Upload add_sub_sorl_v1_abs50_50K
Browse files
add_sub_sorl_v1_abs50_50K/metrics.json
CHANGED
|
@@ -153,1069 +153,1069 @@
|
|
| 153 |
7788
|
| 154 |
],
|
| 155 |
"loss": [
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
2.
|
| 161 |
-
2.
|
| 162 |
-
2.
|
| 163 |
-
|
| 164 |
-
1.
|
| 165 |
-
1.
|
| 166 |
-
1.
|
| 167 |
-
1.
|
| 168 |
-
1.
|
| 169 |
-
|
| 170 |
-
0.
|
| 171 |
-
|
| 172 |
-
-
|
| 173 |
-
-
|
| 174 |
-
-
|
| 175 |
-
-
|
| 176 |
-
-
|
| 177 |
-
-
|
| 178 |
-
-
|
| 179 |
-
-
|
| 180 |
-
-
|
| 181 |
-
-
|
| 182 |
-
-
|
| 183 |
-
-10.
|
| 184 |
-
-
|
| 185 |
-
-10.
|
| 186 |
-
-11.
|
| 187 |
-
-11.
|
| 188 |
-
-
|
| 189 |
-
-12.
|
| 190 |
-
-12.
|
| 191 |
-
-
|
| 192 |
-
-12.
|
| 193 |
-
-12.
|
| 194 |
-
-11.
|
| 195 |
-
-
|
| 196 |
-
-12.
|
| 197 |
-
-13.
|
| 198 |
-
-
|
| 199 |
-
-12.
|
| 200 |
-
-
|
| 201 |
-
-13.
|
| 202 |
-
-
|
| 203 |
-
-13.
|
| 204 |
-
-12.
|
| 205 |
-
-
|
| 206 |
-
-12.
|
| 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 |
-
-1.
|
| 244 |
-
-
|
| 245 |
-
-
|
| 246 |
-
-
|
| 247 |
-
-
|
| 248 |
-
-1.
|
| 249 |
-
-1.
|
| 250 |
-
-1.
|
| 251 |
-
-1.
|
| 252 |
-
-
|
| 253 |
-
-
|
| 254 |
-
-0.
|
| 255 |
-
-1.
|
| 256 |
-
-1.
|
| 257 |
-
-
|
| 258 |
-
-
|
| 259 |
-
-0.
|
| 260 |
-
-
|
| 261 |
-
-0.
|
| 262 |
-
-0.
|
| 263 |
-
-
|
| 264 |
-
-0.
|
| 265 |
-
-0.
|
| 266 |
-
-0.
|
| 267 |
-
-0.
|
| 268 |
-
-0.
|
| 269 |
-
-0.
|
| 270 |
-
-0.
|
| 271 |
-
-0.
|
| 272 |
-
-0.
|
| 273 |
-
-0.
|
| 274 |
-
-0.
|
| 275 |
-
-0.
|
| 276 |
-
-0.
|
| 277 |
-
-0.
|
| 278 |
-
-0.
|
| 279 |
-
-0.
|
| 280 |
-
-0.
|
| 281 |
-
-0.
|
| 282 |
-
-0.
|
| 283 |
-
-0.
|
| 284 |
-
-0.
|
| 285 |
-
-0.
|
| 286 |
-
-0.
|
| 287 |
-
-0.
|
| 288 |
-
-0.
|
| 289 |
-
-0.
|
| 290 |
-
-0.
|
| 291 |
-
-0.
|
| 292 |
-
-0.
|
| 293 |
-
-0.
|
| 294 |
-
-0.
|
| 295 |
-
-0.
|
| 296 |
-
-0.
|
| 297 |
-
-0.
|
| 298 |
-
|
| 299 |
-
-0.
|
| 300 |
-
-0.
|
| 301 |
-
-0.
|
| 302 |
-
-0.
|
| 303 |
-
-0.
|
| 304 |
-
-0.
|
| 305 |
-
-0.
|
| 306 |
],
|
| 307 |
"base_loss": [
|
| 308 |
-
|
| 309 |
-
|
| 310 |
-
|
| 311 |
-
|
| 312 |
-
|
| 313 |
-
1.
|
| 314 |
-
1.
|
| 315 |
-
1.
|
| 316 |
-
1.
|
| 317 |
-
1.
|
| 318 |
-
1.
|
| 319 |
-
1.
|
| 320 |
-
1.
|
| 321 |
-
1.
|
| 322 |
-
1.
|
| 323 |
-
|
| 324 |
-
1.
|
| 325 |
-
1.
|
| 326 |
-
|
| 327 |
-
1.
|
| 328 |
-
1.
|
| 329 |
-
|
| 330 |
-
1.
|
| 331 |
-
1.
|
| 332 |
-
1.
|
| 333 |
-
1.
|
| 334 |
-
1.
|
| 335 |
-
1.
|
| 336 |
-
1.
|
| 337 |
-
1.
|
| 338 |
-
1.
|
| 339 |
-
1.
|
| 340 |
-
1.
|
| 341 |
-
1.
|
| 342 |
-
1.
|
| 343 |
-
1.
|
| 344 |
-
1.
|
| 345 |
-
1.
|
| 346 |
-
1.
|
| 347 |
-
1.
|
| 348 |
-
1.
|
| 349 |
-
1.
|
| 350 |
-
1.
|
| 351 |
-
1.
|
| 352 |
-
1.
|
| 353 |
-
1.
|
| 354 |
-
1.
|
| 355 |
-
1.
|
| 356 |
-
1.
|
| 357 |
-
1.
|
| 358 |
-
1.
|
| 359 |
-
1.
|
| 360 |
-
1.
|
| 361 |
-
1.
|
| 362 |
-
1.
|
| 363 |
-
1.
|
| 364 |
-
|
| 365 |
-
|
| 366 |
-
|
| 367 |
-
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
|
| 372 |
-
|
| 373 |
-
|
| 374 |
-
|
| 375 |
-
0.
|
| 376 |
-
0.
|
| 377 |
-
0.
|
| 378 |
-
0.
|
| 379 |
-
0.
|
| 380 |
-
0.
|
| 381 |
-
0.
|
| 382 |
-
0.
|
| 383 |
-
0.
|
| 384 |
-
0.
|
| 385 |
-
0.
|
| 386 |
-
0.
|
| 387 |
-
0.
|
| 388 |
-
0.
|
| 389 |
-
0.
|
| 390 |
-
0.
|
| 391 |
-
0.
|
| 392 |
-
0.
|
| 393 |
-
0.
|
| 394 |
-
0.
|
| 395 |
-
0.
|
| 396 |
-
0.
|
| 397 |
-
0.
|
| 398 |
-
0.
|
| 399 |
-
0.
|
| 400 |
-
0.
|
| 401 |
-
0.
|
| 402 |
-
0.
|
| 403 |
-
0.
|
| 404 |
-
0.
|
| 405 |
-
0.
|
| 406 |
-
0.
|
| 407 |
-
0.
|
| 408 |
-
0.
|
| 409 |
-
0.
|
| 410 |
-
0.
|
| 411 |
-
0.
|
| 412 |
-
0.
|
| 413 |
-
0.
|
| 414 |
-
0.
|
| 415 |
-
0.
|
| 416 |
-
0.
|
| 417 |
-
0.
|
| 418 |
-
0.
|
| 419 |
-
0.
|
| 420 |
-
0.
|
| 421 |
-
0.
|
| 422 |
-
0.
|
| 423 |
-
0.
|
| 424 |
-
0.
|
| 425 |
-
0.
|
| 426 |
-
0.
|
| 427 |
-
0.
|
| 428 |
-
0.
|
| 429 |
-
0.
|
| 430 |
-
0.
|
| 431 |
-
0.
|
| 432 |
-
0.
|
| 433 |
-
0.
|
| 434 |
-
0.
|
| 435 |
-
0.
|
| 436 |
-
0.
|
| 437 |
-
0.
|
| 438 |
-
0.
|
| 439 |
-
0.
|
| 440 |
-
0.
|
| 441 |
-
0.
|
| 442 |
-
0.
|
| 443 |
-
0.
|
| 444 |
-
0.
|
| 445 |
-
0.
|
| 446 |
-
0.
|
| 447 |
-
0.
|
| 448 |
-
0.
|
| 449 |
-
0.
|
| 450 |
-
0.
|
| 451 |
-
0.
|
| 452 |
-
0.
|
| 453 |
-
0.
|
| 454 |
-
0.
|
| 455 |
-
0.
|
| 456 |
-
0.
|
| 457 |
-
0.
|
| 458 |
],
|
| 459 |
"info_loss": [
|
| 460 |
-
-0.
|
| 461 |
-
-0.
|
| 462 |
-
-0.
|
| 463 |
-
-0.
|
| 464 |
-
-0.
|
| 465 |
-
-0.
|
| 466 |
-
-0.
|
| 467 |
-
-0.
|
| 468 |
-
-0.
|
| 469 |
-
-0.
|
| 470 |
-
-0.
|
| 471 |
-
-0.
|
| 472 |
-
-0.
|
| 473 |
-
-0.
|
| 474 |
-
-0.
|
| 475 |
-
-
|
| 476 |
-
-
|
| 477 |
-
-
|
| 478 |
-
-
|
| 479 |
-
-
|
| 480 |
-
-
|
| 481 |
-
-1.
|
| 482 |
-
-1.
|
| 483 |
-
-1.
|
| 484 |
-
-1.
|
| 485 |
-
-1.
|
| 486 |
-
-1.
|
| 487 |
-
-1.
|
| 488 |
-
-1.
|
| 489 |
-
-1.
|
| 490 |
-
-1.
|
| 491 |
-
-1.
|
| 492 |
-
-1.
|
| 493 |
-
-1.
|
| 494 |
-
-1.
|
| 495 |
-
-1.
|
| 496 |
-
-1.
|
| 497 |
-
-1.
|
| 498 |
-
-1.
|
| 499 |
-
-1.
|
| 500 |
-
-1.
|
| 501 |
-
-1.
|
| 502 |
-
-1.
|
| 503 |
-
-1.
|
| 504 |
-
-1.
|
| 505 |
-
-1.
|
| 506 |
-
-1.
|
| 507 |
-
-1.
|
| 508 |
-
-1.
|
| 509 |
-
-1.
|
| 510 |
-
-1.
|
| 511 |
-
-1.
|
| 512 |
-
-1.
|
| 513 |
-
-1.
|
| 514 |
-
-1.
|
| 515 |
-
-1.
|
| 516 |
-
-
|
| 517 |
-
-
|
| 518 |
-
-
|
| 519 |
-
-
|
| 520 |
-
-
|
| 521 |
-
-
|
| 522 |
-
-
|
| 523 |
-
-
|
| 524 |
-
-
|
| 525 |
-
-
|
| 526 |
-
-
|
| 527 |
-
-0.
|
| 528 |
-
-0.
|
| 529 |
-
-0.
|
| 530 |
-
-0.
|
| 531 |
-
-0.
|
| 532 |
-
-0.
|
| 533 |
-
-0.
|
| 534 |
-
-0.
|
| 535 |
-
-0.
|
| 536 |
-
-0.
|
| 537 |
-
-0.
|
| 538 |
-
-0.
|
| 539 |
-
-0.
|
| 540 |
-
-0.
|
| 541 |
-
-0.
|
| 542 |
-
-0.
|
| 543 |
-
-0.
|
| 544 |
-
-0.
|
| 545 |
-
-0.
|
| 546 |
-
-0.
|
| 547 |
-
-0.
|
| 548 |
-
-0.
|
| 549 |
-
-0.
|
| 550 |
-
-0.
|
| 551 |
-
-0.
|
| 552 |
-
-0.
|
| 553 |
-
-0.
|
| 554 |
-
-0.
|
| 555 |
-
-0.
|
| 556 |
-
-0.
|
| 557 |
-
-0.
|
| 558 |
-
-0.
|
| 559 |
-
-0.
|
| 560 |
-
-0.
|
| 561 |
-
-0.
|
| 562 |
-
-0.
|
| 563 |
-
-0.
|
| 564 |
-
-0.
|
| 565 |
-
-0.
|
| 566 |
-
-0.
|
| 567 |
-
-0.
|
| 568 |
-
-0.
|
| 569 |
-
-0.
|
| 570 |
-
-0.
|
| 571 |
-
-0.
|
| 572 |
-
-0.
|
| 573 |
-
-0.
|
| 574 |
-
-0.
|
| 575 |
-
-0.
|
| 576 |
-
-0.
|
| 577 |
-
-0.
|
| 578 |
-
-0.
|
| 579 |
-
-0.
|
| 580 |
-
-0.
|
| 581 |
-
-0.
|
| 582 |
-
-0.
|
| 583 |
-
-0.
|
| 584 |
-
-0.
|
| 585 |
-
-0.
|
| 586 |
-
-0.
|
| 587 |
-
-0.
|
| 588 |
-
-0.
|
| 589 |
-
-0.
|
| 590 |
-
-0.
|
| 591 |
-
-0.
|
| 592 |
-
-0.
|
| 593 |
-
-0.
|
| 594 |
-
-0.
|
| 595 |
-
-0.
|
| 596 |
-
-0.
|
| 597 |
-
-0.
|
| 598 |
-
-0.
|
| 599 |
-
-0.
|
| 600 |
-
-0.
|
| 601 |
-
-0.
|
| 602 |
-
-0.
|
| 603 |
-
-0.
|
| 604 |
-
-0.
|
| 605 |
-
-0.
|
| 606 |
-
-0.
|
| 607 |
-
-0.
|
| 608 |
-
-0.
|
| 609 |
-
-0.
|
| 610 |
],
|
| 611 |
"abs_loss": [
|
| 612 |
-
3.
|
| 613 |
-
3.
|
| 614 |
-
3.
|
| 615 |
-
|
| 616 |
-
2.
|
| 617 |
-
2.
|
| 618 |
-
2.
|
| 619 |
-
2.
|
| 620 |
-
2.
|
| 621 |
-
2.
|
| 622 |
-
2.
|
| 623 |
-
2.
|
| 624 |
-
|
| 625 |
-
|
| 626 |
-
|
| 627 |
-
|
| 628 |
-
|
| 629 |
-
|
| 630 |
-
|
| 631 |
-
|
| 632 |
-
1.
|
| 633 |
-
1.
|
| 634 |
-
1.
|
| 635 |
-
1.
|
| 636 |
-
1.
|
| 637 |
-
|
| 638 |
-
1.
|
| 639 |
-
|
| 640 |
-
|
| 641 |
-
|
| 642 |
-
1.
|
| 643 |
-
|
| 644 |
-
|
| 645 |
-
1.
|
| 646 |
-
|
| 647 |
-
|
| 648 |
-
|
| 649 |
-
|
| 650 |
-
|
| 651 |
-
|
| 652 |
-
|
| 653 |
-
|
| 654 |
-
|
| 655 |
-
|
| 656 |
-
0.
|
| 657 |
-
|
| 658 |
-
|
| 659 |
-
0.
|
| 660 |
-
0.
|
| 661 |
-
0.
|
| 662 |
-
0.
|
| 663 |
-
|
| 664 |
-
0.
|
| 665 |
-
|
| 666 |
-
0.
|
| 667 |
-
0.
|
| 668 |
-
0.
|
| 669 |
-
0.
|
| 670 |
-
0.
|
| 671 |
-
0.
|
| 672 |
-
0.
|
| 673 |
-
0.
|
| 674 |
-
0.
|
| 675 |
-
0.
|
| 676 |
-
0.
|
| 677 |
-
0.
|
| 678 |
-
0.
|
| 679 |
-
0.
|
| 680 |
-
0.
|
| 681 |
-
0.
|
| 682 |
-
0.
|
| 683 |
-
0.
|
| 684 |
-
0.
|
| 685 |
-
0.
|
| 686 |
-
0.
|
| 687 |
-
0.
|
| 688 |
-
0.
|
| 689 |
-
0.
|
| 690 |
-
0.
|
| 691 |
-
0.
|
| 692 |
-
0.
|
| 693 |
-
0.
|
| 694 |
-
0.
|
| 695 |
-
0.
|
| 696 |
-
0.
|
| 697 |
-
0.
|
| 698 |
-
0.
|
| 699 |
-
0.
|
| 700 |
-
0.
|
| 701 |
-
0.
|
| 702 |
-
0.
|
| 703 |
-
0.
|
| 704 |
-
0.
|
| 705 |
-
0.
|
| 706 |
-
0.
|
| 707 |
-
0.
|
| 708 |
-
0.
|
| 709 |
-
0.
|
| 710 |
-
0.
|
| 711 |
-
0.
|
| 712 |
-
0.
|
| 713 |
-
0.
|
| 714 |
-
0.
|
| 715 |
-
0.
|
| 716 |
-
0.
|
| 717 |
-
0.
|
| 718 |
-
0.
|
| 719 |
-
0.
|
| 720 |
-
0.
|
| 721 |
-
0.
|
| 722 |
-
0.
|
| 723 |
-
0.
|
| 724 |
-
0.
|
| 725 |
-
0.
|
| 726 |
-
0.
|
| 727 |
-
0.
|
| 728 |
-
0.
|
| 729 |
-
0.
|
| 730 |
-
0.
|
| 731 |
-
0.
|
| 732 |
-
0.
|
| 733 |
-
0.
|
| 734 |
-
0.
|
| 735 |
-
0.
|
| 736 |
-
0.
|
| 737 |
-
0.
|
| 738 |
-
0.
|
| 739 |
-
0.
|
| 740 |
-
0.
|
| 741 |
-
0.
|
| 742 |
-
0.
|
| 743 |
-
0.
|
| 744 |
-
0.
|
| 745 |
-
0.
|
| 746 |
-
0.
|
| 747 |
-
0.
|
| 748 |
-
0.
|
| 749 |
-
0.
|
| 750 |
-
0.
|
| 751 |
-
0.
|
| 752 |
-
0.
|
| 753 |
-
0.
|
| 754 |
-
0.
|
| 755 |
-
0.
|
| 756 |
-
0.
|
| 757 |
-
0.
|
| 758 |
-
0.
|
| 759 |
-
0.
|
| 760 |
-
0.
|
| 761 |
-
0.
|
| 762 |
],
|
| 763 |
"zipf_loss": [
|
| 764 |
-
5.
|
| 765 |
-
|
| 766 |
-
|
| 767 |
-
|
| 768 |
-
0.
|
| 769 |
-
0.
|
| 770 |
-
0.
|
| 771 |
-
0.
|
| 772 |
-
0.
|
| 773 |
-
0.
|
| 774 |
-
0.
|
| 775 |
-
0.
|
| 776 |
-
0.
|
| 777 |
-
0.
|
| 778 |
-
0.
|
| 779 |
-
0.
|
| 780 |
-
0.
|
| 781 |
-
0.
|
| 782 |
-
0.
|
| 783 |
-
0.
|
| 784 |
-
0.
|
| 785 |
-
0.
|
| 786 |
-
0.
|
| 787 |
-
0.
|
| 788 |
-
0.
|
| 789 |
-
0.
|
| 790 |
-
0.
|
| 791 |
-
0.
|
| 792 |
-
0.
|
| 793 |
-
0.
|
| 794 |
-
0.
|
| 795 |
-
0.
|
| 796 |
-
0.
|
| 797 |
-
0.
|
| 798 |
-
0.
|
| 799 |
-
0.
|
| 800 |
-
0.
|
| 801 |
-
0.
|
| 802 |
-
0.
|
| 803 |
-
0.
|
| 804 |
-
0.
|
| 805 |
-
0.
|
| 806 |
-
0.
|
| 807 |
-
0.
|
| 808 |
-
0.
|
| 809 |
-
0.
|
| 810 |
-
0.
|
| 811 |
-
0.
|
| 812 |
-
0.
|
| 813 |
-
0.
|
| 814 |
-
0.
|
| 815 |
-
0.
|
| 816 |
-
0.
|
| 817 |
-
0.
|
| 818 |
-
0.
|
| 819 |
-
0.
|
| 820 |
-
0.
|
| 821 |
-
0.
|
| 822 |
-
0.
|
| 823 |
-
0.
|
| 824 |
-
0.
|
| 825 |
-
0.
|
| 826 |
-
0.
|
| 827 |
-
0.
|
| 828 |
-
0.
|
| 829 |
-
0.
|
| 830 |
-
0.
|
| 831 |
-
0.
|
| 832 |
-
0.
|
| 833 |
-
0.
|
| 834 |
-
0.
|
| 835 |
-
0.
|
| 836 |
-
0.
|
| 837 |
-
0.
|
| 838 |
-
0.
|
| 839 |
-
0.
|
| 840 |
-
0.
|
| 841 |
-
0.
|
| 842 |
-
0.
|
| 843 |
-
0.
|
| 844 |
-
0.
|
| 845 |
-
0.
|
| 846 |
-
0.
|
| 847 |
-
0.
|
| 848 |
-
0.
|
| 849 |
-
0.
|
| 850 |
-
0.
|
| 851 |
-
0.
|
| 852 |
-
0.
|
| 853 |
-
0.
|
| 854 |
-
0.
|
| 855 |
-
0.
|
| 856 |
-
0.
|
| 857 |
-
0.
|
| 858 |
-
0.
|
| 859 |
-
0.
|
| 860 |
-
0.
|
| 861 |
-
0.
|
| 862 |
-
0.
|
| 863 |
-
0.
|
| 864 |
-
0.
|
| 865 |
-
0.
|
| 866 |
-
0.
|
| 867 |
-
0.
|
| 868 |
-
0.
|
| 869 |
-
0.
|
| 870 |
-
0.
|
| 871 |
-
0.
|
| 872 |
-
0.
|
| 873 |
-
0.
|
| 874 |
-
0.
|
| 875 |
-
0.
|
| 876 |
-
0.
|
| 877 |
-
0.
|
| 878 |
-
0.
|
| 879 |
-
0.
|
| 880 |
-
0.
|
| 881 |
-
0.
|
| 882 |
-
0.
|
| 883 |
-
0.
|
| 884 |
-
0.
|
| 885 |
-
0.
|
| 886 |
-
0.
|
| 887 |
-
0.
|
| 888 |
-
0.
|
| 889 |
-
0.
|
| 890 |
-
0.
|
| 891 |
-
0.
|
| 892 |
-
0.
|
| 893 |
-
0.
|
| 894 |
-
0.
|
| 895 |
-
0.
|
| 896 |
-
0.
|
| 897 |
-
0.
|
| 898 |
-
0.
|
| 899 |
-
0.
|
| 900 |
-
0.
|
| 901 |
-
0.
|
| 902 |
-
0.
|
| 903 |
-
0.
|
| 904 |
-
0.
|
| 905 |
-
0.
|
| 906 |
-
0.
|
| 907 |
-
0.
|
| 908 |
-
0.
|
| 909 |
-
0.
|
| 910 |
-
0.
|
| 911 |
-
0.
|
| 912 |
-
0.
|
| 913 |
-
0.
|
| 914 |
],
|
| 915 |
"denoise_loss": [],
|
| 916 |
"ortho_loss": [
|
| 917 |
-
0.
|
| 918 |
-
0.
|
| 919 |
-
0.
|
| 920 |
-
0.
|
| 921 |
-
0.
|
| 922 |
-
0.
|
| 923 |
-
0.
|
| 924 |
-
0.
|
| 925 |
-
0.
|
| 926 |
-
0.
|
| 927 |
-
0.
|
| 928 |
-
0.
|
| 929 |
-
0.
|
| 930 |
-
0.
|
| 931 |
-
0.
|
| 932 |
-
0.
|
| 933 |
-
0.
|
| 934 |
-
0.
|
| 935 |
-
0.
|
| 936 |
-
0.
|
| 937 |
-
0.
|
| 938 |
-
0.
|
| 939 |
-
0.
|
| 940 |
-
0.
|
| 941 |
-
0.
|
| 942 |
-
0.
|
| 943 |
-
0.
|
| 944 |
-
0.
|
| 945 |
-
0.
|
| 946 |
-
0.
|
| 947 |
-
0.
|
| 948 |
-
0.
|
| 949 |
-
0.
|
| 950 |
-
0.
|
| 951 |
-
0.
|
| 952 |
-
0.
|
| 953 |
-
0.
|
| 954 |
-
0.
|
| 955 |
-
0.
|
| 956 |
-
0.
|
| 957 |
-
0.
|
| 958 |
-
0.
|
| 959 |
-
0.
|
| 960 |
-
0.
|
| 961 |
-
0.
|
| 962 |
-
0.
|
| 963 |
-
0.
|
| 964 |
-
0.
|
| 965 |
-
0.
|
| 966 |
-
0.
|
| 967 |
-
0.
|
| 968 |
-
0.
|
| 969 |
-
0.
|
| 970 |
-
0.
|
| 971 |
-
0.
|
| 972 |
-
0.
|
| 973 |
-
0.
|
| 974 |
-
0.
|
| 975 |
-
0.
|
| 976 |
-
0.
|
| 977 |
-
0.
|
| 978 |
-
0.
|
| 979 |
-
0.
|
| 980 |
-
0.
|
| 981 |
-
0.
|
| 982 |
-
0.
|
| 983 |
-
0.
|
| 984 |
-
0.
|
| 985 |
-
0.
|
| 986 |
-
0.
|
| 987 |
-
0.
|
| 988 |
-
0.
|
| 989 |
-
0.
|
| 990 |
-
0.
|
| 991 |
-
0.
|
| 992 |
-
0.
|
| 993 |
-
0.
|
| 994 |
-
0.
|
| 995 |
-
0.
|
| 996 |
-
0.
|
| 997 |
-
0.
|
| 998 |
-
0.
|
| 999 |
-
0.
|
| 1000 |
-
0.
|
| 1001 |
-
0.
|
| 1002 |
-
0.
|
| 1003 |
-
0.
|
| 1004 |
-
0.
|
| 1005 |
-
0.
|
| 1006 |
-
0.
|
| 1007 |
-
0.
|
| 1008 |
-
0.
|
| 1009 |
-
0.
|
| 1010 |
-
0.
|
| 1011 |
-
0.
|
| 1012 |
-
0.
|
| 1013 |
-
0.
|
| 1014 |
-
0.
|
| 1015 |
-
0.
|
| 1016 |
-
0.
|
| 1017 |
-
0.
|
| 1018 |
-
0.
|
| 1019 |
-
0.
|
| 1020 |
-
0.
|
| 1021 |
-
0.
|
| 1022 |
-
0.
|
| 1023 |
-
0.
|
| 1024 |
-
0.
|
| 1025 |
-
0.
|
| 1026 |
-
0.
|
| 1027 |
-
0.
|
| 1028 |
-
0.
|
| 1029 |
-
0.
|
| 1030 |
-
0.
|
| 1031 |
-
0.
|
| 1032 |
-
0.
|
| 1033 |
-
0.
|
| 1034 |
-
0.
|
| 1035 |
-
0.
|
| 1036 |
-
0.
|
| 1037 |
-
0.
|
| 1038 |
-
0.
|
| 1039 |
-
0.
|
| 1040 |
-
0.
|
| 1041 |
-
0.
|
| 1042 |
-
0.
|
| 1043 |
-
0.
|
| 1044 |
-
0.
|
| 1045 |
-
0.
|
| 1046 |
-
0.
|
| 1047 |
-
0.
|
| 1048 |
-
0.
|
| 1049 |
-
0.
|
| 1050 |
-
0.
|
| 1051 |
-
0.
|
| 1052 |
-
0.
|
| 1053 |
-
0.
|
| 1054 |
-
0.
|
| 1055 |
-
0.
|
| 1056 |
-
0.
|
| 1057 |
-
0.
|
| 1058 |
-
0.
|
| 1059 |
-
0.
|
| 1060 |
-
0.
|
| 1061 |
-
0.
|
| 1062 |
-
0.
|
| 1063 |
-
0.
|
| 1064 |
-
0.
|
| 1065 |
-
0.
|
| 1066 |
-
0.
|
| 1067 |
],
|
| 1068 |
"lr": [
|
| 1069 |
-
|
| 1070 |
-
|
| 1071 |
-
|
| 1072 |
-
|
| 1073 |
-
|
| 1074 |
-
|
| 1075 |
-
|
| 1076 |
-
|
| 1077 |
-
|
| 1078 |
-
|
| 1079 |
-
|
| 1080 |
-
|
| 1081 |
-
|
| 1082 |
-
|
| 1083 |
-
|
| 1084 |
-
|
| 1085 |
-
|
| 1086 |
-
|
| 1087 |
-
|
| 1088 |
-
|
| 1089 |
-
|
| 1090 |
-
|
| 1091 |
-
|
| 1092 |
-
|
| 1093 |
-
|
| 1094 |
-
|
| 1095 |
-
|
| 1096 |
-
|
| 1097 |
-
|
| 1098 |
-
|
| 1099 |
-
|
| 1100 |
-
|
| 1101 |
-
|
| 1102 |
-
|
| 1103 |
-
|
| 1104 |
-
|
| 1105 |
-
|
| 1106 |
-
|
| 1107 |
-
|
| 1108 |
-
|
| 1109 |
-
|
| 1110 |
-
|
| 1111 |
-
|
| 1112 |
-
|
| 1113 |
-
|
| 1114 |
-
|
| 1115 |
-
|
| 1116 |
-
|
| 1117 |
-
|
| 1118 |
-
|
| 1119 |
-
|
| 1120 |
-
|
| 1121 |
-
|
| 1122 |
-
|
| 1123 |
-
|
| 1124 |
-
|
| 1125 |
-
|
| 1126 |
-
|
| 1127 |
-
|
| 1128 |
-
|
| 1129 |
-
|
| 1130 |
-
|
| 1131 |
-
|
| 1132 |
-
|
| 1133 |
-
|
| 1134 |
-
|
| 1135 |
-
|
| 1136 |
-
|
| 1137 |
-
|
| 1138 |
-
|
| 1139 |
-
|
| 1140 |
-
|
| 1141 |
-
|
| 1142 |
-
|
| 1143 |
-
|
| 1144 |
-
|
| 1145 |
-
|
| 1146 |
-
|
| 1147 |
-
|
| 1148 |
-
|
| 1149 |
-
|
| 1150 |
-
|
| 1151 |
-
|
| 1152 |
-
|
| 1153 |
-
|
| 1154 |
-
|
| 1155 |
-
|
| 1156 |
-
|
| 1157 |
-
|
| 1158 |
-
|
| 1159 |
-
|
| 1160 |
-
|
| 1161 |
-
|
| 1162 |
-
|
| 1163 |
-
|
| 1164 |
-
|
| 1165 |
-
|
| 1166 |
-
|
| 1167 |
-
|
| 1168 |
-
|
| 1169 |
-
|
| 1170 |
-
|
| 1171 |
-
|
| 1172 |
-
|
| 1173 |
-
|
| 1174 |
-
|
| 1175 |
-
|
| 1176 |
-
|
| 1177 |
-
|
| 1178 |
-
|
| 1179 |
-
|
| 1180 |
-
|
| 1181 |
-
|
| 1182 |
-
|
| 1183 |
-
|
| 1184 |
-
|
| 1185 |
-
|
| 1186 |
-
|
| 1187 |
-
|
| 1188 |
-
|
| 1189 |
-
|
| 1190 |
-
|
| 1191 |
-
|
| 1192 |
-
|
| 1193 |
-
|
| 1194 |
-
|
| 1195 |
-
|
| 1196 |
-
|
| 1197 |
-
|
| 1198 |
-
|
| 1199 |
-
|
| 1200 |
-
|
| 1201 |
-
|
| 1202 |
-
|
| 1203 |
-
|
| 1204 |
-
|
| 1205 |
-
|
| 1206 |
-
|
| 1207 |
-
|
| 1208 |
-
|
| 1209 |
-
|
| 1210 |
-
|
| 1211 |
-
|
| 1212 |
-
|
| 1213 |
-
|
| 1214 |
-
|
| 1215 |
-
|
| 1216 |
-
|
| 1217 |
-
|
| 1218 |
-
|
| 1219 |
],
|
| 1220 |
"emb_lr": [],
|
| 1221 |
"eval_step": [
|
|
@@ -1232,18 +1232,18 @@
|
|
| 1232 |
],
|
| 1233 |
"eval_accuracy": [
|
| 1234 |
0.0,
|
| 1235 |
-
0.
|
| 1236 |
-
0.
|
| 1237 |
-
0.94,
|
| 1238 |
-
0.99,
|
| 1239 |
0.95,
|
| 1240 |
0.99,
|
|
|
|
|
|
|
|
|
|
| 1241 |
1.0,
|
| 1242 |
-
0.99,
|
| 1243 |
1.0
|
| 1244 |
]
|
| 1245 |
},
|
| 1246 |
-
"final_accuracy": 0.
|
| 1247 |
"sft_eval": {
|
| 1248 |
"config": {
|
| 1249 |
"ops": "add_sub",
|
|
@@ -1254,21 +1254,21 @@
|
|
| 1254 |
},
|
| 1255 |
"splits": {
|
| 1256 |
"add_S0": {
|
| 1257 |
-
"full_accuracy":
|
| 1258 |
"n_examples": 100,
|
| 1259 |
"per_subtask": {
|
| 1260 |
"SA": {
|
| 1261 |
-
"accuracy":
|
| 1262 |
"count": 605
|
| 1263 |
},
|
| 1264 |
"SS": {
|
| 1265 |
-
"accuracy":
|
| 1266 |
"count": 95
|
| 1267 |
}
|
| 1268 |
}
|
| 1269 |
},
|
| 1270 |
"add_S1": {
|
| 1271 |
-
"full_accuracy": 0.
|
| 1272 |
"n_examples": 100,
|
| 1273 |
"per_subtask": {
|
| 1274 |
"SA": {
|
|
@@ -1284,13 +1284,13 @@
|
|
| 1284 |
"count": 31
|
| 1285 |
},
|
| 1286 |
"UC": {
|
| 1287 |
-
"accuracy":
|
| 1288 |
"count": 296
|
| 1289 |
}
|
| 1290 |
}
|
| 1291 |
},
|
| 1292 |
"add_S2": {
|
| 1293 |
-
"full_accuracy":
|
| 1294 |
"n_examples": 100,
|
| 1295 |
"per_subtask": {
|
| 1296 |
"SA": {
|
|
@@ -1298,11 +1298,11 @@
|
|
| 1298 |
"count": 163
|
| 1299 |
},
|
| 1300 |
"SC": {
|
| 1301 |
-
"accuracy":
|
| 1302 |
"count": 130
|
| 1303 |
},
|
| 1304 |
"SS": {
|
| 1305 |
-
"accuracy":
|
| 1306 |
"count": 87
|
| 1307 |
},
|
| 1308 |
"UC": {
|
|
@@ -1316,7 +1316,7 @@
|
|
| 1316 |
}
|
| 1317 |
},
|
| 1318 |
"add_S3": {
|
| 1319 |
-
"full_accuracy": 0.
|
| 1320 |
"n_examples": 100,
|
| 1321 |
"per_subtask": {
|
| 1322 |
"SA": {
|
|
@@ -1332,7 +1332,7 @@
|
|
| 1332 |
"count": 49
|
| 1333 |
},
|
| 1334 |
"UC": {
|
| 1335 |
-
"accuracy": 0.
|
| 1336 |
"count": 186
|
| 1337 |
},
|
| 1338 |
"US": {
|
|
@@ -1342,7 +1342,7 @@
|
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
"add_S4": {
|
| 1345 |
-
"full_accuracy": 0.
|
| 1346 |
"n_examples": 100,
|
| 1347 |
"per_subtask": {
|
| 1348 |
"SA": {
|
|
@@ -1358,17 +1358,17 @@
|
|
| 1358 |
"count": 23
|
| 1359 |
},
|
| 1360 |
"UC": {
|
| 1361 |
-
"accuracy": 0.
|
| 1362 |
"count": 160
|
| 1363 |
},
|
| 1364 |
"US": {
|
| 1365 |
-
"accuracy":
|
| 1366 |
"count": 307
|
| 1367 |
}
|
| 1368 |
}
|
| 1369 |
},
|
| 1370 |
"add_S5": {
|
| 1371 |
-
"full_accuracy": 0.
|
| 1372 |
"n_examples": 100,
|
| 1373 |
"per_subtask": {
|
| 1374 |
"SA": {
|
|
@@ -1380,17 +1380,17 @@
|
|
| 1380 |
"count": 100
|
| 1381 |
},
|
| 1382 |
"UC": {
|
| 1383 |
-
"accuracy": 0.
|
| 1384 |
"count": 100
|
| 1385 |
},
|
| 1386 |
"US": {
|
| 1387 |
-
"accuracy": 0.
|
| 1388 |
"count": 400
|
| 1389 |
}
|
| 1390 |
}
|
| 1391 |
},
|
| 1392 |
"add_S6": {
|
| 1393 |
-
"full_accuracy": 0.
|
| 1394 |
"n_examples": 100,
|
| 1395 |
"per_subtask": {
|
| 1396 |
"SC": {
|
|
@@ -1398,17 +1398,17 @@
|
|
| 1398 |
"count": 100
|
| 1399 |
},
|
| 1400 |
"UC": {
|
| 1401 |
-
"accuracy": 0.
|
| 1402 |
"count": 100
|
| 1403 |
},
|
| 1404 |
"US": {
|
| 1405 |
-
"accuracy": 0.
|
| 1406 |
"count": 500
|
| 1407 |
}
|
| 1408 |
}
|
| 1409 |
},
|
| 1410 |
"add_random": {
|
| 1411 |
-
"full_accuracy": 0.
|
| 1412 |
"n_examples": 200,
|
| 1413 |
"per_subtask": {
|
| 1414 |
"SA": {
|
|
@@ -1424,7 +1424,7 @@
|
|
| 1424 |
"count": 56
|
| 1425 |
},
|
| 1426 |
"UC": {
|
| 1427 |
-
"accuracy":
|
| 1428 |
"count": 529
|
| 1429 |
},
|
| 1430 |
"US": {
|
|
@@ -1434,7 +1434,7 @@
|
|
| 1434 |
}
|
| 1435 |
},
|
| 1436 |
"add_C3": {
|
| 1437 |
-
"full_accuracy": 0.
|
| 1438 |
"n_examples": 100,
|
| 1439 |
"per_subtask": {
|
| 1440 |
"SA": {
|
|
@@ -1446,17 +1446,17 @@
|
|
| 1446 |
"count": 100
|
| 1447 |
},
|
| 1448 |
"UC": {
|
| 1449 |
-
"accuracy": 0.
|
| 1450 |
"count": 193
|
| 1451 |
},
|
| 1452 |
"US": {
|
| 1453 |
-
"accuracy":
|
| 1454 |
"count": 107
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"add_C4": {
|
| 1459 |
-
"full_accuracy": 0.
|
| 1460 |
"n_examples": 100,
|
| 1461 |
"per_subtask": {
|
| 1462 |
"SA": {
|
|
@@ -1468,17 +1468,17 @@
|
|
| 1468 |
"count": 100
|
| 1469 |
},
|
| 1470 |
"UC": {
|
| 1471 |
-
"accuracy": 0.
|
| 1472 |
"count": 256
|
| 1473 |
},
|
| 1474 |
"US": {
|
| 1475 |
-
"accuracy":
|
| 1476 |
"count": 144
|
| 1477 |
}
|
| 1478 |
}
|
| 1479 |
},
|
| 1480 |
"add_C5": {
|
| 1481 |
-
"full_accuracy": 0.
|
| 1482 |
"n_examples": 100,
|
| 1483 |
"per_subtask": {
|
| 1484 |
"SA": {
|
|
@@ -1490,17 +1490,17 @@
|
|
| 1490 |
"count": 100
|
| 1491 |
},
|
| 1492 |
"UC": {
|
| 1493 |
-
"accuracy": 0.
|
| 1494 |
"count": 306
|
| 1495 |
},
|
| 1496 |
"US": {
|
| 1497 |
-
"accuracy":
|
| 1498 |
"count": 194
|
| 1499 |
}
|
| 1500 |
}
|
| 1501 |
},
|
| 1502 |
"add_C6": {
|
| 1503 |
-
"full_accuracy": 0.
|
| 1504 |
"n_examples": 100,
|
| 1505 |
"per_subtask": {
|
| 1506 |
"SC": {
|
|
@@ -1508,21 +1508,21 @@
|
|
| 1508 |
"count": 100
|
| 1509 |
},
|
| 1510 |
"UC": {
|
| 1511 |
-
"accuracy": 0.
|
| 1512 |
"count": 366
|
| 1513 |
},
|
| 1514 |
"US": {
|
| 1515 |
-
"accuracy":
|
| 1516 |
"count": 234
|
| 1517 |
}
|
| 1518 |
}
|
| 1519 |
},
|
| 1520 |
"sub_M0": {
|
| 1521 |
-
"full_accuracy":
|
| 1522 |
"n_examples": 100,
|
| 1523 |
"per_subtask": {
|
| 1524 |
"MD": {
|
| 1525 |
-
"accuracy":
|
| 1526 |
"count": 601
|
| 1527 |
},
|
| 1528 |
"ME": {
|
|
@@ -1532,7 +1532,7 @@
|
|
| 1532 |
}
|
| 1533 |
},
|
| 1534 |
"sub_M1": {
|
| 1535 |
-
"full_accuracy": 0.
|
| 1536 |
"n_examples": 100,
|
| 1537 |
"per_subtask": {
|
| 1538 |
"MD": {
|
|
@@ -1540,7 +1540,7 @@
|
|
| 1540 |
"count": 279
|
| 1541 |
},
|
| 1542 |
"MB": {
|
| 1543 |
-
"accuracy":
|
| 1544 |
"count": 145
|
| 1545 |
},
|
| 1546 |
"ME": {
|
|
@@ -1580,7 +1580,7 @@
|
|
| 1580 |
}
|
| 1581 |
},
|
| 1582 |
"sub_M3": {
|
| 1583 |
-
"full_accuracy": 0.
|
| 1584 |
"n_examples": 100,
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
|
@@ -1596,7 +1596,7 @@
|
|
| 1596 |
"count": 56
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
-
"accuracy": 0.
|
| 1600 |
"count": 149
|
| 1601 |
},
|
| 1602 |
"UD": {
|
|
@@ -1606,7 +1606,7 @@
|
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_M4": {
|
| 1609 |
-
"full_accuracy": 0.
|
| 1610 |
"n_examples": 100,
|
| 1611 |
"per_subtask": {
|
| 1612 |
"MD": {
|
|
@@ -1618,17 +1618,17 @@
|
|
| 1618 |
"count": 100
|
| 1619 |
},
|
| 1620 |
"UB": {
|
| 1621 |
-
"accuracy": 0.
|
| 1622 |
"count": 100
|
| 1623 |
},
|
| 1624 |
"UD": {
|
| 1625 |
-
"accuracy": 0.
|
| 1626 |
"count": 300
|
| 1627 |
}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
"sub_M5": {
|
| 1631 |
-
"full_accuracy": 0.
|
| 1632 |
"n_examples": 100,
|
| 1633 |
"per_subtask": {
|
| 1634 |
"MD": {
|
|
@@ -1640,25 +1640,25 @@
|
|
| 1640 |
"count": 100
|
| 1641 |
},
|
| 1642 |
"UB": {
|
| 1643 |
-
"accuracy": 0.
|
| 1644 |
"count": 100
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
-
"accuracy": 0.
|
| 1648 |
"count": 400
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
-
"full_accuracy": 0.
|
| 1654 |
"n_examples": 200,
|
| 1655 |
"per_subtask": {
|
| 1656 |
"MD": {
|
| 1657 |
-
"accuracy":
|
| 1658 |
"count": 600
|
| 1659 |
},
|
| 1660 |
"MB": {
|
| 1661 |
-
"accuracy":
|
| 1662 |
"count": 267
|
| 1663 |
},
|
| 1664 |
"ME": {
|
|
@@ -1676,11 +1676,11 @@
|
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"sub_B3": {
|
| 1679 |
-
"full_accuracy": 0.
|
| 1680 |
"n_examples": 100,
|
| 1681 |
"per_subtask": {
|
| 1682 |
"MD": {
|
| 1683 |
-
"accuracy":
|
| 1684 |
"count": 300
|
| 1685 |
},
|
| 1686 |
"MB": {
|
|
@@ -1688,7 +1688,7 @@
|
|
| 1688 |
"count": 100
|
| 1689 |
},
|
| 1690 |
"UB": {
|
| 1691 |
-
"accuracy": 0.
|
| 1692 |
"count": 197
|
| 1693 |
},
|
| 1694 |
"UD": {
|
|
@@ -1698,11 +1698,11 @@
|
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
"sub_B4": {
|
| 1701 |
-
"full_accuracy": 0.
|
| 1702 |
"n_examples": 100,
|
| 1703 |
"per_subtask": {
|
| 1704 |
"MD": {
|
| 1705 |
-
"accuracy":
|
| 1706 |
"count": 200
|
| 1707 |
},
|
| 1708 |
"MB": {
|
|
@@ -1710,17 +1710,17 @@
|
|
| 1710 |
"count": 100
|
| 1711 |
},
|
| 1712 |
"UB": {
|
| 1713 |
-
"accuracy": 0.
|
| 1714 |
"count": 247
|
| 1715 |
},
|
| 1716 |
"UD": {
|
| 1717 |
-
"accuracy": 0.
|
| 1718 |
"count": 153
|
| 1719 |
}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
"sub_B5": {
|
| 1723 |
-
"full_accuracy": 0.
|
| 1724 |
"n_examples": 100,
|
| 1725 |
"per_subtask": {
|
| 1726 |
"MD": {
|
|
@@ -1732,18 +1732,18 @@
|
|
| 1732 |
"count": 100
|
| 1733 |
},
|
| 1734 |
"UB": {
|
| 1735 |
-
"accuracy": 0.
|
| 1736 |
"count": 298
|
| 1737 |
},
|
| 1738 |
"UD": {
|
| 1739 |
-
"accuracy": 0.
|
| 1740 |
"count": 202
|
| 1741 |
}
|
| 1742 |
}
|
| 1743 |
}
|
| 1744 |
},
|
| 1745 |
"summary": {
|
| 1746 |
-
"overall_accuracy": 0.
|
| 1747 |
"total_examples": 2400,
|
| 1748 |
"n_splits": 22
|
| 1749 |
}
|
|
@@ -1872,7 +1872,7 @@
|
|
| 1872 |
}
|
| 1873 |
},
|
| 1874 |
"add_S5": {
|
| 1875 |
-
"full_accuracy":
|
| 1876 |
"n_examples": 100,
|
| 1877 |
"per_subtask": {
|
| 1878 |
"SA": {
|
|
@@ -1884,7 +1884,7 @@
|
|
| 1884 |
"count": 100
|
| 1885 |
},
|
| 1886 |
"UC": {
|
| 1887 |
-
"accuracy":
|
| 1888 |
"count": 100
|
| 1889 |
},
|
| 1890 |
"US": {
|
|
@@ -2110,7 +2110,7 @@
|
|
| 2110 |
}
|
| 2111 |
},
|
| 2112 |
"sub_M4": {
|
| 2113 |
-
"full_accuracy":
|
| 2114 |
"n_examples": 100,
|
| 2115 |
"per_subtask": {
|
| 2116 |
"MD": {
|
|
@@ -2122,7 +2122,7 @@
|
|
| 2122 |
"count": 100
|
| 2123 |
},
|
| 2124 |
"UB": {
|
| 2125 |
-
"accuracy":
|
| 2126 |
"count": 100
|
| 2127 |
},
|
| 2128 |
"UD": {
|
|
@@ -2132,7 +2132,7 @@
|
|
| 2132 |
}
|
| 2133 |
},
|
| 2134 |
"sub_M5": {
|
| 2135 |
-
"full_accuracy":
|
| 2136 |
"n_examples": 100,
|
| 2137 |
"per_subtask": {
|
| 2138 |
"MD": {
|
|
@@ -2144,7 +2144,7 @@
|
|
| 2144 |
"count": 100
|
| 2145 |
},
|
| 2146 |
"UB": {
|
| 2147 |
-
"accuracy":
|
| 2148 |
"count": 100
|
| 2149 |
},
|
| 2150 |
"UD": {
|
|
@@ -2247,11 +2247,11 @@
|
|
| 2247 |
}
|
| 2248 |
},
|
| 2249 |
"summary": {
|
| 2250 |
-
"overall_accuracy": 0.
|
| 2251 |
"total_examples": 2400,
|
| 2252 |
"n_splits": 22
|
| 2253 |
}
|
| 2254 |
},
|
| 2255 |
-
"sorl_overall_accuracy": 0.
|
| 2256 |
-
"sft_overall_accuracy": 0.
|
| 2257 |
}
|
|
|
|
| 153 |
7788
|
| 154 |
],
|
| 155 |
"loss": [
|
| 156 |
+
12.67892837524414,
|
| 157 |
+
8.191485404968262,
|
| 158 |
+
4.352431774139404,
|
| 159 |
+
2.522091865539551,
|
| 160 |
+
2.2780187129974365,
|
| 161 |
+
2.380795955657959,
|
| 162 |
+
2.0039758682250977,
|
| 163 |
+
1.9988082647323608,
|
| 164 |
+
1.7572784423828125,
|
| 165 |
+
1.3259050846099854,
|
| 166 |
+
1.6416562795639038,
|
| 167 |
+
1.219172477722168,
|
| 168 |
+
1.2386716604232788,
|
| 169 |
+
0.8806266784667969,
|
| 170 |
+
-0.20963618159294128,
|
| 171 |
+
-9.859777450561523,
|
| 172 |
+
-9.113763809204102,
|
| 173 |
+
-9.5258150100708,
|
| 174 |
+
-10.300243377685547,
|
| 175 |
+
-9.634173393249512,
|
| 176 |
+
-10.759025573730469,
|
| 177 |
+
-10.662871360778809,
|
| 178 |
+
-11.247064590454102,
|
| 179 |
+
-10.378228187561035,
|
| 180 |
+
-11.903186798095703,
|
| 181 |
+
-11.019442558288574,
|
| 182 |
+
-11.83310317993164,
|
| 183 |
+
-10.5678129196167,
|
| 184 |
+
-11.108699798583984,
|
| 185 |
+
-10.90021800994873,
|
| 186 |
+
-11.947670936584473,
|
| 187 |
+
-11.865416526794434,
|
| 188 |
+
-10.908041954040527,
|
| 189 |
+
-12.68329906463623,
|
| 190 |
+
-12.241023063659668,
|
| 191 |
+
-11.298798561096191,
|
| 192 |
+
-12.071434020996094,
|
| 193 |
+
-12.021255493164062,
|
| 194 |
+
-11.684292793273926,
|
| 195 |
+
-12.938379287719727,
|
| 196 |
+
-12.888108253479004,
|
| 197 |
+
-13.309358596801758,
|
| 198 |
+
-12.430334091186523,
|
| 199 |
+
-12.229331970214844,
|
| 200 |
+
-12.266661643981934,
|
| 201 |
+
-13.700284004211426,
|
| 202 |
+
-14.133016586303711,
|
| 203 |
+
-13.916891098022461,
|
| 204 |
+
-12.834698677062988,
|
| 205 |
+
-12.934271812438965,
|
| 206 |
+
-12.887510299682617,
|
| 207 |
+
-11.524942398071289,
|
| 208 |
+
-12.328432083129883,
|
| 209 |
+
-10.240029335021973,
|
| 210 |
+
-10.574095726013184,
|
| 211 |
+
-9.970398902893066,
|
| 212 |
+
-8.172858238220215,
|
| 213 |
+
-6.089545726776123,
|
| 214 |
+
-5.253147602081299,
|
| 215 |
+
-5.1576738357543945,
|
| 216 |
+
-4.68107795715332,
|
| 217 |
+
-3.675668954849243,
|
| 218 |
+
-3.848482608795166,
|
| 219 |
+
-3.109677314758301,
|
| 220 |
+
-2.806471586227417,
|
| 221 |
+
-3.232398509979248,
|
| 222 |
+
-3.178936004638672,
|
| 223 |
+
-2.6559717655181885,
|
| 224 |
+
-3.095219373703003,
|
| 225 |
+
-2.731898546218872,
|
| 226 |
+
-1.9003783464431763,
|
| 227 |
+
-2.4217422008514404,
|
| 228 |
+
-1.971528172492981,
|
| 229 |
+
-2.045112371444702,
|
| 230 |
+
-2.311786413192749,
|
| 231 |
+
-1.8736507892608643,
|
| 232 |
+
-1.5437003374099731,
|
| 233 |
+
-2.029801368713379,
|
| 234 |
+
-1.5818710327148438,
|
| 235 |
+
-1.4641690254211426,
|
| 236 |
+
-1.4351928234100342,
|
| 237 |
+
-1.4494510889053345,
|
| 238 |
+
-1.6452739238739014,
|
| 239 |
+
-1.4723519086837769,
|
| 240 |
+
-1.5316369533538818,
|
| 241 |
+
-1.464418649673462,
|
| 242 |
+
-0.7855635285377502,
|
| 243 |
+
-1.0341215133666992,
|
| 244 |
+
-1.2656478881835938,
|
| 245 |
+
-1.4580594301223755,
|
| 246 |
+
-0.8084070682525635,
|
| 247 |
+
-0.99681556224823,
|
| 248 |
+
-1.617496132850647,
|
| 249 |
+
-1.0002158880233765,
|
| 250 |
+
-1.0948678255081177,
|
| 251 |
+
-1.0256470441818237,
|
| 252 |
+
-0.6143571138381958,
|
| 253 |
+
-0.9969443082809448,
|
| 254 |
+
-0.5588001608848572,
|
| 255 |
+
-1.7324066162109375,
|
| 256 |
+
-1.3033020496368408,
|
| 257 |
+
-0.5088945627212524,
|
| 258 |
+
-0.9286077618598938,
|
| 259 |
+
-0.32349681854248047,
|
| 260 |
+
-0.5033729672431946,
|
| 261 |
+
-0.47450047731399536,
|
| 262 |
+
-0.4403214752674103,
|
| 263 |
+
-0.5367404818534851,
|
| 264 |
+
-0.3997519612312317,
|
| 265 |
+
-0.7537015080451965,
|
| 266 |
+
-0.39303842186927795,
|
| 267 |
+
-0.40187329053878784,
|
| 268 |
+
-0.5620273351669312,
|
| 269 |
+
-0.4098934233188629,
|
| 270 |
+
-0.3252432942390442,
|
| 271 |
+
-0.44802966713905334,
|
| 272 |
+
-0.5599377155303955,
|
| 273 |
+
-0.33734801411628723,
|
| 274 |
+
-0.37426117062568665,
|
| 275 |
+
-0.5350562334060669,
|
| 276 |
+
-0.36393025517463684,
|
| 277 |
+
-0.3666161298751831,
|
| 278 |
+
-0.38534849882125854,
|
| 279 |
+
-0.305103063583374,
|
| 280 |
+
-0.5940544009208679,
|
| 281 |
+
-0.19180399179458618,
|
| 282 |
+
-0.4214673638343811,
|
| 283 |
+
-0.12443143129348755,
|
| 284 |
+
-0.2960967719554901,
|
| 285 |
+
-0.3407119810581207,
|
| 286 |
+
-0.24766972661018372,
|
| 287 |
+
-0.157465860247612,
|
| 288 |
+
-0.012223627418279648,
|
| 289 |
+
-0.2642403244972229,
|
| 290 |
+
-0.2627325654029846,
|
| 291 |
+
-0.10439814627170563,
|
| 292 |
+
-0.09931731224060059,
|
| 293 |
+
-0.23622454702854156,
|
| 294 |
+
-0.2288854718208313,
|
| 295 |
+
-0.07412329316139221,
|
| 296 |
+
-0.2846939265727997,
|
| 297 |
+
-0.1377047598361969,
|
| 298 |
+
0.013486653566360474,
|
| 299 |
+
-0.14698845148086548,
|
| 300 |
+
-0.11050604283809662,
|
| 301 |
+
-0.073063924908638,
|
| 302 |
+
-0.08298930525779724,
|
| 303 |
+
-0.02777700126171112,
|
| 304 |
+
-0.09498019516468048,
|
| 305 |
+
-0.011802252382040024
|
| 306 |
],
|
| 307 |
"base_loss": [
|
| 308 |
+
8.175139427185059,
|
| 309 |
+
6.075762748718262,
|
| 310 |
+
3.783433198928833,
|
| 311 |
+
2.0279407501220703,
|
| 312 |
+
1.9594535827636719,
|
| 313 |
+
1.8934462070465088,
|
| 314 |
+
1.8501828908920288,
|
| 315 |
+
1.903078317642212,
|
| 316 |
+
1.8371549844741821,
|
| 317 |
+
1.7587207555770874,
|
| 318 |
+
1.7393006086349487,
|
| 319 |
+
1.6968368291854858,
|
| 320 |
+
1.743001937866211,
|
| 321 |
+
1.7118394374847412,
|
| 322 |
+
1.7587076425552368,
|
| 323 |
+
2.1217286586761475,
|
| 324 |
+
1.7817907333374023,
|
| 325 |
+
1.7153218984603882,
|
| 326 |
+
1.7984426021575928,
|
| 327 |
+
1.675990343093872,
|
| 328 |
+
1.6814289093017578,
|
| 329 |
+
1.6889286041259766,
|
| 330 |
+
1.7132903337478638,
|
| 331 |
+
1.5579944849014282,
|
| 332 |
+
1.7281142473220825,
|
| 333 |
+
1.638057827949524,
|
| 334 |
+
1.6829408407211304,
|
| 335 |
+
1.6178058385849,
|
| 336 |
+
1.5718839168548584,
|
| 337 |
+
1.5950709581375122,
|
| 338 |
+
1.6310195922851562,
|
| 339 |
+
1.622833490371704,
|
| 340 |
+
1.525478720664978,
|
| 341 |
+
1.6557903289794922,
|
| 342 |
+
1.5996358394622803,
|
| 343 |
+
1.524327278137207,
|
| 344 |
+
1.6040916442871094,
|
| 345 |
+
1.53284752368927,
|
| 346 |
+
1.466318130493164,
|
| 347 |
+
1.5987164974212646,
|
| 348 |
+
1.6175482273101807,
|
| 349 |
+
1.628091812133789,
|
| 350 |
+
1.5662003755569458,
|
| 351 |
+
1.4833447933197021,
|
| 352 |
+
1.5381290912628174,
|
| 353 |
+
1.600269079208374,
|
| 354 |
+
1.673256754875183,
|
| 355 |
+
1.6239449977874756,
|
| 356 |
+
1.4986480474472046,
|
| 357 |
+
1.5241094827651978,
|
| 358 |
+
1.4789596796035767,
|
| 359 |
+
1.3508294820785522,
|
| 360 |
+
1.420906901359558,
|
| 361 |
+
1.217974305152893,
|
| 362 |
+
1.2073873281478882,
|
| 363 |
+
1.1402941942214966,
|
| 364 |
+
0.9508804082870483,
|
| 365 |
+
0.724185585975647,
|
| 366 |
+
0.6423880457878113,
|
| 367 |
+
0.610244870185852,
|
| 368 |
+
0.5481444597244263,
|
| 369 |
+
0.4364292323589325,
|
| 370 |
+
0.44845670461654663,
|
| 371 |
+
0.3712286353111267,
|
| 372 |
+
0.3391755521297455,
|
| 373 |
+
0.38700053095817566,
|
| 374 |
+
0.37053346633911133,
|
| 375 |
+
0.32595524191856384,
|
| 376 |
+
0.3669354021549225,
|
| 377 |
+
0.3271975517272949,
|
| 378 |
+
0.2374112904071808,
|
| 379 |
+
0.2933013439178467,
|
| 380 |
+
0.2643923759460449,
|
| 381 |
+
0.27279627323150635,
|
| 382 |
+
0.27454128861427307,
|
| 383 |
+
0.23557938635349274,
|
| 384 |
+
0.18664655089378357,
|
| 385 |
+
0.23771674931049347,
|
| 386 |
+
0.19177906215190887,
|
| 387 |
+
0.18533799052238464,
|
| 388 |
+
0.16908080875873566,
|
| 389 |
+
0.1830829232931137,
|
| 390 |
+
0.1944981813430786,
|
| 391 |
+
0.178822860121727,
|
| 392 |
+
0.17905712127685547,
|
| 393 |
+
0.1718132644891739,
|
| 394 |
+
0.09683103859424591,
|
| 395 |
+
0.12245485931634903,
|
| 396 |
+
0.14752057194709778,
|
| 397 |
+
0.17010627686977386,
|
| 398 |
+
0.09792697429656982,
|
| 399 |
+
0.12507063150405884,
|
| 400 |
+
0.2109687775373459,
|
| 401 |
+
0.11979462206363678,
|
| 402 |
+
0.12996187806129456,
|
| 403 |
+
0.1257127821445465,
|
| 404 |
+
0.10164304822683334,
|
| 405 |
+
0.11947854608297348,
|
| 406 |
+
0.06947648525238037,
|
| 407 |
+
0.20376794040203094,
|
| 408 |
+
0.15444506704807281,
|
| 409 |
+
0.06554622203111649,
|
| 410 |
+
0.11583036929368973,
|
| 411 |
+
0.04441644623875618,
|
| 412 |
+
0.08033192157745361,
|
| 413 |
+
0.05915657430887222,
|
| 414 |
+
0.057279665023088455,
|
| 415 |
+
0.0654909536242485,
|
| 416 |
+
0.05282890051603317,
|
| 417 |
+
0.09097499400377274,
|
| 418 |
+
0.050892170518636703,
|
| 419 |
+
0.054239530116319656,
|
| 420 |
+
0.06922085583209991,
|
| 421 |
+
0.0526835136115551,
|
| 422 |
+
0.04487794265151024,
|
| 423 |
+
0.05662527307868004,
|
| 424 |
+
0.06981002539396286,
|
| 425 |
+
0.04629513993859291,
|
| 426 |
+
0.048202354460954666,
|
| 427 |
+
0.06608594208955765,
|
| 428 |
+
0.04808187484741211,
|
| 429 |
+
0.05681002140045166,
|
| 430 |
+
0.04994560033082962,
|
| 431 |
+
0.04187649488449097,
|
| 432 |
+
0.07288409769535065,
|
| 433 |
+
0.027385542169213295,
|
| 434 |
+
0.052197426557540894,
|
| 435 |
+
0.029422065243124962,
|
| 436 |
+
0.041962604969739914,
|
| 437 |
+
0.04330725595355034,
|
| 438 |
+
0.03315514698624611,
|
| 439 |
+
0.023204902186989784,
|
| 440 |
+
0.02981250360608101,
|
| 441 |
+
0.03681867569684982,
|
| 442 |
+
0.03531672805547714,
|
| 443 |
+
0.020786035805940628,
|
| 444 |
+
0.018126586452126503,
|
| 445 |
+
0.03248458728194237,
|
| 446 |
+
0.03152026981115341,
|
| 447 |
+
0.013861392624676228,
|
| 448 |
+
0.03954928368330002,
|
| 449 |
+
0.022461380809545517,
|
| 450 |
+
0.00311906635761261,
|
| 451 |
+
0.020407771691679955,
|
| 452 |
+
0.017763862386345863,
|
| 453 |
+
0.013093484565615654,
|
| 454 |
+
0.014994284138083458,
|
| 455 |
+
0.009757052175700665,
|
| 456 |
+
0.02090434916317463,
|
| 457 |
+
0.007689598947763443
|
| 458 |
],
|
| 459 |
"info_loss": [
|
| 460 |
+
-0.1406078338623047,
|
| 461 |
+
-0.09821081161499023,
|
| 462 |
+
-0.07674527168273926,
|
| 463 |
+
-0.04948115348815918,
|
| 464 |
+
-0.06285381317138672,
|
| 465 |
+
-0.0457533597946167,
|
| 466 |
+
-0.07926464080810547,
|
| 467 |
+
-0.08498406410217285,
|
| 468 |
+
-0.10213601589202881,
|
| 469 |
+
-0.13344013690948486,
|
| 470 |
+
-0.08259034156799316,
|
| 471 |
+
-0.09507668018341064,
|
| 472 |
+
-0.08322620391845703,
|
| 473 |
+
-0.11139428615570068,
|
| 474 |
+
-0.2232828140258789,
|
| 475 |
+
-1.2267482280731201,
|
| 476 |
+
-1.113345742225647,
|
| 477 |
+
-1.1485538482666016,
|
| 478 |
+
-1.2319607734680176,
|
| 479 |
+
-1.1535847187042236,
|
| 480 |
+
-1.264868140220642,
|
| 481 |
+
-1.2549021244049072,
|
| 482 |
+
-1.3155022859573364,
|
| 483 |
+
-1.2114543914794922,
|
| 484 |
+
-1.3819411993026733,
|
| 485 |
+
-1.2823961973190308,
|
| 486 |
+
-1.3693645000457764,
|
| 487 |
+
-1.2348055839538574,
|
| 488 |
+
-1.2836614847183228,
|
| 489 |
+
-1.2640974521636963,
|
| 490 |
+
-1.372936487197876,
|
| 491 |
+
-1.363095760345459,
|
| 492 |
+
-1.25725519657135,
|
| 493 |
+
-1.4489041566848755,
|
| 494 |
+
-1.3969898223876953,
|
| 495 |
+
-1.2950832843780518,
|
| 496 |
+
-1.38006591796875,
|
| 497 |
+
-1.3681342601776123,
|
| 498 |
+
-1.3281453847885132,
|
| 499 |
+
-1.4650731086730957,
|
| 500 |
+
-1.4617775678634644,
|
| 501 |
+
-1.503858208656311,
|
| 502 |
+
-1.4098341464996338,
|
| 503 |
+
-1.381147861480713,
|
| 504 |
+
-1.3913785219192505,
|
| 505 |
+
-1.5395087003707886,
|
| 506 |
+
-1.589634656906128,
|
| 507 |
+
-1.5628442764282227,
|
| 508 |
+
-1.4419020414352417,
|
| 509 |
+
-1.4551329612731934,
|
| 510 |
+
-1.4442074298858643,
|
| 511 |
+
-1.2961931228637695,
|
| 512 |
+
-1.382449746131897,
|
| 513 |
+
-1.1550946235656738,
|
| 514 |
+
-1.1871305704116821,
|
| 515 |
+
-1.11911940574646,
|
| 516 |
+
-0.9211147427558899,
|
| 517 |
+
-0.6894612908363342,
|
| 518 |
+
-0.5988896489143372,
|
| 519 |
+
-0.5864489078521729,
|
| 520 |
+
-0.5306638479232788,
|
| 521 |
+
-0.41922348737716675,
|
| 522 |
+
-0.43873268365859985,
|
| 523 |
+
-0.35574495792388916,
|
| 524 |
+
-0.3218325078487396,
|
| 525 |
+
-0.3698967695236206,
|
| 526 |
+
-0.3617374002933502,
|
| 527 |
+
-0.30592790246009827,
|
| 528 |
+
-0.35313671827316284,
|
| 529 |
+
-0.3120341897010803,
|
| 530 |
+
-0.22083844244480133,
|
| 531 |
+
-0.2789214253425598,
|
| 532 |
+
-0.23039886355400085,
|
| 533 |
+
-0.2383309006690979,
|
| 534 |
+
-0.2649160921573639,
|
| 535 |
+
-0.21758969128131866,
|
| 536 |
+
-0.17926090955734253,
|
| 537 |
+
-0.23309476673603058,
|
| 538 |
+
-0.1844792366027832,
|
| 539 |
+
-0.1725887954235077,
|
| 540 |
+
-0.1671394556760788,
|
| 541 |
+
-0.1700686663389206,
|
| 542 |
+
-0.1907423436641693,
|
| 543 |
+
-0.17181335389614105,
|
| 544 |
+
-0.17715275287628174,
|
| 545 |
+
-0.16998039186000824,
|
| 546 |
+
-0.09564366936683655,
|
| 547 |
+
-0.12137357145547867,
|
| 548 |
+
-0.14595358073711395,
|
| 549 |
+
-0.169093519449234,
|
| 550 |
+
-0.0965929850935936,
|
| 551 |
+
-0.11820736527442932,
|
| 552 |
+
-0.18986539542675018,
|
| 553 |
+
-0.11808352172374725,
|
| 554 |
+
-0.1273777186870575,
|
| 555 |
+
-0.12252979725599289,
|
| 556 |
+
-0.07934901863336563,
|
| 557 |
+
-0.11888580024242401,
|
| 558 |
+
-0.06833749264478683,
|
| 559 |
+
-0.19960084557533264,
|
| 560 |
+
-0.15267471969127655,
|
| 561 |
+
-0.06464723497629166,
|
| 562 |
+
-0.11036423593759537,
|
| 563 |
+
-0.041933849453926086,
|
| 564 |
+
-0.06360318511724472,
|
| 565 |
+
-0.0584120973944664,
|
| 566 |
+
-0.056712184101343155,
|
| 567 |
+
-0.06440874189138412,
|
| 568 |
+
-0.052568674087524414,
|
| 569 |
+
-0.08996984362602234,
|
| 570 |
+
-0.048663992434740067,
|
| 571 |
+
-0.05403685197234154,
|
| 572 |
+
-0.06870617717504501,
|
| 573 |
+
-0.05249454826116562,
|
| 574 |
+
-0.04473206400871277,
|
| 575 |
+
-0.056433867663145065,
|
| 576 |
+
-0.0695694237947464,
|
| 577 |
+
-0.045398302376270294,
|
| 578 |
+
-0.04746449738740921,
|
| 579 |
+
-0.06530661135911942,
|
| 580 |
+
-0.047672662883996964,
|
| 581 |
+
-0.04788694903254509,
|
| 582 |
+
-0.04977806285023689,
|
| 583 |
+
-0.040316712111234665,
|
| 584 |
+
-0.07268588244915009,
|
| 585 |
+
-0.027013925835490227,
|
| 586 |
+
-0.05200999230146408,
|
| 587 |
+
-0.021213047206401825,
|
| 588 |
+
-0.041462358087301254,
|
| 589 |
+
-0.04304017499089241,
|
| 590 |
+
-0.032975614070892334,
|
| 591 |
+
-0.02306353859603405,
|
| 592 |
+
-0.011100322008132935,
|
| 593 |
+
-0.03651665151119232,
|
| 594 |
+
-0.03525616601109505,
|
| 595 |
+
-0.0206893440335989,
|
| 596 |
+
-0.017962217330932617,
|
| 597 |
+
-0.0323893241584301,
|
| 598 |
+
-0.03146279975771904,
|
| 599 |
+
-0.013802221976220608,
|
| 600 |
+
-0.03790447488427162,
|
| 601 |
+
-0.02238229103386402,
|
| 602 |
+
-0.003057879628613591,
|
| 603 |
+
-0.0203342754393816,
|
| 604 |
+
-0.017628828063607216,
|
| 605 |
+
-0.013046156615018845,
|
| 606 |
+
-0.014944502152502537,
|
| 607 |
+
-0.009699908085167408,
|
| 608 |
+
-0.016671348363161087,
|
| 609 |
+
-0.007629582192748785
|
| 610 |
],
|
| 611 |
"abs_loss": [
|
| 612 |
+
3.8940813541412354,
|
| 613 |
+
3.7336649894714355,
|
| 614 |
+
3.1092171669006348,
|
| 615 |
+
2.842017889022827,
|
| 616 |
+
2.721194267272949,
|
| 617 |
+
2.7295258045196533,
|
| 618 |
+
2.8091413974761963,
|
| 619 |
+
2.8224925994873047,
|
| 620 |
+
2.7906839847564697,
|
| 621 |
+
2.74942684173584,
|
| 622 |
+
2.5859627723693848,
|
| 623 |
+
2.0573041439056396,
|
| 624 |
+
1.4365499019622803,
|
| 625 |
+
1.277630090713501,
|
| 626 |
+
1.2900981903076172,
|
| 627 |
+
1.6139904260635376,
|
| 628 |
+
1.0711069107055664,
|
| 629 |
+
1.2892038822174072,
|
| 630 |
+
1.235854148864746,
|
| 631 |
+
1.1754491329193115,
|
| 632 |
+
1.2126238346099854,
|
| 633 |
+
1.0512967109680176,
|
| 634 |
+
1.0807137489318848,
|
| 635 |
+
1.055290937423706,
|
| 636 |
+
1.098618745803833,
|
| 637 |
+
0.9691460132598877,
|
| 638 |
+
1.195742130279541,
|
| 639 |
+
0.9021354913711548,
|
| 640 |
+
0.815509557723999,
|
| 641 |
+
0.901701807975769,
|
| 642 |
+
1.0237162113189697,
|
| 643 |
+
0.9478892683982849,
|
| 644 |
+
0.9123111963272095,
|
| 645 |
+
1.037805438041687,
|
| 646 |
+
0.8250418901443481,
|
| 647 |
+
0.7932180166244507,
|
| 648 |
+
0.87883460521698,
|
| 649 |
+
0.7833858132362366,
|
| 650 |
+
0.7834078073501587,
|
| 651 |
+
0.7488945722579956,
|
| 652 |
+
0.6982825398445129,
|
| 653 |
+
0.6155017018318176,
|
| 654 |
+
0.7811354994773865,
|
| 655 |
+
0.7143194675445557,
|
| 656 |
+
0.5621134042739868,
|
| 657 |
+
0.5227675437927246,
|
| 658 |
+
0.5837538242340088,
|
| 659 |
+
0.5188642740249634,
|
| 660 |
+
0.545297384262085,
|
| 661 |
+
0.4773949682712555,
|
| 662 |
+
0.49671515822410583,
|
| 663 |
+
0.4398581385612488,
|
| 664 |
+
0.48808902502059937,
|
| 665 |
+
0.517977774143219,
|
| 666 |
+
0.5309848189353943,
|
| 667 |
+
0.45294398069381714,
|
| 668 |
+
0.4019848704338074,
|
| 669 |
+
0.519283652305603,
|
| 670 |
+
0.3544163703918457,
|
| 671 |
+
0.33730629086494446,
|
| 672 |
+
0.2914344072341919,
|
| 673 |
+
0.426680326461792,
|
| 674 |
+
0.3723861575126648,
|
| 675 |
+
0.37098586559295654,
|
| 676 |
+
0.3665745258331299,
|
| 677 |
+
0.3464042544364929,
|
| 678 |
+
0.3030303120613098,
|
| 679 |
+
0.31845754384994507,
|
| 680 |
+
0.2541038393974304,
|
| 681 |
+
0.2829054594039917,
|
| 682 |
+
0.34755414724349976,
|
| 683 |
+
0.41225311160087585,
|
| 684 |
+
0.3649803400039673,
|
| 685 |
+
0.2859313189983368,
|
| 686 |
+
0.25069183111190796,
|
| 687 |
+
0.2457413375377655,
|
| 688 |
+
0.3258231282234192,
|
| 689 |
+
0.26403719186782837,
|
| 690 |
+
0.23960518836975098,
|
| 691 |
+
0.25264933705329895,
|
| 692 |
+
0.3009341359138489,
|
| 693 |
+
0.23419302701950073,
|
| 694 |
+
0.2310016006231308,
|
| 695 |
+
0.25005489587783813,
|
| 696 |
+
0.2157013714313507,
|
| 697 |
+
0.24478872120380402,
|
| 698 |
+
0.18399158120155334,
|
| 699 |
+
0.25713664293289185,
|
| 700 |
+
0.20990487933158875,
|
| 701 |
+
0.1861613243818283,
|
| 702 |
+
0.18391621112823486,
|
| 703 |
+
0.21477115154266357,
|
| 704 |
+
0.1756722778081894,
|
| 705 |
+
0.21409966051578522,
|
| 706 |
+
0.23994490504264832,
|
| 707 |
+
0.22935672104358673,
|
| 708 |
+
0.2253214418888092,
|
| 709 |
+
0.1604989767074585,
|
| 710 |
+
0.19127511978149414,
|
| 711 |
+
0.22364018857479095,
|
| 712 |
+
0.19713473320007324,
|
| 713 |
+
0.16757990419864655,
|
| 714 |
+
0.1519395262002945,
|
| 715 |
+
0.1956753432750702,
|
| 716 |
+
0.1744147539138794,
|
| 717 |
+
0.2321409285068512,
|
| 718 |
+
0.13768763840198517,
|
| 719 |
+
0.23297205567359924,
|
| 720 |
+
0.14285501837730408,
|
| 721 |
+
0.1547240912914276,
|
| 722 |
+
0.18175172805786133,
|
| 723 |
+
0.16273121535778046,
|
| 724 |
+
0.1803196370601654,
|
| 725 |
+
0.18007409572601318,
|
| 726 |
+
0.15982943773269653,
|
| 727 |
+
0.23455564677715302,
|
| 728 |
+
0.17059823870658875,
|
| 729 |
+
0.13607117533683777,
|
| 730 |
+
0.1691424548625946,
|
| 731 |
+
0.1645020842552185,
|
| 732 |
+
0.1407187283039093,
|
| 733 |
+
0.15654246509075165,
|
| 734 |
+
0.16038723289966583,
|
| 735 |
+
0.16506516933441162,
|
| 736 |
+
0.131463885307312,
|
| 737 |
+
0.1274046152830124,
|
| 738 |
+
0.1848076581954956,
|
| 739 |
+
0.1635836660861969,
|
| 740 |
+
0.1434631198644638,
|
| 741 |
+
0.16331462562084198,
|
| 742 |
+
0.12345422804355621,
|
| 743 |
+
0.1436048448085785,
|
| 744 |
+
0.19684480130672455,
|
| 745 |
+
0.16364730894565582,
|
| 746 |
+
0.16607016324996948,
|
| 747 |
+
0.20140975713729858,
|
| 748 |
+
0.08408752083778381,
|
| 749 |
+
0.1640971601009369,
|
| 750 |
+
0.15419058501720428,
|
| 751 |
+
0.12306832522153854,
|
| 752 |
+
0.0888054147362709,
|
| 753 |
+
0.10666976869106293,
|
| 754 |
+
0.19911688566207886,
|
| 755 |
+
0.143904447555542,
|
| 756 |
+
0.12154616415500641,
|
| 757 |
+
0.11547724157571793,
|
| 758 |
+
0.13714294135570526,
|
| 759 |
+
0.12812788784503937,
|
| 760 |
+
0.16408056020736694,
|
| 761 |
+
0.1393263339996338
|
| 762 |
],
|
| 763 |
"zipf_loss": [
|
| 764 |
+
5.520458698272705,
|
| 765 |
+
2.724464178085327,
|
| 766 |
+
1.0255296230316162,
|
| 767 |
+
0.7047606706619263,
|
| 768 |
+
0.6749839186668396,
|
| 769 |
+
0.6719306707382202,
|
| 770 |
+
0.6655250787734985,
|
| 771 |
+
0.6633213758468628,
|
| 772 |
+
0.6624152064323425,
|
| 773 |
+
0.6266430616378784,
|
| 774 |
+
0.4696628153324127,
|
| 775 |
+
0.2673720121383667,
|
| 776 |
+
0.18427684903144836,
|
| 777 |
+
0.1549670696258545,
|
| 778 |
+
0.13547447323799133,
|
| 779 |
+
0.12457747757434845,
|
| 780 |
+
0.13079211115837097,
|
| 781 |
+
0.11548108607530594,
|
| 782 |
+
0.09733611345291138,
|
| 783 |
+
0.1081380546092987,
|
| 784 |
+
0.08696448802947998,
|
| 785 |
+
0.0920911505818367,
|
| 786 |
+
0.0865960344672203,
|
| 787 |
+
0.0727919340133667,
|
| 788 |
+
0.07824882119894028,
|
| 789 |
+
0.06954751908779144,
|
| 790 |
+
0.05802743881940842,
|
| 791 |
+
0.07222349941730499,
|
| 792 |
+
0.07448042929172516,
|
| 793 |
+
0.05551524832844734,
|
| 794 |
+
0.0483030267059803,
|
| 795 |
+
0.04791921377182007,
|
| 796 |
+
0.04779967665672302,
|
| 797 |
+
0.04617128521203995,
|
| 798 |
+
0.04673522710800171,
|
| 799 |
+
0.04838429391384125,
|
| 800 |
+
0.037250399589538574,
|
| 801 |
+
0.04890108108520508,
|
| 802 |
+
0.05250226706266403,
|
| 803 |
+
0.03874621540307999,
|
| 804 |
+
0.0422917976975441,
|
| 805 |
+
0.039581410586833954,
|
| 806 |
+
0.023693282157182693,
|
| 807 |
+
0.027369800955057144,
|
| 808 |
+
0.05278322100639343,
|
| 809 |
+
0.04225717484951019,
|
| 810 |
+
0.03169860690832138,
|
| 811 |
+
0.03571942821145058,
|
| 812 |
+
0.031144462525844574,
|
| 813 |
+
0.04520869255065918,
|
| 814 |
+
0.025932321324944496,
|
| 815 |
+
0.04217460751533508,
|
| 816 |
+
0.026349296793341637,
|
| 817 |
+
0.041144728660583496,
|
| 818 |
+
0.03672437369823456,
|
| 819 |
+
0.03520722687244415,
|
| 820 |
+
0.04721111059188843,
|
| 821 |
+
0.028953010216355324,
|
| 822 |
+
0.057918816804885864,
|
| 823 |
+
0.06283990293741226,
|
| 824 |
+
0.04827304184436798,
|
| 825 |
+
0.03746875375509262,
|
| 826 |
+
0.0531487762928009,
|
| 827 |
+
0.03944481164216995,
|
| 828 |
+
0.036020535975694656,
|
| 829 |
+
0.04492820054292679,
|
| 830 |
+
0.0376015342772007,
|
| 831 |
+
0.04550633579492569,
|
| 832 |
+
0.04380195587873459,
|
| 833 |
+
0.03295513242483139,
|
| 834 |
+
0.035839494317770004,
|
| 835 |
+
0.032945387065410614,
|
| 836 |
+
0.03157005086541176,
|
| 837 |
+
0.03680720180273056,
|
| 838 |
+
0.03776375204324722,
|
| 839 |
+
0.04209259897470474,
|
| 840 |
+
0.02967984601855278,
|
| 841 |
+
0.03702588379383087,
|
| 842 |
+
0.047181881964206696,
|
| 843 |
+
0.0511159673333168,
|
| 844 |
+
0.03702745959162712,
|
| 845 |
+
0.04473336040973663,
|
| 846 |
+
0.04455123096704483,
|
| 847 |
+
0.04195331037044525,
|
| 848 |
+
0.039263349026441574,
|
| 849 |
+
0.03909315913915634,
|
| 850 |
+
0.05564294755458832,
|
| 851 |
+
0.03144568204879761,
|
| 852 |
+
0.025376860052347183,
|
| 853 |
+
0.04415329545736313,
|
| 854 |
+
0.04120419919490814,
|
| 855 |
+
0.03871038556098938,
|
| 856 |
+
0.05262188985943794,
|
| 857 |
+
0.03941471129655838,
|
| 858 |
+
0.024953138083219528,
|
| 859 |
+
0.05100245401263237,
|
| 860 |
+
0.054957855492830276,
|
| 861 |
+
0.056385260075330734,
|
| 862 |
+
0.035970814526081085,
|
| 863 |
+
0.037469856441020966,
|
| 864 |
+
0.049286577850580215,
|
| 865 |
+
0.05527356639504433,
|
| 866 |
+
0.04401029646396637,
|
| 867 |
+
0.031857676804065704,
|
| 868 |
+
0.034885551780462265,
|
| 869 |
+
0.02724980190396309,
|
| 870 |
+
0.0557519905269146,
|
| 871 |
+
0.01855882629752159,
|
| 872 |
+
0.05882035940885544,
|
| 873 |
+
0.03954955190420151,
|
| 874 |
+
0.02453412488102913,
|
| 875 |
+
0.06798255443572998,
|
| 876 |
+
0.03778166323900223,
|
| 877 |
+
0.0443611666560173,
|
| 878 |
+
0.06121644005179405,
|
| 879 |
+
0.03622821718454361,
|
| 880 |
+
0.04888666421175003,
|
| 881 |
+
0.056732747703790665,
|
| 882 |
+
0.0352671816945076,
|
| 883 |
+
0.03547373414039612,
|
| 884 |
+
0.05064262077212334,
|
| 885 |
+
0.0397891066968441,
|
| 886 |
+
0.04644780606031418,
|
| 887 |
+
0.039681047201156616,
|
| 888 |
+
0.04677397012710571,
|
| 889 |
+
0.03820924460887909,
|
| 890 |
+
0.027954362332820892,
|
| 891 |
+
0.041918620467185974,
|
| 892 |
+
0.062217921018600464,
|
| 893 |
+
0.030051065608859062,
|
| 894 |
+
0.03658584505319595,
|
| 895 |
+
0.03560413420200348,
|
| 896 |
+
0.04928261414170265,
|
| 897 |
+
0.047742798924446106,
|
| 898 |
+
0.037905339151620865,
|
| 899 |
+
0.06156828626990318,
|
| 900 |
+
0.053769513964653015,
|
| 901 |
+
0.03877438232302666,
|
| 902 |
+
0.038803182542324066,
|
| 903 |
+
0.03773069381713867,
|
| 904 |
+
0.0459209568798542,
|
| 905 |
+
0.05298977717757225,
|
| 906 |
+
0.021034693345427513,
|
| 907 |
+
0.02155609056353569,
|
| 908 |
+
0.03586374223232269,
|
| 909 |
+
0.032756440341472626,
|
| 910 |
+
0.03774715214967728,
|
| 911 |
+
0.04665224254131317,
|
| 912 |
+
0.03442087769508362,
|
| 913 |
+
0.04287134110927582
|
| 914 |
],
|
| 915 |
"denoise_loss": [],
|
| 916 |
"ortho_loss": [
|
| 917 |
+
0.47937828302383423,
|
| 918 |
+
0.1507955640554428,
|
| 919 |
+
0.059393465518951416,
|
| 920 |
+
0.04442813619971275,
|
| 921 |
+
0.0324716791510582,
|
| 922 |
+
0.026790229603648186,
|
| 923 |
+
0.02599812112748623,
|
| 924 |
+
0.026838652789592743,
|
| 925 |
+
0.03308980539441109,
|
| 926 |
+
0.03936305269598961,
|
| 927 |
+
0.046892400830984116,
|
| 928 |
+
0.054657381027936935,
|
| 929 |
+
0.06615152955055237,
|
| 930 |
+
0.07190698385238647,
|
| 931 |
+
0.08240365236997604,
|
| 932 |
+
0.09521664679050446,
|
| 933 |
+
0.10861148685216904,
|
| 934 |
+
0.1214362159371376,
|
| 935 |
+
0.1258803755044937,
|
| 936 |
+
0.1299659013748169,
|
| 937 |
+
0.1402484029531479,
|
| 938 |
+
0.14295075833797455,
|
| 939 |
+
0.149370938539505,
|
| 940 |
+
0.15252968668937683,
|
| 941 |
+
0.1605893224477768,
|
| 942 |
+
0.16262884438037872,
|
| 943 |
+
0.1668718159198761,
|
| 944 |
+
0.1677456796169281,
|
| 945 |
+
0.17001178860664368,
|
| 946 |
+
0.16833247244358063,
|
| 947 |
+
0.17318005859851837,
|
| 948 |
+
0.17326097190380096,
|
| 949 |
+
0.17671826481819153,
|
| 950 |
+
0.17965927720069885,
|
| 951 |
+
0.17709869146347046,
|
| 952 |
+
0.17812584340572357,
|
| 953 |
+
0.18094243109226227,
|
| 954 |
+
0.17931658029556274,
|
| 955 |
+
0.1780029535293579,
|
| 956 |
+
0.1778276562690735,
|
| 957 |
+
0.17606784403324127,
|
| 958 |
+
0.17577897012233734,
|
| 959 |
+
0.17276717722415924,
|
| 960 |
+
0.17193765938282013,
|
| 961 |
+
0.17166247963905334,
|
| 962 |
+
0.16964799165725708,
|
| 963 |
+
0.16706812381744385,
|
| 964 |
+
0.16757197678089142,
|
| 965 |
+
0.16796070337295532,
|
| 966 |
+
0.17077603936195374,
|
| 967 |
+
0.16790732741355896,
|
| 968 |
+
0.16808928549289703,
|
| 969 |
+
0.17049027979373932,
|
| 970 |
+
0.16959191858768463,
|
| 971 |
+
0.16786660254001617,
|
| 972 |
+
0.1698780059814453,
|
| 973 |
+
0.17389650642871857,
|
| 974 |
+
0.1759837120771408,
|
| 975 |
+
0.1825551986694336,
|
| 976 |
+
0.1941106617450714,
|
| 977 |
+
0.20087893307209015,
|
| 978 |
+
0.20311099290847778,
|
| 979 |
+
0.20108184218406677,
|
| 980 |
+
0.2060651034116745,
|
| 981 |
+
0.2042357623577118,
|
| 982 |
+
0.20703236758708954,
|
| 983 |
+
0.21205003559589386,
|
| 984 |
+
0.2158161699771881,
|
| 985 |
+
0.2168900966644287,
|
| 986 |
+
0.21410465240478516,
|
| 987 |
+
0.21417385339736938,
|
| 988 |
+
0.2129133939743042,
|
| 989 |
+
0.21731425821781158,
|
| 990 |
+
0.21567592024803162,
|
| 991 |
+
0.21867820620536804,
|
| 992 |
+
0.22142289578914642,
|
| 993 |
+
0.2225620299577713,
|
| 994 |
+
0.22172413766384125,
|
| 995 |
+
0.2218010574579239,
|
| 996 |
+
0.22009830176830292,
|
| 997 |
+
0.21785126626491547,
|
| 998 |
+
0.21678262948989868,
|
| 999 |
+
0.21671107411384583,
|
| 1000 |
+
0.2209888994693756,
|
| 1001 |
+
0.22106041014194489,
|
| 1002 |
+
0.22590550780296326,
|
| 1003 |
+
0.22786492109298706,
|
| 1004 |
+
0.23093664646148682,
|
| 1005 |
+
0.22673366963863373,
|
| 1006 |
+
0.22699661552906036,
|
| 1007 |
+
0.23137319087982178,
|
| 1008 |
+
0.23347441852092743,
|
| 1009 |
+
0.23230887949466705,
|
| 1010 |
+
0.23691625893115997,
|
| 1011 |
+
0.23728600144386292,
|
| 1012 |
+
0.23905602097511292,
|
| 1013 |
+
0.24103665351867676,
|
| 1014 |
+
0.23820726573467255,
|
| 1015 |
+
0.23968391120433807,
|
| 1016 |
+
0.240958109498024,
|
| 1017 |
+
0.24235181510448456,
|
| 1018 |
+
0.2462717443704605,
|
| 1019 |
+
0.2495051473379135,
|
| 1020 |
+
0.2500581443309784,
|
| 1021 |
+
0.25138387084007263,
|
| 1022 |
+
0.2525486350059509,
|
| 1023 |
+
0.25259435176849365,
|
| 1024 |
+
0.25351014733314514,
|
| 1025 |
+
0.25713658332824707,
|
| 1026 |
+
0.26032426953315735,
|
| 1027 |
+
0.2599243223667145,
|
| 1028 |
+
0.26285797357559204,
|
| 1029 |
+
0.2655181884765625,
|
| 1030 |
+
0.27248892188072205,
|
| 1031 |
+
0.2755123972892761,
|
| 1032 |
+
0.27839818596839905,
|
| 1033 |
+
0.280465692281723,
|
| 1034 |
+
0.28088274598121643,
|
| 1035 |
+
0.28307604789733887,
|
| 1036 |
+
0.28578928112983704,
|
| 1037 |
+
0.28797510266304016,
|
| 1038 |
+
0.28915101289749146,
|
| 1039 |
+
0.2902125418186188,
|
| 1040 |
+
0.28890639543533325,
|
| 1041 |
+
0.28958800435066223,
|
| 1042 |
+
0.28951144218444824,
|
| 1043 |
+
0.28970345854759216,
|
| 1044 |
+
0.28964078426361084,
|
| 1045 |
+
0.28985023498535156,
|
| 1046 |
+
0.2914946377277374,
|
| 1047 |
+
0.2916889190673828,
|
| 1048 |
+
0.29132041335105896,
|
| 1049 |
+
0.2919837236404419,
|
| 1050 |
+
0.29286372661590576,
|
| 1051 |
+
0.29286906123161316,
|
| 1052 |
+
0.29427701234817505,
|
| 1053 |
+
0.2967914044857025,
|
| 1054 |
+
0.2974070906639099,
|
| 1055 |
+
0.29844793677330017,
|
| 1056 |
+
0.2980978190898895,
|
| 1057 |
+
0.29862624406814575,
|
| 1058 |
+
0.29875603318214417,
|
| 1059 |
+
0.300121009349823,
|
| 1060 |
+
0.30075713992118835,
|
| 1061 |
+
0.3011188507080078,
|
| 1062 |
+
0.3021273612976074,
|
| 1063 |
+
0.3024706542491913,
|
| 1064 |
+
0.30297189950942993,
|
| 1065 |
+
0.30314701795578003,
|
| 1066 |
+
0.303840696811676
|
| 1067 |
],
|
| 1068 |
"lr": [
|
| 1069 |
+
1.6752136752136756e-05,
|
| 1070 |
+
3.384615384615385e-05,
|
| 1071 |
+
5.094017094017095e-05,
|
| 1072 |
+
6.803418803418804e-05,
|
| 1073 |
+
8e-05,
|
| 1074 |
+
8e-05,
|
| 1075 |
+
8e-05,
|
| 1076 |
+
8e-05,
|
| 1077 |
+
8e-05,
|
| 1078 |
+
8e-05,
|
| 1079 |
+
8e-05,
|
| 1080 |
+
8e-05,
|
| 1081 |
+
8e-05,
|
| 1082 |
+
8e-05,
|
| 1083 |
+
8e-05,
|
| 1084 |
+
8e-05,
|
| 1085 |
+
8e-05,
|
| 1086 |
+
8e-05,
|
| 1087 |
+
8e-05,
|
| 1088 |
+
8e-05,
|
| 1089 |
+
8e-05,
|
| 1090 |
+
8e-05,
|
| 1091 |
+
8e-05,
|
| 1092 |
+
8e-05,
|
| 1093 |
+
8e-05,
|
| 1094 |
+
8e-05,
|
| 1095 |
+
8e-05,
|
| 1096 |
+
8e-05,
|
| 1097 |
+
8e-05,
|
| 1098 |
+
8e-05,
|
| 1099 |
+
8e-05,
|
| 1100 |
+
8e-05,
|
| 1101 |
+
8e-05,
|
| 1102 |
+
8e-05,
|
| 1103 |
+
8e-05,
|
| 1104 |
+
8e-05,
|
| 1105 |
+
8e-05,
|
| 1106 |
+
8e-05,
|
| 1107 |
+
8e-05,
|
| 1108 |
+
8e-05,
|
| 1109 |
+
8e-05,
|
| 1110 |
+
8e-05,
|
| 1111 |
+
8e-05,
|
| 1112 |
+
8e-05,
|
| 1113 |
+
8e-05,
|
| 1114 |
+
8e-05,
|
| 1115 |
+
8e-05,
|
| 1116 |
+
8e-05,
|
| 1117 |
+
8e-05,
|
| 1118 |
+
8e-05,
|
| 1119 |
+
8e-05,
|
| 1120 |
+
8e-05,
|
| 1121 |
+
8e-05,
|
| 1122 |
+
8e-05,
|
| 1123 |
+
8e-05,
|
| 1124 |
+
8e-05,
|
| 1125 |
+
8e-05,
|
| 1126 |
+
8e-05,
|
| 1127 |
+
8e-05,
|
| 1128 |
+
8e-05,
|
| 1129 |
+
8e-05,
|
| 1130 |
+
8e-05,
|
| 1131 |
+
8e-05,
|
| 1132 |
+
8e-05,
|
| 1133 |
+
8e-05,
|
| 1134 |
+
8e-05,
|
| 1135 |
+
8e-05,
|
| 1136 |
+
8e-05,
|
| 1137 |
+
8e-05,
|
| 1138 |
+
8e-05,
|
| 1139 |
+
8e-05,
|
| 1140 |
+
8e-05,
|
| 1141 |
+
8e-05,
|
| 1142 |
+
8e-05,
|
| 1143 |
+
8e-05,
|
| 1144 |
+
8e-05,
|
| 1145 |
+
8e-05,
|
| 1146 |
+
8e-05,
|
| 1147 |
+
8e-05,
|
| 1148 |
+
8e-05,
|
| 1149 |
+
8e-05,
|
| 1150 |
+
8e-05,
|
| 1151 |
+
8e-05,
|
| 1152 |
+
8e-05,
|
| 1153 |
+
8e-05,
|
| 1154 |
+
8e-05,
|
| 1155 |
+
8e-05,
|
| 1156 |
+
8e-05,
|
| 1157 |
+
8e-05,
|
| 1158 |
+
8e-05,
|
| 1159 |
+
8e-05,
|
| 1160 |
+
7.987186923279727e-05,
|
| 1161 |
+
7.868547324017929e-05,
|
| 1162 |
+
7.74990772475613e-05,
|
| 1163 |
+
7.631268125494332e-05,
|
| 1164 |
+
7.512628526232533e-05,
|
| 1165 |
+
7.393988926970736e-05,
|
| 1166 |
+
7.275349327708938e-05,
|
| 1167 |
+
7.156709728447139e-05,
|
| 1168 |
+
7.038070129185342e-05,
|
| 1169 |
+
6.919430529923543e-05,
|
| 1170 |
+
6.800790930661746e-05,
|
| 1171 |
+
6.682151331399946e-05,
|
| 1172 |
+
6.56351173213815e-05,
|
| 1173 |
+
6.444872132876353e-05,
|
| 1174 |
+
6.250303190087003e-05,
|
| 1175 |
+
6.131663590825203e-05,
|
| 1176 |
+
6.0130239915634074e-05,
|
| 1177 |
+
5.894384392301608e-05,
|
| 1178 |
+
5.77574479303981e-05,
|
| 1179 |
+
5.657105193778013e-05,
|
| 1180 |
+
5.538465594516214e-05,
|
| 1181 |
+
5.419825995254416e-05,
|
| 1182 |
+
5.3011863959926175e-05,
|
| 1183 |
+
5.182546796730821e-05,
|
| 1184 |
+
5.063907197469023e-05,
|
| 1185 |
+
4.945267598207224e-05,
|
| 1186 |
+
4.8266279989454265e-05,
|
| 1187 |
+
4.707988399683627e-05,
|
| 1188 |
+
4.5893488004218296e-05,
|
| 1189 |
+
4.3947798576324816e-05,
|
| 1190 |
+
4.276140258370682e-05,
|
| 1191 |
+
4.157500659108885e-05,
|
| 1192 |
+
4.038861059847088e-05,
|
| 1193 |
+
3.9202214605852886e-05,
|
| 1194 |
+
3.801581861323492e-05,
|
| 1195 |
+
3.6829422620616924e-05,
|
| 1196 |
+
3.564302662799895e-05,
|
| 1197 |
+
3.4456630635380976e-05,
|
| 1198 |
+
3.327023464276298e-05,
|
| 1199 |
+
3.2083838650145014e-05,
|
| 1200 |
+
3.089744265752702e-05,
|
| 1201 |
+
2.971104666490905e-05,
|
| 1202 |
+
2.8524650672291075e-05,
|
| 1203 |
+
2.733825467967308e-05,
|
| 1204 |
+
2.5392565251779594e-05,
|
| 1205 |
+
2.4206169259161623e-05,
|
| 1206 |
+
2.3019773266543632e-05,
|
| 1207 |
+
2.1833377273925658e-05,
|
| 1208 |
+
2.0646981281307667e-05,
|
| 1209 |
+
1.9460585288689693e-05,
|
| 1210 |
+
1.8274189296071722e-05,
|
| 1211 |
+
1.7087793303453728e-05,
|
| 1212 |
+
1.5901397310835757e-05,
|
| 1213 |
+
1.4715001318217762e-05,
|
| 1214 |
+
1.352860532559979e-05,
|
| 1215 |
+
1.2342209332981818e-05,
|
| 1216 |
+
1.1155813340363827e-05,
|
| 1217 |
+
9.969417347745854e-06,
|
| 1218 |
+
8.783021355127861e-06
|
| 1219 |
],
|
| 1220 |
"emb_lr": [],
|
| 1221 |
"eval_step": [
|
|
|
|
| 1232 |
],
|
| 1233 |
"eval_accuracy": [
|
| 1234 |
0.0,
|
| 1235 |
+
0.44,
|
| 1236 |
+
0.8,
|
|
|
|
|
|
|
| 1237 |
0.95,
|
| 1238 |
0.99,
|
| 1239 |
+
0.95,
|
| 1240 |
+
0.98,
|
| 1241 |
+
0.95,
|
| 1242 |
1.0,
|
|
|
|
| 1243 |
1.0
|
| 1244 |
]
|
| 1245 |
},
|
| 1246 |
+
"final_accuracy": 0.9995833333333334,
|
| 1247 |
"sft_eval": {
|
| 1248 |
"config": {
|
| 1249 |
"ops": "add_sub",
|
|
|
|
| 1254 |
},
|
| 1255 |
"splits": {
|
| 1256 |
"add_S0": {
|
| 1257 |
+
"full_accuracy": 1.0,
|
| 1258 |
"n_examples": 100,
|
| 1259 |
"per_subtask": {
|
| 1260 |
"SA": {
|
| 1261 |
+
"accuracy": 1.0,
|
| 1262 |
"count": 605
|
| 1263 |
},
|
| 1264 |
"SS": {
|
| 1265 |
+
"accuracy": 1.0,
|
| 1266 |
"count": 95
|
| 1267 |
}
|
| 1268 |
}
|
| 1269 |
},
|
| 1270 |
"add_S1": {
|
| 1271 |
+
"full_accuracy": 0.97,
|
| 1272 |
"n_examples": 100,
|
| 1273 |
"per_subtask": {
|
| 1274 |
"SA": {
|
|
|
|
| 1284 |
"count": 31
|
| 1285 |
},
|
| 1286 |
"UC": {
|
| 1287 |
+
"accuracy": 0.9966216216216216,
|
| 1288 |
"count": 296
|
| 1289 |
}
|
| 1290 |
}
|
| 1291 |
},
|
| 1292 |
"add_S2": {
|
| 1293 |
+
"full_accuracy": 1.0,
|
| 1294 |
"n_examples": 100,
|
| 1295 |
"per_subtask": {
|
| 1296 |
"SA": {
|
|
|
|
| 1298 |
"count": 163
|
| 1299 |
},
|
| 1300 |
"SC": {
|
| 1301 |
+
"accuracy": 1.0,
|
| 1302 |
"count": 130
|
| 1303 |
},
|
| 1304 |
"SS": {
|
| 1305 |
+
"accuracy": 1.0,
|
| 1306 |
"count": 87
|
| 1307 |
},
|
| 1308 |
"UC": {
|
|
|
|
| 1316 |
}
|
| 1317 |
},
|
| 1318 |
"add_S3": {
|
| 1319 |
+
"full_accuracy": 0.99,
|
| 1320 |
"n_examples": 100,
|
| 1321 |
"per_subtask": {
|
| 1322 |
"SA": {
|
|
|
|
| 1332 |
"count": 49
|
| 1333 |
},
|
| 1334 |
"UC": {
|
| 1335 |
+
"accuracy": 0.9946236559139785,
|
| 1336 |
"count": 186
|
| 1337 |
},
|
| 1338 |
"US": {
|
|
|
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
"add_S4": {
|
| 1345 |
+
"full_accuracy": 0.89,
|
| 1346 |
"n_examples": 100,
|
| 1347 |
"per_subtask": {
|
| 1348 |
"SA": {
|
|
|
|
| 1358 |
"count": 23
|
| 1359 |
},
|
| 1360 |
"UC": {
|
| 1361 |
+
"accuracy": 0.93125,
|
| 1362 |
"count": 160
|
| 1363 |
},
|
| 1364 |
"US": {
|
| 1365 |
+
"accuracy": 1.0,
|
| 1366 |
"count": 307
|
| 1367 |
}
|
| 1368 |
}
|
| 1369 |
},
|
| 1370 |
"add_S5": {
|
| 1371 |
+
"full_accuracy": 0.87,
|
| 1372 |
"n_examples": 100,
|
| 1373 |
"per_subtask": {
|
| 1374 |
"SA": {
|
|
|
|
| 1380 |
"count": 100
|
| 1381 |
},
|
| 1382 |
"UC": {
|
| 1383 |
+
"accuracy": 0.88,
|
| 1384 |
"count": 100
|
| 1385 |
},
|
| 1386 |
"US": {
|
| 1387 |
+
"accuracy": 0.97,
|
| 1388 |
"count": 400
|
| 1389 |
}
|
| 1390 |
}
|
| 1391 |
},
|
| 1392 |
"add_S6": {
|
| 1393 |
+
"full_accuracy": 0.75,
|
| 1394 |
"n_examples": 100,
|
| 1395 |
"per_subtask": {
|
| 1396 |
"SC": {
|
|
|
|
| 1398 |
"count": 100
|
| 1399 |
},
|
| 1400 |
"UC": {
|
| 1401 |
+
"accuracy": 0.75,
|
| 1402 |
"count": 100
|
| 1403 |
},
|
| 1404 |
"US": {
|
| 1405 |
+
"accuracy": 0.934,
|
| 1406 |
"count": 500
|
| 1407 |
}
|
| 1408 |
}
|
| 1409 |
},
|
| 1410 |
"add_random": {
|
| 1411 |
+
"full_accuracy": 0.995,
|
| 1412 |
"n_examples": 200,
|
| 1413 |
"per_subtask": {
|
| 1414 |
"SA": {
|
|
|
|
| 1424 |
"count": 56
|
| 1425 |
},
|
| 1426 |
"UC": {
|
| 1427 |
+
"accuracy": 1.0,
|
| 1428 |
"count": 529
|
| 1429 |
},
|
| 1430 |
"US": {
|
|
|
|
| 1434 |
}
|
| 1435 |
},
|
| 1436 |
"add_C3": {
|
| 1437 |
+
"full_accuracy": 0.99,
|
| 1438 |
"n_examples": 100,
|
| 1439 |
"per_subtask": {
|
| 1440 |
"SA": {
|
|
|
|
| 1446 |
"count": 100
|
| 1447 |
},
|
| 1448 |
"UC": {
|
| 1449 |
+
"accuracy": 0.9948186528497409,
|
| 1450 |
"count": 193
|
| 1451 |
},
|
| 1452 |
"US": {
|
| 1453 |
+
"accuracy": 1.0,
|
| 1454 |
"count": 107
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"add_C4": {
|
| 1459 |
+
"full_accuracy": 0.97,
|
| 1460 |
"n_examples": 100,
|
| 1461 |
"per_subtask": {
|
| 1462 |
"SA": {
|
|
|
|
| 1468 |
"count": 100
|
| 1469 |
},
|
| 1470 |
"UC": {
|
| 1471 |
+
"accuracy": 0.98828125,
|
| 1472 |
"count": 256
|
| 1473 |
},
|
| 1474 |
"US": {
|
| 1475 |
+
"accuracy": 1.0,
|
| 1476 |
"count": 144
|
| 1477 |
}
|
| 1478 |
}
|
| 1479 |
},
|
| 1480 |
"add_C5": {
|
| 1481 |
+
"full_accuracy": 0.95,
|
| 1482 |
"n_examples": 100,
|
| 1483 |
"per_subtask": {
|
| 1484 |
"SA": {
|
|
|
|
| 1490 |
"count": 100
|
| 1491 |
},
|
| 1492 |
"UC": {
|
| 1493 |
+
"accuracy": 0.9836601307189542,
|
| 1494 |
"count": 306
|
| 1495 |
},
|
| 1496 |
"US": {
|
| 1497 |
+
"accuracy": 1.0,
|
| 1498 |
"count": 194
|
| 1499 |
}
|
| 1500 |
}
|
| 1501 |
},
|
| 1502 |
"add_C6": {
|
| 1503 |
+
"full_accuracy": 0.99,
|
| 1504 |
"n_examples": 100,
|
| 1505 |
"per_subtask": {
|
| 1506 |
"SC": {
|
|
|
|
| 1508 |
"count": 100
|
| 1509 |
},
|
| 1510 |
"UC": {
|
| 1511 |
+
"accuracy": 0.9972677595628415,
|
| 1512 |
"count": 366
|
| 1513 |
},
|
| 1514 |
"US": {
|
| 1515 |
+
"accuracy": 1.0,
|
| 1516 |
"count": 234
|
| 1517 |
}
|
| 1518 |
}
|
| 1519 |
},
|
| 1520 |
"sub_M0": {
|
| 1521 |
+
"full_accuracy": 1.0,
|
| 1522 |
"n_examples": 100,
|
| 1523 |
"per_subtask": {
|
| 1524 |
"MD": {
|
| 1525 |
+
"accuracy": 1.0,
|
| 1526 |
"count": 601
|
| 1527 |
},
|
| 1528 |
"ME": {
|
|
|
|
| 1532 |
}
|
| 1533 |
},
|
| 1534 |
"sub_M1": {
|
| 1535 |
+
"full_accuracy": 0.99,
|
| 1536 |
"n_examples": 100,
|
| 1537 |
"per_subtask": {
|
| 1538 |
"MD": {
|
|
|
|
| 1540 |
"count": 279
|
| 1541 |
},
|
| 1542 |
"MB": {
|
| 1543 |
+
"accuracy": 1.0,
|
| 1544 |
"count": 145
|
| 1545 |
},
|
| 1546 |
"ME": {
|
|
|
|
| 1580 |
}
|
| 1581 |
},
|
| 1582 |
"sub_M3": {
|
| 1583 |
+
"full_accuracy": 0.89,
|
| 1584 |
"n_examples": 100,
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
|
|
|
| 1596 |
"count": 56
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
+
"accuracy": 0.9261744966442953,
|
| 1600 |
"count": 149
|
| 1601 |
},
|
| 1602 |
"UD": {
|
|
|
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_M4": {
|
| 1609 |
+
"full_accuracy": 0.41,
|
| 1610 |
"n_examples": 100,
|
| 1611 |
"per_subtask": {
|
| 1612 |
"MD": {
|
|
|
|
| 1618 |
"count": 100
|
| 1619 |
},
|
| 1620 |
"UB": {
|
| 1621 |
+
"accuracy": 0.48,
|
| 1622 |
"count": 100
|
| 1623 |
},
|
| 1624 |
"UD": {
|
| 1625 |
+
"accuracy": 0.9133333333333333,
|
| 1626 |
"count": 300
|
| 1627 |
}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
"sub_M5": {
|
| 1631 |
+
"full_accuracy": 0.2,
|
| 1632 |
"n_examples": 100,
|
| 1633 |
"per_subtask": {
|
| 1634 |
"MD": {
|
|
|
|
| 1640 |
"count": 100
|
| 1641 |
},
|
| 1642 |
"UB": {
|
| 1643 |
+
"accuracy": 0.51,
|
| 1644 |
"count": 100
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
+
"accuracy": 0.735,
|
| 1648 |
"count": 400
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
+
"full_accuracy": 0.995,
|
| 1654 |
"n_examples": 200,
|
| 1655 |
"per_subtask": {
|
| 1656 |
"MD": {
|
| 1657 |
+
"accuracy": 1.0,
|
| 1658 |
"count": 600
|
| 1659 |
},
|
| 1660 |
"MB": {
|
| 1661 |
+
"accuracy": 1.0,
|
| 1662 |
"count": 267
|
| 1663 |
},
|
| 1664 |
"ME": {
|
|
|
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"sub_B3": {
|
| 1679 |
+
"full_accuracy": 0.89,
|
| 1680 |
"n_examples": 100,
|
| 1681 |
"per_subtask": {
|
| 1682 |
"MD": {
|
| 1683 |
+
"accuracy": 0.9966666666666667,
|
| 1684 |
"count": 300
|
| 1685 |
},
|
| 1686 |
"MB": {
|
|
|
|
| 1688 |
"count": 100
|
| 1689 |
},
|
| 1690 |
"UB": {
|
| 1691 |
+
"accuracy": 0.949238578680203,
|
| 1692 |
"count": 197
|
| 1693 |
},
|
| 1694 |
"UD": {
|
|
|
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
"sub_B4": {
|
| 1701 |
+
"full_accuracy": 0.85,
|
| 1702 |
"n_examples": 100,
|
| 1703 |
"per_subtask": {
|
| 1704 |
"MD": {
|
| 1705 |
+
"accuracy": 0.995,
|
| 1706 |
"count": 200
|
| 1707 |
},
|
| 1708 |
"MB": {
|
|
|
|
| 1710 |
"count": 100
|
| 1711 |
},
|
| 1712 |
"UB": {
|
| 1713 |
+
"accuracy": 0.9473684210526315,
|
| 1714 |
"count": 247
|
| 1715 |
},
|
| 1716 |
"UD": {
|
| 1717 |
+
"accuracy": 0.9738562091503268,
|
| 1718 |
"count": 153
|
| 1719 |
}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
"sub_B5": {
|
| 1723 |
+
"full_accuracy": 0.91,
|
| 1724 |
"n_examples": 100,
|
| 1725 |
"per_subtask": {
|
| 1726 |
"MD": {
|
|
|
|
| 1732 |
"count": 100
|
| 1733 |
},
|
| 1734 |
"UB": {
|
| 1735 |
+
"accuracy": 0.9697986577181208,
|
| 1736 |
"count": 298
|
| 1737 |
},
|
| 1738 |
"UD": {
|
| 1739 |
+
"accuracy": 0.9801980198019802,
|
| 1740 |
"count": 202
|
| 1741 |
}
|
| 1742 |
}
|
| 1743 |
}
|
| 1744 |
},
|
| 1745 |
"summary": {
|
| 1746 |
+
"overall_accuracy": 0.8954166666666666,
|
| 1747 |
"total_examples": 2400,
|
| 1748 |
"n_splits": 22
|
| 1749 |
}
|
|
|
|
| 1872 |
}
|
| 1873 |
},
|
| 1874 |
"add_S5": {
|
| 1875 |
+
"full_accuracy": 1.0,
|
| 1876 |
"n_examples": 100,
|
| 1877 |
"per_subtask": {
|
| 1878 |
"SA": {
|
|
|
|
| 1884 |
"count": 100
|
| 1885 |
},
|
| 1886 |
"UC": {
|
| 1887 |
+
"accuracy": 1.0,
|
| 1888 |
"count": 100
|
| 1889 |
},
|
| 1890 |
"US": {
|
|
|
|
| 2110 |
}
|
| 2111 |
},
|
| 2112 |
"sub_M4": {
|
| 2113 |
+
"full_accuracy": 1.0,
|
| 2114 |
"n_examples": 100,
|
| 2115 |
"per_subtask": {
|
| 2116 |
"MD": {
|
|
|
|
| 2122 |
"count": 100
|
| 2123 |
},
|
| 2124 |
"UB": {
|
| 2125 |
+
"accuracy": 1.0,
|
| 2126 |
"count": 100
|
| 2127 |
},
|
| 2128 |
"UD": {
|
|
|
|
| 2132 |
}
|
| 2133 |
},
|
| 2134 |
"sub_M5": {
|
| 2135 |
+
"full_accuracy": 1.0,
|
| 2136 |
"n_examples": 100,
|
| 2137 |
"per_subtask": {
|
| 2138 |
"MD": {
|
|
|
|
| 2144 |
"count": 100
|
| 2145 |
},
|
| 2146 |
"UB": {
|
| 2147 |
+
"accuracy": 1.0,
|
| 2148 |
"count": 100
|
| 2149 |
},
|
| 2150 |
"UD": {
|
|
|
|
| 2247 |
}
|
| 2248 |
},
|
| 2249 |
"summary": {
|
| 2250 |
+
"overall_accuracy": 0.9995833333333334,
|
| 2251 |
"total_examples": 2400,
|
| 2252 |
"n_splits": 22
|
| 2253 |
}
|
| 2254 |
},
|
| 2255 |
+
"sorl_overall_accuracy": 0.9995833333333334,
|
| 2256 |
+
"sft_overall_accuracy": 0.8954166666666666
|
| 2257 |
}
|
add_sub_sorl_v1_abs50_50K/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650466940
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f20c93728acb4d46e808ec7e294845cd9e4f4f5e60f7f61517d13f7c28391a31
|
| 3 |
size 650466940
|
add_sub_sorl_v1_abs50_50K/train_config.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"target_vocab_util": 0.8,
|
| 18 |
"min_abs_ppl": 0.0,
|
| 19 |
"zipf_alpha": 1.0,
|
| 20 |
-
"lr":
|
| 21 |
"emb_lr_mult": 1.0,
|
| 22 |
"weight_decay": 0.01,
|
| 23 |
"warmup_steps": 234,
|
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"eval_every": 781,
|
| 37 |
"save_every": 999999,
|
| 38 |
"eval_samples": 100,
|
| 39 |
-
"output_dir": "ckpt/sweep/
|
| 40 |
"eval_K": 4,
|
| 41 |
"alpha_traj": 0.0,
|
| 42 |
"corrupt_method": "shuffle",
|
|
@@ -69,16 +69,16 @@
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 162540062,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs50_50K",
|
| 72 |
-
"git_commit": "
|
| 73 |
-
"timestamp": "2026-04-
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
| 77 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
"trainer_version": "v1",
|
| 79 |
-
"wandb_run_id": "
|
| 80 |
-
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/
|
| 81 |
-
"final_accuracy": 0.
|
| 82 |
-
"sft_accuracy": 0.
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|
|
|
|
| 17 |
"target_vocab_util": 0.8,
|
| 18 |
"min_abs_ppl": 0.0,
|
| 19 |
"zipf_alpha": 1.0,
|
| 20 |
+
"lr": 8e-05,
|
| 21 |
"emb_lr_mult": 1.0,
|
| 22 |
"weight_decay": 0.01,
|
| 23 |
"warmup_steps": 234,
|
|
|
|
| 36 |
"eval_every": 781,
|
| 37 |
"save_every": 999999,
|
| 38 |
"eval_samples": 100,
|
| 39 |
+
"output_dir": "ckpt/sweep/as_sorl_abs50_50K",
|
| 40 |
"eval_K": 4,
|
| 41 |
"alpha_traj": 0.0,
|
| 42 |
"corrupt_method": "shuffle",
|
|
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 162540062,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs50_50K",
|
| 72 |
+
"git_commit": "dc8dd776fb0c30a4c9073052dcc5e943e0fd80c6",
|
| 73 |
+
"timestamp": "2026-04-13T07:43:04.556438+00:00",
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
| 77 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
"trainer_version": "v1",
|
| 79 |
+
"wandb_run_id": "bck2cmmy",
|
| 80 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/bck2cmmy",
|
| 81 |
+
"final_accuracy": 0.9995833333333334,
|
| 82 |
+
"sft_accuracy": 0.8954166666666666,
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|