Upload add_sub_baseline_10K/metrics.json with huggingface_hub
Browse files- add_sub_baseline_10K/metrics.json +238 -173
add_sub_baseline_10K/metrics.json
CHANGED
|
@@ -330,502 +330,567 @@
|
|
| 330 |
"K": null,
|
| 331 |
"mode": "sft",
|
| 332 |
"n_digits": 6,
|
| 333 |
-
"n_per_split":
|
| 334 |
},
|
| 335 |
"splits": {
|
| 336 |
"add_S0": {
|
| 337 |
"full_accuracy": 0.94,
|
| 338 |
-
"
|
|
|
|
| 339 |
"per_subtask": {
|
| 340 |
"SA": {
|
| 341 |
-
"accuracy": 0.
|
| 342 |
-
"count":
|
| 343 |
},
|
| 344 |
"SS": {
|
| 345 |
"accuracy": 1.0,
|
| 346 |
-
"count":
|
| 347 |
}
|
| 348 |
}
|
| 349 |
},
|
| 350 |
"add_S1": {
|
| 351 |
-
"full_accuracy": 0.
|
| 352 |
-
"
|
|
|
|
| 353 |
"per_subtask": {
|
| 354 |
"SA": {
|
| 355 |
-
"accuracy":
|
| 356 |
-
"count":
|
| 357 |
},
|
| 358 |
"SC": {
|
| 359 |
"accuracy": 1.0,
|
| 360 |
-
"count":
|
| 361 |
},
|
| 362 |
"SS": {
|
| 363 |
"accuracy": 1.0,
|
| 364 |
-
"count":
|
| 365 |
},
|
| 366 |
"UC": {
|
| 367 |
-
"accuracy":
|
| 368 |
-
"count":
|
| 369 |
}
|
| 370 |
}
|
| 371 |
},
|
| 372 |
"add_S2": {
|
| 373 |
-
"full_accuracy": 0.
|
| 374 |
-
"
|
|
|
|
| 375 |
"per_subtask": {
|
| 376 |
"SA": {
|
| 377 |
-
"accuracy": 0.
|
| 378 |
-
"count":
|
| 379 |
},
|
| 380 |
"SC": {
|
| 381 |
"accuracy": 1.0,
|
| 382 |
-
"count":
|
| 383 |
},
|
| 384 |
"SS": {
|
| 385 |
-
"accuracy":
|
| 386 |
-
"count":
|
| 387 |
},
|
| 388 |
"UC": {
|
| 389 |
-
"accuracy": 0.
|
| 390 |
-
"count":
|
| 391 |
},
|
| 392 |
"US": {
|
| 393 |
"accuracy": 1.0,
|
| 394 |
-
"count":
|
| 395 |
}
|
| 396 |
}
|
| 397 |
},
|
| 398 |
"add_S3": {
|
| 399 |
-
"full_accuracy": 0.
|
| 400 |
-
"
|
|
|
|
| 401 |
"per_subtask": {
|
| 402 |
"SA": {
|
| 403 |
"accuracy": 1.0,
|
| 404 |
-
"count":
|
| 405 |
},
|
| 406 |
"SC": {
|
| 407 |
-
"accuracy":
|
| 408 |
-
"count":
|
| 409 |
},
|
| 410 |
"SS": {
|
| 411 |
"accuracy": 1.0,
|
| 412 |
-
"count":
|
| 413 |
},
|
| 414 |
"UC": {
|
| 415 |
-
"accuracy": 0.
|
| 416 |
-
"count":
|
| 417 |
},
|
| 418 |
"US": {
|
| 419 |
"accuracy": 1.0,
|
| 420 |
-
"count":
|
| 421 |
}
|
| 422 |
}
|
| 423 |
},
|
| 424 |
"add_S4": {
|
| 425 |
-
"full_accuracy": 0.
|
| 426 |
-
"
|
|
|
|
| 427 |
"per_subtask": {
|
| 428 |
"SA": {
|
| 429 |
"accuracy": 1.0,
|
| 430 |
-
"count":
|
| 431 |
},
|
| 432 |
"SC": {
|
| 433 |
"accuracy": 1.0,
|
| 434 |
-
"count":
|
| 435 |
},
|
| 436 |
"SS": {
|
| 437 |
"accuracy": 1.0,
|
| 438 |
-
"count":
|
| 439 |
},
|
| 440 |
"UC": {
|
| 441 |
-
"accuracy": 0.
|
| 442 |
-
"count":
|
| 443 |
},
|
| 444 |
"US": {
|
| 445 |
-
"accuracy": 0.
|
| 446 |
-
"count":
|
| 447 |
}
|
| 448 |
}
|
| 449 |
},
|
| 450 |
"add_S5": {
|
| 451 |
-
"full_accuracy": 0.
|
| 452 |
-
"
|
|
|
|
| 453 |
"per_subtask": {
|
| 454 |
"SA": {
|
| 455 |
"accuracy": 1.0,
|
| 456 |
-
"count":
|
| 457 |
},
|
| 458 |
"SC": {
|
| 459 |
"accuracy": 1.0,
|
| 460 |
-
"count":
|
| 461 |
},
|
| 462 |
"UC": {
|
| 463 |
-
"accuracy": 0.
|
| 464 |
-
"count":
|
| 465 |
},
|
| 466 |
"US": {
|
| 467 |
-
"accuracy": 0.
|
| 468 |
-
"count":
|
| 469 |
}
|
| 470 |
}
|
| 471 |
},
|
| 472 |
"add_S6": {
|
| 473 |
-
"full_accuracy": 0.
|
| 474 |
-
"
|
|
|
|
| 475 |
"per_subtask": {
|
| 476 |
"SC": {
|
| 477 |
"accuracy": 1.0,
|
| 478 |
-
"count":
|
| 479 |
},
|
| 480 |
"UC": {
|
| 481 |
-
"accuracy": 0.
|
| 482 |
-
"count":
|
| 483 |
},
|
| 484 |
"US": {
|
| 485 |
-
"accuracy": 0.
|
| 486 |
-
"count":
|
| 487 |
}
|
| 488 |
}
|
| 489 |
},
|
| 490 |
"add_random": {
|
| 491 |
-
"full_accuracy": 0.
|
|
|
|
| 492 |
"n_examples": 200,
|
| 493 |
"per_subtask": {
|
| 494 |
"SA": {
|
| 495 |
-
"accuracy": 0.
|
| 496 |
-
"count":
|
| 497 |
},
|
| 498 |
"SC": {
|
| 499 |
"accuracy": 1.0,
|
| 500 |
-
"count":
|
| 501 |
},
|
| 502 |
"SS": {
|
| 503 |
"accuracy": 1.0,
|
| 504 |
-
"count":
|
| 505 |
},
|
| 506 |
"UC": {
|
| 507 |
-
"accuracy": 0.
|
| 508 |
-
"count":
|
| 509 |
},
|
| 510 |
"US": {
|
| 511 |
"accuracy": 1.0,
|
| 512 |
-
"count":
|
| 513 |
}
|
| 514 |
}
|
| 515 |
},
|
| 516 |
-
"
|
| 517 |
-
"full_accuracy":
|
| 518 |
-
"
|
|
|
|
| 519 |
"per_subtask": {
|
| 520 |
"SA": {
|
| 521 |
"accuracy": 1.0,
|
| 522 |
-
"count":
|
| 523 |
},
|
| 524 |
"SC": {
|
| 525 |
"accuracy": 1.0,
|
| 526 |
-
"count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 527 |
},
|
| 528 |
"UC": {
|
| 529 |
-
"accuracy": 0.
|
| 530 |
-
"count":
|
| 531 |
},
|
| 532 |
"US": {
|
| 533 |
"accuracy": 1.0,
|
| 534 |
-
"count":
|
| 535 |
}
|
| 536 |
}
|
| 537 |
},
|
| 538 |
"add_C4": {
|
| 539 |
"full_accuracy": 0.88,
|
| 540 |
-
"
|
|
|
|
| 541 |
"per_subtask": {
|
| 542 |
"SA": {
|
| 543 |
-
"accuracy":
|
| 544 |
-
"count":
|
| 545 |
},
|
| 546 |
"SC": {
|
| 547 |
"accuracy": 1.0,
|
| 548 |
-
"count":
|
| 549 |
},
|
| 550 |
"UC": {
|
| 551 |
-
"accuracy": 0.
|
| 552 |
-
"count":
|
| 553 |
},
|
| 554 |
"US": {
|
| 555 |
"accuracy": 1.0,
|
| 556 |
-
"count":
|
| 557 |
}
|
| 558 |
}
|
| 559 |
},
|
| 560 |
"add_C5": {
|
| 561 |
-
"full_accuracy": 0.
|
| 562 |
-
"
|
|
|
|
| 563 |
"per_subtask": {
|
| 564 |
"SA": {
|
| 565 |
"accuracy": 1.0,
|
| 566 |
-
"count":
|
| 567 |
},
|
| 568 |
"SC": {
|
| 569 |
"accuracy": 1.0,
|
| 570 |
-
"count":
|
| 571 |
},
|
| 572 |
"UC": {
|
| 573 |
-
"accuracy": 0.
|
| 574 |
-
"count":
|
| 575 |
},
|
| 576 |
"US": {
|
| 577 |
-
"accuracy": 0.
|
| 578 |
-
"count":
|
| 579 |
}
|
| 580 |
}
|
| 581 |
},
|
| 582 |
"add_C6": {
|
| 583 |
-
"full_accuracy": 0.
|
| 584 |
-
"
|
|
|
|
| 585 |
"per_subtask": {
|
| 586 |
"SC": {
|
| 587 |
"accuracy": 1.0,
|
| 588 |
-
"count":
|
| 589 |
},
|
| 590 |
"UC": {
|
| 591 |
-
"accuracy": 0.
|
| 592 |
-
"count":
|
| 593 |
},
|
| 594 |
"US": {
|
| 595 |
-
"accuracy":
|
| 596 |
-
"count":
|
| 597 |
}
|
| 598 |
}
|
| 599 |
},
|
| 600 |
"sub_M0": {
|
| 601 |
-
"full_accuracy":
|
| 602 |
-
"
|
|
|
|
| 603 |
"per_subtask": {
|
| 604 |
"MD": {
|
| 605 |
-
"accuracy":
|
| 606 |
-
"count":
|
| 607 |
},
|
| 608 |
"ME": {
|
| 609 |
"accuracy": 1.0,
|
| 610 |
-
"count":
|
| 611 |
}
|
| 612 |
}
|
| 613 |
},
|
| 614 |
"sub_M1": {
|
| 615 |
-
"full_accuracy":
|
| 616 |
-
"
|
|
|
|
| 617 |
"per_subtask": {
|
| 618 |
"MD": {
|
| 619 |
-
"accuracy":
|
| 620 |
-
"count":
|
| 621 |
},
|
| 622 |
"MB": {
|
| 623 |
-
"accuracy":
|
| 624 |
-
"count":
|
| 625 |
},
|
| 626 |
"ME": {
|
| 627 |
"accuracy": 1.0,
|
| 628 |
-
"count":
|
| 629 |
},
|
| 630 |
"UB": {
|
| 631 |
"accuracy": 1.0,
|
| 632 |
-
"count":
|
| 633 |
}
|
| 634 |
}
|
| 635 |
},
|
| 636 |
"sub_M2": {
|
| 637 |
-
"full_accuracy": 0.
|
| 638 |
-
"
|
|
|
|
| 639 |
"per_subtask": {
|
| 640 |
"MD": {
|
| 641 |
"accuracy": 1.0,
|
| 642 |
-
"count":
|
| 643 |
},
|
| 644 |
"MB": {
|
| 645 |
-
"accuracy": 0.
|
| 646 |
-
"count":
|
| 647 |
},
|
| 648 |
"ME": {
|
| 649 |
"accuracy": 1.0,
|
| 650 |
-
"count":
|
| 651 |
},
|
| 652 |
"UB": {
|
| 653 |
-
"accuracy": 0.
|
| 654 |
-
"count":
|
| 655 |
},
|
| 656 |
"UD": {
|
| 657 |
"accuracy": 1.0,
|
| 658 |
-
"count":
|
| 659 |
}
|
| 660 |
}
|
| 661 |
},
|
| 662 |
"sub_M3": {
|
| 663 |
-
"full_accuracy": 0.
|
| 664 |
-
"
|
|
|
|
| 665 |
"per_subtask": {
|
| 666 |
"MD": {
|
| 667 |
"accuracy": 1.0,
|
| 668 |
-
"count":
|
| 669 |
},
|
| 670 |
"MB": {
|
| 671 |
-
"accuracy":
|
| 672 |
-
"count":
|
| 673 |
},
|
| 674 |
"ME": {
|
| 675 |
"accuracy": 1.0,
|
| 676 |
-
"count":
|
| 677 |
},
|
| 678 |
"UB": {
|
| 679 |
-
"accuracy": 0.
|
| 680 |
-
"count":
|
| 681 |
},
|
| 682 |
"UD": {
|
| 683 |
"accuracy": 1.0,
|
| 684 |
-
"count":
|
| 685 |
}
|
| 686 |
}
|
| 687 |
},
|
| 688 |
"sub_M4": {
|
| 689 |
-
"full_accuracy": 0.
|
| 690 |
-
"
|
|
|
|
| 691 |
"per_subtask": {
|
| 692 |
"MD": {
|
| 693 |
"accuracy": 1.0,
|
| 694 |
-
"count":
|
| 695 |
},
|
| 696 |
"MB": {
|
| 697 |
"accuracy": 1.0,
|
| 698 |
-
"count":
|
| 699 |
},
|
| 700 |
"UB": {
|
| 701 |
-
"accuracy": 0.
|
| 702 |
-
"count":
|
| 703 |
},
|
| 704 |
"UD": {
|
| 705 |
-
"accuracy": 0.
|
| 706 |
-
"count":
|
| 707 |
}
|
| 708 |
}
|
| 709 |
},
|
| 710 |
"sub_M5": {
|
| 711 |
-
"full_accuracy": 0.
|
| 712 |
-
"
|
|
|
|
| 713 |
"per_subtask": {
|
| 714 |
"MD": {
|
| 715 |
"accuracy": 1.0,
|
| 716 |
-
"count":
|
| 717 |
},
|
| 718 |
"MB": {
|
| 719 |
"accuracy": 1.0,
|
| 720 |
-
"count":
|
| 721 |
},
|
| 722 |
"UB": {
|
| 723 |
"accuracy": 0.38,
|
| 724 |
-
"count":
|
| 725 |
},
|
| 726 |
"UD": {
|
| 727 |
-
"accuracy": 0.
|
| 728 |
-
"count":
|
| 729 |
}
|
| 730 |
}
|
| 731 |
},
|
| 732 |
"sub_random": {
|
| 733 |
"full_accuracy": 0.96,
|
|
|
|
| 734 |
"n_examples": 200,
|
| 735 |
"per_subtask": {
|
| 736 |
"MD": {
|
| 737 |
-
"accuracy": 0.
|
| 738 |
-
"count":
|
| 739 |
},
|
| 740 |
"MB": {
|
| 741 |
-
"accuracy": 0.
|
| 742 |
-
"count":
|
| 743 |
},
|
| 744 |
"ME": {
|
| 745 |
"accuracy": 1.0,
|
| 746 |
"count": 53
|
| 747 |
},
|
| 748 |
"UB": {
|
| 749 |
-
"accuracy": 0.
|
| 750 |
-
"count":
|
| 751 |
},
|
| 752 |
"UD": {
|
| 753 |
"accuracy": 1.0,
|
| 754 |
-
"count":
|
| 755 |
}
|
| 756 |
}
|
| 757 |
},
|
| 758 |
"sub_B3": {
|
| 759 |
-
"full_accuracy": 0.
|
| 760 |
-
"
|
|
|
|
| 761 |
"per_subtask": {
|
| 762 |
"MD": {
|
| 763 |
"accuracy": 1.0,
|
| 764 |
-
"count":
|
| 765 |
},
|
| 766 |
"MB": {
|
| 767 |
"accuracy": 1.0,
|
| 768 |
-
"count":
|
| 769 |
},
|
| 770 |
"UB": {
|
| 771 |
-
"accuracy": 0.
|
| 772 |
-
"count":
|
| 773 |
},
|
| 774 |
"UD": {
|
| 775 |
"accuracy": 1.0,
|
| 776 |
-
"count":
|
| 777 |
}
|
| 778 |
}
|
| 779 |
},
|
| 780 |
"sub_B4": {
|
| 781 |
-
"full_accuracy": 0.
|
| 782 |
-
"
|
|
|
|
| 783 |
"per_subtask": {
|
| 784 |
"MD": {
|
| 785 |
"accuracy": 1.0,
|
| 786 |
-
"count":
|
| 787 |
},
|
| 788 |
"MB": {
|
| 789 |
"accuracy": 1.0,
|
| 790 |
-
"count":
|
| 791 |
},
|
| 792 |
"UB": {
|
| 793 |
-
"accuracy": 0.
|
| 794 |
-
"count":
|
| 795 |
},
|
| 796 |
"UD": {
|
| 797 |
-
"accuracy": 0.
|
| 798 |
-
"count":
|
| 799 |
}
|
| 800 |
}
|
| 801 |
},
|
| 802 |
"sub_B5": {
|
| 803 |
-
"full_accuracy": 0.
|
| 804 |
-
"
|
|
|
|
| 805 |
"per_subtask": {
|
| 806 |
"MD": {
|
| 807 |
"accuracy": 1.0,
|
| 808 |
-
"count":
|
| 809 |
},
|
| 810 |
"MB": {
|
| 811 |
"accuracy": 1.0,
|
| 812 |
-
"count":
|
| 813 |
},
|
| 814 |
"UB": {
|
| 815 |
-
"accuracy": 0.
|
| 816 |
-
"count":
|
| 817 |
},
|
| 818 |
"UD": {
|
| 819 |
-
"accuracy": 0.
|
| 820 |
-
"count":
|
| 821 |
}
|
| 822 |
}
|
| 823 |
}
|
| 824 |
},
|
| 825 |
"summary": {
|
| 826 |
-
"overall_accuracy": 0.
|
| 827 |
-
"
|
| 828 |
-
"
|
|
|
|
| 829 |
}
|
| 830 |
}
|
| 831 |
}
|
|
|
|
| 330 |
"K": null,
|
| 331 |
"mode": "sft",
|
| 332 |
"n_digits": 6,
|
| 333 |
+
"n_per_split": 50
|
| 334 |
},
|
| 335 |
"splits": {
|
| 336 |
"add_S0": {
|
| 337 |
"full_accuracy": 0.94,
|
| 338 |
+
"digit_accuracy": 0.9914285714285714,
|
| 339 |
+
"n_examples": 50,
|
| 340 |
"per_subtask": {
|
| 341 |
"SA": {
|
| 342 |
+
"accuracy": 0.9898305084745763,
|
| 343 |
+
"count": 295
|
| 344 |
},
|
| 345 |
"SS": {
|
| 346 |
"accuracy": 1.0,
|
| 347 |
+
"count": 55
|
| 348 |
}
|
| 349 |
}
|
| 350 |
},
|
| 351 |
"add_S1": {
|
| 352 |
+
"full_accuracy": 0.98,
|
| 353 |
+
"digit_accuracy": 0.9971428571428571,
|
| 354 |
+
"n_examples": 50,
|
| 355 |
"per_subtask": {
|
| 356 |
"SA": {
|
| 357 |
+
"accuracy": 1.0,
|
| 358 |
+
"count": 126
|
| 359 |
},
|
| 360 |
"SC": {
|
| 361 |
"accuracy": 1.0,
|
| 362 |
+
"count": 79
|
| 363 |
},
|
| 364 |
"SS": {
|
| 365 |
"accuracy": 1.0,
|
| 366 |
+
"count": 21
|
| 367 |
},
|
| 368 |
"UC": {
|
| 369 |
+
"accuracy": 0.9919354838709677,
|
| 370 |
+
"count": 124
|
| 371 |
}
|
| 372 |
}
|
| 373 |
},
|
| 374 |
"add_S2": {
|
| 375 |
+
"full_accuracy": 0.9,
|
| 376 |
+
"digit_accuracy": 0.9828571428571429,
|
| 377 |
+
"n_examples": 50,
|
| 378 |
"per_subtask": {
|
| 379 |
"SA": {
|
| 380 |
+
"accuracy": 0.9866666666666667,
|
| 381 |
+
"count": 75
|
| 382 |
},
|
| 383 |
"SC": {
|
| 384 |
"accuracy": 1.0,
|
| 385 |
+
"count": 62
|
| 386 |
},
|
| 387 |
"SS": {
|
| 388 |
+
"accuracy": 1.0,
|
| 389 |
+
"count": 39
|
| 390 |
},
|
| 391 |
"UC": {
|
| 392 |
+
"accuracy": 0.954954954954955,
|
| 393 |
+
"count": 111
|
| 394 |
},
|
| 395 |
"US": {
|
| 396 |
"accuracy": 1.0,
|
| 397 |
+
"count": 63
|
| 398 |
}
|
| 399 |
}
|
| 400 |
},
|
| 401 |
"add_S3": {
|
| 402 |
+
"full_accuracy": 0.7,
|
| 403 |
+
"digit_accuracy": 0.9571428571428572,
|
| 404 |
+
"n_examples": 50,
|
| 405 |
"per_subtask": {
|
| 406 |
"SA": {
|
| 407 |
"accuracy": 1.0,
|
| 408 |
+
"count": 60
|
| 409 |
},
|
| 410 |
"SC": {
|
| 411 |
+
"accuracy": 1.0,
|
| 412 |
+
"count": 57
|
| 413 |
},
|
| 414 |
"SS": {
|
| 415 |
"accuracy": 1.0,
|
| 416 |
+
"count": 19
|
| 417 |
},
|
| 418 |
"UC": {
|
| 419 |
+
"accuracy": 0.8557692307692307,
|
| 420 |
+
"count": 104
|
| 421 |
},
|
| 422 |
"US": {
|
| 423 |
"accuracy": 1.0,
|
| 424 |
+
"count": 110
|
| 425 |
}
|
| 426 |
}
|
| 427 |
},
|
| 428 |
"add_S4": {
|
| 429 |
+
"full_accuracy": 0.64,
|
| 430 |
+
"digit_accuracy": 0.9342857142857143,
|
| 431 |
+
"n_examples": 50,
|
| 432 |
"per_subtask": {
|
| 433 |
"SA": {
|
| 434 |
"accuracy": 1.0,
|
| 435 |
+
"count": 48
|
| 436 |
},
|
| 437 |
"SC": {
|
| 438 |
"accuracy": 1.0,
|
| 439 |
+
"count": 52
|
| 440 |
},
|
| 441 |
"SS": {
|
| 442 |
"accuracy": 1.0,
|
| 443 |
+
"count": 7
|
| 444 |
},
|
| 445 |
"UC": {
|
| 446 |
+
"accuracy": 0.8202247191011236,
|
| 447 |
+
"count": 89
|
| 448 |
},
|
| 449 |
"US": {
|
| 450 |
+
"accuracy": 0.9545454545454546,
|
| 451 |
+
"count": 154
|
| 452 |
}
|
| 453 |
}
|
| 454 |
},
|
| 455 |
"add_S5": {
|
| 456 |
+
"full_accuracy": 0.3,
|
| 457 |
+
"digit_accuracy": 0.7342857142857143,
|
| 458 |
+
"n_examples": 50,
|
| 459 |
"per_subtask": {
|
| 460 |
"SA": {
|
| 461 |
"accuracy": 1.0,
|
| 462 |
+
"count": 50
|
| 463 |
},
|
| 464 |
"SC": {
|
| 465 |
"accuracy": 1.0,
|
| 466 |
+
"count": 50
|
| 467 |
},
|
| 468 |
"UC": {
|
| 469 |
+
"accuracy": 0.38,
|
| 470 |
+
"count": 50
|
| 471 |
},
|
| 472 |
"US": {
|
| 473 |
+
"accuracy": 0.69,
|
| 474 |
+
"count": 200
|
| 475 |
}
|
| 476 |
}
|
| 477 |
},
|
| 478 |
"add_S6": {
|
| 479 |
+
"full_accuracy": 0.36,
|
| 480 |
+
"digit_accuracy": 0.6685714285714286,
|
| 481 |
+
"n_examples": 50,
|
| 482 |
"per_subtask": {
|
| 483 |
"SC": {
|
| 484 |
"accuracy": 1.0,
|
| 485 |
+
"count": 50
|
| 486 |
},
|
| 487 |
"UC": {
|
| 488 |
+
"accuracy": 0.46,
|
| 489 |
+
"count": 50
|
| 490 |
},
|
| 491 |
"US": {
|
| 492 |
+
"accuracy": 0.644,
|
| 493 |
+
"count": 250
|
| 494 |
}
|
| 495 |
}
|
| 496 |
},
|
| 497 |
"add_random": {
|
| 498 |
+
"full_accuracy": 0.96,
|
| 499 |
+
"digit_accuracy": 0.9935714285714285,
|
| 500 |
"n_examples": 200,
|
| 501 |
"per_subtask": {
|
| 502 |
"SA": {
|
| 503 |
+
"accuracy": 0.9953596287703016,
|
| 504 |
+
"count": 431
|
| 505 |
},
|
| 506 |
"SC": {
|
| 507 |
"accuracy": 1.0,
|
| 508 |
+
"count": 316
|
| 509 |
},
|
| 510 |
"SS": {
|
| 511 |
"accuracy": 1.0,
|
| 512 |
+
"count": 39
|
| 513 |
},
|
| 514 |
"UC": {
|
| 515 |
+
"accuracy": 0.9875,
|
| 516 |
+
"count": 560
|
| 517 |
},
|
| 518 |
"US": {
|
| 519 |
"accuracy": 1.0,
|
| 520 |
+
"count": 54
|
| 521 |
}
|
| 522 |
}
|
| 523 |
},
|
| 524 |
+
"add_C1": {
|
| 525 |
+
"full_accuracy": 1.0,
|
| 526 |
+
"digit_accuracy": 1.0,
|
| 527 |
+
"n_examples": 50,
|
| 528 |
"per_subtask": {
|
| 529 |
"SA": {
|
| 530 |
"accuracy": 1.0,
|
| 531 |
+
"count": 250
|
| 532 |
},
|
| 533 |
"SC": {
|
| 534 |
"accuracy": 1.0,
|
| 535 |
+
"count": 50
|
| 536 |
+
},
|
| 537 |
+
"UC": {
|
| 538 |
+
"accuracy": 1.0,
|
| 539 |
+
"count": 50
|
| 540 |
+
}
|
| 541 |
+
}
|
| 542 |
+
},
|
| 543 |
+
"add_C2": {
|
| 544 |
+
"full_accuracy": 0.98,
|
| 545 |
+
"digit_accuracy": 0.9971428571428571,
|
| 546 |
+
"n_examples": 50,
|
| 547 |
+
"per_subtask": {
|
| 548 |
+
"SA": {
|
| 549 |
+
"accuracy": 1.0,
|
| 550 |
+
"count": 200
|
| 551 |
+
},
|
| 552 |
+
"SC": {
|
| 553 |
+
"accuracy": 1.0,
|
| 554 |
+
"count": 50
|
| 555 |
+
},
|
| 556 |
+
"UC": {
|
| 557 |
+
"accuracy": 0.9879518072289156,
|
| 558 |
+
"count": 83
|
| 559 |
+
},
|
| 560 |
+
"US": {
|
| 561 |
+
"accuracy": 1.0,
|
| 562 |
+
"count": 17
|
| 563 |
+
}
|
| 564 |
+
}
|
| 565 |
+
},
|
| 566 |
+
"add_C3": {
|
| 567 |
+
"full_accuracy": 0.78,
|
| 568 |
+
"digit_accuracy": 0.9685714285714285,
|
| 569 |
+
"n_examples": 50,
|
| 570 |
+
"per_subtask": {
|
| 571 |
+
"SA": {
|
| 572 |
+
"accuracy": 0.9933333333333333,
|
| 573 |
+
"count": 150
|
| 574 |
+
},
|
| 575 |
+
"SC": {
|
| 576 |
+
"accuracy": 1.0,
|
| 577 |
+
"count": 50
|
| 578 |
},
|
| 579 |
"UC": {
|
| 580 |
+
"accuracy": 0.9,
|
| 581 |
+
"count": 100
|
| 582 |
},
|
| 583 |
"US": {
|
| 584 |
"accuracy": 1.0,
|
| 585 |
+
"count": 50
|
| 586 |
}
|
| 587 |
}
|
| 588 |
},
|
| 589 |
"add_C4": {
|
| 590 |
"full_accuracy": 0.88,
|
| 591 |
+
"digit_accuracy": 0.9828571428571429,
|
| 592 |
+
"n_examples": 50,
|
| 593 |
"per_subtask": {
|
| 594 |
"SA": {
|
| 595 |
+
"accuracy": 1.0,
|
| 596 |
+
"count": 100
|
| 597 |
},
|
| 598 |
"SC": {
|
| 599 |
"accuracy": 1.0,
|
| 600 |
+
"count": 50
|
| 601 |
},
|
| 602 |
"UC": {
|
| 603 |
+
"accuracy": 0.9545454545454546,
|
| 604 |
+
"count": 132
|
| 605 |
},
|
| 606 |
"US": {
|
| 607 |
"accuracy": 1.0,
|
| 608 |
+
"count": 68
|
| 609 |
}
|
| 610 |
}
|
| 611 |
},
|
| 612 |
"add_C5": {
|
| 613 |
+
"full_accuracy": 0.76,
|
| 614 |
+
"digit_accuracy": 0.9571428571428572,
|
| 615 |
+
"n_examples": 50,
|
| 616 |
"per_subtask": {
|
| 617 |
"SA": {
|
| 618 |
"accuracy": 1.0,
|
| 619 |
+
"count": 50
|
| 620 |
},
|
| 621 |
"SC": {
|
| 622 |
"accuracy": 1.0,
|
| 623 |
+
"count": 50
|
| 624 |
},
|
| 625 |
"UC": {
|
| 626 |
+
"accuracy": 0.9178082191780822,
|
| 627 |
+
"count": 146
|
| 628 |
},
|
| 629 |
"US": {
|
| 630 |
+
"accuracy": 0.9711538461538461,
|
| 631 |
+
"count": 104
|
| 632 |
}
|
| 633 |
}
|
| 634 |
},
|
| 635 |
"add_C6": {
|
| 636 |
+
"full_accuracy": 0.92,
|
| 637 |
+
"digit_accuracy": 0.9885714285714285,
|
| 638 |
+
"n_examples": 50,
|
| 639 |
"per_subtask": {
|
| 640 |
"SC": {
|
| 641 |
"accuracy": 1.0,
|
| 642 |
+
"count": 50
|
| 643 |
},
|
| 644 |
"UC": {
|
| 645 |
+
"accuracy": 0.9788359788359788,
|
| 646 |
+
"count": 189
|
| 647 |
},
|
| 648 |
"US": {
|
| 649 |
+
"accuracy": 1.0,
|
| 650 |
+
"count": 111
|
| 651 |
}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
"sub_M0": {
|
| 655 |
+
"full_accuracy": 1.0,
|
| 656 |
+
"digit_accuracy": 1.0,
|
| 657 |
+
"n_examples": 50,
|
| 658 |
"per_subtask": {
|
| 659 |
"MD": {
|
| 660 |
+
"accuracy": 1.0,
|
| 661 |
+
"count": 303
|
| 662 |
},
|
| 663 |
"ME": {
|
| 664 |
"accuracy": 1.0,
|
| 665 |
+
"count": 47
|
| 666 |
}
|
| 667 |
}
|
| 668 |
},
|
| 669 |
"sub_M1": {
|
| 670 |
+
"full_accuracy": 0.92,
|
| 671 |
+
"digit_accuracy": 0.9885714285714285,
|
| 672 |
+
"n_examples": 50,
|
| 673 |
"per_subtask": {
|
| 674 |
"MD": {
|
| 675 |
+
"accuracy": 0.9858156028368794,
|
| 676 |
+
"count": 141
|
| 677 |
},
|
| 678 |
"MB": {
|
| 679 |
+
"accuracy": 0.9722222222222222,
|
| 680 |
+
"count": 72
|
| 681 |
},
|
| 682 |
"ME": {
|
| 683 |
"accuracy": 1.0,
|
| 684 |
+
"count": 18
|
| 685 |
},
|
| 686 |
"UB": {
|
| 687 |
"accuracy": 1.0,
|
| 688 |
+
"count": 119
|
| 689 |
}
|
| 690 |
}
|
| 691 |
},
|
| 692 |
"sub_M2": {
|
| 693 |
+
"full_accuracy": 0.76,
|
| 694 |
+
"digit_accuracy": 0.9657142857142857,
|
| 695 |
+
"n_examples": 50,
|
| 696 |
"per_subtask": {
|
| 697 |
"MD": {
|
| 698 |
"accuracy": 1.0,
|
| 699 |
+
"count": 112
|
| 700 |
},
|
| 701 |
"MB": {
|
| 702 |
+
"accuracy": 0.9056603773584906,
|
| 703 |
+
"count": 53
|
| 704 |
},
|
| 705 |
"ME": {
|
| 706 |
"accuracy": 1.0,
|
| 707 |
+
"count": 47
|
| 708 |
},
|
| 709 |
"UB": {
|
| 710 |
+
"accuracy": 0.9176470588235294,
|
| 711 |
+
"count": 85
|
| 712 |
},
|
| 713 |
"UD": {
|
| 714 |
"accuracy": 1.0,
|
| 715 |
+
"count": 53
|
| 716 |
}
|
| 717 |
}
|
| 718 |
},
|
| 719 |
"sub_M3": {
|
| 720 |
+
"full_accuracy": 0.42,
|
| 721 |
+
"digit_accuracy": 0.9171428571428571,
|
| 722 |
+
"n_examples": 50,
|
| 723 |
"per_subtask": {
|
| 724 |
"MD": {
|
| 725 |
"accuracy": 1.0,
|
| 726 |
+
"count": 97
|
| 727 |
},
|
| 728 |
"MB": {
|
| 729 |
+
"accuracy": 1.0,
|
| 730 |
+
"count": 51
|
| 731 |
},
|
| 732 |
"ME": {
|
| 733 |
"accuracy": 1.0,
|
| 734 |
+
"count": 27
|
| 735 |
},
|
| 736 |
"UB": {
|
| 737 |
+
"accuracy": 0.6081081081081081,
|
| 738 |
+
"count": 74
|
| 739 |
},
|
| 740 |
"UD": {
|
| 741 |
"accuracy": 1.0,
|
| 742 |
+
"count": 101
|
| 743 |
}
|
| 744 |
}
|
| 745 |
},
|
| 746 |
"sub_M4": {
|
| 747 |
+
"full_accuracy": 0.1,
|
| 748 |
+
"digit_accuracy": 0.8228571428571428,
|
| 749 |
+
"n_examples": 50,
|
| 750 |
"per_subtask": {
|
| 751 |
"MD": {
|
| 752 |
"accuracy": 1.0,
|
| 753 |
+
"count": 100
|
| 754 |
},
|
| 755 |
"MB": {
|
| 756 |
"accuracy": 1.0,
|
| 757 |
+
"count": 50
|
| 758 |
},
|
| 759 |
"UB": {
|
| 760 |
+
"accuracy": 0.44,
|
| 761 |
+
"count": 50
|
| 762 |
},
|
| 763 |
"UD": {
|
| 764 |
+
"accuracy": 0.7733333333333333,
|
| 765 |
+
"count": 150
|
| 766 |
}
|
| 767 |
}
|
| 768 |
},
|
| 769 |
"sub_M5": {
|
| 770 |
+
"full_accuracy": 0.06,
|
| 771 |
+
"digit_accuracy": 0.6885714285714286,
|
| 772 |
+
"n_examples": 50,
|
| 773 |
"per_subtask": {
|
| 774 |
"MD": {
|
| 775 |
"accuracy": 1.0,
|
| 776 |
+
"count": 50
|
| 777 |
},
|
| 778 |
"MB": {
|
| 779 |
"accuracy": 1.0,
|
| 780 |
+
"count": 50
|
| 781 |
},
|
| 782 |
"UB": {
|
| 783 |
"accuracy": 0.38,
|
| 784 |
+
"count": 50
|
| 785 |
},
|
| 786 |
"UD": {
|
| 787 |
+
"accuracy": 0.61,
|
| 788 |
+
"count": 200
|
| 789 |
}
|
| 790 |
}
|
| 791 |
},
|
| 792 |
"sub_random": {
|
| 793 |
"full_accuracy": 0.96,
|
| 794 |
+
"digit_accuracy": 0.9942857142857143,
|
| 795 |
"n_examples": 200,
|
| 796 |
"per_subtask": {
|
| 797 |
"MD": {
|
| 798 |
+
"accuracy": 0.9964912280701754,
|
| 799 |
+
"count": 570
|
| 800 |
},
|
| 801 |
"MB": {
|
| 802 |
+
"accuracy": 0.9819494584837545,
|
| 803 |
+
"count": 277
|
| 804 |
},
|
| 805 |
"ME": {
|
| 806 |
"accuracy": 1.0,
|
| 807 |
"count": 53
|
| 808 |
},
|
| 809 |
"UB": {
|
| 810 |
+
"accuracy": 0.9978768577494692,
|
| 811 |
+
"count": 471
|
| 812 |
},
|
| 813 |
"UD": {
|
| 814 |
"accuracy": 1.0,
|
| 815 |
+
"count": 29
|
| 816 |
}
|
| 817 |
}
|
| 818 |
},
|
| 819 |
"sub_B3": {
|
| 820 |
+
"full_accuracy": 0.82,
|
| 821 |
+
"digit_accuracy": 0.9742857142857143,
|
| 822 |
+
"n_examples": 50,
|
| 823 |
"per_subtask": {
|
| 824 |
"MD": {
|
| 825 |
"accuracy": 1.0,
|
| 826 |
+
"count": 150
|
| 827 |
},
|
| 828 |
"MB": {
|
| 829 |
"accuracy": 1.0,
|
| 830 |
+
"count": 50
|
| 831 |
},
|
| 832 |
"UB": {
|
| 833 |
+
"accuracy": 0.9108910891089109,
|
| 834 |
+
"count": 101
|
| 835 |
},
|
| 836 |
"UD": {
|
| 837 |
"accuracy": 1.0,
|
| 838 |
+
"count": 49
|
| 839 |
}
|
| 840 |
}
|
| 841 |
},
|
| 842 |
"sub_B4": {
|
| 843 |
+
"full_accuracy": 0.62,
|
| 844 |
+
"digit_accuracy": 0.9371428571428572,
|
| 845 |
+
"n_examples": 50,
|
| 846 |
"per_subtask": {
|
| 847 |
"MD": {
|
| 848 |
"accuracy": 1.0,
|
| 849 |
+
"count": 100
|
| 850 |
},
|
| 851 |
"MB": {
|
| 852 |
"accuracy": 1.0,
|
| 853 |
+
"count": 50
|
| 854 |
},
|
| 855 |
"UB": {
|
| 856 |
+
"accuracy": 0.859504132231405,
|
| 857 |
+
"count": 121
|
| 858 |
},
|
| 859 |
"UD": {
|
| 860 |
+
"accuracy": 0.9367088607594937,
|
| 861 |
+
"count": 79
|
| 862 |
}
|
| 863 |
}
|
| 864 |
},
|
| 865 |
"sub_B5": {
|
| 866 |
+
"full_accuracy": 0.46,
|
| 867 |
+
"digit_accuracy": 0.9142857142857143,
|
| 868 |
+
"n_examples": 50,
|
| 869 |
"per_subtask": {
|
| 870 |
"MD": {
|
| 871 |
"accuracy": 1.0,
|
| 872 |
+
"count": 50
|
| 873 |
},
|
| 874 |
"MB": {
|
| 875 |
"accuracy": 1.0,
|
| 876 |
+
"count": 50
|
| 877 |
},
|
| 878 |
"UB": {
|
| 879 |
+
"accuracy": 0.8289473684210527,
|
| 880 |
+
"count": 152
|
| 881 |
},
|
| 882 |
"UD": {
|
| 883 |
+
"accuracy": 0.9591836734693877,
|
| 884 |
+
"count": 98
|
| 885 |
}
|
| 886 |
}
|
| 887 |
}
|
| 888 |
},
|
| 889 |
"summary": {
|
| 890 |
+
"overall_accuracy": 0.766,
|
| 891 |
+
"digit_accuracy": 0.9439047619047619,
|
| 892 |
+
"total_examples": 1500,
|
| 893 |
+
"n_splits": 24
|
| 894 |
}
|
| 895 |
}
|
| 896 |
}
|