Upload add_sub_sorl_v1_abs10_K1_25K_1L3H510d
Browse files
add_sub_sorl_v1_abs10_K1_25K_1L3H510d/metrics.json
CHANGED
|
@@ -143,857 +143,857 @@
|
|
| 143 |
7779
|
| 144 |
],
|
| 145 |
"loss": [
|
| 146 |
-
-
|
| 147 |
-
7.
|
| 148 |
-
|
| 149 |
-
3.
|
| 150 |
-
3.
|
| 151 |
-
|
| 152 |
-
3.
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
-
|
| 157 |
-
-
|
| 158 |
-
-
|
| 159 |
-
-
|
| 160 |
-
-
|
| 161 |
-
-
|
| 162 |
-
-
|
| 163 |
-
-
|
| 164 |
-
-
|
| 165 |
-
-
|
| 166 |
-
-
|
| 167 |
-
-
|
| 168 |
-
-
|
| 169 |
-
-
|
| 170 |
-
|
| 171 |
-
-
|
| 172 |
-
-
|
| 173 |
-
|
| 174 |
-
-
|
| 175 |
-
-
|
| 176 |
-
-
|
| 177 |
-
-
|
| 178 |
-
-
|
| 179 |
-
-
|
| 180 |
-
-
|
| 181 |
-
-
|
| 182 |
-
-
|
| 183 |
-
-
|
| 184 |
-
-
|
| 185 |
-
-
|
| 186 |
-
-
|
| 187 |
-
-
|
| 188 |
-
-
|
| 189 |
-
-
|
| 190 |
-
-
|
| 191 |
-
-
|
| 192 |
-
-
|
| 193 |
-
-
|
| 194 |
-
-
|
| 195 |
-
-
|
| 196 |
-
-
|
| 197 |
-
-
|
| 198 |
-
-
|
| 199 |
-
-
|
| 200 |
-
-
|
| 201 |
-
-
|
| 202 |
-
-0.
|
| 203 |
-
-
|
| 204 |
-
-
|
| 205 |
-
-
|
| 206 |
-
-0.
|
| 207 |
-
-0.
|
| 208 |
-
-0.
|
| 209 |
-
-0.
|
| 210 |
-
-
|
| 211 |
-
-0.
|
| 212 |
-
-0.
|
| 213 |
-
-0.
|
| 214 |
-
-0.
|
| 215 |
-
-0.
|
| 216 |
-
-0.
|
| 217 |
-
-0.
|
| 218 |
-
-0.
|
| 219 |
-
-0.
|
| 220 |
-
-0.
|
| 221 |
-
-0.
|
| 222 |
-
-0.
|
| 223 |
-
-0.
|
| 224 |
-
-0.
|
| 225 |
-
0.
|
| 226 |
-
-0.
|
| 227 |
-
-0.
|
| 228 |
-
-0.
|
| 229 |
-
-0.
|
| 230 |
-
-0.
|
| 231 |
-
-0.
|
| 232 |
-
-0.
|
| 233 |
-
-0.
|
| 234 |
-
-0.
|
| 235 |
-
-0.
|
| 236 |
-
-0.
|
| 237 |
-
-0.
|
| 238 |
-
-0.
|
| 239 |
-
-0.
|
| 240 |
-
-0.
|
| 241 |
-
-0.
|
| 242 |
-
-0.
|
| 243 |
-
-0.
|
| 244 |
-
-0.
|
| 245 |
-
|
| 246 |
-
-0.
|
| 247 |
-
-0.
|
| 248 |
-
-0.
|
| 249 |
-
|
| 250 |
-
-0.
|
| 251 |
-
-0.
|
| 252 |
-
-0.
|
| 253 |
-
-0.
|
| 254 |
-
-0.
|
| 255 |
-
-0.
|
| 256 |
-
-0.
|
| 257 |
-
-0.
|
| 258 |
-
-0.
|
| 259 |
-
|
| 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 |
],
|
| 287 |
"base_loss": [
|
| 288 |
-
10.
|
| 289 |
-
6.
|
| 290 |
-
3.
|
| 291 |
-
|
| 292 |
-
1.
|
| 293 |
-
1.
|
| 294 |
-
1.
|
| 295 |
-
1.
|
| 296 |
-
|
| 297 |
-
1.
|
| 298 |
-
1.
|
| 299 |
-
1.
|
| 300 |
-
1.
|
| 301 |
-
1.
|
| 302 |
-
1.
|
| 303 |
-
1.
|
| 304 |
-
1.
|
| 305 |
-
1.
|
| 306 |
-
1.
|
| 307 |
-
1.
|
| 308 |
-
|
| 309 |
-
|
| 310 |
-
|
| 311 |
-
|
| 312 |
-
|
| 313 |
-
|
| 314 |
-
|
| 315 |
-
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
| 319 |
-
|
| 320 |
-
|
| 321 |
-
|
| 322 |
-
|
| 323 |
-
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
|
| 327 |
-
|
| 328 |
-
|
| 329 |
-
|
| 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 |
-
0.
|
| 414 |
-
0.
|
| 415 |
-
0.
|
| 416 |
-
0.
|
| 417 |
-
0.
|
| 418 |
-
0.
|
| 419 |
-
0.
|
| 420 |
-
0.
|
| 421 |
-
0.
|
| 422 |
-
0.
|
| 423 |
-
0.
|
| 424 |
-
0.
|
| 425 |
-
0.
|
| 426 |
-
0.
|
| 427 |
-
0.
|
| 428 |
],
|
| 429 |
"info_loss": [
|
| 430 |
-
-2.
|
| 431 |
-
-0.
|
| 432 |
-
-0.
|
| 433 |
-
-0.
|
| 434 |
-
-0.
|
| 435 |
-
-0.
|
| 436 |
-
-0.
|
| 437 |
-
-0.
|
| 438 |
-
-0.
|
| 439 |
-
-0.
|
| 440 |
-
-0.
|
| 441 |
-
-
|
| 442 |
-
-
|
| 443 |
-
-1.
|
| 444 |
-
-1.
|
| 445 |
-
-
|
| 446 |
-
-
|
| 447 |
-
-
|
| 448 |
-
-
|
| 449 |
-
-
|
| 450 |
-
-
|
| 451 |
-
-
|
| 452 |
-
-
|
| 453 |
-
-
|
| 454 |
-
-
|
| 455 |
-
-
|
| 456 |
-
-
|
| 457 |
-
-
|
| 458 |
-
-
|
| 459 |
-
-
|
| 460 |
-
-
|
| 461 |
-
-
|
| 462 |
-
-
|
| 463 |
-
-
|
| 464 |
-
-
|
| 465 |
-
-
|
| 466 |
-
-
|
| 467 |
-
-
|
| 468 |
-
-
|
| 469 |
-
-
|
| 470 |
-
-
|
| 471 |
-
-
|
| 472 |
-
-0.
|
| 473 |
-
-0.
|
| 474 |
-
-0.
|
| 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 |
-
-0.
|
| 566 |
-
-0.
|
| 567 |
-
-0.
|
| 568 |
-
-0.
|
| 569 |
-
-0.
|
| 570 |
],
|
| 571 |
"abs_loss": [
|
| 572 |
-
2.
|
| 573 |
-
2.
|
| 574 |
-
1.
|
| 575 |
-
1.
|
| 576 |
-
1.
|
| 577 |
-
1.
|
| 578 |
-
1.
|
| 579 |
-
1.
|
| 580 |
-
1.
|
| 581 |
-
1.
|
| 582 |
-
1.
|
| 583 |
-
1.
|
| 584 |
-
1.
|
| 585 |
-
1.
|
| 586 |
-
1.
|
| 587 |
-
1.
|
| 588 |
-
1.
|
| 589 |
-
1.
|
| 590 |
-
|
| 591 |
-
0.
|
| 592 |
-
0.
|
| 593 |
-
0.
|
| 594 |
-
0.
|
| 595 |
-
0.
|
| 596 |
-
0.
|
| 597 |
-
0.
|
| 598 |
-
0.
|
| 599 |
-
0.
|
| 600 |
-
0.
|
| 601 |
-
0.
|
| 602 |
-
0.
|
| 603 |
-
0.
|
| 604 |
-
0.
|
| 605 |
-
0.
|
| 606 |
-
0.
|
| 607 |
-
0.
|
| 608 |
-
0.
|
| 609 |
-
0.
|
| 610 |
-
0.
|
| 611 |
-
0.
|
| 612 |
-
0.
|
| 613 |
-
0.
|
| 614 |
-
0.
|
| 615 |
-
0.
|
| 616 |
-
0.
|
| 617 |
-
0.
|
| 618 |
-
0.
|
| 619 |
-
0.
|
| 620 |
-
0.
|
| 621 |
-
0.
|
| 622 |
-
0.
|
| 623 |
-
0.
|
| 624 |
-
0.
|
| 625 |
-
0.
|
| 626 |
-
0.
|
| 627 |
-
0.
|
| 628 |
-
0.
|
| 629 |
-
0.
|
| 630 |
-
0.
|
| 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 |
],
|
| 713 |
"zipf_loss": [
|
| 714 |
-
8.
|
| 715 |
-
4.
|
| 716 |
-
|
| 717 |
-
1.
|
| 718 |
-
1.
|
| 719 |
-
1.
|
| 720 |
-
1.
|
| 721 |
-
1.
|
| 722 |
-
1.
|
| 723 |
-
1.
|
| 724 |
-
1.
|
| 725 |
-
1.
|
| 726 |
-
1.
|
| 727 |
-
1.
|
| 728 |
-
1.
|
| 729 |
-
1.
|
| 730 |
-
1.
|
| 731 |
-
1.
|
| 732 |
-
1.
|
| 733 |
-
1.
|
| 734 |
-
1.
|
| 735 |
-
0.
|
| 736 |
-
0.
|
| 737 |
-
0.
|
| 738 |
-
0.
|
| 739 |
-
0.
|
| 740 |
-
0.
|
| 741 |
-
0.
|
| 742 |
-
0.
|
| 743 |
-
0.
|
| 744 |
-
0.
|
| 745 |
-
0.
|
| 746 |
-
0.
|
| 747 |
-
0.
|
| 748 |
-
0.
|
| 749 |
-
0.
|
| 750 |
-
0.
|
| 751 |
-
0.
|
| 752 |
-
0.
|
| 753 |
-
0.
|
| 754 |
-
0.
|
| 755 |
-
0.
|
| 756 |
-
0.
|
| 757 |
-
0.
|
| 758 |
-
0.
|
| 759 |
-
0.
|
| 760 |
-
0.
|
| 761 |
-
0.
|
| 762 |
-
0.
|
| 763 |
-
0.
|
| 764 |
-
0.
|
| 765 |
-
0.
|
| 766 |
-
0.
|
| 767 |
-
0.
|
| 768 |
-
0.
|
| 769 |
-
0.
|
| 770 |
-
0.
|
| 771 |
-
0.
|
| 772 |
-
0.
|
| 773 |
-
0.
|
| 774 |
-
0.
|
| 775 |
-
0.
|
| 776 |
-
0.
|
| 777 |
-
0.
|
| 778 |
-
0.
|
| 779 |
-
0.
|
| 780 |
-
0.
|
| 781 |
-
0.
|
| 782 |
-
0.
|
| 783 |
-
0.
|
| 784 |
-
0.
|
| 785 |
-
0.
|
| 786 |
-
0.
|
| 787 |
-
0.
|
| 788 |
-
0.
|
| 789 |
-
0.
|
| 790 |
-
0.
|
| 791 |
-
0.
|
| 792 |
-
0.
|
| 793 |
-
0.
|
| 794 |
-
0.
|
| 795 |
-
0.
|
| 796 |
-
0.
|
| 797 |
-
0.
|
| 798 |
-
0.
|
| 799 |
-
0.
|
| 800 |
-
0.
|
| 801 |
-
0.
|
| 802 |
-
0.
|
| 803 |
-
0.
|
| 804 |
-
0.
|
| 805 |
-
0.
|
| 806 |
-
0.
|
| 807 |
-
0.
|
| 808 |
-
0.
|
| 809 |
-
0.
|
| 810 |
-
0.
|
| 811 |
-
0.
|
| 812 |
-
0.
|
| 813 |
-
0.
|
| 814 |
-
0.
|
| 815 |
-
0.
|
| 816 |
-
0.
|
| 817 |
-
0.
|
| 818 |
-
0.
|
| 819 |
-
0.
|
| 820 |
-
0.
|
| 821 |
-
0.
|
| 822 |
-
0.
|
| 823 |
-
0.
|
| 824 |
-
0.
|
| 825 |
-
0.
|
| 826 |
-
0.
|
| 827 |
-
0.
|
| 828 |
-
0.
|
| 829 |
-
0.
|
| 830 |
-
0.
|
| 831 |
-
0.
|
| 832 |
-
0.
|
| 833 |
-
0.
|
| 834 |
-
0.
|
| 835 |
-
0.
|
| 836 |
-
0.
|
| 837 |
-
0.
|
| 838 |
-
0.
|
| 839 |
-
0.
|
| 840 |
-
0.
|
| 841 |
-
0.
|
| 842 |
-
0.
|
| 843 |
-
0.
|
| 844 |
-
0.
|
| 845 |
-
0.
|
| 846 |
-
0.
|
| 847 |
-
0.
|
| 848 |
-
0.
|
| 849 |
-
0.
|
| 850 |
-
0.
|
| 851 |
-
0.
|
| 852 |
-
0.
|
| 853 |
-
0.
|
| 854 |
],
|
| 855 |
"denoise_loss": [],
|
| 856 |
"ortho_loss": [
|
| 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 |
-
0.
|
| 915 |
-
0.
|
| 916 |
-
0.
|
| 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 |
],
|
| 998 |
"lr": [
|
| 999 |
1.6752136752136756e-05,
|
|
@@ -1161,7 +1161,7 @@
|
|
| 1161 |
7779
|
| 1162 |
],
|
| 1163 |
"eval_accuracy": [
|
| 1164 |
-
0.
|
| 1165 |
0.0,
|
| 1166 |
0.0,
|
| 1167 |
0.0,
|
|
@@ -1183,573 +1183,573 @@
|
|
| 1183 |
0.0
|
| 1184 |
]
|
| 1185 |
},
|
| 1186 |
-
"final_accuracy": 0.
|
| 1187 |
"sft_eval": {
|
| 1188 |
"config": {
|
| 1189 |
"ops": "add_sub",
|
| 1190 |
"K": null,
|
| 1191 |
"mode": "sft",
|
| 1192 |
"n_digits": 6,
|
| 1193 |
-
"n_per_split":
|
| 1194 |
},
|
| 1195 |
"splits": {
|
| 1196 |
"add_S0": {
|
| 1197 |
-
"full_accuracy": 0.
|
| 1198 |
-
"digit_accuracy": 0.
|
| 1199 |
-
"n_examples":
|
| 1200 |
"per_subtask": {
|
| 1201 |
"SA": {
|
| 1202 |
-
"accuracy": 0.
|
| 1203 |
-
"count":
|
| 1204 |
},
|
| 1205 |
"SS": {
|
| 1206 |
"accuracy": 1.0,
|
| 1207 |
-
"count":
|
| 1208 |
}
|
| 1209 |
}
|
| 1210 |
},
|
| 1211 |
"add_S1": {
|
| 1212 |
-
"full_accuracy": 0.
|
| 1213 |
-
"digit_accuracy": 0.
|
| 1214 |
-
"n_examples":
|
| 1215 |
"per_subtask": {
|
| 1216 |
"SA": {
|
| 1217 |
-
"accuracy": 0.
|
| 1218 |
-
"count":
|
| 1219 |
},
|
| 1220 |
"SC": {
|
| 1221 |
-
"accuracy": 0.
|
| 1222 |
-
"count":
|
| 1223 |
},
|
| 1224 |
"SS": {
|
| 1225 |
-
"accuracy":
|
| 1226 |
-
"count":
|
| 1227 |
},
|
| 1228 |
"UC": {
|
| 1229 |
-
"accuracy": 0.
|
| 1230 |
-
"count":
|
| 1231 |
}
|
| 1232 |
}
|
| 1233 |
},
|
| 1234 |
"add_S2": {
|
| 1235 |
-
"full_accuracy": 0.
|
| 1236 |
-
"digit_accuracy": 0.
|
| 1237 |
-
"n_examples":
|
| 1238 |
"per_subtask": {
|
| 1239 |
"SA": {
|
| 1240 |
-
"accuracy": 0.
|
| 1241 |
-
"count":
|
| 1242 |
},
|
| 1243 |
"SC": {
|
| 1244 |
-
"accuracy": 0.
|
| 1245 |
-
"count":
|
| 1246 |
},
|
| 1247 |
"SS": {
|
| 1248 |
-
"accuracy": 0.
|
| 1249 |
-
"count":
|
| 1250 |
},
|
| 1251 |
"UC": {
|
| 1252 |
-
"accuracy": 0.
|
| 1253 |
-
"count":
|
| 1254 |
},
|
| 1255 |
"US": {
|
| 1256 |
-
"accuracy": 0.
|
| 1257 |
-
"count":
|
| 1258 |
}
|
| 1259 |
}
|
| 1260 |
},
|
| 1261 |
"add_S3": {
|
| 1262 |
-
"full_accuracy": 0.
|
| 1263 |
-
"digit_accuracy": 0.
|
| 1264 |
-
"n_examples":
|
| 1265 |
"per_subtask": {
|
| 1266 |
"SA": {
|
| 1267 |
"accuracy": 1.0,
|
| 1268 |
-
"count":
|
| 1269 |
},
|
| 1270 |
"SC": {
|
| 1271 |
-
"accuracy": 0.
|
| 1272 |
-
"count":
|
| 1273 |
},
|
| 1274 |
"SS": {
|
| 1275 |
"accuracy": 1.0,
|
| 1276 |
-
"count":
|
| 1277 |
},
|
| 1278 |
"UC": {
|
| 1279 |
-
"accuracy": 0.
|
| 1280 |
-
"count":
|
| 1281 |
},
|
| 1282 |
"US": {
|
| 1283 |
-
"accuracy": 0.
|
| 1284 |
-
"count":
|
| 1285 |
}
|
| 1286 |
}
|
| 1287 |
},
|
| 1288 |
"add_S4": {
|
| 1289 |
-
"full_accuracy": 0.
|
| 1290 |
-
"digit_accuracy": 0.
|
| 1291 |
-
"n_examples":
|
| 1292 |
"per_subtask": {
|
| 1293 |
"SA": {
|
| 1294 |
"accuracy": 1.0,
|
| 1295 |
-
"count":
|
| 1296 |
},
|
| 1297 |
"SC": {
|
| 1298 |
"accuracy": 1.0,
|
| 1299 |
-
"count":
|
| 1300 |
},
|
| 1301 |
"SS": {
|
| 1302 |
"accuracy": 1.0,
|
| 1303 |
-
"count":
|
| 1304 |
},
|
| 1305 |
"UC": {
|
| 1306 |
-
"accuracy": 0.
|
| 1307 |
-
"count":
|
| 1308 |
},
|
| 1309 |
"US": {
|
| 1310 |
-
"accuracy": 0.
|
| 1311 |
-
"count":
|
| 1312 |
}
|
| 1313 |
}
|
| 1314 |
},
|
| 1315 |
"add_S5": {
|
| 1316 |
-
"full_accuracy": 0.
|
| 1317 |
-
"digit_accuracy": 0.
|
| 1318 |
-
"n_examples":
|
| 1319 |
"per_subtask": {
|
| 1320 |
"SA": {
|
| 1321 |
"accuracy": 1.0,
|
| 1322 |
-
"count":
|
| 1323 |
},
|
| 1324 |
"SC": {
|
| 1325 |
"accuracy": 1.0,
|
| 1326 |
-
"count":
|
| 1327 |
},
|
| 1328 |
"UC": {
|
| 1329 |
-
"accuracy": 0.
|
| 1330 |
-
"count":
|
| 1331 |
},
|
| 1332 |
"US": {
|
| 1333 |
-
"accuracy": 0.
|
| 1334 |
-
"count":
|
| 1335 |
}
|
| 1336 |
}
|
| 1337 |
},
|
| 1338 |
"add_S6": {
|
| 1339 |
-
"full_accuracy": 0.
|
| 1340 |
-
"digit_accuracy": 0.
|
| 1341 |
-
"n_examples":
|
| 1342 |
"per_subtask": {
|
| 1343 |
"SC": {
|
| 1344 |
"accuracy": 1.0,
|
| 1345 |
-
"count":
|
| 1346 |
},
|
| 1347 |
"UC": {
|
| 1348 |
-
"accuracy": 0.
|
| 1349 |
-
"count":
|
| 1350 |
},
|
| 1351 |
"US": {
|
| 1352 |
-
"accuracy": 0.
|
| 1353 |
-
"count":
|
| 1354 |
}
|
| 1355 |
}
|
| 1356 |
},
|
| 1357 |
"add_random": {
|
| 1358 |
-
"full_accuracy": 0.
|
| 1359 |
-
"digit_accuracy": 0.
|
| 1360 |
"n_examples": 200,
|
| 1361 |
"per_subtask": {
|
| 1362 |
"SA": {
|
| 1363 |
-
"accuracy": 0.
|
| 1364 |
-
"count":
|
| 1365 |
},
|
| 1366 |
"SC": {
|
| 1367 |
-
"accuracy": 0.
|
| 1368 |
-
"count":
|
| 1369 |
},
|
| 1370 |
"SS": {
|
| 1371 |
-
"accuracy": 0.
|
| 1372 |
-
"count":
|
| 1373 |
},
|
| 1374 |
"UC": {
|
| 1375 |
-
"accuracy": 0.
|
| 1376 |
-
"count":
|
| 1377 |
},
|
| 1378 |
"US": {
|
| 1379 |
-
"accuracy":
|
| 1380 |
-
"count":
|
| 1381 |
}
|
| 1382 |
}
|
| 1383 |
},
|
| 1384 |
"add_C1": {
|
| 1385 |
-
"full_accuracy": 0.
|
| 1386 |
-
"digit_accuracy": 0.
|
| 1387 |
-
"n_examples":
|
| 1388 |
"per_subtask": {
|
| 1389 |
"SA": {
|
| 1390 |
"accuracy": 1.0,
|
| 1391 |
-
"count":
|
| 1392 |
},
|
| 1393 |
"SC": {
|
| 1394 |
"accuracy": 1.0,
|
| 1395 |
-
"count":
|
| 1396 |
},
|
| 1397 |
"UC": {
|
| 1398 |
-
"accuracy": 0.
|
| 1399 |
-
"count":
|
| 1400 |
}
|
| 1401 |
}
|
| 1402 |
},
|
| 1403 |
"add_C2": {
|
| 1404 |
"full_accuracy": 0.84,
|
| 1405 |
-
"digit_accuracy": 0.
|
| 1406 |
-
"n_examples":
|
| 1407 |
"per_subtask": {
|
| 1408 |
"SA": {
|
| 1409 |
"accuracy": 1.0,
|
| 1410 |
-
"count":
|
| 1411 |
},
|
| 1412 |
"SC": {
|
| 1413 |
"accuracy": 1.0,
|
| 1414 |
-
"count":
|
| 1415 |
},
|
| 1416 |
"UC": {
|
| 1417 |
-
"accuracy": 0.
|
| 1418 |
-
"count":
|
| 1419 |
},
|
| 1420 |
"US": {
|
| 1421 |
-
"accuracy": 0.
|
| 1422 |
-
"count":
|
| 1423 |
}
|
| 1424 |
}
|
| 1425 |
},
|
| 1426 |
"add_C3": {
|
| 1427 |
-
"full_accuracy": 0.
|
| 1428 |
-
"digit_accuracy": 0.
|
| 1429 |
-
"n_examples":
|
| 1430 |
"per_subtask": {
|
| 1431 |
"SA": {
|
| 1432 |
"accuracy": 1.0,
|
| 1433 |
-
"count":
|
| 1434 |
},
|
| 1435 |
"SC": {
|
| 1436 |
"accuracy": 1.0,
|
| 1437 |
-
"count":
|
| 1438 |
},
|
| 1439 |
"UC": {
|
| 1440 |
-
"accuracy": 0.
|
| 1441 |
-
"count":
|
| 1442 |
},
|
| 1443 |
"US": {
|
| 1444 |
-
"accuracy": 0.
|
| 1445 |
-
"count":
|
| 1446 |
}
|
| 1447 |
}
|
| 1448 |
},
|
| 1449 |
"add_C4": {
|
| 1450 |
-
"full_accuracy": 0.
|
| 1451 |
-
"digit_accuracy": 0.
|
| 1452 |
-
"n_examples":
|
| 1453 |
"per_subtask": {
|
| 1454 |
"SA": {
|
| 1455 |
"accuracy": 1.0,
|
| 1456 |
-
"count":
|
| 1457 |
},
|
| 1458 |
"SC": {
|
| 1459 |
"accuracy": 1.0,
|
| 1460 |
-
"count":
|
| 1461 |
},
|
| 1462 |
"UC": {
|
| 1463 |
-
"accuracy": 0.
|
| 1464 |
-
"count":
|
| 1465 |
},
|
| 1466 |
"US": {
|
| 1467 |
-
"accuracy": 0.
|
| 1468 |
-
"count":
|
| 1469 |
}
|
| 1470 |
}
|
| 1471 |
},
|
| 1472 |
"add_C5": {
|
| 1473 |
-
"full_accuracy": 0.
|
| 1474 |
-
"digit_accuracy": 0.
|
| 1475 |
-
"n_examples":
|
| 1476 |
"per_subtask": {
|
| 1477 |
"SA": {
|
| 1478 |
"accuracy": 1.0,
|
| 1479 |
-
"count":
|
| 1480 |
},
|
| 1481 |
"SC": {
|
| 1482 |
"accuracy": 1.0,
|
| 1483 |
-
"count":
|
| 1484 |
},
|
| 1485 |
"UC": {
|
| 1486 |
-
"accuracy": 0.
|
| 1487 |
-
"count":
|
| 1488 |
},
|
| 1489 |
"US": {
|
| 1490 |
-
"accuracy": 0.
|
| 1491 |
-
"count":
|
| 1492 |
}
|
| 1493 |
}
|
| 1494 |
},
|
| 1495 |
"add_C6": {
|
| 1496 |
-
"full_accuracy": 0.
|
| 1497 |
-
"digit_accuracy": 0.
|
| 1498 |
-
"n_examples":
|
| 1499 |
"per_subtask": {
|
| 1500 |
"SC": {
|
| 1501 |
"accuracy": 1.0,
|
| 1502 |
-
"count":
|
| 1503 |
},
|
| 1504 |
"UC": {
|
| 1505 |
-
"accuracy": 0.
|
| 1506 |
-
"count":
|
| 1507 |
},
|
| 1508 |
"US": {
|
| 1509 |
-
"accuracy": 0.
|
| 1510 |
-
"count":
|
| 1511 |
}
|
| 1512 |
}
|
| 1513 |
},
|
| 1514 |
"sub_M0": {
|
| 1515 |
-
"full_accuracy": 0.
|
| 1516 |
-
"digit_accuracy": 0.
|
| 1517 |
-
"n_examples":
|
| 1518 |
"per_subtask": {
|
| 1519 |
"MD": {
|
| 1520 |
-
"accuracy": 0.
|
| 1521 |
-
"count":
|
| 1522 |
},
|
| 1523 |
"ME": {
|
| 1524 |
"accuracy": 1.0,
|
| 1525 |
-
"count":
|
| 1526 |
}
|
| 1527 |
}
|
| 1528 |
},
|
| 1529 |
"sub_M1": {
|
| 1530 |
-
"full_accuracy": 0.
|
| 1531 |
-
"digit_accuracy": 0.
|
| 1532 |
-
"n_examples":
|
| 1533 |
"per_subtask": {
|
| 1534 |
"MD": {
|
| 1535 |
-
"accuracy":
|
| 1536 |
-
"count":
|
| 1537 |
},
|
| 1538 |
"MB": {
|
| 1539 |
-
"accuracy": 0.
|
| 1540 |
-
"count":
|
| 1541 |
},
|
| 1542 |
"ME": {
|
| 1543 |
-
"accuracy":
|
| 1544 |
-
"count":
|
| 1545 |
},
|
| 1546 |
"UB": {
|
| 1547 |
-
"accuracy": 0.
|
| 1548 |
-
"count":
|
| 1549 |
}
|
| 1550 |
}
|
| 1551 |
},
|
| 1552 |
"sub_M2": {
|
| 1553 |
-
"full_accuracy": 0.
|
| 1554 |
-
"digit_accuracy": 0.
|
| 1555 |
-
"n_examples":
|
| 1556 |
"per_subtask": {
|
| 1557 |
"MD": {
|
| 1558 |
-
"accuracy": 0.
|
| 1559 |
-
"count":
|
| 1560 |
},
|
| 1561 |
"MB": {
|
| 1562 |
-
"accuracy": 0.
|
| 1563 |
-
"count":
|
| 1564 |
},
|
| 1565 |
"ME": {
|
| 1566 |
-
"accuracy": 0.
|
| 1567 |
-
"count":
|
| 1568 |
},
|
| 1569 |
"UB": {
|
| 1570 |
-
"accuracy": 0.
|
| 1571 |
-
"count":
|
| 1572 |
},
|
| 1573 |
"UD": {
|
| 1574 |
-
"accuracy":
|
| 1575 |
-
"count":
|
| 1576 |
}
|
| 1577 |
}
|
| 1578 |
},
|
| 1579 |
"sub_M3": {
|
| 1580 |
-
"full_accuracy": 0.
|
| 1581 |
-
"digit_accuracy": 0.
|
| 1582 |
-
"n_examples":
|
| 1583 |
"per_subtask": {
|
| 1584 |
"MD": {
|
| 1585 |
-
"accuracy": 0.
|
| 1586 |
-
"count":
|
| 1587 |
},
|
| 1588 |
"MB": {
|
| 1589 |
-
"accuracy": 0.
|
| 1590 |
-
"count":
|
| 1591 |
},
|
| 1592 |
"ME": {
|
| 1593 |
"accuracy": 1.0,
|
| 1594 |
-
"count":
|
| 1595 |
},
|
| 1596 |
"UB": {
|
| 1597 |
-
"accuracy": 0.
|
| 1598 |
-
"count":
|
| 1599 |
},
|
| 1600 |
"UD": {
|
| 1601 |
-
"accuracy": 0.
|
| 1602 |
-
"count":
|
| 1603 |
}
|
| 1604 |
}
|
| 1605 |
},
|
| 1606 |
"sub_M4": {
|
| 1607 |
-
"full_accuracy": 0.
|
| 1608 |
-
"digit_accuracy": 0.
|
| 1609 |
-
"n_examples":
|
| 1610 |
"per_subtask": {
|
| 1611 |
"MD": {
|
| 1612 |
"accuracy": 1.0,
|
| 1613 |
-
"count":
|
| 1614 |
},
|
| 1615 |
"MB": {
|
| 1616 |
"accuracy": 1.0,
|
| 1617 |
-
"count":
|
| 1618 |
},
|
| 1619 |
"UB": {
|
| 1620 |
-
"accuracy": 0.
|
| 1621 |
-
"count":
|
| 1622 |
},
|
| 1623 |
"UD": {
|
| 1624 |
-
"accuracy": 0.
|
| 1625 |
-
"count":
|
| 1626 |
}
|
| 1627 |
}
|
| 1628 |
},
|
| 1629 |
"sub_M5": {
|
| 1630 |
-
"full_accuracy": 0.
|
| 1631 |
-
"digit_accuracy": 0.
|
| 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": 0.
|
| 1644 |
-
"count":
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
-
"accuracy": 0.
|
| 1648 |
-
"count":
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
-
"full_accuracy": 0.
|
| 1654 |
-
"digit_accuracy": 0.
|
| 1655 |
"n_examples": 200,
|
| 1656 |
"per_subtask": {
|
| 1657 |
"MD": {
|
| 1658 |
-
"accuracy": 0.
|
| 1659 |
-
"count":
|
| 1660 |
},
|
| 1661 |
"MB": {
|
| 1662 |
-
"accuracy": 0.
|
| 1663 |
-
"count":
|
| 1664 |
},
|
| 1665 |
"ME": {
|
| 1666 |
"accuracy": 1.0,
|
| 1667 |
"count": 53
|
| 1668 |
},
|
| 1669 |
"UB": {
|
| 1670 |
-
"accuracy": 0.
|
| 1671 |
-
"count":
|
| 1672 |
},
|
| 1673 |
"UD": {
|
| 1674 |
-
"accuracy": 0.
|
| 1675 |
-
"count":
|
| 1676 |
}
|
| 1677 |
}
|
| 1678 |
},
|
| 1679 |
"sub_B3": {
|
| 1680 |
-
"full_accuracy": 0.
|
| 1681 |
-
"digit_accuracy": 0.
|
| 1682 |
-
"n_examples":
|
| 1683 |
"per_subtask": {
|
| 1684 |
"MD": {
|
| 1685 |
-
"accuracy":
|
| 1686 |
-
"count":
|
| 1687 |
},
|
| 1688 |
"MB": {
|
| 1689 |
-
"accuracy":
|
| 1690 |
-
"count":
|
| 1691 |
},
|
| 1692 |
"UB": {
|
| 1693 |
-
"accuracy": 0.
|
| 1694 |
-
"count":
|
| 1695 |
},
|
| 1696 |
"UD": {
|
| 1697 |
-
"accuracy": 0.
|
| 1698 |
-
"count":
|
| 1699 |
}
|
| 1700 |
}
|
| 1701 |
},
|
| 1702 |
"sub_B4": {
|
| 1703 |
-
"full_accuracy": 0.
|
| 1704 |
-
"digit_accuracy": 0.
|
| 1705 |
-
"n_examples":
|
| 1706 |
"per_subtask": {
|
| 1707 |
"MD": {
|
| 1708 |
-
"accuracy":
|
| 1709 |
-
"count":
|
| 1710 |
},
|
| 1711 |
"MB": {
|
| 1712 |
-
"accuracy":
|
| 1713 |
-
"count":
|
| 1714 |
},
|
| 1715 |
"UB": {
|
| 1716 |
-
"accuracy": 0.
|
| 1717 |
-
"count":
|
| 1718 |
},
|
| 1719 |
"UD": {
|
| 1720 |
-
"accuracy": 0.
|
| 1721 |
-
"count":
|
| 1722 |
}
|
| 1723 |
}
|
| 1724 |
},
|
| 1725 |
"sub_B5": {
|
| 1726 |
-
"full_accuracy": 0.
|
| 1727 |
-
"digit_accuracy": 0.
|
| 1728 |
-
"n_examples":
|
| 1729 |
"per_subtask": {
|
| 1730 |
"MD": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
-
"count":
|
| 1733 |
},
|
| 1734 |
"MB": {
|
| 1735 |
"accuracy": 1.0,
|
| 1736 |
-
"count":
|
| 1737 |
},
|
| 1738 |
"UB": {
|
| 1739 |
-
"accuracy": 0.
|
| 1740 |
-
"count":
|
| 1741 |
},
|
| 1742 |
"UD": {
|
| 1743 |
-
"accuracy": 0.
|
| 1744 |
-
"count":
|
| 1745 |
}
|
| 1746 |
}
|
| 1747 |
}
|
| 1748 |
},
|
| 1749 |
"summary": {
|
| 1750 |
-
"overall_accuracy": 0.
|
| 1751 |
-
"digit_accuracy": 0.
|
| 1752 |
-
"total_examples":
|
| 1753 |
"n_splits": 24
|
| 1754 |
}
|
| 1755 |
},
|
|
@@ -1759,569 +1759,569 @@
|
|
| 1759 |
"K": 1,
|
| 1760 |
"mode": "sorl",
|
| 1761 |
"n_digits": 6,
|
| 1762 |
-
"n_per_split":
|
| 1763 |
},
|
| 1764 |
"splits": {
|
| 1765 |
"add_S0": {
|
| 1766 |
-
"full_accuracy": 0.
|
| 1767 |
-
"digit_accuracy": 0.
|
| 1768 |
-
"n_examples":
|
| 1769 |
"per_subtask": {
|
| 1770 |
"SA": {
|
| 1771 |
-
"accuracy": 0.
|
| 1772 |
-
"count":
|
| 1773 |
},
|
| 1774 |
"SS": {
|
| 1775 |
-
"accuracy":
|
| 1776 |
-
"count":
|
| 1777 |
}
|
| 1778 |
}
|
| 1779 |
},
|
| 1780 |
"add_S1": {
|
| 1781 |
-
"full_accuracy": 0.
|
| 1782 |
-
"digit_accuracy": 0.
|
| 1783 |
-
"n_examples":
|
| 1784 |
"per_subtask": {
|
| 1785 |
"SA": {
|
| 1786 |
-
"accuracy": 0.
|
| 1787 |
-
"count":
|
| 1788 |
},
|
| 1789 |
"SC": {
|
| 1790 |
-
"accuracy": 0.
|
| 1791 |
-
"count":
|
| 1792 |
},
|
| 1793 |
"SS": {
|
| 1794 |
"accuracy": 1.0,
|
| 1795 |
-
"count":
|
| 1796 |
},
|
| 1797 |
"UC": {
|
| 1798 |
-
"accuracy": 0.
|
| 1799 |
-
"count":
|
| 1800 |
}
|
| 1801 |
}
|
| 1802 |
},
|
| 1803 |
"add_S2": {
|
| 1804 |
-
"full_accuracy": 0.
|
| 1805 |
-
"digit_accuracy": 0.
|
| 1806 |
-
"n_examples":
|
| 1807 |
"per_subtask": {
|
| 1808 |
"SA": {
|
| 1809 |
-
"accuracy": 0.
|
| 1810 |
-
"count":
|
| 1811 |
},
|
| 1812 |
"SC": {
|
| 1813 |
-
"accuracy": 0.
|
| 1814 |
-
"count":
|
| 1815 |
},
|
| 1816 |
"SS": {
|
| 1817 |
-
"accuracy": 0.
|
| 1818 |
-
"count":
|
| 1819 |
},
|
| 1820 |
"UC": {
|
| 1821 |
-
"accuracy": 0.
|
| 1822 |
-
"count":
|
| 1823 |
},
|
| 1824 |
"US": {
|
| 1825 |
"accuracy": 1.0,
|
| 1826 |
-
"count":
|
| 1827 |
}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
"add_S3": {
|
| 1831 |
-
"full_accuracy": 0.
|
| 1832 |
-
"digit_accuracy": 0.
|
| 1833 |
-
"n_examples":
|
| 1834 |
"per_subtask": {
|
| 1835 |
"SA": {
|
| 1836 |
-
"accuracy": 0.
|
| 1837 |
-
"count":
|
| 1838 |
},
|
| 1839 |
"SC": {
|
| 1840 |
-
"accuracy": 0.
|
| 1841 |
-
"count":
|
| 1842 |
},
|
| 1843 |
"SS": {
|
| 1844 |
-
"accuracy":
|
| 1845 |
-
"count":
|
| 1846 |
},
|
| 1847 |
"UC": {
|
| 1848 |
-
"accuracy": 0.
|
| 1849 |
-
"count":
|
| 1850 |
},
|
| 1851 |
"US": {
|
| 1852 |
-
"accuracy": 0.
|
| 1853 |
-
"count":
|
| 1854 |
}
|
| 1855 |
}
|
| 1856 |
},
|
| 1857 |
"add_S4": {
|
| 1858 |
-
"full_accuracy": 0.
|
| 1859 |
-
"digit_accuracy": 0.
|
| 1860 |
-
"n_examples":
|
| 1861 |
"per_subtask": {
|
| 1862 |
"SA": {
|
| 1863 |
"accuracy": 1.0,
|
| 1864 |
-
"count":
|
| 1865 |
},
|
| 1866 |
"SC": {
|
| 1867 |
"accuracy": 1.0,
|
| 1868 |
-
"count":
|
| 1869 |
},
|
| 1870 |
"SS": {
|
| 1871 |
"accuracy": 1.0,
|
| 1872 |
-
"count":
|
| 1873 |
},
|
| 1874 |
"UC": {
|
| 1875 |
-
"accuracy": 0.
|
| 1876 |
-
"count":
|
| 1877 |
},
|
| 1878 |
"US": {
|
| 1879 |
-
"accuracy": 0.
|
| 1880 |
-
"count":
|
| 1881 |
}
|
| 1882 |
}
|
| 1883 |
},
|
| 1884 |
"add_S5": {
|
| 1885 |
-
"full_accuracy": 0.
|
| 1886 |
-
"digit_accuracy": 0.
|
| 1887 |
-
"n_examples":
|
| 1888 |
"per_subtask": {
|
| 1889 |
"SA": {
|
| 1890 |
"accuracy": 1.0,
|
| 1891 |
-
"count":
|
| 1892 |
},
|
| 1893 |
"SC": {
|
| 1894 |
"accuracy": 1.0,
|
| 1895 |
-
"count":
|
| 1896 |
},
|
| 1897 |
"UC": {
|
| 1898 |
-
"accuracy": 0.
|
| 1899 |
-
"count":
|
| 1900 |
},
|
| 1901 |
"US": {
|
| 1902 |
-
"accuracy": 0.
|
| 1903 |
-
"count":
|
| 1904 |
}
|
| 1905 |
}
|
| 1906 |
},
|
| 1907 |
"add_S6": {
|
| 1908 |
-
"full_accuracy": 0.
|
| 1909 |
-
"digit_accuracy": 0.
|
| 1910 |
-
"n_examples":
|
| 1911 |
"per_subtask": {
|
| 1912 |
"SC": {
|
| 1913 |
"accuracy": 1.0,
|
| 1914 |
-
"count":
|
| 1915 |
},
|
| 1916 |
"UC": {
|
| 1917 |
-
"accuracy": 0.
|
| 1918 |
-
"count":
|
| 1919 |
},
|
| 1920 |
"US": {
|
| 1921 |
-
"accuracy": 0.
|
| 1922 |
-
"count":
|
| 1923 |
}
|
| 1924 |
}
|
| 1925 |
},
|
| 1926 |
"add_random": {
|
| 1927 |
-
"full_accuracy": 0.
|
| 1928 |
-
"digit_accuracy": 0.
|
| 1929 |
"n_examples": 200,
|
| 1930 |
"per_subtask": {
|
| 1931 |
"SA": {
|
| 1932 |
-
"accuracy": 0.
|
| 1933 |
-
"count":
|
| 1934 |
},
|
| 1935 |
"SC": {
|
| 1936 |
-
"accuracy": 0.
|
| 1937 |
-
"count":
|
| 1938 |
},
|
| 1939 |
"SS": {
|
| 1940 |
-
"accuracy": 0.
|
| 1941 |
-
"count":
|
| 1942 |
},
|
| 1943 |
"UC": {
|
| 1944 |
-
"accuracy": 0.
|
| 1945 |
-
"count":
|
| 1946 |
},
|
| 1947 |
"US": {
|
| 1948 |
-
"accuracy": 0.
|
| 1949 |
-
"count":
|
| 1950 |
}
|
| 1951 |
}
|
| 1952 |
},
|
| 1953 |
"add_C1": {
|
| 1954 |
-
"full_accuracy": 0.
|
| 1955 |
-
"digit_accuracy": 0.
|
| 1956 |
-
"n_examples":
|
| 1957 |
"per_subtask": {
|
| 1958 |
"SA": {
|
| 1959 |
"accuracy": 1.0,
|
| 1960 |
-
"count":
|
| 1961 |
},
|
| 1962 |
"SC": {
|
| 1963 |
"accuracy": 1.0,
|
| 1964 |
-
"count":
|
| 1965 |
},
|
| 1966 |
"UC": {
|
| 1967 |
-
"accuracy": 0.
|
| 1968 |
-
"count":
|
| 1969 |
}
|
| 1970 |
}
|
| 1971 |
},
|
| 1972 |
"add_C2": {
|
| 1973 |
-
"full_accuracy": 0.
|
| 1974 |
-
"digit_accuracy": 0.
|
| 1975 |
-
"n_examples":
|
| 1976 |
"per_subtask": {
|
| 1977 |
"SA": {
|
| 1978 |
"accuracy": 1.0,
|
| 1979 |
-
"count":
|
| 1980 |
},
|
| 1981 |
"SC": {
|
| 1982 |
"accuracy": 1.0,
|
| 1983 |
-
"count":
|
| 1984 |
},
|
| 1985 |
"UC": {
|
| 1986 |
-
"accuracy": 0.
|
| 1987 |
-
"count":
|
| 1988 |
},
|
| 1989 |
"US": {
|
| 1990 |
-
"accuracy": 0.
|
| 1991 |
-
"count":
|
| 1992 |
}
|
| 1993 |
}
|
| 1994 |
},
|
| 1995 |
"add_C3": {
|
| 1996 |
"full_accuracy": 0.58,
|
| 1997 |
-
"digit_accuracy": 0.
|
| 1998 |
-
"n_examples":
|
| 1999 |
"per_subtask": {
|
| 2000 |
"SA": {
|
| 2001 |
"accuracy": 1.0,
|
| 2002 |
-
"count":
|
| 2003 |
},
|
| 2004 |
"SC": {
|
| 2005 |
"accuracy": 1.0,
|
| 2006 |
-
"count":
|
| 2007 |
},
|
| 2008 |
"UC": {
|
| 2009 |
-
"accuracy": 0.
|
| 2010 |
-
"count":
|
| 2011 |
},
|
| 2012 |
"US": {
|
| 2013 |
-
"accuracy": 0.
|
| 2014 |
-
"count":
|
| 2015 |
}
|
| 2016 |
}
|
| 2017 |
},
|
| 2018 |
"add_C4": {
|
| 2019 |
-
"full_accuracy": 0.
|
| 2020 |
-
"digit_accuracy": 0.
|
| 2021 |
-
"n_examples":
|
| 2022 |
"per_subtask": {
|
| 2023 |
"SA": {
|
| 2024 |
"accuracy": 1.0,
|
| 2025 |
-
"count":
|
| 2026 |
},
|
| 2027 |
"SC": {
|
| 2028 |
"accuracy": 1.0,
|
| 2029 |
-
"count":
|
| 2030 |
},
|
| 2031 |
"UC": {
|
| 2032 |
-
"accuracy": 0.
|
| 2033 |
-
"count":
|
| 2034 |
},
|
| 2035 |
"US": {
|
| 2036 |
-
"accuracy": 0.
|
| 2037 |
-
"count":
|
| 2038 |
}
|
| 2039 |
}
|
| 2040 |
},
|
| 2041 |
"add_C5": {
|
| 2042 |
-
"full_accuracy": 0.
|
| 2043 |
-
"digit_accuracy": 0.
|
| 2044 |
-
"n_examples":
|
| 2045 |
"per_subtask": {
|
| 2046 |
"SA": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
-
"count":
|
| 2049 |
},
|
| 2050 |
"SC": {
|
| 2051 |
"accuracy": 1.0,
|
| 2052 |
-
"count":
|
| 2053 |
},
|
| 2054 |
"UC": {
|
| 2055 |
-
"accuracy": 0.
|
| 2056 |
-
"count":
|
| 2057 |
},
|
| 2058 |
"US": {
|
| 2059 |
-
"accuracy": 0.
|
| 2060 |
-
"count":
|
| 2061 |
}
|
| 2062 |
}
|
| 2063 |
},
|
| 2064 |
"add_C6": {
|
| 2065 |
-
"full_accuracy": 0.
|
| 2066 |
-
"digit_accuracy": 0.
|
| 2067 |
-
"n_examples":
|
| 2068 |
"per_subtask": {
|
| 2069 |
"SC": {
|
| 2070 |
"accuracy": 1.0,
|
| 2071 |
-
"count":
|
| 2072 |
},
|
| 2073 |
"UC": {
|
| 2074 |
-
"accuracy": 0.
|
| 2075 |
-
"count":
|
| 2076 |
},
|
| 2077 |
"US": {
|
| 2078 |
-
"accuracy": 0.
|
| 2079 |
-
"count":
|
| 2080 |
}
|
| 2081 |
}
|
| 2082 |
},
|
| 2083 |
"sub_M0": {
|
| 2084 |
-
"full_accuracy": 0.
|
| 2085 |
-
"digit_accuracy": 0.
|
| 2086 |
-
"n_examples":
|
| 2087 |
"per_subtask": {
|
| 2088 |
"MD": {
|
| 2089 |
-
"accuracy": 0.
|
| 2090 |
-
"count":
|
| 2091 |
},
|
| 2092 |
"ME": {
|
| 2093 |
-
"accuracy":
|
| 2094 |
-
"count":
|
| 2095 |
}
|
| 2096 |
}
|
| 2097 |
},
|
| 2098 |
"sub_M1": {
|
| 2099 |
-
"full_accuracy": 0.
|
| 2100 |
-
"digit_accuracy": 0.
|
| 2101 |
-
"n_examples":
|
| 2102 |
"per_subtask": {
|
| 2103 |
"MD": {
|
| 2104 |
-
"accuracy": 0.
|
| 2105 |
-
"count":
|
| 2106 |
},
|
| 2107 |
"MB": {
|
| 2108 |
"accuracy": 0.9861111111111112,
|
| 2109 |
-
"count":
|
| 2110 |
},
|
| 2111 |
"ME": {
|
| 2112 |
-
"accuracy":
|
| 2113 |
-
"count":
|
| 2114 |
},
|
| 2115 |
"UB": {
|
| 2116 |
-
"accuracy": 0.
|
| 2117 |
-
"count":
|
| 2118 |
}
|
| 2119 |
}
|
| 2120 |
},
|
| 2121 |
"sub_M2": {
|
| 2122 |
-
"full_accuracy": 0.
|
| 2123 |
-
"digit_accuracy": 0.
|
| 2124 |
-
"n_examples":
|
| 2125 |
"per_subtask": {
|
| 2126 |
"MD": {
|
| 2127 |
-
"accuracy": 0.
|
| 2128 |
-
"count":
|
| 2129 |
},
|
| 2130 |
"MB": {
|
| 2131 |
-
"accuracy": 0.
|
| 2132 |
-
"count":
|
| 2133 |
},
|
| 2134 |
"ME": {
|
| 2135 |
-
"accuracy": 0.
|
| 2136 |
-
"count":
|
| 2137 |
},
|
| 2138 |
"UB": {
|
| 2139 |
-
"accuracy": 0.
|
| 2140 |
-
"count":
|
| 2141 |
},
|
| 2142 |
"UD": {
|
| 2143 |
-
"accuracy":
|
| 2144 |
-
"count":
|
| 2145 |
}
|
| 2146 |
}
|
| 2147 |
},
|
| 2148 |
"sub_M3": {
|
| 2149 |
-
"full_accuracy": 0.
|
| 2150 |
-
"digit_accuracy": 0.
|
| 2151 |
-
"n_examples":
|
| 2152 |
"per_subtask": {
|
| 2153 |
"MD": {
|
| 2154 |
-
"accuracy": 0.
|
| 2155 |
-
"count":
|
| 2156 |
},
|
| 2157 |
"MB": {
|
| 2158 |
-
"accuracy": 0.
|
| 2159 |
-
"count":
|
| 2160 |
},
|
| 2161 |
"ME": {
|
| 2162 |
-
"accuracy":
|
| 2163 |
-
"count":
|
| 2164 |
},
|
| 2165 |
"UB": {
|
| 2166 |
-
"accuracy": 0.
|
| 2167 |
-
"count":
|
| 2168 |
},
|
| 2169 |
"UD": {
|
| 2170 |
-
"accuracy": 0.
|
| 2171 |
-
"count":
|
| 2172 |
}
|
| 2173 |
}
|
| 2174 |
},
|
| 2175 |
"sub_M4": {
|
| 2176 |
-
"full_accuracy": 0.
|
| 2177 |
-
"digit_accuracy": 0.
|
| 2178 |
-
"n_examples":
|
| 2179 |
"per_subtask": {
|
| 2180 |
"MD": {
|
| 2181 |
"accuracy": 1.0,
|
| 2182 |
-
"count":
|
| 2183 |
},
|
| 2184 |
"MB": {
|
| 2185 |
"accuracy": 1.0,
|
| 2186 |
-
"count":
|
| 2187 |
},
|
| 2188 |
"UB": {
|
| 2189 |
-
"accuracy": 0.
|
| 2190 |
-
"count":
|
| 2191 |
},
|
| 2192 |
"UD": {
|
| 2193 |
-
"accuracy": 0.
|
| 2194 |
-
"count":
|
| 2195 |
}
|
| 2196 |
}
|
| 2197 |
},
|
| 2198 |
"sub_M5": {
|
| 2199 |
-
"full_accuracy": 0.
|
| 2200 |
-
"digit_accuracy": 0.
|
| 2201 |
-
"n_examples":
|
| 2202 |
"per_subtask": {
|
| 2203 |
"MD": {
|
| 2204 |
"accuracy": 1.0,
|
| 2205 |
-
"count":
|
| 2206 |
},
|
| 2207 |
"MB": {
|
| 2208 |
"accuracy": 1.0,
|
| 2209 |
-
"count":
|
| 2210 |
},
|
| 2211 |
"UB": {
|
| 2212 |
-
"accuracy": 0.
|
| 2213 |
-
"count":
|
| 2214 |
},
|
| 2215 |
"UD": {
|
| 2216 |
-
"accuracy": 0.
|
| 2217 |
-
"count":
|
| 2218 |
}
|
| 2219 |
}
|
| 2220 |
},
|
| 2221 |
"sub_random": {
|
| 2222 |
-
"full_accuracy": 0.
|
| 2223 |
-
"digit_accuracy": 0.
|
| 2224 |
"n_examples": 200,
|
| 2225 |
"per_subtask": {
|
| 2226 |
"MD": {
|
| 2227 |
-
"accuracy": 0.
|
| 2228 |
-
"count":
|
| 2229 |
},
|
| 2230 |
"MB": {
|
| 2231 |
-
"accuracy": 0.
|
| 2232 |
-
"count":
|
| 2233 |
},
|
| 2234 |
"ME": {
|
| 2235 |
"accuracy": 1.0,
|
| 2236 |
"count": 53
|
| 2237 |
},
|
| 2238 |
"UB": {
|
| 2239 |
-
"accuracy": 0.
|
| 2240 |
-
"count":
|
| 2241 |
},
|
| 2242 |
"UD": {
|
| 2243 |
-
"accuracy": 0.
|
| 2244 |
-
"count":
|
| 2245 |
}
|
| 2246 |
}
|
| 2247 |
},
|
| 2248 |
"sub_B3": {
|
| 2249 |
-
"full_accuracy": 0.
|
| 2250 |
-
"digit_accuracy": 0.
|
| 2251 |
-
"n_examples":
|
| 2252 |
"per_subtask": {
|
| 2253 |
"MD": {
|
| 2254 |
"accuracy": 0.9933333333333333,
|
| 2255 |
-
"count":
|
| 2256 |
},
|
| 2257 |
"MB": {
|
| 2258 |
"accuracy": 1.0,
|
| 2259 |
-
"count":
|
| 2260 |
},
|
| 2261 |
"UB": {
|
| 2262 |
-
"accuracy": 0.
|
| 2263 |
-
"count":
|
| 2264 |
},
|
| 2265 |
"UD": {
|
| 2266 |
-
"accuracy": 0.
|
| 2267 |
-
"count":
|
| 2268 |
}
|
| 2269 |
}
|
| 2270 |
},
|
| 2271 |
"sub_B4": {
|
| 2272 |
-
"full_accuracy": 0.
|
| 2273 |
-
"digit_accuracy": 0.
|
| 2274 |
-
"n_examples":
|
| 2275 |
"per_subtask": {
|
| 2276 |
"MD": {
|
| 2277 |
-
"accuracy":
|
| 2278 |
-
"count":
|
| 2279 |
},
|
| 2280 |
"MB": {
|
| 2281 |
-
"accuracy": 0.
|
| 2282 |
-
"count":
|
| 2283 |
},
|
| 2284 |
"UB": {
|
| 2285 |
-
"accuracy": 0.
|
| 2286 |
-
"count":
|
| 2287 |
},
|
| 2288 |
"UD": {
|
| 2289 |
-
"accuracy": 0.
|
| 2290 |
-
"count":
|
| 2291 |
}
|
| 2292 |
}
|
| 2293 |
},
|
| 2294 |
"sub_B5": {
|
| 2295 |
-
"full_accuracy": 0.
|
| 2296 |
-
"digit_accuracy": 0.
|
| 2297 |
-
"n_examples":
|
| 2298 |
"per_subtask": {
|
| 2299 |
"MD": {
|
| 2300 |
"accuracy": 1.0,
|
| 2301 |
-
"count":
|
| 2302 |
},
|
| 2303 |
"MB": {
|
| 2304 |
"accuracy": 1.0,
|
| 2305 |
-
"count":
|
| 2306 |
},
|
| 2307 |
"UB": {
|
| 2308 |
-
"accuracy": 0.
|
| 2309 |
-
"count":
|
| 2310 |
},
|
| 2311 |
"UD": {
|
| 2312 |
-
"accuracy": 0.
|
| 2313 |
-
"count":
|
| 2314 |
}
|
| 2315 |
}
|
| 2316 |
}
|
| 2317 |
},
|
| 2318 |
"summary": {
|
| 2319 |
-
"overall_accuracy": 0.
|
| 2320 |
-
"digit_accuracy": 0.
|
| 2321 |
-
"total_examples":
|
| 2322 |
"n_splits": 24
|
| 2323 |
}
|
| 2324 |
},
|
| 2325 |
-
"sorl_overall_accuracy": 0.
|
| 2326 |
-
"sft_overall_accuracy": 0.
|
| 2327 |
}
|
|
|
|
| 143 |
7779
|
| 144 |
],
|
| 145 |
"loss": [
|
| 146 |
+
-1.4991626739501953,
|
| 147 |
+
7.734500885009766,
|
| 148 |
+
5.436001777648926,
|
| 149 |
+
3.4542782306671143,
|
| 150 |
+
3.120439052581787,
|
| 151 |
+
3.0616321563720703,
|
| 152 |
+
3.3218164443969727,
|
| 153 |
+
3.004723072052002,
|
| 154 |
+
1.9910811185836792,
|
| 155 |
+
0.6555660963058472,
|
| 156 |
+
-0.9676400423049927,
|
| 157 |
+
-2.3662240505218506,
|
| 158 |
+
-5.7794880867004395,
|
| 159 |
+
-7.444696426391602,
|
| 160 |
+
-9.871407508850098,
|
| 161 |
+
-9.68606948852539,
|
| 162 |
+
-10.215792655944824,
|
| 163 |
+
-10.611030578613281,
|
| 164 |
+
-10.236133575439453,
|
| 165 |
+
-11.204968452453613,
|
| 166 |
+
-11.310162544250488,
|
| 167 |
+
-12.506915092468262,
|
| 168 |
+
-12.20246410369873,
|
| 169 |
+
-11.986822128295898,
|
| 170 |
+
-12.56383991241455,
|
| 171 |
+
-13.523144721984863,
|
| 172 |
+
-12.998540878295898,
|
| 173 |
+
-12.551019668579102,
|
| 174 |
+
-14.125226974487305,
|
| 175 |
+
-14.020819664001465,
|
| 176 |
+
-13.266901016235352,
|
| 177 |
+
-13.1586275100708,
|
| 178 |
+
-13.030251502990723,
|
| 179 |
+
-12.78680419921875,
|
| 180 |
+
-12.259639739990234,
|
| 181 |
+
-12.242656707763672,
|
| 182 |
+
-11.402668952941895,
|
| 183 |
+
-12.361416816711426,
|
| 184 |
+
-11.902348518371582,
|
| 185 |
+
-11.421567916870117,
|
| 186 |
+
-10.673042297363281,
|
| 187 |
+
-11.382230758666992,
|
| 188 |
+
-6.558827877044678,
|
| 189 |
+
-6.498293876647949,
|
| 190 |
+
-4.6974992752075195,
|
| 191 |
+
-5.150529861450195,
|
| 192 |
+
-4.423306941986084,
|
| 193 |
+
-3.7705271244049072,
|
| 194 |
+
-3.8951430320739746,
|
| 195 |
+
-2.417325735092163,
|
| 196 |
+
-2.104322671890259,
|
| 197 |
+
-2.5029518604278564,
|
| 198 |
+
-1.6507831811904907,
|
| 199 |
+
-1.296630620956421,
|
| 200 |
+
-1.3789325952529907,
|
| 201 |
+
-1.2700506448745728,
|
| 202 |
+
-0.47501254081726074,
|
| 203 |
+
-1.239183783531189,
|
| 204 |
+
-1.1124522686004639,
|
| 205 |
+
-1.035009741783142,
|
| 206 |
+
-0.9158291816711426,
|
| 207 |
+
-0.7348793745040894,
|
| 208 |
+
-0.6639032959938049,
|
| 209 |
+
-0.8863333463668823,
|
| 210 |
+
-1.0262635946273804,
|
| 211 |
+
-0.49884942173957825,
|
| 212 |
+
-0.6950386166572571,
|
| 213 |
+
-0.4942106306552887,
|
| 214 |
+
-0.2716549038887024,
|
| 215 |
+
-0.5381484031677246,
|
| 216 |
+
-0.8825717568397522,
|
| 217 |
+
-0.6018041968345642,
|
| 218 |
+
-0.33367589116096497,
|
| 219 |
+
-0.5229771137237549,
|
| 220 |
+
-0.2667657732963562,
|
| 221 |
+
-0.5897171497344971,
|
| 222 |
+
-0.33587557077407837,
|
| 223 |
+
-0.4438111484050751,
|
| 224 |
+
-0.29231590032577515,
|
| 225 |
+
-0.37558865547180176,
|
| 226 |
+
-0.7385783195495605,
|
| 227 |
+
-0.29125189781188965,
|
| 228 |
+
-0.13102558255195618,
|
| 229 |
+
-0.24600398540496826,
|
| 230 |
+
-0.23949313163757324,
|
| 231 |
+
-0.4070977568626404,
|
| 232 |
+
-0.2605511546134949,
|
| 233 |
+
-0.3812254071235657,
|
| 234 |
+
-0.22385181486606598,
|
| 235 |
+
-0.3658450245857239,
|
| 236 |
+
-0.467978298664093,
|
| 237 |
+
-0.14255213737487793,
|
| 238 |
+
-0.173037588596344,
|
| 239 |
+
-0.43948355317115784,
|
| 240 |
+
-0.01865462213754654,
|
| 241 |
+
-0.3687412738800049,
|
| 242 |
+
-0.023503027856349945,
|
| 243 |
+
-0.7068221569061279,
|
| 244 |
+
-0.25219908356666565,
|
| 245 |
+
0.1554774045944214,
|
| 246 |
+
-0.5628666877746582,
|
| 247 |
+
-0.577951192855835,
|
| 248 |
+
-0.44770199060440063,
|
| 249 |
+
0.13656851649284363,
|
| 250 |
+
-0.4713708758354187,
|
| 251 |
+
-0.13712182641029358,
|
| 252 |
+
-0.20912747085094452,
|
| 253 |
+
-0.480000376701355,
|
| 254 |
+
-0.4113278090953827,
|
| 255 |
+
-0.4733881652355194,
|
| 256 |
+
-0.27355921268463135,
|
| 257 |
+
-0.3161522448062897,
|
| 258 |
+
-0.3382975459098816,
|
| 259 |
+
0.14343056082725525,
|
| 260 |
+
-0.26643693447113037,
|
| 261 |
+
-0.10106643289327621,
|
| 262 |
+
-0.18165260553359985,
|
| 263 |
+
-0.3992097079753876,
|
| 264 |
+
-0.0171702578663826,
|
| 265 |
+
-0.1860802173614502,
|
| 266 |
+
-0.3103711009025574,
|
| 267 |
+
-0.4309031665325165,
|
| 268 |
+
-0.13910165429115295,
|
| 269 |
+
-0.3424716591835022,
|
| 270 |
+
0.11052711308002472,
|
| 271 |
+
-0.1522039771080017,
|
| 272 |
+
-0.19839590787887573,
|
| 273 |
+
-0.12273947149515152,
|
| 274 |
+
-0.0678120106458664,
|
| 275 |
+
-0.25733813643455505,
|
| 276 |
+
-0.07050967961549759,
|
| 277 |
+
-0.19385433197021484,
|
| 278 |
+
-0.12846776843070984,
|
| 279 |
+
-0.06633119285106659,
|
| 280 |
+
-0.24687248468399048,
|
| 281 |
+
-0.20333541929721832,
|
| 282 |
+
-0.18603983521461487,
|
| 283 |
+
-0.381289005279541,
|
| 284 |
+
-0.3737454414367676,
|
| 285 |
+
-0.32912370562553406
|
| 286 |
],
|
| 287 |
"base_loss": [
|
| 288 |
+
10.222891807556152,
|
| 289 |
+
6.434610843658447,
|
| 290 |
+
3.7198283672332764,
|
| 291 |
+
1.9681453704833984,
|
| 292 |
+
1.959210753440857,
|
| 293 |
+
1.929343342781067,
|
| 294 |
+
1.9306913614273071,
|
| 295 |
+
1.8596428632736206,
|
| 296 |
+
1.8303827047348022,
|
| 297 |
+
1.9475268125534058,
|
| 298 |
+
1.855019211769104,
|
| 299 |
+
1.9119843244552612,
|
| 300 |
+
1.8700278997421265,
|
| 301 |
+
1.8823758363723755,
|
| 302 |
+
1.8745900392532349,
|
| 303 |
+
1.836315393447876,
|
| 304 |
+
1.8635133504867554,
|
| 305 |
+
1.8799570798873901,
|
| 306 |
+
1.838736653327942,
|
| 307 |
+
1.8712080717086792,
|
| 308 |
+
1.8709423542022705,
|
| 309 |
+
1.875689148902893,
|
| 310 |
+
1.7823193073272705,
|
| 311 |
+
1.7674901485443115,
|
| 312 |
+
1.8198670148849487,
|
| 313 |
+
1.844150424003601,
|
| 314 |
+
1.8199037313461304,
|
| 315 |
+
1.76785409450531,
|
| 316 |
+
1.8722307682037354,
|
| 317 |
+
1.8727575540542603,
|
| 318 |
+
1.7651337385177612,
|
| 319 |
+
1.7576688528060913,
|
| 320 |
+
1.7199641466140747,
|
| 321 |
+
1.6449308395385742,
|
| 322 |
+
1.640900731086731,
|
| 323 |
+
1.617160677909851,
|
| 324 |
+
1.5190116167068481,
|
| 325 |
+
1.594099998474121,
|
| 326 |
+
1.506998062133789,
|
| 327 |
+
1.4643415212631226,
|
| 328 |
+
1.4485048055648804,
|
| 329 |
+
1.45021653175354,
|
| 330 |
+
0.9755846858024597,
|
| 331 |
+
0.9805561900138855,
|
| 332 |
+
0.8023272752761841,
|
| 333 |
+
0.7398602366447449,
|
| 334 |
+
0.6865811944007874,
|
| 335 |
+
0.6157902479171753,
|
| 336 |
+
0.6458702683448792,
|
| 337 |
+
0.47322097420692444,
|
| 338 |
+
0.41887447237968445,
|
| 339 |
+
0.455700546503067,
|
| 340 |
+
0.36339297890663147,
|
| 341 |
+
0.31774353981018066,
|
| 342 |
+
0.3184225559234619,
|
| 343 |
+
0.2997283637523651,
|
| 344 |
+
0.2608298361301422,
|
| 345 |
+
0.2871330678462982,
|
| 346 |
+
0.2896370589733124,
|
| 347 |
+
0.25344473123550415,
|
| 348 |
+
0.2470230907201767,
|
| 349 |
+
0.20899748802185059,
|
| 350 |
+
0.20870697498321533,
|
| 351 |
+
0.23385517299175262,
|
| 352 |
+
0.265758752822876,
|
| 353 |
+
0.1959606260061264,
|
| 354 |
+
0.23661544919013977,
|
| 355 |
+
0.2046181857585907,
|
| 356 |
+
0.2053668349981308,
|
| 357 |
+
0.211956188082695,
|
| 358 |
+
0.2493533343076706,
|
| 359 |
+
0.2304404079914093,
|
| 360 |
+
0.20379698276519775,
|
| 361 |
+
0.2550745904445648,
|
| 362 |
+
0.21894343197345734,
|
| 363 |
+
0.24354372918605804,
|
| 364 |
+
0.16568894684314728,
|
| 365 |
+
0.22153237462043762,
|
| 366 |
+
0.17909720540046692,
|
| 367 |
+
0.14946947991847992,
|
| 368 |
+
0.1980229616165161,
|
| 369 |
+
0.16256201267242432,
|
| 370 |
+
0.2212965339422226,
|
| 371 |
+
0.14926958084106445,
|
| 372 |
+
0.16306713223457336,
|
| 373 |
+
0.14940468966960907,
|
| 374 |
+
0.1395643949508667,
|
| 375 |
+
0.18206553161144257,
|
| 376 |
+
0.15634550154209137,
|
| 377 |
+
0.16714580357074738,
|
| 378 |
+
0.16745184361934662,
|
| 379 |
+
0.11398492753505707,
|
| 380 |
+
0.11608642339706421,
|
| 381 |
+
0.1713183969259262,
|
| 382 |
+
0.10937852412462234,
|
| 383 |
+
0.1577722728252411,
|
| 384 |
+
0.11792578548192978,
|
| 385 |
+
0.1740894764661789,
|
| 386 |
+
0.13912317156791687,
|
| 387 |
+
0.16688987612724304,
|
| 388 |
+
0.15285928547382355,
|
| 389 |
+
0.16415275633335114,
|
| 390 |
+
0.12775208055973053,
|
| 391 |
+
0.1447954922914505,
|
| 392 |
+
0.14248152077198029,
|
| 393 |
+
0.11021719872951508,
|
| 394 |
+
0.11120182275772095,
|
| 395 |
+
0.13144712150096893,
|
| 396 |
+
0.11101575940847397,
|
| 397 |
+
0.15845659375190735,
|
| 398 |
+
0.12258584052324295,
|
| 399 |
+
0.1119571402668953,
|
| 400 |
+
0.12098769098520279,
|
| 401 |
+
0.12010190635919571,
|
| 402 |
+
0.07548805326223373,
|
| 403 |
+
0.0853903666138649,
|
| 404 |
+
0.10983582586050034,
|
| 405 |
+
0.10240059345960617,
|
| 406 |
+
0.12491006404161453,
|
| 407 |
+
0.09631884098052979,
|
| 408 |
+
0.1358448565006256,
|
| 409 |
+
0.10576845705509186,
|
| 410 |
+
0.11273549497127533,
|
| 411 |
+
0.15282641351222992,
|
| 412 |
+
0.08400528877973557,
|
| 413 |
+
0.12438462674617767,
|
| 414 |
+
0.10317623615264893,
|
| 415 |
+
0.09730804711580276,
|
| 416 |
+
0.08032923936843872,
|
| 417 |
+
0.08921071141958237,
|
| 418 |
+
0.09194045513868332,
|
| 419 |
+
0.07488199323415756,
|
| 420 |
+
0.06639757007360458,
|
| 421 |
+
0.0887700691819191,
|
| 422 |
+
0.0883544310927391,
|
| 423 |
+
0.09428595006465912,
|
| 424 |
+
0.07859671115875244,
|
| 425 |
+
0.10635203123092651,
|
| 426 |
+
0.10783649235963821,
|
| 427 |
+
0.08185470104217529
|
| 428 |
],
|
| 429 |
"info_loss": [
|
| 430 |
+
-2.037433624267578,
|
| 431 |
+
-0.31572675704956055,
|
| 432 |
+
-0.05017352104187012,
|
| 433 |
+
-0.04210937023162842,
|
| 434 |
+
-0.07202112674713135,
|
| 435 |
+
-0.07436704635620117,
|
| 436 |
+
-0.04826033115386963,
|
| 437 |
+
-0.07273316383361816,
|
| 438 |
+
-0.1699002981185913,
|
| 439 |
+
-0.30787158012390137,
|
| 440 |
+
-0.4511171579360962,
|
| 441 |
+
-0.5922137498855591,
|
| 442 |
+
-0.9263088703155518,
|
| 443 |
+
-1.0923757553100586,
|
| 444 |
+
-1.3311564922332764,
|
| 445 |
+
-1.307382583618164,
|
| 446 |
+
-1.3608746528625488,
|
| 447 |
+
-1.3961358070373535,
|
| 448 |
+
-1.3470678329467773,
|
| 449 |
+
-1.4397988319396973,
|
| 450 |
+
-1.4440470933914185,
|
| 451 |
+
-1.5294926166534424,
|
| 452 |
+
-1.4736708402633667,
|
| 453 |
+
-1.438417673110962,
|
| 454 |
+
-1.4990330934524536,
|
| 455 |
+
-1.5943763256072998,
|
| 456 |
+
-1.5328370332717896,
|
| 457 |
+
-1.4824275970458984,
|
| 458 |
+
-1.6502817869186401,
|
| 459 |
+
-1.6358681917190552,
|
| 460 |
+
-1.54860520362854,
|
| 461 |
+
-1.5320099592208862,
|
| 462 |
+
-1.51332688331604,
|
| 463 |
+
-1.4763262271881104,
|
| 464 |
+
-1.4228277206420898,
|
| 465 |
+
-1.4195810556411743,
|
| 466 |
+
-1.3227262496948242,
|
| 467 |
+
-1.4174060821533203,
|
| 468 |
+
-1.360844612121582,
|
| 469 |
+
-1.3054325580596924,
|
| 470 |
+
-1.226885437965393,
|
| 471 |
+
-1.2967873811721802,
|
| 472 |
+
-0.7679556012153625,
|
| 473 |
+
-0.7592524290084839,
|
| 474 |
+
-0.5631743669509888,
|
| 475 |
+
-0.5992276072502136,
|
| 476 |
+
-0.5220549702644348,
|
| 477 |
+
-0.44866302609443665,
|
| 478 |
+
-0.4627205729484558,
|
| 479 |
+
-0.2990763783454895,
|
| 480 |
+
-0.26095426082611084,
|
| 481 |
+
-0.30547964572906494,
|
| 482 |
+
-0.20989865064620972,
|
| 483 |
+
-0.17013928294181824,
|
| 484 |
+
-0.1788894385099411,
|
| 485 |
+
-0.16711220145225525,
|
| 486 |
+
-0.08040527999401093,
|
| 487 |
+
-0.15986192226409912,
|
| 488 |
+
-0.1477246880531311,
|
| 489 |
+
-0.13738852739334106,
|
| 490 |
+
-0.12397092580795288,
|
| 491 |
+
-0.10177233070135117,
|
| 492 |
+
-0.09493035823106766,
|
| 493 |
+
-0.11996994912624359,
|
| 494 |
+
-0.1356387436389923,
|
| 495 |
+
-0.07737710326910019,
|
| 496 |
+
-0.10097216069698334,
|
| 497 |
+
-0.07617561519145966,
|
| 498 |
+
-0.05582185089588165,
|
| 499 |
+
-0.08229339122772217,
|
| 500 |
+
-0.11973747611045837,
|
| 501 |
+
-0.08974818885326385,
|
| 502 |
+
-0.060351938009262085,
|
| 503 |
+
-0.08523020148277283,
|
| 504 |
+
-0.0554652065038681,
|
| 505 |
+
-0.08915802836418152,
|
| 506 |
+
-0.05697622150182724,
|
| 507 |
+
-0.07321585714817047,
|
| 508 |
+
-0.05324859917163849,
|
| 509 |
+
-0.05828547477722168,
|
| 510 |
+
-0.10016466677188873,
|
| 511 |
+
-0.051857367157936096,
|
| 512 |
+
-0.040182337164878845,
|
| 513 |
+
-0.04722199589014053,
|
| 514 |
+
-0.04640142619609833,
|
| 515 |
+
-0.06200437247753143,
|
| 516 |
+
-0.04559026658535004,
|
| 517 |
+
-0.0621969997882843,
|
| 518 |
+
-0.04386666417121887,
|
| 519 |
+
-0.058832526206970215,
|
| 520 |
+
-0.06905774027109146,
|
| 521 |
+
-0.03173664212226868,
|
| 522 |
+
-0.034987613558769226,
|
| 523 |
+
-0.06714990735054016,
|
| 524 |
+
-0.018569253385066986,
|
| 525 |
+
-0.05842562019824982,
|
| 526 |
+
-0.02083367109298706,
|
| 527 |
+
-0.09449857473373413,
|
| 528 |
+
-0.04437990486621857,
|
| 529 |
+
-0.007008716464042664,
|
| 530 |
+
-0.07735760509967804,
|
| 531 |
+
-0.08071395009756088,
|
| 532 |
+
-0.06259468197822571,
|
| 533 |
+
-0.006447583436965942,
|
| 534 |
+
-0.06709475815296173,
|
| 535 |
+
-0.031158633530139923,
|
| 536 |
+
-0.03744358569383621,
|
| 537 |
+
-0.06632976233959198,
|
| 538 |
+
-0.057221584022045135,
|
| 539 |
+
-0.06812497973442078,
|
| 540 |
+
-0.04631491005420685,
|
| 541 |
+
-0.04810434579849243,
|
| 542 |
+
-0.05078253149986267,
|
| 543 |
+
-0.003159046173095703,
|
| 544 |
+
-0.03911986202001572,
|
| 545 |
+
-0.024468280375003815,
|
| 546 |
+
-0.03566398471593857,
|
| 547 |
+
-0.05539749562740326,
|
| 548 |
+
-0.01884063333272934,
|
| 549 |
+
-0.03409624472260475,
|
| 550 |
+
-0.05011004954576492,
|
| 551 |
+
-0.05908038467168808,
|
| 552 |
+
-0.03038986772298813,
|
| 553 |
+
-0.054623715579509735,
|
| 554 |
+
-0.0025235339999198914,
|
| 555 |
+
-0.03323037177324295,
|
| 556 |
+
-0.03580985218286514,
|
| 557 |
+
-0.0279695987701416,
|
| 558 |
+
-0.019559767097234726,
|
| 559 |
+
-0.039626412093639374,
|
| 560 |
+
-0.021337643265724182,
|
| 561 |
+
-0.03141063079237938,
|
| 562 |
+
-0.024501889944076538,
|
| 563 |
+
-0.020283721387386322,
|
| 564 |
+
-0.03983597829937935,
|
| 565 |
+
-0.03490420803427696,
|
| 566 |
+
-0.032450538128614426,
|
| 567 |
+
-0.05533437058329582,
|
| 568 |
+
-0.053110718727111816,
|
| 569 |
+
-0.046020276844501495
|
| 570 |
],
|
| 571 |
"abs_loss": [
|
| 572 |
+
2.2782208919525146,
|
| 573 |
+
2.0877914428710938,
|
| 574 |
+
1.8768965005874634,
|
| 575 |
+
1.8503764867782593,
|
| 576 |
+
1.860660433769226,
|
| 577 |
+
1.8386014699935913,
|
| 578 |
+
1.8303370475769043,
|
| 579 |
+
1.837899088859558,
|
| 580 |
+
1.8108211755752563,
|
| 581 |
+
1.5847219228744507,
|
| 582 |
+
1.391497015953064,
|
| 583 |
+
1.3384944200515747,
|
| 584 |
+
1.329427719116211,
|
| 585 |
+
1.3017956018447876,
|
| 586 |
+
1.2399191856384277,
|
| 587 |
+
1.2146539688110352,
|
| 588 |
+
1.135986328125,
|
| 589 |
+
1.0552599430084229,
|
| 590 |
+
0.887962818145752,
|
| 591 |
+
0.8350238800048828,
|
| 592 |
+
0.6903941631317139,
|
| 593 |
+
0.5229440331459045,
|
| 594 |
+
0.4153222143650055,
|
| 595 |
+
0.3750406801700592,
|
| 596 |
+
0.3795664310455322,
|
| 597 |
+
0.30999478697776794,
|
| 598 |
+
0.2965479791164398,
|
| 599 |
+
0.3220847547054291,
|
| 600 |
+
0.29502496123313904,
|
| 601 |
+
0.29283303022384644,
|
| 602 |
+
0.29946067929267883,
|
| 603 |
+
0.2762465178966522,
|
| 604 |
+
0.27067646384239197,
|
| 605 |
+
0.2124723196029663,
|
| 606 |
+
0.2123774290084839,
|
| 607 |
+
0.27615517377853394,
|
| 608 |
+
0.2274278849363327,
|
| 609 |
+
0.1947956085205078,
|
| 610 |
+
0.1658640205860138,
|
| 611 |
+
0.14536798000335693,
|
| 612 |
+
0.13485930860042572,
|
| 613 |
+
0.1487635374069214,
|
| 614 |
+
0.09887402504682541,
|
| 615 |
+
0.08551109582185745,
|
| 616 |
+
0.11851557344198227,
|
| 617 |
+
0.07192469388246536,
|
| 618 |
+
0.09643194824457169,
|
| 619 |
+
0.07271024584770203,
|
| 620 |
+
0.08401944488286972,
|
| 621 |
+
0.0711170956492424,
|
| 622 |
+
0.10404173284769058,
|
| 623 |
+
0.07230190932750702,
|
| 624 |
+
0.07444865256547928,
|
| 625 |
+
0.057993996888399124,
|
| 626 |
+
0.06331399083137512,
|
| 627 |
+
0.06968239694833755,
|
| 628 |
+
0.058420877903699875,
|
| 629 |
+
0.05234828591346741,
|
| 630 |
+
0.04469572380185127,
|
| 631 |
+
0.060892462730407715,
|
| 632 |
+
0.06377529352903366,
|
| 633 |
+
0.05298902466893196,
|
| 634 |
+
0.06325497478246689,
|
| 635 |
+
0.0557883195579052,
|
| 636 |
+
0.05224437639117241,
|
| 637 |
+
0.04783019796013832,
|
| 638 |
+
0.0495179109275341,
|
| 639 |
+
0.0373246930539608,
|
| 640 |
+
0.05701762065291405,
|
| 641 |
+
0.03870227187871933,
|
| 642 |
+
0.059414517134428024,
|
| 643 |
+
0.029631739482283592,
|
| 644 |
+
0.04484502971172333,
|
| 645 |
+
0.042912598699331284,
|
| 646 |
+
0.05295603349804878,
|
| 647 |
+
0.04987824335694313,
|
| 648 |
+
0.03641092777252197,
|
| 649 |
+
0.040556978434324265,
|
| 650 |
+
0.03168303146958351,
|
| 651 |
+
0.028551781550049782,
|
| 652 |
+
0.02967704087495804,
|
| 653 |
+
0.027214542031288147,
|
| 654 |
+
0.017562584951519966,
|
| 655 |
+
0.024341275915503502,
|
| 656 |
+
0.032353684306144714,
|
| 657 |
+
0.037270668894052505,
|
| 658 |
+
0.027527958154678345,
|
| 659 |
+
0.025686120614409447,
|
| 660 |
+
0.021791374310851097,
|
| 661 |
+
0.02155947871506214,
|
| 662 |
+
0.017588598653674126,
|
| 663 |
+
0.019590383395552635,
|
| 664 |
+
0.024403566494584084,
|
| 665 |
+
0.040734563022851944,
|
| 666 |
+
0.01853681355714798,
|
| 667 |
+
0.022299962118268013,
|
| 668 |
+
0.020661523565649986,
|
| 669 |
+
0.018253402784466743,
|
| 670 |
+
0.014955420047044754,
|
| 671 |
+
0.01722128875553608,
|
| 672 |
+
0.014421396888792515,
|
| 673 |
+
0.022876715287566185,
|
| 674 |
+
0.022903740406036377,
|
| 675 |
+
0.019680185243487358,
|
| 676 |
+
0.023799598217010498,
|
| 677 |
+
0.02028706483542919,
|
| 678 |
+
0.011872164905071259,
|
| 679 |
+
0.019997278228402138,
|
| 680 |
+
0.014807574450969696,
|
| 681 |
+
0.01684972085058689,
|
| 682 |
+
0.014521368779242039,
|
| 683 |
+
0.014271489344537258,
|
| 684 |
+
0.013847983442246914,
|
| 685 |
+
0.02395080029964447,
|
| 686 |
+
0.021941566839814186,
|
| 687 |
+
0.017697757109999657,
|
| 688 |
+
0.013051857240498066,
|
| 689 |
+
0.01706533133983612,
|
| 690 |
+
0.014984418638050556,
|
| 691 |
+
0.012025459669530392,
|
| 692 |
+
0.02180357836186886,
|
| 693 |
+
0.007351210806518793,
|
| 694 |
+
0.012332173995673656,
|
| 695 |
+
0.0186754297465086,
|
| 696 |
+
0.009667596779763699,
|
| 697 |
+
0.01859714835882187,
|
| 698 |
+
0.0180825162678957,
|
| 699 |
+
0.009598099626600742,
|
| 700 |
+
0.012128149159252644,
|
| 701 |
+
0.009924765676259995,
|
| 702 |
+
0.005770361050963402,
|
| 703 |
+
0.017123397439718246,
|
| 704 |
+
0.01288231834769249,
|
| 705 |
+
0.006488412618637085,
|
| 706 |
+
0.015862809494137764,
|
| 707 |
+
0.016753973439335823,
|
| 708 |
+
0.011881467886269093,
|
| 709 |
+
0.014946346171200275,
|
| 710 |
+
0.023875480517745018,
|
| 711 |
+
0.01311760675162077
|
| 712 |
],
|
| 713 |
"zipf_loss": [
|
| 714 |
+
8.424459457397461,
|
| 715 |
+
4.248378753662109,
|
| 716 |
+
2.030219078063965,
|
| 717 |
+
1.722188949584961,
|
| 718 |
+
1.69537353515625,
|
| 719 |
+
1.6920992136001587,
|
| 720 |
+
1.6906945705413818,
|
| 721 |
+
1.688621997833252,
|
| 722 |
+
1.6786192655563354,
|
| 723 |
+
1.628282904624939,
|
| 724 |
+
1.5493625402450562,
|
| 725 |
+
1.5100793838500977,
|
| 726 |
+
1.4806294441223145,
|
| 727 |
+
1.4665058851242065,
|
| 728 |
+
1.4415757656097412,
|
| 729 |
+
1.4299758672714233,
|
| 730 |
+
1.415842056274414,
|
| 731 |
+
1.3648438453674316,
|
| 732 |
+
1.3070120811462402,
|
| 733 |
+
1.2383089065551758,
|
| 734 |
+
1.1903269290924072,
|
| 735 |
+
0.8600262999534607,
|
| 736 |
+
0.7103928327560425,
|
| 737 |
+
0.5923600196838379,
|
| 738 |
+
0.5686673521995544,
|
| 739 |
+
0.5454696416854858,
|
| 740 |
+
0.48027122020721436,
|
| 741 |
+
0.47319427132606506,
|
| 742 |
+
0.47585660219192505,
|
| 743 |
+
0.435821533203125,
|
| 744 |
+
0.42406991124153137,
|
| 745 |
+
0.3761786222457886,
|
| 746 |
+
0.3559854030609131,
|
| 747 |
+
0.31027960777282715,
|
| 748 |
+
0.3064996898174286,
|
| 749 |
+
0.3083776831626892,
|
| 750 |
+
0.2828387916088104,
|
| 751 |
+
0.19906440377235413,
|
| 752 |
+
0.18251287937164307,
|
| 753 |
+
0.15387912094593048,
|
| 754 |
+
0.13382180035114288,
|
| 755 |
+
0.12054996937513351,
|
| 756 |
+
0.13525637984275818,
|
| 757 |
+
0.10512371361255646,
|
| 758 |
+
0.1200651153922081,
|
| 759 |
+
0.09469343721866608,
|
| 760 |
+
0.10101855546236038,
|
| 761 |
+
0.09304188936948776,
|
| 762 |
+
0.07779079675674438,
|
| 763 |
+
0.09310503304004669,
|
| 764 |
+
0.07594139128923416,
|
| 765 |
+
0.08891379088163376,
|
| 766 |
+
0.0773656815290451,
|
| 767 |
+
0.08121927082538605,
|
| 768 |
+
0.08520787209272385,
|
| 769 |
+
0.09437482804059982,
|
| 770 |
+
0.06236838549375534,
|
| 771 |
+
0.067067451775074,
|
| 772 |
+
0.07068801671266556,
|
| 773 |
+
0.07934156805276871,
|
| 774 |
+
0.07047945261001587,
|
| 775 |
+
0.06854751706123352,
|
| 776 |
+
0.07036779075860977,
|
| 777 |
+
0.07393214106559753,
|
| 778 |
+
0.05914054065942764,
|
| 779 |
+
0.07417795062065125,
|
| 780 |
+
0.07311580330133438,
|
| 781 |
+
0.0591949000954628,
|
| 782 |
+
0.07549495995044708,
|
| 783 |
+
0.06895903497934341,
|
| 784 |
+
0.05950825661420822,
|
| 785 |
+
0.062274135649204254,
|
| 786 |
+
0.061562009155750275,
|
| 787 |
+
0.06995910406112671,
|
| 788 |
+
0.0636473149061203,
|
| 789 |
+
0.053331539034843445,
|
| 790 |
+
0.06455662846565247,
|
| 791 |
+
0.06275936961174011,
|
| 792 |
+
0.05790455639362335,
|
| 793 |
+
0.05494140088558197,
|
| 794 |
+
0.06207764893770218,
|
| 795 |
+
0.06203828006982803,
|
| 796 |
+
0.0477449893951416,
|
| 797 |
+
0.07451224327087402,
|
| 798 |
+
0.05821862816810608,
|
| 799 |
+
0.059814199805259705,
|
| 800 |
+
0.05303432047367096,
|
| 801 |
+
0.0561104416847229,
|
| 802 |
+
0.056290194392204285,
|
| 803 |
+
0.05317850410938263,
|
| 804 |
+
0.053388360887765884,
|
| 805 |
+
0.05887032300233841,
|
| 806 |
+
0.05831175297498703,
|
| 807 |
+
0.05662363022565842,
|
| 808 |
+
0.05580570548772812,
|
| 809 |
+
0.05551263689994812,
|
| 810 |
+
0.06484174728393555,
|
| 811 |
+
0.06224876269698143,
|
| 812 |
+
0.05098125338554382,
|
| 813 |
+
0.056952573359012604,
|
| 814 |
+
0.056407906115055084,
|
| 815 |
+
0.06274788081645966,
|
| 816 |
+
0.04820239916443825,
|
| 817 |
+
0.054280832409858704,
|
| 818 |
+
0.05471523106098175,
|
| 819 |
+
0.062218599021434784,
|
| 820 |
+
0.05291934311389923,
|
| 821 |
+
0.04985041171312332,
|
| 822 |
+
0.04839150980114937,
|
| 823 |
+
0.0477200448513031,
|
| 824 |
+
0.06555189192295074,
|
| 825 |
+
0.05150694400072098,
|
| 826 |
+
0.04715529829263687,
|
| 827 |
+
0.05252403765916824,
|
| 828 |
+
0.04707948490977287,
|
| 829 |
+
0.05645621567964554,
|
| 830 |
+
0.06384622305631638,
|
| 831 |
+
0.050658129155635834,
|
| 832 |
+
0.04482756927609444,
|
| 833 |
+
0.05736084282398224,
|
| 834 |
+
0.05270415171980858,
|
| 835 |
+
0.05339711531996727,
|
| 836 |
+
0.050828322768211365,
|
| 837 |
+
0.0490715391933918,
|
| 838 |
+
0.05079040676355362,
|
| 839 |
+
0.053855396807193756,
|
| 840 |
+
0.054718103259801865,
|
| 841 |
+
0.05868866294622421,
|
| 842 |
+
0.046243615448474884,
|
| 843 |
+
0.04872281104326248,
|
| 844 |
+
0.050349265336990356,
|
| 845 |
+
0.043657638132572174,
|
| 846 |
+
0.04886531084775925,
|
| 847 |
+
0.047087110579013824,
|
| 848 |
+
0.06154657155275345,
|
| 849 |
+
0.049745336174964905,
|
| 850 |
+
0.0586807057261467,
|
| 851 |
+
0.06420803815126419,
|
| 852 |
+
0.04713771492242813,
|
| 853 |
+
0.047912608832120895
|
| 854 |
],
|
| 855 |
"denoise_loss": [],
|
| 856 |
"ortho_loss": [
|
| 857 |
+
0.7175698280334473,
|
| 858 |
+
0.42890316247940063,
|
| 859 |
+
0.33829447627067566,
|
| 860 |
+
0.22440843284130096,
|
| 861 |
+
0.18137924373149872,
|
| 862 |
+
0.2310202568769455,
|
| 863 |
+
0.22335532307624817,
|
| 864 |
+
0.21682365238666534,
|
| 865 |
+
0.25529515743255615,
|
| 866 |
+
0.30100017786026,
|
| 867 |
+
0.3371667265892029,
|
| 868 |
+
0.3791210651397705,
|
| 869 |
+
0.3911088705062866,
|
| 870 |
+
0.3969413936138153,
|
| 871 |
+
0.4060496985912323,
|
| 872 |
+
0.40077337622642517,
|
| 873 |
+
0.39444079995155334,
|
| 874 |
+
0.3958539366722107,
|
| 875 |
+
0.4089014232158661,
|
| 876 |
+
0.40195876359939575,
|
| 877 |
+
0.3901920020580292,
|
| 878 |
+
0.3879682719707489,
|
| 879 |
+
0.37536731362342834,
|
| 880 |
+
0.36621353030204773,
|
| 881 |
+
0.3571617305278778,
|
| 882 |
+
0.34676823019981384,
|
| 883 |
+
0.3404388427734375,
|
| 884 |
+
0.3386509418487549,
|
| 885 |
+
0.3293488025665283,
|
| 886 |
+
0.3230898678302765,
|
| 887 |
+
0.31814470887184143,
|
| 888 |
+
0.31388574838638306,
|
| 889 |
+
0.30950528383255005,
|
| 890 |
+
0.3056495189666748,
|
| 891 |
+
0.30528897047042847,
|
| 892 |
+
0.3057379424571991,
|
| 893 |
+
0.3013770282268524,
|
| 894 |
+
0.29826030135154724,
|
| 895 |
+
0.29658982157707214,
|
| 896 |
+
0.2873019576072693,
|
| 897 |
+
0.2833050787448883,
|
| 898 |
+
0.27994805574417114,
|
| 899 |
+
0.2750612199306488,
|
| 900 |
+
0.2668859660625458,
|
| 901 |
+
0.25714653730392456,
|
| 902 |
+
0.25182783603668213,
|
| 903 |
+
0.25069114565849304,
|
| 904 |
+
0.24311591684818268,
|
| 905 |
+
0.24343299865722656,
|
| 906 |
+
0.23794493079185486,
|
| 907 |
+
0.23388665914535522,
|
| 908 |
+
0.22817164659500122,
|
| 909 |
+
0.22779357433319092,
|
| 910 |
+
0.2294483184814453,
|
| 911 |
+
0.22844713926315308,
|
| 912 |
+
0.23184555768966675,
|
| 913 |
+
0.22146819531917572,
|
| 914 |
+
0.22426211833953857,
|
| 915 |
+
0.22186093032360077,
|
| 916 |
+
0.2249176949262619,
|
| 917 |
+
0.22080540657043457,
|
| 918 |
+
0.22399508953094482,
|
| 919 |
+
0.2173675149679184,
|
| 920 |
+
0.2208639681339264,
|
| 921 |
+
0.22077171504497528,
|
| 922 |
+
0.22138890624046326,
|
| 923 |
+
0.22595320641994476,
|
| 924 |
+
0.22017161548137665,
|
| 925 |
+
0.21775898337364197,
|
| 926 |
+
0.22427847981452942,
|
| 927 |
+
0.22222276031970978,
|
| 928 |
+
0.22420811653137207,
|
| 929 |
+
0.22324113547801971,
|
| 930 |
+
0.22908048331737518,
|
| 931 |
+
0.22781133651733398,
|
| 932 |
+
0.23045624792575836,
|
| 933 |
+
0.23191936314105988,
|
| 934 |
+
0.23010753095149994,
|
| 935 |
+
0.2286965698003769,
|
| 936 |
+
0.2256595641374588,
|
| 937 |
+
0.22391031682491302,
|
| 938 |
+
0.22720178961753845,
|
| 939 |
+
0.22458872199058533,
|
| 940 |
+
0.21908141672611237,
|
| 941 |
+
0.21781863272190094,
|
| 942 |
+
0.22157607972621918,
|
| 943 |
+
0.22329872846603394,
|
| 944 |
+
0.22436219453811646,
|
| 945 |
+
0.22031615674495697,
|
| 946 |
+
0.22133824229240417,
|
| 947 |
+
0.21895863115787506,
|
| 948 |
+
0.21569904685020447,
|
| 949 |
+
0.21912707388401031,
|
| 950 |
+
0.2237694412469864,
|
| 951 |
+
0.22242595255374908,
|
| 952 |
+
0.22354666888713837,
|
| 953 |
+
0.22155342996120453,
|
| 954 |
+
0.2200615555047989,
|
| 955 |
+
0.22214236855506897,
|
| 956 |
+
0.22286343574523926,
|
| 957 |
+
0.21898429095745087,
|
| 958 |
+
0.21795101463794708,
|
| 959 |
+
0.2166079729795456,
|
| 960 |
+
0.21775244176387787,
|
| 961 |
+
0.21914467215538025,
|
| 962 |
+
0.22057823836803436,
|
| 963 |
+
0.21595270931720734,
|
| 964 |
+
0.21475619077682495,
|
| 965 |
+
0.2145148068666458,
|
| 966 |
+
0.2125515639781952,
|
| 967 |
+
0.21255271136760712,
|
| 968 |
+
0.21542948484420776,
|
| 969 |
+
0.21557892858982086,
|
| 970 |
+
0.22325363755226135,
|
| 971 |
+
0.22297166287899017,
|
| 972 |
+
0.2213776558637619,
|
| 973 |
+
0.22247739136219025,
|
| 974 |
+
0.22220821678638458,
|
| 975 |
+
0.2229536771774292,
|
| 976 |
+
0.2249082773923874,
|
| 977 |
+
0.22506743669509888,
|
| 978 |
+
0.223460391163826,
|
| 979 |
+
0.22405298054218292,
|
| 980 |
+
0.22543157637119293,
|
| 981 |
+
0.22438181936740875,
|
| 982 |
+
0.22402642667293549,
|
| 983 |
+
0.23021270334720612,
|
| 984 |
+
0.22955596446990967,
|
| 985 |
+
0.22911269962787628,
|
| 986 |
+
0.23038555681705475,
|
| 987 |
+
0.23054704070091248,
|
| 988 |
+
0.23122508823871613,
|
| 989 |
+
0.2306143045425415,
|
| 990 |
+
0.23163563013076782,
|
| 991 |
+
0.23052428662776947,
|
| 992 |
+
0.2300809919834137,
|
| 993 |
+
0.22999243438243866,
|
| 994 |
+
0.23001831769943237,
|
| 995 |
+
0.23135921359062195,
|
| 996 |
+
0.23247401416301727
|
| 997 |
],
|
| 998 |
"lr": [
|
| 999 |
1.6752136752136756e-05,
|
|
|
|
| 1161 |
7779
|
| 1162 |
],
|
| 1163 |
"eval_accuracy": [
|
| 1164 |
+
0.0,
|
| 1165 |
0.0,
|
| 1166 |
0.0,
|
| 1167 |
0.0,
|
|
|
|
| 1183 |
0.0
|
| 1184 |
]
|
| 1185 |
},
|
| 1186 |
+
"final_accuracy": 0.6407692307692308,
|
| 1187 |
"sft_eval": {
|
| 1188 |
"config": {
|
| 1189 |
"ops": "add_sub",
|
| 1190 |
"K": null,
|
| 1191 |
"mode": "sft",
|
| 1192 |
"n_digits": 6,
|
| 1193 |
+
"n_per_split": 100
|
| 1194 |
},
|
| 1195 |
"splits": {
|
| 1196 |
"add_S0": {
|
| 1197 |
+
"full_accuracy": 0.95,
|
| 1198 |
+
"digit_accuracy": 0.9928571428571429,
|
| 1199 |
+
"n_examples": 100,
|
| 1200 |
"per_subtask": {
|
| 1201 |
"SA": {
|
| 1202 |
+
"accuracy": 0.9917355371900827,
|
| 1203 |
+
"count": 605
|
| 1204 |
},
|
| 1205 |
"SS": {
|
| 1206 |
"accuracy": 1.0,
|
| 1207 |
+
"count": 95
|
| 1208 |
}
|
| 1209 |
}
|
| 1210 |
},
|
| 1211 |
"add_S1": {
|
| 1212 |
+
"full_accuracy": 0.88,
|
| 1213 |
+
"digit_accuracy": 0.9828571428571429,
|
| 1214 |
+
"n_examples": 100,
|
| 1215 |
"per_subtask": {
|
| 1216 |
"SA": {
|
| 1217 |
+
"accuracy": 0.9901960784313726,
|
| 1218 |
+
"count": 204
|
| 1219 |
},
|
| 1220 |
"SC": {
|
| 1221 |
+
"accuracy": 0.9881656804733728,
|
| 1222 |
+
"count": 169
|
| 1223 |
},
|
| 1224 |
"SS": {
|
| 1225 |
+
"accuracy": 1.0,
|
| 1226 |
+
"count": 31
|
| 1227 |
},
|
| 1228 |
"UC": {
|
| 1229 |
+
"accuracy": 0.972972972972973,
|
| 1230 |
+
"count": 296
|
| 1231 |
}
|
| 1232 |
}
|
| 1233 |
},
|
| 1234 |
"add_S2": {
|
| 1235 |
+
"full_accuracy": 0.79,
|
| 1236 |
+
"digit_accuracy": 0.97,
|
| 1237 |
+
"n_examples": 100,
|
| 1238 |
"per_subtask": {
|
| 1239 |
"SA": {
|
| 1240 |
+
"accuracy": 0.9938650306748467,
|
| 1241 |
+
"count": 163
|
| 1242 |
},
|
| 1243 |
"SC": {
|
| 1244 |
+
"accuracy": 0.9615384615384616,
|
| 1245 |
+
"count": 130
|
| 1246 |
},
|
| 1247 |
"SS": {
|
| 1248 |
+
"accuracy": 0.9655172413793104,
|
| 1249 |
+
"count": 87
|
| 1250 |
},
|
| 1251 |
"UC": {
|
| 1252 |
+
"accuracy": 0.9556650246305419,
|
| 1253 |
+
"count": 203
|
| 1254 |
},
|
| 1255 |
"US": {
|
| 1256 |
+
"accuracy": 0.9743589743589743,
|
| 1257 |
+
"count": 117
|
| 1258 |
}
|
| 1259 |
}
|
| 1260 |
},
|
| 1261 |
"add_S3": {
|
| 1262 |
+
"full_accuracy": 0.47,
|
| 1263 |
+
"digit_accuracy": 0.91,
|
| 1264 |
+
"n_examples": 100,
|
| 1265 |
"per_subtask": {
|
| 1266 |
"SA": {
|
| 1267 |
"accuracy": 1.0,
|
| 1268 |
+
"count": 121
|
| 1269 |
},
|
| 1270 |
"SC": {
|
| 1271 |
+
"accuracy": 0.9834710743801653,
|
| 1272 |
+
"count": 121
|
| 1273 |
},
|
| 1274 |
"SS": {
|
| 1275 |
"accuracy": 1.0,
|
| 1276 |
+
"count": 49
|
| 1277 |
},
|
| 1278 |
"UC": {
|
| 1279 |
+
"accuracy": 0.7365591397849462,
|
| 1280 |
+
"count": 186
|
| 1281 |
},
|
| 1282 |
"US": {
|
| 1283 |
+
"accuracy": 0.9461883408071748,
|
| 1284 |
+
"count": 223
|
| 1285 |
}
|
| 1286 |
}
|
| 1287 |
},
|
| 1288 |
"add_S4": {
|
| 1289 |
+
"full_accuracy": 0.25,
|
| 1290 |
+
"digit_accuracy": 0.7671428571428571,
|
| 1291 |
+
"n_examples": 100,
|
| 1292 |
"per_subtask": {
|
| 1293 |
"SA": {
|
| 1294 |
"accuracy": 1.0,
|
| 1295 |
+
"count": 104
|
| 1296 |
},
|
| 1297 |
"SC": {
|
| 1298 |
"accuracy": 1.0,
|
| 1299 |
+
"count": 106
|
| 1300 |
},
|
| 1301 |
"SS": {
|
| 1302 |
"accuracy": 1.0,
|
| 1303 |
+
"count": 23
|
| 1304 |
},
|
| 1305 |
"UC": {
|
| 1306 |
+
"accuracy": 0.60625,
|
| 1307 |
+
"count": 160
|
| 1308 |
},
|
| 1309 |
"US": {
|
| 1310 |
+
"accuracy": 0.6742671009771987,
|
| 1311 |
+
"count": 307
|
| 1312 |
}
|
| 1313 |
}
|
| 1314 |
},
|
| 1315 |
"add_S5": {
|
| 1316 |
+
"full_accuracy": 0.0,
|
| 1317 |
+
"digit_accuracy": 0.5,
|
| 1318 |
+
"n_examples": 100,
|
| 1319 |
"per_subtask": {
|
| 1320 |
"SA": {
|
| 1321 |
"accuracy": 1.0,
|
| 1322 |
+
"count": 100
|
| 1323 |
},
|
| 1324 |
"SC": {
|
| 1325 |
"accuracy": 1.0,
|
| 1326 |
+
"count": 100
|
| 1327 |
},
|
| 1328 |
"UC": {
|
| 1329 |
+
"accuracy": 0.08,
|
| 1330 |
+
"count": 100
|
| 1331 |
},
|
| 1332 |
"US": {
|
| 1333 |
+
"accuracy": 0.355,
|
| 1334 |
+
"count": 400
|
| 1335 |
}
|
| 1336 |
}
|
| 1337 |
},
|
| 1338 |
"add_S6": {
|
| 1339 |
+
"full_accuracy": 0.07,
|
| 1340 |
+
"digit_accuracy": 0.46714285714285714,
|
| 1341 |
+
"n_examples": 100,
|
| 1342 |
"per_subtask": {
|
| 1343 |
"SC": {
|
| 1344 |
"accuracy": 1.0,
|
| 1345 |
+
"count": 100
|
| 1346 |
},
|
| 1347 |
"UC": {
|
| 1348 |
+
"accuracy": 0.27,
|
| 1349 |
+
"count": 100
|
| 1350 |
},
|
| 1351 |
"US": {
|
| 1352 |
+
"accuracy": 0.4,
|
| 1353 |
+
"count": 500
|
| 1354 |
}
|
| 1355 |
}
|
| 1356 |
},
|
| 1357 |
"add_random": {
|
| 1358 |
+
"full_accuracy": 0.905,
|
| 1359 |
+
"digit_accuracy": 0.9835714285714285,
|
| 1360 |
"n_examples": 200,
|
| 1361 |
"per_subtask": {
|
| 1362 |
"SA": {
|
| 1363 |
+
"accuracy": 0.9932885906040269,
|
| 1364 |
+
"count": 447
|
| 1365 |
},
|
| 1366 |
"SC": {
|
| 1367 |
+
"accuracy": 0.996875,
|
| 1368 |
+
"count": 320
|
| 1369 |
},
|
| 1370 |
"SS": {
|
| 1371 |
+
"accuracy": 0.9821428571428571,
|
| 1372 |
+
"count": 56
|
| 1373 |
},
|
| 1374 |
"UC": {
|
| 1375 |
+
"accuracy": 0.9716446124763705,
|
| 1376 |
+
"count": 529
|
| 1377 |
},
|
| 1378 |
"US": {
|
| 1379 |
+
"accuracy": 0.9375,
|
| 1380 |
+
"count": 48
|
| 1381 |
}
|
| 1382 |
}
|
| 1383 |
},
|
| 1384 |
"add_C1": {
|
| 1385 |
+
"full_accuracy": 0.85,
|
| 1386 |
+
"digit_accuracy": 0.9785714285714285,
|
| 1387 |
+
"n_examples": 100,
|
| 1388 |
"per_subtask": {
|
| 1389 |
"SA": {
|
| 1390 |
"accuracy": 1.0,
|
| 1391 |
+
"count": 500
|
| 1392 |
},
|
| 1393 |
"SC": {
|
| 1394 |
"accuracy": 1.0,
|
| 1395 |
+
"count": 100
|
| 1396 |
},
|
| 1397 |
"UC": {
|
| 1398 |
+
"accuracy": 0.85,
|
| 1399 |
+
"count": 100
|
| 1400 |
}
|
| 1401 |
}
|
| 1402 |
},
|
| 1403 |
"add_C2": {
|
| 1404 |
"full_accuracy": 0.84,
|
| 1405 |
+
"digit_accuracy": 0.9771428571428571,
|
| 1406 |
+
"n_examples": 100,
|
| 1407 |
"per_subtask": {
|
| 1408 |
"SA": {
|
| 1409 |
"accuracy": 1.0,
|
| 1410 |
+
"count": 400
|
| 1411 |
},
|
| 1412 |
"SC": {
|
| 1413 |
"accuracy": 1.0,
|
| 1414 |
+
"count": 100
|
| 1415 |
},
|
| 1416 |
"UC": {
|
| 1417 |
+
"accuracy": 0.9102564102564102,
|
| 1418 |
+
"count": 156
|
| 1419 |
},
|
| 1420 |
"US": {
|
| 1421 |
+
"accuracy": 0.9545454545454546,
|
| 1422 |
+
"count": 44
|
| 1423 |
}
|
| 1424 |
}
|
| 1425 |
},
|
| 1426 |
"add_C3": {
|
| 1427 |
+
"full_accuracy": 0.58,
|
| 1428 |
+
"digit_accuracy": 0.9271428571428572,
|
| 1429 |
+
"n_examples": 100,
|
| 1430 |
"per_subtask": {
|
| 1431 |
"SA": {
|
| 1432 |
"accuracy": 1.0,
|
| 1433 |
+
"count": 300
|
| 1434 |
},
|
| 1435 |
"SC": {
|
| 1436 |
"accuracy": 1.0,
|
| 1437 |
+
"count": 100
|
| 1438 |
},
|
| 1439 |
"UC": {
|
| 1440 |
+
"accuracy": 0.7889447236180904,
|
| 1441 |
+
"count": 199
|
| 1442 |
},
|
| 1443 |
"US": {
|
| 1444 |
+
"accuracy": 0.9108910891089109,
|
| 1445 |
+
"count": 101
|
| 1446 |
}
|
| 1447 |
}
|
| 1448 |
},
|
| 1449 |
"add_C4": {
|
| 1450 |
+
"full_accuracy": 0.53,
|
| 1451 |
+
"digit_accuracy": 0.9128571428571428,
|
| 1452 |
+
"n_examples": 100,
|
| 1453 |
"per_subtask": {
|
| 1454 |
"SA": {
|
| 1455 |
"accuracy": 1.0,
|
| 1456 |
+
"count": 200
|
| 1457 |
},
|
| 1458 |
"SC": {
|
| 1459 |
"accuracy": 1.0,
|
| 1460 |
+
"count": 100
|
| 1461 |
},
|
| 1462 |
"UC": {
|
| 1463 |
+
"accuracy": 0.8409090909090909,
|
| 1464 |
+
"count": 264
|
| 1465 |
},
|
| 1466 |
"US": {
|
| 1467 |
+
"accuracy": 0.8602941176470589,
|
| 1468 |
+
"count": 136
|
| 1469 |
}
|
| 1470 |
}
|
| 1471 |
},
|
| 1472 |
"add_C5": {
|
| 1473 |
+
"full_accuracy": 0.56,
|
| 1474 |
+
"digit_accuracy": 0.8928571428571429,
|
| 1475 |
+
"n_examples": 100,
|
| 1476 |
"per_subtask": {
|
| 1477 |
"SA": {
|
| 1478 |
"accuracy": 1.0,
|
| 1479 |
+
"count": 100
|
| 1480 |
},
|
| 1481 |
"SC": {
|
| 1482 |
"accuracy": 1.0,
|
| 1483 |
+
"count": 100
|
| 1484 |
},
|
| 1485 |
"UC": {
|
| 1486 |
+
"accuracy": 0.8580645161290322,
|
| 1487 |
+
"count": 310
|
| 1488 |
},
|
| 1489 |
"US": {
|
| 1490 |
+
"accuracy": 0.8368421052631579,
|
| 1491 |
+
"count": 190
|
| 1492 |
}
|
| 1493 |
}
|
| 1494 |
},
|
| 1495 |
"add_C6": {
|
| 1496 |
+
"full_accuracy": 0.63,
|
| 1497 |
+
"digit_accuracy": 0.8971428571428571,
|
| 1498 |
+
"n_examples": 100,
|
| 1499 |
"per_subtask": {
|
| 1500 |
"SC": {
|
| 1501 |
"accuracy": 1.0,
|
| 1502 |
+
"count": 100
|
| 1503 |
},
|
| 1504 |
"UC": {
|
| 1505 |
+
"accuracy": 0.9027027027027027,
|
| 1506 |
+
"count": 370
|
| 1507 |
},
|
| 1508 |
"US": {
|
| 1509 |
+
"accuracy": 0.8434782608695652,
|
| 1510 |
+
"count": 230
|
| 1511 |
}
|
| 1512 |
}
|
| 1513 |
},
|
| 1514 |
"sub_M0": {
|
| 1515 |
+
"full_accuracy": 0.96,
|
| 1516 |
+
"digit_accuracy": 0.9942857142857143,
|
| 1517 |
+
"n_examples": 100,
|
| 1518 |
"per_subtask": {
|
| 1519 |
"MD": {
|
| 1520 |
+
"accuracy": 0.9934959349593496,
|
| 1521 |
+
"count": 615
|
| 1522 |
},
|
| 1523 |
"ME": {
|
| 1524 |
"accuracy": 1.0,
|
| 1525 |
+
"count": 85
|
| 1526 |
}
|
| 1527 |
}
|
| 1528 |
},
|
| 1529 |
"sub_M1": {
|
| 1530 |
+
"full_accuracy": 0.85,
|
| 1531 |
+
"digit_accuracy": 0.9771428571428571,
|
| 1532 |
+
"n_examples": 100,
|
| 1533 |
"per_subtask": {
|
| 1534 |
"MD": {
|
| 1535 |
+
"accuracy": 0.9863013698630136,
|
| 1536 |
+
"count": 292
|
| 1537 |
},
|
| 1538 |
"MB": {
|
| 1539 |
+
"accuracy": 0.9861111111111112,
|
| 1540 |
+
"count": 144
|
| 1541 |
},
|
| 1542 |
"ME": {
|
| 1543 |
+
"accuracy": 1.0,
|
| 1544 |
+
"count": 25
|
| 1545 |
},
|
| 1546 |
"UB": {
|
| 1547 |
+
"accuracy": 0.9581589958158996,
|
| 1548 |
+
"count": 239
|
| 1549 |
}
|
| 1550 |
}
|
| 1551 |
},
|
| 1552 |
"sub_M2": {
|
| 1553 |
+
"full_accuracy": 0.59,
|
| 1554 |
+
"digit_accuracy": 0.9371428571428572,
|
| 1555 |
+
"n_examples": 100,
|
| 1556 |
"per_subtask": {
|
| 1557 |
"MD": {
|
| 1558 |
+
"accuracy": 0.990521327014218,
|
| 1559 |
+
"count": 211
|
| 1560 |
},
|
| 1561 |
"MB": {
|
| 1562 |
+
"accuracy": 0.9391304347826087,
|
| 1563 |
+
"count": 115
|
| 1564 |
},
|
| 1565 |
"ME": {
|
| 1566 |
+
"accuracy": 0.9882352941176471,
|
| 1567 |
+
"count": 85
|
| 1568 |
},
|
| 1569 |
"UB": {
|
| 1570 |
+
"accuracy": 0.8121546961325967,
|
| 1571 |
+
"count": 181
|
| 1572 |
},
|
| 1573 |
"UD": {
|
| 1574 |
+
"accuracy": 1.0,
|
| 1575 |
+
"count": 108
|
| 1576 |
}
|
| 1577 |
}
|
| 1578 |
},
|
| 1579 |
"sub_M3": {
|
| 1580 |
+
"full_accuracy": 0.3,
|
| 1581 |
+
"digit_accuracy": 0.8628571428571429,
|
| 1582 |
+
"n_examples": 100,
|
| 1583 |
"per_subtask": {
|
| 1584 |
"MD": {
|
| 1585 |
+
"accuracy": 0.9888268156424581,
|
| 1586 |
+
"count": 179
|
| 1587 |
},
|
| 1588 |
"MB": {
|
| 1589 |
+
"accuracy": 0.970873786407767,
|
| 1590 |
+
"count": 103
|
| 1591 |
},
|
| 1592 |
"ME": {
|
| 1593 |
"accuracy": 1.0,
|
| 1594 |
+
"count": 56
|
| 1595 |
},
|
| 1596 |
"UB": {
|
| 1597 |
+
"accuracy": 0.5906040268456376,
|
| 1598 |
+
"count": 149
|
| 1599 |
},
|
| 1600 |
"UD": {
|
| 1601 |
+
"accuracy": 0.8591549295774648,
|
| 1602 |
+
"count": 213
|
| 1603 |
}
|
| 1604 |
}
|
| 1605 |
},
|
| 1606 |
"sub_M4": {
|
| 1607 |
+
"full_accuracy": 0.05,
|
| 1608 |
+
"digit_accuracy": 0.7171428571428572,
|
| 1609 |
+
"n_examples": 100,
|
| 1610 |
"per_subtask": {
|
| 1611 |
"MD": {
|
| 1612 |
"accuracy": 1.0,
|
| 1613 |
+
"count": 200
|
| 1614 |
},
|
| 1615 |
"MB": {
|
| 1616 |
"accuracy": 1.0,
|
| 1617 |
+
"count": 100
|
| 1618 |
},
|
| 1619 |
"UB": {
|
| 1620 |
+
"accuracy": 0.5,
|
| 1621 |
+
"count": 100
|
| 1622 |
},
|
| 1623 |
"UD": {
|
| 1624 |
+
"accuracy": 0.5066666666666667,
|
| 1625 |
+
"count": 300
|
| 1626 |
}
|
| 1627 |
}
|
| 1628 |
},
|
| 1629 |
"sub_M5": {
|
| 1630 |
+
"full_accuracy": 0.06,
|
| 1631 |
+
"digit_accuracy": 0.6242857142857143,
|
| 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": 0.52,
|
| 1644 |
+
"count": 100
|
| 1645 |
},
|
| 1646 |
"UD": {
|
| 1647 |
+
"accuracy": 0.4625,
|
| 1648 |
+
"count": 400
|
| 1649 |
}
|
| 1650 |
}
|
| 1651 |
},
|
| 1652 |
"sub_random": {
|
| 1653 |
+
"full_accuracy": 0.86,
|
| 1654 |
+
"digit_accuracy": 0.9792857142857143,
|
| 1655 |
"n_examples": 200,
|
| 1656 |
"per_subtask": {
|
| 1657 |
"MD": {
|
| 1658 |
+
"accuracy": 0.9966666666666667,
|
| 1659 |
+
"count": 600
|
| 1660 |
},
|
| 1661 |
"MB": {
|
| 1662 |
+
"accuracy": 0.9812734082397003,
|
| 1663 |
+
"count": 267
|
| 1664 |
},
|
| 1665 |
"ME": {
|
| 1666 |
"accuracy": 1.0,
|
| 1667 |
"count": 53
|
| 1668 |
},
|
| 1669 |
"UB": {
|
| 1670 |
+
"accuracy": 0.9521640091116174,
|
| 1671 |
+
"count": 439
|
| 1672 |
},
|
| 1673 |
"UD": {
|
| 1674 |
+
"accuracy": 0.975609756097561,
|
| 1675 |
+
"count": 41
|
| 1676 |
}
|
| 1677 |
}
|
| 1678 |
},
|
| 1679 |
"sub_B3": {
|
| 1680 |
+
"full_accuracy": 0.61,
|
| 1681 |
+
"digit_accuracy": 0.9314285714285714,
|
| 1682 |
+
"n_examples": 100,
|
| 1683 |
"per_subtask": {
|
| 1684 |
"MD": {
|
| 1685 |
+
"accuracy": 0.99,
|
| 1686 |
+
"count": 300
|
| 1687 |
},
|
| 1688 |
"MB": {
|
| 1689 |
+
"accuracy": 0.98,
|
| 1690 |
+
"count": 100
|
| 1691 |
},
|
| 1692 |
"UB": {
|
| 1693 |
+
"accuracy": 0.8527918781725888,
|
| 1694 |
+
"count": 197
|
| 1695 |
},
|
| 1696 |
"UD": {
|
| 1697 |
+
"accuracy": 0.8640776699029126,
|
| 1698 |
+
"count": 103
|
| 1699 |
}
|
| 1700 |
}
|
| 1701 |
},
|
| 1702 |
"sub_B4": {
|
| 1703 |
+
"full_accuracy": 0.5,
|
| 1704 |
+
"digit_accuracy": 0.9,
|
| 1705 |
+
"n_examples": 100,
|
| 1706 |
"per_subtask": {
|
| 1707 |
"MD": {
|
| 1708 |
+
"accuracy": 0.995,
|
| 1709 |
+
"count": 200
|
| 1710 |
},
|
| 1711 |
"MB": {
|
| 1712 |
+
"accuracy": 0.99,
|
| 1713 |
+
"count": 100
|
| 1714 |
},
|
| 1715 |
"UB": {
|
| 1716 |
+
"accuracy": 0.8299595141700404,
|
| 1717 |
+
"count": 247
|
| 1718 |
},
|
| 1719 |
"UD": {
|
| 1720 |
+
"accuracy": 0.8300653594771242,
|
| 1721 |
+
"count": 153
|
| 1722 |
}
|
| 1723 |
}
|
| 1724 |
},
|
| 1725 |
"sub_B5": {
|
| 1726 |
+
"full_accuracy": 0.5,
|
| 1727 |
+
"digit_accuracy": 0.8842857142857142,
|
| 1728 |
+
"n_examples": 100,
|
| 1729 |
"per_subtask": {
|
| 1730 |
"MD": {
|
| 1731 |
"accuracy": 1.0,
|
| 1732 |
+
"count": 100
|
| 1733 |
},
|
| 1734 |
"MB": {
|
| 1735 |
"accuracy": 1.0,
|
| 1736 |
+
"count": 100
|
| 1737 |
},
|
| 1738 |
"UB": {
|
| 1739 |
+
"accuracy": 0.87248322147651,
|
| 1740 |
+
"count": 298
|
| 1741 |
},
|
| 1742 |
"UD": {
|
| 1743 |
+
"accuracy": 0.7871287128712872,
|
| 1744 |
+
"count": 202
|
| 1745 |
}
|
| 1746 |
}
|
| 1747 |
}
|
| 1748 |
},
|
| 1749 |
"summary": {
|
| 1750 |
+
"overall_accuracy": 0.59,
|
| 1751 |
+
"digit_accuracy": 0.8818131868131868,
|
| 1752 |
+
"total_examples": 2600,
|
| 1753 |
"n_splits": 24
|
| 1754 |
}
|
| 1755 |
},
|
|
|
|
| 1759 |
"K": 1,
|
| 1760 |
"mode": "sorl",
|
| 1761 |
"n_digits": 6,
|
| 1762 |
+
"n_per_split": 100
|
| 1763 |
},
|
| 1764 |
"splits": {
|
| 1765 |
"add_S0": {
|
| 1766 |
+
"full_accuracy": 0.93,
|
| 1767 |
+
"digit_accuracy": 0.9885714285714285,
|
| 1768 |
+
"n_examples": 100,
|
| 1769 |
"per_subtask": {
|
| 1770 |
"SA": {
|
| 1771 |
+
"accuracy": 0.9884297520661157,
|
| 1772 |
+
"count": 605
|
| 1773 |
},
|
| 1774 |
"SS": {
|
| 1775 |
+
"accuracy": 0.9894736842105263,
|
| 1776 |
+
"count": 95
|
| 1777 |
}
|
| 1778 |
}
|
| 1779 |
},
|
| 1780 |
"add_S1": {
|
| 1781 |
+
"full_accuracy": 0.87,
|
| 1782 |
+
"digit_accuracy": 0.98,
|
| 1783 |
+
"n_examples": 100,
|
| 1784 |
"per_subtask": {
|
| 1785 |
"SA": {
|
| 1786 |
+
"accuracy": 0.9950980392156863,
|
| 1787 |
+
"count": 204
|
| 1788 |
},
|
| 1789 |
"SC": {
|
| 1790 |
+
"accuracy": 0.9763313609467456,
|
| 1791 |
+
"count": 169
|
| 1792 |
},
|
| 1793 |
"SS": {
|
| 1794 |
"accuracy": 1.0,
|
| 1795 |
+
"count": 31
|
| 1796 |
},
|
| 1797 |
"UC": {
|
| 1798 |
+
"accuracy": 0.9695945945945946,
|
| 1799 |
+
"count": 296
|
| 1800 |
}
|
| 1801 |
}
|
| 1802 |
},
|
| 1803 |
"add_S2": {
|
| 1804 |
+
"full_accuracy": 0.85,
|
| 1805 |
+
"digit_accuracy": 0.9757142857142858,
|
| 1806 |
+
"n_examples": 100,
|
| 1807 |
"per_subtask": {
|
| 1808 |
"SA": {
|
| 1809 |
+
"accuracy": 0.9815950920245399,
|
| 1810 |
+
"count": 163
|
| 1811 |
},
|
| 1812 |
"SC": {
|
| 1813 |
+
"accuracy": 0.9769230769230769,
|
| 1814 |
+
"count": 130
|
| 1815 |
},
|
| 1816 |
"SS": {
|
| 1817 |
+
"accuracy": 0.9770114942528736,
|
| 1818 |
+
"count": 87
|
| 1819 |
},
|
| 1820 |
"UC": {
|
| 1821 |
+
"accuracy": 0.9556650246305419,
|
| 1822 |
+
"count": 203
|
| 1823 |
},
|
| 1824 |
"US": {
|
| 1825 |
"accuracy": 1.0,
|
| 1826 |
+
"count": 117
|
| 1827 |
}
|
| 1828 |
}
|
| 1829 |
},
|
| 1830 |
"add_S3": {
|
| 1831 |
+
"full_accuracy": 0.64,
|
| 1832 |
+
"digit_accuracy": 0.9314285714285714,
|
| 1833 |
+
"n_examples": 100,
|
| 1834 |
"per_subtask": {
|
| 1835 |
"SA": {
|
| 1836 |
+
"accuracy": 0.9917355371900827,
|
| 1837 |
+
"count": 121
|
| 1838 |
},
|
| 1839 |
"SC": {
|
| 1840 |
+
"accuracy": 0.9752066115702479,
|
| 1841 |
+
"count": 121
|
| 1842 |
},
|
| 1843 |
"SS": {
|
| 1844 |
+
"accuracy": 1.0,
|
| 1845 |
+
"count": 49
|
| 1846 |
},
|
| 1847 |
"UC": {
|
| 1848 |
+
"accuracy": 0.8440860215053764,
|
| 1849 |
+
"count": 186
|
| 1850 |
},
|
| 1851 |
"US": {
|
| 1852 |
+
"accuracy": 0.9327354260089686,
|
| 1853 |
+
"count": 223
|
| 1854 |
}
|
| 1855 |
}
|
| 1856 |
},
|
| 1857 |
"add_S4": {
|
| 1858 |
+
"full_accuracy": 0.41,
|
| 1859 |
+
"digit_accuracy": 0.8485714285714285,
|
| 1860 |
+
"n_examples": 100,
|
| 1861 |
"per_subtask": {
|
| 1862 |
"SA": {
|
| 1863 |
"accuracy": 1.0,
|
| 1864 |
+
"count": 104
|
| 1865 |
},
|
| 1866 |
"SC": {
|
| 1867 |
"accuracy": 1.0,
|
| 1868 |
+
"count": 106
|
| 1869 |
},
|
| 1870 |
"SS": {
|
| 1871 |
"accuracy": 1.0,
|
| 1872 |
+
"count": 23
|
| 1873 |
},
|
| 1874 |
"UC": {
|
| 1875 |
+
"accuracy": 0.7375,
|
| 1876 |
+
"count": 160
|
| 1877 |
},
|
| 1878 |
"US": {
|
| 1879 |
+
"accuracy": 0.7915309446254072,
|
| 1880 |
+
"count": 307
|
| 1881 |
}
|
| 1882 |
}
|
| 1883 |
},
|
| 1884 |
"add_S5": {
|
| 1885 |
+
"full_accuracy": 0.07,
|
| 1886 |
+
"digit_accuracy": 0.64,
|
| 1887 |
+
"n_examples": 100,
|
| 1888 |
"per_subtask": {
|
| 1889 |
"SA": {
|
| 1890 |
"accuracy": 1.0,
|
| 1891 |
+
"count": 100
|
| 1892 |
},
|
| 1893 |
"SC": {
|
| 1894 |
"accuracy": 1.0,
|
| 1895 |
+
"count": 100
|
| 1896 |
},
|
| 1897 |
"UC": {
|
| 1898 |
+
"accuracy": 0.3,
|
| 1899 |
+
"count": 100
|
| 1900 |
},
|
| 1901 |
"US": {
|
| 1902 |
+
"accuracy": 0.545,
|
| 1903 |
+
"count": 400
|
| 1904 |
}
|
| 1905 |
}
|
| 1906 |
},
|
| 1907 |
"add_S6": {
|
| 1908 |
+
"full_accuracy": 0.12,
|
| 1909 |
+
"digit_accuracy": 0.5871428571428572,
|
| 1910 |
+
"n_examples": 100,
|
| 1911 |
"per_subtask": {
|
| 1912 |
"SC": {
|
| 1913 |
"accuracy": 1.0,
|
| 1914 |
+
"count": 100
|
| 1915 |
},
|
| 1916 |
"UC": {
|
| 1917 |
+
"accuracy": 0.3,
|
| 1918 |
+
"count": 100
|
| 1919 |
},
|
| 1920 |
"US": {
|
| 1921 |
+
"accuracy": 0.562,
|
| 1922 |
+
"count": 500
|
| 1923 |
}
|
| 1924 |
}
|
| 1925 |
},
|
| 1926 |
"add_random": {
|
| 1927 |
+
"full_accuracy": 0.93,
|
| 1928 |
+
"digit_accuracy": 0.9885714285714285,
|
| 1929 |
"n_examples": 200,
|
| 1930 |
"per_subtask": {
|
| 1931 |
"SA": {
|
| 1932 |
+
"accuracy": 0.9955257270693513,
|
| 1933 |
+
"count": 447
|
| 1934 |
},
|
| 1935 |
"SC": {
|
| 1936 |
+
"accuracy": 0.99375,
|
| 1937 |
+
"count": 320
|
| 1938 |
},
|
| 1939 |
"SS": {
|
| 1940 |
+
"accuracy": 0.9821428571428571,
|
| 1941 |
+
"count": 56
|
| 1942 |
},
|
| 1943 |
"UC": {
|
| 1944 |
+
"accuracy": 0.9810964083175804,
|
| 1945 |
+
"count": 529
|
| 1946 |
},
|
| 1947 |
"US": {
|
| 1948 |
+
"accuracy": 0.9791666666666666,
|
| 1949 |
+
"count": 48
|
| 1950 |
}
|
| 1951 |
}
|
| 1952 |
},
|
| 1953 |
"add_C1": {
|
| 1954 |
+
"full_accuracy": 0.87,
|
| 1955 |
+
"digit_accuracy": 0.9814285714285714,
|
| 1956 |
+
"n_examples": 100,
|
| 1957 |
"per_subtask": {
|
| 1958 |
"SA": {
|
| 1959 |
"accuracy": 1.0,
|
| 1960 |
+
"count": 500
|
| 1961 |
},
|
| 1962 |
"SC": {
|
| 1963 |
"accuracy": 1.0,
|
| 1964 |
+
"count": 100
|
| 1965 |
},
|
| 1966 |
"UC": {
|
| 1967 |
+
"accuracy": 0.87,
|
| 1968 |
+
"count": 100
|
| 1969 |
}
|
| 1970 |
}
|
| 1971 |
},
|
| 1972 |
"add_C2": {
|
| 1973 |
+
"full_accuracy": 0.79,
|
| 1974 |
+
"digit_accuracy": 0.9685714285714285,
|
| 1975 |
+
"n_examples": 100,
|
| 1976 |
"per_subtask": {
|
| 1977 |
"SA": {
|
| 1978 |
"accuracy": 1.0,
|
| 1979 |
+
"count": 400
|
| 1980 |
},
|
| 1981 |
"SC": {
|
| 1982 |
"accuracy": 1.0,
|
| 1983 |
+
"count": 100
|
| 1984 |
},
|
| 1985 |
"UC": {
|
| 1986 |
+
"accuracy": 0.8653846153846154,
|
| 1987 |
+
"count": 156
|
| 1988 |
},
|
| 1989 |
"US": {
|
| 1990 |
+
"accuracy": 0.9772727272727273,
|
| 1991 |
+
"count": 44
|
| 1992 |
}
|
| 1993 |
}
|
| 1994 |
},
|
| 1995 |
"add_C3": {
|
| 1996 |
"full_accuracy": 0.58,
|
| 1997 |
+
"digit_accuracy": 0.92,
|
| 1998 |
+
"n_examples": 100,
|
| 1999 |
"per_subtask": {
|
| 2000 |
"SA": {
|
| 2001 |
"accuracy": 1.0,
|
| 2002 |
+
"count": 300
|
| 2003 |
},
|
| 2004 |
"SC": {
|
| 2005 |
"accuracy": 1.0,
|
| 2006 |
+
"count": 100
|
| 2007 |
},
|
| 2008 |
"UC": {
|
| 2009 |
+
"accuracy": 0.7788944723618091,
|
| 2010 |
+
"count": 199
|
| 2011 |
},
|
| 2012 |
"US": {
|
| 2013 |
+
"accuracy": 0.8811881188118812,
|
| 2014 |
+
"count": 101
|
| 2015 |
}
|
| 2016 |
}
|
| 2017 |
},
|
| 2018 |
"add_C4": {
|
| 2019 |
+
"full_accuracy": 0.64,
|
| 2020 |
+
"digit_accuracy": 0.9214285714285714,
|
| 2021 |
+
"n_examples": 100,
|
| 2022 |
"per_subtask": {
|
| 2023 |
"SA": {
|
| 2024 |
"accuracy": 1.0,
|
| 2025 |
+
"count": 200
|
| 2026 |
},
|
| 2027 |
"SC": {
|
| 2028 |
"accuracy": 1.0,
|
| 2029 |
+
"count": 100
|
| 2030 |
},
|
| 2031 |
"UC": {
|
| 2032 |
+
"accuracy": 0.8636363636363636,
|
| 2033 |
+
"count": 264
|
| 2034 |
},
|
| 2035 |
"US": {
|
| 2036 |
+
"accuracy": 0.8602941176470589,
|
| 2037 |
+
"count": 136
|
| 2038 |
}
|
| 2039 |
}
|
| 2040 |
},
|
| 2041 |
"add_C5": {
|
| 2042 |
+
"full_accuracy": 0.59,
|
| 2043 |
+
"digit_accuracy": 0.9114285714285715,
|
| 2044 |
+
"n_examples": 100,
|
| 2045 |
"per_subtask": {
|
| 2046 |
"SA": {
|
| 2047 |
"accuracy": 1.0,
|
| 2048 |
+
"count": 100
|
| 2049 |
},
|
| 2050 |
"SC": {
|
| 2051 |
"accuracy": 1.0,
|
| 2052 |
+
"count": 100
|
| 2053 |
},
|
| 2054 |
"UC": {
|
| 2055 |
+
"accuracy": 0.8838709677419355,
|
| 2056 |
+
"count": 310
|
| 2057 |
},
|
| 2058 |
"US": {
|
| 2059 |
+
"accuracy": 0.8631578947368421,
|
| 2060 |
+
"count": 190
|
| 2061 |
}
|
| 2062 |
}
|
| 2063 |
},
|
| 2064 |
"add_C6": {
|
| 2065 |
+
"full_accuracy": 0.65,
|
| 2066 |
+
"digit_accuracy": 0.9014285714285715,
|
| 2067 |
+
"n_examples": 100,
|
| 2068 |
"per_subtask": {
|
| 2069 |
"SC": {
|
| 2070 |
"accuracy": 1.0,
|
| 2071 |
+
"count": 100
|
| 2072 |
},
|
| 2073 |
"UC": {
|
| 2074 |
+
"accuracy": 0.8945945945945946,
|
| 2075 |
+
"count": 370
|
| 2076 |
},
|
| 2077 |
"US": {
|
| 2078 |
+
"accuracy": 0.8695652173913043,
|
| 2079 |
+
"count": 230
|
| 2080 |
}
|
| 2081 |
}
|
| 2082 |
},
|
| 2083 |
"sub_M0": {
|
| 2084 |
+
"full_accuracy": 0.93,
|
| 2085 |
+
"digit_accuracy": 0.99,
|
| 2086 |
+
"n_examples": 100,
|
| 2087 |
"per_subtask": {
|
| 2088 |
"MD": {
|
| 2089 |
+
"accuracy": 0.9886178861788618,
|
| 2090 |
+
"count": 615
|
| 2091 |
},
|
| 2092 |
"ME": {
|
| 2093 |
+
"accuracy": 1.0,
|
| 2094 |
+
"count": 85
|
| 2095 |
}
|
| 2096 |
}
|
| 2097 |
},
|
| 2098 |
"sub_M1": {
|
| 2099 |
+
"full_accuracy": 0.89,
|
| 2100 |
+
"digit_accuracy": 0.9842857142857143,
|
| 2101 |
+
"n_examples": 100,
|
| 2102 |
"per_subtask": {
|
| 2103 |
"MD": {
|
| 2104 |
+
"accuracy": 0.9965753424657534,
|
| 2105 |
+
"count": 292
|
| 2106 |
},
|
| 2107 |
"MB": {
|
| 2108 |
"accuracy": 0.9861111111111112,
|
| 2109 |
+
"count": 144
|
| 2110 |
},
|
| 2111 |
"ME": {
|
| 2112 |
+
"accuracy": 1.0,
|
| 2113 |
+
"count": 25
|
| 2114 |
},
|
| 2115 |
"UB": {
|
| 2116 |
+
"accuracy": 0.9665271966527197,
|
| 2117 |
+
"count": 239
|
| 2118 |
}
|
| 2119 |
}
|
| 2120 |
},
|
| 2121 |
"sub_M2": {
|
| 2122 |
+
"full_accuracy": 0.7,
|
| 2123 |
+
"digit_accuracy": 0.9542857142857143,
|
| 2124 |
+
"n_examples": 100,
|
| 2125 |
"per_subtask": {
|
| 2126 |
"MD": {
|
| 2127 |
+
"accuracy": 0.995260663507109,
|
| 2128 |
+
"count": 211
|
| 2129 |
},
|
| 2130 |
"MB": {
|
| 2131 |
+
"accuracy": 0.9739130434782609,
|
| 2132 |
+
"count": 115
|
| 2133 |
},
|
| 2134 |
"ME": {
|
| 2135 |
+
"accuracy": 0.9882352941176471,
|
| 2136 |
+
"count": 85
|
| 2137 |
},
|
| 2138 |
"UB": {
|
| 2139 |
+
"accuracy": 0.850828729281768,
|
| 2140 |
+
"count": 181
|
| 2141 |
},
|
| 2142 |
"UD": {
|
| 2143 |
+
"accuracy": 1.0,
|
| 2144 |
+
"count": 108
|
| 2145 |
}
|
| 2146 |
}
|
| 2147 |
},
|
| 2148 |
"sub_M3": {
|
| 2149 |
+
"full_accuracy": 0.35,
|
| 2150 |
+
"digit_accuracy": 0.8571428571428571,
|
| 2151 |
+
"n_examples": 100,
|
| 2152 |
"per_subtask": {
|
| 2153 |
"MD": {
|
| 2154 |
+
"accuracy": 0.9888268156424581,
|
| 2155 |
+
"count": 179
|
| 2156 |
},
|
| 2157 |
"MB": {
|
| 2158 |
+
"accuracy": 0.970873786407767,
|
| 2159 |
+
"count": 103
|
| 2160 |
},
|
| 2161 |
"ME": {
|
| 2162 |
+
"accuracy": 1.0,
|
| 2163 |
+
"count": 56
|
| 2164 |
},
|
| 2165 |
"UB": {
|
| 2166 |
+
"accuracy": 0.610738255033557,
|
| 2167 |
+
"count": 149
|
| 2168 |
},
|
| 2169 |
"UD": {
|
| 2170 |
+
"accuracy": 0.8262910798122066,
|
| 2171 |
+
"count": 213
|
| 2172 |
}
|
| 2173 |
}
|
| 2174 |
},
|
| 2175 |
"sub_M4": {
|
| 2176 |
+
"full_accuracy": 0.23,
|
| 2177 |
+
"digit_accuracy": 0.77,
|
| 2178 |
+
"n_examples": 100,
|
| 2179 |
"per_subtask": {
|
| 2180 |
"MD": {
|
| 2181 |
"accuracy": 1.0,
|
| 2182 |
+
"count": 200
|
| 2183 |
},
|
| 2184 |
"MB": {
|
| 2185 |
"accuracy": 1.0,
|
| 2186 |
+
"count": 100
|
| 2187 |
},
|
| 2188 |
"UB": {
|
| 2189 |
+
"accuracy": 0.45,
|
| 2190 |
+
"count": 100
|
| 2191 |
},
|
| 2192 |
"UD": {
|
| 2193 |
+
"accuracy": 0.6466666666666666,
|
| 2194 |
+
"count": 300
|
| 2195 |
}
|
| 2196 |
}
|
| 2197 |
},
|
| 2198 |
"sub_M5": {
|
| 2199 |
+
"full_accuracy": 0.12,
|
| 2200 |
+
"digit_accuracy": 0.6314285714285715,
|
| 2201 |
+
"n_examples": 100,
|
| 2202 |
"per_subtask": {
|
| 2203 |
"MD": {
|
| 2204 |
"accuracy": 1.0,
|
| 2205 |
+
"count": 100
|
| 2206 |
},
|
| 2207 |
"MB": {
|
| 2208 |
"accuracy": 1.0,
|
| 2209 |
+
"count": 100
|
| 2210 |
},
|
| 2211 |
"UB": {
|
| 2212 |
+
"accuracy": 0.48,
|
| 2213 |
+
"count": 100
|
| 2214 |
},
|
| 2215 |
"UD": {
|
| 2216 |
+
"accuracy": 0.485,
|
| 2217 |
+
"count": 400
|
| 2218 |
}
|
| 2219 |
}
|
| 2220 |
},
|
| 2221 |
"sub_random": {
|
| 2222 |
+
"full_accuracy": 0.91,
|
| 2223 |
+
"digit_accuracy": 0.9864285714285714,
|
| 2224 |
"n_examples": 200,
|
| 2225 |
"per_subtask": {
|
| 2226 |
"MD": {
|
| 2227 |
+
"accuracy": 0.9983333333333333,
|
| 2228 |
+
"count": 600
|
| 2229 |
},
|
| 2230 |
"MB": {
|
| 2231 |
+
"accuracy": 0.9850187265917603,
|
| 2232 |
+
"count": 267
|
| 2233 |
},
|
| 2234 |
"ME": {
|
| 2235 |
"accuracy": 1.0,
|
| 2236 |
"count": 53
|
| 2237 |
},
|
| 2238 |
"UB": {
|
| 2239 |
+
"accuracy": 0.9703872437357631,
|
| 2240 |
+
"count": 439
|
| 2241 |
},
|
| 2242 |
"UD": {
|
| 2243 |
+
"accuracy": 0.975609756097561,
|
| 2244 |
+
"count": 41
|
| 2245 |
}
|
| 2246 |
}
|
| 2247 |
},
|
| 2248 |
"sub_B3": {
|
| 2249 |
+
"full_accuracy": 0.6,
|
| 2250 |
+
"digit_accuracy": 0.9214285714285714,
|
| 2251 |
+
"n_examples": 100,
|
| 2252 |
"per_subtask": {
|
| 2253 |
"MD": {
|
| 2254 |
"accuracy": 0.9933333333333333,
|
| 2255 |
+
"count": 300
|
| 2256 |
},
|
| 2257 |
"MB": {
|
| 2258 |
"accuracy": 1.0,
|
| 2259 |
+
"count": 100
|
| 2260 |
},
|
| 2261 |
"UB": {
|
| 2262 |
+
"accuracy": 0.817258883248731,
|
| 2263 |
+
"count": 197
|
| 2264 |
},
|
| 2265 |
"UD": {
|
| 2266 |
+
"accuracy": 0.8349514563106796,
|
| 2267 |
+
"count": 103
|
| 2268 |
}
|
| 2269 |
}
|
| 2270 |
},
|
| 2271 |
"sub_B4": {
|
| 2272 |
+
"full_accuracy": 0.62,
|
| 2273 |
+
"digit_accuracy": 0.9171428571428571,
|
| 2274 |
+
"n_examples": 100,
|
| 2275 |
"per_subtask": {
|
| 2276 |
"MD": {
|
| 2277 |
+
"accuracy": 0.995,
|
| 2278 |
+
"count": 200
|
| 2279 |
},
|
| 2280 |
"MB": {
|
| 2281 |
+
"accuracy": 0.99,
|
| 2282 |
+
"count": 100
|
| 2283 |
},
|
| 2284 |
"UB": {
|
| 2285 |
+
"accuracy": 0.8704453441295547,
|
| 2286 |
+
"count": 247
|
| 2287 |
},
|
| 2288 |
"UD": {
|
| 2289 |
+
"accuracy": 0.8431372549019608,
|
| 2290 |
+
"count": 153
|
| 2291 |
}
|
| 2292 |
}
|
| 2293 |
},
|
| 2294 |
"sub_B5": {
|
| 2295 |
+
"full_accuracy": 0.54,
|
| 2296 |
+
"digit_accuracy": 0.8971428571428571,
|
| 2297 |
+
"n_examples": 100,
|
| 2298 |
"per_subtask": {
|
| 2299 |
"MD": {
|
| 2300 |
"accuracy": 1.0,
|
| 2301 |
+
"count": 100
|
| 2302 |
},
|
| 2303 |
"MB": {
|
| 2304 |
"accuracy": 1.0,
|
| 2305 |
+
"count": 100
|
| 2306 |
},
|
| 2307 |
"UB": {
|
| 2308 |
+
"accuracy": 0.8657718120805369,
|
| 2309 |
+
"count": 298
|
| 2310 |
},
|
| 2311 |
"UD": {
|
| 2312 |
+
"accuracy": 0.8415841584158416,
|
| 2313 |
+
"count": 202
|
| 2314 |
}
|
| 2315 |
}
|
| 2316 |
}
|
| 2317 |
},
|
| 2318 |
"summary": {
|
| 2319 |
+
"overall_accuracy": 0.6407692307692308,
|
| 2320 |
+
"digit_accuracy": 0.900989010989011,
|
| 2321 |
+
"total_examples": 2600,
|
| 2322 |
"n_splits": 24
|
| 2323 |
}
|
| 2324 |
},
|
| 2325 |
+
"sorl_overall_accuracy": 0.6407692307692308,
|
| 2326 |
+
"sft_overall_accuracy": 0.59
|
| 2327 |
}
|
add_sub_sorl_v1_abs10_K1_25K_1L3H510d/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 634679036
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abedcbc3a527a5ac60f33047ce6a4eb7c6124a4b9647aa1463c93dd8b722d329
|
| 3 |
size 634679036
|
add_sub_sorl_v1_abs10_K1_25K_1L3H510d/train_config.json
CHANGED
|
@@ -69,16 +69,20 @@
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 158593426,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs10_K1_25K_1L3H510d",
|
| 72 |
-
"git_commit": "
|
| 73 |
-
"timestamp": "2026-04-
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
|
|
|
| 77 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
"trainer_version": "v1",
|
| 79 |
-
"wandb_run_id": "
|
| 80 |
-
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/
|
| 81 |
-
"
|
| 82 |
-
"
|
|
|
|
|
|
|
|
|
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|
|
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 158593426,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs10_K1_25K_1L3H510d",
|
| 72 |
+
"git_commit": "f835493c19eb98267697007042c9d440cad2afbb",
|
| 73 |
+
"timestamp": "2026-04-15T21:12:50.528525+00:00",
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
| 77 |
+
"train_dataset": "fixed_train/train_25K_seed42.pt",
|
| 78 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 79 |
"trainer_version": "v1",
|
| 80 |
+
"wandb_run_id": "yh5kauv2",
|
| 81 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/yh5kauv2",
|
| 82 |
+
"eval_final_dataset": "eval_sets/eval_add_sub_6d_N100_seed42.json",
|
| 83 |
+
"eval_epoch_dataset": "eval_sets/eval_add_sub_6d_N25_seed42.json",
|
| 84 |
+
"eval_hf_repo": "thoughtworks/arithmetic-sorl-data",
|
| 85 |
+
"final_accuracy": 0.6407692307692308,
|
| 86 |
+
"sft_accuracy": 0.59,
|
| 87 |
"eval_method": "ArithmeticEvaluator"
|
| 88 |
}
|