/2023 08:09:45 - INFO - __main__ - ***** Eval results *****
09/30/2023 08:09:45 - INFO - __main__ - acc = 0.8151
09/30/2023 08:13:38 - INFO - __main__ - global_step = 4850, average loss = 0.09068508470605594
09/30/2023 08:17:36 - INFO - __main__ - global_step = 4900, average loss = 0.08361487613161443
09/30/2023 08:21:45 - INFO - __main__ - global_step = 4950, average loss = 0.09231334731652169
09/30/2023 08:26:13 - INFO - __main__ - global_step = 5000, average loss = 0.09210781741610845
09/30/2023 08:26:13 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 08:26:13 - INFO - __main__ - Num examples = 10000
09/30/2023 08:26:13 - INFO - __main__ - Batch size = 32
09/30/2023 08:30:31 - INFO - __main__ - ***** Eval results *****
09/30/2023 08:30:31 - INFO - __main__ - acc = 0.8182
09/30/2023 08:34:31 - INFO - __main__ - global_step = 5050, average loss = 0.0987089884125453
09/30/2023 08:38:41 - INFO - __main__ - global_step = 5100, average loss = 0.08649987229902763
09/30/2023 08:43:07 - INFO - __main__ - global_step = 5150, average loss = 0.08150071838943404
09/30/2023 08:47:36 - INFO - __main__ - global_step = 5200, average loss = 0.09248840492458839
09/30/2023 08:47:36 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 08:47:36 - INFO - __main__ - Num examples = 10000
09/30/2023 08:47:36 - INFO - __main__ - Batch size = 32
09/30/2023 08:51:54 - INFO - __main__ - ***** Eval results *****
09/30/2023 08:51:54 - INFO - __main__ - acc = 0.8098
09/30/2023 08:56:07 - INFO - __main__ - global_step = 5250, average loss = 0.08664297451652601
09/30/2023 09:00:14 - INFO - __main__ - global_step = 5300, average loss = 0.0810040804851451
09/30/2023 09:04:19 - INFO - __main__ - global_step = 5350, average loss = 0.08586231906258035
09/30/2023 09:08:41 - INFO - __main__ - global_step = 5400, average loss = 0.06912091931983014
09/30/2023 09:08:41 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 09:08:41 - INFO - __main__ - Num examples = 10000
09/30/2023 09:08:41 - INFO - __main__ - Batch size = 32
09/30/2023 09:12:59 - INFO - __main__ - ***** Eval results *****
09/30/2023 09:12:59 - INFO - __main__ - acc = 0.8138
09/30/2023 09:17:04 - INFO - __main__ - global_step = 5450, average loss = 0.08094093154666553
09/30/2023 09:21:20 - INFO - __main__ - global_step = 5500, average loss = 0.08313021952490089
09/30/2023 09:25:34 - INFO - __main__ - global_step = 5550, average loss = 0.08020198410889862
09/30/2023 09:30:01 - INFO - __main__ - global_step = 5600, average loss = 0.08213623003844987
09/30/2023 09:30:01 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 09:30:01 - INFO - __main__ - Num examples = 10000
09/30/2023 09:30:01 - INFO - __main__ - Batch size = 32
09/30/2023 09:34:19 - INFO - __main__ - ***** Eval results *****
09/30/2023 09:34:19 - INFO - __main__ - acc = 0.8138
09/30/2023 09:38:25 - INFO - __main__ - global_step = 5650, average loss = 0.0817357241499849
09/30/2023 09:42:30 - INFO - __main__ - global_step = 5700, average loss = 0.07617272696845248
09/30/2023 09:46:47 - INFO - __main__ - global_step = 5750, average loss = 0.08003306837461423
09/30/2023 09:51:07 - INFO - __main__ - global_step = 5800, average loss = 0.08461861441275687
09/30/2023 09:51:07 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 09:51:07 - INFO - __main__ - Num examples = 10000
09/30/2023 09:51:07 - INFO - __main__ - Batch size = 32
09/30/2023 09:55:24 - INFO - __main__ - ***** Eval results *****
09/30/2023 09:55:24 - INFO - __main__ - acc = 0.819
09/30/2023 09:59:31 - INFO - __main__ - global_step = 5850, average loss = 0.0827079386992773
09/30/2023 10:03:45 - INFO - __main__ - global_step = 5900, average loss = 0.09033509934786707
09/30/2023 10:08:04 - INFO - __main__ - global_step = 5950, average loss = 0.08679367909935536
09/30/2023 10:12:29 - INFO - __main__ - global_step = 6000, average loss = 0.0677787430045646
09/30/2023 10:12:30 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 10:12:30 - INFO - __main__ - Num examples = 10000
09/30/2023 10:12:30 - INFO - __main__ - Batch size = 32
09/30/2023 10:16:48 - INFO - __main__ - ***** Eval results *****
09/30/2023 10:16:48 - INFO - __main__ - acc = 0.793
09/30/2023 10:20:46 - INFO - __main__ - global_step = 6050, average loss = 0.07449474892706348
09/30/2023 10:24:57 - INFO - __main__ - global_step = 6100, average loss = 0.08253852118214126
09/30/2023 10:29:21 - INFO - __main__ - global_step = 6150, average loss = 0.07779288738580363
09/30/2023 10:33:50 - INFO - __main__ - global_step = 6200, average loss = 0.08415637877900735
09/30/2023 10:33:51 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 10:33:51 - INFO - __main__ - Num examples = 10000
09/30/2023 10:33:51 - INFO - __main__ - Batch size = 32
09/30/2023 10:38:09 - INFO - __main__ - ***** Eval results *****
09/30/2023 10:38:09 - INFO - __main__ - acc = 0.8152
09/30/2023 10:42:10 - INFO - __main__ - global_step = 6250, average loss = 0.0836084969737567
09/30/2023 10:46:22 - INFO - __main__ - global_step = 6300, average loss = 0.09385589220066322
09/30/2023 10:50:35 - INFO - __main__ - global_step = 6350, average loss = 0.09158665712571747
09/30/2023 10:55:02 - INFO - __main__ - global_step = 6400, average loss = 0.0775194574438865
09/30/2023 10:55:03 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 10:55:03 - INFO - __main__ - Num examples = 10000
09/30/2023 10:55:03 - INFO - __main__ - Batch size = 32
09/30/2023 10:59:20 - INFO - __main__ - ***** Eval results *****
09/30/2023 10:59:20 - INFO - __main__ - acc = 0.8155
09/30/2023 11:03:28 - INFO - __main__ - global_step = 6450, average loss = 0.08119687895305105
09/30/2023 11:07:51 - INFO - __main__ - global_step = 6500, average loss = 0.07420433169674652
09/30/2023 11:12:28 - INFO - __main__ - global_step = 6550, average loss = 0.06907126017362315
09/30/2023 11:16:58 - INFO - __main__ - global_step = 6600, average loss = 0.07694708627823274
09/30/2023 11:16:58 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 11:16:58 - INFO - __main__ - Num examples = 10000
09/30/2023 11:16:58 - INFO - __main__ - Batch size = 32
09/30/2023 11:21:17 - INFO - __main__ - ***** Eval results *****
09/30/2023 11:21:17 - INFO - __main__ - acc = 0.8118
09/30/2023 11:25:39 - INFO - __main__ - global_step = 6650, average loss = 0.07814562884639599
09/30/2023 11:30:08 - INFO - __main__ - global_step = 6700, average loss = 0.08736841517616994
09/30/2023 11:34:35 - INFO - __main__ - global_step = 6750, average loss = 0.08082478447904577
09/30/2023 11:39:03 - INFO - __main__ - global_step = 6800, average loss = 0.07488631383661414
09/30/2023 11:39:04 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 11:39:04 - INFO - __main__ - Num examples = 10000
09/30/2023 11:39:04 - INFO - __main__ - Batch size = 32
09/30/2023 11:43:23 - INFO - __main__ - ***** Eval results *****
09/30/2023 11:43:23 - INFO - __main__ - acc = 0.8213
09/30/2023 11:43:49 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 11:47:44 - INFO - __main__ - global_step = 6850, average loss = 0.08088931010104716
09/30/2023 11:51:57 - INFO - __main__ - global_step = 6900, average loss = 0.07495710194933053
09/30/2023 11:56:20 - INFO - __main__ - global_step = 6950, average loss = 0.08142732598964358
09/30/2023 12:00:40 - INFO - __main__ - global_step = 7000, average loss = 0.08055740728428645
09/30/2023 12:00:41 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 12:00:41 - INFO - __main__ - Num examples = 10000
09/30/2023 12:00:41 - INFO - __main__ - Batch size = 32
09/30/2023 12:04:58 - INFO - __main__ - ***** Eval results *****
09/30/2023 12:04:58 - INFO - __main__ - acc = 0.8081
09/30/2023 12:08:49 - INFO - __main__ - global_step = 7050, average loss = 0.08094024127516604
09/30/2023 12:13:05 - INFO - __main__ - global_step = 7100, average loss = 0.08965814252063865
09/30/2023 12:17:22 - INFO - __main__ - global_step = 7150, average loss = 0.07722920090716798
09/30/2023 12:21:45 - INFO - __main__ - global_step = 7200, average loss = 0.08899519631431758
09/30/2023 12:21:46 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 12:21:46 - INFO - __main__ - Num examples = 10000
09/30/2023 12:21:46 - INFO - __main__ - Batch size = 32
09/30/2023 12:26:05 - INFO - __main__ - ***** Eval results *****
09/30/2023 12:26:05 - INFO - __main__ - acc = 0.8124
09/30/2023 12:30:21 - INFO - __main__ - global_step = 7250, average loss = 0.06652378371007217
09/30/2023 12:34:39 - INFO - __main__ - global_step = 7300, average loss = 0.07190304783754982
09/30/2023 12:39:04 - INFO - __main__ - global_step = 7350, average loss = 0.07759228288079612
09/30/2023 12:43:26 - INFO - __main__ - global_step = 7400, average loss = 0.07959542326259907
09/30/2023 12:43:27 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 12:43:27 - INFO - __main__ - Num examples = 10000
09/30/2023 12:43:27 - INFO - __main__ - Batch size = 32
09/30/2023 12:47:45 - INFO - __main__ - ***** Eval results *****
09/30/2023 12:47:45 - INFO - __main__ - acc = 0.8246
09/30/2023 12:48:12 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 12:52:13 - INFO - __main__ - global_step = 7450, average loss = 0.07954016777908691
09/30/2023 12:56:27 - INFO - __main__ - global_step = 7500, average loss = 0.06745836471483926
09/30/2023 13:00:43 - INFO - __main__ - global_step = 7550, average loss = 0.07651237843449053
09/30/2023 13:04:59 - INFO - __main__ - global_step = 7600, average loss = 0.08067735946224275
09/30/2023 13:05:00 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 13:05:00 - INFO - __main__ - Num examples = 10000
09/30/2023 13:05:00 - INFO - __main__ - Batch size = 32
09/30/2023 13:09:19 - INFO - __main__ - ***** Eval results *****
09/30/2023 13:09:19 - INFO - __main__ - acc = 0.8296
09/30/2023 13:09:45 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 13:13:52 - INFO - __main__ - global_step = 7650, average loss = 0.07473264377593296
09/30/2023 13:18:02 - INFO - __main__ - global_step = 7700, average loss = 0.07815635729657515
09/30/2023 13:22:14 - INFO - __main__ - global_step = 7750, average loss = 0.08072268578209332
09/30/2023 13:26:29 - INFO - __main__ - global_step = 7800, average loss = 0.0779763015091885
09/30/2023 13:26:30 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 13:26:30 - INFO - __main__ - Num examples = 10000
09/30/2023 13:26:30 - INFO - __main__ - Batch size = 32
09/30/2023 13:30:49 - INFO - __main__ - ***** Eval results *****
09/30/2023 13:30:49 - INFO - __main__ - acc = 0.8052
09/30/2023 13:34:56 - INFO - __main__ - global_step = 7850, average loss = 0.08846644978621043
09/30/2023 13:39:08 - INFO - __main__ - global_step = 7900, average loss = 0.08965322268464661
09/30/2023 13:43:18 - INFO - __main__ - global_step = 7950, average loss = 0.07646228883138974
09/30/2023 13:47:34 - INFO - __main__ - global_step = 8000, average loss = 0.06746727024801658
09/30/2023 13:47:35 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 13:47:35 - INFO - __main__ - Num examples = 10000
09/30/2023 13:47:35 - INFO - __main__ - Batch size = 32
09/30/2023 13:51:54 - INFO - __main__ - ***** Eval results *****
09/30/2023 13:51:54 - INFO - __main__ - acc = 0.8243
09/30/2023 13:56:06 - INFO - __main__ - global_step = 8050, average loss = 0.08350399916278547
09/30/2023 14:00:19 - INFO - __main__ - global_step = 8100, average loss = 0.06798540580417466
09/30/2023 14:04:46 - INFO - __main__ - global_step = 8150, average loss = 0.06554304141827742
09/30/2023 14:09:04 - INFO - __main__ - global_step = 8200, average loss = 0.06514280185193229
09/30/2023 14:09:05 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 14:09:05 - INFO - __main__ - Num examples = 10000
09/30/2023 14:09:05 - INFO - __main__ - Batch size = 32
09/30/2023 14:13:23 - INFO - __main__ - ***** Eval results *****
09/30/2023 14:13:23 - INFO - __main__ - acc = 0.8146
09/30/2023 14:17:36 - INFO - __main__ - global_step = 8250, average loss = 0.07990871949750726
09/30/2023 14:21:47 - INFO - __main__ - global_step = 8300, average loss = 0.07364155332470546
09/30/2023 14:25:52 - INFO - __main__ - global_step = 8350, average loss = 0.08377082656683342
09/30/2023 14:30:12 - INFO - __main__ - global_step = 8400, average loss = 0.07954915106311092
09/30/2023 14:30:13 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 14:30:13 - INFO - __main__ - Num examples = 10000
09/30/2023 14:30:13 - INFO - __main__ - Batch size = 32
09/30/2023 14:34:32 - INFO - __main__ - ***** Eval results *****
09/30/2023 14:34:32 - INFO - __main__ - acc = 0.8148
09/30/2023 14:38:42 - INFO - __main__ - global_step = 8450, average loss = 0.07030039706209208
09/30/2023 14:42:55 - INFO - __main__ - global_step = 8500, average loss = 0.08003189989045495
09/30/2023 14:47:10 - INFO - __main__ - global_step = 8550, average loss = 0.07293609037540591
09/30/2023 14:51:25 - INFO - __main__ - global_step = 8600, average loss = 0.07146468496641319
09/30/2023 14:51:25 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 14:51:25 - INFO - __main__ - Num examples = 10000
09/30/2023 14:51:25 - INFO - __main__ - Batch size = 32
09/30/2023 14:55:43 - INFO - __main__ - ***** Eval results *****
09/30/2023 14:55:43 - INFO - __main__ - acc = 0.8119
09/30/2023 14:59:48 - INFO - __main__ - global_step = 8650, average loss = 0.08003535972715327
09/30/2023 15:03:55 - INFO - __main__ - global_step = 8700, average loss = 0.06597046624192444
09/30/2023 15:08:18 - INFO - __main__ - global_step = 8750, average loss = 0.07181154116915422
09/30/2023 15:12:39 - INFO - __main__ - global_step = 8800, average loss = 0.068559150480869
09/30/2023 15:12:40 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 15:12:40 - INFO - __main__ - Num examples = 10000
09/30/2023 15:12:40 - INFO - __main__ - Batch size = 32
09/30/2023 15:16:57 - INFO - __main__ - ***** Eval results *****
09/30/2023 15:16:57 - INFO - __main__ - acc = 0.8027
09/30/2023 15:20:57 - INFO - __main__ - global_step = 8850, average loss = 0.08192624930914462
09/30/2023 15:25:08 - INFO - __main__ - global_step = 8900, average loss = 0.06891920362562814
09/30/2023 15:29:21 - INFO - __main__ - global_step = 8950, average loss = 0.07183136703236868
09/30/2023 15:33:32 - INFO - __main__ - global_step = 9000, average loss = 0.07862215217377524
09/30/2023 15:33:32 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 15:33:32 - INFO - __main__ - Num examples = 10000
09/30/2023 15:33:32 - INFO - __main__ - Batch size = 32
09/30/2023 15:37:51 - INFO - __main__ - ***** Eval results *****
09/30/2023 15:37:51 - INFO - __main__ - acc = 0.8145
09/30/2023 15:42:00 - INFO - __main__ - global_step = 9050, average loss = 0.08039317954942816
09/30/2023 15:46:04 - INFO - __main__ - global_step = 9100, average loss = 0.07681855217753991
09/30/2023 15:50:19 - INFO - __main__ - global_step = 9150, average loss = 0.06908466021588539
09/30/2023 15:54:39 - INFO - __main__ - global_step = 9200, average loss = 0.07285123934067088
09/30/2023 15:54:40 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 15:54:40 - INFO - __main__ - Num examples = 10000
09/30/2023 15:54:40 - INFO - __main__ - Batch size = 32
09/30/2023 15:58:58 - INFO - __main__ - ***** Eval results *****
09/30/2023 15:58:58 - INFO - __main__ - acc = 0.8157
09/30/2023 16:03:12 - INFO - __main__ - global_step = 9250, average loss = 0.07457796319955377
09/30/2023 16:07:29 - INFO - __main__ - global_step = 9300, average loss = 0.08509899367534672
09/30/2023 16:11:53 - INFO - __main__ - global_step = 9350, average loss = 0.07013603730166323
09/30/2023 16:16:21 - INFO - __main__ - global_step = 9400, average loss = 0.07017059165984392
09/30/2023 16:16:22 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 16:16:22 - INFO - __main__ - Num examples = 10000
09/30/2023 16:16:22 - INFO - __main__ - Batch size = 32
09/30/2023 16:20:40 - INFO - __main__ - ***** Eval results *****
09/30/2023 16:20:40 - INFO - __main__ - acc = 0.8141
09/30/2023 16:24:51 - INFO - __main__ - global_step = 9450, average loss = 0.0831688746976215
09/30/2023 16:29:17 - INFO - __main__ - global_step = 9500, average loss = 0.08576202854252188
09/30/2023 16:33:37 - INFO - __main__ - global_step = 9550, average loss = 0.08213058317254764
09/30/2023 16:37:58 - INFO - __main__ - global_step = 9600, average loss = 0.072965028858016
09/30/2023 16:37:58 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 16:37:58 - INFO - __main__ - Num examples = 10000
09/30/2023 16:37:58 - INFO - __main__ - Batch size = 32
09/30/2023 16:42:15 - INFO - __main__ - ***** Eval results *****
09/30/2023 16:42:15 - INFO - __main__ - acc = 0.8122
09/30/2023 16:46:15 - INFO - __main__ - global_step = 9650, average loss = 0.07125714480011083
09/30/2023 16:50:19 - INFO - __main__ - global_step = 9700, average loss = 0.07434062254025775
09/30/2023 16:54:30 - INFO - __main__ - global_step = 9750, average loss = 0.07218598224179004
09/30/2023 16:58:52 - INFO - __main__ - global_step = 9800, average loss = 0.06753908861952368
09/30/2023 16:58:52 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 16:58:52 - INFO - __main__ - Num examples = 10000
09/30/2023 16:58:52 - INFO - __main__ - Batch size = 32
09/30/2023 17:03:10 - INFO - __main__ - ***** Eval results *****
09/30/2023 17:03:10 - INFO - __main__ - acc = 0.8208
09/30/2023 17:07:12 - INFO - __main__ - global_step = 9850, average loss = 0.0787789156648796
09/30/2023 17:11:24 - INFO - __main__ - global_step = 9900, average loss = 0.06863431145990034
09/30/2023 17:15:44 - INFO - __main__ - global_step = 9950, average loss = 0.0729100130192819
09/30/2023 17:20:01 - INFO - __main__ - global_step = 10000, average loss = 0.07118722895695101
09/30/2023 17:20:01 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 17:20:01 - INFO - __main__ - Num examples = 10000
09/30/2023 17:20:01 - INFO - __main__ - Batch size = 32
09/30/2023 17:24:20 - INFO - __main__ - ***** Eval results *****
09/30/2023 17:24:20 - INFO - __main__ - acc = 0.8212
09/30/2023 17:28:25 - INFO - __main__ - global_step = 10050, average loss = 0.06967489041242515
09/30/2023 17:32:40 - INFO - __main__ - global_step = 10100, average loss = 0.07503812584323896
09/30/2023 17:37:07 - INFO - __main__ - global_step = 10150, average loss = 0.07984486830362585
09/30/2023 17:41:19 - INFO - __main__ - global_step = 10200, average loss = 0.06886661994401948
09/30/2023 17:41:19 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 17:41:19 - INFO - __main__ - Num examples = 10000
09/30/2023 17:41:19 - INFO - __main__ - Batch size = 32
09/30/2023 17:45:37 - INFO - __main__ - ***** Eval results *****
09/30/2023 17:45:37 - INFO - __main__ - acc = 0.8134
09/30/2023 17:49:55 - INFO - __main__ - global_step = 10250, average loss = 0.07405807184350124
09/30/2023 17:54:14 - INFO - __main__ - global_step = 10300, average loss = 0.08030594819738326
09/30/2023 17:58:33 - INFO - __main__ - global_step = 10350, average loss = 0.08568550381663954
09/30/2023 18:02:39 - INFO - __main__ - global_step = 10400, average loss = 0.08110691699486779
09/30/2023 18:02:39 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 18:02:39 - INFO - __main__ - Num examples = 10000
09/30/2023 18:02:39 - INFO - __main__ - Batch size = 32
09/30/2023 18:07:00 - INFO - __main__ - ***** Eval results *****
09/30/2023 18:07:00 - INFO - __main__ - acc = 0.8226
09/30/2023 18:10:59 - INFO - __main__ - global_step = 10450, average loss = 0.07698049577564234
09/30/2023 18:15:18 - INFO - __main__ - global_step = 10500, average loss = 0.07489776252514276
09/30/2023 18:19:38 - INFO - __main__ - global_step = 10550, average loss = 0.08084082975808997
09/30/2023 18:24:06 - INFO - __main__ - global_step = 10600, average loss = 0.077233616621088
09/30/2023 18:24:06 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 18:24:06 - INFO - __main__ - Num examples = 10000
09/30/2023 18:24:06 - INFO - __main__ - Batch size = 32
09/30/2023 18:28:26 - INFO - __main__ - ***** Eval results *****
09/30/2023 18:28:26 - INFO - __main__ - acc = 0.8219
09/30/2023 18:32:23 - INFO - __main__ - global_step = 10650, average loss = 0.0749396042097942
09/30/2023 18:36:24 - INFO - __main__ - global_step = 10700, average loss = 0.07035453407006571
09/30/2023 18:40:30 - INFO - __main__ - global_step = 10750, average loss = 0.0701333080389304
09/30/2023 18:44:44 - INFO - __main__ - global_step = 10800, average loss = 0.06815460226869618
09/30/2023 18:44:45 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 18:44:45 - INFO - __main__ - Num examples = 10000
09/30/2023 18:44:45 - INFO - __main__ - Batch size = 32
09/30/2023 18:49:04 - INFO - __main__ - ***** Eval results *****
09/30/2023 18:49:04 - INFO - __main__ - acc = 0.8246
09/30/2023 18:53:04 - INFO - __main__ - global_step = 10850, average loss = 0.06231740675430046
09/30/2023 18:57:11 - INFO - __main__ - global_step = 10900, average loss = 0.07749273380759406
09/30/2023 19:01:27 - INFO - __main__ - global_step = 10950, average loss = 0.07356921623417292
09/30/2023 19:05:44 - INFO - __main__ - global_step = 11000, average loss = 0.06861940244401922
09/30/2023 19:05:44 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 19:05:44 - INFO - __main__ - Num examples = 10000
09/30/2023 19:05:44 - INFO - __main__ - Batch size = 32
09/30/2023 19:10:04 - INFO - __main__ - ***** Eval results *****
09/30/2023 19:10:04 - INFO - __main__ - acc = 0.8237
09/30/2023 19:13:58 - INFO - __main__ - global_step = 11050, average loss = 0.07190075869159046
09/30/2023 19:18:18 - INFO - __main__ - global_step = 11100, average loss = 0.07798185770014243
09/30/2023 19:22:25 - INFO - __main__ - global_step = 11150, average loss = 0.05461175944059505
09/30/2023 19:26:36 - INFO - __main__ - global_step = 11200, average loss = 0.07214928590841736
09/30/2023 19:26:36 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 19:26:36 - INFO - __main__ - Num examples = 10000
09/30/2023 19:26:36 - INFO - __main__ - Batch size = 32
09/30/2023 19:30:56 - INFO - __main__ - ***** Eval results *****
09/30/2023 19:30:56 - INFO - __main__ - acc = 0.8281
09/30/2023 19:34:46 - INFO - __main__ - global_step = 11250, average loss = 0.07595877689196641
09/30/2023 19:38:51 - INFO - __main__ - global_step = 11300, average loss = 0.06289271867310163
09/30/2023 19:42:58 - INFO - __main__ - global_step = 11350, average loss = 0.07287138866693567
09/30/2023 19:47:05 - INFO - __main__ - global_step = 11400, average loss = 0.0736375573805708
09/30/2023 19:47:05 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 19:47:05 - INFO - __main__ - Num examples = 10000
09/30/2023 19:47:05 - INFO - __main__ - Batch size = 32
09/30/2023 19:51:26 - INFO - __main__ - ***** Eval results *****
09/30/2023 19:51:26 - INFO - __main__ - acc = 0.8265
09/30/2023 19:55:14 - INFO - __main__ - global_step = 11450, average loss = 0.07105860608404328
09/30/2023 19:59:22 - INFO - __main__ - global_step = 11500, average loss = 0.07589100849851092
09/30/2023 20:03:31 - INFO - __main__ - global_step = 11550, average loss = 0.07193597211022279
09/30/2023 20:07:44 - INFO - __main__ - global_step = 11600, average loss = 0.0786158631305443
09/30/2023 20:07:45 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 20:07:45 - INFO - __main__ - Num examples = 10000
09/30/2023 20:07:45 - INFO - __main__ - Batch size = 32
09/30/2023 20:12:05 - INFO - __main__ - ***** Eval results *****
09/30/2023 20:12:05 - INFO - __main__ - acc = 0.8224
09/30/2023 20:16:14 - INFO - __main__ - global_step = 11650, average loss = 0.07484395604304155
09/30/2023 20:20:16 - INFO - __main__ - global_step = 11700, average loss = 0.07182746810896788
09/30/2023 20:24:28 - INFO - __main__ - global_step = 11750, average loss = 0.06392118992527684
09/30/2023 20:28:47 - INFO - __main__ - global_step = 11800, average loss = 0.06359485059540021
09/30/2023 20:28:48 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 20:28:48 - INFO - __main__ - Num examples = 10000
09/30/2023 20:28:48 - INFO - __main__ - Batch size = 32
09/30/2023 20:33:07 - INFO - __main__ - ***** Eval results *****
09/30/2023 20:33:07 - INFO - __main__ - acc = 0.8225
09/30/2023 20:36:55 - INFO - __main__ - global_step = 11850, average loss = 0.06557874951142367
09/30/2023 20:40:51 - INFO - __main__ - global_step = 11900, average loss = 0.06787695961887948
09/30/2023 20:45:01 - INFO - __main__ - global_step = 11950, average loss = 0.07802391385892406
09/30/2023 20:49:19 - INFO - __main__ - global_step = 12000, average loss = 0.062383338503277624
09/30/2023 20:49:19 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 20:49:19 - INFO - __main__ - Num examples = 10000
09/30/2023 20:49:19 - INFO - __main__ - Batch size = 32
09/30/2023 20:53:41 - INFO - __main__ - ***** Eval results *****
09/30/2023 20:53:41 - INFO - __main__ - acc = 0.8221
09/30/2023 20:57:31 - INFO - __main__ - global_step = 12050, average loss = 0.07041985652205768
09/30/2023 21:01:33 - INFO - __main__ - global_step = 12100, average loss = 0.07904728068271652
09/30/2023 21:05:47 - INFO - __main__ - global_step = 12150, average loss = 0.07474817682654247
09/30/2023 21:09:58 - INFO - __main__ - global_step = 12200, average loss = 0.07402907914118259
09/30/2023 21:09:58 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 21:09:58 - INFO - __main__ - Num examples = 10000
09/30/2023 21:09:58 - INFO - __main__ - Batch size = 32
09/30/2023 21:14:19 - INFO - __main__ - ***** Eval results *****
09/30/2023 21:14:19 - INFO - __main__ - acc = 0.8327
09/30/2023 21:14:46 - INFO - __main__ - Saving model checkpoint to output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
09/30/2023 21:18:46 - INFO - __main__ - global_step = 12250, average loss = 0.07039213450989337
09/30/2023 21:22:59 - INFO - __main__ - global_step = 12300, average loss = 0.0842395970186044
09/30/2023 21:27:05 - INFO - __main__ - global_step = 12350, average loss = 0.06603515204827999
09/30/2023 21:31:22 - INFO - __main__ - global_step = 12400, average loss = 0.06760421821546515
09/30/2023 21:31:22 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 21:31:22 - INFO - __main__ - Num examples = 10000
09/30/2023 21:31:22 - INFO - __main__ - Batch size = 32
09/30/2023 21:35:43 - INFO - __main__ - ***** Eval results *****
09/30/2023 21:35:43 - INFO - __main__ - acc = 0.8208
09/30/2023 21:39:33 - INFO - __main__ - global_step = 12450, average loss = 0.06917047601906233
09/30/2023 21:43:44 - INFO - __main__ - global_step = 12500, average loss = 0.07573592953915068
09/30/2023 21:48:03 - INFO - __main__ - global_step = 12550, average loss = 0.06653125052485848
09/30/2023 21:52:22 - INFO - __main__ - global_step = 12600, average loss = 0.06815064429247286
09/30/2023 21:52:23 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 21:52:23 - INFO - __main__ - Num examples = 10000
09/30/2023 21:52:23 - INFO - __main__ - Batch size = 32
09/30/2023 21:56:43 - INFO - __main__ - ***** Eval results *****
09/30/2023 21:56:43 - INFO - __main__ - acc = 0.819
09/30/2023 22:00:39 - INFO - __main__ - global_step = 12650, average loss = 0.07732899946378893
09/30/2023 22:04:44 - INFO - __main__ - global_step = 12700, average loss = 0.06547158910783764
09/30/2023 22:08:49 - INFO - __main__ - global_step = 12750, average loss = 0.0728905378174386
09/30/2023 22:13:03 - INFO - __main__ - global_step = 12800, average loss = 0.07366545890477937
09/30/2023 22:13:04 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 22:13:04 - INFO - __main__ - Num examples = 10000
09/30/2023 22:13:04 - INFO - __main__ - Batch size = 32
09/30/2023 22:17:25 - INFO - __main__ - ***** Eval results *****
09/30/2023 22:17:25 - INFO - __main__ - acc = 0.8182
09/30/2023 22:21:28 - INFO - __main__ - global_step = 12850, average loss = 0.06894337675126735
09/30/2023 22:25:41 - INFO - __main__ - global_step = 12900, average loss = 0.07351460054007475
09/30/2023 22:29:49 - INFO - __main__ - global_step = 12950, average loss = 0.0674650944762834
09/30/2023 22:34:09 - INFO - __main__ - global_step = 13000, average loss = 0.07850258736492834
09/30/2023 22:34:09 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 22:34:09 - INFO - __main__ - Num examples = 10000
09/30/2023 22:34:09 - INFO - __main__ - Batch size = 32
09/30/2023 22:38:30 - INFO - __main__ - ***** Eval results *****
09/30/2023 22:38:30 - INFO - __main__ - acc = 0.8321
09/30/2023 22:42:24 - INFO - __main__ - global_step = 13050, average loss = 0.07653208828101925
09/30/2023 22:46:20 - INFO - __main__ - global_step = 13100, average loss = 0.06802368102005857
09/30/2023 22:50:29 - INFO - __main__ - global_step = 13150, average loss = 0.06454230795552576
09/30/2023 22:54:34 - INFO - __main__ - global_step = 13200, average loss = 0.07258539929578546
09/30/2023 22:54:35 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 22:54:35 - INFO - __main__ - Num examples = 10000
09/30/2023 22:54:35 - INFO - __main__ - Batch size = 32
09/30/2023 22:58:54 - INFO - __main__ - ***** Eval results *****
09/30/2023 22:58:54 - INFO - __main__ - acc = 0.8252
09/30/2023 23:02:57 - INFO - __main__ - global_step = 13250, average loss = 0.07325911161562544
09/30/2023 23:07:12 - INFO - __main__ - global_step = 13300, average loss = 0.06880584957727479
09/30/2023 23:11:21 - INFO - __main__ - global_step = 13350, average loss = 0.07009069720297703
09/30/2023 23:15:34 - INFO - __main__ - global_step = 13400, average loss = 0.07083460625182852
09/30/2023 23:15:35 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 23:15:35 - INFO - __main__ - Num examples = 10000
09/30/2023 23:15:35 - INFO - __main__ - Batch size = 32
09/30/2023 23:19:56 - INFO - __main__ - ***** Eval results *****
09/30/2023 23:19:56 - INFO - __main__ - acc = 0.813
09/30/2023 23:23:55 - INFO - __main__ - global_step = 13450, average loss = 0.06977577161625959
09/30/2023 23:27:49 - INFO - __main__ - global_step = 13500, average loss = 0.0730690676838276
09/30/2023 23:31:51 - INFO - __main__ - global_step = 13550, average loss = 0.07233811266596604
09/30/2023 23:35:53 - INFO - __main__ - global_step = 13600, average loss = 0.0773136636797426
09/30/2023 23:35:54 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 23:35:54 - INFO - __main__ - Num examples = 10000
09/30/2023 23:35:54 - INFO - __main__ - Batch size = 32
09/30/2023 23:40:14 - INFO - __main__ - ***** Eval results *****
09/30/2023 23:40:14 - INFO - __main__ - acc = 0.8254
09/30/2023 23:44:18 - INFO - __main__ - global_step = 13650, average loss = 0.0625762648001546
09/30/2023 23:48:29 - INFO - __main__ - global_step = 13700, average loss = 0.07835062241327251
09/30/2023 23:52:47 - INFO - __main__ - global_step = 13750, average loss = 0.06917831582177314
09/30/2023 23:57:06 - INFO - __main__ - global_step = 13800, average loss = 0.06653823942549934
09/30/2023 23:57:07 - INFO - __main__ - ***** Running evaluation *****
09/30/2023 23:57:07 - INFO - __main__ - Num examples = 10000
09/30/2023 23:57:07 - INFO - __main__ - Batch size = 32
10/01/2023 00:01:27 - INFO - __main__ - ***** Eval results *****
10/01/2023 00:01:27 - INFO - __main__ - acc = 0.8231
10/01/2023 00:05:24 - INFO - __main__ - global_step = 13850, average loss = 0.07134979092643334
10/01/2023 00:09:31 - INFO - __main__ - global_step = 13900, average loss = 0.07882154490274842
10/01/2023 00:13:33 - INFO - __main__ - global_step = 13950, average loss = 0.067044138008132
10/01/2023 00:17:54 - INFO - __main__ - global_step = 14000, average loss = 0.06602240080737828
10/01/2023 00:17:55 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 00:17:55 - INFO - __main__ - Num examples = 10000
10/01/2023 00:17:55 - INFO - __main__ - Batch size = 32
10/01/2023 00:22:16 - INFO - __main__ - ***** Eval results *****
10/01/2023 00:22:16 - INFO - __main__ - acc = 0.8185
10/01/2023 00:26:20 - INFO - __main__ - global_step = 14050, average loss = 0.07546966458212409
10/01/2023 00:30:49 - INFO - __main__ - global_step = 14100, average loss = 0.06855787578620948
10/01/2023 00:35:15 - INFO - __main__ - global_step = 14150, average loss = 0.06737258993505747
10/01/2023 00:39:39 - INFO - __main__ - global_step = 14200, average loss = 0.05966844407041208
10/01/2023 00:39:40 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 00:39:40 - INFO - __main__ - Num examples = 10000
10/01/2023 00:39:40 - INFO - __main__ - Batch size = 32
10/01/2023 00:44:00 - INFO - __main__ - ***** Eval results *****
10/01/2023 00:44:00 - INFO - __main__ - acc = 0.8282
10/01/2023 00:47:56 - INFO - __main__ - global_step = 14250, average loss = 0.0709371871012263
10/01/2023 00:51:54 - INFO - __main__ - global_step = 14300, average loss = 0.07779215545522675
10/01/2023 00:56:02 - INFO - __main__ - global_step = 14350, average loss = 0.06590510867084959
10/01/2023 01:00:08 - INFO - __main__ - global_step = 14400, average loss = 0.061885312875092496
10/01/2023 01:00:09 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 01:00:09 - INFO - __main__ - Num examples = 10000
10/01/2023 01:00:09 - INFO - __main__ - Batch size = 32
10/01/2023 01:04:29 - INFO - __main__ - ***** Eval results *****
10/01/2023 01:04:29 - INFO - __main__ - acc = 0.8195
10/01/2023 01:08:20 - INFO - __main__ - global_step = 14450, average loss = 0.07757491528376705
10/01/2023 01:12:26 - INFO - __main__ - global_step = 14500, average loss = 0.061351443203457166
10/01/2023 01:16:44 - INFO - __main__ - global_step = 14550, average loss = 0.06742463728594884
10/01/2023 01:20:55 - INFO - __main__ - global_step = 14600, average loss = 0.06395716872473713
10/01/2023 01:20:56 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 01:20:56 - INFO - __main__ - Num examples = 10000
10/01/2023 01:20:56 - INFO - __main__ - Batch size = 32
10/01/2023 01:25:16 - INFO - __main__ - ***** Eval results *****
10/01/2023 01:25:16 - INFO - __main__ - acc = 0.8271
10/01/2023 01:29:11 - INFO - __main__ - global_step = 14650, average loss = 0.0680865884249215
10/01/2023 01:33:17 - INFO - __main__ - global_step = 14700, average loss = 0.07319515083199804
10/01/2023 01:37:31 - INFO - __main__ - global_step = 14750, average loss = 0.0750861974158397
10/01/2023 01:41:39 - INFO - __main__ - global_step = 14800, average loss = 0.07455838610287174
10/01/2023 01:41:39 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 01:41:39 - INFO - __main__ - Num examples = 10000
10/01/2023 01:41:39 - INFO - __main__ - Batch size = 32
10/01/2023 01:45:59 - INFO - __main__ - ***** Eval results *****
10/01/2023 01:45:59 - INFO - __main__ - acc = 0.8285
10/01/2023 01:49:49 - INFO - __main__ - global_step = 14850, average loss = 0.0746920863639025
10/01/2023 01:53:48 - INFO - __main__ - global_step = 14900, average loss = 0.06193213762038795
10/01/2023 01:58:00 - INFO - __main__ - global_step = 14950, average loss = 0.0684903811987897
10/01/2023 02:02:20 - INFO - __main__ - global_step = 15000, average loss = 0.07475626632280181
10/01/2023 02:02:21 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 02:02:21 - INFO - __main__ - Num examples = 10000
10/01/2023 02:02:21 - INFO - __main__ - Batch size = 32
10/01/2023 02:06:40 - INFO - __main__ - ***** Eval results *****
10/01/2023 02:06:40 - INFO - __main__ - acc = 0.8221
10/01/2023 02:10:33 - INFO - __main__ - global_step = 15050, average loss = 0.06398421550955391
10/01/2023 02:14:31 - INFO - __main__ - global_step = 15100, average loss = 0.07387388837814797
10/01/2023 02:18:36 - INFO - __main__ - global_step = 15150, average loss = 0.07215547483820046
10/01/2023 02:22:42 - INFO - __main__ - global_step = 15200, average loss = 0.06692371807614109
10/01/2023 02:22:42 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 02:22:42 - INFO - __main__ - Num examples = 10000
10/01/2023 02:22:42 - INFO - __main__ - Batch size = 32
10/01/2023 02:27:06 - INFO - __main__ - ***** Eval results *****
10/01/2023 02:27:06 - INFO - __main__ - acc = 0.828
10/01/2023 02:31:03 - INFO - __main__ - global_step = 15250, average loss = 0.07475481618889716
10/01/2023 02:35:03 - INFO - __main__ - global_step = 15300, average loss = 0.06605282124131918
10/01/2023 02:39:06 - INFO - __main__ - global_step = 15350, average loss = 0.0742860847054817
10/01/2023 02:43:08 - INFO - __main__ - global_step = 15400, average loss = 0.06508645007126689
10/01/2023 02:43:09 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 02:43:09 - INFO - __main__ - Num examples = 10000
10/01/2023 02:43:09 - INFO - __main__ - Batch size = 32
10/01/2023 02:47:27 - INFO - __main__ - ***** Eval results *****
10/01/2023 02:47:27 - INFO - __main__ - acc = 0.8244
10/01/2023 02:51:15 - INFO - __main__ - global_step = 15450, average loss = 0.0657403554152188
10/01/2023 02:55:25 - INFO - __main__ - global_step = 15500, average loss = 0.06363382869447377
10/01/2023 02:59:33 - INFO - __main__ - global_step = 15550, average loss = 0.068332606570184
10/01/2023 03:03:36 - INFO - __main__ - global_step = 15600, average loss = 0.0638002801532275
10/01/2023 03:03:37 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 03:03:37 - INFO - __main__ - Num examples = 10000
10/01/2023 03:03:37 - INFO - __main__ - Batch size = 32
10/01/2023 03:07:54 - INFO - __main__ - ***** Eval results *****
10/01/2023 03:07:54 - INFO - __main__ - acc = 0.8245
10/01/2023 03:11:47 - INFO - __main__ - global_step = 15650, average loss = 0.07057813088395051
10/01/2023 03:15:48 - INFO - __main__ - global_step = 15700, average loss = 0.059586076617561046
10/01/2023 03:19:50 - INFO - __main__ - global_step = 15750, average loss = 0.06329842852351249
10/01/2023 03:24:07 - INFO - __main__ - global_step = 15800, average loss = 0.0673095579940309
10/01/2023 03:24:08 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 03:24:08 - INFO - __main__ - Num examples = 10000
10/01/2023 03:24:08 - INFO - __main__ - Batch size = 32
10/01/2023 03:28:27 - INFO - __main__ - ***** Eval results *****
10/01/2023 03:28:27 - INFO - __main__ - acc = 0.8191
10/01/2023 03:32:25 - INFO - __main__ - global_step = 15850, average loss = 0.06719043602446619
10/01/2023 03:36:22 - INFO - __main__ - global_step = 15900, average loss = 0.06470626855618321
10/01/2023 03:40:22 - INFO - __main__ - global_step = 15950, average loss = 0.0673678615699464
10/01/2023 03:44:32 - INFO - __main__ - global_step = 16000, average loss = 0.06654785299411742
10/01/2023 03:44:32 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 03:44:32 - INFO - __main__ - Num examples = 10000
10/01/2023 03:44:32 - INFO - __main__ - Batch size = 32
10/01/2023 03:48:51 - INFO - __main__ - ***** Eval results *****
10/01/2023 03:48:51 - INFO - __main__ - acc = 0.826
10/01/2023 03:52:42 - INFO - __main__ - global_step = 16050, average loss = 0.07211193255971012
10/01/2023 03:56:30 - INFO - __main__ - global_step = 16100, average loss = 0.07810956820030697
10/01/2023 04:00:37 - INFO - __main__ - global_step = 16150, average loss = 0.07871339554849328
10/01/2023 04:04:48 - INFO - __main__ - global_step = 16200, average loss = 0.06766451962915199
10/01/2023 04:04:48 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 04:04:48 - INFO - __main__ - Num examples = 10000
10/01/2023 04:04:48 - INFO - __main__ - Batch size = 32
10/01/2023 04:09:07 - INFO - __main__ - ***** Eval results *****
10/01/2023 04:09:07 - INFO - __main__ - acc = 0.8234
10/01/2023 04:13:00 - INFO - __main__ - global_step = 16250, average loss = 0.07233332002186216
10/01/2023 04:17:08 - INFO - __main__ - global_step = 16300, average loss = 0.06269402921956498
10/01/2023 04:21:18 - INFO - __main__ - global_step = 16350, average loss = 0.066974333815524
10/01/2023 04:25:36 - INFO - __main__ - global_step = 16400, average loss = 0.06326851320967762
10/01/2023 04:25:36 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 04:25:36 - INFO - __main__ - Num examples = 10000
10/01/2023 04:25:36 - INFO - __main__ - Batch size = 32
10/01/2023 04:29:55 - INFO - __main__ - ***** Eval results *****
10/01/2023 04:29:55 - INFO - __main__ - acc = 0.8218
10/01/2023 04:33:53 - INFO - __main__ - global_step = 16450, average loss = 0.0583337911261151
10/01/2023 04:38:00 - INFO - __main__ - global_step = 16500, average loss = 0.06651346774706327
10/01/2023 04:42:10 - INFO - __main__ - global_step = 16550, average loss = 0.07442569829370768
10/01/2023 04:46:19 - INFO - __main__ - global_step = 16600, average loss = 0.0704036247156182
10/01/2023 04:46:19 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 04:46:19 - INFO - __main__ - Num examples = 10000
10/01/2023 04:46:19 - INFO - __main__ - Batch size = 32
10/01/2023 04:50:38 - INFO - __main__ - ***** Eval results *****
10/01/2023 04:50:38 - INFO - __main__ - acc = 0.8268
10/01/2023 04:54:40 - INFO - __main__ - global_step = 16650, average loss = 0.07102784802380484
10/01/2023 04:58:39 - INFO - __main__ - global_step = 16700, average loss = 0.07482151540141785
10/01/2023 05:02:48 - INFO - __main__ - global_step = 16750, average loss = 0.06266404812475229
10/01/2023 05:06:49 - INFO - __main__ - global_step = 16800, average loss = 0.06936132206232287
10/01/2023 05:06:50 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 05:06:50 - INFO - __main__ - Num examples = 10000
10/01/2023 05:06:50 - INFO - __main__ - Batch size = 32
10/01/2023 05:11:07 - INFO - __main__ - ***** Eval results *****
10/01/2023 05:11:07 - INFO - __main__ - acc = 0.8313
10/01/2023 05:15:16 - INFO - __main__ - global_step = 16850, average loss = 0.060352628196997105
10/01/2023 05:19:33 - INFO - __main__ - global_step = 16900, average loss = 0.0641949670168833
10/01/2023 05:23:53 - INFO - __main__ - global_step = 16950, average loss = 0.0711748162342701
10/01/2023 05:28:04 - INFO - __main__ - global_step = 17000, average loss = 0.07767359625780955
10/01/2023 05:28:05 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 05:28:05 - INFO - __main__ - Num examples = 10000
10/01/2023 05:28:05 - INFO - __main__ - Batch size = 32
10/01/2023 05:32:22 - INFO - __main__ - ***** Eval results *****
10/01/2023 05:32:22 - INFO - __main__ - acc = 0.8302
10/01/2023 05:36:19 - INFO - __main__ - global_step = 17050, average loss = 0.059951672412971675
10/01/2023 05:40:23 - INFO - __main__ - global_step = 17100, average loss = 0.0679468241819086
10/01/2023 05:44:37 - INFO - __main__ - global_step = 17150, average loss = 0.06287542213140114
10/01/2023 05:48:53 - INFO - __main__ - global_step = 17200, average loss = 0.07064101672236575
10/01/2023 05:48:53 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 05:48:53 - INFO - __main__ - Num examples = 10000
10/01/2023 05:48:53 - INFO - __main__ - Batch size = 32
10/01/2023 05:53:11 - INFO - __main__ - ***** Eval results *****
10/01/2023 05:53:11 - INFO - __main__ - acc = 0.8288
10/01/2023 05:57:08 - INFO - __main__ - global_step = 17250, average loss = 0.06821862254073494
10/01/2023 06:01:07 - INFO - __main__ - global_step = 17300, average loss = 0.06737288911346695
10/01/2023 06:05:09 - INFO - __main__ - global_step = 17350, average loss = 0.06524526451248676
10/01/2023 06:09:17 - INFO - __main__ - global_step = 17400, average loss = 0.06838752188666604
10/01/2023 06:09:17 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 06:09:17 - INFO - __main__ - Num examples = 10000
10/01/2023 06:09:17 - INFO - __main__ - Batch size = 32
10/01/2023 06:13:34 - INFO - __main__ - ***** Eval results *****
10/01/2023 06:13:34 - INFO - __main__ - acc = 0.8292
10/01/2023 06:17:34 - INFO - __main__ - global_step = 17450, average loss = 0.07033179465208378
10/01/2023 06:21:42 - INFO - __main__ - global_step = 17500, average loss = 0.07338941472058651
10/01/2023 06:25:54 - INFO - __main__ - global_step = 17550, average loss = 0.06760536882744418
10/01/2023 06:30:29 - INFO - __main__ - global_step = 17600, average loss = 0.06395369231896893
10/01/2023 06:30:30 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 06:30:30 - INFO - __main__ - Num examples = 10000
10/01/2023 06:30:30 - INFO - __main__ - Batch size = 32
10/01/2023 06:34:46 - INFO - __main__ - ***** Eval results *****
10/01/2023 06:34:46 - INFO - __main__ - acc = 0.8226
10/01/2023 06:38:42 - INFO - __main__ - global_step = 17650, average loss = 0.0788995540245378
10/01/2023 06:42:45 - INFO - __main__ - global_step = 17700, average loss = 0.058938835552726235
10/01/2023 06:46:55 - INFO - __main__ - global_step = 17750, average loss = 0.062029462043719834
10/01/2023 06:51:15 - INFO - __main__ - global_step = 17800, average loss = 0.07220558329383493
10/01/2023 06:51:15 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 06:51:15 - INFO - __main__ - Num examples = 10000
10/01/2023 06:51:15 - INFO - __main__ - Batch size = 32
10/01/2023 06:55:33 - INFO - __main__ - ***** Eval results *****
10/01/2023 06:55:33 - INFO - __main__ - acc = 0.823
10/01/2023 06:59:32 - INFO - __main__ - global_step = 17850, average loss = 0.07046543042039048
10/01/2023 07:03:39 - INFO - __main__ - global_step = 17900, average loss = 0.0620857437804807
10/01/2023 07:07:50 - INFO - __main__ - global_step = 17950, average loss = 0.05406381562563183
10/01/2023 07:12:05 - INFO - __main__ - global_step = 18000, average loss = 0.05979254503792617
10/01/2023 07:12:05 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 07:12:05 - INFO - __main__ - Num examples = 10000
10/01/2023 07:12:05 - INFO - __main__ - Batch size = 32
10/01/2023 07:16:22 - INFO - __main__ - ***** Eval results *****
10/01/2023 07:16:22 - INFO - __main__ - acc = 0.8237
10/01/2023 07:20:13 - INFO - __main__ - global_step = 18050, average loss = 0.06541542315782863
10/01/2023 07:24:31 - INFO - __main__ - global_step = 18100, average loss = 0.06534778851972078
10/01/2023 07:28:50 - INFO - __main__ - global_step = 18150, average loss = 0.06520377914806887
10/01/2023 07:33:09 - INFO - __main__ - global_step = 18200, average loss = 0.05995443502964917
10/01/2023 07:33:10 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 07:33:10 - INFO - __main__ - Num examples = 10000
10/01/2023 07:33:10 - INFO - __main__ - Batch size = 32
10/01/2023 07:37:27 - INFO - __main__ - ***** Eval results *****
10/01/2023 07:37:27 - INFO - __main__ - acc = 0.825
10/01/2023 07:41:29 - INFO - __main__ - global_step = 18250, average loss = 0.0729160438424151
10/01/2023 07:45:44 - INFO - __main__ - global_step = 18300, average loss = 0.06983143856698007
10/01/2023 07:48:53 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 07:48:53 - INFO - __main__ - Num examples = 10000
10/01/2023 07:48:53 - INFO - __main__ - Batch size = 32
10/01/2023 07:53:22 - INFO - __main__ - ***** Eval results *****
10/01/2023 07:53:22 - INFO - __main__ - acc = 0.8249
10/01/2023 07:53:22 - INFO - __main__ - global_step = 18336, average loss = 0.09140925639286196
10/01/2023 07:53:56 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 07:53:56 - INFO - __main__ - Num examples = 10000
10/01/2023 07:53:56 - INFO - __main__ - Batch size = 32
10/01/2023 07:58:24 - INFO - __main__ - ***** Eval results *****
10/01/2023 07:58:24 - INFO - __main__ - acc = 0.8326
10/01/2023 07:58:30 - INFO - evaluate_DeBERTa - Namespace(dataset_file='../../../data/mcqa/eval/socialiqa_dev.jsonl', lm='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', out_dir='./eval_results/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', device=0, reader='socialiqa', overwrite_output_dir=False, cache_dir=None)
10/01/2023 07:58:30 - INFO - evaluate_DeBERTa - Initializing output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
10/01/2023 08:06:13 - INFO - evaluate_DeBERTa - Namespace(dataset_file='../../../data/mcqa/eval/winogrande_dev.jsonl', lm='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', out_dir='./eval_results/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', device=0, reader='winogrande', overwrite_output_dir=False, cache_dir=None)
10/01/2023 08:06:13 - INFO - evaluate_DeBERTa - Initializing output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
10/01/2023 08:08:40 - INFO - evaluate_DeBERTa - Namespace(dataset_file='../../../data/mcqa/eval/piqa_dev.jsonl', lm='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', out_dir='./eval_results/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', device=0, reader='piqa', overwrite_output_dir=False, cache_dir=None)
10/01/2023 08:08:40 - INFO - evaluate_DeBERTa - Initializing output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
10/01/2023 08:17:19 - INFO - evaluate_DeBERTa - Namespace(dataset_file='../../../data/mcqa/eval/commonsenseqa_dev.jsonl', lm='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', out_dir='./eval_results/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', device=0, reader='commonsenseqa', overwrite_output_dir=False, cache_dir=None)
10/01/2023 08:17:19 - INFO - evaluate_DeBERTa - Initializing output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
10/01/2023 08:23:12 - INFO - evaluate_DeBERTa - Namespace(dataset_file='../../../data/mcqa/eval/anli_dev.jsonl', lm='output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', out_dir='./eval_results/deberta-v3-large_car_2i_name_100k_seed_101_5e-6', device=0, reader='anli', overwrite_output_dir=False, cache_dir=None)
10/01/2023 08:23:12 - INFO - evaluate_DeBERTa - Initializing output/Output_ATOMIC-pseudo-wWC/car_2i/deberta-v3-large_car_2i_name_100k_seed_101_5e-6
10/01/2023 08:28:58 - INFO - __main__ - ***** Running evaluation *****
10/01/2023 08:28:58 - INFO - __main__ - Num examples = 120
10/01/2023 08:28:58 - INFO - __main__ - Batch size = 32
10/01/2023 08:29:16 - INFO - __main__ - ***** Eval results *****
10/01/2023 08:29:16 - INFO - __main__ - acc = 0.475
|