File size: 58,645 Bytes
5dbaccf |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 |
2021-01-16 03:26:26,142 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,146 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): XLMRobertaModel(
(embeddings): RobertaEmbeddings(
(word_embeddings): Embedding(250002, 1024, padding_idx=1)
(position_embeddings): Embedding(514, 1024, padding_idx=1)
(token_type_embeddings): Embedding(1, 1024)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): RobertaEncoder(
(layer): ModuleList(
(0): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(1): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(2): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(3): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(4): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(5): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(6): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(7): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(8): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(9): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(10): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(11): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(12): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(13): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(14): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(15): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(16): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(17): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(18): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(19): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(20): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(21): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(22): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(23): RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=1024, out_features=1024, bias=True)
(key): Linear(in_features=1024, out_features=1024, bias=True)
(value): Linear(in_features=1024, out_features=1024, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=1024, out_features=4096, bias=True)
)
(output): RobertaOutput(
(dense): Linear(in_features=4096, out_features=1024, bias=True)
(LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): RobertaPooler(
(dense): Linear(in_features=1024, out_features=1024, bias=True)
(activation): Tanh()
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1024, out_features=20, bias=True)
(beta): 1.0
(weights): None
(weight_tensor) None
)"
2021-01-16 03:26:26,148 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,148 Corpus: "Corpus: 8323 train + 1915 dev + 1517 test sentences"
2021-01-16 03:26:26,148 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,148 Parameters:
2021-01-16 03:26:26,148 - learning_rate: "5e-06"
2021-01-16 03:26:26,148 - mini_batch_size: "4"
2021-01-16 03:26:26,148 - patience: "3"
2021-01-16 03:26:26,148 - anneal_factor: "0.5"
2021-01-16 03:26:26,148 - max_epochs: "20"
2021-01-16 03:26:26,148 - shuffle: "True"
2021-01-16 03:26:26,148 - train_with_dev: "True"
2021-01-16 03:26:26,148 - batch_growth_annealing: "False"
2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,149 Model training base path: "resources/contextdrop/flert-es-ft+dev-xlm-roberta-large-context+drop-64-True-258"
2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,149 Device: cuda:3
2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
2021-01-16 03:26:26,149 Embeddings storage mode: none
2021-01-16 03:26:26,161 ----------------------------------------------------------------------------------------------------
2021-01-16 03:28:04,650 epoch 1 - iter 256/2560 - loss 0.87027155 - samples/sec: 10.40 - lr: 0.000005
2021-01-16 03:29:42,988 epoch 1 - iter 512/2560 - loss 0.59530026 - samples/sec: 10.41 - lr: 0.000005
2021-01-16 03:31:21,817 epoch 1 - iter 768/2560 - loss 0.52507711 - samples/sec: 10.36 - lr: 0.000005
2021-01-16 03:33:00,647 epoch 1 - iter 1024/2560 - loss 0.45703199 - samples/sec: 10.36 - lr: 0.000005
2021-01-16 03:34:42,020 epoch 1 - iter 1280/2560 - loss 0.41694313 - samples/sec: 10.10 - lr: 0.000005
2021-01-16 03:36:21,509 epoch 1 - iter 1536/2560 - loss 0.38192728 - samples/sec: 10.29 - lr: 0.000005
2021-01-16 03:38:00,214 epoch 1 - iter 1792/2560 - loss 0.36367874 - samples/sec: 10.38 - lr: 0.000005
2021-01-16 03:39:38,871 epoch 1 - iter 2048/2560 - loss 0.34546215 - samples/sec: 10.38 - lr: 0.000005
2021-01-16 03:41:16,409 epoch 1 - iter 2304/2560 - loss 0.33346538 - samples/sec: 10.50 - lr: 0.000005
2021-01-16 03:42:54,136 epoch 1 - iter 2560/2560 - loss 0.32667036 - samples/sec: 10.48 - lr: 0.000005
2021-01-16 03:42:54,138 ----------------------------------------------------------------------------------------------------
2021-01-16 03:42:54,138 EPOCH 1 done: loss 0.3267 - lr 0.0000050
2021-01-16 03:42:54,138 BAD EPOCHS (no improvement): 4
2021-01-16 03:42:54,141 ----------------------------------------------------------------------------------------------------
2021-01-16 03:44:32,764 epoch 2 - iter 256/2560 - loss 0.21108762 - samples/sec: 10.38 - lr: 0.000005
2021-01-16 03:46:11,253 epoch 2 - iter 512/2560 - loss 0.22128268 - samples/sec: 10.40 - lr: 0.000005
2021-01-16 03:47:49,772 epoch 2 - iter 768/2560 - loss 0.22246430 - samples/sec: 10.39 - lr: 0.000005
2021-01-16 03:49:28,129 epoch 2 - iter 1024/2560 - loss 0.21358276 - samples/sec: 10.41 - lr: 0.000005
2021-01-16 03:51:06,924 epoch 2 - iter 1280/2560 - loss 0.21429265 - samples/sec: 10.37 - lr: 0.000005
2021-01-16 03:52:46,984 epoch 2 - iter 1536/2560 - loss 0.21196466 - samples/sec: 10.23 - lr: 0.000005
2021-01-16 03:54:29,705 epoch 2 - iter 1792/2560 - loss 0.21758704 - samples/sec: 9.97 - lr: 0.000005
2021-01-16 03:56:10,481 epoch 2 - iter 2048/2560 - loss 0.21965157 - samples/sec: 10.16 - lr: 0.000005
2021-01-16 03:57:50,615 epoch 2 - iter 2304/2560 - loss 0.21877101 - samples/sec: 10.23 - lr: 0.000005
2021-01-16 03:59:31,158 epoch 2 - iter 2560/2560 - loss 0.21954602 - samples/sec: 10.19 - lr: 0.000005
2021-01-16 03:59:31,160 ----------------------------------------------------------------------------------------------------
2021-01-16 03:59:31,160 EPOCH 2 done: loss 0.2195 - lr 0.0000049
2021-01-16 03:59:31,160 BAD EPOCHS (no improvement): 4
2021-01-16 03:59:31,163 ----------------------------------------------------------------------------------------------------
2021-01-16 04:01:11,656 epoch 3 - iter 256/2560 - loss 0.20612080 - samples/sec: 10.19 - lr: 0.000005
2021-01-16 04:02:51,941 epoch 3 - iter 512/2560 - loss 0.19317841 - samples/sec: 10.21 - lr: 0.000005
2021-01-16 04:04:32,511 epoch 3 - iter 768/2560 - loss 0.19963626 - samples/sec: 10.18 - lr: 0.000005
2021-01-16 04:06:11,909 epoch 3 - iter 1024/2560 - loss 0.19312694 - samples/sec: 10.30 - lr: 0.000005
2021-01-16 04:07:53,866 epoch 3 - iter 1280/2560 - loss 0.19674287 - samples/sec: 10.04 - lr: 0.000005
2021-01-16 04:09:33,688 epoch 3 - iter 1536/2560 - loss 0.19699039 - samples/sec: 10.26 - lr: 0.000005
2021-01-16 04:11:13,497 epoch 3 - iter 1792/2560 - loss 0.19513463 - samples/sec: 10.26 - lr: 0.000005
2021-01-16 04:12:53,541 epoch 3 - iter 2048/2560 - loss 0.19334227 - samples/sec: 10.24 - lr: 0.000005
2021-01-16 04:14:33,916 epoch 3 - iter 2304/2560 - loss 0.19294838 - samples/sec: 10.20 - lr: 0.000005
2021-01-16 04:16:13,001 epoch 3 - iter 2560/2560 - loss 0.19331988 - samples/sec: 10.34 - lr: 0.000005
2021-01-16 04:16:13,003 ----------------------------------------------------------------------------------------------------
2021-01-16 04:16:13,003 EPOCH 3 done: loss 0.1933 - lr 0.0000047
2021-01-16 04:16:13,003 BAD EPOCHS (no improvement): 4
2021-01-16 04:16:13,006 ----------------------------------------------------------------------------------------------------
2021-01-16 04:17:52,069 epoch 4 - iter 256/2560 - loss 0.16853571 - samples/sec: 10.34 - lr: 0.000005
2021-01-16 04:19:31,083 epoch 4 - iter 512/2560 - loss 0.16783710 - samples/sec: 10.34 - lr: 0.000005
2021-01-16 04:21:09,860 epoch 4 - iter 768/2560 - loss 0.17852492 - samples/sec: 10.37 - lr: 0.000005
2021-01-16 04:22:48,222 epoch 4 - iter 1024/2560 - loss 0.18170671 - samples/sec: 10.41 - lr: 0.000005
2021-01-16 04:24:28,304 epoch 4 - iter 1280/2560 - loss 0.17619093 - samples/sec: 10.23 - lr: 0.000005
2021-01-16 04:26:06,542 epoch 4 - iter 1536/2560 - loss 0.18313451 - samples/sec: 10.42 - lr: 0.000005
2021-01-16 04:27:44,976 epoch 4 - iter 1792/2560 - loss 0.18543083 - samples/sec: 10.40 - lr: 0.000005
2021-01-16 04:29:25,900 epoch 4 - iter 2048/2560 - loss 0.18948785 - samples/sec: 10.15 - lr: 0.000005
2021-01-16 04:31:03,494 epoch 4 - iter 2304/2560 - loss 0.18818842 - samples/sec: 10.49 - lr: 0.000005
2021-01-16 04:32:40,881 epoch 4 - iter 2560/2560 - loss 0.18725109 - samples/sec: 10.52 - lr: 0.000005
2021-01-16 04:32:40,883 ----------------------------------------------------------------------------------------------------
2021-01-16 04:32:40,884 EPOCH 4 done: loss 0.1873 - lr 0.0000045
2021-01-16 04:32:40,884 BAD EPOCHS (no improvement): 4
2021-01-16 04:32:40,886 ----------------------------------------------------------------------------------------------------
2021-01-16 04:34:18,022 epoch 5 - iter 256/2560 - loss 0.19665239 - samples/sec: 10.54 - lr: 0.000004
2021-01-16 04:35:54,846 epoch 5 - iter 512/2560 - loss 0.19948870 - samples/sec: 10.58 - lr: 0.000004
2021-01-16 04:37:32,278 epoch 5 - iter 768/2560 - loss 0.19201483 - samples/sec: 10.51 - lr: 0.000004
2021-01-16 04:39:11,686 epoch 5 - iter 1024/2560 - loss 0.18716260 - samples/sec: 10.30 - lr: 0.000004
2021-01-16 04:40:48,941 epoch 5 - iter 1280/2560 - loss 0.17767008 - samples/sec: 10.53 - lr: 0.000004
2021-01-16 04:42:26,151 epoch 5 - iter 1536/2560 - loss 0.17738586 - samples/sec: 10.53 - lr: 0.000004
2021-01-16 04:44:03,440 epoch 5 - iter 1792/2560 - loss 0.17437861 - samples/sec: 10.53 - lr: 0.000004
2021-01-16 04:45:40,641 epoch 5 - iter 2048/2560 - loss 0.17843058 - samples/sec: 10.54 - lr: 0.000004
2021-01-16 04:47:18,726 epoch 5 - iter 2304/2560 - loss 0.17962338 - samples/sec: 10.44 - lr: 0.000004
2021-01-16 04:48:56,938 epoch 5 - iter 2560/2560 - loss 0.17857406 - samples/sec: 10.43 - lr: 0.000004
2021-01-16 04:48:56,941 ----------------------------------------------------------------------------------------------------
2021-01-16 04:48:56,941 EPOCH 5 done: loss 0.1786 - lr 0.0000043
2021-01-16 04:48:56,941 BAD EPOCHS (no improvement): 4
2021-01-16 04:48:56,944 ----------------------------------------------------------------------------------------------------
2021-01-16 04:50:37,578 epoch 6 - iter 256/2560 - loss 0.19558805 - samples/sec: 10.18 - lr: 0.000004
2021-01-16 04:52:15,762 epoch 6 - iter 512/2560 - loss 0.17503759 - samples/sec: 10.43 - lr: 0.000004
2021-01-16 04:53:52,814 epoch 6 - iter 768/2560 - loss 0.17416353 - samples/sec: 10.55 - lr: 0.000004
2021-01-16 04:55:29,984 epoch 6 - iter 1024/2560 - loss 0.16483752 - samples/sec: 10.54 - lr: 0.000004
2021-01-16 04:57:07,349 epoch 6 - iter 1280/2560 - loss 0.16624319 - samples/sec: 10.52 - lr: 0.000004
2021-01-16 04:58:44,378 epoch 6 - iter 1536/2560 - loss 0.16546115 - samples/sec: 10.55 - lr: 0.000004
2021-01-16 05:00:21,884 epoch 6 - iter 1792/2560 - loss 0.16436590 - samples/sec: 10.50 - lr: 0.000004
2021-01-16 05:01:58,951 epoch 6 - iter 2048/2560 - loss 0.16724299 - samples/sec: 10.55 - lr: 0.000004
2021-01-16 05:03:36,482 epoch 6 - iter 2304/2560 - loss 0.16918433 - samples/sec: 10.50 - lr: 0.000004
2021-01-16 05:05:14,584 epoch 6 - iter 2560/2560 - loss 0.16921876 - samples/sec: 10.44 - lr: 0.000004
2021-01-16 05:05:14,587 ----------------------------------------------------------------------------------------------------
2021-01-16 05:05:14,587 EPOCH 6 done: loss 0.1692 - lr 0.0000040
2021-01-16 05:05:14,587 BAD EPOCHS (no improvement): 4
2021-01-16 05:05:14,599 ----------------------------------------------------------------------------------------------------
2021-01-16 05:06:51,663 epoch 7 - iter 256/2560 - loss 0.18482960 - samples/sec: 10.55 - lr: 0.000004
2021-01-16 05:08:28,534 epoch 7 - iter 512/2560 - loss 0.16880554 - samples/sec: 10.57 - lr: 0.000004
2021-01-16 05:10:05,876 epoch 7 - iter 768/2560 - loss 0.16822603 - samples/sec: 10.52 - lr: 0.000004
2021-01-16 05:11:42,818 epoch 7 - iter 1024/2560 - loss 0.17842509 - samples/sec: 10.56 - lr: 0.000004
2021-01-16 05:13:20,349 epoch 7 - iter 1280/2560 - loss 0.16997025 - samples/sec: 10.50 - lr: 0.000004
2021-01-16 05:14:57,279 epoch 7 - iter 1536/2560 - loss 0.16850697 - samples/sec: 10.57 - lr: 0.000004
2021-01-16 05:16:33,604 epoch 7 - iter 1792/2560 - loss 0.16897440 - samples/sec: 10.63 - lr: 0.000004
2021-01-16 05:18:11,130 epoch 7 - iter 2048/2560 - loss 0.16901586 - samples/sec: 10.50 - lr: 0.000004
2021-01-16 05:19:48,742 epoch 7 - iter 2304/2560 - loss 0.16746824 - samples/sec: 10.49 - lr: 0.000004
2021-01-16 05:21:27,376 epoch 7 - iter 2560/2560 - loss 0.16665962 - samples/sec: 10.38 - lr: 0.000004
2021-01-16 05:21:27,378 ----------------------------------------------------------------------------------------------------
2021-01-16 05:21:27,378 EPOCH 7 done: loss 0.1667 - lr 0.0000036
2021-01-16 05:21:27,378 BAD EPOCHS (no improvement): 4
2021-01-16 05:21:27,381 ----------------------------------------------------------------------------------------------------
2021-01-16 05:23:04,098 epoch 8 - iter 256/2560 - loss 0.17170512 - samples/sec: 10.59 - lr: 0.000004
2021-01-16 05:24:40,963 epoch 8 - iter 512/2560 - loss 0.16578343 - samples/sec: 10.57 - lr: 0.000004
2021-01-16 05:26:17,874 epoch 8 - iter 768/2560 - loss 0.15936900 - samples/sec: 10.57 - lr: 0.000004
2021-01-16 05:27:54,684 epoch 8 - iter 1024/2560 - loss 0.16254958 - samples/sec: 10.58 - lr: 0.000003
2021-01-16 05:29:31,674 epoch 8 - iter 1280/2560 - loss 0.16254652 - samples/sec: 10.56 - lr: 0.000003
2021-01-16 05:31:09,021 epoch 8 - iter 1536/2560 - loss 0.16126451 - samples/sec: 10.52 - lr: 0.000003
2021-01-16 05:32:48,943 epoch 8 - iter 1792/2560 - loss 0.15960888 - samples/sec: 10.25 - lr: 0.000003
2021-01-16 05:34:26,910 epoch 8 - iter 2048/2560 - loss 0.16106515 - samples/sec: 10.45 - lr: 0.000003
2021-01-16 05:36:05,072 epoch 8 - iter 2304/2560 - loss 0.15881735 - samples/sec: 10.43 - lr: 0.000003
2021-01-16 05:37:43,202 epoch 8 - iter 2560/2560 - loss 0.16070351 - samples/sec: 10.44 - lr: 0.000003
2021-01-16 05:37:43,204 ----------------------------------------------------------------------------------------------------
2021-01-16 05:37:43,204 EPOCH 8 done: loss 0.1607 - lr 0.0000033
2021-01-16 05:37:43,204 BAD EPOCHS (no improvement): 4
2021-01-16 05:37:43,207 ----------------------------------------------------------------------------------------------------
2021-01-16 05:39:21,420 epoch 9 - iter 256/2560 - loss 0.17227183 - samples/sec: 10.43 - lr: 0.000003
2021-01-16 05:40:59,261 epoch 9 - iter 512/2560 - loss 0.17554657 - samples/sec: 10.47 - lr: 0.000003
2021-01-16 05:42:38,175 epoch 9 - iter 768/2560 - loss 0.16616659 - samples/sec: 10.35 - lr: 0.000003
2021-01-16 05:44:16,618 epoch 9 - iter 1024/2560 - loss 0.16832605 - samples/sec: 10.40 - lr: 0.000003
2021-01-16 05:45:57,429 epoch 9 - iter 1280/2560 - loss 0.16394874 - samples/sec: 10.16 - lr: 0.000003
2021-01-16 05:47:35,957 epoch 9 - iter 1536/2560 - loss 0.16352007 - samples/sec: 10.39 - lr: 0.000003
2021-01-16 05:49:13,705 epoch 9 - iter 1792/2560 - loss 0.16385724 - samples/sec: 10.48 - lr: 0.000003
2021-01-16 05:50:52,424 epoch 9 - iter 2048/2560 - loss 0.16055360 - samples/sec: 10.37 - lr: 0.000003
2021-01-16 05:52:30,508 epoch 9 - iter 2304/2560 - loss 0.16334559 - samples/sec: 10.44 - lr: 0.000003
2021-01-16 05:54:08,468 epoch 9 - iter 2560/2560 - loss 0.16240605 - samples/sec: 10.45 - lr: 0.000003
2021-01-16 05:54:08,470 ----------------------------------------------------------------------------------------------------
2021-01-16 05:54:08,470 EPOCH 9 done: loss 0.1624 - lr 0.0000029
2021-01-16 05:54:08,470 BAD EPOCHS (no improvement): 4
2021-01-16 05:54:08,473 ----------------------------------------------------------------------------------------------------
2021-01-16 05:55:47,128 epoch 10 - iter 256/2560 - loss 0.16313144 - samples/sec: 10.38 - lr: 0.000003
2021-01-16 05:57:25,407 epoch 10 - iter 512/2560 - loss 0.15020732 - samples/sec: 10.42 - lr: 0.000003
2021-01-16 05:59:03,413 epoch 10 - iter 768/2560 - loss 0.15983365 - samples/sec: 10.45 - lr: 0.000003
2021-01-16 06:00:41,548 epoch 10 - iter 1024/2560 - loss 0.15880243 - samples/sec: 10.44 - lr: 0.000003
2021-01-16 06:02:19,846 epoch 10 - iter 1280/2560 - loss 0.15641733 - samples/sec: 10.42 - lr: 0.000003
2021-01-16 06:03:57,792 epoch 10 - iter 1536/2560 - loss 0.15979563 - samples/sec: 10.46 - lr: 0.000003
2021-01-16 06:05:37,942 epoch 10 - iter 1792/2560 - loss 0.15822496 - samples/sec: 10.23 - lr: 0.000003
2021-01-16 06:07:15,923 epoch 10 - iter 2048/2560 - loss 0.15759511 - samples/sec: 10.45 - lr: 0.000003
2021-01-16 06:08:53,939 epoch 10 - iter 2304/2560 - loss 0.15693087 - samples/sec: 10.45 - lr: 0.000003
2021-01-16 06:10:32,048 epoch 10 - iter 2560/2560 - loss 0.15801453 - samples/sec: 10.44 - lr: 0.000002
2021-01-16 06:10:32,051 ----------------------------------------------------------------------------------------------------
2021-01-16 06:10:32,051 EPOCH 10 done: loss 0.1580 - lr 0.0000025
2021-01-16 06:10:32,051 BAD EPOCHS (no improvement): 4
2021-01-16 06:10:32,054 ----------------------------------------------------------------------------------------------------
2021-01-16 06:12:10,483 epoch 11 - iter 256/2560 - loss 0.16742767 - samples/sec: 10.40 - lr: 0.000002
2021-01-16 06:13:48,782 epoch 11 - iter 512/2560 - loss 0.15327274 - samples/sec: 10.42 - lr: 0.000002
2021-01-16 06:15:26,970 epoch 11 - iter 768/2560 - loss 0.15209073 - samples/sec: 10.43 - lr: 0.000002
2021-01-16 06:17:05,366 epoch 11 - iter 1024/2560 - loss 0.14838890 - samples/sec: 10.41 - lr: 0.000002
2021-01-16 06:18:43,497 epoch 11 - iter 1280/2560 - loss 0.14857876 - samples/sec: 10.44 - lr: 0.000002
2021-01-16 06:20:21,564 epoch 11 - iter 1536/2560 - loss 0.14942513 - samples/sec: 10.44 - lr: 0.000002
2021-01-16 06:21:59,181 epoch 11 - iter 1792/2560 - loss 0.14977847 - samples/sec: 10.49 - lr: 0.000002
2021-01-16 06:23:37,984 epoch 11 - iter 2048/2560 - loss 0.15052564 - samples/sec: 10.37 - lr: 0.000002
2021-01-16 06:25:18,744 epoch 11 - iter 2304/2560 - loss 0.15348464 - samples/sec: 10.16 - lr: 0.000002
2021-01-16 06:26:56,801 epoch 11 - iter 2560/2560 - loss 0.15405217 - samples/sec: 10.44 - lr: 0.000002
2021-01-16 06:26:56,804 ----------------------------------------------------------------------------------------------------
2021-01-16 06:26:56,804 EPOCH 11 done: loss 0.1541 - lr 0.0000021
2021-01-16 06:26:56,804 BAD EPOCHS (no improvement): 4
2021-01-16 06:26:56,806 ----------------------------------------------------------------------------------------------------
2021-01-16 06:28:34,919 epoch 12 - iter 256/2560 - loss 0.14515525 - samples/sec: 10.44 - lr: 0.000002
2021-01-16 06:30:14,290 epoch 12 - iter 512/2560 - loss 0.16185121 - samples/sec: 10.31 - lr: 0.000002
2021-01-16 06:31:51,825 epoch 12 - iter 768/2560 - loss 0.15630178 - samples/sec: 10.50 - lr: 0.000002
2021-01-16 06:33:29,645 epoch 12 - iter 1024/2560 - loss 0.16061640 - samples/sec: 10.47 - lr: 0.000002
2021-01-16 06:35:07,390 epoch 12 - iter 1280/2560 - loss 0.16106939 - samples/sec: 10.48 - lr: 0.000002
2021-01-16 06:36:45,537 epoch 12 - iter 1536/2560 - loss 0.16553326 - samples/sec: 10.43 - lr: 0.000002
2021-01-16 06:38:23,976 epoch 12 - iter 1792/2560 - loss 0.16298360 - samples/sec: 10.40 - lr: 0.000002
2021-01-16 06:40:01,697 epoch 12 - iter 2048/2560 - loss 0.15791582 - samples/sec: 10.48 - lr: 0.000002
2021-01-16 06:41:40,081 epoch 12 - iter 2304/2560 - loss 0.15724189 - samples/sec: 10.41 - lr: 0.000002
2021-01-16 06:43:17,722 epoch 12 - iter 2560/2560 - loss 0.15517561 - samples/sec: 10.49 - lr: 0.000002
2021-01-16 06:43:17,724 ----------------------------------------------------------------------------------------------------
2021-01-16 06:43:17,724 EPOCH 12 done: loss 0.1552 - lr 0.0000017
2021-01-16 06:43:17,724 BAD EPOCHS (no improvement): 4
2021-01-16 06:43:17,727 ----------------------------------------------------------------------------------------------------
2021-01-16 06:44:55,687 epoch 13 - iter 256/2560 - loss 0.15713525 - samples/sec: 10.45 - lr: 0.000002
2021-01-16 06:46:36,001 epoch 13 - iter 512/2560 - loss 0.15100717 - samples/sec: 10.21 - lr: 0.000002
2021-01-16 06:48:13,819 epoch 13 - iter 768/2560 - loss 0.15847721 - samples/sec: 10.47 - lr: 0.000002
2021-01-16 06:49:52,306 epoch 13 - iter 1024/2560 - loss 0.15904259 - samples/sec: 10.40 - lr: 0.000002
2021-01-16 06:51:29,891 epoch 13 - iter 1280/2560 - loss 0.15989578 - samples/sec: 10.49 - lr: 0.000002
2021-01-16 06:53:08,047 epoch 13 - iter 1536/2560 - loss 0.15584846 - samples/sec: 10.43 - lr: 0.000002
2021-01-16 06:54:45,903 epoch 13 - iter 1792/2560 - loss 0.15456669 - samples/sec: 10.47 - lr: 0.000001
2021-01-16 06:56:23,958 epoch 13 - iter 2048/2560 - loss 0.15476196 - samples/sec: 10.44 - lr: 0.000001
2021-01-16 06:58:01,860 epoch 13 - iter 2304/2560 - loss 0.15554818 - samples/sec: 10.46 - lr: 0.000001
2021-01-16 06:59:39,510 epoch 13 - iter 2560/2560 - loss 0.15582554 - samples/sec: 10.49 - lr: 0.000001
2021-01-16 06:59:39,513 ----------------------------------------------------------------------------------------------------
2021-01-16 06:59:39,513 EPOCH 13 done: loss 0.1558 - lr 0.0000014
2021-01-16 06:59:39,513 BAD EPOCHS (no improvement): 4
2021-01-16 06:59:39,536 ----------------------------------------------------------------------------------------------------
2021-01-16 07:01:17,550 epoch 14 - iter 256/2560 - loss 0.14336771 - samples/sec: 10.45 - lr: 0.000001
2021-01-16 07:02:55,149 epoch 14 - iter 512/2560 - loss 0.13420979 - samples/sec: 10.49 - lr: 0.000001
2021-01-16 07:04:33,295 epoch 14 - iter 768/2560 - loss 0.14666678 - samples/sec: 10.43 - lr: 0.000001
2021-01-16 07:06:11,482 epoch 14 - iter 1024/2560 - loss 0.14107045 - samples/sec: 10.43 - lr: 0.000001
2021-01-16 07:07:50,423 epoch 14 - iter 1280/2560 - loss 0.14810884 - samples/sec: 10.35 - lr: 0.000001
2021-01-16 07:09:29,149 epoch 14 - iter 1536/2560 - loss 0.15039081 - samples/sec: 10.37 - lr: 0.000001
2021-01-16 07:11:08,549 epoch 14 - iter 1792/2560 - loss 0.15404881 - samples/sec: 10.30 - lr: 0.000001
2021-01-16 07:12:48,860 epoch 14 - iter 2048/2560 - loss 0.15398198 - samples/sec: 10.21 - lr: 0.000001
2021-01-16 07:14:26,993 epoch 14 - iter 2304/2560 - loss 0.15119867 - samples/sec: 10.44 - lr: 0.000001
2021-01-16 07:16:07,905 epoch 14 - iter 2560/2560 - loss 0.14988600 - samples/sec: 10.15 - lr: 0.000001
2021-01-16 07:16:07,907 ----------------------------------------------------------------------------------------------------
2021-01-16 07:16:07,907 EPOCH 14 done: loss 0.1499 - lr 0.0000010
2021-01-16 07:16:07,907 BAD EPOCHS (no improvement): 4
2021-01-16 07:16:07,910 ----------------------------------------------------------------------------------------------------
2021-01-16 07:17:47,163 epoch 15 - iter 256/2560 - loss 0.13211162 - samples/sec: 10.32 - lr: 0.000001
2021-01-16 07:19:26,428 epoch 15 - iter 512/2560 - loss 0.14312262 - samples/sec: 10.32 - lr: 0.000001
2021-01-16 07:21:04,402 epoch 15 - iter 768/2560 - loss 0.14991927 - samples/sec: 10.45 - lr: 0.000001
2021-01-16 07:22:42,083 epoch 15 - iter 1024/2560 - loss 0.15132502 - samples/sec: 10.48 - lr: 0.000001
2021-01-16 07:24:23,248 epoch 15 - iter 1280/2560 - loss 0.15012698 - samples/sec: 10.12 - lr: 0.000001
2021-01-16 07:26:02,510 epoch 15 - iter 1536/2560 - loss 0.15443282 - samples/sec: 10.32 - lr: 0.000001
2021-01-16 07:27:41,227 epoch 15 - iter 1792/2560 - loss 0.15337861 - samples/sec: 10.37 - lr: 0.000001
2021-01-16 07:29:19,916 epoch 15 - iter 2048/2560 - loss 0.15342457 - samples/sec: 10.38 - lr: 0.000001
2021-01-16 07:30:58,353 epoch 15 - iter 2304/2560 - loss 0.15126241 - samples/sec: 10.40 - lr: 0.000001
2021-01-16 07:32:36,692 epoch 15 - iter 2560/2560 - loss 0.14841692 - samples/sec: 10.41 - lr: 0.000001
2021-01-16 07:32:36,694 ----------------------------------------------------------------------------------------------------
2021-01-16 07:32:36,694 EPOCH 15 done: loss 0.1484 - lr 0.0000007
2021-01-16 07:32:36,694 BAD EPOCHS (no improvement): 4
2021-01-16 07:32:36,700 ----------------------------------------------------------------------------------------------------
2021-01-16 07:34:15,608 epoch 16 - iter 256/2560 - loss 0.14154861 - samples/sec: 10.35 - lr: 0.000001
2021-01-16 07:35:54,182 epoch 16 - iter 512/2560 - loss 0.15666068 - samples/sec: 10.39 - lr: 0.000001
2021-01-16 07:37:32,436 epoch 16 - iter 768/2560 - loss 0.14965853 - samples/sec: 10.42 - lr: 0.000001
2021-01-16 07:39:11,322 epoch 16 - iter 1024/2560 - loss 0.14517837 - samples/sec: 10.36 - lr: 0.000001
2021-01-16 07:40:50,070 epoch 16 - iter 1280/2560 - loss 0.15012946 - samples/sec: 10.37 - lr: 0.000001
2021-01-16 07:42:28,901 epoch 16 - iter 1536/2560 - loss 0.14944365 - samples/sec: 10.36 - lr: 0.000001
2021-01-16 07:44:07,511 epoch 16 - iter 1792/2560 - loss 0.15203691 - samples/sec: 10.39 - lr: 0.000001
2021-01-16 07:45:46,097 epoch 16 - iter 2048/2560 - loss 0.15361748 - samples/sec: 10.39 - lr: 0.000001
2021-01-16 07:47:24,743 epoch 16 - iter 2304/2560 - loss 0.15600239 - samples/sec: 10.38 - lr: 0.000001
2021-01-16 07:49:05,943 epoch 16 - iter 2560/2560 - loss 0.15282003 - samples/sec: 10.12 - lr: 0.000000
2021-01-16 07:49:05,945 ----------------------------------------------------------------------------------------------------
2021-01-16 07:49:05,945 EPOCH 16 done: loss 0.1528 - lr 0.0000005
2021-01-16 07:49:05,945 BAD EPOCHS (no improvement): 4
2021-01-16 07:49:05,948 ----------------------------------------------------------------------------------------------------
2021-01-16 07:50:44,838 epoch 17 - iter 256/2560 - loss 0.16498748 - samples/sec: 10.36 - lr: 0.000000
2021-01-16 07:52:23,007 epoch 17 - iter 512/2560 - loss 0.16360209 - samples/sec: 10.43 - lr: 0.000000
2021-01-16 07:54:00,994 epoch 17 - iter 768/2560 - loss 0.15339211 - samples/sec: 10.45 - lr: 0.000000
2021-01-16 07:55:39,191 epoch 17 - iter 1024/2560 - loss 0.15505899 - samples/sec: 10.43 - lr: 0.000000
2021-01-16 07:57:19,956 epoch 17 - iter 1280/2560 - loss 0.15433689 - samples/sec: 10.16 - lr: 0.000000
2021-01-16 07:58:58,357 epoch 17 - iter 1536/2560 - loss 0.15255959 - samples/sec: 10.41 - lr: 0.000000
2021-01-16 08:00:36,819 epoch 17 - iter 1792/2560 - loss 0.15399288 - samples/sec: 10.40 - lr: 0.000000
2021-01-16 08:02:15,472 epoch 17 - iter 2048/2560 - loss 0.15148049 - samples/sec: 10.38 - lr: 0.000000
2021-01-16 08:03:54,072 epoch 17 - iter 2304/2560 - loss 0.15382739 - samples/sec: 10.39 - lr: 0.000000
2021-01-16 08:05:31,830 epoch 17 - iter 2560/2560 - loss 0.15712540 - samples/sec: 10.48 - lr: 0.000000
2021-01-16 08:05:31,833 ----------------------------------------------------------------------------------------------------
2021-01-16 08:05:31,833 EPOCH 17 done: loss 0.1571 - lr 0.0000003
2021-01-16 08:05:31,833 BAD EPOCHS (no improvement): 4
2021-01-16 08:05:31,841 ----------------------------------------------------------------------------------------------------
2021-01-16 08:07:10,239 epoch 18 - iter 256/2560 - loss 0.15978983 - samples/sec: 10.41 - lr: 0.000000
2021-01-16 08:08:48,106 epoch 18 - iter 512/2560 - loss 0.14347639 - samples/sec: 10.46 - lr: 0.000000
2021-01-16 08:10:26,495 epoch 18 - iter 768/2560 - loss 0.15206254 - samples/sec: 10.41 - lr: 0.000000
2021-01-16 08:12:04,438 epoch 18 - iter 1024/2560 - loss 0.16796272 - samples/sec: 10.46 - lr: 0.000000
2021-01-16 08:13:42,204 epoch 18 - iter 1280/2560 - loss 0.16531154 - samples/sec: 10.48 - lr: 0.000000
2021-01-16 08:15:23,133 epoch 18 - iter 1536/2560 - loss 0.16233384 - samples/sec: 10.15 - lr: 0.000000
2021-01-16 08:17:01,293 epoch 18 - iter 1792/2560 - loss 0.16011966 - samples/sec: 10.43 - lr: 0.000000
2021-01-16 08:18:39,512 epoch 18 - iter 2048/2560 - loss 0.16087553 - samples/sec: 10.43 - lr: 0.000000
2021-01-16 08:20:17,092 epoch 18 - iter 2304/2560 - loss 0.16158800 - samples/sec: 10.50 - lr: 0.000000
2021-01-16 08:21:54,438 epoch 18 - iter 2560/2560 - loss 0.16291885 - samples/sec: 10.52 - lr: 0.000000
2021-01-16 08:21:54,441 ----------------------------------------------------------------------------------------------------
2021-01-16 08:21:54,441 EPOCH 18 done: loss 0.1629 - lr 0.0000001
2021-01-16 08:21:54,441 BAD EPOCHS (no improvement): 4
2021-01-16 08:21:54,456 ----------------------------------------------------------------------------------------------------
2021-01-16 08:23:31,809 epoch 19 - iter 256/2560 - loss 0.13830293 - samples/sec: 10.52 - lr: 0.000000
2021-01-16 08:25:09,222 epoch 19 - iter 512/2560 - loss 0.14792782 - samples/sec: 10.51 - lr: 0.000000
2021-01-16 08:26:47,079 epoch 19 - iter 768/2560 - loss 0.13707639 - samples/sec: 10.47 - lr: 0.000000
2021-01-16 08:28:27,701 epoch 19 - iter 1024/2560 - loss 0.13387744 - samples/sec: 10.18 - lr: 0.000000
2021-01-16 08:30:05,328 epoch 19 - iter 1280/2560 - loss 0.13241945 - samples/sec: 10.49 - lr: 0.000000
2021-01-16 08:31:43,732 epoch 19 - iter 1536/2560 - loss 0.13879341 - samples/sec: 10.41 - lr: 0.000000
2021-01-16 08:33:21,817 epoch 19 - iter 1792/2560 - loss 0.13955545 - samples/sec: 10.44 - lr: 0.000000
2021-01-16 08:34:59,377 epoch 19 - iter 2048/2560 - loss 0.13983331 - samples/sec: 10.50 - lr: 0.000000
2021-01-16 08:36:36,814 epoch 19 - iter 2304/2560 - loss 0.14005413 - samples/sec: 10.51 - lr: 0.000000
2021-01-16 08:38:14,963 epoch 19 - iter 2560/2560 - loss 0.14057681 - samples/sec: 10.43 - lr: 0.000000
2021-01-16 08:38:14,965 ----------------------------------------------------------------------------------------------------
2021-01-16 08:38:14,965 EPOCH 19 done: loss 0.1406 - lr 0.0000000
2021-01-16 08:38:14,965 BAD EPOCHS (no improvement): 4
2021-01-16 08:38:14,968 ----------------------------------------------------------------------------------------------------
2021-01-16 08:39:54,826 epoch 20 - iter 256/2560 - loss 0.14269958 - samples/sec: 10.26 - lr: 0.000000
2021-01-16 08:41:32,343 epoch 20 - iter 512/2560 - loss 0.13295984 - samples/sec: 10.50 - lr: 0.000000
2021-01-16 08:43:09,612 epoch 20 - iter 768/2560 - loss 0.13303004 - samples/sec: 10.53 - lr: 0.000000
2021-01-16 08:44:46,898 epoch 20 - iter 1024/2560 - loss 0.13511050 - samples/sec: 10.53 - lr: 0.000000
2021-01-16 08:46:24,453 epoch 20 - iter 1280/2560 - loss 0.14147167 - samples/sec: 10.50 - lr: 0.000000
2021-01-16 08:48:01,998 epoch 20 - iter 1536/2560 - loss 0.14640782 - samples/sec: 10.50 - lr: 0.000000
2021-01-16 08:49:39,864 epoch 20 - iter 1792/2560 - loss 0.14698716 - samples/sec: 10.46 - lr: 0.000000
2021-01-16 08:51:17,251 epoch 20 - iter 2048/2560 - loss 0.14558654 - samples/sec: 10.52 - lr: 0.000000
2021-01-16 08:52:55,347 epoch 20 - iter 2304/2560 - loss 0.14717600 - samples/sec: 10.44 - lr: 0.000000
2021-01-16 08:54:33,232 epoch 20 - iter 2560/2560 - loss 0.14611906 - samples/sec: 10.46 - lr: 0.000000
2021-01-16 08:54:33,234 ----------------------------------------------------------------------------------------------------
2021-01-16 08:54:33,234 EPOCH 20 done: loss 0.1461 - lr 0.0000000
2021-01-16 08:54:33,234 BAD EPOCHS (no improvement): 4
2021-01-16 08:55:12,409 ----------------------------------------------------------------------------------------------------
2021-01-16 08:55:12,409 Testing using best model ...
2021-01-16 08:56:13,946 0.9021 0.9087 0.9054
2021-01-16 08:56:13,946
Results:
- F1-score (micro) 0.9054
- F1-score (macro) 0.8961
By class:
LOC tp: 942 - fp: 87 - fn: 142 - precision: 0.9155 - recall: 0.8690 - f1-score: 0.8916
MISC tp: 272 - fp: 57 - fn: 68 - precision: 0.8267 - recall: 0.8000 - f1-score: 0.8132
ORG tp: 1292 - fp: 188 - fn: 108 - precision: 0.8730 - recall: 0.9229 - f1-score: 0.8972
PER tp: 728 - fp: 19 - fn: 7 - precision: 0.9746 - recall: 0.9905 - f1-score: 0.9825
2021-01-16 08:56:13,946 ----------------------------------------------------------------------------------------------------
|