Upload add_sub_sorl_v1_abs10_K1_50K
Browse files
add_sub_sorl_v1_abs10_K1_50K/metrics.json
CHANGED
|
@@ -153,1069 +153,1069 @@
|
|
| 153 |
7788
|
| 154 |
],
|
| 155 |
"loss": [
|
| 156 |
-
|
| 157 |
-
4.
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
3.
|
| 161 |
-
|
| 162 |
-
2.
|
| 163 |
-
2.
|
| 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 |
-
-0.
|
| 189 |
-
-0.
|
| 190 |
-
-0.
|
| 191 |
-
-0.
|
| 192 |
-
-0.
|
| 193 |
-
-0.
|
| 194 |
-
-0.
|
| 195 |
-
-0.
|
| 196 |
-
-0.
|
| 197 |
-
-0.
|
| 198 |
-
-0.
|
| 199 |
-
-0.
|
| 200 |
-
-0.
|
| 201 |
-
-0.
|
| 202 |
-
-0.
|
| 203 |
-
-0.
|
| 204 |
-
-
|
| 205 |
-
-0.
|
| 206 |
-
-0.
|
| 207 |
-
-0.
|
| 208 |
-
-0.
|
| 209 |
-
-0.
|
| 210 |
-
-0.
|
| 211 |
-
-0.
|
| 212 |
-
-0.
|
| 213 |
-
-0.
|
| 214 |
-
|
| 215 |
-
-0.
|
| 216 |
-
-0.
|
| 217 |
-
-0.
|
| 218 |
-
-
|
| 219 |
-
-0.
|
| 220 |
-
-0.
|
| 221 |
-
-0.
|
| 222 |
-
-0.
|
| 223 |
-
-0.
|
| 224 |
-
-0.
|
| 225 |
-
-0.
|
| 226 |
-
-0.
|
| 227 |
-
-0.
|
| 228 |
-
-0.
|
| 229 |
-
-
|
| 230 |
-
-0.
|
| 231 |
-
-
|
| 232 |
-
-0.
|
| 233 |
-
-0.
|
| 234 |
-
-0.
|
| 235 |
-
-0.
|
| 236 |
-
-0.
|
| 237 |
-
-0.
|
| 238 |
-
-0.
|
| 239 |
-
-0.
|
| 240 |
-
-
|
| 241 |
-
-0.
|
| 242 |
-
-0.
|
| 243 |
-
-0.
|
| 244 |
-
-0.
|
| 245 |
-
-
|
| 246 |
-
-0.
|
| 247 |
-
-0.
|
| 248 |
-
-
|
| 249 |
-
0.
|
| 250 |
-
-0.
|
| 251 |
-
-0.
|
| 252 |
-
0.
|
| 253 |
-
-0.
|
| 254 |
-
-0.
|
| 255 |
-
-0.
|
| 256 |
-
-0.
|
| 257 |
-
0.
|
| 258 |
-
-0.
|
| 259 |
-
-0.
|
| 260 |
-
-0.
|
| 261 |
-
0.
|
| 262 |
-
-0.
|
| 263 |
-
-0.
|
| 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 |
-
0.
|
| 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 |
-
|
| 325 |
-
0.
|
| 326 |
-
0.
|
| 327 |
-
0.
|
| 328 |
-
0.
|
| 329 |
-
0.
|
| 330 |
-
0.
|
| 331 |
-
0.
|
| 332 |
-
0.
|
| 333 |
-
0.
|
| 334 |
-
0.
|
| 335 |
-
0.
|
| 336 |
-
0.
|
| 337 |
-
0.
|
| 338 |
-
0.
|
| 339 |
-
0.
|
| 340 |
-
0.
|
| 341 |
-
0.
|
| 342 |
-
0.
|
| 343 |
-
0.
|
| 344 |
-
0.
|
| 345 |
-
0.
|
| 346 |
-
0.
|
| 347 |
-
0.
|
| 348 |
-
0.
|
| 349 |
-
0.
|
| 350 |
-
0.
|
| 351 |
-
0.
|
| 352 |
-
0.
|
| 353 |
-
0.
|
| 354 |
-
0.
|
| 355 |
-
0.
|
| 356 |
-
0.
|
| 357 |
-
0.
|
| 358 |
-
0.
|
| 359 |
-
0.
|
| 360 |
-
0.
|
| 361 |
-
0.
|
| 362 |
-
0.
|
| 363 |
-
0.
|
| 364 |
-
0.
|
| 365 |
-
0.
|
| 366 |
-
0.
|
| 367 |
-
0.
|
| 368 |
-
0.
|
| 369 |
-
0.
|
| 370 |
-
0.
|
| 371 |
-
0.
|
| 372 |
-
0.
|
| 373 |
-
0.
|
| 374 |
-
0.
|
| 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 |
-
|
| 414 |
-
0.
|
| 415 |
-
0.
|
| 416 |
-
0.
|
| 417 |
-
0.
|
| 418 |
-
0.
|
| 419 |
-
0.
|
| 420 |
-
|
| 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 |
-
|
| 434 |
-
0.
|
| 435 |
-
0.
|
| 436 |
-
0.
|
| 437 |
-
0.
|
| 438 |
-
0.
|
| 439 |
-
0.
|
| 440 |
-
0.
|
| 441 |
-
0.
|
| 442 |
-
|
| 443 |
-
0.
|
| 444 |
-
0.
|
| 445 |
-
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
|
| 449 |
-
|
| 450 |
-
0.
|
| 451 |
-
|
| 452 |
-
|
| 453 |
-
|
| 454 |
-
|
| 455 |
-
0.
|
| 456 |
-
|
| 457 |
-
|
| 458 |
],
|
| 459 |
"info_loss": [
|
| 460 |
-
-
|
| 461 |
-
-
|
| 462 |
-
-0.
|
| 463 |
-
-0.
|
| 464 |
-
-0.
|
| 465 |
-
-0.
|
| 466 |
-
-0.
|
| 467 |
-
-0.
|
| 468 |
-
-0.
|
| 469 |
-
-0.
|
| 470 |
-
-0.
|
| 471 |
-
-0.
|
| 472 |
-
-0.
|
| 473 |
-
-
|
| 474 |
-
-
|
| 475 |
-
-0.
|
| 476 |
-
-0.
|
| 477 |
-
-0.
|
| 478 |
-
-0.
|
| 479 |
-
-0.
|
| 480 |
-
-0.
|
| 481 |
-
-0.
|
| 482 |
-
-0.
|
| 483 |
-
-0.
|
| 484 |
-
-0.
|
| 485 |
-
-0.
|
| 486 |
-
-0.
|
| 487 |
-
-0.
|
| 488 |
-
-0.
|
| 489 |
-
-0.
|
| 490 |
-
-0.
|
| 491 |
-
-0.
|
| 492 |
-
-0.
|
| 493 |
-
-0.
|
| 494 |
-
-0.
|
| 495 |
-
-0.
|
| 496 |
-
-0.
|
| 497 |
-
-0.
|
| 498 |
-
-0.
|
| 499 |
-
-0.
|
| 500 |
-
-0.
|
| 501 |
-
-0.
|
| 502 |
-
-0.
|
| 503 |
-
-0.
|
| 504 |
-
-0.
|
| 505 |
-
-0.
|
| 506 |
-
-0.
|
| 507 |
-
-0.
|
| 508 |
-
-0.
|
| 509 |
-
-0.
|
| 510 |
-
-0.
|
| 511 |
-
-0.
|
| 512 |
-
-0.
|
| 513 |
-
-0.
|
| 514 |
-
-0.
|
| 515 |
-
-0.
|
| 516 |
-
-0.
|
| 517 |
-
-0.
|
| 518 |
-
-0.
|
| 519 |
-
-0.
|
| 520 |
-
-0.
|
| 521 |
-
-0.
|
| 522 |
-
-0.
|
| 523 |
-
-0.
|
| 524 |
-
-0.
|
| 525 |
-
-0.
|
| 526 |
-
-0.
|
| 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 |
-
-
|
| 566 |
-
-0.
|
| 567 |
-
-0.
|
| 568 |
-
-0.
|
| 569 |
-
-0.
|
| 570 |
-
-0.
|
| 571 |
-
-0.
|
| 572 |
-
-
|
| 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 |
-
-
|
| 586 |
-
-0.
|
| 587 |
-
-0.
|
| 588 |
-
-0.
|
| 589 |
-
-0.
|
| 590 |
-
-0.
|
| 591 |
-
-0.
|
| 592 |
-
-0.
|
| 593 |
-
-0.
|
| 594 |
-
-
|
| 595 |
-
-0.
|
| 596 |
-
-0.
|
| 597 |
-
-
|
| 598 |
-
-
|
| 599 |
-
-
|
| 600 |
-
-
|
| 601 |
-
-
|
| 602 |
-
-0.
|
| 603 |
-
-
|
| 604 |
-
-
|
| 605 |
-
-
|
| 606 |
-
-
|
| 607 |
-
-0.
|
| 608 |
-
-
|
| 609 |
-
-
|
| 610 |
],
|
| 611 |
"abs_loss": [
|
| 612 |
-
2.
|
| 613 |
-
|
| 614 |
-
|
| 615 |
-
1.
|
| 616 |
-
1.
|
| 617 |
-
1.
|
| 618 |
-
1.
|
| 619 |
-
1.
|
| 620 |
-
1.
|
| 621 |
-
1.
|
| 622 |
-
1.
|
| 623 |
-
1.
|
| 624 |
-
1.
|
| 625 |
-
1.
|
| 626 |
-
1.
|
| 627 |
-
|
| 628 |
-
|
| 629 |
-
|
| 630 |
-
|
| 631 |
-
0.
|
| 632 |
-
0.
|
| 633 |
-
0.
|
| 634 |
-
0.
|
| 635 |
-
0.
|
| 636 |
-
0.
|
| 637 |
-
0.
|
| 638 |
-
0.
|
| 639 |
-
0.
|
| 640 |
-
0.
|
| 641 |
-
0.
|
| 642 |
-
0.
|
| 643 |
-
0.
|
| 644 |
-
0.
|
| 645 |
-
0.
|
| 646 |
-
0.
|
| 647 |
-
0.
|
| 648 |
-
0.
|
| 649 |
-
0.
|
| 650 |
-
0.
|
| 651 |
-
0.
|
| 652 |
-
0.
|
| 653 |
-
0.
|
| 654 |
-
0.
|
| 655 |
-
0.
|
| 656 |
-
0.
|
| 657 |
-
0.
|
| 658 |
-
0.
|
| 659 |
-
0.
|
| 660 |
-
0.
|
| 661 |
-
0.
|
| 662 |
-
0.
|
| 663 |
-
0.
|
| 664 |
-
0.
|
| 665 |
-
0.
|
| 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 |
-
|
| 723 |
-
0.
|
| 724 |
-
0.
|
| 725 |
-
0.
|
| 726 |
-
|
| 727 |
-
0.
|
| 728 |
-
0.
|
| 729 |
-
|
| 730 |
-
0.
|
| 731 |
-
0.
|
| 732 |
-
0.
|
| 733 |
-
0.
|
| 734 |
-
0.
|
| 735 |
-
0.
|
| 736 |
-
|
| 737 |
-
0.
|
| 738 |
-
|
| 739 |
-
0.
|
| 740 |
-
|
| 741 |
-
0.
|
| 742 |
-
0.
|
| 743 |
-
0.
|
| 744 |
-
|
| 745 |
-
|
| 746 |
-
|
| 747 |
-
|
| 748 |
-
|
| 749 |
-
|
| 750 |
-
|
| 751 |
-
0.
|
| 752 |
-
|
| 753 |
-
|
| 754 |
-
|
| 755 |
-
0.
|
| 756 |
-
|
| 757 |
-
|
| 758 |
-
|
| 759 |
-
|
| 760 |
-
|
| 761 |
-
|
| 762 |
],
|
| 763 |
"zipf_loss": [
|
| 764 |
-
|
| 765 |
-
|
| 766 |
-
|
| 767 |
-
|
| 768 |
-
1.
|
| 769 |
-
1.
|
| 770 |
-
1.
|
| 771 |
-
1.
|
| 772 |
-
1.
|
| 773 |
-
1.
|
| 774 |
-
1.
|
| 775 |
-
1.
|
| 776 |
-
1.
|
| 777 |
-
1.
|
| 778 |
-
1.
|
| 779 |
-
1.
|
| 780 |
-
1.
|
| 781 |
-
1.
|
| 782 |
-
1.
|
| 783 |
-
|
| 784 |
-
|
| 785 |
-
|
| 786 |
-
|
| 787 |
-
|
| 788 |
-
|
| 789 |
-
|
| 790 |
-
|
| 791 |
-
|
| 792 |
-
|
| 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": [
|
|
@@ -1243,508 +1243,508 @@
|
|
| 1243 |
0.0
|
| 1244 |
]
|
| 1245 |
},
|
| 1246 |
-
"final_accuracy":
|
| 1247 |
"sft_eval": {
|
| 1248 |
"config": {
|
| 1249 |
"ops": "add_sub",
|
| 1250 |
"K": null,
|
| 1251 |
"mode": "sft",
|
| 1252 |
"n_digits": 6,
|
| 1253 |
-
"n_per_split":
|
| 1254 |
},
|
| 1255 |
"splits": {
|
| 1256 |
"add_S0": {
|
| 1257 |
-
"full_accuracy":
|
| 1258 |
-
"n_examples":
|
| 1259 |
"per_subtask": {
|
| 1260 |
"SA": {
|
| 1261 |
-
"accuracy":
|
| 1262 |
-
"count":
|
| 1263 |
},
|
| 1264 |
"SS": {
|
| 1265 |
"accuracy": 1.0,
|
| 1266 |
-
"count":
|
| 1267 |
}
|
| 1268 |
}
|
| 1269 |
},
|
| 1270 |
"add_S1": {
|
| 1271 |
"full_accuracy": 1.0,
|
| 1272 |
-
"n_examples":
|
| 1273 |
"per_subtask": {
|
| 1274 |
"SA": {
|
| 1275 |
"accuracy": 1.0,
|
| 1276 |
-
"count":
|
| 1277 |
},
|
| 1278 |
"SC": {
|
| 1279 |
"accuracy": 1.0,
|
| 1280 |
-
"count":
|
| 1281 |
},
|
| 1282 |
"SS": {
|
| 1283 |
"accuracy": 1.0,
|
| 1284 |
-
"count":
|
| 1285 |
},
|
| 1286 |
"UC": {
|
| 1287 |
"accuracy": 1.0,
|
| 1288 |
-
"count":
|
| 1289 |
}
|
| 1290 |
}
|
| 1291 |
},
|
| 1292 |
"add_S2": {
|
| 1293 |
-
"full_accuracy":
|
| 1294 |
-
"n_examples":
|
| 1295 |
"per_subtask": {
|
| 1296 |
"SA": {
|
| 1297 |
"accuracy": 1.0,
|
| 1298 |
-
"count":
|
| 1299 |
},
|
| 1300 |
"SC": {
|
| 1301 |
-
"accuracy":
|
| 1302 |
-
"count":
|
| 1303 |
},
|
| 1304 |
"SS": {
|
| 1305 |
-
"accuracy":
|
| 1306 |
-
"count":
|
| 1307 |
},
|
| 1308 |
"UC": {
|
| 1309 |
-
"accuracy":
|
| 1310 |
-
"count":
|
| 1311 |
},
|
| 1312 |
"US": {
|
| 1313 |
"accuracy": 1.0,
|
| 1314 |
-
"count":
|
| 1315 |
}
|
| 1316 |
}
|
| 1317 |
},
|
| 1318 |
"add_S3": {
|
| 1319 |
-
"full_accuracy":
|
| 1320 |
-
"n_examples":
|
| 1321 |
"per_subtask": {
|
| 1322 |
"SA": {
|
| 1323 |
"accuracy": 1.0,
|
| 1324 |
-
"count":
|
| 1325 |
},
|
| 1326 |
"SC": {
|
| 1327 |
-
"accuracy":
|
| 1328 |
-
"count":
|
| 1329 |
},
|
| 1330 |
"SS": {
|
| 1331 |
"accuracy": 1.0,
|
| 1332 |
-
"count":
|
| 1333 |
},
|
| 1334 |
"UC": {
|
| 1335 |
-
"accuracy":
|
| 1336 |
-
"count":
|
| 1337 |
},
|
| 1338 |
"US": {
|
| 1339 |
-
"accuracy":
|
| 1340 |
-
"count":
|
| 1341 |
}
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
"add_S4": {
|
| 1345 |
-
"full_accuracy": 0.
|
| 1346 |
-
"n_examples":
|
| 1347 |
"per_subtask": {
|
| 1348 |
"SA": {
|
| 1349 |
"accuracy": 1.0,
|
| 1350 |
-
"count":
|
| 1351 |
},
|
| 1352 |
"SC": {
|
| 1353 |
"accuracy": 1.0,
|
| 1354 |
-
"count":
|
| 1355 |
},
|
| 1356 |
"SS": {
|
| 1357 |
"accuracy": 1.0,
|
| 1358 |
-
"count":
|
| 1359 |
},
|
| 1360 |
"UC": {
|
| 1361 |
-
"accuracy": 0.
|
| 1362 |
-
"count":
|
| 1363 |
},
|
| 1364 |
"US": {
|
| 1365 |
-
"accuracy":
|
| 1366 |
-
"count":
|
| 1367 |
}
|
| 1368 |
}
|
| 1369 |
},
|
| 1370 |
"add_S5": {
|
| 1371 |
-
"full_accuracy": 0.
|
| 1372 |
-
"n_examples":
|
| 1373 |
"per_subtask": {
|
| 1374 |
"SA": {
|
| 1375 |
"accuracy": 1.0,
|
| 1376 |
-
"count":
|
| 1377 |
},
|
| 1378 |
"SC": {
|
| 1379 |
"accuracy": 1.0,
|
| 1380 |
-
"count":
|
| 1381 |
},
|
| 1382 |
"UC": {
|
| 1383 |
-
"accuracy": 0.
|
| 1384 |
-
"count":
|
| 1385 |
},
|
| 1386 |
"US": {
|
| 1387 |
-
"accuracy":
|
| 1388 |
-
"count":
|
| 1389 |
}
|
| 1390 |
}
|
| 1391 |
},
|
| 1392 |
"add_S6": {
|
| 1393 |
-
"full_accuracy":
|
| 1394 |
-
"n_examples":
|
| 1395 |
"per_subtask": {
|
| 1396 |
"SC": {
|
| 1397 |
"accuracy": 1.0,
|
| 1398 |
-
"count":
|
| 1399 |
},
|
| 1400 |
"UC": {
|
| 1401 |
-
"accuracy":
|
| 1402 |
-
"count":
|
| 1403 |
},
|
| 1404 |
"US": {
|
| 1405 |
-
"accuracy":
|
| 1406 |
-
"count":
|
| 1407 |
}
|
| 1408 |
}
|
| 1409 |
},
|
| 1410 |
"add_random": {
|
| 1411 |
-
"full_accuracy":
|
| 1412 |
"n_examples": 200,
|
| 1413 |
"per_subtask": {
|
| 1414 |
"SA": {
|
| 1415 |
"accuracy": 1.0,
|
| 1416 |
-
"count":
|
| 1417 |
},
|
| 1418 |
"SC": {
|
| 1419 |
-
"accuracy":
|
| 1420 |
-
"count":
|
| 1421 |
},
|
| 1422 |
"SS": {
|
| 1423 |
"accuracy": 1.0,
|
| 1424 |
-
"count":
|
| 1425 |
},
|
| 1426 |
"UC": {
|
| 1427 |
-
"accuracy":
|
| 1428 |
-
"count":
|
| 1429 |
},
|
| 1430 |
"US": {
|
| 1431 |
"accuracy": 1.0,
|
| 1432 |
-
"count":
|
| 1433 |
}
|
| 1434 |
}
|
| 1435 |
},
|
| 1436 |
"add_C3": {
|
| 1437 |
-
"full_accuracy":
|
| 1438 |
-
"n_examples":
|
| 1439 |
"per_subtask": {
|
| 1440 |
"SA": {
|
| 1441 |
"accuracy": 1.0,
|
| 1442 |
-
"count":
|
| 1443 |
},
|
| 1444 |
"SC": {
|
| 1445 |
"accuracy": 1.0,
|
| 1446 |
-
"count":
|
| 1447 |
},
|
| 1448 |
"UC": {
|
| 1449 |
-
"accuracy":
|
| 1450 |
-
"count":
|
| 1451 |
},
|
| 1452 |
"US": {
|
| 1453 |
"accuracy": 1.0,
|
| 1454 |
-
"count":
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"add_C4": {
|
| 1459 |
-
"full_accuracy": 0.
|
| 1460 |
-
"n_examples":
|
| 1461 |
"per_subtask": {
|
| 1462 |
"SA": {
|
| 1463 |
"accuracy": 1.0,
|
| 1464 |
-
"count":
|
| 1465 |
},
|
| 1466 |
"SC": {
|
| 1467 |
"accuracy": 1.0,
|
| 1468 |
-
"count":
|
| 1469 |
},
|
| 1470 |
"UC": {
|
| 1471 |
-
"accuracy": 0.
|
| 1472 |
-
"count":
|
| 1473 |
},
|
| 1474 |
"US": {
|
| 1475 |
-
"accuracy":
|
| 1476 |
-
"count":
|
| 1477 |
}
|
| 1478 |
}
|
| 1479 |
},
|
| 1480 |
"add_C5": {
|
| 1481 |
-
"full_accuracy":
|
| 1482 |
-
"n_examples":
|
| 1483 |
"per_subtask": {
|
| 1484 |
"SA": {
|
| 1485 |
"accuracy": 1.0,
|
| 1486 |
-
"count":
|
| 1487 |
},
|
| 1488 |
"SC": {
|
| 1489 |
"accuracy": 1.0,
|
| 1490 |
-
"count":
|
| 1491 |
},
|
| 1492 |
"UC": {
|
| 1493 |
-
"accuracy":
|
| 1494 |
-
"count":
|
| 1495 |
},
|
| 1496 |
"US": {
|
| 1497 |
-
"accuracy":
|
| 1498 |
-
"count":
|
| 1499 |
}
|
| 1500 |
}
|
| 1501 |
},
|
| 1502 |
"add_C6": {
|
| 1503 |
-
"full_accuracy":
|
| 1504 |
-
"n_examples":
|
| 1505 |
"per_subtask": {
|
| 1506 |
"SC": {
|
| 1507 |
"accuracy": 1.0,
|
| 1508 |
-
"count":
|
| 1509 |
},
|
| 1510 |
"UC": {
|
| 1511 |
-
"accuracy":
|
| 1512 |
-
"count":
|
| 1513 |
},
|
| 1514 |
"US": {
|
| 1515 |
-
"accuracy":
|
| 1516 |
-
"count":
|
| 1517 |
}
|
| 1518 |
}
|
| 1519 |
},
|
| 1520 |
"sub_M0": {
|
| 1521 |
-
"full_accuracy":
|
| 1522 |
-
"n_examples":
|
| 1523 |
"per_subtask": {
|
| 1524 |
"MD": {
|
| 1525 |
-
"accuracy":
|
| 1526 |
-
"count":
|
| 1527 |
},
|
| 1528 |
"ME": {
|
| 1529 |
-
"accuracy":
|
| 1530 |
-
"count":
|
| 1531 |
}
|
| 1532 |
}
|
| 1533 |
},
|
| 1534 |
"sub_M1": {
|
| 1535 |
-
"full_accuracy":
|
| 1536 |
-
"n_examples":
|
| 1537 |
"per_subtask": {
|
| 1538 |
"MD": {
|
| 1539 |
"accuracy": 1.0,
|
| 1540 |
-
"count":
|
| 1541 |
},
|
| 1542 |
"MB": {
|
| 1543 |
-
"accuracy":
|
| 1544 |
-
"count":
|
| 1545 |
},
|
| 1546 |
"ME": {
|
| 1547 |
"accuracy": 1.0,
|
| 1548 |
-
"count":
|
| 1549 |
},
|
| 1550 |
"UB": {
|
| 1551 |
"accuracy": 1.0,
|
| 1552 |
-
"count":
|
| 1553 |
}
|
| 1554 |
}
|
| 1555 |
},
|
| 1556 |
"sub_M2": {
|
| 1557 |
-
"full_accuracy":
|
| 1558 |
-
"n_examples":
|
| 1559 |
"per_subtask": {
|
| 1560 |
"MD": {
|
| 1561 |
"accuracy": 1.0,
|
| 1562 |
-
"count":
|
| 1563 |
},
|
| 1564 |
"MB": {
|
| 1565 |
-
"accuracy":
|
| 1566 |
-
"count":
|
| 1567 |
},
|
| 1568 |
"ME": {
|
| 1569 |
"accuracy": 1.0,
|
| 1570 |
-
"count":
|
| 1571 |
},
|
| 1572 |
"UB": {
|
| 1573 |
-
"accuracy":
|
| 1574 |
-
"count":
|
| 1575 |
},
|
| 1576 |
"UD": {
|
| 1577 |
"accuracy": 1.0,
|
| 1578 |
-
"count":
|
| 1579 |
}
|
| 1580 |
}
|
| 1581 |
},
|
| 1582 |
"sub_M3": {
|
| 1583 |
-
"full_accuracy":
|
| 1584 |
-
"n_examples":
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
| 1587 |
"accuracy": 1.0,
|
| 1588 |
-
"count":
|
| 1589 |
},
|
| 1590 |
"MB": {
|
| 1591 |
"accuracy": 1.0,
|
| 1592 |
-
"count":
|
| 1593 |
},
|
| 1594 |
"ME": {
|
| 1595 |
"accuracy": 1.0,
|
| 1596 |
-
"count":
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
-
"accuracy":
|
| 1600 |
-
"count":
|
| 1601 |
},
|
| 1602 |
"UD": {
|
| 1603 |
-
"accuracy":
|
| 1604 |
-
"count":
|
| 1605 |
}
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_M4": {
|
| 1609 |
-
"full_accuracy":
|
| 1610 |
-
"n_examples":
|
| 1611 |
"per_subtask": {
|
| 1612 |
"MD": {
|
| 1613 |
"accuracy": 1.0,
|
| 1614 |
-
"count":
|
| 1615 |
},
|
| 1616 |
"MB": {
|
| 1617 |
"accuracy": 1.0,
|
| 1618 |
-
"count":
|
| 1619 |
},
|
| 1620 |
"UB": {
|
| 1621 |
-
"accuracy":
|
| 1622 |
-
"count":
|
| 1623 |
},
|
| 1624 |
"UD": {
|
| 1625 |
-
"accuracy":
|
| 1626 |
-
"count":
|
| 1627 |
}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
"sub_M5": {
|
| 1631 |
-
"full_accuracy":
|
| 1632 |
-
"n_examples":
|
| 1633 |
"per_subtask": {
|
| 1634 |
"MD": {
|
| 1635 |
"accuracy": 1.0,
|
| 1636 |
-
"count":
|
| 1637 |
},
|
| 1638 |
"MB": {
|
| 1639 |
"accuracy": 1.0,
|
| 1640 |
-
"count":
|
| 1641 |
},
|
| 1642 |
"UB": {
|
| 1643 |
-
"accuracy":
|
| 1644 |
-
"count":
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
-
"accuracy":
|
| 1648 |
-
"count":
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
-
"full_accuracy":
|
| 1654 |
"n_examples": 200,
|
| 1655 |
"per_subtask": {
|
| 1656 |
"MD": {
|
| 1657 |
-
"accuracy":
|
| 1658 |
-
"count":
|
| 1659 |
},
|
| 1660 |
"MB": {
|
| 1661 |
-
"accuracy":
|
| 1662 |
-
"count":
|
| 1663 |
},
|
| 1664 |
"ME": {
|
| 1665 |
"accuracy": 1.0,
|
| 1666 |
-
"count":
|
| 1667 |
},
|
| 1668 |
"UB": {
|
| 1669 |
-
"accuracy":
|
| 1670 |
-
"count":
|
| 1671 |
},
|
| 1672 |
"UD": {
|
| 1673 |
"accuracy": 1.0,
|
| 1674 |
-
"count":
|
| 1675 |
}
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"sub_B3": {
|
| 1679 |
-
"full_accuracy":
|
| 1680 |
-
"n_examples":
|
| 1681 |
"per_subtask": {
|
| 1682 |
"MD": {
|
| 1683 |
"accuracy": 1.0,
|
| 1684 |
-
"count":
|
| 1685 |
},
|
| 1686 |
"MB": {
|
| 1687 |
"accuracy": 1.0,
|
| 1688 |
-
"count":
|
| 1689 |
},
|
| 1690 |
"UB": {
|
| 1691 |
-
"accuracy":
|
| 1692 |
-
"count":
|
| 1693 |
},
|
| 1694 |
"UD": {
|
| 1695 |
"accuracy": 1.0,
|
| 1696 |
-
"count":
|
| 1697 |
}
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
"sub_B4": {
|
| 1701 |
-
"full_accuracy":
|
| 1702 |
-
"n_examples":
|
| 1703 |
"per_subtask": {
|
| 1704 |
"MD": {
|
| 1705 |
"accuracy": 1.0,
|
| 1706 |
-
"count":
|
| 1707 |
},
|
| 1708 |
"MB": {
|
| 1709 |
"accuracy": 1.0,
|
| 1710 |
-
"count":
|
| 1711 |
},
|
| 1712 |
"UB": {
|
| 1713 |
-
"accuracy":
|
| 1714 |
-
"count":
|
| 1715 |
},
|
| 1716 |
"UD": {
|
| 1717 |
-
"accuracy":
|
| 1718 |
-
"count":
|
| 1719 |
}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
"sub_B5": {
|
| 1723 |
-
"full_accuracy":
|
| 1724 |
-
"n_examples":
|
| 1725 |
"per_subtask": {
|
| 1726 |
"MD": {
|
| 1727 |
"accuracy": 1.0,
|
| 1728 |
-
"count":
|
| 1729 |
},
|
| 1730 |
"MB": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
-
"count":
|
| 1733 |
},
|
| 1734 |
"UB": {
|
| 1735 |
-
"accuracy":
|
| 1736 |
-
"count":
|
| 1737 |
},
|
| 1738 |
"UD": {
|
| 1739 |
-
"accuracy":
|
| 1740 |
-
"count":
|
| 1741 |
}
|
| 1742 |
}
|
| 1743 |
}
|
| 1744 |
},
|
| 1745 |
"summary": {
|
| 1746 |
-
"overall_accuracy": 0.
|
| 1747 |
-
"total_examples":
|
| 1748 |
"n_splits": 22
|
| 1749 |
}
|
| 1750 |
},
|
|
@@ -1754,402 +1754,402 @@
|
|
| 1754 |
"K": 1,
|
| 1755 |
"mode": "sorl",
|
| 1756 |
"n_digits": 6,
|
| 1757 |
-
"n_per_split":
|
| 1758 |
},
|
| 1759 |
"splits": {
|
| 1760 |
"add_S0": {
|
| 1761 |
"full_accuracy": 1.0,
|
| 1762 |
-
"n_examples":
|
| 1763 |
"per_subtask": {
|
| 1764 |
"SA": {
|
| 1765 |
"accuracy": 1.0,
|
| 1766 |
-
"count":
|
| 1767 |
},
|
| 1768 |
"SS": {
|
| 1769 |
"accuracy": 1.0,
|
| 1770 |
-
"count":
|
| 1771 |
}
|
| 1772 |
}
|
| 1773 |
},
|
| 1774 |
"add_S1": {
|
| 1775 |
"full_accuracy": 1.0,
|
| 1776 |
-
"n_examples":
|
| 1777 |
"per_subtask": {
|
| 1778 |
"SA": {
|
| 1779 |
"accuracy": 1.0,
|
| 1780 |
-
"count":
|
| 1781 |
},
|
| 1782 |
"SC": {
|
| 1783 |
"accuracy": 1.0,
|
| 1784 |
-
"count":
|
| 1785 |
},
|
| 1786 |
"SS": {
|
| 1787 |
"accuracy": 1.0,
|
| 1788 |
-
"count":
|
| 1789 |
},
|
| 1790 |
"UC": {
|
| 1791 |
"accuracy": 1.0,
|
| 1792 |
-
"count":
|
| 1793 |
}
|
| 1794 |
}
|
| 1795 |
},
|
| 1796 |
"add_S2": {
|
| 1797 |
"full_accuracy": 1.0,
|
| 1798 |
-
"n_examples":
|
| 1799 |
"per_subtask": {
|
| 1800 |
"SA": {
|
| 1801 |
"accuracy": 1.0,
|
| 1802 |
-
"count":
|
| 1803 |
},
|
| 1804 |
"SC": {
|
| 1805 |
"accuracy": 1.0,
|
| 1806 |
-
"count":
|
| 1807 |
},
|
| 1808 |
"SS": {
|
| 1809 |
"accuracy": 1.0,
|
| 1810 |
-
"count":
|
| 1811 |
},
|
| 1812 |
"UC": {
|
| 1813 |
"accuracy": 1.0,
|
| 1814 |
-
"count":
|
| 1815 |
},
|
| 1816 |
"US": {
|
| 1817 |
"accuracy": 1.0,
|
| 1818 |
-
"count":
|
| 1819 |
}
|
| 1820 |
}
|
| 1821 |
},
|
| 1822 |
"add_S3": {
|
| 1823 |
"full_accuracy": 1.0,
|
| 1824 |
-
"n_examples":
|
| 1825 |
"per_subtask": {
|
| 1826 |
"SA": {
|
| 1827 |
"accuracy": 1.0,
|
| 1828 |
-
"count":
|
| 1829 |
},
|
| 1830 |
"SC": {
|
| 1831 |
"accuracy": 1.0,
|
| 1832 |
-
"count":
|
| 1833 |
},
|
| 1834 |
"SS": {
|
| 1835 |
"accuracy": 1.0,
|
| 1836 |
-
"count":
|
| 1837 |
},
|
| 1838 |
"UC": {
|
| 1839 |
"accuracy": 1.0,
|
| 1840 |
-
"count":
|
| 1841 |
},
|
| 1842 |
"US": {
|
| 1843 |
"accuracy": 1.0,
|
| 1844 |
-
"count":
|
| 1845 |
}
|
| 1846 |
}
|
| 1847 |
},
|
| 1848 |
"add_S4": {
|
| 1849 |
-
"full_accuracy":
|
| 1850 |
-
"n_examples":
|
| 1851 |
"per_subtask": {
|
| 1852 |
"SA": {
|
| 1853 |
"accuracy": 1.0,
|
| 1854 |
-
"count":
|
| 1855 |
},
|
| 1856 |
"SC": {
|
| 1857 |
"accuracy": 1.0,
|
| 1858 |
-
"count":
|
| 1859 |
},
|
| 1860 |
"SS": {
|
| 1861 |
"accuracy": 1.0,
|
| 1862 |
-
"count":
|
| 1863 |
},
|
| 1864 |
"UC": {
|
| 1865 |
-
"accuracy":
|
| 1866 |
-
"count":
|
| 1867 |
},
|
| 1868 |
"US": {
|
| 1869 |
-
"accuracy":
|
| 1870 |
-
"count":
|
| 1871 |
}
|
| 1872 |
}
|
| 1873 |
},
|
| 1874 |
"add_S5": {
|
| 1875 |
-
"full_accuracy":
|
| 1876 |
-
"n_examples":
|
| 1877 |
"per_subtask": {
|
| 1878 |
"SA": {
|
| 1879 |
"accuracy": 1.0,
|
| 1880 |
-
"count":
|
| 1881 |
},
|
| 1882 |
"SC": {
|
| 1883 |
"accuracy": 1.0,
|
| 1884 |
-
"count":
|
| 1885 |
},
|
| 1886 |
"UC": {
|
| 1887 |
-
"accuracy":
|
| 1888 |
-
"count":
|
| 1889 |
},
|
| 1890 |
"US": {
|
| 1891 |
-
"accuracy":
|
| 1892 |
-
"count":
|
| 1893 |
}
|
| 1894 |
}
|
| 1895 |
},
|
| 1896 |
"add_S6": {
|
| 1897 |
-
"full_accuracy":
|
| 1898 |
-
"n_examples":
|
| 1899 |
"per_subtask": {
|
| 1900 |
"SC": {
|
| 1901 |
"accuracy": 1.0,
|
| 1902 |
-
"count":
|
| 1903 |
},
|
| 1904 |
"UC": {
|
| 1905 |
-
"accuracy":
|
| 1906 |
-
"count":
|
| 1907 |
},
|
| 1908 |
"US": {
|
| 1909 |
-
"accuracy":
|
| 1910 |
-
"count":
|
| 1911 |
}
|
| 1912 |
}
|
| 1913 |
},
|
| 1914 |
"add_random": {
|
| 1915 |
-
"full_accuracy":
|
| 1916 |
"n_examples": 200,
|
| 1917 |
"per_subtask": {
|
| 1918 |
"SA": {
|
| 1919 |
"accuracy": 1.0,
|
| 1920 |
-
"count":
|
| 1921 |
},
|
| 1922 |
"SC": {
|
| 1923 |
-
"accuracy":
|
| 1924 |
-
"count":
|
| 1925 |
},
|
| 1926 |
"SS": {
|
| 1927 |
"accuracy": 1.0,
|
| 1928 |
-
"count":
|
| 1929 |
},
|
| 1930 |
"UC": {
|
| 1931 |
"accuracy": 1.0,
|
| 1932 |
-
"count":
|
| 1933 |
},
|
| 1934 |
"US": {
|
| 1935 |
"accuracy": 1.0,
|
| 1936 |
-
"count":
|
| 1937 |
}
|
| 1938 |
}
|
| 1939 |
},
|
| 1940 |
"add_C3": {
|
| 1941 |
-
"full_accuracy":
|
| 1942 |
-
"n_examples":
|
| 1943 |
"per_subtask": {
|
| 1944 |
"SA": {
|
| 1945 |
"accuracy": 1.0,
|
| 1946 |
-
"count":
|
| 1947 |
},
|
| 1948 |
"SC": {
|
| 1949 |
"accuracy": 1.0,
|
| 1950 |
-
"count":
|
| 1951 |
},
|
| 1952 |
"UC": {
|
| 1953 |
-
"accuracy":
|
| 1954 |
-
"count":
|
| 1955 |
},
|
| 1956 |
"US": {
|
| 1957 |
-
"accuracy":
|
| 1958 |
-
"count":
|
| 1959 |
}
|
| 1960 |
}
|
| 1961 |
},
|
| 1962 |
"add_C4": {
|
| 1963 |
-
"full_accuracy":
|
| 1964 |
-
"n_examples":
|
| 1965 |
"per_subtask": {
|
| 1966 |
"SA": {
|
| 1967 |
"accuracy": 1.0,
|
| 1968 |
-
"count":
|
| 1969 |
},
|
| 1970 |
"SC": {
|
| 1971 |
"accuracy": 1.0,
|
| 1972 |
-
"count":
|
| 1973 |
},
|
| 1974 |
"UC": {
|
| 1975 |
-
"accuracy":
|
| 1976 |
-
"count":
|
| 1977 |
},
|
| 1978 |
"US": {
|
| 1979 |
"accuracy": 1.0,
|
| 1980 |
-
"count":
|
| 1981 |
}
|
| 1982 |
}
|
| 1983 |
},
|
| 1984 |
"add_C5": {
|
| 1985 |
-
"full_accuracy":
|
| 1986 |
-
"n_examples":
|
| 1987 |
"per_subtask": {
|
| 1988 |
"SA": {
|
| 1989 |
"accuracy": 1.0,
|
| 1990 |
-
"count":
|
| 1991 |
},
|
| 1992 |
"SC": {
|
| 1993 |
"accuracy": 1.0,
|
| 1994 |
-
"count":
|
| 1995 |
},
|
| 1996 |
"UC": {
|
| 1997 |
-
"accuracy":
|
| 1998 |
-
"count":
|
| 1999 |
},
|
| 2000 |
"US": {
|
| 2001 |
"accuracy": 1.0,
|
| 2002 |
-
"count":
|
| 2003 |
}
|
| 2004 |
}
|
| 2005 |
},
|
| 2006 |
"add_C6": {
|
| 2007 |
"full_accuracy": 1.0,
|
| 2008 |
-
"n_examples":
|
| 2009 |
"per_subtask": {
|
| 2010 |
"SC": {
|
| 2011 |
"accuracy": 1.0,
|
| 2012 |
-
"count":
|
| 2013 |
},
|
| 2014 |
"UC": {
|
| 2015 |
"accuracy": 1.0,
|
| 2016 |
-
"count":
|
| 2017 |
},
|
| 2018 |
"US": {
|
| 2019 |
"accuracy": 1.0,
|
| 2020 |
-
"count":
|
| 2021 |
}
|
| 2022 |
}
|
| 2023 |
},
|
| 2024 |
"sub_M0": {
|
| 2025 |
"full_accuracy": 1.0,
|
| 2026 |
-
"n_examples":
|
| 2027 |
"per_subtask": {
|
| 2028 |
"MD": {
|
| 2029 |
"accuracy": 1.0,
|
| 2030 |
-
"count":
|
| 2031 |
},
|
| 2032 |
"ME": {
|
| 2033 |
"accuracy": 1.0,
|
| 2034 |
-
"count":
|
| 2035 |
}
|
| 2036 |
}
|
| 2037 |
},
|
| 2038 |
"sub_M1": {
|
| 2039 |
"full_accuracy": 1.0,
|
| 2040 |
-
"n_examples":
|
| 2041 |
"per_subtask": {
|
| 2042 |
"MD": {
|
| 2043 |
"accuracy": 1.0,
|
| 2044 |
-
"count":
|
| 2045 |
},
|
| 2046 |
"MB": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
-
"count":
|
| 2049 |
},
|
| 2050 |
"ME": {
|
| 2051 |
"accuracy": 1.0,
|
| 2052 |
-
"count":
|
| 2053 |
},
|
| 2054 |
"UB": {
|
| 2055 |
"accuracy": 1.0,
|
| 2056 |
-
"count":
|
| 2057 |
}
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
"sub_M2": {
|
| 2061 |
"full_accuracy": 1.0,
|
| 2062 |
-
"n_examples":
|
| 2063 |
"per_subtask": {
|
| 2064 |
"MD": {
|
| 2065 |
"accuracy": 1.0,
|
| 2066 |
-
"count":
|
| 2067 |
},
|
| 2068 |
"MB": {
|
| 2069 |
"accuracy": 1.0,
|
| 2070 |
-
"count":
|
| 2071 |
},
|
| 2072 |
"ME": {
|
| 2073 |
"accuracy": 1.0,
|
| 2074 |
-
"count":
|
| 2075 |
},
|
| 2076 |
"UB": {
|
| 2077 |
"accuracy": 1.0,
|
| 2078 |
-
"count":
|
| 2079 |
},
|
| 2080 |
"UD": {
|
| 2081 |
"accuracy": 1.0,
|
| 2082 |
-
"count":
|
| 2083 |
}
|
| 2084 |
}
|
| 2085 |
},
|
| 2086 |
"sub_M3": {
|
| 2087 |
-
"full_accuracy":
|
| 2088 |
-
"n_examples":
|
| 2089 |
"per_subtask": {
|
| 2090 |
"MD": {
|
| 2091 |
"accuracy": 1.0,
|
| 2092 |
-
"count":
|
| 2093 |
},
|
| 2094 |
"MB": {
|
| 2095 |
"accuracy": 1.0,
|
| 2096 |
-
"count":
|
| 2097 |
},
|
| 2098 |
"ME": {
|
| 2099 |
"accuracy": 1.0,
|
| 2100 |
-
"count":
|
| 2101 |
},
|
| 2102 |
"UB": {
|
| 2103 |
-
"accuracy":
|
| 2104 |
-
"count":
|
| 2105 |
},
|
| 2106 |
"UD": {
|
| 2107 |
"accuracy": 1.0,
|
| 2108 |
-
"count":
|
| 2109 |
}
|
| 2110 |
}
|
| 2111 |
},
|
| 2112 |
"sub_M4": {
|
| 2113 |
-
"full_accuracy":
|
| 2114 |
-
"n_examples":
|
| 2115 |
"per_subtask": {
|
| 2116 |
"MD": {
|
| 2117 |
"accuracy": 1.0,
|
| 2118 |
-
"count":
|
| 2119 |
},
|
| 2120 |
"MB": {
|
| 2121 |
"accuracy": 1.0,
|
| 2122 |
-
"count":
|
| 2123 |
},
|
| 2124 |
"UB": {
|
| 2125 |
-
"accuracy":
|
| 2126 |
-
"count":
|
| 2127 |
},
|
| 2128 |
"UD": {
|
| 2129 |
-
"accuracy":
|
| 2130 |
-
"count":
|
| 2131 |
}
|
| 2132 |
}
|
| 2133 |
},
|
| 2134 |
"sub_M5": {
|
| 2135 |
-
"full_accuracy":
|
| 2136 |
-
"n_examples":
|
| 2137 |
"per_subtask": {
|
| 2138 |
"MD": {
|
| 2139 |
"accuracy": 1.0,
|
| 2140 |
-
"count":
|
| 2141 |
},
|
| 2142 |
"MB": {
|
| 2143 |
"accuracy": 1.0,
|
| 2144 |
-
"count":
|
| 2145 |
},
|
| 2146 |
"UB": {
|
| 2147 |
-
"accuracy":
|
| 2148 |
-
"count":
|
| 2149 |
},
|
| 2150 |
"UD": {
|
| 2151 |
-
"accuracy":
|
| 2152 |
-
"count":
|
| 2153 |
}
|
| 2154 |
}
|
| 2155 |
},
|
|
@@ -2159,99 +2159,99 @@
|
|
| 2159 |
"per_subtask": {
|
| 2160 |
"MD": {
|
| 2161 |
"accuracy": 1.0,
|
| 2162 |
-
"count":
|
| 2163 |
},
|
| 2164 |
"MB": {
|
| 2165 |
"accuracy": 1.0,
|
| 2166 |
-
"count":
|
| 2167 |
},
|
| 2168 |
"ME": {
|
| 2169 |
"accuracy": 1.0,
|
| 2170 |
-
"count":
|
| 2171 |
},
|
| 2172 |
"UB": {
|
| 2173 |
"accuracy": 1.0,
|
| 2174 |
-
"count":
|
| 2175 |
},
|
| 2176 |
"UD": {
|
| 2177 |
"accuracy": 1.0,
|
| 2178 |
-
"count":
|
| 2179 |
}
|
| 2180 |
}
|
| 2181 |
},
|
| 2182 |
"sub_B3": {
|
| 2183 |
-
"full_accuracy":
|
| 2184 |
-
"n_examples":
|
| 2185 |
"per_subtask": {
|
| 2186 |
"MD": {
|
| 2187 |
-
"accuracy":
|
| 2188 |
-
"count":
|
| 2189 |
},
|
| 2190 |
"MB": {
|
| 2191 |
"accuracy": 1.0,
|
| 2192 |
-
"count":
|
| 2193 |
},
|
| 2194 |
"UB": {
|
| 2195 |
-
"accuracy":
|
| 2196 |
-
"count":
|
| 2197 |
},
|
| 2198 |
"UD": {
|
| 2199 |
"accuracy": 1.0,
|
| 2200 |
-
"count":
|
| 2201 |
}
|
| 2202 |
}
|
| 2203 |
},
|
| 2204 |
"sub_B4": {
|
| 2205 |
-
"full_accuracy":
|
| 2206 |
-
"n_examples":
|
| 2207 |
"per_subtask": {
|
| 2208 |
"MD": {
|
| 2209 |
"accuracy": 1.0,
|
| 2210 |
-
"count":
|
| 2211 |
},
|
| 2212 |
"MB": {
|
| 2213 |
"accuracy": 1.0,
|
| 2214 |
-
"count":
|
| 2215 |
},
|
| 2216 |
"UB": {
|
| 2217 |
"accuracy": 1.0,
|
| 2218 |
-
"count":
|
| 2219 |
},
|
| 2220 |
"UD": {
|
| 2221 |
-
"accuracy":
|
| 2222 |
-
"count":
|
| 2223 |
}
|
| 2224 |
}
|
| 2225 |
},
|
| 2226 |
"sub_B5": {
|
| 2227 |
-
"full_accuracy":
|
| 2228 |
-
"n_examples":
|
| 2229 |
"per_subtask": {
|
| 2230 |
"MD": {
|
| 2231 |
"accuracy": 1.0,
|
| 2232 |
-
"count":
|
| 2233 |
},
|
| 2234 |
"MB": {
|
| 2235 |
"accuracy": 1.0,
|
| 2236 |
-
"count":
|
| 2237 |
},
|
| 2238 |
"UB": {
|
| 2239 |
-
"accuracy":
|
| 2240 |
-
"count":
|
| 2241 |
},
|
| 2242 |
"UD": {
|
| 2243 |
-
"accuracy":
|
| 2244 |
-
"count":
|
| 2245 |
}
|
| 2246 |
}
|
| 2247 |
}
|
| 2248 |
},
|
| 2249 |
"summary": {
|
| 2250 |
-
"overall_accuracy":
|
| 2251 |
-
"total_examples":
|
| 2252 |
"n_splits": 22
|
| 2253 |
}
|
| 2254 |
},
|
| 2255 |
-
"sorl_overall_accuracy":
|
| 2256 |
-
"sft_overall_accuracy": 0.
|
| 2257 |
}
|
|
|
|
| 153 |
7788
|
| 154 |
],
|
| 155 |
"loss": [
|
| 156 |
+
-1.8434085845947266,
|
| 157 |
+
4.601749897003174,
|
| 158 |
+
7.194036483764648,
|
| 159 |
+
5.0404052734375,
|
| 160 |
+
3.3781490325927734,
|
| 161 |
+
3.1354575157165527,
|
| 162 |
+
2.926358222961426,
|
| 163 |
+
2.5029892921447754,
|
| 164 |
+
2.0447211265563965,
|
| 165 |
+
1.5462324619293213,
|
| 166 |
+
1.9651050567626953,
|
| 167 |
+
0.8674120306968689,
|
| 168 |
+
-4.487154006958008,
|
| 169 |
+
-2.787264347076416,
|
| 170 |
+
-1.155447006225586,
|
| 171 |
+
-0.85890793800354,
|
| 172 |
+
-0.9630429744720459,
|
| 173 |
+
-0.0802149772644043,
|
| 174 |
+
-0.5840421915054321,
|
| 175 |
+
0.3685035705566406,
|
| 176 |
+
0.3820621967315674,
|
| 177 |
+
0.4070768356323242,
|
| 178 |
+
0.276447057723999,
|
| 179 |
+
0.4328266978263855,
|
| 180 |
+
0.31342917680740356,
|
| 181 |
+
0.08820533752441406,
|
| 182 |
+
0.2808014154434204,
|
| 183 |
+
0.37512701749801636,
|
| 184 |
+
0.21351540088653564,
|
| 185 |
+
-0.10308700799942017,
|
| 186 |
+
0.1635807752609253,
|
| 187 |
+
0.30520498752593994,
|
| 188 |
+
-0.3326461911201477,
|
| 189 |
+
-0.079348623752594,
|
| 190 |
+
-0.22553598880767822,
|
| 191 |
+
-0.6694775819778442,
|
| 192 |
+
-0.12208181619644165,
|
| 193 |
+
-0.4667024612426758,
|
| 194 |
+
-0.3665081858634949,
|
| 195 |
+
-0.5729897022247314,
|
| 196 |
+
-0.319536030292511,
|
| 197 |
+
-0.268004834651947,
|
| 198 |
+
-0.6419415473937988,
|
| 199 |
+
-0.849314272403717,
|
| 200 |
+
-0.7858723402023315,
|
| 201 |
+
-0.4214107394218445,
|
| 202 |
+
-0.7283056974411011,
|
| 203 |
+
-0.7725470066070557,
|
| 204 |
+
-1.0740588903427124,
|
| 205 |
+
-0.8130712509155273,
|
| 206 |
+
-0.7111601829528809,
|
| 207 |
+
-0.5225681066513062,
|
| 208 |
+
-0.7696350812911987,
|
| 209 |
+
-0.6449387073516846,
|
| 210 |
+
-0.84492427110672,
|
| 211 |
+
-0.9666432738304138,
|
| 212 |
+
-0.8239792585372925,
|
| 213 |
+
-0.5367516279220581,
|
| 214 |
+
-1.0095380544662476,
|
| 215 |
+
-0.7369661927223206,
|
| 216 |
+
-0.6510933041572571,
|
| 217 |
+
-0.40475571155548096,
|
| 218 |
+
-1.082499623298645,
|
| 219 |
+
-0.7328605651855469,
|
| 220 |
+
-0.46966123580932617,
|
| 221 |
+
-0.8196786642074585,
|
| 222 |
+
-0.883029580116272,
|
| 223 |
+
-0.6008321046829224,
|
| 224 |
+
-0.6783343553543091,
|
| 225 |
+
-0.47368329763412476,
|
| 226 |
+
-0.5314733386039734,
|
| 227 |
+
-0.6840003132820129,
|
| 228 |
+
-0.8546187877655029,
|
| 229 |
+
-1.0287953615188599,
|
| 230 |
+
-0.7920441031455994,
|
| 231 |
+
-1.12400484085083,
|
| 232 |
+
-0.171156644821167,
|
| 233 |
+
-0.7633827924728394,
|
| 234 |
+
-0.28973886370658875,
|
| 235 |
+
-0.7079243659973145,
|
| 236 |
+
-0.5050032138824463,
|
| 237 |
+
-0.5431491136550903,
|
| 238 |
+
-0.9902877807617188,
|
| 239 |
+
-0.7746119499206543,
|
| 240 |
+
-1.0959405899047852,
|
| 241 |
+
-0.79856938123703,
|
| 242 |
+
-0.5256845951080322,
|
| 243 |
+
-0.5318572521209717,
|
| 244 |
+
-0.5035209655761719,
|
| 245 |
+
-1.0650602579116821,
|
| 246 |
+
-0.7206735014915466,
|
| 247 |
+
-0.5032709240913391,
|
| 248 |
+
-1.0785185098648071,
|
| 249 |
+
-0.6859839558601379,
|
| 250 |
+
-0.8046289086341858,
|
| 251 |
+
-0.804704487323761,
|
| 252 |
+
-0.24211524426937103,
|
| 253 |
+
-0.5526420474052429,
|
| 254 |
+
-0.47156620025634766,
|
| 255 |
+
-0.4604480266571045,
|
| 256 |
+
-0.45559704303741455,
|
| 257 |
+
-0.3846482038497925,
|
| 258 |
+
-0.40795981884002686,
|
| 259 |
+
-0.5747178196907043,
|
| 260 |
+
-0.6696513295173645,
|
| 261 |
+
-0.2594130337238312,
|
| 262 |
+
-0.49968406558036804,
|
| 263 |
+
-0.22021031379699707,
|
| 264 |
+
-0.2839840352535248,
|
| 265 |
+
-0.8381754159927368,
|
| 266 |
+
-0.5067592263221741,
|
| 267 |
+
-0.5559624433517456,
|
| 268 |
+
-0.549471378326416,
|
| 269 |
+
-0.475965291261673,
|
| 270 |
+
-0.5202930569648743,
|
| 271 |
+
-0.344407320022583,
|
| 272 |
+
-0.5949522852897644,
|
| 273 |
+
-0.7239079475402832,
|
| 274 |
+
-0.384538859128952,
|
| 275 |
+
-0.4866296350955963,
|
| 276 |
+
-0.5028886198997498,
|
| 277 |
+
-0.4689003527164459,
|
| 278 |
+
-0.3037208616733551,
|
| 279 |
+
-0.3365515172481537,
|
| 280 |
+
-0.491973876953125,
|
| 281 |
+
-0.5374771356582642,
|
| 282 |
+
-0.44399985671043396,
|
| 283 |
+
-0.3381360173225403,
|
| 284 |
+
-0.6350717544555664,
|
| 285 |
+
-0.7178548574447632,
|
| 286 |
+
-0.7123309373855591,
|
| 287 |
+
-0.361316442489624,
|
| 288 |
+
-0.48409828543663025,
|
| 289 |
+
-0.35243964195251465,
|
| 290 |
+
-0.32026398181915283,
|
| 291 |
+
-0.3339604139328003,
|
| 292 |
+
-0.5739341378211975,
|
| 293 |
+
-0.48164811730384827,
|
| 294 |
+
-0.27859148383140564,
|
| 295 |
+
-0.4119768738746643,
|
| 296 |
+
-0.5286878347396851,
|
| 297 |
+
-0.43117451667785645,
|
| 298 |
+
-0.17727109789848328,
|
| 299 |
+
-0.32236069440841675,
|
| 300 |
+
-0.30850881338119507,
|
| 301 |
+
-0.171178936958313,
|
| 302 |
+
0.0003298455849289894,
|
| 303 |
+
-0.2117927074432373,
|
| 304 |
+
-0.4036300480365753,
|
| 305 |
+
-0.22921818494796753
|
| 306 |
],
|
| 307 |
"base_loss": [
|
| 308 |
+
10.632209777832031,
|
| 309 |
+
7.982909202575684,
|
| 310 |
+
6.587821006774902,
|
| 311 |
+
4.520709037780762,
|
| 312 |
+
2.366877794265747,
|
| 313 |
+
1.9632508754730225,
|
| 314 |
+
1.8810948133468628,
|
| 315 |
+
1.9167741537094116,
|
| 316 |
+
1.844687819480896,
|
| 317 |
+
1.7828369140625,
|
| 318 |
+
1.7966865301132202,
|
| 319 |
+
1.7256510257720947,
|
| 320 |
+
1.7833250761032104,
|
| 321 |
+
1.2931102514266968,
|
| 322 |
+
1.0006948709487915,
|
| 323 |
+
0.7514185905456543,
|
| 324 |
+
0.6519206166267395,
|
| 325 |
+
0.5393238663673401,
|
| 326 |
+
0.530279278755188,
|
| 327 |
+
0.39657315611839294,
|
| 328 |
+
0.3370395004749298,
|
| 329 |
+
0.3314581513404846,
|
| 330 |
+
0.3087233901023865,
|
| 331 |
+
0.2733350098133087,
|
| 332 |
+
0.23935171961784363,
|
| 333 |
+
0.27275773882865906,
|
| 334 |
+
0.24247510731220245,
|
| 335 |
+
0.28289082646369934,
|
| 336 |
+
0.22242148220539093,
|
| 337 |
+
0.2697955071926117,
|
| 338 |
+
0.1733320951461792,
|
| 339 |
+
0.17720375955104828,
|
| 340 |
+
0.2333591878414154,
|
| 341 |
+
0.198623389005661,
|
| 342 |
+
0.1980445683002472,
|
| 343 |
+
0.21090729534626007,
|
| 344 |
+
0.16744916141033173,
|
| 345 |
+
0.18613393604755402,
|
| 346 |
+
0.21154451370239258,
|
| 347 |
+
0.18181976675987244,
|
| 348 |
+
0.17725704610347748,
|
| 349 |
+
0.13323216140270233,
|
| 350 |
+
0.16674815118312836,
|
| 351 |
+
0.17612770199775696,
|
| 352 |
+
0.17982850968837738,
|
| 353 |
+
0.1417199820280075,
|
| 354 |
+
0.18565697968006134,
|
| 355 |
+
0.14755335450172424,
|
| 356 |
+
0.23154662549495697,
|
| 357 |
+
0.16445398330688477,
|
| 358 |
+
0.1381044238805771,
|
| 359 |
+
0.13191550970077515,
|
| 360 |
+
0.15085211396217346,
|
| 361 |
+
0.1167411357164383,
|
| 362 |
+
0.14990152418613434,
|
| 363 |
+
0.16644109785556793,
|
| 364 |
+
0.14282704889774323,
|
| 365 |
+
0.1638578325510025,
|
| 366 |
+
0.1709999144077301,
|
| 367 |
+
0.1265479475259781,
|
| 368 |
+
0.12137407809495926,
|
| 369 |
+
0.10415997356176376,
|
| 370 |
+
0.15311507880687714,
|
| 371 |
+
0.12468172609806061,
|
| 372 |
+
0.09021791070699692,
|
| 373 |
+
0.14292022585868835,
|
| 374 |
+
0.1497221142053604,
|
| 375 |
+
0.12576691806316376,
|
| 376 |
+
0.12008222192525864,
|
| 377 |
+
0.10113135725259781,
|
| 378 |
+
0.10323481261730194,
|
| 379 |
+
0.12529759109020233,
|
| 380 |
+
0.1529254913330078,
|
| 381 |
+
0.15987373888492584,
|
| 382 |
+
0.14235952496528625,
|
| 383 |
+
0.20790931582450867,
|
| 384 |
+
0.061390843242406845,
|
| 385 |
+
0.12248917669057846,
|
| 386 |
+
0.09990566223859787,
|
| 387 |
+
0.11467760056257248,
|
| 388 |
+
0.0947195515036583,
|
| 389 |
+
0.08677514642477036,
|
| 390 |
+
0.13148511946201324,
|
| 391 |
+
0.11599191278219223,
|
| 392 |
+
0.15351541340351105,
|
| 393 |
+
0.14467176795005798,
|
| 394 |
+
0.10693149268627167,
|
| 395 |
+
0.0818195566534996,
|
| 396 |
+
0.07594471424818039,
|
| 397 |
+
0.13786852359771729,
|
| 398 |
+
0.11684416234493256,
|
| 399 |
+
0.08686824887990952,
|
| 400 |
+
0.1478288620710373,
|
| 401 |
+
0.09056692570447922,
|
| 402 |
+
0.11744058132171631,
|
| 403 |
+
0.11174892634153366,
|
| 404 |
+
0.09015238285064697,
|
| 405 |
+
0.09197457879781723,
|
| 406 |
+
0.11186979711055756,
|
| 407 |
+
0.09412705153226852,
|
| 408 |
+
0.07431621104478836,
|
| 409 |
+
0.06726263463497162,
|
| 410 |
+
0.06874510645866394,
|
| 411 |
+
0.0801924392580986,
|
| 412 |
+
0.08614066988229752,
|
| 413 |
+
0.061670560389757156,
|
| 414 |
+
0.06508062779903412,
|
| 415 |
+
0.04255122318863869,
|
| 416 |
+
0.055706512182950974,
|
| 417 |
+
0.10073022544384003,
|
| 418 |
+
0.0699356347322464,
|
| 419 |
+
0.07034023106098175,
|
| 420 |
+
0.07284118235111237,
|
| 421 |
+
0.05894910916686058,
|
| 422 |
+
0.06553871184587479,
|
| 423 |
+
0.05204320698976517,
|
| 424 |
+
0.08224407583475113,
|
| 425 |
+
0.09726792573928833,
|
| 426 |
+
0.056048717349767685,
|
| 427 |
+
0.06981342285871506,
|
| 428 |
+
0.06146648898720741,
|
| 429 |
+
0.05570295825600624,
|
| 430 |
+
0.03937968239188194,
|
| 431 |
+
0.06238776817917824,
|
| 432 |
+
0.062181949615478516,
|
| 433 |
+
0.06271430850028992,
|
| 434 |
+
0.059197068214416504,
|
| 435 |
+
0.040904540568590164,
|
| 436 |
+
0.09744566679000854,
|
| 437 |
+
0.09057306498289108,
|
| 438 |
+
0.08372751623392105,
|
| 439 |
+
0.048680566251277924,
|
| 440 |
+
0.058032240718603134,
|
| 441 |
+
0.04298799857497215,
|
| 442 |
+
0.040354255586862564,
|
| 443 |
+
0.04210610315203667,
|
| 444 |
+
0.06739182025194168,
|
| 445 |
+
0.05643216148018837,
|
| 446 |
+
0.04799077659845352,
|
| 447 |
+
0.06582634150981903,
|
| 448 |
+
0.06786034256219864,
|
| 449 |
+
0.050336603075265884,
|
| 450 |
+
0.02372969686985016,
|
| 451 |
+
0.03990420699119568,
|
| 452 |
+
0.03799917548894882,
|
| 453 |
+
0.028297116979956627,
|
| 454 |
+
0.02373545430600643,
|
| 455 |
+
0.025898095220327377,
|
| 456 |
+
0.04849785566329956,
|
| 457 |
+
0.031204676255583763
|
| 458 |
],
|
| 459 |
"info_loss": [
|
| 460 |
+
-2.154280662536621,
|
| 461 |
+
-1.0021514892578125,
|
| 462 |
+
-0.3421025276184082,
|
| 463 |
+
-0.18748807907104492,
|
| 464 |
+
-0.09576106071472168,
|
| 465 |
+
-0.07301223278045654,
|
| 466 |
+
-0.08417975902557373,
|
| 467 |
+
-0.12956106662750244,
|
| 468 |
+
-0.16788971424102783,
|
| 469 |
+
-0.21119403839111328,
|
| 470 |
+
-0.17039883136749268,
|
| 471 |
+
-0.2731666564941406,
|
| 472 |
+
-0.8152903318405151,
|
| 473 |
+
-0.5971963405609131,
|
| 474 |
+
-0.4048205018043518,
|
| 475 |
+
-0.3479783236980438,
|
| 476 |
+
-0.34581685066223145,
|
| 477 |
+
-0.24254611134529114,
|
| 478 |
+
-0.2833747863769531,
|
| 479 |
+
-0.17116348445415497,
|
| 480 |
+
-0.15951943397521973,
|
| 481 |
+
-0.14711491763591766,
|
| 482 |
+
-0.15129919350147247,
|
| 483 |
+
-0.12494440376758575,
|
| 484 |
+
-0.12257607281208038,
|
| 485 |
+
-0.14566345512866974,
|
| 486 |
+
-0.11530952155590057,
|
| 487 |
+
-0.10817962884902954,
|
| 488 |
+
-0.11163761466741562,
|
| 489 |
+
-0.1392165869474411,
|
| 490 |
+
-0.09404353052377701,
|
| 491 |
+
-0.07652720808982849,
|
| 492 |
+
-0.1374932825565338,
|
| 493 |
+
-0.10515429824590683,
|
| 494 |
+
-0.11093274503946304,
|
| 495 |
+
-0.15530039370059967,
|
| 496 |
+
-0.08905307948589325,
|
| 497 |
+
-0.12400266528129578,
|
| 498 |
+
-0.11530351638793945,
|
| 499 |
+
-0.12510216236114502,
|
| 500 |
+
-0.09754804521799088,
|
| 501 |
+
-0.08323977142572403,
|
| 502 |
+
-0.11513569951057434,
|
| 503 |
+
-0.13081255555152893,
|
| 504 |
+
-0.12103089690208435,
|
| 505 |
+
-0.07875619828701019,
|
| 506 |
+
-0.11085333675146103,
|
| 507 |
+
-0.11415205895900726,
|
| 508 |
+
-0.14868390560150146,
|
| 509 |
+
-0.1161792203783989,
|
| 510 |
+
-0.10286684334278107,
|
| 511 |
+
-0.0834745243191719,
|
| 512 |
+
-0.10393297672271729,
|
| 513 |
+
-0.08899596333503723,
|
| 514 |
+
-0.11577439308166504,
|
| 515 |
+
-0.126922607421875,
|
| 516 |
+
-0.10949666798114777,
|
| 517 |
+
-0.08246820420026779,
|
| 518 |
+
-0.13254199922084808,
|
| 519 |
+
-0.09857504069805145,
|
| 520 |
+
-0.08806297183036804,
|
| 521 |
+
-0.05941857397556305,
|
| 522 |
+
-0.1342480182647705,
|
| 523 |
+
-0.09697772562503815,
|
| 524 |
+
-0.06593884527683258,
|
| 525 |
+
-0.1053750067949295,
|
| 526 |
+
-0.11373204737901688,
|
| 527 |
+
-0.08303886651992798,
|
| 528 |
+
-0.09026733785867691,
|
| 529 |
+
-0.06653150916099548,
|
| 530 |
+
-0.0719875693321228,
|
| 531 |
+
-0.09049896895885468,
|
| 532 |
+
-0.10918503999710083,
|
| 533 |
+
-0.1262160688638687,
|
| 534 |
+
-0.10122648626565933,
|
| 535 |
+
-0.14089807868003845,
|
| 536 |
+
-0.029779095202684402,
|
| 537 |
+
-0.0962420180439949,
|
| 538 |
+
-0.047804489731788635,
|
| 539 |
+
-0.08722390234470367,
|
| 540 |
+
-0.06539133191108704,
|
| 541 |
+
-0.06894926726818085,
|
| 542 |
+
-0.11804205924272537,
|
| 543 |
+
-0.0951739102602005,
|
| 544 |
+
-0.13116803765296936,
|
| 545 |
+
-0.09864196181297302,
|
| 546 |
+
-0.06698055565357208,
|
| 547 |
+
-0.06694429367780685,
|
| 548 |
+
-0.06296820938587189,
|
| 549 |
+
-0.12387578189373016,
|
| 550 |
+
-0.08796757459640503,
|
| 551 |
+
-0.062432579696178436,
|
| 552 |
+
-0.12553571164608002,
|
| 553 |
+
-0.0832127183675766,
|
| 554 |
+
-0.09543228149414062,
|
| 555 |
+
-0.09485894441604614,
|
| 556 |
+
-0.036285944283008575,
|
| 557 |
+
-0.06779389083385468,
|
| 558 |
+
-0.06049571931362152,
|
| 559 |
+
-0.058584053069353104,
|
| 560 |
+
-0.055953070521354675,
|
| 561 |
+
-0.047370679676532745,
|
| 562 |
+
-0.05011027306318283,
|
| 563 |
+
-0.06846652179956436,
|
| 564 |
+
-0.07830111682415009,
|
| 565 |
+
-0.03379259258508682,
|
| 566 |
+
-0.05865723267197609,
|
| 567 |
+
-0.028443146497011185,
|
| 568 |
+
-0.035759612917900085,
|
| 569 |
+
-0.0959823876619339,
|
| 570 |
+
-0.059016164392232895,
|
| 571 |
+
-0.06514833867549896,
|
| 572 |
+
-0.06384195387363434,
|
| 573 |
+
-0.0550120510160923,
|
| 574 |
+
-0.060162171721458435,
|
| 575 |
+
-0.04142150282859802,
|
| 576 |
+
-0.06948015093803406,
|
| 577 |
+
-0.0849016010761261,
|
| 578 |
+
-0.045488521456718445,
|
| 579 |
+
-0.05761241167783737,
|
| 580 |
+
-0.057915620505809784,
|
| 581 |
+
-0.05375836789608002,
|
| 582 |
+
-0.035428501665592194,
|
| 583 |
+
-0.04135306924581528,
|
| 584 |
+
-0.05687076970934868,
|
| 585 |
+
-0.06063086912035942,
|
| 586 |
+
-0.051737695932388306,
|
| 587 |
+
-0.03874053806066513,
|
| 588 |
+
-0.07501217722892761,
|
| 589 |
+
-0.08296582847833633,
|
| 590 |
+
-0.08084855228662491,
|
| 591 |
+
-0.042594727128744125,
|
| 592 |
+
-0.05497287958860397,
|
| 593 |
+
-0.0409231036901474,
|
| 594 |
+
-0.03714267536997795,
|
| 595 |
+
-0.038515087217092514,
|
| 596 |
+
-0.06470105051994324,
|
| 597 |
+
-0.05475146695971489,
|
| 598 |
+
-0.03366674482822418,
|
| 599 |
+
-0.04840214550495148,
|
| 600 |
+
-0.060448870062828064,
|
| 601 |
+
-0.04944160580635071,
|
| 602 |
+
-0.021861515939235687,
|
| 603 |
+
-0.037364523857831955,
|
| 604 |
+
-0.036250390112400055,
|
| 605 |
+
-0.02058701030910015,
|
| 606 |
+
-0.002962470054626465,
|
| 607 |
+
-0.025446342304348946,
|
| 608 |
+
-0.04629882797598839,
|
| 609 |
+
-0.02684767358005047
|
| 610 |
],
|
| 611 |
"abs_loss": [
|
| 612 |
+
2.295839309692383,
|
| 613 |
+
2.2275989055633545,
|
| 614 |
+
2.1086981296539307,
|
| 615 |
+
1.9274109601974487,
|
| 616 |
+
1.8521722555160522,
|
| 617 |
+
1.8391518592834473,
|
| 618 |
+
1.847801685333252,
|
| 619 |
+
1.8374954462051392,
|
| 620 |
+
1.859724998474121,
|
| 621 |
+
1.839316964149475,
|
| 622 |
+
1.8190250396728516,
|
| 623 |
+
1.8263120651245117,
|
| 624 |
+
1.842314600944519,
|
| 625 |
+
1.8191477060317993,
|
| 626 |
+
1.8260663747787476,
|
| 627 |
+
1.7081365585327148,
|
| 628 |
+
1.5390478372573853,
|
| 629 |
+
1.371956706047058,
|
| 630 |
+
1.1772456169128418,
|
| 631 |
+
0.9864012598991394,
|
| 632 |
+
0.9074253439903259,
|
| 633 |
+
0.7410576343536377,
|
| 634 |
+
0.6223271489143372,
|
| 635 |
+
0.6221668124198914,
|
| 636 |
+
0.43830597400665283,
|
| 637 |
+
0.44572123885154724,
|
| 638 |
+
0.3767019808292389,
|
| 639 |
+
0.35089340806007385,
|
| 640 |
+
0.3511207401752472,
|
| 641 |
+
0.3073037564754486,
|
| 642 |
+
0.29159554839134216,
|
| 643 |
+
0.24927647411823273,
|
| 644 |
+
0.3035431206226349,
|
| 645 |
+
0.25916072726249695,
|
| 646 |
+
0.2765158712863922,
|
| 647 |
+
0.2680075466632843,
|
| 648 |
+
0.2417924404144287,
|
| 649 |
+
0.24473977088928223,
|
| 650 |
+
0.2632721960544586,
|
| 651 |
+
0.18410980701446533,
|
| 652 |
+
0.24242109060287476,
|
| 653 |
+
0.18900169432163239,
|
| 654 |
+
0.19975590705871582,
|
| 655 |
+
0.24563705921173096,
|
| 656 |
+
0.19445772469043732,
|
| 657 |
+
0.1802707314491272,
|
| 658 |
+
0.1908070594072342,
|
| 659 |
+
0.17807352542877197,
|
| 660 |
+
0.16488361358642578,
|
| 661 |
+
0.16828572750091553,
|
| 662 |
+
0.14867036044597626,
|
| 663 |
+
0.13234008848667145,
|
| 664 |
+
0.12273865938186646,
|
| 665 |
+
0.13265569508075714,
|
| 666 |
+
0.1418759822845459,
|
| 667 |
+
0.12655209004878998,
|
| 668 |
+
0.13035091757774353,
|
| 669 |
+
0.12680990993976593,
|
| 670 |
+
0.12576831877231598,
|
| 671 |
+
0.1071438416838646,
|
| 672 |
+
0.08369839936494827,
|
| 673 |
+
0.11819586157798767,
|
| 674 |
+
0.09716847538948059,
|
| 675 |
+
0.08509200811386108,
|
| 676 |
+
0.09195878356695175,
|
| 677 |
+
0.1108873188495636,
|
| 678 |
+
0.11018844693899155,
|
| 679 |
+
0.08684412389993668,
|
| 680 |
+
0.07969897240400314,
|
| 681 |
+
0.09847602993249893,
|
| 682 |
+
0.08994873613119125,
|
| 683 |
+
0.09757273644208908,
|
| 684 |
+
0.09574266523122787,
|
| 685 |
+
0.06722705811262131,
|
| 686 |
+
0.06617828458547592,
|
| 687 |
+
0.06307429075241089,
|
| 688 |
+
0.06398019939661026,
|
| 689 |
+
0.08491411060094833,
|
| 690 |
+
0.09034520387649536,
|
| 691 |
+
0.07061836123466492,
|
| 692 |
+
0.07410930842161179,
|
| 693 |
+
0.05841822549700737,
|
| 694 |
+
0.07203157991170883,
|
| 695 |
+
0.08528313785791397,
|
| 696 |
+
0.05755283311009407,
|
| 697 |
+
0.07202991098165512,
|
| 698 |
+
0.05258053168654442,
|
| 699 |
+
0.06566968560218811,
|
| 700 |
+
0.06831564009189606,
|
| 701 |
+
0.06705842912197113,
|
| 702 |
+
0.05826202407479286,
|
| 703 |
+
0.04075853154063225,
|
| 704 |
+
0.03090234287083149,
|
| 705 |
+
0.05761478468775749,
|
| 706 |
+
0.049483027309179306,
|
| 707 |
+
0.03950760141015053,
|
| 708 |
+
0.04932594671845436,
|
| 709 |
+
0.06133858859539032,
|
| 710 |
+
0.03659173473715782,
|
| 711 |
+
0.05550849437713623,
|
| 712 |
+
0.04838262125849724,
|
| 713 |
+
0.04907850921154022,
|
| 714 |
+
0.03190474584698677,
|
| 715 |
+
0.06149425730109215,
|
| 716 |
+
0.04875805974006653,
|
| 717 |
+
0.033366646617650986,
|
| 718 |
+
0.051348015666007996,
|
| 719 |
+
0.035183101892471313,
|
| 720 |
+
0.039095643907785416,
|
| 721 |
+
0.03418345749378204,
|
| 722 |
+
0.040615808218717575,
|
| 723 |
+
0.03146129101514816,
|
| 724 |
+
0.0399123840034008,
|
| 725 |
+
0.04412614926695824,
|
| 726 |
+
0.040752146393060684,
|
| 727 |
+
0.037193093448877335,
|
| 728 |
+
0.0368574783205986,
|
| 729 |
+
0.04091322049498558,
|
| 730 |
+
0.03710327669978142,
|
| 731 |
+
0.046610523015260696,
|
| 732 |
+
0.035114776343107224,
|
| 733 |
+
0.021831894293427467,
|
| 734 |
+
0.02761470340192318,
|
| 735 |
+
0.04176108166575432,
|
| 736 |
+
0.027305403724312782,
|
| 737 |
+
0.022344252094626427,
|
| 738 |
+
0.02350372076034546,
|
| 739 |
+
0.01890672743320465,
|
| 740 |
+
0.01600734330713749,
|
| 741 |
+
0.03159425035119057,
|
| 742 |
+
0.024362294003367424,
|
| 743 |
+
0.041135501116514206,
|
| 744 |
+
0.025996312499046326,
|
| 745 |
+
0.031951699405908585,
|
| 746 |
+
0.017715437337756157,
|
| 747 |
+
0.018048007041215897,
|
| 748 |
+
0.01970280520617962,
|
| 749 |
+
0.018691396340727806,
|
| 750 |
+
0.02166912704706192,
|
| 751 |
+
0.01686987467110157,
|
| 752 |
+
0.016625938937067986,
|
| 753 |
+
0.023458026349544525,
|
| 754 |
+
0.01721585914492607,
|
| 755 |
+
0.018662672489881516,
|
| 756 |
+
0.010516829788684845,
|
| 757 |
+
0.020678414031863213,
|
| 758 |
+
0.02106313593685627,
|
| 759 |
+
0.016574682667851448,
|
| 760 |
+
0.01006575208157301,
|
| 761 |
+
0.011027336120605469
|
| 762 |
],
|
| 763 |
"zipf_loss": [
|
| 764 |
+
8.837604522705078,
|
| 765 |
+
6.417595863342285,
|
| 766 |
+
3.816370725631714,
|
| 767 |
+
2.2018356323242188,
|
| 768 |
+
1.7836644649505615,
|
| 769 |
+
1.7184137105941772,
|
| 770 |
+
1.7022809982299805,
|
| 771 |
+
1.6980761289596558,
|
| 772 |
+
1.6929579973220825,
|
| 773 |
+
1.6914042234420776,
|
| 774 |
+
1.6905043125152588,
|
| 775 |
+
1.6907963752746582,
|
| 776 |
+
1.698193073272705,
|
| 777 |
+
1.7096740007400513,
|
| 778 |
+
1.709456443786621,
|
| 779 |
+
1.6986432075500488,
|
| 780 |
+
1.689300298690796,
|
| 781 |
+
1.6687265634536743,
|
| 782 |
+
1.6017018556594849,
|
| 783 |
+
1.5849251747131348,
|
| 784 |
+
1.5494744777679443,
|
| 785 |
+
1.4726622104644775,
|
| 786 |
+
1.418482780456543,
|
| 787 |
+
1.3467190265655518,
|
| 788 |
+
1.2560075521469116,
|
| 789 |
+
1.2275099754333496,
|
| 790 |
+
1.1537513732910156,
|
| 791 |
+
1.1389431953430176,
|
| 792 |
+
1.0723580121994019,
|
| 793 |
+
0.988552987575531,
|
| 794 |
+
0.9015244245529175,
|
| 795 |
+
0.8683456182479858,
|
| 796 |
+
0.7785730957984924,
|
| 797 |
+
0.7476548552513123,
|
| 798 |
+
0.6580953001976013,
|
| 799 |
+
0.6458182334899902,
|
| 800 |
+
0.5768206119537354,
|
| 801 |
+
0.5627162456512451,
|
| 802 |
+
0.5486552715301514,
|
| 803 |
+
0.47780105471611023,
|
| 804 |
+
0.4544452428817749,
|
| 805 |
+
0.4122605323791504,
|
| 806 |
+
0.3226916491985321,
|
| 807 |
+
0.2581198811531067,
|
| 808 |
+
0.2251623570919037,
|
| 809 |
+
0.2064042091369629,
|
| 810 |
+
0.17549002170562744,
|
| 811 |
+
0.20361295342445374,
|
| 812 |
+
0.16474522650241852,
|
| 813 |
+
0.1674383580684662,
|
| 814 |
+
0.1645367443561554,
|
| 815 |
+
0.16702760756015778,
|
| 816 |
+
0.10656872391700745,
|
| 817 |
+
0.11501426249742508,
|
| 818 |
+
0.1487305909395218,
|
| 819 |
+
0.12348644435405731,
|
| 820 |
+
0.11512525379657745,
|
| 821 |
+
0.11139161139726639,
|
| 822 |
+
0.13230526447296143,
|
| 823 |
+
0.1115218997001648,
|
| 824 |
+
0.0997924953699112,
|
| 825 |
+
0.07345044612884521,
|
| 826 |
+
0.09714864939451218,
|
| 827 |
+
0.10372570157051086,
|
| 828 |
+
0.09031343460083008,
|
| 829 |
+
0.0800623744726181,
|
| 830 |
+
0.0935499519109726,
|
| 831 |
+
0.09510523825883865,
|
| 832 |
+
0.09628686308860779,
|
| 833 |
+
0.08065283298492432,
|
| 834 |
+
0.07617263495922089,
|
| 835 |
+
0.08593451976776123,
|
| 836 |
+
0.07473184168338776,
|
| 837 |
+
0.06676889210939407,
|
| 838 |
+
0.07124341279268265,
|
| 839 |
+
0.07075919955968857,
|
| 840 |
+
0.05884542316198349,
|
| 841 |
+
0.06805682182312012,
|
| 842 |
+
0.07936585694551468,
|
| 843 |
+
0.042575180530548096,
|
| 844 |
+
0.04677964001893997,
|
| 845 |
+
0.05372660234570503,
|
| 846 |
+
0.0514446459710598,
|
| 847 |
+
0.052606962621212006,
|
| 848 |
+
0.0564689114689827,
|
| 849 |
+
0.03597549721598625,
|
| 850 |
+
0.03193143010139465,
|
| 851 |
+
0.04919925332069397,
|
| 852 |
+
0.04338479042053223,
|
| 853 |
+
0.029123149812221527,
|
| 854 |
+
0.036331869661808014,
|
| 855 |
+
0.030110809952020645,
|
| 856 |
+
0.025919612497091293,
|
| 857 |
+
0.049814846366643906,
|
| 858 |
+
0.027304984629154205,
|
| 859 |
+
0.028185272589325905,
|
| 860 |
+
0.025659216567873955,
|
| 861 |
+
0.027188461273908615,
|
| 862 |
+
0.017862066626548767,
|
| 863 |
+
0.025714563205838203,
|
| 864 |
+
0.024779241532087326,
|
| 865 |
+
0.016888093203306198,
|
| 866 |
+
0.021207323297858238,
|
| 867 |
+
0.023605545982718468,
|
| 868 |
+
0.022343382239341736,
|
| 869 |
+
0.013505632989108562,
|
| 870 |
+
0.016672832891345024,
|
| 871 |
+
0.018151607364416122,
|
| 872 |
+
0.013996030203998089,
|
| 873 |
+
0.017499890178442,
|
| 874 |
+
0.009405192919075489,
|
| 875 |
+
0.022034645080566406,
|
| 876 |
+
0.01211574301123619,
|
| 877 |
+
0.010793512687087059,
|
| 878 |
+
0.011714756488800049,
|
| 879 |
+
0.014045214280486107,
|
| 880 |
+
0.013919351622462273,
|
| 881 |
+
0.023748818784952164,
|
| 882 |
+
0.0105872992426157,
|
| 883 |
+
0.015020033344626427,
|
| 884 |
+
0.011289582587778568,
|
| 885 |
+
0.01079719141125679,
|
| 886 |
+
0.00842297077178955,
|
| 887 |
+
0.010415313765406609,
|
| 888 |
+
0.011821335181593895,
|
| 889 |
+
0.003882814198732376,
|
| 890 |
+
0.011829675175249577,
|
| 891 |
+
0.0064741685055196285,
|
| 892 |
+
0.01600360870361328,
|
| 893 |
+
0.018070947378873825,
|
| 894 |
+
0.009990808553993702,
|
| 895 |
+
0.0118367038667202,
|
| 896 |
+
0.0049986522644758224,
|
| 897 |
+
0.010608217678964138,
|
| 898 |
+
0.009036979638040066,
|
| 899 |
+
0.007279562763869762,
|
| 900 |
+
0.003714243182912469,
|
| 901 |
+
0.007565267849713564,
|
| 902 |
+
0.007918259128928185,
|
| 903 |
+
0.004531252663582563,
|
| 904 |
+
0.0062779211439192295,
|
| 905 |
+
0.010559145361185074,
|
| 906 |
+
0.015892773866653442,
|
| 907 |
+
0.00951406266540289,
|
| 908 |
+
0.014944195747375488,
|
| 909 |
+
0.004326231777667999,
|
| 910 |
+
0.004112778231501579,
|
| 911 |
+
0.015115153044462204,
|
| 912 |
+
0.009853800758719444,
|
| 913 |
+
0.006951141636818647
|
| 914 |
],
|
| 915 |
"denoise_loss": [],
|
| 916 |
"ortho_loss": [
|
| 917 |
+
0.781010627746582,
|
| 918 |
+
0.41265496611595154,
|
| 919 |
+
0.2843867242336273,
|
| 920 |
+
0.24464908242225647,
|
| 921 |
+
0.19372586905956268,
|
| 922 |
+
0.14653630554676056,
|
| 923 |
+
0.12690894305706024,
|
| 924 |
+
0.14035648107528687,
|
| 925 |
+
0.1467403918504715,
|
| 926 |
+
0.14873139560222626,
|
| 927 |
+
0.15076600015163422,
|
| 928 |
+
0.14134259521961212,
|
| 929 |
+
0.1720886081457138,
|
| 930 |
+
0.1841181069612503,
|
| 931 |
+
0.1892372965812683,
|
| 932 |
+
0.21692992746829987,
|
| 933 |
+
0.22920839488506317,
|
| 934 |
+
0.2306986153125763,
|
| 935 |
+
0.24093444645404816,
|
| 936 |
+
0.23348228633403778,
|
| 937 |
+
0.2318994104862213,
|
| 938 |
+
0.23281653225421906,
|
| 939 |
+
0.23523861169815063,
|
| 940 |
+
0.2338293194770813,
|
| 941 |
+
0.23984688520431519,
|
| 942 |
+
0.228520467877388,
|
| 943 |
+
0.23014824092388153,
|
| 944 |
+
0.23708471655845642,
|
| 945 |
+
0.2367626279592514,
|
| 946 |
+
0.25205540657043457,
|
| 947 |
+
0.24284140765666962,
|
| 948 |
+
0.2406301349401474,
|
| 949 |
+
0.24487775564193726,
|
| 950 |
+
0.24423283338546753,
|
| 951 |
+
0.24222709238529205,
|
| 952 |
+
0.25248923897743225,
|
| 953 |
+
0.2593522071838379,
|
| 954 |
+
0.2549932897090912,
|
| 955 |
+
0.2515001893043518,
|
| 956 |
+
0.2542876601219177,
|
| 957 |
+
0.2529506981372833,
|
| 958 |
+
0.245258629322052,
|
| 959 |
+
0.237806499004364,
|
| 960 |
+
0.23592640459537506,
|
| 961 |
+
0.24321071803569794,
|
| 962 |
+
0.24525290727615356,
|
| 963 |
+
0.24101296067237854,
|
| 964 |
+
0.24652710556983948,
|
| 965 |
+
0.2437056005001068,
|
| 966 |
+
0.24346786737442017,
|
| 967 |
+
0.25308147072792053,
|
| 968 |
+
0.24983635544776917,
|
| 969 |
+
0.25005075335502625,
|
| 970 |
+
0.23971964418888092,
|
| 971 |
+
0.2432299554347992,
|
| 972 |
+
0.25051483511924744,
|
| 973 |
+
0.2469548135995865,
|
| 974 |
+
0.24723848700523376,
|
| 975 |
+
0.24422234296798706,
|
| 976 |
+
0.24903486669063568,
|
| 977 |
+
0.24440790712833405,
|
| 978 |
+
0.24016746878623962,
|
| 979 |
+
0.23948362469673157,
|
| 980 |
+
0.23534326255321503,
|
| 981 |
+
0.23412300646305084,
|
| 982 |
+
0.2343894988298416,
|
| 983 |
+
0.23666509985923767,
|
| 984 |
+
0.23666077852249146,
|
| 985 |
+
0.23825353384017944,
|
| 986 |
+
0.2527136504650116,
|
| 987 |
+
0.25252288579940796,
|
| 988 |
+
0.25081130862236023,
|
| 989 |
+
0.24570871889591217,
|
| 990 |
+
0.24748820066452026,
|
| 991 |
+
0.24196210503578186,
|
| 992 |
+
0.24245427548885345,
|
| 993 |
+
0.24320077896118164,
|
| 994 |
+
0.24153552949428558,
|
| 995 |
+
0.24637219309806824,
|
| 996 |
+
0.242042675614357,
|
| 997 |
+
0.23713023960590363,
|
| 998 |
+
0.2407684028148651,
|
| 999 |
+
0.23842504620552063,
|
| 1000 |
+
0.24096037447452545,
|
| 1001 |
+
0.24619616568088531,
|
| 1002 |
+
0.24676693975925446,
|
| 1003 |
+
0.24391302466392517,
|
| 1004 |
+
0.24174487590789795,
|
| 1005 |
+
0.24000799655914307,
|
| 1006 |
+
0.23665545880794525,
|
| 1007 |
+
0.23401790857315063,
|
| 1008 |
+
0.2326340228319168,
|
| 1009 |
+
0.23159004747867584,
|
| 1010 |
+
0.232310488820076,
|
| 1011 |
+
0.23389995098114014,
|
| 1012 |
+
0.2368544340133667,
|
| 1013 |
+
0.23794226348400116,
|
| 1014 |
+
0.24407798051834106,
|
| 1015 |
+
0.2495008260011673,
|
| 1016 |
+
0.2494269162416458,
|
| 1017 |
+
0.25290295481681824,
|
| 1018 |
+
0.2539801001548767,
|
| 1019 |
+
0.253307968378067,
|
| 1020 |
+
0.2537336051464081,
|
| 1021 |
+
0.2523295283317566,
|
| 1022 |
+
0.2574489712715149,
|
| 1023 |
+
0.2591862380504608,
|
| 1024 |
+
0.26531365513801575,
|
| 1025 |
+
0.2681552469730377,
|
| 1026 |
+
0.26963144540786743,
|
| 1027 |
+
0.26582789421081543,
|
| 1028 |
+
0.27341020107269287,
|
| 1029 |
+
0.2646898329257965,
|
| 1030 |
+
0.2681393325328827,
|
| 1031 |
+
0.26452261209487915,
|
| 1032 |
+
0.25970354676246643,
|
| 1033 |
+
0.2689834535121918,
|
| 1034 |
+
0.26815590262413025,
|
| 1035 |
+
0.2703576385974884,
|
| 1036 |
+
0.2661500573158264,
|
| 1037 |
+
0.2652627229690552,
|
| 1038 |
+
0.2631981670856476,
|
| 1039 |
+
0.2618700861930847,
|
| 1040 |
+
0.26570484042167664,
|
| 1041 |
+
0.2647176682949066,
|
| 1042 |
+
0.2638062834739685,
|
| 1043 |
+
0.2641897201538086,
|
| 1044 |
+
0.2632160782814026,
|
| 1045 |
+
0.26223623752593994,
|
| 1046 |
+
0.2630186676979065,
|
| 1047 |
+
0.26291322708129883,
|
| 1048 |
+
0.2645634114742279,
|
| 1049 |
+
0.26017430424690247,
|
| 1050 |
+
0.2622302174568176,
|
| 1051 |
+
0.261454313993454,
|
| 1052 |
+
0.26418259739875793,
|
| 1053 |
+
0.2659493684768677,
|
| 1054 |
+
0.26712343096733093,
|
| 1055 |
+
0.2653505802154541,
|
| 1056 |
+
0.26495692133903503,
|
| 1057 |
+
0.26624882221221924,
|
| 1058 |
+
0.26568034291267395,
|
| 1059 |
+
0.265586256980896,
|
| 1060 |
+
0.2662001848220825,
|
| 1061 |
+
0.2667205333709717,
|
| 1062 |
+
0.26666462421417236,
|
| 1063 |
+
0.2664743661880493,
|
| 1064 |
+
0.26669737696647644,
|
| 1065 |
+
0.26664936542510986,
|
| 1066 |
+
0.26581791043281555
|
| 1067 |
],
|
| 1068 |
"lr": [
|
| 1069 |
+
8.376068376068378e-06,
|
| 1070 |
+
1.6923076923076924e-05,
|
| 1071 |
+
2.5470085470085475e-05,
|
| 1072 |
+
3.401709401709402e-05,
|
| 1073 |
+
4e-05,
|
| 1074 |
+
4e-05,
|
| 1075 |
+
4e-05,
|
| 1076 |
+
4e-05,
|
| 1077 |
+
4e-05,
|
| 1078 |
+
4e-05,
|
| 1079 |
+
4e-05,
|
| 1080 |
+
4e-05,
|
| 1081 |
+
4e-05,
|
| 1082 |
+
4e-05,
|
| 1083 |
+
4e-05,
|
| 1084 |
+
4e-05,
|
| 1085 |
+
4e-05,
|
| 1086 |
+
4e-05,
|
| 1087 |
+
4e-05,
|
| 1088 |
+
4e-05,
|
| 1089 |
+
4e-05,
|
| 1090 |
+
4e-05,
|
| 1091 |
+
4e-05,
|
| 1092 |
+
4e-05,
|
| 1093 |
+
4e-05,
|
| 1094 |
+
4e-05,
|
| 1095 |
+
4e-05,
|
| 1096 |
+
4e-05,
|
| 1097 |
+
4e-05,
|
| 1098 |
+
4e-05,
|
| 1099 |
+
4e-05,
|
| 1100 |
+
4e-05,
|
| 1101 |
+
4e-05,
|
| 1102 |
+
4e-05,
|
| 1103 |
+
4e-05,
|
| 1104 |
+
4e-05,
|
| 1105 |
+
4e-05,
|
| 1106 |
+
4e-05,
|
| 1107 |
+
4e-05,
|
| 1108 |
+
4e-05,
|
| 1109 |
+
4e-05,
|
| 1110 |
+
4e-05,
|
| 1111 |
+
4e-05,
|
| 1112 |
+
4e-05,
|
| 1113 |
+
4e-05,
|
| 1114 |
+
4e-05,
|
| 1115 |
+
4e-05,
|
| 1116 |
+
4e-05,
|
| 1117 |
+
4e-05,
|
| 1118 |
+
4e-05,
|
| 1119 |
+
4e-05,
|
| 1120 |
+
4e-05,
|
| 1121 |
+
4e-05,
|
| 1122 |
+
4e-05,
|
| 1123 |
+
4e-05,
|
| 1124 |
+
4e-05,
|
| 1125 |
+
4e-05,
|
| 1126 |
+
4e-05,
|
| 1127 |
+
4e-05,
|
| 1128 |
+
4e-05,
|
| 1129 |
+
4e-05,
|
| 1130 |
+
4e-05,
|
| 1131 |
+
4e-05,
|
| 1132 |
+
4e-05,
|
| 1133 |
+
4e-05,
|
| 1134 |
+
4e-05,
|
| 1135 |
+
4e-05,
|
| 1136 |
+
4e-05,
|
| 1137 |
+
4e-05,
|
| 1138 |
+
4e-05,
|
| 1139 |
+
4e-05,
|
| 1140 |
+
4e-05,
|
| 1141 |
+
4e-05,
|
| 1142 |
+
4e-05,
|
| 1143 |
+
4e-05,
|
| 1144 |
+
4e-05,
|
| 1145 |
+
4e-05,
|
| 1146 |
+
4e-05,
|
| 1147 |
+
4e-05,
|
| 1148 |
+
4e-05,
|
| 1149 |
+
4e-05,
|
| 1150 |
+
4e-05,
|
| 1151 |
+
4e-05,
|
| 1152 |
+
4e-05,
|
| 1153 |
+
4e-05,
|
| 1154 |
+
4e-05,
|
| 1155 |
+
4e-05,
|
| 1156 |
+
4e-05,
|
| 1157 |
+
4e-05,
|
| 1158 |
+
4e-05,
|
| 1159 |
+
4e-05,
|
| 1160 |
+
3.993593461639863e-05,
|
| 1161 |
+
3.934273662008964e-05,
|
| 1162 |
+
3.874953862378065e-05,
|
| 1163 |
+
3.815634062747166e-05,
|
| 1164 |
+
3.7563142631162665e-05,
|
| 1165 |
+
3.696994463485368e-05,
|
| 1166 |
+
3.637674663854469e-05,
|
| 1167 |
+
3.5783548642235693e-05,
|
| 1168 |
+
3.519035064592671e-05,
|
| 1169 |
+
3.459715264961771e-05,
|
| 1170 |
+
3.400395465330873e-05,
|
| 1171 |
+
3.341075665699973e-05,
|
| 1172 |
+
3.281755866069075e-05,
|
| 1173 |
+
3.2224360664381764e-05,
|
| 1174 |
+
3.1251515950435014e-05,
|
| 1175 |
+
3.065831795412602e-05,
|
| 1176 |
+
3.0065119957817037e-05,
|
| 1177 |
+
2.947192196150804e-05,
|
| 1178 |
+
2.887872396519905e-05,
|
| 1179 |
+
2.8285525968890065e-05,
|
| 1180 |
+
2.769232797258107e-05,
|
| 1181 |
+
2.709912997627208e-05,
|
| 1182 |
+
2.6505931979963087e-05,
|
| 1183 |
+
2.5912733983654104e-05,
|
| 1184 |
+
2.5319535987345117e-05,
|
| 1185 |
+
2.472633799103612e-05,
|
| 1186 |
+
2.4133139994727132e-05,
|
| 1187 |
+
2.3539941998418135e-05,
|
| 1188 |
+
2.2946744002109148e-05,
|
| 1189 |
+
2.1973899288162408e-05,
|
| 1190 |
+
2.138070129185341e-05,
|
| 1191 |
+
2.0787503295544424e-05,
|
| 1192 |
+
2.019430529923544e-05,
|
| 1193 |
+
1.9601107302926443e-05,
|
| 1194 |
+
1.900790930661746e-05,
|
| 1195 |
+
1.8414711310308462e-05,
|
| 1196 |
+
1.7821513313999475e-05,
|
| 1197 |
+
1.7228315317690488e-05,
|
| 1198 |
+
1.663511732138149e-05,
|
| 1199 |
+
1.6041919325072507e-05,
|
| 1200 |
+
1.544872132876351e-05,
|
| 1201 |
+
1.4855523332454524e-05,
|
| 1202 |
+
1.4262325336145537e-05,
|
| 1203 |
+
1.366912733983654e-05,
|
| 1204 |
+
1.2696282625889797e-05,
|
| 1205 |
+
1.2103084629580812e-05,
|
| 1206 |
+
1.1509886633271816e-05,
|
| 1207 |
+
1.0916688636962829e-05,
|
| 1208 |
+
1.0323490640653833e-05,
|
| 1209 |
+
9.730292644344846e-06,
|
| 1210 |
+
9.137094648035861e-06,
|
| 1211 |
+
8.543896651726864e-06,
|
| 1212 |
+
7.950698655417878e-06,
|
| 1213 |
+
7.357500659108881e-06,
|
| 1214 |
+
6.764302662799895e-06,
|
| 1215 |
+
6.171104666490909e-06,
|
| 1216 |
+
5.577906670181913e-06,
|
| 1217 |
+
4.984708673872927e-06,
|
| 1218 |
+
4.391510677563931e-06
|
| 1219 |
],
|
| 1220 |
"emb_lr": [],
|
| 1221 |
"eval_step": [
|
|
|
|
| 1243 |
0.0
|
| 1244 |
]
|
| 1245 |
},
|
| 1246 |
+
"final_accuracy": 0.9266666666666666,
|
| 1247 |
"sft_eval": {
|
| 1248 |
"config": {
|
| 1249 |
"ops": "add_sub",
|
| 1250 |
"K": null,
|
| 1251 |
"mode": "sft",
|
| 1252 |
"n_digits": 6,
|
| 1253 |
+
"n_per_split": 100
|
| 1254 |
},
|
| 1255 |
"splits": {
|
| 1256 |
"add_S0": {
|
| 1257 |
+
"full_accuracy": 0.98,
|
| 1258 |
+
"n_examples": 100,
|
| 1259 |
"per_subtask": {
|
| 1260 |
"SA": {
|
| 1261 |
+
"accuracy": 0.996694214876033,
|
| 1262 |
+
"count": 605
|
| 1263 |
},
|
| 1264 |
"SS": {
|
| 1265 |
"accuracy": 1.0,
|
| 1266 |
+
"count": 95
|
| 1267 |
}
|
| 1268 |
}
|
| 1269 |
},
|
| 1270 |
"add_S1": {
|
| 1271 |
"full_accuracy": 1.0,
|
| 1272 |
+
"n_examples": 100,
|
| 1273 |
"per_subtask": {
|
| 1274 |
"SA": {
|
| 1275 |
"accuracy": 1.0,
|
| 1276 |
+
"count": 204
|
| 1277 |
},
|
| 1278 |
"SC": {
|
| 1279 |
"accuracy": 1.0,
|
| 1280 |
+
"count": 169
|
| 1281 |
},
|
| 1282 |
"SS": {
|
| 1283 |
"accuracy": 1.0,
|
| 1284 |
+
"count": 31
|
| 1285 |
},
|
| 1286 |
"UC": {
|
| 1287 |
"accuracy": 1.0,
|
| 1288 |
+
"count": 296
|
| 1289 |
}
|
| 1290 |
}
|
| 1291 |
},
|
| 1292 |
"add_S2": {
|
| 1293 |
+
"full_accuracy": 0.97,
|
| 1294 |
+
"n_examples": 100,
|
| 1295 |
"per_subtask": {
|
| 1296 |
"SA": {
|
| 1297 |
"accuracy": 1.0,
|
| 1298 |
+
"count": 163
|
| 1299 |
},
|
| 1300 |
"SC": {
|
| 1301 |
+
"accuracy": 0.9923076923076923,
|
| 1302 |
+
"count": 130
|
| 1303 |
},
|
| 1304 |
"SS": {
|
| 1305 |
+
"accuracy": 0.9885057471264368,
|
| 1306 |
+
"count": 87
|
| 1307 |
},
|
| 1308 |
"UC": {
|
| 1309 |
+
"accuracy": 0.9950738916256158,
|
| 1310 |
+
"count": 203
|
| 1311 |
},
|
| 1312 |
"US": {
|
| 1313 |
"accuracy": 1.0,
|
| 1314 |
+
"count": 117
|
| 1315 |
}
|
| 1316 |
}
|
| 1317 |
},
|
| 1318 |
"add_S3": {
|
| 1319 |
+
"full_accuracy": 0.6,
|
| 1320 |
+
"n_examples": 100,
|
| 1321 |
"per_subtask": {
|
| 1322 |
"SA": {
|
| 1323 |
"accuracy": 1.0,
|
| 1324 |
+
"count": 121
|
| 1325 |
},
|
| 1326 |
"SC": {
|
| 1327 |
+
"accuracy": 0.9917355371900827,
|
| 1328 |
+
"count": 121
|
| 1329 |
},
|
| 1330 |
"SS": {
|
| 1331 |
"accuracy": 1.0,
|
| 1332 |
+
"count": 49
|
| 1333 |
},
|
| 1334 |
"UC": {
|
| 1335 |
+
"accuracy": 0.7849462365591398,
|
| 1336 |
+
"count": 186
|
| 1337 |
},
|
| 1338 |
"US": {
|
| 1339 |
+
"accuracy": 0.9865470852017937,
|
| 1340 |
+
"count": 223
|
| 1341 |
}
|
| 1342 |
}
|
| 1343 |
},
|
| 1344 |
"add_S4": {
|
| 1345 |
+
"full_accuracy": 0.35,
|
| 1346 |
+
"n_examples": 100,
|
| 1347 |
"per_subtask": {
|
| 1348 |
"SA": {
|
| 1349 |
"accuracy": 1.0,
|
| 1350 |
+
"count": 104
|
| 1351 |
},
|
| 1352 |
"SC": {
|
| 1353 |
"accuracy": 1.0,
|
| 1354 |
+
"count": 106
|
| 1355 |
},
|
| 1356 |
"SS": {
|
| 1357 |
"accuracy": 1.0,
|
| 1358 |
+
"count": 23
|
| 1359 |
},
|
| 1360 |
"UC": {
|
| 1361 |
+
"accuracy": 0.6625,
|
| 1362 |
+
"count": 160
|
| 1363 |
},
|
| 1364 |
"US": {
|
| 1365 |
+
"accuracy": 0.8338762214983714,
|
| 1366 |
+
"count": 307
|
| 1367 |
}
|
| 1368 |
}
|
| 1369 |
},
|
| 1370 |
"add_S5": {
|
| 1371 |
+
"full_accuracy": 0.05,
|
| 1372 |
+
"n_examples": 100,
|
| 1373 |
"per_subtask": {
|
| 1374 |
"SA": {
|
| 1375 |
"accuracy": 1.0,
|
| 1376 |
+
"count": 100
|
| 1377 |
},
|
| 1378 |
"SC": {
|
| 1379 |
"accuracy": 1.0,
|
| 1380 |
+
"count": 100
|
| 1381 |
},
|
| 1382 |
"UC": {
|
| 1383 |
+
"accuracy": 0.21,
|
| 1384 |
+
"count": 100
|
| 1385 |
},
|
| 1386 |
"US": {
|
| 1387 |
+
"accuracy": 0.545,
|
| 1388 |
+
"count": 400
|
| 1389 |
}
|
| 1390 |
}
|
| 1391 |
},
|
| 1392 |
"add_S6": {
|
| 1393 |
+
"full_accuracy": 0.1,
|
| 1394 |
+
"n_examples": 100,
|
| 1395 |
"per_subtask": {
|
| 1396 |
"SC": {
|
| 1397 |
"accuracy": 1.0,
|
| 1398 |
+
"count": 100
|
| 1399 |
},
|
| 1400 |
"UC": {
|
| 1401 |
+
"accuracy": 0.17,
|
| 1402 |
+
"count": 100
|
| 1403 |
},
|
| 1404 |
"US": {
|
| 1405 |
+
"accuracy": 0.476,
|
| 1406 |
+
"count": 500
|
| 1407 |
}
|
| 1408 |
}
|
| 1409 |
},
|
| 1410 |
"add_random": {
|
| 1411 |
+
"full_accuracy": 0.985,
|
| 1412 |
"n_examples": 200,
|
| 1413 |
"per_subtask": {
|
| 1414 |
"SA": {
|
| 1415 |
"accuracy": 1.0,
|
| 1416 |
+
"count": 447
|
| 1417 |
},
|
| 1418 |
"SC": {
|
| 1419 |
+
"accuracy": 0.996875,
|
| 1420 |
+
"count": 320
|
| 1421 |
},
|
| 1422 |
"SS": {
|
| 1423 |
"accuracy": 1.0,
|
| 1424 |
+
"count": 56
|
| 1425 |
},
|
| 1426 |
"UC": {
|
| 1427 |
+
"accuracy": 0.996219281663516,
|
| 1428 |
+
"count": 529
|
| 1429 |
},
|
| 1430 |
"US": {
|
| 1431 |
"accuracy": 1.0,
|
| 1432 |
+
"count": 48
|
| 1433 |
}
|
| 1434 |
}
|
| 1435 |
},
|
| 1436 |
"add_C3": {
|
| 1437 |
+
"full_accuracy": 0.87,
|
| 1438 |
+
"n_examples": 100,
|
| 1439 |
"per_subtask": {
|
| 1440 |
"SA": {
|
| 1441 |
"accuracy": 1.0,
|
| 1442 |
+
"count": 300
|
| 1443 |
},
|
| 1444 |
"SC": {
|
| 1445 |
"accuracy": 1.0,
|
| 1446 |
+
"count": 100
|
| 1447 |
},
|
| 1448 |
"UC": {
|
| 1449 |
+
"accuracy": 0.9326424870466321,
|
| 1450 |
+
"count": 193
|
| 1451 |
},
|
| 1452 |
"US": {
|
| 1453 |
"accuracy": 1.0,
|
| 1454 |
+
"count": 107
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"add_C4": {
|
| 1459 |
+
"full_accuracy": 0.76,
|
| 1460 |
+
"n_examples": 100,
|
| 1461 |
"per_subtask": {
|
| 1462 |
"SA": {
|
| 1463 |
"accuracy": 1.0,
|
| 1464 |
+
"count": 200
|
| 1465 |
},
|
| 1466 |
"SC": {
|
| 1467 |
"accuracy": 1.0,
|
| 1468 |
+
"count": 100
|
| 1469 |
},
|
| 1470 |
"UC": {
|
| 1471 |
+
"accuracy": 0.9140625,
|
| 1472 |
+
"count": 256
|
| 1473 |
},
|
| 1474 |
"US": {
|
| 1475 |
+
"accuracy": 0.9375,
|
| 1476 |
+
"count": 144
|
| 1477 |
}
|
| 1478 |
}
|
| 1479 |
},
|
| 1480 |
"add_C5": {
|
| 1481 |
+
"full_accuracy": 0.64,
|
| 1482 |
+
"n_examples": 100,
|
| 1483 |
"per_subtask": {
|
| 1484 |
"SA": {
|
| 1485 |
"accuracy": 1.0,
|
| 1486 |
+
"count": 100
|
| 1487 |
},
|
| 1488 |
"SC": {
|
| 1489 |
"accuracy": 1.0,
|
| 1490 |
+
"count": 100
|
| 1491 |
},
|
| 1492 |
"UC": {
|
| 1493 |
+
"accuracy": 0.8888888888888888,
|
| 1494 |
+
"count": 306
|
| 1495 |
},
|
| 1496 |
"US": {
|
| 1497 |
+
"accuracy": 0.8969072164948454,
|
| 1498 |
+
"count": 194
|
| 1499 |
}
|
| 1500 |
}
|
| 1501 |
},
|
| 1502 |
"add_C6": {
|
| 1503 |
+
"full_accuracy": 0.68,
|
| 1504 |
+
"n_examples": 100,
|
| 1505 |
"per_subtask": {
|
| 1506 |
"SC": {
|
| 1507 |
"accuracy": 1.0,
|
| 1508 |
+
"count": 100
|
| 1509 |
},
|
| 1510 |
"UC": {
|
| 1511 |
+
"accuracy": 0.9180327868852459,
|
| 1512 |
+
"count": 366
|
| 1513 |
},
|
| 1514 |
"US": {
|
| 1515 |
+
"accuracy": 0.9487179487179487,
|
| 1516 |
+
"count": 234
|
| 1517 |
}
|
| 1518 |
}
|
| 1519 |
},
|
| 1520 |
"sub_M0": {
|
| 1521 |
+
"full_accuracy": 0.94,
|
| 1522 |
+
"n_examples": 100,
|
| 1523 |
"per_subtask": {
|
| 1524 |
"MD": {
|
| 1525 |
+
"accuracy": 0.9916805324459235,
|
| 1526 |
+
"count": 601
|
| 1527 |
},
|
| 1528 |
"ME": {
|
| 1529 |
+
"accuracy": 0.98989898989899,
|
| 1530 |
+
"count": 99
|
| 1531 |
}
|
| 1532 |
}
|
| 1533 |
},
|
| 1534 |
"sub_M1": {
|
| 1535 |
+
"full_accuracy": 0.99,
|
| 1536 |
+
"n_examples": 100,
|
| 1537 |
"per_subtask": {
|
| 1538 |
"MD": {
|
| 1539 |
"accuracy": 1.0,
|
| 1540 |
+
"count": 279
|
| 1541 |
},
|
| 1542 |
"MB": {
|
| 1543 |
+
"accuracy": 0.993103448275862,
|
| 1544 |
+
"count": 145
|
| 1545 |
},
|
| 1546 |
"ME": {
|
| 1547 |
"accuracy": 1.0,
|
| 1548 |
+
"count": 24
|
| 1549 |
},
|
| 1550 |
"UB": {
|
| 1551 |
"accuracy": 1.0,
|
| 1552 |
+
"count": 252
|
| 1553 |
}
|
| 1554 |
}
|
| 1555 |
},
|
| 1556 |
"sub_M2": {
|
| 1557 |
+
"full_accuracy": 0.98,
|
| 1558 |
+
"n_examples": 100,
|
| 1559 |
"per_subtask": {
|
| 1560 |
"MD": {
|
| 1561 |
"accuracy": 1.0,
|
| 1562 |
+
"count": 213
|
| 1563 |
},
|
| 1564 |
"MB": {
|
| 1565 |
+
"accuracy": 0.9911504424778761,
|
| 1566 |
+
"count": 113
|
| 1567 |
},
|
| 1568 |
"ME": {
|
| 1569 |
"accuracy": 1.0,
|
| 1570 |
+
"count": 85
|
| 1571 |
},
|
| 1572 |
"UB": {
|
| 1573 |
+
"accuracy": 0.994475138121547,
|
| 1574 |
+
"count": 181
|
| 1575 |
},
|
| 1576 |
"UD": {
|
| 1577 |
"accuracy": 1.0,
|
| 1578 |
+
"count": 108
|
| 1579 |
}
|
| 1580 |
}
|
| 1581 |
},
|
| 1582 |
"sub_M3": {
|
| 1583 |
+
"full_accuracy": 0.44,
|
| 1584 |
+
"n_examples": 100,
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
| 1587 |
"accuracy": 1.0,
|
| 1588 |
+
"count": 179
|
| 1589 |
},
|
| 1590 |
"MB": {
|
| 1591 |
"accuracy": 1.0,
|
| 1592 |
+
"count": 103
|
| 1593 |
},
|
| 1594 |
"ME": {
|
| 1595 |
"accuracy": 1.0,
|
| 1596 |
+
"count": 56
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
+
"accuracy": 0.6241610738255033,
|
| 1600 |
+
"count": 149
|
| 1601 |
},
|
| 1602 |
"UD": {
|
| 1603 |
+
"accuracy": 0.9906103286384976,
|
| 1604 |
+
"count": 213
|
| 1605 |
}
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_M4": {
|
| 1609 |
+
"full_accuracy": 0.12,
|
| 1610 |
+
"n_examples": 100,
|
| 1611 |
"per_subtask": {
|
| 1612 |
"MD": {
|
| 1613 |
"accuracy": 1.0,
|
| 1614 |
+
"count": 200
|
| 1615 |
},
|
| 1616 |
"MB": {
|
| 1617 |
"accuracy": 1.0,
|
| 1618 |
+
"count": 100
|
| 1619 |
},
|
| 1620 |
"UB": {
|
| 1621 |
+
"accuracy": 0.55,
|
| 1622 |
+
"count": 100
|
| 1623 |
},
|
| 1624 |
"UD": {
|
| 1625 |
+
"accuracy": 0.7333333333333333,
|
| 1626 |
+
"count": 300
|
| 1627 |
}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
"sub_M5": {
|
| 1631 |
+
"full_accuracy": 0.09,
|
| 1632 |
+
"n_examples": 100,
|
| 1633 |
"per_subtask": {
|
| 1634 |
"MD": {
|
| 1635 |
"accuracy": 1.0,
|
| 1636 |
+
"count": 100
|
| 1637 |
},
|
| 1638 |
"MB": {
|
| 1639 |
"accuracy": 1.0,
|
| 1640 |
+
"count": 100
|
| 1641 |
},
|
| 1642 |
"UB": {
|
| 1643 |
+
"accuracy": 0.54,
|
| 1644 |
+
"count": 100
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
+
"accuracy": 0.5925,
|
| 1648 |
+
"count": 400
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
+
"full_accuracy": 0.98,
|
| 1654 |
"n_examples": 200,
|
| 1655 |
"per_subtask": {
|
| 1656 |
"MD": {
|
| 1657 |
+
"accuracy": 0.9966666666666667,
|
| 1658 |
+
"count": 600
|
| 1659 |
},
|
| 1660 |
"MB": {
|
| 1661 |
+
"accuracy": 0.9962546816479401,
|
| 1662 |
+
"count": 267
|
| 1663 |
},
|
| 1664 |
"ME": {
|
| 1665 |
"accuracy": 1.0,
|
| 1666 |
+
"count": 53
|
| 1667 |
},
|
| 1668 |
"UB": {
|
| 1669 |
+
"accuracy": 0.9977220956719818,
|
| 1670 |
+
"count": 439
|
| 1671 |
},
|
| 1672 |
"UD": {
|
| 1673 |
"accuracy": 1.0,
|
| 1674 |
+
"count": 41
|
| 1675 |
}
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"sub_B3": {
|
| 1679 |
+
"full_accuracy": 0.9,
|
| 1680 |
+
"n_examples": 100,
|
| 1681 |
"per_subtask": {
|
| 1682 |
"MD": {
|
| 1683 |
"accuracy": 1.0,
|
| 1684 |
+
"count": 300
|
| 1685 |
},
|
| 1686 |
"MB": {
|
| 1687 |
"accuracy": 1.0,
|
| 1688 |
+
"count": 100
|
| 1689 |
},
|
| 1690 |
"UB": {
|
| 1691 |
+
"accuracy": 0.949238578680203,
|
| 1692 |
+
"count": 197
|
| 1693 |
},
|
| 1694 |
"UD": {
|
| 1695 |
"accuracy": 1.0,
|
| 1696 |
+
"count": 103
|
| 1697 |
}
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
"sub_B4": {
|
| 1701 |
+
"full_accuracy": 0.75,
|
| 1702 |
+
"n_examples": 100,
|
| 1703 |
"per_subtask": {
|
| 1704 |
"MD": {
|
| 1705 |
"accuracy": 1.0,
|
| 1706 |
+
"count": 200
|
| 1707 |
},
|
| 1708 |
"MB": {
|
| 1709 |
"accuracy": 1.0,
|
| 1710 |
+
"count": 100
|
| 1711 |
},
|
| 1712 |
"UB": {
|
| 1713 |
+
"accuracy": 0.9109311740890689,
|
| 1714 |
+
"count": 247
|
| 1715 |
},
|
| 1716 |
"UD": {
|
| 1717 |
+
"accuracy": 0.954248366013072,
|
| 1718 |
+
"count": 153
|
| 1719 |
}
|
| 1720 |
}
|
| 1721 |
},
|
| 1722 |
"sub_B5": {
|
| 1723 |
+
"full_accuracy": 0.63,
|
| 1724 |
+
"n_examples": 100,
|
| 1725 |
"per_subtask": {
|
| 1726 |
"MD": {
|
| 1727 |
"accuracy": 1.0,
|
| 1728 |
+
"count": 100
|
| 1729 |
},
|
| 1730 |
"MB": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
+
"count": 100
|
| 1733 |
},
|
| 1734 |
"UB": {
|
| 1735 |
+
"accuracy": 0.8959731543624161,
|
| 1736 |
+
"count": 298
|
| 1737 |
},
|
| 1738 |
"UD": {
|
| 1739 |
+
"accuracy": 0.9158415841584159,
|
| 1740 |
+
"count": 202
|
| 1741 |
}
|
| 1742 |
}
|
| 1743 |
}
|
| 1744 |
},
|
| 1745 |
"summary": {
|
| 1746 |
+
"overall_accuracy": 0.69875,
|
| 1747 |
+
"total_examples": 2400,
|
| 1748 |
"n_splits": 22
|
| 1749 |
}
|
| 1750 |
},
|
|
|
|
| 1754 |
"K": 1,
|
| 1755 |
"mode": "sorl",
|
| 1756 |
"n_digits": 6,
|
| 1757 |
+
"n_per_split": 100
|
| 1758 |
},
|
| 1759 |
"splits": {
|
| 1760 |
"add_S0": {
|
| 1761 |
"full_accuracy": 1.0,
|
| 1762 |
+
"n_examples": 100,
|
| 1763 |
"per_subtask": {
|
| 1764 |
"SA": {
|
| 1765 |
"accuracy": 1.0,
|
| 1766 |
+
"count": 605
|
| 1767 |
},
|
| 1768 |
"SS": {
|
| 1769 |
"accuracy": 1.0,
|
| 1770 |
+
"count": 95
|
| 1771 |
}
|
| 1772 |
}
|
| 1773 |
},
|
| 1774 |
"add_S1": {
|
| 1775 |
"full_accuracy": 1.0,
|
| 1776 |
+
"n_examples": 100,
|
| 1777 |
"per_subtask": {
|
| 1778 |
"SA": {
|
| 1779 |
"accuracy": 1.0,
|
| 1780 |
+
"count": 204
|
| 1781 |
},
|
| 1782 |
"SC": {
|
| 1783 |
"accuracy": 1.0,
|
| 1784 |
+
"count": 169
|
| 1785 |
},
|
| 1786 |
"SS": {
|
| 1787 |
"accuracy": 1.0,
|
| 1788 |
+
"count": 31
|
| 1789 |
},
|
| 1790 |
"UC": {
|
| 1791 |
"accuracy": 1.0,
|
| 1792 |
+
"count": 296
|
| 1793 |
}
|
| 1794 |
}
|
| 1795 |
},
|
| 1796 |
"add_S2": {
|
| 1797 |
"full_accuracy": 1.0,
|
| 1798 |
+
"n_examples": 100,
|
| 1799 |
"per_subtask": {
|
| 1800 |
"SA": {
|
| 1801 |
"accuracy": 1.0,
|
| 1802 |
+
"count": 163
|
| 1803 |
},
|
| 1804 |
"SC": {
|
| 1805 |
"accuracy": 1.0,
|
| 1806 |
+
"count": 130
|
| 1807 |
},
|
| 1808 |
"SS": {
|
| 1809 |
"accuracy": 1.0,
|
| 1810 |
+
"count": 87
|
| 1811 |
},
|
| 1812 |
"UC": {
|
| 1813 |
"accuracy": 1.0,
|
| 1814 |
+
"count": 203
|
| 1815 |
},
|
| 1816 |
"US": {
|
| 1817 |
"accuracy": 1.0,
|
| 1818 |
+
"count": 117
|
| 1819 |
}
|
| 1820 |
}
|
| 1821 |
},
|
| 1822 |
"add_S3": {
|
| 1823 |
"full_accuracy": 1.0,
|
| 1824 |
+
"n_examples": 100,
|
| 1825 |
"per_subtask": {
|
| 1826 |
"SA": {
|
| 1827 |
"accuracy": 1.0,
|
| 1828 |
+
"count": 121
|
| 1829 |
},
|
| 1830 |
"SC": {
|
| 1831 |
"accuracy": 1.0,
|
| 1832 |
+
"count": 121
|
| 1833 |
},
|
| 1834 |
"SS": {
|
| 1835 |
"accuracy": 1.0,
|
| 1836 |
+
"count": 49
|
| 1837 |
},
|
| 1838 |
"UC": {
|
| 1839 |
"accuracy": 1.0,
|
| 1840 |
+
"count": 186
|
| 1841 |
},
|
| 1842 |
"US": {
|
| 1843 |
"accuracy": 1.0,
|
| 1844 |
+
"count": 223
|
| 1845 |
}
|
| 1846 |
}
|
| 1847 |
},
|
| 1848 |
"add_S4": {
|
| 1849 |
+
"full_accuracy": 0.96,
|
| 1850 |
+
"n_examples": 100,
|
| 1851 |
"per_subtask": {
|
| 1852 |
"SA": {
|
| 1853 |
"accuracy": 1.0,
|
| 1854 |
+
"count": 104
|
| 1855 |
},
|
| 1856 |
"SC": {
|
| 1857 |
"accuracy": 1.0,
|
| 1858 |
+
"count": 106
|
| 1859 |
},
|
| 1860 |
"SS": {
|
| 1861 |
"accuracy": 1.0,
|
| 1862 |
+
"count": 23
|
| 1863 |
},
|
| 1864 |
"UC": {
|
| 1865 |
+
"accuracy": 0.9875,
|
| 1866 |
+
"count": 160
|
| 1867 |
},
|
| 1868 |
"US": {
|
| 1869 |
+
"accuracy": 0.990228013029316,
|
| 1870 |
+
"count": 307
|
| 1871 |
}
|
| 1872 |
}
|
| 1873 |
},
|
| 1874 |
"add_S5": {
|
| 1875 |
+
"full_accuracy": 0.75,
|
| 1876 |
+
"n_examples": 100,
|
| 1877 |
"per_subtask": {
|
| 1878 |
"SA": {
|
| 1879 |
"accuracy": 1.0,
|
| 1880 |
+
"count": 100
|
| 1881 |
},
|
| 1882 |
"SC": {
|
| 1883 |
"accuracy": 1.0,
|
| 1884 |
+
"count": 100
|
| 1885 |
},
|
| 1886 |
"UC": {
|
| 1887 |
+
"accuracy": 0.75,
|
| 1888 |
+
"count": 100
|
| 1889 |
},
|
| 1890 |
"US": {
|
| 1891 |
+
"accuracy": 0.9975,
|
| 1892 |
+
"count": 400
|
| 1893 |
}
|
| 1894 |
}
|
| 1895 |
},
|
| 1896 |
"add_S6": {
|
| 1897 |
+
"full_accuracy": 0.52,
|
| 1898 |
+
"n_examples": 100,
|
| 1899 |
"per_subtask": {
|
| 1900 |
"SC": {
|
| 1901 |
"accuracy": 1.0,
|
| 1902 |
+
"count": 100
|
| 1903 |
},
|
| 1904 |
"UC": {
|
| 1905 |
+
"accuracy": 0.53,
|
| 1906 |
+
"count": 100
|
| 1907 |
},
|
| 1908 |
"US": {
|
| 1909 |
+
"accuracy": 0.91,
|
| 1910 |
+
"count": 500
|
| 1911 |
}
|
| 1912 |
}
|
| 1913 |
},
|
| 1914 |
"add_random": {
|
| 1915 |
+
"full_accuracy": 0.995,
|
| 1916 |
"n_examples": 200,
|
| 1917 |
"per_subtask": {
|
| 1918 |
"SA": {
|
| 1919 |
"accuracy": 1.0,
|
| 1920 |
+
"count": 447
|
| 1921 |
},
|
| 1922 |
"SC": {
|
| 1923 |
+
"accuracy": 0.996875,
|
| 1924 |
+
"count": 320
|
| 1925 |
},
|
| 1926 |
"SS": {
|
| 1927 |
"accuracy": 1.0,
|
| 1928 |
+
"count": 56
|
| 1929 |
},
|
| 1930 |
"UC": {
|
| 1931 |
"accuracy": 1.0,
|
| 1932 |
+
"count": 529
|
| 1933 |
},
|
| 1934 |
"US": {
|
| 1935 |
"accuracy": 1.0,
|
| 1936 |
+
"count": 48
|
| 1937 |
}
|
| 1938 |
}
|
| 1939 |
},
|
| 1940 |
"add_C3": {
|
| 1941 |
+
"full_accuracy": 0.98,
|
| 1942 |
+
"n_examples": 100,
|
| 1943 |
"per_subtask": {
|
| 1944 |
"SA": {
|
| 1945 |
"accuracy": 1.0,
|
| 1946 |
+
"count": 300
|
| 1947 |
},
|
| 1948 |
"SC": {
|
| 1949 |
"accuracy": 1.0,
|
| 1950 |
+
"count": 100
|
| 1951 |
},
|
| 1952 |
"UC": {
|
| 1953 |
+
"accuracy": 0.9948186528497409,
|
| 1954 |
+
"count": 193
|
| 1955 |
},
|
| 1956 |
"US": {
|
| 1957 |
+
"accuracy": 0.9906542056074766,
|
| 1958 |
+
"count": 107
|
| 1959 |
}
|
| 1960 |
}
|
| 1961 |
},
|
| 1962 |
"add_C4": {
|
| 1963 |
+
"full_accuracy": 0.98,
|
| 1964 |
+
"n_examples": 100,
|
| 1965 |
"per_subtask": {
|
| 1966 |
"SA": {
|
| 1967 |
"accuracy": 1.0,
|
| 1968 |
+
"count": 200
|
| 1969 |
},
|
| 1970 |
"SC": {
|
| 1971 |
"accuracy": 1.0,
|
| 1972 |
+
"count": 100
|
| 1973 |
},
|
| 1974 |
"UC": {
|
| 1975 |
+
"accuracy": 0.9921875,
|
| 1976 |
+
"count": 256
|
| 1977 |
},
|
| 1978 |
"US": {
|
| 1979 |
"accuracy": 1.0,
|
| 1980 |
+
"count": 144
|
| 1981 |
}
|
| 1982 |
}
|
| 1983 |
},
|
| 1984 |
"add_C5": {
|
| 1985 |
+
"full_accuracy": 0.98,
|
| 1986 |
+
"n_examples": 100,
|
| 1987 |
"per_subtask": {
|
| 1988 |
"SA": {
|
| 1989 |
"accuracy": 1.0,
|
| 1990 |
+
"count": 100
|
| 1991 |
},
|
| 1992 |
"SC": {
|
| 1993 |
"accuracy": 1.0,
|
| 1994 |
+
"count": 100
|
| 1995 |
},
|
| 1996 |
"UC": {
|
| 1997 |
+
"accuracy": 0.9934640522875817,
|
| 1998 |
+
"count": 306
|
| 1999 |
},
|
| 2000 |
"US": {
|
| 2001 |
"accuracy": 1.0,
|
| 2002 |
+
"count": 194
|
| 2003 |
}
|
| 2004 |
}
|
| 2005 |
},
|
| 2006 |
"add_C6": {
|
| 2007 |
"full_accuracy": 1.0,
|
| 2008 |
+
"n_examples": 100,
|
| 2009 |
"per_subtask": {
|
| 2010 |
"SC": {
|
| 2011 |
"accuracy": 1.0,
|
| 2012 |
+
"count": 100
|
| 2013 |
},
|
| 2014 |
"UC": {
|
| 2015 |
"accuracy": 1.0,
|
| 2016 |
+
"count": 366
|
| 2017 |
},
|
| 2018 |
"US": {
|
| 2019 |
"accuracy": 1.0,
|
| 2020 |
+
"count": 234
|
| 2021 |
}
|
| 2022 |
}
|
| 2023 |
},
|
| 2024 |
"sub_M0": {
|
| 2025 |
"full_accuracy": 1.0,
|
| 2026 |
+
"n_examples": 100,
|
| 2027 |
"per_subtask": {
|
| 2028 |
"MD": {
|
| 2029 |
"accuracy": 1.0,
|
| 2030 |
+
"count": 601
|
| 2031 |
},
|
| 2032 |
"ME": {
|
| 2033 |
"accuracy": 1.0,
|
| 2034 |
+
"count": 99
|
| 2035 |
}
|
| 2036 |
}
|
| 2037 |
},
|
| 2038 |
"sub_M1": {
|
| 2039 |
"full_accuracy": 1.0,
|
| 2040 |
+
"n_examples": 100,
|
| 2041 |
"per_subtask": {
|
| 2042 |
"MD": {
|
| 2043 |
"accuracy": 1.0,
|
| 2044 |
+
"count": 279
|
| 2045 |
},
|
| 2046 |
"MB": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
+
"count": 145
|
| 2049 |
},
|
| 2050 |
"ME": {
|
| 2051 |
"accuracy": 1.0,
|
| 2052 |
+
"count": 24
|
| 2053 |
},
|
| 2054 |
"UB": {
|
| 2055 |
"accuracy": 1.0,
|
| 2056 |
+
"count": 252
|
| 2057 |
}
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
"sub_M2": {
|
| 2061 |
"full_accuracy": 1.0,
|
| 2062 |
+
"n_examples": 100,
|
| 2063 |
"per_subtask": {
|
| 2064 |
"MD": {
|
| 2065 |
"accuracy": 1.0,
|
| 2066 |
+
"count": 213
|
| 2067 |
},
|
| 2068 |
"MB": {
|
| 2069 |
"accuracy": 1.0,
|
| 2070 |
+
"count": 113
|
| 2071 |
},
|
| 2072 |
"ME": {
|
| 2073 |
"accuracy": 1.0,
|
| 2074 |
+
"count": 85
|
| 2075 |
},
|
| 2076 |
"UB": {
|
| 2077 |
"accuracy": 1.0,
|
| 2078 |
+
"count": 181
|
| 2079 |
},
|
| 2080 |
"UD": {
|
| 2081 |
"accuracy": 1.0,
|
| 2082 |
+
"count": 108
|
| 2083 |
}
|
| 2084 |
}
|
| 2085 |
},
|
| 2086 |
"sub_M3": {
|
| 2087 |
+
"full_accuracy": 0.98,
|
| 2088 |
+
"n_examples": 100,
|
| 2089 |
"per_subtask": {
|
| 2090 |
"MD": {
|
| 2091 |
"accuracy": 1.0,
|
| 2092 |
+
"count": 179
|
| 2093 |
},
|
| 2094 |
"MB": {
|
| 2095 |
"accuracy": 1.0,
|
| 2096 |
+
"count": 103
|
| 2097 |
},
|
| 2098 |
"ME": {
|
| 2099 |
"accuracy": 1.0,
|
| 2100 |
+
"count": 56
|
| 2101 |
},
|
| 2102 |
"UB": {
|
| 2103 |
+
"accuracy": 0.9865771812080537,
|
| 2104 |
+
"count": 149
|
| 2105 |
},
|
| 2106 |
"UD": {
|
| 2107 |
"accuracy": 1.0,
|
| 2108 |
+
"count": 213
|
| 2109 |
}
|
| 2110 |
}
|
| 2111 |
},
|
| 2112 |
"sub_M4": {
|
| 2113 |
+
"full_accuracy": 0.91,
|
| 2114 |
+
"n_examples": 100,
|
| 2115 |
"per_subtask": {
|
| 2116 |
"MD": {
|
| 2117 |
"accuracy": 1.0,
|
| 2118 |
+
"count": 200
|
| 2119 |
},
|
| 2120 |
"MB": {
|
| 2121 |
"accuracy": 1.0,
|
| 2122 |
+
"count": 100
|
| 2123 |
},
|
| 2124 |
"UB": {
|
| 2125 |
+
"accuracy": 0.96,
|
| 2126 |
+
"count": 100
|
| 2127 |
},
|
| 2128 |
"UD": {
|
| 2129 |
+
"accuracy": 0.9766666666666667,
|
| 2130 |
+
"count": 300
|
| 2131 |
}
|
| 2132 |
}
|
| 2133 |
},
|
| 2134 |
"sub_M5": {
|
| 2135 |
+
"full_accuracy": 0.3,
|
| 2136 |
+
"n_examples": 100,
|
| 2137 |
"per_subtask": {
|
| 2138 |
"MD": {
|
| 2139 |
"accuracy": 1.0,
|
| 2140 |
+
"count": 100
|
| 2141 |
},
|
| 2142 |
"MB": {
|
| 2143 |
"accuracy": 1.0,
|
| 2144 |
+
"count": 100
|
| 2145 |
},
|
| 2146 |
"UB": {
|
| 2147 |
+
"accuracy": 0.32,
|
| 2148 |
+
"count": 100
|
| 2149 |
},
|
| 2150 |
"UD": {
|
| 2151 |
+
"accuracy": 0.9425,
|
| 2152 |
+
"count": 400
|
| 2153 |
}
|
| 2154 |
}
|
| 2155 |
},
|
|
|
|
| 2159 |
"per_subtask": {
|
| 2160 |
"MD": {
|
| 2161 |
"accuracy": 1.0,
|
| 2162 |
+
"count": 600
|
| 2163 |
},
|
| 2164 |
"MB": {
|
| 2165 |
"accuracy": 1.0,
|
| 2166 |
+
"count": 267
|
| 2167 |
},
|
| 2168 |
"ME": {
|
| 2169 |
"accuracy": 1.0,
|
| 2170 |
+
"count": 53
|
| 2171 |
},
|
| 2172 |
"UB": {
|
| 2173 |
"accuracy": 1.0,
|
| 2174 |
+
"count": 439
|
| 2175 |
},
|
| 2176 |
"UD": {
|
| 2177 |
"accuracy": 1.0,
|
| 2178 |
+
"count": 41
|
| 2179 |
}
|
| 2180 |
}
|
| 2181 |
},
|
| 2182 |
"sub_B3": {
|
| 2183 |
+
"full_accuracy": 0.98,
|
| 2184 |
+
"n_examples": 100,
|
| 2185 |
"per_subtask": {
|
| 2186 |
"MD": {
|
| 2187 |
+
"accuracy": 0.9966666666666667,
|
| 2188 |
+
"count": 300
|
| 2189 |
},
|
| 2190 |
"MB": {
|
| 2191 |
"accuracy": 1.0,
|
| 2192 |
+
"count": 100
|
| 2193 |
},
|
| 2194 |
"UB": {
|
| 2195 |
+
"accuracy": 0.9949238578680203,
|
| 2196 |
+
"count": 197
|
| 2197 |
},
|
| 2198 |
"UD": {
|
| 2199 |
"accuracy": 1.0,
|
| 2200 |
+
"count": 103
|
| 2201 |
}
|
| 2202 |
}
|
| 2203 |
},
|
| 2204 |
"sub_B4": {
|
| 2205 |
+
"full_accuracy": 0.98,
|
| 2206 |
+
"n_examples": 100,
|
| 2207 |
"per_subtask": {
|
| 2208 |
"MD": {
|
| 2209 |
"accuracy": 1.0,
|
| 2210 |
+
"count": 200
|
| 2211 |
},
|
| 2212 |
"MB": {
|
| 2213 |
"accuracy": 1.0,
|
| 2214 |
+
"count": 100
|
| 2215 |
},
|
| 2216 |
"UB": {
|
| 2217 |
"accuracy": 1.0,
|
| 2218 |
+
"count": 247
|
| 2219 |
},
|
| 2220 |
"UD": {
|
| 2221 |
+
"accuracy": 0.9869281045751634,
|
| 2222 |
+
"count": 153
|
| 2223 |
}
|
| 2224 |
}
|
| 2225 |
},
|
| 2226 |
"sub_B5": {
|
| 2227 |
+
"full_accuracy": 0.93,
|
| 2228 |
+
"n_examples": 100,
|
| 2229 |
"per_subtask": {
|
| 2230 |
"MD": {
|
| 2231 |
"accuracy": 1.0,
|
| 2232 |
+
"count": 100
|
| 2233 |
},
|
| 2234 |
"MB": {
|
| 2235 |
"accuracy": 1.0,
|
| 2236 |
+
"count": 100
|
| 2237 |
},
|
| 2238 |
"UB": {
|
| 2239 |
+
"accuracy": 0.9765100671140939,
|
| 2240 |
+
"count": 298
|
| 2241 |
},
|
| 2242 |
"UD": {
|
| 2243 |
+
"accuracy": 0.9900990099009901,
|
| 2244 |
+
"count": 202
|
| 2245 |
}
|
| 2246 |
}
|
| 2247 |
}
|
| 2248 |
},
|
| 2249 |
"summary": {
|
| 2250 |
+
"overall_accuracy": 0.9266666666666666,
|
| 2251 |
+
"total_examples": 2400,
|
| 2252 |
"n_splits": 22
|
| 2253 |
}
|
| 2254 |
},
|
| 2255 |
+
"sorl_overall_accuracy": 0.9266666666666666,
|
| 2256 |
+
"sft_overall_accuracy": 0.69875
|
| 2257 |
}
|
add_sub_sorl_v1_abs10_K1_50K/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650303660
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a2c0251ad09fdb996d2fea102a5627dae806ff705f7c530ac476b1e21327481
|
| 3 |
size 650303660
|
add_sub_sorl_v1_abs10_K1_50K/train_config.json
CHANGED
|
@@ -1,35 +1,84 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"ops": "add_sub",
|
| 4 |
-
"n_digits": 6,
|
| 5 |
-
"n_layer": 2,
|
| 6 |
-
"n_head": 3,
|
| 7 |
-
"n_embd": 510,
|
| 8 |
-
"abs_vocab": 10,
|
| 9 |
"K": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"alpha_info_gain": 10.0,
|
| 11 |
"alpha_abs": 0.1,
|
| 12 |
"alpha_soft_zipf": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"batch_size": 64,
|
|
|
|
| 14 |
"num_epochs": 10,
|
| 15 |
-
"
|
| 16 |
-
"
|
|
|
|
|
|
|
|
|
|
| 17 |
"output_dir": "ckpt/sweep/as_sorl_abs10_K1_50K",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"device": "cuda",
|
| 19 |
"push_to_hub": true,
|
| 20 |
"no_wandb": false,
|
| 21 |
"n_params": 162499262,
|
| 22 |
"run_name": "add_sub_sorl_v1_abs10_K1_50K",
|
| 23 |
-
"git_commit": "
|
| 24 |
-
"timestamp": "2026-04-
|
| 25 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 26 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 27 |
"dataset_config": "add_sub_6digit",
|
| 28 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 29 |
"trainer_version": "v1",
|
| 30 |
-
"wandb_run_id": "
|
| 31 |
-
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/
|
| 32 |
-
"final_accuracy":
|
| 33 |
-
"sft_accuracy": 0.
|
| 34 |
"eval_method": "ArithmeticEvaluator"
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"num_rollouts": 4,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"K": 1,
|
| 4 |
+
"max_iterations": 2,
|
| 5 |
+
"memory_span_abs": 1792,
|
| 6 |
+
"memory_span_traj": 1792,
|
| 7 |
+
"temperature": 1.0,
|
| 8 |
+
"ar_search": false,
|
| 9 |
+
"response_only_abs": false,
|
| 10 |
"alpha_info_gain": 10.0,
|
| 11 |
"alpha_abs": 0.1,
|
| 12 |
"alpha_soft_zipf": 1.0,
|
| 13 |
+
"alpha_ortho": 0.0,
|
| 14 |
+
"alpha_anchor": 0.0,
|
| 15 |
+
"alpha_jacobi": 0.0,
|
| 16 |
+
"decay": 0.8,
|
| 17 |
+
"target_vocab_util": 0.8,
|
| 18 |
+
"min_abs_ppl": 0.0,
|
| 19 |
+
"zipf_alpha": 1.0,
|
| 20 |
+
"lr": 4e-05,
|
| 21 |
+
"emb_lr_mult": 1.0,
|
| 22 |
+
"weight_decay": 0.01,
|
| 23 |
+
"warmup_steps": 234,
|
| 24 |
+
"cooldown_frac": 0.4,
|
| 25 |
+
"max_grad_norm": 1.0,
|
| 26 |
+
"vq_abs_pretrain_steps": 0,
|
| 27 |
+
"vq_abs_pretrain_lr": 0.001,
|
| 28 |
+
"vq_abs_pretrain_layer": -1,
|
| 29 |
+
"vq_abs_pretrain_batch_size": 256,
|
| 30 |
+
"vq_abs_pretrain_target_vectors": 20000,
|
| 31 |
"batch_size": 64,
|
| 32 |
+
"gradient_accumulation_steps": 1,
|
| 33 |
"num_epochs": 10,
|
| 34 |
+
"emb_warmup_steps": 0,
|
| 35 |
+
"log_every": 50,
|
| 36 |
+
"eval_every": 781,
|
| 37 |
+
"save_every": 999999,
|
| 38 |
+
"eval_samples": 100,
|
| 39 |
"output_dir": "ckpt/sweep/as_sorl_abs10_K1_50K",
|
| 40 |
+
"eval_K": 4,
|
| 41 |
+
"alpha_traj": 0.0,
|
| 42 |
+
"corrupt_method": "shuffle",
|
| 43 |
+
"corrupt_ratio": 0.3,
|
| 44 |
+
"alpha_contrastive": 1.0,
|
| 45 |
+
"gamma_contrastive": 0.5,
|
| 46 |
+
"alpha_masked_traj": 0.0,
|
| 47 |
+
"mask_nl_ratio": 0.3,
|
| 48 |
+
"mask_nl_mode": "fixed",
|
| 49 |
+
"mask_nl_fixed_id": 0,
|
| 50 |
+
"use_ste": true,
|
| 51 |
+
"n_inner": 1,
|
| 52 |
+
"random_K": null,
|
| 53 |
+
"strip_suffix": null,
|
| 54 |
+
"compress_prefix": null,
|
| 55 |
+
"random_mem_span": null,
|
| 56 |
+
"warmup_ratio": 0.03,
|
| 57 |
+
"beta2": 0.999,
|
| 58 |
+
"seed": 42,
|
| 59 |
+
"n_digits": 6,
|
| 60 |
+
"n_layer": 2,
|
| 61 |
+
"n_head": 3,
|
| 62 |
+
"n_embd": 510,
|
| 63 |
+
"ops": "add_sub",
|
| 64 |
+
"abs_vocab": 10,
|
| 65 |
+
"dataset_size": 50000,
|
| 66 |
+
"mode": "sorl",
|
| 67 |
"device": "cuda",
|
| 68 |
"push_to_hub": true,
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 162499262,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs10_K1_50K",
|
| 72 |
+
"git_commit": "f447da529caceac8c7d256cbb2cd185cbc50feac",
|
| 73 |
+
"timestamp": "2026-04-12T16:03:25.379451+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": "e21wdqti",
|
| 80 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/e21wdqti",
|
| 81 |
+
"final_accuracy": 0.9266666666666666,
|
| 82 |
+
"sft_accuracy": 0.69875,
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|