File size: 47,139 Bytes
8f0563d |
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 |
2022-04-25 01:39:43,366 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,370 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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(intermediate_act_fn): GELUActivation()
)
(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)
(loss_function): CrossEntropyLoss()
)"
2022-04-25 01:39:43,372 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,372 Corpus: "Corpus: 1820 train + 50 dev + 67 test sentences"
2022-04-25 01:39:43,373 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,374 Parameters:
2022-04-25 01:39:43,374 - learning_rate: "0.000005"
2022-04-25 01:39:43,375 - mini_batch_size: "4"
2022-04-25 01:39:43,375 - patience: "3"
2022-04-25 01:39:43,376 - anneal_factor: "0.5"
2022-04-25 01:39:43,377 - max_epochs: "10"
2022-04-25 01:39:43,378 - shuffle: "True"
2022-04-25 01:39:43,378 - train_with_dev: "False"
2022-04-25 01:39:43,379 - batch_growth_annealing: "False"
2022-04-25 01:39:43,379 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,380 Model training base path: "resources/taggers/ner_xlm_finedtuned_ck1_ft"
2022-04-25 01:39:43,381 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,381 Device: cuda:0
2022-04-25 01:39:43,382 ----------------------------------------------------------------------------------------------------
2022-04-25 01:39:43,382 Embeddings storage mode: none
2022-04-25 01:39:43,383 ----------------------------------------------------------------------------------------------------
2022-04-25 01:40:01,316 epoch 1 - iter 45/455 - loss 2.02383973 - samples/sec: 10.04 - lr: 0.000000
2022-04-25 01:40:19,778 epoch 1 - iter 90/455 - loss 1.77018784 - samples/sec: 9.75 - lr: 0.000001
2022-04-25 01:40:38,303 epoch 1 - iter 135/455 - loss 1.55487540 - samples/sec: 9.72 - lr: 0.000001
2022-04-25 01:40:57,281 epoch 1 - iter 180/455 - loss 1.34519623 - samples/sec: 9.49 - lr: 0.000002
2022-04-25 01:41:18,145 epoch 1 - iter 225/455 - loss 1.15539089 - samples/sec: 8.63 - lr: 0.000002
2022-04-25 01:41:36,602 epoch 1 - iter 270/455 - loss 1.02895662 - samples/sec: 9.76 - lr: 0.000003
2022-04-25 01:41:55,400 epoch 1 - iter 315/455 - loss 0.93416075 - samples/sec: 9.58 - lr: 0.000003
2022-04-25 01:42:14,308 epoch 1 - iter 360/455 - loss 0.86211554 - samples/sec: 9.52 - lr: 0.000004
2022-04-25 01:42:33,218 epoch 1 - iter 405/455 - loss 0.80736508 - samples/sec: 9.52 - lr: 0.000004
2022-04-25 01:42:52,404 epoch 1 - iter 450/455 - loss 0.76251684 - samples/sec: 9.38 - lr: 0.000005
2022-04-25 01:42:54,450 ----------------------------------------------------------------------------------------------------
2022-04-25 01:42:54,452 EPOCH 1 done: loss 0.7578 - lr 0.000005
2022-04-25 01:43:03,256 Evaluating as a multi-label problem: False
2022-04-25 01:43:03,269 DEV : loss 0.3607260286808014 - f1-score (micro avg) 0.0
2022-04-25 01:43:03,277 BAD EPOCHS (no improvement): 4
2022-04-25 01:43:03,278 ----------------------------------------------------------------------------------------------------
2022-04-25 01:43:22,465 epoch 2 - iter 45/455 - loss 0.35669344 - samples/sec: 9.38 - lr: 0.000005
2022-04-25 01:43:41,226 epoch 2 - iter 90/455 - loss 0.33744187 - samples/sec: 9.60 - lr: 0.000005
2022-04-25 01:44:00,335 epoch 2 - iter 135/455 - loss 0.33264492 - samples/sec: 9.42 - lr: 0.000005
2022-04-25 01:44:19,259 epoch 2 - iter 180/455 - loss 0.33442139 - samples/sec: 9.51 - lr: 0.000005
2022-04-25 01:44:37,971 epoch 2 - iter 225/455 - loss 0.33062050 - samples/sec: 9.62 - lr: 0.000005
2022-04-25 01:44:56,896 epoch 2 - iter 270/455 - loss 0.32856691 - samples/sec: 9.51 - lr: 0.000005
2022-04-25 01:45:17,782 epoch 2 - iter 315/455 - loss 0.32794608 - samples/sec: 8.62 - lr: 0.000005
2022-04-25 01:45:36,760 epoch 2 - iter 360/455 - loss 0.32718419 - samples/sec: 9.49 - lr: 0.000005
2022-04-25 01:45:55,772 epoch 2 - iter 405/455 - loss 0.32696006 - samples/sec: 9.47 - lr: 0.000005
2022-04-25 01:46:15,075 epoch 2 - iter 450/455 - loss 0.32726336 - samples/sec: 9.33 - lr: 0.000004
2022-04-25 01:46:17,246 ----------------------------------------------------------------------------------------------------
2022-04-25 01:46:17,247 EPOCH 2 done: loss 0.3274 - lr 0.000004
2022-04-25 01:46:23,646 Evaluating as a multi-label problem: False
2022-04-25 01:46:23,664 DEV : loss 0.44372475147247314 - f1-score (micro avg) 0.0
2022-04-25 01:46:23,675 BAD EPOCHS (no improvement): 4
2022-04-25 01:46:23,676 ----------------------------------------------------------------------------------------------------
2022-04-25 01:46:42,384 epoch 3 - iter 45/455 - loss 0.31045361 - samples/sec: 9.63 - lr: 0.000004
2022-04-25 01:47:03,681 epoch 3 - iter 90/455 - loss 0.30688918 - samples/sec: 8.45 - lr: 0.000004
2022-04-25 01:47:22,548 epoch 3 - iter 135/455 - loss 0.30176367 - samples/sec: 9.54 - lr: 0.000004
2022-04-25 01:47:41,337 epoch 3 - iter 180/455 - loss 0.29894450 - samples/sec: 9.58 - lr: 0.000004
2022-04-25 01:48:00,045 epoch 3 - iter 225/455 - loss 0.29867330 - samples/sec: 9.62 - lr: 0.000004
2022-04-25 01:48:18,928 epoch 3 - iter 270/455 - loss 0.29997778 - samples/sec: 9.54 - lr: 0.000004
2022-04-25 01:48:37,737 epoch 3 - iter 315/455 - loss 0.30151499 - samples/sec: 9.57 - lr: 0.000004
2022-04-25 01:48:56,808 epoch 3 - iter 360/455 - loss 0.30030851 - samples/sec: 9.44 - lr: 0.000004
2022-04-25 01:49:15,866 epoch 3 - iter 405/455 - loss 0.29995926 - samples/sec: 9.45 - lr: 0.000004
2022-04-25 01:49:37,329 epoch 3 - iter 450/455 - loss 0.30000599 - samples/sec: 8.39 - lr: 0.000004
2022-04-25 01:49:39,502 ----------------------------------------------------------------------------------------------------
2022-04-25 01:49:39,503 EPOCH 3 done: loss 0.3004 - lr 0.000004
2022-04-25 01:49:46,186 Evaluating as a multi-label problem: False
2022-04-25 01:49:46,198 DEV : loss 0.4250624477863312 - f1-score (micro avg) 0.0
2022-04-25 01:49:46,207 BAD EPOCHS (no improvement): 4
2022-04-25 01:49:46,208 ----------------------------------------------------------------------------------------------------
2022-04-25 01:50:04,886 epoch 4 - iter 45/455 - loss 0.27018579 - samples/sec: 9.64 - lr: 0.000004
2022-04-25 01:50:23,747 epoch 4 - iter 90/455 - loss 0.28505798 - samples/sec: 9.55 - lr: 0.000004
2022-04-25 01:50:42,591 epoch 4 - iter 135/455 - loss 0.28106699 - samples/sec: 9.55 - lr: 0.000004
2022-04-25 01:51:01,834 epoch 4 - iter 180/455 - loss 0.28213592 - samples/sec: 9.36 - lr: 0.000004
2022-04-25 01:51:22,523 epoch 4 - iter 225/455 - loss 0.28339344 - samples/sec: 8.70 - lr: 0.000004
2022-04-25 01:51:41,984 epoch 4 - iter 270/455 - loss 0.28600075 - samples/sec: 9.25 - lr: 0.000004
2022-04-25 01:52:01,001 epoch 4 - iter 315/455 - loss 0.28507349 - samples/sec: 9.47 - lr: 0.000004
2022-04-25 01:52:19,572 epoch 4 - iter 360/455 - loss 0.28385244 - samples/sec: 9.70 - lr: 0.000003
2022-04-25 01:52:38,471 epoch 4 - iter 405/455 - loss 0.28397099 - samples/sec: 9.53 - lr: 0.000003
2022-04-25 01:52:57,371 epoch 4 - iter 450/455 - loss 0.28432390 - samples/sec: 9.53 - lr: 0.000003
2022-04-25 01:52:59,489 ----------------------------------------------------------------------------------------------------
2022-04-25 01:52:59,490 EPOCH 4 done: loss 0.2844 - lr 0.000003
2022-04-25 01:53:06,144 Evaluating as a multi-label problem: False
2022-04-25 01:53:06,157 DEV : loss 0.4436105787754059 - f1-score (micro avg) 0.0
2022-04-25 01:53:06,166 BAD EPOCHS (no improvement): 4
2022-04-25 01:53:06,168 ----------------------------------------------------------------------------------------------------
2022-04-25 01:53:27,165 epoch 5 - iter 45/455 - loss 0.26753679 - samples/sec: 8.58 - lr: 0.000003
2022-04-25 01:53:46,071 epoch 5 - iter 90/455 - loss 0.27230605 - samples/sec: 9.52 - lr: 0.000003
2022-04-25 01:54:04,859 epoch 5 - iter 135/455 - loss 0.27246786 - samples/sec: 9.58 - lr: 0.000003
2022-04-25 01:54:23,704 epoch 5 - iter 180/455 - loss 0.27259198 - samples/sec: 9.55 - lr: 0.000003
2022-04-25 01:54:42,577 epoch 5 - iter 225/455 - loss 0.27431760 - samples/sec: 9.54 - lr: 0.000003
2022-04-25 01:55:01,271 epoch 5 - iter 270/455 - loss 0.27392484 - samples/sec: 9.63 - lr: 0.000003
2022-04-25 01:55:20,066 epoch 5 - iter 315/455 - loss 0.27357625 - samples/sec: 9.58 - lr: 0.000003
2022-04-25 01:55:39,125 epoch 5 - iter 360/455 - loss 0.27202662 - samples/sec: 9.45 - lr: 0.000003
2022-04-25 01:55:57,915 epoch 5 - iter 405/455 - loss 0.27381644 - samples/sec: 9.58 - lr: 0.000003
2022-04-25 01:56:19,310 epoch 5 - iter 450/455 - loss 0.27384803 - samples/sec: 8.42 - lr: 0.000003
2022-04-25 01:56:21,405 ----------------------------------------------------------------------------------------------------
2022-04-25 01:56:21,405 EPOCH 5 done: loss 0.2735 - lr 0.000003
2022-04-25 01:56:27,996 Evaluating as a multi-label problem: False
2022-04-25 01:56:28,008 DEV : loss 0.46451953053474426 - f1-score (micro avg) 0.0
2022-04-25 01:56:28,017 BAD EPOCHS (no improvement): 4
2022-04-25 01:56:28,018 ----------------------------------------------------------------------------------------------------
2022-04-25 01:56:46,994 epoch 6 - iter 45/455 - loss 0.26238774 - samples/sec: 9.49 - lr: 0.000003
2022-04-25 01:57:06,067 epoch 6 - iter 90/455 - loss 0.26228525 - samples/sec: 9.44 - lr: 0.000003
2022-04-25 01:57:25,103 epoch 6 - iter 135/455 - loss 0.26298919 - samples/sec: 9.46 - lr: 0.000003
2022-04-25 01:57:45,904 epoch 6 - iter 180/455 - loss 0.26033810 - samples/sec: 8.66 - lr: 0.000003
2022-04-25 01:58:04,752 epoch 6 - iter 225/455 - loss 0.25980613 - samples/sec: 9.55 - lr: 0.000003
2022-04-25 01:58:23,635 epoch 6 - iter 270/455 - loss 0.25741937 - samples/sec: 9.53 - lr: 0.000002
2022-04-25 01:58:42,770 epoch 6 - iter 315/455 - loss 0.25761401 - samples/sec: 9.41 - lr: 0.000002
2022-04-25 01:59:01,669 epoch 6 - iter 360/455 - loss 0.25802951 - samples/sec: 9.53 - lr: 0.000002
2022-04-25 01:59:20,507 epoch 6 - iter 405/455 - loss 0.25786031 - samples/sec: 9.56 - lr: 0.000002
2022-04-25 01:59:39,104 epoch 6 - iter 450/455 - loss 0.25875289 - samples/sec: 9.68 - lr: 0.000002
2022-04-25 01:59:41,245 ----------------------------------------------------------------------------------------------------
2022-04-25 01:59:41,247 EPOCH 6 done: loss 0.2586 - lr 0.000002
2022-04-25 01:59:50,159 Evaluating as a multi-label problem: False
2022-04-25 01:59:50,176 DEV : loss 0.5034258961677551 - f1-score (micro avg) 0.0
2022-04-25 01:59:50,186 BAD EPOCHS (no improvement): 4
2022-04-25 01:59:50,188 ----------------------------------------------------------------------------------------------------
2022-04-25 02:00:09,428 epoch 7 - iter 45/455 - loss 0.25272579 - samples/sec: 9.36 - lr: 0.000002
2022-04-25 02:00:28,674 epoch 7 - iter 90/455 - loss 0.24877335 - samples/sec: 9.35 - lr: 0.000002
2022-04-25 02:00:47,419 epoch 7 - iter 135/455 - loss 0.25029754 - samples/sec: 9.61 - lr: 0.000002
2022-04-25 02:01:06,330 epoch 7 - iter 180/455 - loss 0.24783496 - samples/sec: 9.52 - lr: 0.000002
2022-04-25 02:01:25,050 epoch 7 - iter 225/455 - loss 0.24702442 - samples/sec: 9.62 - lr: 0.000002
2022-04-25 02:01:43,981 epoch 7 - iter 270/455 - loss 0.24574698 - samples/sec: 9.51 - lr: 0.000002
2022-04-25 02:02:02,729 epoch 7 - iter 315/455 - loss 0.24814380 - samples/sec: 9.60 - lr: 0.000002
2022-04-25 02:02:24,035 epoch 7 - iter 360/455 - loss 0.24891601 - samples/sec: 8.45 - lr: 0.000002
2022-04-25 02:02:43,529 epoch 7 - iter 405/455 - loss 0.24938588 - samples/sec: 9.24 - lr: 0.000002
2022-04-25 02:03:02,611 epoch 7 - iter 450/455 - loss 0.24975402 - samples/sec: 9.44 - lr: 0.000002
2022-04-25 02:03:04,674 ----------------------------------------------------------------------------------------------------
2022-04-25 02:03:04,675 EPOCH 7 done: loss 0.2496 - lr 0.000002
2022-04-25 02:03:11,014 Evaluating as a multi-label problem: False
2022-04-25 02:03:11,028 DEV : loss 0.5326654314994812 - f1-score (micro avg) 0.0
2022-04-25 02:03:11,037 BAD EPOCHS (no improvement): 4
2022-04-25 02:03:11,039 ----------------------------------------------------------------------------------------------------
2022-04-25 02:03:29,928 epoch 8 - iter 45/455 - loss 0.23902515 - samples/sec: 9.53 - lr: 0.000002
2022-04-25 02:03:48,547 epoch 8 - iter 90/455 - loss 0.24182299 - samples/sec: 9.67 - lr: 0.000002
2022-04-25 02:04:09,761 epoch 8 - iter 135/455 - loss 0.23794694 - samples/sec: 8.49 - lr: 0.000002
2022-04-25 02:04:28,820 epoch 8 - iter 180/455 - loss 0.23901632 - samples/sec: 9.45 - lr: 0.000001
2022-04-25 02:04:47,476 epoch 8 - iter 225/455 - loss 0.24089284 - samples/sec: 9.65 - lr: 0.000001
2022-04-25 02:05:06,576 epoch 8 - iter 270/455 - loss 0.24050137 - samples/sec: 9.43 - lr: 0.000001
2022-04-25 02:05:25,230 epoch 8 - iter 315/455 - loss 0.24061046 - samples/sec: 9.65 - lr: 0.000001
2022-04-25 02:05:43,780 epoch 8 - iter 360/455 - loss 0.24122314 - samples/sec: 9.71 - lr: 0.000001
2022-04-25 02:06:03,140 epoch 8 - iter 405/455 - loss 0.24068138 - samples/sec: 9.30 - lr: 0.000001
2022-04-25 02:06:22,289 epoch 8 - iter 450/455 - loss 0.24028428 - samples/sec: 9.40 - lr: 0.000001
2022-04-25 02:06:24,348 ----------------------------------------------------------------------------------------------------
2022-04-25 02:06:24,350 EPOCH 8 done: loss 0.2403 - lr 0.000001
2022-04-25 02:06:33,470 Evaluating as a multi-label problem: False
2022-04-25 02:06:33,485 DEV : loss 0.5238903760910034 - f1-score (micro avg) 0.0
2022-04-25 02:06:33,495 BAD EPOCHS (no improvement): 4
2022-04-25 02:06:33,497 ----------------------------------------------------------------------------------------------------
2022-04-25 02:06:52,645 epoch 9 - iter 45/455 - loss 0.22659045 - samples/sec: 9.40 - lr: 0.000001
2022-04-25 02:07:11,647 epoch 9 - iter 90/455 - loss 0.23007686 - samples/sec: 9.48 - lr: 0.000001
2022-04-25 02:07:30,432 epoch 9 - iter 135/455 - loss 0.23182102 - samples/sec: 9.59 - lr: 0.000001
2022-04-25 02:07:49,161 epoch 9 - iter 180/455 - loss 0.23484638 - samples/sec: 9.61 - lr: 0.000001
2022-04-25 02:08:08,185 epoch 9 - iter 225/455 - loss 0.23575341 - samples/sec: 9.46 - lr: 0.000001
2022-04-25 02:08:29,084 epoch 9 - iter 270/455 - loss 0.23430629 - samples/sec: 8.62 - lr: 0.000001
2022-04-25 02:08:48,058 epoch 9 - iter 315/455 - loss 0.23511980 - samples/sec: 9.49 - lr: 0.000001
2022-04-25 02:09:07,055 epoch 9 - iter 360/455 - loss 0.23591144 - samples/sec: 9.48 - lr: 0.000001
2022-04-25 02:09:25,960 epoch 9 - iter 405/455 - loss 0.23587694 - samples/sec: 9.52 - lr: 0.000001
2022-04-25 02:09:45,046 epoch 9 - iter 450/455 - loss 0.23596768 - samples/sec: 9.43 - lr: 0.000001
2022-04-25 02:09:47,133 ----------------------------------------------------------------------------------------------------
2022-04-25 02:09:47,134 EPOCH 9 done: loss 0.2358 - lr 0.000001
2022-04-25 02:09:53,727 Evaluating as a multi-label problem: False
2022-04-25 02:09:53,740 DEV : loss 0.5382402539253235 - f1-score (micro avg) 0.0
2022-04-25 02:09:53,749 BAD EPOCHS (no improvement): 4
2022-04-25 02:09:53,750 ----------------------------------------------------------------------------------------------------
2022-04-25 02:10:14,720 epoch 10 - iter 45/455 - loss 0.22667111 - samples/sec: 8.59 - lr: 0.000001
2022-04-25 02:10:34,134 epoch 10 - iter 90/455 - loss 0.22673460 - samples/sec: 9.27 - lr: 0.000000
2022-04-25 02:10:53,154 epoch 10 - iter 135/455 - loss 0.22714280 - samples/sec: 9.47 - lr: 0.000000
2022-04-25 02:11:12,101 epoch 10 - iter 180/455 - loss 0.22947185 - samples/sec: 9.50 - lr: 0.000000
2022-04-25 02:11:30,855 epoch 10 - iter 225/455 - loss 0.23026782 - samples/sec: 9.60 - lr: 0.000000
2022-04-25 02:11:49,560 epoch 10 - iter 270/455 - loss 0.23211704 - samples/sec: 9.63 - lr: 0.000000
2022-04-25 02:12:08,468 epoch 10 - iter 315/455 - loss 0.23132383 - samples/sec: 9.52 - lr: 0.000000
2022-04-25 02:12:27,224 epoch 10 - iter 360/455 - loss 0.23094819 - samples/sec: 9.60 - lr: 0.000000
2022-04-25 02:12:46,168 epoch 10 - iter 405/455 - loss 0.23152902 - samples/sec: 9.50 - lr: 0.000000
2022-04-25 02:13:07,714 epoch 10 - iter 450/455 - loss 0.23243307 - samples/sec: 8.36 - lr: 0.000000
2022-04-25 02:13:09,804 ----------------------------------------------------------------------------------------------------
2022-04-25 02:13:09,806 EPOCH 10 done: loss 0.2321 - lr 0.000000
2022-04-25 02:13:16,510 Evaluating as a multi-label problem: False
2022-04-25 02:13:16,522 DEV : loss 0.5321827530860901 - f1-score (micro avg) 0.0
2022-04-25 02:13:16,531 BAD EPOCHS (no improvement): 4
2022-04-25 02:13:19,604 ----------------------------------------------------------------------------------------------------
2022-04-25 02:13:19,607 Testing using last state of model ...
2022-04-25 02:13:30,230 Evaluating as a multi-label problem: False
2022-04-25 02:13:30,247 0.0 0.0 0.0 0.0
2022-04-25 02:13:30,248
Results:
- F-score (micro) 0.0
- F-score (macro) 0.0
- Accuracy 0.0
By class:
precision recall f1-score support
nk> 0.0000 0.0000 0.0000 0.0
ORG 0.0000 0.0000 0.0000 687.0
LOC 0.0000 0.0000 0.0000 304.0
PENT 0.0000 0.0000 0.0000 6.0
micro avg 0.0000 0.0000 0.0000 997.0
macro avg 0.0000 0.0000 0.0000 997.0
weighted avg 0.0000 0.0000 0.0000 997.0
2022-04-25 02:13:30,248 ----------------------------------------------------------------------------------------------------
|