Upload add_sub_baseline_25K_1L3H510d
Browse files
add_sub_baseline_25K_1L3H510d/metrics.json
CHANGED
|
@@ -159,478 +159,478 @@
|
|
| 159 |
7800
|
| 160 |
],
|
| 161 |
"loss": [
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
1.
|
| 169 |
-
1.
|
| 170 |
-
1.
|
| 171 |
-
1.
|
| 172 |
-
1.
|
| 173 |
-
1.
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
0.
|
| 183 |
-
0.
|
| 184 |
-
0.
|
| 185 |
-
0.
|
| 186 |
-
0.
|
| 187 |
-
0.
|
| 188 |
-
0.
|
| 189 |
-
0.
|
| 190 |
-
0.
|
| 191 |
-
0.
|
| 192 |
-
0.
|
| 193 |
-
0.
|
| 194 |
-
0.
|
| 195 |
-
0.
|
| 196 |
-
0.
|
| 197 |
-
0.
|
| 198 |
-
0.
|
| 199 |
-
0.
|
| 200 |
-
0.
|
| 201 |
-
0.
|
| 202 |
-
0.
|
| 203 |
-
0.
|
| 204 |
-
0.
|
| 205 |
-
0.
|
| 206 |
-
0.
|
| 207 |
-
0.
|
| 208 |
-
0.
|
| 209 |
-
0.
|
| 210 |
-
0.
|
| 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 |
-
0.
|
| 246 |
-
0.
|
| 247 |
-
0.
|
| 248 |
-
0.
|
| 249 |
-
0.
|
| 250 |
-
0.
|
| 251 |
-
0.
|
| 252 |
-
0.
|
| 253 |
-
0.
|
| 254 |
-
0.
|
| 255 |
-
0.
|
| 256 |
-
0.
|
| 257 |
-
0.
|
| 258 |
-
0.
|
| 259 |
-
0.
|
| 260 |
-
0.
|
| 261 |
-
0.
|
| 262 |
-
0.
|
| 263 |
-
0.
|
| 264 |
-
0.
|
| 265 |
-
0.
|
| 266 |
-
0.
|
| 267 |
-
0.
|
| 268 |
-
0.
|
| 269 |
-
0.
|
| 270 |
-
0.
|
| 271 |
-
0.
|
| 272 |
-
0.
|
| 273 |
-
0.
|
| 274 |
-
0.
|
| 275 |
-
0.
|
| 276 |
-
0.
|
| 277 |
-
0.
|
| 278 |
-
0.
|
| 279 |
-
0.
|
| 280 |
-
0.
|
| 281 |
-
0.
|
| 282 |
-
0.
|
| 283 |
-
0.
|
| 284 |
-
0.
|
| 285 |
-
0.
|
| 286 |
-
0.
|
| 287 |
-
0.
|
| 288 |
-
0.
|
| 289 |
-
0.
|
| 290 |
-
0.
|
| 291 |
-
0.
|
| 292 |
-
0.
|
| 293 |
-
0.
|
| 294 |
-
0.
|
| 295 |
-
0.
|
| 296 |
-
0.
|
| 297 |
-
0.
|
| 298 |
-
0.
|
| 299 |
-
0.
|
| 300 |
-
0.
|
| 301 |
-
0.
|
| 302 |
-
0.
|
| 303 |
-
0.
|
| 304 |
-
0.
|
| 305 |
-
0.
|
| 306 |
-
0.
|
| 307 |
-
0.
|
| 308 |
-
0.
|
| 309 |
-
0.
|
| 310 |
-
0.
|
| 311 |
-
0.
|
| 312 |
-
0.
|
| 313 |
-
0.
|
| 314 |
-
0.
|
| 315 |
-
0.
|
| 316 |
-
0.
|
| 317 |
-
0.
|
| 318 |
],
|
| 319 |
"base_loss": [
|
| 320 |
-
|
| 321 |
-
|
| 322 |
-
|
| 323 |
-
|
| 324 |
-
|
| 325 |
-
|
| 326 |
-
1.
|
| 327 |
-
1.
|
| 328 |
-
1.
|
| 329 |
-
1.
|
| 330 |
-
1.
|
| 331 |
-
1.
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
|
| 335 |
-
|
| 336 |
-
|
| 337 |
-
|
| 338 |
-
|
| 339 |
-
|
| 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 |
-
0.
|
| 429 |
-
0.
|
| 430 |
-
0.
|
| 431 |
-
0.
|
| 432 |
-
0.
|
| 433 |
-
0.
|
| 434 |
-
0.
|
| 435 |
-
0.
|
| 436 |
-
0.
|
| 437 |
-
0.
|
| 438 |
-
0.
|
| 439 |
-
0.
|
| 440 |
-
0.
|
| 441 |
-
0.
|
| 442 |
-
0.
|
| 443 |
-
0.
|
| 444 |
-
0.
|
| 445 |
-
0.
|
| 446 |
-
0.
|
| 447 |
-
0.
|
| 448 |
-
0.
|
| 449 |
-
0.
|
| 450 |
-
0.
|
| 451 |
-
0.
|
| 452 |
-
0.
|
| 453 |
-
0.
|
| 454 |
-
0.
|
| 455 |
-
0.
|
| 456 |
-
0.
|
| 457 |
-
0.
|
| 458 |
-
0.
|
| 459 |
-
0.
|
| 460 |
-
0.
|
| 461 |
-
0.
|
| 462 |
-
0.
|
| 463 |
-
0.
|
| 464 |
-
0.
|
| 465 |
-
0.
|
| 466 |
-
0.
|
| 467 |
-
0.
|
| 468 |
-
0.
|
| 469 |
-
0.
|
| 470 |
-
0.
|
| 471 |
-
0.
|
| 472 |
-
0.
|
| 473 |
-
0.
|
| 474 |
-
0.
|
| 475 |
-
0.
|
| 476 |
],
|
| 477 |
"lr": [
|
| 478 |
-
|
| 479 |
-
|
| 480 |
-
|
| 481 |
-
|
| 482 |
-
|
| 483 |
-
|
| 484 |
-
|
| 485 |
-
|
| 486 |
-
|
| 487 |
-
|
| 488 |
-
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
|
| 493 |
-
|
| 494 |
-
|
| 495 |
-
|
| 496 |
-
|
| 497 |
-
|
| 498 |
-
|
| 499 |
-
|
| 500 |
-
|
| 501 |
-
|
| 502 |
-
|
| 503 |
-
|
| 504 |
-
|
| 505 |
-
|
| 506 |
-
|
| 507 |
-
|
| 508 |
-
|
| 509 |
-
|
| 510 |
-
|
| 511 |
-
|
| 512 |
-
|
| 513 |
-
|
| 514 |
-
|
| 515 |
-
|
| 516 |
-
|
| 517 |
-
|
| 518 |
-
|
| 519 |
-
|
| 520 |
-
|
| 521 |
-
|
| 522 |
-
|
| 523 |
-
|
| 524 |
-
|
| 525 |
-
|
| 526 |
-
|
| 527 |
-
|
| 528 |
-
|
| 529 |
-
|
| 530 |
-
|
| 531 |
-
|
| 532 |
-
|
| 533 |
-
|
| 534 |
-
|
| 535 |
-
|
| 536 |
-
|
| 537 |
-
|
| 538 |
-
|
| 539 |
-
|
| 540 |
-
|
| 541 |
-
|
| 542 |
-
|
| 543 |
-
|
| 544 |
-
|
| 545 |
-
|
| 546 |
-
|
| 547 |
-
|
| 548 |
-
|
| 549 |
-
|
| 550 |
-
|
| 551 |
-
|
| 552 |
-
|
| 553 |
-
|
| 554 |
-
|
| 555 |
-
|
| 556 |
-
|
| 557 |
-
|
| 558 |
-
|
| 559 |
-
|
| 560 |
-
|
| 561 |
-
|
| 562 |
-
|
| 563 |
-
|
| 564 |
-
|
| 565 |
-
|
| 566 |
-
|
| 567 |
-
|
| 568 |
-
|
| 569 |
-
|
| 570 |
-
|
| 571 |
-
|
| 572 |
-
|
| 573 |
-
|
| 574 |
-
|
| 575 |
-
|
| 576 |
-
|
| 577 |
-
|
| 578 |
-
|
| 579 |
-
|
| 580 |
-
|
| 581 |
-
|
| 582 |
-
|
| 583 |
-
|
| 584 |
-
|
| 585 |
-
|
| 586 |
-
|
| 587 |
-
|
| 588 |
-
|
| 589 |
-
|
| 590 |
-
|
| 591 |
-
|
| 592 |
-
|
| 593 |
-
|
| 594 |
-
|
| 595 |
-
|
| 596 |
-
|
| 597 |
-
|
| 598 |
-
|
| 599 |
-
|
| 600 |
-
|
| 601 |
-
|
| 602 |
-
|
| 603 |
-
|
| 604 |
-
|
| 605 |
-
|
| 606 |
-
|
| 607 |
-
|
| 608 |
-
|
| 609 |
-
|
| 610 |
-
|
| 611 |
-
|
| 612 |
-
|
| 613 |
-
|
| 614 |
-
|
| 615 |
-
|
| 616 |
-
|
| 617 |
-
|
| 618 |
-
|
| 619 |
-
|
| 620 |
-
|
| 621 |
-
|
| 622 |
-
|
| 623 |
-
|
| 624 |
-
|
| 625 |
-
|
| 626 |
-
|
| 627 |
-
|
| 628 |
-
|
| 629 |
-
|
| 630 |
-
|
| 631 |
-
|
| 632 |
-
|
| 633 |
-
|
| 634 |
],
|
| 635 |
"eval_step": [
|
| 636 |
390,
|
|
@@ -677,29 +677,29 @@
|
|
| 677 |
20
|
| 678 |
],
|
| 679 |
"eval_accuracy": [
|
| 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 |
]
|
| 701 |
},
|
| 702 |
-
"final_accuracy": 0.
|
| 703 |
"sft_eval": {
|
| 704 |
"config": {
|
| 705 |
"ops": "add_sub",
|
|
@@ -710,51 +710,51 @@
|
|
| 710 |
},
|
| 711 |
"splits": {
|
| 712 |
"add_S0": {
|
| 713 |
-
"full_accuracy": 0.
|
| 714 |
"n_examples": 100,
|
| 715 |
"per_subtask": {
|
| 716 |
"SA": {
|
| 717 |
-
"accuracy": 0.
|
| 718 |
"count": 605
|
| 719 |
},
|
| 720 |
"SS": {
|
| 721 |
-
"accuracy":
|
| 722 |
"count": 95
|
| 723 |
}
|
| 724 |
}
|
| 725 |
},
|
| 726 |
"add_S1": {
|
| 727 |
-
"full_accuracy": 0.
|
| 728 |
"n_examples": 100,
|
| 729 |
"per_subtask": {
|
| 730 |
"SA": {
|
| 731 |
-
"accuracy": 0.
|
| 732 |
"count": 204
|
| 733 |
},
|
| 734 |
"SC": {
|
| 735 |
-
"accuracy": 0.
|
| 736 |
"count": 169
|
| 737 |
},
|
| 738 |
"SS": {
|
| 739 |
-
"accuracy": 0.
|
| 740 |
"count": 31
|
| 741 |
},
|
| 742 |
"UC": {
|
| 743 |
-
"accuracy": 0.
|
| 744 |
"count": 296
|
| 745 |
}
|
| 746 |
}
|
| 747 |
},
|
| 748 |
"add_S2": {
|
| 749 |
-
"full_accuracy": 0.
|
| 750 |
"n_examples": 100,
|
| 751 |
"per_subtask": {
|
| 752 |
"SA": {
|
| 753 |
-
"accuracy": 0.
|
| 754 |
"count": 163
|
| 755 |
},
|
| 756 |
"SC": {
|
| 757 |
-
"accuracy": 0.
|
| 758 |
"count": 130
|
| 759 |
},
|
| 760 |
"SS": {
|
|
@@ -762,43 +762,43 @@
|
|
| 762 |
"count": 87
|
| 763 |
},
|
| 764 |
"UC": {
|
| 765 |
-
"accuracy": 0.
|
| 766 |
"count": 203
|
| 767 |
},
|
| 768 |
"US": {
|
| 769 |
-
"accuracy": 0.
|
| 770 |
"count": 117
|
| 771 |
}
|
| 772 |
}
|
| 773 |
},
|
| 774 |
"add_S3": {
|
| 775 |
-
"full_accuracy": 0.
|
| 776 |
"n_examples": 100,
|
| 777 |
"per_subtask": {
|
| 778 |
"SA": {
|
| 779 |
-
"accuracy": 0.
|
| 780 |
"count": 121
|
| 781 |
},
|
| 782 |
"SC": {
|
| 783 |
-
"accuracy": 0.
|
| 784 |
"count": 121
|
| 785 |
},
|
| 786 |
"SS": {
|
| 787 |
-
"accuracy": 0.
|
| 788 |
"count": 49
|
| 789 |
},
|
| 790 |
"UC": {
|
| 791 |
-
"accuracy": 0.
|
| 792 |
"count": 186
|
| 793 |
},
|
| 794 |
"US": {
|
| 795 |
-
"accuracy": 0.
|
| 796 |
"count": 223
|
| 797 |
}
|
| 798 |
}
|
| 799 |
},
|
| 800 |
"add_S4": {
|
| 801 |
-
"full_accuracy": 0.
|
| 802 |
"n_examples": 100,
|
| 803 |
"per_subtask": {
|
| 804 |
"SA": {
|
|
@@ -806,7 +806,7 @@
|
|
| 806 |
"count": 104
|
| 807 |
},
|
| 808 |
"SC": {
|
| 809 |
-
"accuracy": 0.
|
| 810 |
"count": 106
|
| 811 |
},
|
| 812 |
"SS": {
|
|
@@ -814,17 +814,17 @@
|
|
| 814 |
"count": 23
|
| 815 |
},
|
| 816 |
"UC": {
|
| 817 |
-
"accuracy": 0.
|
| 818 |
"count": 160
|
| 819 |
},
|
| 820 |
"US": {
|
| 821 |
-
"accuracy": 0.
|
| 822 |
"count": 307
|
| 823 |
}
|
| 824 |
}
|
| 825 |
},
|
| 826 |
"add_S5": {
|
| 827 |
-
"full_accuracy": 0.
|
| 828 |
"n_examples": 100,
|
| 829 |
"per_subtask": {
|
| 830 |
"SA": {
|
|
@@ -836,17 +836,17 @@
|
|
| 836 |
"count": 100
|
| 837 |
},
|
| 838 |
"UC": {
|
| 839 |
-
"accuracy": 0.
|
| 840 |
"count": 100
|
| 841 |
},
|
| 842 |
"US": {
|
| 843 |
-
"accuracy": 0.
|
| 844 |
"count": 400
|
| 845 |
}
|
| 846 |
}
|
| 847 |
},
|
| 848 |
"add_S6": {
|
| 849 |
-
"full_accuracy": 0.
|
| 850 |
"n_examples": 100,
|
| 851 |
"per_subtask": {
|
| 852 |
"SC": {
|
|
@@ -854,47 +854,47 @@
|
|
| 854 |
"count": 100
|
| 855 |
},
|
| 856 |
"UC": {
|
| 857 |
-
"accuracy": 0.
|
| 858 |
"count": 100
|
| 859 |
},
|
| 860 |
"US": {
|
| 861 |
-
"accuracy": 0.
|
| 862 |
"count": 500
|
| 863 |
}
|
| 864 |
}
|
| 865 |
},
|
| 866 |
"add_random": {
|
| 867 |
-
"full_accuracy": 0.
|
| 868 |
"n_examples": 200,
|
| 869 |
"per_subtask": {
|
| 870 |
"SA": {
|
| 871 |
-
"accuracy": 0.
|
| 872 |
"count": 447
|
| 873 |
},
|
| 874 |
"SC": {
|
| 875 |
-
"accuracy": 0.
|
| 876 |
"count": 320
|
| 877 |
},
|
| 878 |
"SS": {
|
| 879 |
-
"accuracy": 0.
|
| 880 |
"count": 56
|
| 881 |
},
|
| 882 |
"UC": {
|
| 883 |
-
"accuracy": 0.
|
| 884 |
"count": 529
|
| 885 |
},
|
| 886 |
"US": {
|
| 887 |
-
"accuracy": 0.
|
| 888 |
"count": 48
|
| 889 |
}
|
| 890 |
}
|
| 891 |
},
|
| 892 |
"add_C3": {
|
| 893 |
-
"full_accuracy": 0.
|
| 894 |
"n_examples": 100,
|
| 895 |
"per_subtask": {
|
| 896 |
"SA": {
|
| 897 |
-
"accuracy": 0.
|
| 898 |
"count": 300
|
| 899 |
},
|
| 900 |
"SC": {
|
|
@@ -902,39 +902,39 @@
|
|
| 902 |
"count": 100
|
| 903 |
},
|
| 904 |
"UC": {
|
| 905 |
-
"accuracy": 0.
|
| 906 |
"count": 193
|
| 907 |
},
|
| 908 |
"US": {
|
| 909 |
-
"accuracy": 0.
|
| 910 |
"count": 107
|
| 911 |
}
|
| 912 |
}
|
| 913 |
},
|
| 914 |
"add_C4": {
|
| 915 |
-
"full_accuracy": 0.
|
| 916 |
"n_examples": 100,
|
| 917 |
"per_subtask": {
|
| 918 |
"SA": {
|
| 919 |
-
"accuracy": 0.
|
| 920 |
"count": 200
|
| 921 |
},
|
| 922 |
"SC": {
|
| 923 |
-
"accuracy":
|
| 924 |
"count": 100
|
| 925 |
},
|
| 926 |
"UC": {
|
| 927 |
-
"accuracy": 0.
|
| 928 |
"count": 256
|
| 929 |
},
|
| 930 |
"US": {
|
| 931 |
-
"accuracy": 0.
|
| 932 |
"count": 144
|
| 933 |
}
|
| 934 |
}
|
| 935 |
},
|
| 936 |
"add_C5": {
|
| 937 |
-
"full_accuracy": 0.
|
| 938 |
"n_examples": 100,
|
| 939 |
"per_subtask": {
|
| 940 |
"SA": {
|
|
@@ -942,21 +942,21 @@
|
|
| 942 |
"count": 100
|
| 943 |
},
|
| 944 |
"SC": {
|
| 945 |
-
"accuracy":
|
| 946 |
"count": 100
|
| 947 |
},
|
| 948 |
"UC": {
|
| 949 |
-
"accuracy": 0.
|
| 950 |
"count": 306
|
| 951 |
},
|
| 952 |
"US": {
|
| 953 |
-
"accuracy": 0.
|
| 954 |
"count": 194
|
| 955 |
}
|
| 956 |
}
|
| 957 |
},
|
| 958 |
"add_C6": {
|
| 959 |
-
"full_accuracy": 0.
|
| 960 |
"n_examples": 100,
|
| 961 |
"per_subtask": {
|
| 962 |
"SC": {
|
|
@@ -964,39 +964,39 @@
|
|
| 964 |
"count": 100
|
| 965 |
},
|
| 966 |
"UC": {
|
| 967 |
-
"accuracy": 0.
|
| 968 |
"count": 366
|
| 969 |
},
|
| 970 |
"US": {
|
| 971 |
-
"accuracy": 0.
|
| 972 |
"count": 234
|
| 973 |
}
|
| 974 |
}
|
| 975 |
},
|
| 976 |
"sub_M0": {
|
| 977 |
-
"full_accuracy": 0.
|
| 978 |
"n_examples": 100,
|
| 979 |
"per_subtask": {
|
| 980 |
"MD": {
|
| 981 |
-
"accuracy": 0.
|
| 982 |
"count": 601
|
| 983 |
},
|
| 984 |
"ME": {
|
| 985 |
-
"accuracy":
|
| 986 |
"count": 99
|
| 987 |
}
|
| 988 |
}
|
| 989 |
},
|
| 990 |
"sub_M1": {
|
| 991 |
-
"full_accuracy": 0.
|
| 992 |
"n_examples": 100,
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
-
"accuracy": 0.
|
| 996 |
"count": 279
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
-
"accuracy": 0.
|
| 1000 |
"count": 145
|
| 1001 |
},
|
| 1002 |
"ME": {
|
|
@@ -1004,17 +1004,17 @@
|
|
| 1004 |
"count": 24
|
| 1005 |
},
|
| 1006 |
"UB": {
|
| 1007 |
-
"accuracy": 0.
|
| 1008 |
"count": 252
|
| 1009 |
}
|
| 1010 |
}
|
| 1011 |
},
|
| 1012 |
"sub_M2": {
|
| 1013 |
-
"full_accuracy": 0.
|
| 1014 |
"n_examples": 100,
|
| 1015 |
"per_subtask": {
|
| 1016 |
"MD": {
|
| 1017 |
-
"accuracy": 0.
|
| 1018 |
"count": 213
|
| 1019 |
},
|
| 1020 |
"MB": {
|
|
@@ -1022,29 +1022,29 @@
|
|
| 1022 |
"count": 113
|
| 1023 |
},
|
| 1024 |
"ME": {
|
| 1025 |
-
"accuracy": 0.
|
| 1026 |
"count": 85
|
| 1027 |
},
|
| 1028 |
"UB": {
|
| 1029 |
-
"accuracy": 0.
|
| 1030 |
"count": 181
|
| 1031 |
},
|
| 1032 |
"UD": {
|
| 1033 |
-
"accuracy": 0.
|
| 1034 |
"count": 108
|
| 1035 |
}
|
| 1036 |
}
|
| 1037 |
},
|
| 1038 |
"sub_M3": {
|
| 1039 |
-
"full_accuracy": 0.
|
| 1040 |
"n_examples": 100,
|
| 1041 |
"per_subtask": {
|
| 1042 |
"MD": {
|
| 1043 |
-
"accuracy":
|
| 1044 |
"count": 179
|
| 1045 |
},
|
| 1046 |
"MB": {
|
| 1047 |
-
"accuracy": 0.
|
| 1048 |
"count": 103
|
| 1049 |
},
|
| 1050 |
"ME": {
|
|
@@ -1052,11 +1052,11 @@
|
|
| 1052 |
"count": 56
|
| 1053 |
},
|
| 1054 |
"UB": {
|
| 1055 |
-
"accuracy": 0.
|
| 1056 |
"count": 149
|
| 1057 |
},
|
| 1058 |
"UD": {
|
| 1059 |
-
"accuracy": 0.
|
| 1060 |
"count": 213
|
| 1061 |
}
|
| 1062 |
}
|
|
@@ -1070,21 +1070,21 @@
|
|
| 1070 |
"count": 200
|
| 1071 |
},
|
| 1072 |
"MB": {
|
| 1073 |
-
"accuracy":
|
| 1074 |
"count": 100
|
| 1075 |
},
|
| 1076 |
"UB": {
|
| 1077 |
-
"accuracy": 0.
|
| 1078 |
"count": 100
|
| 1079 |
},
|
| 1080 |
"UD": {
|
| 1081 |
-
"accuracy": 0.
|
| 1082 |
"count": 300
|
| 1083 |
}
|
| 1084 |
}
|
| 1085 |
},
|
| 1086 |
"sub_M5": {
|
| 1087 |
-
"full_accuracy": 0.
|
| 1088 |
"n_examples": 100,
|
| 1089 |
"per_subtask": {
|
| 1090 |
"MD": {
|
|
@@ -1100,21 +1100,21 @@
|
|
| 1100 |
"count": 100
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
-
"accuracy": 0.
|
| 1104 |
"count": 400
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
},
|
| 1108 |
"sub_random": {
|
| 1109 |
-
"full_accuracy": 0.
|
| 1110 |
"n_examples": 200,
|
| 1111 |
"per_subtask": {
|
| 1112 |
"MD": {
|
| 1113 |
-
"accuracy": 0.
|
| 1114 |
"count": 600
|
| 1115 |
},
|
| 1116 |
"MB": {
|
| 1117 |
-
"accuracy": 0.
|
| 1118 |
"count": 267
|
| 1119 |
},
|
| 1120 |
"ME": {
|
|
@@ -1122,39 +1122,39 @@
|
|
| 1122 |
"count": 53
|
| 1123 |
},
|
| 1124 |
"UB": {
|
| 1125 |
-
"accuracy": 0.
|
| 1126 |
"count": 439
|
| 1127 |
},
|
| 1128 |
"UD": {
|
| 1129 |
-
"accuracy": 0.
|
| 1130 |
"count": 41
|
| 1131 |
}
|
| 1132 |
}
|
| 1133 |
},
|
| 1134 |
"sub_B3": {
|
| 1135 |
-
"full_accuracy": 0.
|
| 1136 |
"n_examples": 100,
|
| 1137 |
"per_subtask": {
|
| 1138 |
"MD": {
|
| 1139 |
-
"accuracy": 0.
|
| 1140 |
"count": 300
|
| 1141 |
},
|
| 1142 |
"MB": {
|
| 1143 |
-
"accuracy": 0.
|
| 1144 |
"count": 100
|
| 1145 |
},
|
| 1146 |
"UB": {
|
| 1147 |
-
"accuracy": 0.
|
| 1148 |
"count": 197
|
| 1149 |
},
|
| 1150 |
"UD": {
|
| 1151 |
-
"accuracy": 0.
|
| 1152 |
"count": 103
|
| 1153 |
}
|
| 1154 |
}
|
| 1155 |
},
|
| 1156 |
"sub_B4": {
|
| 1157 |
-
"full_accuracy": 0.
|
| 1158 |
"n_examples": 100,
|
| 1159 |
"per_subtask": {
|
| 1160 |
"MD": {
|
|
@@ -1166,17 +1166,17 @@
|
|
| 1166 |
"count": 100
|
| 1167 |
},
|
| 1168 |
"UB": {
|
| 1169 |
-
"accuracy": 0.
|
| 1170 |
"count": 247
|
| 1171 |
},
|
| 1172 |
"UD": {
|
| 1173 |
-
"accuracy": 0.
|
| 1174 |
"count": 153
|
| 1175 |
}
|
| 1176 |
}
|
| 1177 |
},
|
| 1178 |
"sub_B5": {
|
| 1179 |
-
"full_accuracy": 0.
|
| 1180 |
"n_examples": 100,
|
| 1181 |
"per_subtask": {
|
| 1182 |
"MD": {
|
|
@@ -1188,18 +1188,18 @@
|
|
| 1188 |
"count": 100
|
| 1189 |
},
|
| 1190 |
"UB": {
|
| 1191 |
-
"accuracy": 0.
|
| 1192 |
"count": 298
|
| 1193 |
},
|
| 1194 |
"UD": {
|
| 1195 |
-
"accuracy": 0.
|
| 1196 |
"count": 202
|
| 1197 |
}
|
| 1198 |
}
|
| 1199 |
}
|
| 1200 |
},
|
| 1201 |
"summary": {
|
| 1202 |
-
"overall_accuracy": 0.
|
| 1203 |
"total_examples": 2400,
|
| 1204 |
"n_splits": 22
|
| 1205 |
}
|
|
|
|
| 159 |
7800
|
| 160 |
],
|
| 161 |
"loss": [
|
| 162 |
+
8.74937915802002,
|
| 163 |
+
6.198915004730225,
|
| 164 |
+
4.366815090179443,
|
| 165 |
+
2.2759313583374023,
|
| 166 |
+
1.9526265859603882,
|
| 167 |
+
1.877150535583496,
|
| 168 |
+
1.8139151334762573,
|
| 169 |
+
1.822188377380371,
|
| 170 |
+
1.71466064453125,
|
| 171 |
+
1.590683937072754,
|
| 172 |
+
1.4826921224594116,
|
| 173 |
+
1.133190393447876,
|
| 174 |
+
0.8561835885047913,
|
| 175 |
+
0.7075616121292114,
|
| 176 |
+
0.6399551033973694,
|
| 177 |
+
0.6669952273368835,
|
| 178 |
+
0.6160100698471069,
|
| 179 |
+
0.5750561952590942,
|
| 180 |
+
0.5242418646812439,
|
| 181 |
+
0.5324519872665405,
|
| 182 |
+
0.49814528226852417,
|
| 183 |
+
0.4612176716327667,
|
| 184 |
+
0.5026556849479675,
|
| 185 |
+
0.47276973724365234,
|
| 186 |
+
0.43902602791786194,
|
| 187 |
+
0.446272611618042,
|
| 188 |
+
0.38574811816215515,
|
| 189 |
+
0.3711676001548767,
|
| 190 |
+
0.3969157338142395,
|
| 191 |
+
0.39037615060806274,
|
| 192 |
+
0.3659220337867737,
|
| 193 |
+
0.2901519238948822,
|
| 194 |
+
0.372765451669693,
|
| 195 |
+
0.33219239115715027,
|
| 196 |
+
0.34733083844184875,
|
| 197 |
+
0.31526169180870056,
|
| 198 |
+
0.33172616362571716,
|
| 199 |
+
0.3349834382534027,
|
| 200 |
+
0.3454124927520752,
|
| 201 |
+
0.32427385449409485,
|
| 202 |
+
0.29763302206993103,
|
| 203 |
+
0.2891975939273834,
|
| 204 |
+
0.3104265332221985,
|
| 205 |
+
0.2937973141670227,
|
| 206 |
+
0.29948028922080994,
|
| 207 |
+
0.26262804865837097,
|
| 208 |
+
0.26943641901016235,
|
| 209 |
+
0.2750188410282135,
|
| 210 |
+
0.2822719216346741,
|
| 211 |
+
0.2253115326166153,
|
| 212 |
+
0.2866693139076233,
|
| 213 |
+
0.29621443152427673,
|
| 214 |
+
0.2518032193183899,
|
| 215 |
+
0.25790685415267944,
|
| 216 |
+
0.33121928572654724,
|
| 217 |
+
0.2776740789413452,
|
| 218 |
+
0.240325927734375,
|
| 219 |
+
0.25502628087997437,
|
| 220 |
+
0.2516288459300995,
|
| 221 |
+
0.2600439190864563,
|
| 222 |
+
0.22953486442565918,
|
| 223 |
+
0.25047045946121216,
|
| 224 |
+
0.287687748670578,
|
| 225 |
+
0.24002419412136078,
|
| 226 |
+
0.20791330933570862,
|
| 227 |
+
0.24204131960868835,
|
| 228 |
+
0.27317410707473755,
|
| 229 |
+
0.24345578253269196,
|
| 230 |
+
0.21374334394931793,
|
| 231 |
+
0.21283268928527832,
|
| 232 |
+
0.21549828350543976,
|
| 233 |
+
0.19832827150821686,
|
| 234 |
+
0.21149209141731262,
|
| 235 |
+
0.1855495721101761,
|
| 236 |
+
0.19525133073329926,
|
| 237 |
+
0.23278847336769104,
|
| 238 |
+
0.2606830298900604,
|
| 239 |
+
0.20044934749603271,
|
| 240 |
+
0.181396022439003,
|
| 241 |
+
0.21328875422477722,
|
| 242 |
+
0.212825208902359,
|
| 243 |
+
0.21052296459674835,
|
| 244 |
+
0.19027332961559296,
|
| 245 |
+
0.2117026001214981,
|
| 246 |
+
0.22618059813976288,
|
| 247 |
+
0.22302715480327606,
|
| 248 |
+
0.17805133759975433,
|
| 249 |
+
0.18642711639404297,
|
| 250 |
+
0.2146042138338089,
|
| 251 |
+
0.19574260711669922,
|
| 252 |
+
0.16053321957588196,
|
| 253 |
+
0.21608540415763855,
|
| 254 |
+
0.20082899928092957,
|
| 255 |
+
0.23242345452308655,
|
| 256 |
+
0.17946086823940277,
|
| 257 |
+
0.2614651918411255,
|
| 258 |
+
0.1651460975408554,
|
| 259 |
+
0.1777617186307907,
|
| 260 |
+
0.15014827251434326,
|
| 261 |
+
0.20371000468730927,
|
| 262 |
+
0.1573261022567749,
|
| 263 |
+
0.19635023176670074,
|
| 264 |
+
0.18772493302822113,
|
| 265 |
+
0.1814812421798706,
|
| 266 |
+
0.18410103023052216,
|
| 267 |
+
0.20629878342151642,
|
| 268 |
+
0.1857832968235016,
|
| 269 |
+
0.17055557668209076,
|
| 270 |
+
0.16345703601837158,
|
| 271 |
+
0.16755636036396027,
|
| 272 |
+
0.17432273924350739,
|
| 273 |
+
0.15670685470104218,
|
| 274 |
+
0.15046896040439606,
|
| 275 |
+
0.14622943103313446,
|
| 276 |
+
0.1660774052143097,
|
| 277 |
+
0.16316993534564972,
|
| 278 |
+
0.16458259522914886,
|
| 279 |
+
0.16533777117729187,
|
| 280 |
+
0.18796680867671967,
|
| 281 |
+
0.16055859625339508,
|
| 282 |
+
0.16241776943206787,
|
| 283 |
+
0.15573906898498535,
|
| 284 |
+
0.18253065645694733,
|
| 285 |
+
0.15446387231349945,
|
| 286 |
+
0.16669152677059174,
|
| 287 |
+
0.16877718269824982,
|
| 288 |
+
0.15042708814144135,
|
| 289 |
+
0.14171156287193298,
|
| 290 |
+
0.1469859778881073,
|
| 291 |
+
0.16647039353847504,
|
| 292 |
+
0.1766190528869629,
|
| 293 |
+
0.15534673631191254,
|
| 294 |
+
0.15092872083187103,
|
| 295 |
+
0.16818329691886902,
|
| 296 |
+
0.14259760081768036,
|
| 297 |
+
0.16949117183685303,
|
| 298 |
+
0.13747766613960266,
|
| 299 |
+
0.16281220316886902,
|
| 300 |
+
0.1641203612089157,
|
| 301 |
+
0.15849816799163818,
|
| 302 |
+
0.14388667047023773,
|
| 303 |
+
0.14095112681388855,
|
| 304 |
+
0.14720116555690765,
|
| 305 |
+
0.15021368861198425,
|
| 306 |
+
0.15137387812137604,
|
| 307 |
+
0.15634380280971527,
|
| 308 |
+
0.14748618006706238,
|
| 309 |
+
0.1435571163892746,
|
| 310 |
+
0.13644962012767792,
|
| 311 |
+
0.16987796127796173,
|
| 312 |
+
0.15995793044567108,
|
| 313 |
+
0.17382332682609558,
|
| 314 |
+
0.157388374209404,
|
| 315 |
+
0.13605724275112152,
|
| 316 |
+
0.174538716673851,
|
| 317 |
+
0.15863211452960968
|
| 318 |
],
|
| 319 |
"base_loss": [
|
| 320 |
+
8.74937915802002,
|
| 321 |
+
6.198915004730225,
|
| 322 |
+
4.366815090179443,
|
| 323 |
+
2.2759313583374023,
|
| 324 |
+
1.9526265859603882,
|
| 325 |
+
1.877150535583496,
|
| 326 |
+
1.8139151334762573,
|
| 327 |
+
1.822188377380371,
|
| 328 |
+
1.71466064453125,
|
| 329 |
+
1.590683937072754,
|
| 330 |
+
1.4826921224594116,
|
| 331 |
+
1.133190393447876,
|
| 332 |
+
0.8561835885047913,
|
| 333 |
+
0.7075616121292114,
|
| 334 |
+
0.6399551033973694,
|
| 335 |
+
0.6669952273368835,
|
| 336 |
+
0.6160100698471069,
|
| 337 |
+
0.5750561952590942,
|
| 338 |
+
0.5242418646812439,
|
| 339 |
+
0.5324519872665405,
|
| 340 |
+
0.49814528226852417,
|
| 341 |
+
0.4612176716327667,
|
| 342 |
+
0.5026556849479675,
|
| 343 |
+
0.47276973724365234,
|
| 344 |
+
0.43902602791786194,
|
| 345 |
+
0.446272611618042,
|
| 346 |
+
0.38574811816215515,
|
| 347 |
+
0.3711676001548767,
|
| 348 |
+
0.3969157338142395,
|
| 349 |
+
0.39037615060806274,
|
| 350 |
+
0.3659220337867737,
|
| 351 |
+
0.2901519238948822,
|
| 352 |
+
0.372765451669693,
|
| 353 |
+
0.33219239115715027,
|
| 354 |
+
0.34733083844184875,
|
| 355 |
+
0.31526169180870056,
|
| 356 |
+
0.33172616362571716,
|
| 357 |
+
0.3349834382534027,
|
| 358 |
+
0.3454124927520752,
|
| 359 |
+
0.32427385449409485,
|
| 360 |
+
0.29763302206993103,
|
| 361 |
+
0.2891975939273834,
|
| 362 |
+
0.3104265332221985,
|
| 363 |
+
0.2937973141670227,
|
| 364 |
+
0.29948028922080994,
|
| 365 |
+
0.26262804865837097,
|
| 366 |
+
0.26943641901016235,
|
| 367 |
+
0.2750188410282135,
|
| 368 |
+
0.2822719216346741,
|
| 369 |
+
0.2253115326166153,
|
| 370 |
+
0.2866693139076233,
|
| 371 |
+
0.29621443152427673,
|
| 372 |
+
0.2518032193183899,
|
| 373 |
+
0.25790685415267944,
|
| 374 |
+
0.33121928572654724,
|
| 375 |
+
0.2776740789413452,
|
| 376 |
+
0.240325927734375,
|
| 377 |
+
0.25502628087997437,
|
| 378 |
+
0.2516288459300995,
|
| 379 |
+
0.2600439190864563,
|
| 380 |
+
0.22953486442565918,
|
| 381 |
+
0.25047045946121216,
|
| 382 |
+
0.287687748670578,
|
| 383 |
+
0.24002419412136078,
|
| 384 |
+
0.20791330933570862,
|
| 385 |
+
0.24204131960868835,
|
| 386 |
+
0.27317410707473755,
|
| 387 |
+
0.24345578253269196,
|
| 388 |
+
0.21374334394931793,
|
| 389 |
+
0.21283268928527832,
|
| 390 |
+
0.21549828350543976,
|
| 391 |
+
0.19832827150821686,
|
| 392 |
+
0.21149209141731262,
|
| 393 |
+
0.1855495721101761,
|
| 394 |
+
0.19525133073329926,
|
| 395 |
+
0.23278847336769104,
|
| 396 |
+
0.2606830298900604,
|
| 397 |
+
0.20044934749603271,
|
| 398 |
+
0.181396022439003,
|
| 399 |
+
0.21328875422477722,
|
| 400 |
+
0.212825208902359,
|
| 401 |
+
0.21052296459674835,
|
| 402 |
+
0.19027332961559296,
|
| 403 |
+
0.2117026001214981,
|
| 404 |
+
0.22618059813976288,
|
| 405 |
+
0.22302715480327606,
|
| 406 |
+
0.17805133759975433,
|
| 407 |
+
0.18642711639404297,
|
| 408 |
+
0.2146042138338089,
|
| 409 |
+
0.19574260711669922,
|
| 410 |
+
0.16053321957588196,
|
| 411 |
+
0.21608540415763855,
|
| 412 |
+
0.20082899928092957,
|
| 413 |
+
0.23242345452308655,
|
| 414 |
+
0.17946086823940277,
|
| 415 |
+
0.2614651918411255,
|
| 416 |
+
0.1651460975408554,
|
| 417 |
+
0.1777617186307907,
|
| 418 |
+
0.15014827251434326,
|
| 419 |
+
0.20371000468730927,
|
| 420 |
+
0.1573261022567749,
|
| 421 |
+
0.19635023176670074,
|
| 422 |
+
0.18772493302822113,
|
| 423 |
+
0.1814812421798706,
|
| 424 |
+
0.18410103023052216,
|
| 425 |
+
0.20629878342151642,
|
| 426 |
+
0.1857832968235016,
|
| 427 |
+
0.17055557668209076,
|
| 428 |
+
0.16345703601837158,
|
| 429 |
+
0.16755636036396027,
|
| 430 |
+
0.17432273924350739,
|
| 431 |
+
0.15670685470104218,
|
| 432 |
+
0.15046896040439606,
|
| 433 |
+
0.14622943103313446,
|
| 434 |
+
0.1660774052143097,
|
| 435 |
+
0.16316993534564972,
|
| 436 |
+
0.16458259522914886,
|
| 437 |
+
0.16533777117729187,
|
| 438 |
+
0.18796680867671967,
|
| 439 |
+
0.16055859625339508,
|
| 440 |
+
0.16241776943206787,
|
| 441 |
+
0.15573906898498535,
|
| 442 |
+
0.18253065645694733,
|
| 443 |
+
0.15446387231349945,
|
| 444 |
+
0.16669152677059174,
|
| 445 |
+
0.16877718269824982,
|
| 446 |
+
0.15042708814144135,
|
| 447 |
+
0.14171156287193298,
|
| 448 |
+
0.1469859778881073,
|
| 449 |
+
0.16647039353847504,
|
| 450 |
+
0.1766190528869629,
|
| 451 |
+
0.15534673631191254,
|
| 452 |
+
0.15092872083187103,
|
| 453 |
+
0.16818329691886902,
|
| 454 |
+
0.14259760081768036,
|
| 455 |
+
0.16949117183685303,
|
| 456 |
+
0.13747766613960266,
|
| 457 |
+
0.16281220316886902,
|
| 458 |
+
0.1641203612089157,
|
| 459 |
+
0.15849816799163818,
|
| 460 |
+
0.14388667047023773,
|
| 461 |
+
0.14095112681388855,
|
| 462 |
+
0.14720116555690765,
|
| 463 |
+
0.15021368861198425,
|
| 464 |
+
0.15137387812137604,
|
| 465 |
+
0.15634380280971527,
|
| 466 |
+
0.14748618006706238,
|
| 467 |
+
0.1435571163892746,
|
| 468 |
+
0.13644962012767792,
|
| 469 |
+
0.16987796127796173,
|
| 470 |
+
0.15995793044567108,
|
| 471 |
+
0.17382332682609558,
|
| 472 |
+
0.157388374209404,
|
| 473 |
+
0.13605724275112152,
|
| 474 |
+
0.174538716673851,
|
| 475 |
+
0.15863211452960968
|
| 476 |
],
|
| 477 |
"lr": [
|
| 478 |
+
1.6752136752136756e-05,
|
| 479 |
+
3.384615384615385e-05,
|
| 480 |
+
5.094017094017095e-05,
|
| 481 |
+
6.803418803418804e-05,
|
| 482 |
+
7.99992282348104e-05,
|
| 483 |
+
7.998550879323477e-05,
|
| 484 |
+
7.99546457847615e-05,
|
| 485 |
+
7.990665244173565e-05,
|
| 486 |
+
7.9841549341039e-05,
|
| 487 |
+
7.975936439526778e-05,
|
| 488 |
+
7.966013284076529e-05,
|
| 489 |
+
7.95438972225146e-05,
|
| 490 |
+
7.941070737589747e-05,
|
| 491 |
+
7.926062040532787e-05,
|
| 492 |
+
7.909370065976863e-05,
|
| 493 |
+
7.891001970514232e-05,
|
| 494 |
+
7.870965629364761e-05,
|
| 495 |
+
7.849269632999478e-05,
|
| 496 |
+
7.825923283457459e-05,
|
| 497 |
+
7.800936590357617e-05,
|
| 498 |
+
7.774320266607144e-05,
|
| 499 |
+
7.746085723808407e-05,
|
| 500 |
+
7.716245067366288e-05,
|
| 501 |
+
7.684811091298052e-05,
|
| 502 |
+
7.651797272747994e-05,
|
| 503 |
+
7.617217766209175e-05,
|
| 504 |
+
7.581087397454772e-05,
|
| 505 |
+
7.5434216571816e-05,
|
| 506 |
+
7.504236694368569e-05,
|
| 507 |
+
7.463549309352889e-05,
|
| 508 |
+
7.421376946627028e-05,
|
| 509 |
+
7.377737687359476e-05,
|
| 510 |
+
7.332650241642543e-05,
|
| 511 |
+
7.286133940470513e-05,
|
| 512 |
+
7.238208727451582e-05,
|
| 513 |
+
7.188895150257153e-05,
|
| 514 |
+
7.138214351812129e-05,
|
| 515 |
+
7.086188061229997e-05,
|
| 516 |
+
7.032838584496603e-05,
|
| 517 |
+
6.97818879490657e-05,
|
| 518 |
+
6.922262123256506e-05,
|
| 519 |
+
6.865082547799175e-05,
|
| 520 |
+
6.806674583962958e-05,
|
| 521 |
+
6.747063273840991e-05,
|
| 522 |
+
6.686274175454515e-05,
|
| 523 |
+
6.624333351795003e-05,
|
| 524 |
+
6.561267359649806e-05,
|
| 525 |
+
6.497103238216073e-05,
|
| 526 |
+
6.43186849750784e-05,
|
| 527 |
+
6.365591106561267e-05,
|
| 528 |
+
6.298299481443074e-05,
|
| 529 |
+
6.230022473067294e-05,
|
| 530 |
+
6.160789354825612e-05,
|
| 531 |
+
6.090629810036558e-05,
|
| 532 |
+
6.019573919218951e-05,
|
| 533 |
+
5.947652147195031e-05,
|
| 534 |
+
5.8748953300288454e-05,
|
| 535 |
+
5.8013346618054525e-05,
|
| 536 |
+
5.7270016812566265e-05,
|
| 537 |
+
5.651928258238803e-05,
|
| 538 |
+
5.5761465800690523e-05,
|
| 539 |
+
5.499689137724945e-05,
|
| 540 |
+
5.422588711914222e-05,
|
| 541 |
+
5.3448783590202484e-05,
|
| 542 |
+
5.26659139692927e-05,
|
| 543 |
+
5.1877613907455556e-05,
|
| 544 |
+
5.1084221384005374e-05,
|
| 545 |
+
5.028607656162141e-05,
|
| 546 |
+
4.948352164050493e-05,
|
| 547 |
+
4.867690071166274e-05,
|
| 548 |
+
4.786655960938013e-05,
|
| 549 |
+
4.705284576294624e-05,
|
| 550 |
+
4.623610804769575e-05,
|
| 551 |
+
4.541669663543045e-05,
|
| 552 |
+
4.4594962844284974e-05,
|
| 553 |
+
4.377125898810118e-05,
|
| 554 |
+
4.294593822537543e-05,
|
| 555 |
+
4.2119354407843914e-05,
|
| 556 |
+
4.129186192877056e-05,
|
| 557 |
+
4.046381557100299e-05,
|
| 558 |
+
3.963557035486121e-05,
|
| 559 |
+
3.8807481385924744e-05,
|
| 560 |
+
3.79799037027829e-05,
|
| 561 |
+
3.7153192124814045e-05,
|
| 562 |
+
3.632770110005876e-05,
|
| 563 |
+
3.5503784553252085e-05,
|
| 564 |
+
3.4681795734080355e-05,
|
| 565 |
+
3.386208706572725e-05,
|
| 566 |
+
3.3045009993774335e-05,
|
| 567 |
+
3.223091483552074e-05,
|
| 568 |
+
3.1420150629786436e-05,
|
| 569 |
+
3.061306498726391e-05,
|
| 570 |
+
2.9810003941481836e-05,
|
| 571 |
+
2.9011311800445205e-05,
|
| 572 |
+
2.8217330999015148e-05,
|
| 573 |
+
2.742840195209184e-05,
|
| 574 |
+
2.664486290866354e-05,
|
| 575 |
+
2.586704980678411e-05,
|
| 576 |
+
2.509529612954155e-05,
|
| 577 |
+
2.432993276207881e-05,
|
| 578 |
+
2.357128784972872e-05,
|
| 579 |
+
2.281968665732344e-05,
|
| 580 |
+
2.2075451429738966e-05,
|
| 581 |
+
2.133890125373438e-05,
|
| 582 |
+
2.061035192114523e-05,
|
| 583 |
+
1.9890115793489398e-05,
|
| 584 |
+
1.9178501668043937e-05,
|
| 585 |
+
1.847581464544989e-05,
|
| 586 |
+
1.7782355998902056e-05,
|
| 587 |
+
1.7098423044979796e-05,
|
| 588 |
+
1.642430901617411e-05,
|
| 589 |
+
1.576030293516598e-05,
|
| 590 |
+
1.5106689490909282e-05,
|
| 591 |
+
1.4463748916572114e-05,
|
| 592 |
+
1.3831756869388313e-05,
|
| 593 |
+
1.3210984312470934e-05,
|
| 594 |
+
1.260169739863832e-05,
|
| 595 |
+
1.2004157356302488e-05,
|
| 596 |
+
1.1418620377469014e-05,
|
| 597 |
+
1.084533750789595e-05,
|
| 598 |
+
1.028455453945948e-05,
|
| 599 |
+
9.73651190477193e-06,
|
| 600 |
+
9.201444574097636e-06,
|
| 601 |
+
8.679581954610725e-06,
|
| 602 |
+
8.171147792038026e-06,
|
| 603 |
+
7.676360074729406e-06,
|
| 604 |
+
7.1954309401963505e-06,
|
| 605 |
+
6.728566584159262e-06,
|
| 606 |
+
6.27596717214213e-06,
|
| 607 |
+
5.8378267536526975e-06,
|
| 608 |
+
5.414333178984774e-06,
|
| 609 |
+
5.005668018678451e-06,
|
| 610 |
+
4.612006485672775e-06,
|
| 611 |
+
4.233517360184123e-06,
|
| 612 |
+
3.870362917342623e-06,
|
| 613 |
+
3.5226988576176015e-06,
|
| 614 |
+
3.1906742400618397e-06,
|
| 615 |
+
2.874431418403334e-06,
|
| 616 |
+
2.5741059800119272e-06,
|
| 617 |
+
2.2898266877669604e-06,
|
| 618 |
+
2.0217154248508964e-06,
|
| 619 |
+
1.7698871424925945e-06,
|
| 620 |
+
1.53444981068255e-06,
|
| 621 |
+
1.315504371881442e-06,
|
| 622 |
+
1.1131446977415172e-06,
|
| 623 |
+
9.274575488597004e-07,
|
| 624 |
+
7.58522537579438e-07,
|
| 625 |
+
6.064120938573448e-07,
|
| 626 |
+
4.7119143420927493e-07,
|
| 627 |
+
3.5291853374905817e-07,
|
| 628 |
+
2.5164410133206253e-07,
|
| 629 |
+
1.6741155781396346e-07,
|
| 630 |
+
1.0025701743435978e-07,
|
| 631 |
+
5.020927233295947e-08,
|
| 632 |
+
1.728978020511196e-08,
|
| 633 |
+
1.5126551019539748e-09
|
| 634 |
],
|
| 635 |
"eval_step": [
|
| 636 |
390,
|
|
|
|
| 677 |
20
|
| 678 |
],
|
| 679 |
"eval_accuracy": [
|
| 680 |
+
0.005555555555555556,
|
| 681 |
+
0.05333333333333334,
|
| 682 |
+
0.20555555555555555,
|
| 683 |
+
0.29333333333333333,
|
| 684 |
+
0.3055555555555556,
|
| 685 |
+
0.31777777777777777,
|
| 686 |
+
0.36777777777777776,
|
| 687 |
+
0.3988888888888889,
|
| 688 |
+
0.4388888888888889,
|
| 689 |
+
0.5322222222222223,
|
| 690 |
+
0.5355555555555556,
|
| 691 |
+
0.5366666666666666,
|
| 692 |
+
0.62,
|
| 693 |
+
0.5488888888888889,
|
| 694 |
+
0.5488888888888889,
|
| 695 |
+
0.5866666666666667,
|
| 696 |
+
0.5811111111111111,
|
| 697 |
+
0.5811111111111111,
|
| 698 |
+
0.5733333333333334,
|
| 699 |
+
0.5777777777777777
|
| 700 |
]
|
| 701 |
},
|
| 702 |
+
"final_accuracy": 0.49541666666666667,
|
| 703 |
"sft_eval": {
|
| 704 |
"config": {
|
| 705 |
"ops": "add_sub",
|
|
|
|
| 710 |
},
|
| 711 |
"splits": {
|
| 712 |
"add_S0": {
|
| 713 |
+
"full_accuracy": 0.8,
|
| 714 |
"n_examples": 100,
|
| 715 |
"per_subtask": {
|
| 716 |
"SA": {
|
| 717 |
+
"accuracy": 0.9636363636363636,
|
| 718 |
"count": 605
|
| 719 |
},
|
| 720 |
"SS": {
|
| 721 |
+
"accuracy": 1.0,
|
| 722 |
"count": 95
|
| 723 |
}
|
| 724 |
}
|
| 725 |
},
|
| 726 |
"add_S1": {
|
| 727 |
+
"full_accuracy": 0.82,
|
| 728 |
"n_examples": 100,
|
| 729 |
"per_subtask": {
|
| 730 |
"SA": {
|
| 731 |
+
"accuracy": 0.9754901960784313,
|
| 732 |
"count": 204
|
| 733 |
},
|
| 734 |
"SC": {
|
| 735 |
+
"accuracy": 0.9881656804733728,
|
| 736 |
"count": 169
|
| 737 |
},
|
| 738 |
"SS": {
|
| 739 |
+
"accuracy": 0.967741935483871,
|
| 740 |
"count": 31
|
| 741 |
},
|
| 742 |
"UC": {
|
| 743 |
+
"accuracy": 0.9628378378378378,
|
| 744 |
"count": 296
|
| 745 |
}
|
| 746 |
}
|
| 747 |
},
|
| 748 |
"add_S2": {
|
| 749 |
+
"full_accuracy": 0.55,
|
| 750 |
"n_examples": 100,
|
| 751 |
"per_subtask": {
|
| 752 |
"SA": {
|
| 753 |
+
"accuracy": 0.9815950920245399,
|
| 754 |
"count": 163
|
| 755 |
},
|
| 756 |
"SC": {
|
| 757 |
+
"accuracy": 0.9384615384615385,
|
| 758 |
"count": 130
|
| 759 |
},
|
| 760 |
"SS": {
|
|
|
|
| 762 |
"count": 87
|
| 763 |
},
|
| 764 |
"UC": {
|
| 765 |
+
"accuracy": 0.8472906403940886,
|
| 766 |
"count": 203
|
| 767 |
},
|
| 768 |
"US": {
|
| 769 |
+
"accuracy": 0.9743589743589743,
|
| 770 |
"count": 117
|
| 771 |
}
|
| 772 |
}
|
| 773 |
},
|
| 774 |
"add_S3": {
|
| 775 |
+
"full_accuracy": 0.27,
|
| 776 |
"n_examples": 100,
|
| 777 |
"per_subtask": {
|
| 778 |
"SA": {
|
| 779 |
+
"accuracy": 0.9834710743801653,
|
| 780 |
"count": 121
|
| 781 |
},
|
| 782 |
"SC": {
|
| 783 |
+
"accuracy": 0.9586776859504132,
|
| 784 |
"count": 121
|
| 785 |
},
|
| 786 |
"SS": {
|
| 787 |
+
"accuracy": 0.9795918367346939,
|
| 788 |
"count": 49
|
| 789 |
},
|
| 790 |
"UC": {
|
| 791 |
+
"accuracy": 0.6720430107526881,
|
| 792 |
"count": 186
|
| 793 |
},
|
| 794 |
"US": {
|
| 795 |
+
"accuracy": 0.7668161434977578,
|
| 796 |
"count": 223
|
| 797 |
}
|
| 798 |
}
|
| 799 |
},
|
| 800 |
"add_S4": {
|
| 801 |
+
"full_accuracy": 0.36,
|
| 802 |
"n_examples": 100,
|
| 803 |
"per_subtask": {
|
| 804 |
"SA": {
|
|
|
|
| 806 |
"count": 104
|
| 807 |
},
|
| 808 |
"SC": {
|
| 809 |
+
"accuracy": 0.9716981132075472,
|
| 810 |
"count": 106
|
| 811 |
},
|
| 812 |
"SS": {
|
|
|
|
| 814 |
"count": 23
|
| 815 |
},
|
| 816 |
"UC": {
|
| 817 |
+
"accuracy": 0.7125,
|
| 818 |
"count": 160
|
| 819 |
},
|
| 820 |
"US": {
|
| 821 |
+
"accuracy": 0.6156351791530945,
|
| 822 |
"count": 307
|
| 823 |
}
|
| 824 |
}
|
| 825 |
},
|
| 826 |
"add_S5": {
|
| 827 |
+
"full_accuracy": 0.22,
|
| 828 |
"n_examples": 100,
|
| 829 |
"per_subtask": {
|
| 830 |
"SA": {
|
|
|
|
| 836 |
"count": 100
|
| 837 |
},
|
| 838 |
"UC": {
|
| 839 |
+
"accuracy": 0.39,
|
| 840 |
"count": 100
|
| 841 |
},
|
| 842 |
"US": {
|
| 843 |
+
"accuracy": 0.5075,
|
| 844 |
"count": 400
|
| 845 |
}
|
| 846 |
}
|
| 847 |
},
|
| 848 |
"add_S6": {
|
| 849 |
+
"full_accuracy": 0.55,
|
| 850 |
"n_examples": 100,
|
| 851 |
"per_subtask": {
|
| 852 |
"SC": {
|
|
|
|
| 854 |
"count": 100
|
| 855 |
},
|
| 856 |
"UC": {
|
| 857 |
+
"accuracy": 0.61,
|
| 858 |
"count": 100
|
| 859 |
},
|
| 860 |
"US": {
|
| 861 |
+
"accuracy": 0.628,
|
| 862 |
"count": 500
|
| 863 |
}
|
| 864 |
}
|
| 865 |
},
|
| 866 |
"add_random": {
|
| 867 |
+
"full_accuracy": 0.75,
|
| 868 |
"n_examples": 200,
|
| 869 |
"per_subtask": {
|
| 870 |
"SA": {
|
| 871 |
+
"accuracy": 0.9753914988814317,
|
| 872 |
"count": 447
|
| 873 |
},
|
| 874 |
"SC": {
|
| 875 |
+
"accuracy": 0.975,
|
| 876 |
"count": 320
|
| 877 |
},
|
| 878 |
"SS": {
|
| 879 |
+
"accuracy": 0.9642857142857143,
|
| 880 |
"count": 56
|
| 881 |
},
|
| 882 |
"UC": {
|
| 883 |
+
"accuracy": 0.9395085066162571,
|
| 884 |
"count": 529
|
| 885 |
},
|
| 886 |
"US": {
|
| 887 |
+
"accuracy": 0.9166666666666666,
|
| 888 |
"count": 48
|
| 889 |
}
|
| 890 |
}
|
| 891 |
},
|
| 892 |
"add_C3": {
|
| 893 |
+
"full_accuracy": 0.54,
|
| 894 |
"n_examples": 100,
|
| 895 |
"per_subtask": {
|
| 896 |
"SA": {
|
| 897 |
+
"accuracy": 0.9866666666666667,
|
| 898 |
"count": 300
|
| 899 |
},
|
| 900 |
"SC": {
|
|
|
|
| 902 |
"count": 100
|
| 903 |
},
|
| 904 |
"UC": {
|
| 905 |
+
"accuracy": 0.7979274611398963,
|
| 906 |
"count": 193
|
| 907 |
},
|
| 908 |
"US": {
|
| 909 |
+
"accuracy": 0.7757009345794392,
|
| 910 |
"count": 107
|
| 911 |
}
|
| 912 |
}
|
| 913 |
},
|
| 914 |
"add_C4": {
|
| 915 |
+
"full_accuracy": 0.48,
|
| 916 |
"n_examples": 100,
|
| 917 |
"per_subtask": {
|
| 918 |
"SA": {
|
| 919 |
+
"accuracy": 0.995,
|
| 920 |
"count": 200
|
| 921 |
},
|
| 922 |
"SC": {
|
| 923 |
+
"accuracy": 1.0,
|
| 924 |
"count": 100
|
| 925 |
},
|
| 926 |
"UC": {
|
| 927 |
+
"accuracy": 0.78515625,
|
| 928 |
"count": 256
|
| 929 |
},
|
| 930 |
"US": {
|
| 931 |
+
"accuracy": 0.75,
|
| 932 |
"count": 144
|
| 933 |
}
|
| 934 |
}
|
| 935 |
},
|
| 936 |
"add_C5": {
|
| 937 |
+
"full_accuracy": 0.45,
|
| 938 |
"n_examples": 100,
|
| 939 |
"per_subtask": {
|
| 940 |
"SA": {
|
|
|
|
| 942 |
"count": 100
|
| 943 |
},
|
| 944 |
"SC": {
|
| 945 |
+
"accuracy": 1.0,
|
| 946 |
"count": 100
|
| 947 |
},
|
| 948 |
"UC": {
|
| 949 |
+
"accuracy": 0.8137254901960784,
|
| 950 |
"count": 306
|
| 951 |
},
|
| 952 |
"US": {
|
| 953 |
+
"accuracy": 0.8195876288659794,
|
| 954 |
"count": 194
|
| 955 |
}
|
| 956 |
}
|
| 957 |
},
|
| 958 |
"add_C6": {
|
| 959 |
+
"full_accuracy": 0.5,
|
| 960 |
"n_examples": 100,
|
| 961 |
"per_subtask": {
|
| 962 |
"SC": {
|
|
|
|
| 964 |
"count": 100
|
| 965 |
},
|
| 966 |
"UC": {
|
| 967 |
+
"accuracy": 0.855191256830601,
|
| 968 |
"count": 366
|
| 969 |
},
|
| 970 |
"US": {
|
| 971 |
+
"accuracy": 0.8717948717948718,
|
| 972 |
"count": 234
|
| 973 |
}
|
| 974 |
}
|
| 975 |
},
|
| 976 |
"sub_M0": {
|
| 977 |
+
"full_accuracy": 0.88,
|
| 978 |
"n_examples": 100,
|
| 979 |
"per_subtask": {
|
| 980 |
"MD": {
|
| 981 |
+
"accuracy": 0.9800332778702163,
|
| 982 |
"count": 601
|
| 983 |
},
|
| 984 |
"ME": {
|
| 985 |
+
"accuracy": 1.0,
|
| 986 |
"count": 99
|
| 987 |
}
|
| 988 |
}
|
| 989 |
},
|
| 990 |
"sub_M1": {
|
| 991 |
+
"full_accuracy": 0.8,
|
| 992 |
"n_examples": 100,
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
+
"accuracy": 0.982078853046595,
|
| 996 |
"count": 279
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
+
"accuracy": 0.9793103448275862,
|
| 1000 |
"count": 145
|
| 1001 |
},
|
| 1002 |
"ME": {
|
|
|
|
| 1004 |
"count": 24
|
| 1005 |
},
|
| 1006 |
"UB": {
|
| 1007 |
+
"accuracy": 0.9444444444444444,
|
| 1008 |
"count": 252
|
| 1009 |
}
|
| 1010 |
}
|
| 1011 |
},
|
| 1012 |
"sub_M2": {
|
| 1013 |
+
"full_accuracy": 0.55,
|
| 1014 |
"n_examples": 100,
|
| 1015 |
"per_subtask": {
|
| 1016 |
"MD": {
|
| 1017 |
+
"accuracy": 0.9812206572769953,
|
| 1018 |
"count": 213
|
| 1019 |
},
|
| 1020 |
"MB": {
|
|
|
|
| 1022 |
"count": 113
|
| 1023 |
},
|
| 1024 |
"ME": {
|
| 1025 |
+
"accuracy": 0.9882352941176471,
|
| 1026 |
"count": 85
|
| 1027 |
},
|
| 1028 |
"UB": {
|
| 1029 |
+
"accuracy": 0.7624309392265194,
|
| 1030 |
"count": 181
|
| 1031 |
},
|
| 1032 |
"UD": {
|
| 1033 |
+
"accuracy": 0.9629629629629629,
|
| 1034 |
"count": 108
|
| 1035 |
}
|
| 1036 |
}
|
| 1037 |
},
|
| 1038 |
"sub_M3": {
|
| 1039 |
+
"full_accuracy": 0.17,
|
| 1040 |
"n_examples": 100,
|
| 1041 |
"per_subtask": {
|
| 1042 |
"MD": {
|
| 1043 |
+
"accuracy": 1.0,
|
| 1044 |
"count": 179
|
| 1045 |
},
|
| 1046 |
"MB": {
|
| 1047 |
+
"accuracy": 0.9902912621359223,
|
| 1048 |
"count": 103
|
| 1049 |
},
|
| 1050 |
"ME": {
|
|
|
|
| 1052 |
"count": 56
|
| 1053 |
},
|
| 1054 |
"UB": {
|
| 1055 |
+
"accuracy": 0.5637583892617449,
|
| 1056 |
"count": 149
|
| 1057 |
},
|
| 1058 |
"UD": {
|
| 1059 |
+
"accuracy": 0.7699530516431925,
|
| 1060 |
"count": 213
|
| 1061 |
}
|
| 1062 |
}
|
|
|
|
| 1070 |
"count": 200
|
| 1071 |
},
|
| 1072 |
"MB": {
|
| 1073 |
+
"accuracy": 1.0,
|
| 1074 |
"count": 100
|
| 1075 |
},
|
| 1076 |
"UB": {
|
| 1077 |
+
"accuracy": 0.39,
|
| 1078 |
"count": 100
|
| 1079 |
},
|
| 1080 |
"UD": {
|
| 1081 |
+
"accuracy": 0.38333333333333336,
|
| 1082 |
"count": 300
|
| 1083 |
}
|
| 1084 |
}
|
| 1085 |
},
|
| 1086 |
"sub_M5": {
|
| 1087 |
+
"full_accuracy": 0.04,
|
| 1088 |
"n_examples": 100,
|
| 1089 |
"per_subtask": {
|
| 1090 |
"MD": {
|
|
|
|
| 1100 |
"count": 100
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
+
"accuracy": 0.3475,
|
| 1104 |
"count": 400
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
},
|
| 1108 |
"sub_random": {
|
| 1109 |
+
"full_accuracy": 0.745,
|
| 1110 |
"n_examples": 200,
|
| 1111 |
"per_subtask": {
|
| 1112 |
"MD": {
|
| 1113 |
+
"accuracy": 0.98,
|
| 1114 |
"count": 600
|
| 1115 |
},
|
| 1116 |
"MB": {
|
| 1117 |
+
"accuracy": 0.9700374531835206,
|
| 1118 |
"count": 267
|
| 1119 |
},
|
| 1120 |
"ME": {
|
|
|
|
| 1122 |
"count": 53
|
| 1123 |
},
|
| 1124 |
"UB": {
|
| 1125 |
+
"accuracy": 0.9225512528473804,
|
| 1126 |
"count": 439
|
| 1127 |
},
|
| 1128 |
"UD": {
|
| 1129 |
+
"accuracy": 0.975609756097561,
|
| 1130 |
"count": 41
|
| 1131 |
}
|
| 1132 |
}
|
| 1133 |
},
|
| 1134 |
"sub_B3": {
|
| 1135 |
+
"full_accuracy": 0.35,
|
| 1136 |
"n_examples": 100,
|
| 1137 |
"per_subtask": {
|
| 1138 |
"MD": {
|
| 1139 |
+
"accuracy": 0.9933333333333333,
|
| 1140 |
"count": 300
|
| 1141 |
},
|
| 1142 |
"MB": {
|
| 1143 |
+
"accuracy": 0.98,
|
| 1144 |
"count": 100
|
| 1145 |
},
|
| 1146 |
"UB": {
|
| 1147 |
+
"accuracy": 0.6852791878172588,
|
| 1148 |
"count": 197
|
| 1149 |
},
|
| 1150 |
"UD": {
|
| 1151 |
+
"accuracy": 0.7184466019417476,
|
| 1152 |
"count": 103
|
| 1153 |
}
|
| 1154 |
}
|
| 1155 |
},
|
| 1156 |
"sub_B4": {
|
| 1157 |
+
"full_accuracy": 0.27,
|
| 1158 |
"n_examples": 100,
|
| 1159 |
"per_subtask": {
|
| 1160 |
"MD": {
|
|
|
|
| 1166 |
"count": 100
|
| 1167 |
},
|
| 1168 |
"UB": {
|
| 1169 |
+
"accuracy": 0.6923076923076923,
|
| 1170 |
"count": 247
|
| 1171 |
},
|
| 1172 |
"UD": {
|
| 1173 |
+
"accuracy": 0.6666666666666666,
|
| 1174 |
"count": 153
|
| 1175 |
}
|
| 1176 |
}
|
| 1177 |
},
|
| 1178 |
"sub_B5": {
|
| 1179 |
+
"full_accuracy": 0.25,
|
| 1180 |
"n_examples": 100,
|
| 1181 |
"per_subtask": {
|
| 1182 |
"MD": {
|
|
|
|
| 1188 |
"count": 100
|
| 1189 |
},
|
| 1190 |
"UB": {
|
| 1191 |
+
"accuracy": 0.7348993288590604,
|
| 1192 |
"count": 298
|
| 1193 |
},
|
| 1194 |
"UD": {
|
| 1195 |
+
"accuracy": 0.6683168316831684,
|
| 1196 |
"count": 202
|
| 1197 |
}
|
| 1198 |
}
|
| 1199 |
}
|
| 1200 |
},
|
| 1201 |
"summary": {
|
| 1202 |
+
"overall_accuracy": 0.49541666666666667,
|
| 1203 |
"total_examples": 2400,
|
| 1204 |
"n_splits": 22
|
| 1205 |
}
|
add_sub_baseline_25K_1L3H510d/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 634642298
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5b3d0a4f5926074c2ad67eaf23945b1b503b7915d0fbafb817b3c7222125cc7
|
| 3 |
size 634642298
|
add_sub_baseline_25K_1L3H510d/train_config.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"target_vocab_util": 0.8,
|
| 18 |
"min_abs_ppl": 0.0,
|
| 19 |
"zipf_alpha": 1.0,
|
| 20 |
-
"lr":
|
| 21 |
"emb_lr_mult": 1.0,
|
| 22 |
"weight_decay": 0.01,
|
| 23 |
"warmup_steps": 234,
|
|
@@ -69,16 +69,16 @@
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 158584246,
|
| 71 |
"run_name": "add_sub_baseline_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": "sft",
|
| 79 |
-
"wandb_run_id": "
|
| 80 |
-
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/
|
| 81 |
-
"final_accuracy": 0.
|
| 82 |
-
"sft_accuracy": 0.
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|
|
|
|
| 17 |
"target_vocab_util": 0.8,
|
| 18 |
"min_abs_ppl": 0.0,
|
| 19 |
"zipf_alpha": 1.0,
|
| 20 |
+
"lr": 8e-05,
|
| 21 |
"emb_lr_mult": 1.0,
|
| 22 |
"weight_decay": 0.01,
|
| 23 |
"warmup_steps": 234,
|
|
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 158584246,
|
| 71 |
"run_name": "add_sub_baseline_25K_1L3H510d",
|
| 72 |
+
"git_commit": "dc8dd776fb0c30a4c9073052dcc5e943e0fd80c6",
|
| 73 |
+
"timestamp": "2026-04-13T06:26:07.104526+00:00",
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
| 77 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
"trainer_version": "sft",
|
| 79 |
+
"wandb_run_id": "wpi2qkei",
|
| 80 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/wpi2qkei",
|
| 81 |
+
"final_accuracy": 0.49541666666666667,
|
| 82 |
+
"sft_accuracy": 0.49541666666666667,
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|