File size: 60,167 Bytes
9c1cbc3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 |
2021-02-20 11:56:18,090 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,093 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
)"
2021-02-20 11:56:18,094 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,095 Corpus: "MultiCorpus: 16744 train + 3449 dev + 3658 test sentences
- CONLL_03 Corpus: 14903 train + 3449 dev + 3658 test sentences
- WIKIGOLD_NER Corpus: 1841 train + 0 dev + 0 test sentences"
2021-02-20 11:56:18,095 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,095 Parameters:
2021-02-20 11:56:18,095 - learning_rate: "5e-06"
2021-02-20 11:56:18,095 - mini_batch_size: "4"
2021-02-20 11:56:18,095 - patience: "3"
2021-02-20 11:56:18,095 - anneal_factor: "0.5"
2021-02-20 11:56:18,095 - max_epochs: "20"
2021-02-20 11:56:18,095 - shuffle: "True"
2021-02-20 11:56:18,095 - train_with_dev: "True"
2021-02-20 11:56:18,095 - batch_growth_annealing: "False"
2021-02-20 11:56:18,095 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,095 Model training base path: "resources/contextdrop/d-flert-en_release-ft+dev-xlm-roberta-large-context+drop-64-True-42"
2021-02-20 11:56:18,095 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,095 Device: cuda:1
2021-02-20 11:56:18,095 ----------------------------------------------------------------------------------------------------
2021-02-20 11:56:18,095 Embeddings storage mode: none
2021-02-20 11:56:18,104 ----------------------------------------------------------------------------------------------------
2021-02-20 11:59:49,493 epoch 1 - iter 504/5049 - loss 0.84988712 - samples/sec: 9.54 - lr: 0.000005
2021-02-20 12:03:17,203 epoch 1 - iter 1008/5049 - loss 0.64131590 - samples/sec: 9.71 - lr: 0.000005
2021-02-20 12:06:42,427 epoch 1 - iter 1512/5049 - loss 0.54315957 - samples/sec: 9.82 - lr: 0.000005
2021-02-20 12:10:12,872 epoch 1 - iter 2016/5049 - loss 0.48025516 - samples/sec: 9.58 - lr: 0.000005
2021-02-20 12:13:43,522 epoch 1 - iter 2520/5049 - loss 0.46057764 - samples/sec: 9.57 - lr: 0.000005
2021-02-20 12:17:12,894 epoch 1 - iter 3024/5049 - loss 0.42570537 - samples/sec: 9.63 - lr: 0.000005
2021-02-20 12:20:41,525 epoch 1 - iter 3528/5049 - loss 0.39857695 - samples/sec: 9.66 - lr: 0.000005
2021-02-20 12:24:14,564 epoch 1 - iter 4032/5049 - loss 0.38416717 - samples/sec: 9.46 - lr: 0.000005
2021-02-20 12:27:45,615 epoch 1 - iter 4536/5049 - loss 0.37032747 - samples/sec: 9.55 - lr: 0.000005
2021-02-20 12:31:13,574 epoch 1 - iter 5040/5049 - loss 0.35966340 - samples/sec: 9.70 - lr: 0.000005
2021-02-20 12:31:17,124 ----------------------------------------------------------------------------------------------------
2021-02-20 12:31:17,124 EPOCH 1 done: loss 0.3592 - lr 0.0000050
2021-02-20 12:33:21,019 TEST : loss 0.17636922001838684 - score 0.9057
2021-02-20 12:33:21,046 BAD EPOCHS (no improvement): 4
2021-02-20 12:33:21,047 ----------------------------------------------------------------------------------------------------
2021-02-20 12:36:49,271 epoch 2 - iter 504/5049 - loss 0.25564826 - samples/sec: 9.68 - lr: 0.000005
2021-02-20 12:40:20,219 epoch 2 - iter 1008/5049 - loss 0.25560543 - samples/sec: 9.56 - lr: 0.000005
2021-02-20 12:43:48,750 epoch 2 - iter 1512/5049 - loss 0.24306949 - samples/sec: 9.67 - lr: 0.000005
2021-02-20 12:47:18,010 epoch 2 - iter 2016/5049 - loss 0.23918902 - samples/sec: 9.63 - lr: 0.000005
2021-02-20 12:50:49,034 epoch 2 - iter 2520/5049 - loss 0.23745494 - samples/sec: 9.55 - lr: 0.000005
2021-02-20 12:54:18,224 epoch 2 - iter 3024/5049 - loss 0.23599522 - samples/sec: 9.64 - lr: 0.000005
2021-02-20 12:57:46,500 epoch 2 - iter 3528/5049 - loss 0.22758435 - samples/sec: 9.68 - lr: 0.000005
2021-02-20 13:01:14,137 epoch 2 - iter 4032/5049 - loss 0.22602197 - samples/sec: 9.71 - lr: 0.000005
2021-02-20 13:04:43,356 epoch 2 - iter 4536/5049 - loss 0.22365802 - samples/sec: 9.64 - lr: 0.000005
2021-02-20 13:08:14,129 epoch 2 - iter 5040/5049 - loss 0.22152549 - samples/sec: 9.57 - lr: 0.000005
2021-02-20 13:08:17,630 ----------------------------------------------------------------------------------------------------
2021-02-20 13:08:17,630 EPOCH 2 done: loss 0.2212 - lr 0.0000049
2021-02-20 13:10:20,643 TEST : loss 0.11124755442142487 - score 0.9279
2021-02-20 13:10:20,675 BAD EPOCHS (no improvement): 4
2021-02-20 13:10:20,680 ----------------------------------------------------------------------------------------------------
2021-02-20 13:13:50,443 epoch 3 - iter 504/5049 - loss 0.17266852 - samples/sec: 9.61 - lr: 0.000005
2021-02-20 13:17:19,023 epoch 3 - iter 1008/5049 - loss 0.18002962 - samples/sec: 9.67 - lr: 0.000005
2021-02-20 13:20:49,199 epoch 3 - iter 1512/5049 - loss 0.18510266 - samples/sec: 9.59 - lr: 0.000005
2021-02-20 13:24:19,385 epoch 3 - iter 2016/5049 - loss 0.19983503 - samples/sec: 9.59 - lr: 0.000005
2021-02-20 13:27:48,348 epoch 3 - iter 2520/5049 - loss 0.20190812 - samples/sec: 9.65 - lr: 0.000005
2021-02-20 13:31:15,582 epoch 3 - iter 3024/5049 - loss 0.19944912 - samples/sec: 9.73 - lr: 0.000005
2021-02-20 13:34:43,944 epoch 3 - iter 3528/5049 - loss 0.19932389 - samples/sec: 9.68 - lr: 0.000005
2021-02-20 13:38:13,075 epoch 3 - iter 4032/5049 - loss 0.19547160 - samples/sec: 9.64 - lr: 0.000005
2021-02-20 13:41:42,971 epoch 3 - iter 4536/5049 - loss 0.19618987 - samples/sec: 9.61 - lr: 0.000005
2021-02-20 13:45:10,066 epoch 3 - iter 5040/5049 - loss 0.19343864 - samples/sec: 9.74 - lr: 0.000005
2021-02-20 13:45:13,621 ----------------------------------------------------------------------------------------------------
2021-02-20 13:45:13,622 EPOCH 3 done: loss 0.1938 - lr 0.0000047
2021-02-20 13:47:17,651 TEST : loss 0.11028687655925751 - score 0.9348
2021-02-20 13:47:17,678 BAD EPOCHS (no improvement): 4
2021-02-20 13:47:17,680 ----------------------------------------------------------------------------------------------------
2021-02-20 13:50:48,046 epoch 4 - iter 504/5049 - loss 0.19022199 - samples/sec: 9.58 - lr: 0.000005
2021-02-20 13:54:14,852 epoch 4 - iter 1008/5049 - loss 0.17976050 - samples/sec: 9.75 - lr: 0.000005
2021-02-20 13:57:44,871 epoch 4 - iter 1512/5049 - loss 0.17729127 - samples/sec: 9.60 - lr: 0.000005
2021-02-20 14:01:14,307 epoch 4 - iter 2016/5049 - loss 0.17812706 - samples/sec: 9.63 - lr: 0.000005
2021-02-20 14:04:41,981 epoch 4 - iter 2520/5049 - loss 0.18816455 - samples/sec: 9.71 - lr: 0.000005
2021-02-20 14:08:10,238 epoch 4 - iter 3024/5049 - loss 0.18990221 - samples/sec: 9.68 - lr: 0.000005
2021-02-20 14:11:38,151 epoch 4 - iter 3528/5049 - loss 0.19181303 - samples/sec: 9.70 - lr: 0.000005
2021-02-20 14:15:03,479 epoch 4 - iter 4032/5049 - loss 0.19180866 - samples/sec: 9.82 - lr: 0.000005
2021-02-20 14:18:32,995 epoch 4 - iter 4536/5049 - loss 0.19160628 - samples/sec: 9.62 - lr: 0.000005
2021-02-20 14:22:00,977 epoch 4 - iter 5040/5049 - loss 0.19256281 - samples/sec: 9.69 - lr: 0.000005
2021-02-20 14:22:04,481 ----------------------------------------------------------------------------------------------------
2021-02-20 14:22:04,482 EPOCH 4 done: loss 0.1926 - lr 0.0000045
2021-02-20 14:24:09,809 TEST : loss 0.10681818425655365 - score 0.9383
2021-02-20 14:24:09,842 BAD EPOCHS (no improvement): 4
2021-02-20 14:24:09,844 ----------------------------------------------------------------------------------------------------
2021-02-20 14:27:37,280 epoch 5 - iter 504/5049 - loss 0.16645148 - samples/sec: 9.72 - lr: 0.000004
2021-02-20 14:31:05,862 epoch 5 - iter 1008/5049 - loss 0.17264234 - samples/sec: 9.67 - lr: 0.000004
2021-02-20 14:34:31,375 epoch 5 - iter 1512/5049 - loss 0.18603685 - samples/sec: 9.81 - lr: 0.000004
2021-02-20 14:37:57,695 epoch 5 - iter 2016/5049 - loss 0.18245931 - samples/sec: 9.77 - lr: 0.000004
2021-02-20 14:41:25,198 epoch 5 - iter 2520/5049 - loss 0.19293042 - samples/sec: 9.72 - lr: 0.000004
2021-02-20 14:44:53,631 epoch 5 - iter 3024/5049 - loss 0.19454820 - samples/sec: 9.67 - lr: 0.000004
2021-02-20 14:48:21,579 epoch 5 - iter 3528/5049 - loss 0.18990338 - samples/sec: 9.70 - lr: 0.000004
2021-02-20 14:51:51,276 epoch 5 - iter 4032/5049 - loss 0.18768864 - samples/sec: 9.61 - lr: 0.000004
2021-02-20 14:55:18,914 epoch 5 - iter 4536/5049 - loss 0.18508693 - samples/sec: 9.71 - lr: 0.000004
2021-02-20 14:58:47,195 epoch 5 - iter 5040/5049 - loss 0.18082235 - samples/sec: 9.68 - lr: 0.000004
2021-02-20 14:58:50,697 ----------------------------------------------------------------------------------------------------
2021-02-20 14:58:50,697 EPOCH 5 done: loss 0.1808 - lr 0.0000043
2021-02-20 15:00:56,633 TEST : loss 0.11206260323524475 - score 0.9387
2021-02-20 15:00:56,668 BAD EPOCHS (no improvement): 4
2021-02-20 15:00:56,672 ----------------------------------------------------------------------------------------------------
2021-02-20 15:04:25,586 epoch 6 - iter 504/5049 - loss 0.15912418 - samples/sec: 9.65 - lr: 0.000004
2021-02-20 15:07:53,476 epoch 6 - iter 1008/5049 - loss 0.14931369 - samples/sec: 9.70 - lr: 0.000004
2021-02-20 15:11:20,667 epoch 6 - iter 1512/5049 - loss 0.15761230 - samples/sec: 9.73 - lr: 0.000004
2021-02-20 15:14:47,624 epoch 6 - iter 2016/5049 - loss 0.16075756 - samples/sec: 9.74 - lr: 0.000004
2021-02-20 15:18:15,842 epoch 6 - iter 2520/5049 - loss 0.16126459 - samples/sec: 9.68 - lr: 0.000004
2021-02-20 15:21:44,174 epoch 6 - iter 3024/5049 - loss 0.16137015 - samples/sec: 9.68 - lr: 0.000004
2021-02-20 15:25:11,675 epoch 6 - iter 3528/5049 - loss 0.16742578 - samples/sec: 9.72 - lr: 0.000004
2021-02-20 15:28:38,600 epoch 6 - iter 4032/5049 - loss 0.17104120 - samples/sec: 9.74 - lr: 0.000004
2021-02-20 15:32:04,821 epoch 6 - iter 4536/5049 - loss 0.17299492 - samples/sec: 9.78 - lr: 0.000004
2021-02-20 15:35:33,611 epoch 6 - iter 5040/5049 - loss 0.17502829 - samples/sec: 9.66 - lr: 0.000004
2021-02-20 15:35:37,145 ----------------------------------------------------------------------------------------------------
2021-02-20 15:35:37,146 EPOCH 6 done: loss 0.1752 - lr 0.0000040
2021-02-20 15:37:42,922 TEST : loss 0.11003755778074265 - score 0.9372
2021-02-20 15:37:42,957 BAD EPOCHS (no improvement): 4
2021-02-20 15:37:42,959 ----------------------------------------------------------------------------------------------------
2021-02-20 15:41:11,469 epoch 7 - iter 504/5049 - loss 0.15970022 - samples/sec: 9.67 - lr: 0.000004
2021-02-20 15:44:38,687 epoch 7 - iter 1008/5049 - loss 0.16257612 - samples/sec: 9.73 - lr: 0.000004
2021-02-20 15:48:07,772 epoch 7 - iter 1512/5049 - loss 0.15637818 - samples/sec: 9.64 - lr: 0.000004
2021-02-20 15:51:34,834 epoch 7 - iter 2016/5049 - loss 0.15584222 - samples/sec: 9.74 - lr: 0.000004
2021-02-20 15:55:02,825 epoch 7 - iter 2520/5049 - loss 0.15669211 - samples/sec: 9.69 - lr: 0.000004
2021-02-20 15:58:30,698 epoch 7 - iter 3024/5049 - loss 0.15856211 - samples/sec: 9.70 - lr: 0.000004
2021-02-20 16:01:58,633 epoch 7 - iter 3528/5049 - loss 0.15671081 - samples/sec: 9.70 - lr: 0.000004
2021-02-20 16:05:28,295 epoch 7 - iter 4032/5049 - loss 0.15648069 - samples/sec: 9.62 - lr: 0.000004
2021-02-20 16:08:56,407 epoch 7 - iter 4536/5049 - loss 0.16071403 - samples/sec: 9.69 - lr: 0.000004
2021-02-20 16:12:23,980 epoch 7 - iter 5040/5049 - loss 0.15912073 - samples/sec: 9.71 - lr: 0.000004
2021-02-20 16:12:27,258 ----------------------------------------------------------------------------------------------------
2021-02-20 16:12:27,258 EPOCH 7 done: loss 0.1593 - lr 0.0000036
2021-02-20 16:14:31,752 TEST : loss 0.1253410428762436 - score 0.9331
2021-02-20 16:14:31,787 BAD EPOCHS (no improvement): 4
2021-02-20 16:14:31,791 ----------------------------------------------------------------------------------------------------
2021-02-20 16:18:01,243 epoch 8 - iter 504/5049 - loss 0.14515327 - samples/sec: 9.63 - lr: 0.000004
2021-02-20 16:21:29,154 epoch 8 - iter 1008/5049 - loss 0.15844524 - samples/sec: 9.70 - lr: 0.000004
2021-02-20 16:24:57,953 epoch 8 - iter 1512/5049 - loss 0.15855560 - samples/sec: 9.66 - lr: 0.000004
2021-02-20 16:28:25,738 epoch 8 - iter 2016/5049 - loss 0.15470104 - samples/sec: 9.70 - lr: 0.000003
2021-02-20 16:31:54,212 epoch 8 - iter 2520/5049 - loss 0.15710933 - samples/sec: 9.67 - lr: 0.000003
2021-02-20 16:35:23,560 epoch 8 - iter 3024/5049 - loss 0.15654992 - samples/sec: 9.63 - lr: 0.000003
2021-02-20 16:38:51,123 epoch 8 - iter 3528/5049 - loss 0.15659144 - samples/sec: 9.71 - lr: 0.000003
2021-02-20 16:42:19,109 epoch 8 - iter 4032/5049 - loss 0.15848049 - samples/sec: 9.69 - lr: 0.000003
2021-02-20 16:45:47,760 epoch 8 - iter 4536/5049 - loss 0.15995362 - samples/sec: 9.66 - lr: 0.000003
2021-02-20 16:49:16,138 epoch 8 - iter 5040/5049 - loss 0.16040715 - samples/sec: 9.68 - lr: 0.000003
2021-02-20 16:49:19,652 ----------------------------------------------------------------------------------------------------
2021-02-20 16:49:19,652 EPOCH 8 done: loss 0.1605 - lr 0.0000033
2021-02-20 16:51:24,065 TEST : loss 0.12391051650047302 - score 0.9411
2021-02-20 16:51:24,100 BAD EPOCHS (no improvement): 4
2021-02-20 16:51:24,104 ----------------------------------------------------------------------------------------------------
2021-02-20 16:54:50,947 epoch 9 - iter 504/5049 - loss 0.14319218 - samples/sec: 9.75 - lr: 0.000003
2021-02-20 16:58:17,610 epoch 9 - iter 1008/5049 - loss 0.14626190 - samples/sec: 9.76 - lr: 0.000003
2021-02-20 17:01:45,887 epoch 9 - iter 1512/5049 - loss 0.14569758 - samples/sec: 9.68 - lr: 0.000003
2021-02-20 17:05:13,774 epoch 9 - iter 2016/5049 - loss 0.15481491 - samples/sec: 9.70 - lr: 0.000003
2021-02-20 17:08:40,875 epoch 9 - iter 2520/5049 - loss 0.15113900 - samples/sec: 9.74 - lr: 0.000003
2021-02-20 17:12:07,457 epoch 9 - iter 3024/5049 - loss 0.15237128 - samples/sec: 9.76 - lr: 0.000003
2021-02-20 17:15:34,821 epoch 9 - iter 3528/5049 - loss 0.15264122 - samples/sec: 9.72 - lr: 0.000003
2021-02-20 17:19:02,407 epoch 9 - iter 4032/5049 - loss 0.15553964 - samples/sec: 9.71 - lr: 0.000003
2021-02-20 17:22:30,994 epoch 9 - iter 4536/5049 - loss 0.15608309 - samples/sec: 9.67 - lr: 0.000003
2021-02-20 17:25:57,168 epoch 9 - iter 5040/5049 - loss 0.15908414 - samples/sec: 9.78 - lr: 0.000003
2021-02-20 17:26:00,585 ----------------------------------------------------------------------------------------------------
2021-02-20 17:26:00,585 EPOCH 9 done: loss 0.1590 - lr 0.0000029
2021-02-20 17:28:05,552 TEST : loss 0.1257738471031189 - score 0.9406
2021-02-20 17:28:05,583 BAD EPOCHS (no improvement): 4
2021-02-20 17:28:05,587 ----------------------------------------------------------------------------------------------------
2021-02-20 17:31:34,037 epoch 10 - iter 504/5049 - loss 0.16538340 - samples/sec: 9.67 - lr: 0.000003
2021-02-20 17:35:01,686 epoch 10 - iter 1008/5049 - loss 0.16480578 - samples/sec: 9.71 - lr: 0.000003
2021-02-20 17:38:30,133 epoch 10 - iter 1512/5049 - loss 0.15934007 - samples/sec: 9.67 - lr: 0.000003
2021-02-20 17:41:57,567 epoch 10 - iter 2016/5049 - loss 0.15438570 - samples/sec: 9.72 - lr: 0.000003
2021-02-20 17:45:26,625 epoch 10 - iter 2520/5049 - loss 0.14967620 - samples/sec: 9.64 - lr: 0.000003
2021-02-20 17:48:54,021 epoch 10 - iter 3024/5049 - loss 0.14847286 - samples/sec: 9.72 - lr: 0.000003
2021-02-20 17:52:21,779 epoch 10 - iter 3528/5049 - loss 0.15086106 - samples/sec: 9.70 - lr: 0.000003
2021-02-20 17:55:47,985 epoch 10 - iter 4032/5049 - loss 0.14921308 - samples/sec: 9.78 - lr: 0.000003
2021-02-20 17:59:16,097 epoch 10 - iter 4536/5049 - loss 0.15006289 - samples/sec: 9.69 - lr: 0.000003
2021-02-20 18:02:43,316 epoch 10 - iter 5040/5049 - loss 0.14961823 - samples/sec: 9.73 - lr: 0.000003
2021-02-20 18:02:46,866 ----------------------------------------------------------------------------------------------------
2021-02-20 18:02:46,866 EPOCH 10 done: loss 0.1496 - lr 0.0000025
2021-02-20 18:04:53,002 TEST : loss 0.1382586508989334 - score 0.9355
2021-02-20 18:04:53,034 BAD EPOCHS (no improvement): 4
2021-02-20 18:04:53,040 ----------------------------------------------------------------------------------------------------
2021-02-20 18:08:21,528 epoch 11 - iter 504/5049 - loss 0.15655231 - samples/sec: 9.67 - lr: 0.000002
2021-02-20 18:11:49,866 epoch 11 - iter 1008/5049 - loss 0.15351701 - samples/sec: 9.68 - lr: 0.000002
2021-02-20 18:15:15,360 epoch 11 - iter 1512/5049 - loss 0.16074115 - samples/sec: 9.81 - lr: 0.000002
2021-02-20 18:18:41,580 epoch 11 - iter 2016/5049 - loss 0.15942462 - samples/sec: 9.78 - lr: 0.000002
2021-02-20 18:22:09,414 epoch 11 - iter 2520/5049 - loss 0.15244022 - samples/sec: 9.70 - lr: 0.000002
2021-02-20 18:25:37,073 epoch 11 - iter 3024/5049 - loss 0.15098374 - samples/sec: 9.71 - lr: 0.000002
2021-02-20 18:29:04,540 epoch 11 - iter 3528/5049 - loss 0.14850464 - samples/sec: 9.72 - lr: 0.000002
2021-02-20 18:32:31,548 epoch 11 - iter 4032/5049 - loss 0.14682730 - samples/sec: 9.74 - lr: 0.000002
2021-02-20 18:35:57,985 epoch 11 - iter 4536/5049 - loss 0.14759185 - samples/sec: 9.77 - lr: 0.000002
2021-02-20 18:39:25,816 epoch 11 - iter 5040/5049 - loss 0.14698340 - samples/sec: 9.70 - lr: 0.000002
2021-02-20 18:39:29,260 ----------------------------------------------------------------------------------------------------
2021-02-20 18:39:29,260 EPOCH 11 done: loss 0.1468 - lr 0.0000021
2021-02-20 18:41:33,245 TEST : loss 0.13701947033405304 - score 0.9387
2021-02-20 18:41:33,275 BAD EPOCHS (no improvement): 4
2021-02-20 18:41:33,280 ----------------------------------------------------------------------------------------------------
2021-02-20 18:45:02,899 epoch 12 - iter 504/5049 - loss 0.14915151 - samples/sec: 9.62 - lr: 0.000002
2021-02-20 18:48:30,072 epoch 12 - iter 1008/5049 - loss 0.13316084 - samples/sec: 9.73 - lr: 0.000002
2021-02-20 18:51:53,567 epoch 12 - iter 1512/5049 - loss 0.13759726 - samples/sec: 9.91 - lr: 0.000002
2021-02-20 18:55:21,958 epoch 12 - iter 2016/5049 - loss 0.14573488 - samples/sec: 9.68 - lr: 0.000002
2021-02-20 18:58:50,123 epoch 12 - iter 2520/5049 - loss 0.14529516 - samples/sec: 9.69 - lr: 0.000002
2021-02-20 19:02:16,173 epoch 12 - iter 3024/5049 - loss 0.14807294 - samples/sec: 9.78 - lr: 0.000002
2021-02-20 19:05:43,697 epoch 12 - iter 3528/5049 - loss 0.15232340 - samples/sec: 9.72 - lr: 0.000002
2021-02-20 19:09:08,910 epoch 12 - iter 4032/5049 - loss 0.15379466 - samples/sec: 9.82 - lr: 0.000002
2021-02-20 19:12:36,683 epoch 12 - iter 4536/5049 - loss 0.15073956 - samples/sec: 9.70 - lr: 0.000002
2021-02-20 19:16:04,449 epoch 12 - iter 5040/5049 - loss 0.15045583 - samples/sec: 9.70 - lr: 0.000002
2021-02-20 19:16:08,082 ----------------------------------------------------------------------------------------------------
2021-02-20 19:16:08,082 EPOCH 12 done: loss 0.1504 - lr 0.0000017
2021-02-20 19:18:12,918 TEST : loss 0.15095502138137817 - score 0.9388
2021-02-20 19:18:12,953 BAD EPOCHS (no improvement): 4
2021-02-20 19:18:12,959 ----------------------------------------------------------------------------------------------------
2021-02-20 19:21:40,048 epoch 13 - iter 504/5049 - loss 0.12902688 - samples/sec: 9.74 - lr: 0.000002
2021-02-20 19:25:08,962 epoch 13 - iter 1008/5049 - loss 0.13949844 - samples/sec: 9.65 - lr: 0.000002
2021-02-20 19:28:34,327 epoch 13 - iter 1512/5049 - loss 0.14321999 - samples/sec: 9.82 - lr: 0.000002
2021-02-20 19:32:01,449 epoch 13 - iter 2016/5049 - loss 0.14469366 - samples/sec: 9.73 - lr: 0.000002
2021-02-20 19:35:30,176 epoch 13 - iter 2520/5049 - loss 0.14233070 - samples/sec: 9.66 - lr: 0.000002
2021-02-20 19:38:58,641 epoch 13 - iter 3024/5049 - loss 0.14131748 - samples/sec: 9.67 - lr: 0.000002
2021-02-20 19:42:27,447 epoch 13 - iter 3528/5049 - loss 0.14047840 - samples/sec: 9.66 - lr: 0.000001
2021-02-20 19:45:52,955 epoch 13 - iter 4032/5049 - loss 0.14627085 - samples/sec: 9.81 - lr: 0.000001
2021-02-20 19:49:18,859 epoch 13 - iter 4536/5049 - loss 0.14438495 - samples/sec: 9.79 - lr: 0.000001
2021-02-20 19:52:48,483 epoch 13 - iter 5040/5049 - loss 0.14466525 - samples/sec: 9.62 - lr: 0.000001
2021-02-20 19:52:51,977 ----------------------------------------------------------------------------------------------------
2021-02-20 19:52:51,977 EPOCH 13 done: loss 0.1446 - lr 0.0000014
2021-02-20 19:54:57,358 TEST : loss 0.14258751273155212 - score 0.9399
2021-02-20 19:54:57,388 BAD EPOCHS (no improvement): 4
2021-02-20 19:54:57,392 ----------------------------------------------------------------------------------------------------
2021-02-20 19:58:27,192 epoch 14 - iter 504/5049 - loss 0.15244849 - samples/sec: 9.61 - lr: 0.000001
2021-02-20 20:01:54,054 epoch 14 - iter 1008/5049 - loss 0.15439315 - samples/sec: 9.75 - lr: 0.000001
2021-02-20 20:05:20,574 epoch 14 - iter 1512/5049 - loss 0.15336394 - samples/sec: 9.76 - lr: 0.000001
2021-02-20 20:08:47,946 epoch 14 - iter 2016/5049 - loss 0.15177470 - samples/sec: 9.72 - lr: 0.000001
2021-02-20 20:12:16,402 epoch 14 - iter 2520/5049 - loss 0.14492786 - samples/sec: 9.67 - lr: 0.000001
2021-02-20 20:15:44,769 epoch 14 - iter 3024/5049 - loss 0.14722528 - samples/sec: 9.68 - lr: 0.000001
2021-02-20 20:19:11,969 epoch 14 - iter 3528/5049 - loss 0.14537507 - samples/sec: 9.73 - lr: 0.000001
2021-02-20 20:22:40,528 epoch 14 - iter 4032/5049 - loss 0.14247368 - samples/sec: 9.67 - lr: 0.000001
2021-02-20 20:26:06,304 epoch 14 - iter 4536/5049 - loss 0.14233014 - samples/sec: 9.80 - lr: 0.000001
2021-02-20 20:29:35,214 epoch 14 - iter 5040/5049 - loss 0.14141983 - samples/sec: 9.65 - lr: 0.000001
2021-02-20 20:29:38,745 ----------------------------------------------------------------------------------------------------
2021-02-20 20:29:38,746 EPOCH 14 done: loss 0.1415 - lr 0.0000010
2021-02-20 20:31:42,742 TEST : loss 0.16016331315040588 - score 0.9396
2021-02-20 20:31:42,776 BAD EPOCHS (no improvement): 4
2021-02-20 20:31:42,874 ----------------------------------------------------------------------------------------------------
2021-02-20 20:35:10,584 epoch 15 - iter 504/5049 - loss 0.16948716 - samples/sec: 9.71 - lr: 0.000001
2021-02-20 20:38:38,789 epoch 15 - iter 1008/5049 - loss 0.16114678 - samples/sec: 9.68 - lr: 0.000001
2021-02-20 20:42:08,608 epoch 15 - iter 1512/5049 - loss 0.15736098 - samples/sec: 9.61 - lr: 0.000001
2021-02-20 20:45:37,135 epoch 15 - iter 2016/5049 - loss 0.15347995 - samples/sec: 9.67 - lr: 0.000001
2021-02-20 20:49:06,383 epoch 15 - iter 2520/5049 - loss 0.15053243 - samples/sec: 9.64 - lr: 0.000001
2021-02-20 20:52:34,741 epoch 15 - iter 3024/5049 - loss 0.15367094 - samples/sec: 9.68 - lr: 0.000001
2021-02-20 20:56:02,251 epoch 15 - iter 3528/5049 - loss 0.15097795 - samples/sec: 9.72 - lr: 0.000001
2021-02-20 20:59:27,407 epoch 15 - iter 4032/5049 - loss 0.14762646 - samples/sec: 9.83 - lr: 0.000001
2021-02-20 21:02:55,468 epoch 15 - iter 4536/5049 - loss 0.14764760 - samples/sec: 9.69 - lr: 0.000001
2021-02-20 21:06:24,604 epoch 15 - iter 5040/5049 - loss 0.14664106 - samples/sec: 9.64 - lr: 0.000001
2021-02-20 21:06:28,160 ----------------------------------------------------------------------------------------------------
2021-02-20 21:06:28,160 EPOCH 15 done: loss 0.1468 - lr 0.0000007
2021-02-20 21:08:34,321 TEST : loss 0.15258659422397614 - score 0.94
2021-02-20 21:08:34,353 BAD EPOCHS (no improvement): 4
2021-02-20 21:08:34,355 ----------------------------------------------------------------------------------------------------
2021-02-20 21:12:02,633 epoch 16 - iter 504/5049 - loss 0.14775549 - samples/sec: 9.68 - lr: 0.000001
2021-02-20 21:15:29,663 epoch 16 - iter 1008/5049 - loss 0.15171173 - samples/sec: 9.74 - lr: 0.000001
2021-02-20 21:18:57,081 epoch 16 - iter 1512/5049 - loss 0.15467193 - samples/sec: 9.72 - lr: 0.000001
2021-02-20 21:22:22,530 epoch 16 - iter 2016/5049 - loss 0.15499647 - samples/sec: 9.81 - lr: 0.000001
2021-02-20 21:25:49,850 epoch 16 - iter 2520/5049 - loss 0.15723807 - samples/sec: 9.73 - lr: 0.000001
2021-02-20 21:29:15,774 epoch 16 - iter 3024/5049 - loss 0.15353327 - samples/sec: 9.79 - lr: 0.000001
2021-02-20 21:32:44,337 epoch 16 - iter 3528/5049 - loss 0.15530051 - samples/sec: 9.67 - lr: 0.000001
2021-02-20 21:36:13,762 epoch 16 - iter 4032/5049 - loss 0.15354102 - samples/sec: 9.63 - lr: 0.000001
2021-02-20 21:39:40,865 epoch 16 - iter 4536/5049 - loss 0.15328424 - samples/sec: 9.74 - lr: 0.000001
2021-02-20 21:43:07,866 epoch 16 - iter 5040/5049 - loss 0.15234921 - samples/sec: 9.74 - lr: 0.000000
2021-02-20 21:43:11,383 ----------------------------------------------------------------------------------------------------
2021-02-20 21:43:11,383 EPOCH 16 done: loss 0.1522 - lr 0.0000005
2021-02-20 21:45:16,386 TEST : loss 0.14317740499973297 - score 0.9434
2021-02-20 21:45:16,421 BAD EPOCHS (no improvement): 4
2021-02-20 21:45:16,435 ----------------------------------------------------------------------------------------------------
2021-02-20 21:48:44,324 epoch 17 - iter 504/5049 - loss 0.17996491 - samples/sec: 9.70 - lr: 0.000000
2021-02-20 21:52:11,485 epoch 17 - iter 1008/5049 - loss 0.15543252 - samples/sec: 9.73 - lr: 0.000000
2021-02-20 21:55:39,073 epoch 17 - iter 1512/5049 - loss 0.15122585 - samples/sec: 9.71 - lr: 0.000000
2021-02-20 21:59:05,347 epoch 17 - iter 2016/5049 - loss 0.14783825 - samples/sec: 9.77 - lr: 0.000000
2021-02-20 22:02:33,153 epoch 17 - iter 2520/5049 - loss 0.14858434 - samples/sec: 9.70 - lr: 0.000000
2021-02-20 22:06:00,594 epoch 17 - iter 3024/5049 - loss 0.14719342 - samples/sec: 9.72 - lr: 0.000000
2021-02-20 22:09:28,634 epoch 17 - iter 3528/5049 - loss 0.14664091 - samples/sec: 9.69 - lr: 0.000000
2021-02-20 22:12:55,588 epoch 17 - iter 4032/5049 - loss 0.14789258 - samples/sec: 9.74 - lr: 0.000000
2021-02-20 22:16:23,015 epoch 17 - iter 4536/5049 - loss 0.14772011 - samples/sec: 9.72 - lr: 0.000000
2021-02-20 22:19:48,689 epoch 17 - iter 5040/5049 - loss 0.14601221 - samples/sec: 9.80 - lr: 0.000000
2021-02-20 22:19:52,053 ----------------------------------------------------------------------------------------------------
2021-02-20 22:19:52,053 EPOCH 17 done: loss 0.1459 - lr 0.0000003
2021-02-20 22:21:56,595 TEST : loss 0.14864514768123627 - score 0.9435
2021-02-20 22:21:56,631 BAD EPOCHS (no improvement): 4
2021-02-20 22:21:56,633 ----------------------------------------------------------------------------------------------------
2021-02-20 22:25:22,139 epoch 18 - iter 504/5049 - loss 0.13554364 - samples/sec: 9.81 - lr: 0.000000
2021-02-20 22:28:49,994 epoch 18 - iter 1008/5049 - loss 0.14305913 - samples/sec: 9.70 - lr: 0.000000
2021-02-20 22:32:15,601 epoch 18 - iter 1512/5049 - loss 0.13788820 - samples/sec: 9.81 - lr: 0.000000
2021-02-20 22:35:43,508 epoch 18 - iter 2016/5049 - loss 0.13837578 - samples/sec: 9.70 - lr: 0.000000
2021-02-20 22:39:11,318 epoch 18 - iter 2520/5049 - loss 0.14012105 - samples/sec: 9.70 - lr: 0.000000
2021-02-20 22:42:39,481 epoch 18 - iter 3024/5049 - loss 0.13876418 - samples/sec: 9.69 - lr: 0.000000
2021-02-20 22:46:07,677 epoch 18 - iter 3528/5049 - loss 0.13934073 - samples/sec: 9.68 - lr: 0.000000
2021-02-20 22:49:36,353 epoch 18 - iter 4032/5049 - loss 0.14036170 - samples/sec: 9.66 - lr: 0.000000
2021-02-20 22:53:02,472 epoch 18 - iter 4536/5049 - loss 0.13826052 - samples/sec: 9.78 - lr: 0.000000
2021-02-20 22:56:29,133 epoch 18 - iter 5040/5049 - loss 0.13982791 - samples/sec: 9.76 - lr: 0.000000
2021-02-20 22:56:32,612 ----------------------------------------------------------------------------------------------------
2021-02-20 22:56:32,613 EPOCH 18 done: loss 0.1397 - lr 0.0000001
2021-02-20 22:58:37,314 TEST : loss 0.1518455296754837 - score 0.9437
2021-02-20 22:58:37,347 BAD EPOCHS (no improvement): 4
2021-02-20 22:58:37,349 ----------------------------------------------------------------------------------------------------
2021-02-20 23:02:03,828 epoch 19 - iter 504/5049 - loss 0.13900759 - samples/sec: 9.76 - lr: 0.000000
2021-02-20 23:05:30,296 epoch 19 - iter 1008/5049 - loss 0.14452024 - samples/sec: 9.77 - lr: 0.000000
2021-02-20 23:08:57,447 epoch 19 - iter 1512/5049 - loss 0.14064833 - samples/sec: 9.73 - lr: 0.000000
2021-02-20 23:12:23,953 epoch 19 - iter 2016/5049 - loss 0.13464772 - samples/sec: 9.76 - lr: 0.000000
2021-02-20 23:15:51,459 epoch 19 - iter 2520/5049 - loss 0.13777886 - samples/sec: 9.72 - lr: 0.000000
2021-02-20 23:19:17,489 epoch 19 - iter 3024/5049 - loss 0.13952515 - samples/sec: 9.79 - lr: 0.000000
2021-02-20 23:22:45,967 epoch 19 - iter 3528/5049 - loss 0.14131733 - samples/sec: 9.67 - lr: 0.000000
2021-02-20 23:26:13,407 epoch 19 - iter 4032/5049 - loss 0.13939496 - samples/sec: 9.72 - lr: 0.000000
2021-02-20 23:29:44,085 epoch 19 - iter 4536/5049 - loss 0.13930015 - samples/sec: 9.57 - lr: 0.000000
2021-02-20 23:33:12,190 epoch 19 - iter 5040/5049 - loss 0.14268221 - samples/sec: 9.69 - lr: 0.000000
2021-02-20 23:33:15,754 ----------------------------------------------------------------------------------------------------
2021-02-20 23:33:15,754 EPOCH 19 done: loss 0.1425 - lr 0.0000000
2021-02-20 23:35:20,374 TEST : loss 0.15170469880104065 - score 0.9433
2021-02-20 23:35:20,405 BAD EPOCHS (no improvement): 4
2021-02-20 23:35:20,408 ----------------------------------------------------------------------------------------------------
2021-02-20 23:38:48,797 epoch 20 - iter 504/5049 - loss 0.11983740 - samples/sec: 9.68 - lr: 0.000000
2021-02-20 23:42:16,401 epoch 20 - iter 1008/5049 - loss 0.12881478 - samples/sec: 9.71 - lr: 0.000000
2021-02-20 23:45:42,588 epoch 20 - iter 1512/5049 - loss 0.13435941 - samples/sec: 9.78 - lr: 0.000000
2021-02-20 23:49:09,566 epoch 20 - iter 2016/5049 - loss 0.13495553 - samples/sec: 9.74 - lr: 0.000000
2021-02-20 23:52:36,896 epoch 20 - iter 2520/5049 - loss 0.13517442 - samples/sec: 9.72 - lr: 0.000000
2021-02-20 23:56:06,234 epoch 20 - iter 3024/5049 - loss 0.13889997 - samples/sec: 9.63 - lr: 0.000000
2021-02-20 23:59:35,831 epoch 20 - iter 3528/5049 - loss 0.13720651 - samples/sec: 9.62 - lr: 0.000000
2021-02-21 00:03:03,594 epoch 20 - iter 4032/5049 - loss 0.13855230 - samples/sec: 9.70 - lr: 0.000000
2021-02-21 00:06:30,095 epoch 20 - iter 4536/5049 - loss 0.14032340 - samples/sec: 9.76 - lr: 0.000000
2021-02-21 00:09:58,484 epoch 20 - iter 5040/5049 - loss 0.13983281 - samples/sec: 9.68 - lr: 0.000000
2021-02-21 00:10:02,013 ----------------------------------------------------------------------------------------------------
2021-02-21 00:10:02,013 EPOCH 20 done: loss 0.1398 - lr 0.0000000
2021-02-21 00:12:06,767 TEST : loss 0.15191785991191864 - score 0.9436
2021-02-21 00:12:06,801 BAD EPOCHS (no improvement): 4
2021-02-21 00:12:53,129 ----------------------------------------------------------------------------------------------------
2021-02-21 00:12:53,129 Testing using best model ...
2021-02-21 00:15:03,989 0.9408 0.9465 0.9436
2021-02-21 00:15:03,989
Results:
- F1-score (micro) 0.9436
- F1-score (macro) 0.9374
By class:
LOC tp: 1445 - fp: 134 - fn: 69 - precision: 0.9151 - recall: 0.9544 - f1-score: 0.9344
MISC tp: 627 - fp: 96 - fn: 51 - precision: 0.8672 - recall: 0.9248 - f1-score: 0.8951
ORG tp: 1679 - fp: 98 - fn: 174 - precision: 0.9449 - recall: 0.9061 - f1-score: 0.9251
PER tp: 1587 - fp: 8 - fn: 8 - precision: 0.9950 - recall: 0.9950 - f1-score: 0.9950
2021-02-21 00:15:03,989 ----------------------------------------------------------------------------------------------------
2021-02-21 00:15:03,989 ----------------------------------------------------------------------------------------------------
|