Upload add_sub_baseline_25K
Browse files
add_sub_baseline_25K/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 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
0.
|
| 176 |
-
0.
|
| 177 |
-
0.
|
| 178 |
-
0.
|
| 179 |
-
0.
|
| 180 |
-
0.
|
| 181 |
-
0.
|
| 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 |
-
|
| 330 |
-
|
| 331 |
-
|
| 332 |
-
|
| 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 |
-
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,
|
|
@@ -678,28 +678,28 @@
|
|
| 678 |
],
|
| 679 |
"eval_accuracy": [
|
| 680 |
0.0044444444444444444,
|
| 681 |
-
0.
|
| 682 |
-
0.
|
| 683 |
-
0.
|
| 684 |
-
0.
|
| 685 |
-
0.
|
| 686 |
-
0.
|
| 687 |
-
0.
|
| 688 |
-
0.6966666666666667,
|
| 689 |
-
0.7366666666666667,
|
| 690 |
-
0.75,
|
| 691 |
-
0.7633333333333333,
|
| 692 |
-
0.7722222222222223,
|
| 693 |
0.7922222222222223,
|
| 694 |
-
0.8388888888888889,
|
| 695 |
-
0.8188888888888889,
|
| 696 |
-
0.84,
|
| 697 |
-
0.8522222222222222,
|
| 698 |
0.8511111111111112,
|
| 699 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 700 |
]
|
| 701 |
},
|
| 702 |
-
"final_accuracy": 0.
|
| 703 |
"sft_eval": {
|
| 704 |
"config": {
|
| 705 |
"ops": "add_sub",
|
|
@@ -710,11 +710,11 @@
|
|
| 710 |
},
|
| 711 |
"splits": {
|
| 712 |
"add_S0": {
|
| 713 |
-
"full_accuracy":
|
| 714 |
"n_examples": 100,
|
| 715 |
"per_subtask": {
|
| 716 |
"SA": {
|
| 717 |
-
"accuracy":
|
| 718 |
"count": 605
|
| 719 |
},
|
| 720 |
"SS": {
|
|
@@ -724,11 +724,11 @@
|
|
| 724 |
}
|
| 725 |
},
|
| 726 |
"add_S1": {
|
| 727 |
-
"full_accuracy":
|
| 728 |
"n_examples": 100,
|
| 729 |
"per_subtask": {
|
| 730 |
"SA": {
|
| 731 |
-
"accuracy":
|
| 732 |
"count": 204
|
| 733 |
},
|
| 734 |
"SC": {
|
|
@@ -746,15 +746,15 @@
|
|
| 746 |
}
|
| 747 |
},
|
| 748 |
"add_S2": {
|
| 749 |
-
"full_accuracy":
|
| 750 |
"n_examples": 100,
|
| 751 |
"per_subtask": {
|
| 752 |
"SA": {
|
| 753 |
-
"accuracy":
|
| 754 |
"count": 163
|
| 755 |
},
|
| 756 |
"SC": {
|
| 757 |
-
"accuracy":
|
| 758 |
"count": 130
|
| 759 |
},
|
| 760 |
"SS": {
|
|
@@ -762,7 +762,7 @@
|
|
| 762 |
"count": 87
|
| 763 |
},
|
| 764 |
"UC": {
|
| 765 |
-
"accuracy":
|
| 766 |
"count": 203
|
| 767 |
},
|
| 768 |
"US": {
|
|
@@ -772,7 +772,7 @@
|
|
| 772 |
}
|
| 773 |
},
|
| 774 |
"add_S3": {
|
| 775 |
-
"full_accuracy": 0.
|
| 776 |
"n_examples": 100,
|
| 777 |
"per_subtask": {
|
| 778 |
"SA": {
|
|
@@ -788,17 +788,17 @@
|
|
| 788 |
"count": 49
|
| 789 |
},
|
| 790 |
"UC": {
|
| 791 |
-
"accuracy": 0.
|
| 792 |
"count": 186
|
| 793 |
},
|
| 794 |
"US": {
|
| 795 |
-
"accuracy":
|
| 796 |
"count": 223
|
| 797 |
}
|
| 798 |
}
|
| 799 |
},
|
| 800 |
"add_S4": {
|
| 801 |
-
"full_accuracy": 0.
|
| 802 |
"n_examples": 100,
|
| 803 |
"per_subtask": {
|
| 804 |
"SA": {
|
|
@@ -814,17 +814,17 @@
|
|
| 814 |
"count": 23
|
| 815 |
},
|
| 816 |
"UC": {
|
| 817 |
-
"accuracy": 0.
|
| 818 |
"count": 160
|
| 819 |
},
|
| 820 |
"US": {
|
| 821 |
-
"accuracy":
|
| 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": {
|
|
@@ -854,25 +854,25 @@
|
|
| 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":
|
| 868 |
"n_examples": 200,
|
| 869 |
"per_subtask": {
|
| 870 |
"SA": {
|
| 871 |
-
"accuracy":
|
| 872 |
"count": 447
|
| 873 |
},
|
| 874 |
"SC": {
|
| 875 |
-
"accuracy":
|
| 876 |
"count": 320
|
| 877 |
},
|
| 878 |
"SS": {
|
|
@@ -880,7 +880,7 @@
|
|
| 880 |
"count": 56
|
| 881 |
},
|
| 882 |
"UC": {
|
| 883 |
-
"accuracy":
|
| 884 |
"count": 529
|
| 885 |
},
|
| 886 |
"US": {
|
|
@@ -890,7 +890,7 @@
|
|
| 890 |
}
|
| 891 |
},
|
| 892 |
"add_C3": {
|
| 893 |
-
"full_accuracy":
|
| 894 |
"n_examples": 100,
|
| 895 |
"per_subtask": {
|
| 896 |
"SA": {
|
|
@@ -902,7 +902,7 @@
|
|
| 902 |
"count": 100
|
| 903 |
},
|
| 904 |
"UC": {
|
| 905 |
-
"accuracy":
|
| 906 |
"count": 193
|
| 907 |
},
|
| 908 |
"US": {
|
|
@@ -912,7 +912,7 @@
|
|
| 912 |
}
|
| 913 |
},
|
| 914 |
"add_C4": {
|
| 915 |
-
"full_accuracy": 0.
|
| 916 |
"n_examples": 100,
|
| 917 |
"per_subtask": {
|
| 918 |
"SA": {
|
|
@@ -924,7 +924,7 @@
|
|
| 924 |
"count": 100
|
| 925 |
},
|
| 926 |
"UC": {
|
| 927 |
-
"accuracy": 0.
|
| 928 |
"count": 256
|
| 929 |
},
|
| 930 |
"US": {
|
|
@@ -934,7 +934,7 @@
|
|
| 934 |
}
|
| 935 |
},
|
| 936 |
"add_C5": {
|
| 937 |
-
"full_accuracy": 0.
|
| 938 |
"n_examples": 100,
|
| 939 |
"per_subtask": {
|
| 940 |
"SA": {
|
|
@@ -946,17 +946,17 @@
|
|
| 946 |
"count": 100
|
| 947 |
},
|
| 948 |
"UC": {
|
| 949 |
-
"accuracy": 0.
|
| 950 |
"count": 306
|
| 951 |
},
|
| 952 |
"US": {
|
| 953 |
-
"accuracy":
|
| 954 |
"count": 194
|
| 955 |
}
|
| 956 |
}
|
| 957 |
},
|
| 958 |
"add_C6": {
|
| 959 |
-
"full_accuracy":
|
| 960 |
"n_examples": 100,
|
| 961 |
"per_subtask": {
|
| 962 |
"SC": {
|
|
@@ -964,21 +964,21 @@
|
|
| 964 |
"count": 100
|
| 965 |
},
|
| 966 |
"UC": {
|
| 967 |
-
"accuracy":
|
| 968 |
"count": 366
|
| 969 |
},
|
| 970 |
"US": {
|
| 971 |
-
"accuracy":
|
| 972 |
"count": 234
|
| 973 |
}
|
| 974 |
}
|
| 975 |
},
|
| 976 |
"sub_M0": {
|
| 977 |
-
"full_accuracy":
|
| 978 |
"n_examples": 100,
|
| 979 |
"per_subtask": {
|
| 980 |
"MD": {
|
| 981 |
-
"accuracy":
|
| 982 |
"count": 601
|
| 983 |
},
|
| 984 |
"ME": {
|
|
@@ -988,15 +988,15 @@
|
|
| 988 |
}
|
| 989 |
},
|
| 990 |
"sub_M1": {
|
| 991 |
-
"full_accuracy":
|
| 992 |
"n_examples": 100,
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
-
"accuracy":
|
| 996 |
"count": 279
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
-
"accuracy":
|
| 1000 |
"count": 145
|
| 1001 |
},
|
| 1002 |
"ME": {
|
|
@@ -1010,15 +1010,15 @@
|
|
| 1010 |
}
|
| 1011 |
},
|
| 1012 |
"sub_M2": {
|
| 1013 |
-
"full_accuracy":
|
| 1014 |
"n_examples": 100,
|
| 1015 |
"per_subtask": {
|
| 1016 |
"MD": {
|
| 1017 |
-
"accuracy":
|
| 1018 |
"count": 213
|
| 1019 |
},
|
| 1020 |
"MB": {
|
| 1021 |
-
"accuracy":
|
| 1022 |
"count": 113
|
| 1023 |
},
|
| 1024 |
"ME": {
|
|
@@ -1026,7 +1026,7 @@
|
|
| 1026 |
"count": 85
|
| 1027 |
},
|
| 1028 |
"UB": {
|
| 1029 |
-
"accuracy":
|
| 1030 |
"count": 181
|
| 1031 |
},
|
| 1032 |
"UD": {
|
|
@@ -1036,7 +1036,7 @@
|
|
| 1036 |
}
|
| 1037 |
},
|
| 1038 |
"sub_M3": {
|
| 1039 |
-
"full_accuracy":
|
| 1040 |
"n_examples": 100,
|
| 1041 |
"per_subtask": {
|
| 1042 |
"MD": {
|
|
@@ -1052,7 +1052,7 @@
|
|
| 1052 |
"count": 56
|
| 1053 |
},
|
| 1054 |
"UB": {
|
| 1055 |
-
"accuracy":
|
| 1056 |
"count": 149
|
| 1057 |
},
|
| 1058 |
"UD": {
|
|
@@ -1062,7 +1062,7 @@
|
|
| 1062 |
}
|
| 1063 |
},
|
| 1064 |
"sub_M4": {
|
| 1065 |
-
"full_accuracy": 0.
|
| 1066 |
"n_examples": 100,
|
| 1067 |
"per_subtask": {
|
| 1068 |
"MD": {
|
|
@@ -1074,17 +1074,17 @@
|
|
| 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": {
|
|
@@ -1096,25 +1096,25 @@
|
|
| 1096 |
"count": 100
|
| 1097 |
},
|
| 1098 |
"UB": {
|
| 1099 |
-
"accuracy": 0.
|
| 1100 |
"count": 100
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
-
"accuracy": 0.
|
| 1104 |
"count": 400
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
},
|
| 1108 |
"sub_random": {
|
| 1109 |
-
"full_accuracy":
|
| 1110 |
"n_examples": 200,
|
| 1111 |
"per_subtask": {
|
| 1112 |
"MD": {
|
| 1113 |
-
"accuracy":
|
| 1114 |
"count": 600
|
| 1115 |
},
|
| 1116 |
"MB": {
|
| 1117 |
-
"accuracy":
|
| 1118 |
"count": 267
|
| 1119 |
},
|
| 1120 |
"ME": {
|
|
@@ -1122,7 +1122,7 @@
|
|
| 1122 |
"count": 53
|
| 1123 |
},
|
| 1124 |
"UB": {
|
| 1125 |
-
"accuracy":
|
| 1126 |
"count": 439
|
| 1127 |
},
|
| 1128 |
"UD": {
|
|
@@ -1132,11 +1132,11 @@
|
|
| 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": {
|
|
@@ -1144,7 +1144,7 @@
|
|
| 1144 |
"count": 100
|
| 1145 |
},
|
| 1146 |
"UB": {
|
| 1147 |
-
"accuracy":
|
| 1148 |
"count": 197
|
| 1149 |
},
|
| 1150 |
"UD": {
|
|
@@ -1154,11 +1154,11 @@
|
|
| 1154 |
}
|
| 1155 |
},
|
| 1156 |
"sub_B4": {
|
| 1157 |
-
"full_accuracy": 0.
|
| 1158 |
"n_examples": 100,
|
| 1159 |
"per_subtask": {
|
| 1160 |
"MD": {
|
| 1161 |
-
"accuracy":
|
| 1162 |
"count": 200
|
| 1163 |
},
|
| 1164 |
"MB": {
|
|
@@ -1166,17 +1166,17 @@
|
|
| 1166 |
"count": 100
|
| 1167 |
},
|
| 1168 |
"UB": {
|
| 1169 |
-
"accuracy": 0.
|
| 1170 |
"count": 247
|
| 1171 |
},
|
| 1172 |
"UD": {
|
| 1173 |
-
"accuracy":
|
| 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 |
+
8.176465034484863,
|
| 163 |
+
6.147647380828857,
|
| 164 |
+
4.317177772521973,
|
| 165 |
+
2.2636711597442627,
|
| 166 |
+
1.9471255540847778,
|
| 167 |
+
1.854894995689392,
|
| 168 |
+
1.7520498037338257,
|
| 169 |
+
1.734231948852539,
|
| 170 |
+
1.5133311748504639,
|
| 171 |
+
0.8570901155471802,
|
| 172 |
+
0.5889905095100403,
|
| 173 |
+
0.4950922429561615,
|
| 174 |
+
0.3594833016395569,
|
| 175 |
+
0.2747909128665924,
|
| 176 |
+
0.2981800138950348,
|
| 177 |
+
0.24328947067260742,
|
| 178 |
+
0.23415543138980865,
|
| 179 |
+
0.17787854373455048,
|
| 180 |
+
0.15139569342136383,
|
| 181 |
+
0.1316671222448349,
|
| 182 |
+
0.11477090418338776,
|
| 183 |
+
0.18589679896831512,
|
| 184 |
+
0.13625285029411316,
|
| 185 |
+
0.17548833787441254,
|
| 186 |
+
0.15588627755641937,
|
| 187 |
+
0.11858738958835602,
|
| 188 |
+
0.12255451828241348,
|
| 189 |
+
0.0896950513124466,
|
| 190 |
+
0.13146252930164337,
|
| 191 |
+
0.11455433070659637,
|
| 192 |
+
0.1151663064956665,
|
| 193 |
+
0.06363785266876221,
|
| 194 |
+
0.14567652344703674,
|
| 195 |
+
0.0746074840426445,
|
| 196 |
+
0.12438829988241196,
|
| 197 |
+
0.07398975640535355,
|
| 198 |
+
0.09149198234081268,
|
| 199 |
+
0.09169436991214752,
|
| 200 |
+
0.08420047909021378,
|
| 201 |
+
0.0836501345038414,
|
| 202 |
+
0.0648670420050621,
|
| 203 |
+
0.049085583537817,
|
| 204 |
+
0.05017789825797081,
|
| 205 |
+
0.06522161513566971,
|
| 206 |
+
0.06036243587732315,
|
| 207 |
+
0.04033808037638664,
|
| 208 |
+
0.05645652487874031,
|
| 209 |
+
0.034583259373903275,
|
| 210 |
+
0.06515158712863922,
|
| 211 |
+
0.03591739013791084,
|
| 212 |
+
0.061068642884492874,
|
| 213 |
+
0.09913851320743561,
|
| 214 |
+
0.06813834607601166,
|
| 215 |
+
0.04658734053373337,
|
| 216 |
+
0.1296006441116333,
|
| 217 |
+
0.030722280964255333,
|
| 218 |
+
0.045777130872011185,
|
| 219 |
+
0.039223652333021164,
|
| 220 |
+
0.046433109790086746,
|
| 221 |
+
0.038826730102300644,
|
| 222 |
+
0.044974811375141144,
|
| 223 |
+
0.0360710583627224,
|
| 224 |
+
0.03967965766787529,
|
| 225 |
+
0.03325542435050011,
|
| 226 |
+
0.02867959998548031,
|
| 227 |
+
0.04904448240995407,
|
| 228 |
+
0.033731549978256226,
|
| 229 |
+
0.042733609676361084,
|
| 230 |
+
0.03133813291788101,
|
| 231 |
+
0.024248523637652397,
|
| 232 |
+
0.04543988034129143,
|
| 233 |
+
0.017340853810310364,
|
| 234 |
+
0.015571562573313713,
|
| 235 |
+
0.026198627427220345,
|
| 236 |
+
0.01237435918301344,
|
| 237 |
+
0.050374116748571396,
|
| 238 |
+
0.026407893747091293,
|
| 239 |
+
0.027872929349541664,
|
| 240 |
+
0.012572596780955791,
|
| 241 |
+
0.032835423946380615,
|
| 242 |
+
0.03447069972753525,
|
| 243 |
+
0.027926044538617134,
|
| 244 |
+
0.024645937606692314,
|
| 245 |
+
0.0438305139541626,
|
| 246 |
+
0.03098066709935665,
|
| 247 |
+
0.028938667848706245,
|
| 248 |
+
0.019119232892990112,
|
| 249 |
+
0.041621122509241104,
|
| 250 |
+
0.0408143475651741,
|
| 251 |
+
0.019923286512494087,
|
| 252 |
+
0.03286880999803543,
|
| 253 |
+
0.049878351390361786,
|
| 254 |
+
0.01593688689172268,
|
| 255 |
+
0.028832128271460533,
|
| 256 |
+
0.03344333916902542,
|
| 257 |
+
0.01330149918794632,
|
| 258 |
+
0.011513492092490196,
|
| 259 |
+
0.018006816506385803,
|
| 260 |
+
0.010299280285835266,
|
| 261 |
+
0.023564040660858154,
|
| 262 |
+
0.019022012129426003,
|
| 263 |
+
0.02632061578333378,
|
| 264 |
+
0.0068031614646315575,
|
| 265 |
+
0.020888177677989006,
|
| 266 |
+
0.0216990914195776,
|
| 267 |
+
0.011892527341842651,
|
| 268 |
+
0.027240386232733727,
|
| 269 |
+
0.012803243473172188,
|
| 270 |
+
0.018175678327679634,
|
| 271 |
+
0.015969112515449524,
|
| 272 |
+
0.014878385700285435,
|
| 273 |
+
0.012554225511848927,
|
| 274 |
+
0.016249483451247215,
|
| 275 |
+
0.008588625118136406,
|
| 276 |
+
0.0071478309109807014,
|
| 277 |
+
0.015623864717781544,
|
| 278 |
+
0.0068113231100142,
|
| 279 |
+
0.01285618357360363,
|
| 280 |
+
0.0049651567824184895,
|
| 281 |
+
0.0020557695534080267,
|
| 282 |
+
0.009064031764864922,
|
| 283 |
+
0.00883619673550129,
|
| 284 |
+
0.0074000284075737,
|
| 285 |
+
0.017076730728149414,
|
| 286 |
+
0.028946170583367348,
|
| 287 |
+
0.010714277625083923,
|
| 288 |
+
0.007734171114861965,
|
| 289 |
+
0.009620459750294685,
|
| 290 |
+
0.001654217834584415,
|
| 291 |
+
0.001388624426908791,
|
| 292 |
+
0.0022322500590234995,
|
| 293 |
+
0.004631389398127794,
|
| 294 |
+
0.003576897317543626,
|
| 295 |
+
0.014710391871631145,
|
| 296 |
+
0.009100036695599556,
|
| 297 |
+
0.007004507817327976,
|
| 298 |
+
0.003731115022674203,
|
| 299 |
+
0.0012912886450067163,
|
| 300 |
+
0.005086787976324558,
|
| 301 |
+
0.002756895497441292,
|
| 302 |
+
0.003515108721330762,
|
| 303 |
+
0.004262362606823444,
|
| 304 |
+
0.000853787234518677,
|
| 305 |
+
0.0030297988560050726,
|
| 306 |
+
0.00271863816305995,
|
| 307 |
+
0.0032161420676857233,
|
| 308 |
+
0.009415960870683193,
|
| 309 |
+
0.0025729541666805744,
|
| 310 |
+
0.007850371301174164,
|
| 311 |
+
0.005563906393945217,
|
| 312 |
+
0.005385746713727713,
|
| 313 |
+
0.004481953103095293,
|
| 314 |
+
0.010044674389064312,
|
| 315 |
+
0.001978748943656683,
|
| 316 |
+
0.015501720830798149,
|
| 317 |
+
0.004191714338958263
|
| 318 |
],
|
| 319 |
"base_loss": [
|
| 320 |
+
8.176465034484863,
|
| 321 |
+
6.147647380828857,
|
| 322 |
+
4.317177772521973,
|
| 323 |
+
2.2636711597442627,
|
| 324 |
+
1.9471255540847778,
|
| 325 |
+
1.854894995689392,
|
| 326 |
+
1.7520498037338257,
|
| 327 |
+
1.734231948852539,
|
| 328 |
+
1.5133311748504639,
|
| 329 |
+
0.8570901155471802,
|
| 330 |
+
0.5889905095100403,
|
| 331 |
+
0.4950922429561615,
|
| 332 |
+
0.3594833016395569,
|
| 333 |
+
0.2747909128665924,
|
| 334 |
+
0.2981800138950348,
|
| 335 |
+
0.24328947067260742,
|
| 336 |
+
0.23415543138980865,
|
| 337 |
+
0.17787854373455048,
|
| 338 |
+
0.15139569342136383,
|
| 339 |
+
0.1316671222448349,
|
| 340 |
+
0.11477090418338776,
|
| 341 |
+
0.18589679896831512,
|
| 342 |
+
0.13625285029411316,
|
| 343 |
+
0.17548833787441254,
|
| 344 |
+
0.15588627755641937,
|
| 345 |
+
0.11858738958835602,
|
| 346 |
+
0.12255451828241348,
|
| 347 |
+
0.0896950513124466,
|
| 348 |
+
0.13146252930164337,
|
| 349 |
+
0.11455433070659637,
|
| 350 |
+
0.1151663064956665,
|
| 351 |
+
0.06363785266876221,
|
| 352 |
+
0.14567652344703674,
|
| 353 |
+
0.0746074840426445,
|
| 354 |
+
0.12438829988241196,
|
| 355 |
+
0.07398975640535355,
|
| 356 |
+
0.09149198234081268,
|
| 357 |
+
0.09169436991214752,
|
| 358 |
+
0.08420047909021378,
|
| 359 |
+
0.0836501345038414,
|
| 360 |
+
0.0648670420050621,
|
| 361 |
+
0.049085583537817,
|
| 362 |
+
0.05017789825797081,
|
| 363 |
+
0.06522161513566971,
|
| 364 |
+
0.06036243587732315,
|
| 365 |
+
0.04033808037638664,
|
| 366 |
+
0.05645652487874031,
|
| 367 |
+
0.034583259373903275,
|
| 368 |
+
0.06515158712863922,
|
| 369 |
+
0.03591739013791084,
|
| 370 |
+
0.061068642884492874,
|
| 371 |
+
0.09913851320743561,
|
| 372 |
+
0.06813834607601166,
|
| 373 |
+
0.04658734053373337,
|
| 374 |
+
0.1296006441116333,
|
| 375 |
+
0.030722280964255333,
|
| 376 |
+
0.045777130872011185,
|
| 377 |
+
0.039223652333021164,
|
| 378 |
+
0.046433109790086746,
|
| 379 |
+
0.038826730102300644,
|
| 380 |
+
0.044974811375141144,
|
| 381 |
+
0.0360710583627224,
|
| 382 |
+
0.03967965766787529,
|
| 383 |
+
0.03325542435050011,
|
| 384 |
+
0.02867959998548031,
|
| 385 |
+
0.04904448240995407,
|
| 386 |
+
0.033731549978256226,
|
| 387 |
+
0.042733609676361084,
|
| 388 |
+
0.03133813291788101,
|
| 389 |
+
0.024248523637652397,
|
| 390 |
+
0.04543988034129143,
|
| 391 |
+
0.017340853810310364,
|
| 392 |
+
0.015571562573313713,
|
| 393 |
+
0.026198627427220345,
|
| 394 |
+
0.01237435918301344,
|
| 395 |
+
0.050374116748571396,
|
| 396 |
+
0.026407893747091293,
|
| 397 |
+
0.027872929349541664,
|
| 398 |
+
0.012572596780955791,
|
| 399 |
+
0.032835423946380615,
|
| 400 |
+
0.03447069972753525,
|
| 401 |
+
0.027926044538617134,
|
| 402 |
+
0.024645937606692314,
|
| 403 |
+
0.0438305139541626,
|
| 404 |
+
0.03098066709935665,
|
| 405 |
+
0.028938667848706245,
|
| 406 |
+
0.019119232892990112,
|
| 407 |
+
0.041621122509241104,
|
| 408 |
+
0.0408143475651741,
|
| 409 |
+
0.019923286512494087,
|
| 410 |
+
0.03286880999803543,
|
| 411 |
+
0.049878351390361786,
|
| 412 |
+
0.01593688689172268,
|
| 413 |
+
0.028832128271460533,
|
| 414 |
+
0.03344333916902542,
|
| 415 |
+
0.01330149918794632,
|
| 416 |
+
0.011513492092490196,
|
| 417 |
+
0.018006816506385803,
|
| 418 |
+
0.010299280285835266,
|
| 419 |
+
0.023564040660858154,
|
| 420 |
+
0.019022012129426003,
|
| 421 |
+
0.02632061578333378,
|
| 422 |
+
0.0068031614646315575,
|
| 423 |
+
0.020888177677989006,
|
| 424 |
+
0.0216990914195776,
|
| 425 |
+
0.011892527341842651,
|
| 426 |
+
0.027240386232733727,
|
| 427 |
+
0.012803243473172188,
|
| 428 |
+
0.018175678327679634,
|
| 429 |
+
0.015969112515449524,
|
| 430 |
+
0.014878385700285435,
|
| 431 |
+
0.012554225511848927,
|
| 432 |
+
0.016249483451247215,
|
| 433 |
+
0.008588625118136406,
|
| 434 |
+
0.0071478309109807014,
|
| 435 |
+
0.015623864717781544,
|
| 436 |
+
0.0068113231100142,
|
| 437 |
+
0.01285618357360363,
|
| 438 |
+
0.0049651567824184895,
|
| 439 |
+
0.0020557695534080267,
|
| 440 |
+
0.009064031764864922,
|
| 441 |
+
0.00883619673550129,
|
| 442 |
+
0.0074000284075737,
|
| 443 |
+
0.017076730728149414,
|
| 444 |
+
0.028946170583367348,
|
| 445 |
+
0.010714277625083923,
|
| 446 |
+
0.007734171114861965,
|
| 447 |
+
0.009620459750294685,
|
| 448 |
+
0.001654217834584415,
|
| 449 |
+
0.001388624426908791,
|
| 450 |
+
0.0022322500590234995,
|
| 451 |
+
0.004631389398127794,
|
| 452 |
+
0.003576897317543626,
|
| 453 |
+
0.014710391871631145,
|
| 454 |
+
0.009100036695599556,
|
| 455 |
+
0.007004507817327976,
|
| 456 |
+
0.003731115022674203,
|
| 457 |
+
0.0012912886450067163,
|
| 458 |
+
0.005086787976324558,
|
| 459 |
+
0.002756895497441292,
|
| 460 |
+
0.003515108721330762,
|
| 461 |
+
0.004262362606823444,
|
| 462 |
+
0.000853787234518677,
|
| 463 |
+
0.0030297988560050726,
|
| 464 |
+
0.00271863816305995,
|
| 465 |
+
0.0032161420676857233,
|
| 466 |
+
0.009415960870683193,
|
| 467 |
+
0.0025729541666805744,
|
| 468 |
+
0.007850371301174164,
|
| 469 |
+
0.005563906393945217,
|
| 470 |
+
0.005385746713727713,
|
| 471 |
+
0.004481953103095293,
|
| 472 |
+
0.010044674389064312,
|
| 473 |
+
0.001978748943656683,
|
| 474 |
+
0.015501720830798149,
|
| 475 |
+
0.004191714338958263
|
| 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,
|
|
|
|
| 678 |
],
|
| 679 |
"eval_accuracy": [
|
| 680 |
0.0044444444444444444,
|
| 681 |
+
0.57,
|
| 682 |
+
0.67,
|
| 683 |
+
0.7711111111111111,
|
| 684 |
+
0.7088888888888889,
|
| 685 |
+
0.7577777777777778,
|
| 686 |
+
0.7988888888888889,
|
| 687 |
+
0.7866666666666666,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 688 |
0.7922222222222223,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 689 |
0.8511111111111112,
|
| 690 |
+
0.8588888888888889,
|
| 691 |
+
0.8533333333333334,
|
| 692 |
+
0.8755555555555555,
|
| 693 |
+
0.9044444444444445,
|
| 694 |
+
0.9244444444444444,
|
| 695 |
+
0.9144444444444444,
|
| 696 |
+
0.9288888888888889,
|
| 697 |
+
0.9311111111111111,
|
| 698 |
+
0.9388888888888889,
|
| 699 |
+
0.9444444444444444
|
| 700 |
]
|
| 701 |
},
|
| 702 |
+
"final_accuracy": 0.91625,
|
| 703 |
"sft_eval": {
|
| 704 |
"config": {
|
| 705 |
"ops": "add_sub",
|
|
|
|
| 710 |
},
|
| 711 |
"splits": {
|
| 712 |
"add_S0": {
|
| 713 |
+
"full_accuracy": 1.0,
|
| 714 |
"n_examples": 100,
|
| 715 |
"per_subtask": {
|
| 716 |
"SA": {
|
| 717 |
+
"accuracy": 1.0,
|
| 718 |
"count": 605
|
| 719 |
},
|
| 720 |
"SS": {
|
|
|
|
| 724 |
}
|
| 725 |
},
|
| 726 |
"add_S1": {
|
| 727 |
+
"full_accuracy": 0.99,
|
| 728 |
"n_examples": 100,
|
| 729 |
"per_subtask": {
|
| 730 |
"SA": {
|
| 731 |
+
"accuracy": 0.9950980392156863,
|
| 732 |
"count": 204
|
| 733 |
},
|
| 734 |
"SC": {
|
|
|
|
| 746 |
}
|
| 747 |
},
|
| 748 |
"add_S2": {
|
| 749 |
+
"full_accuracy": 1.0,
|
| 750 |
"n_examples": 100,
|
| 751 |
"per_subtask": {
|
| 752 |
"SA": {
|
| 753 |
+
"accuracy": 1.0,
|
| 754 |
"count": 163
|
| 755 |
},
|
| 756 |
"SC": {
|
| 757 |
+
"accuracy": 1.0,
|
| 758 |
"count": 130
|
| 759 |
},
|
| 760 |
"SS": {
|
|
|
|
| 762 |
"count": 87
|
| 763 |
},
|
| 764 |
"UC": {
|
| 765 |
+
"accuracy": 1.0,
|
| 766 |
"count": 203
|
| 767 |
},
|
| 768 |
"US": {
|
|
|
|
| 772 |
}
|
| 773 |
},
|
| 774 |
"add_S3": {
|
| 775 |
+
"full_accuracy": 0.98,
|
| 776 |
"n_examples": 100,
|
| 777 |
"per_subtask": {
|
| 778 |
"SA": {
|
|
|
|
| 788 |
"count": 49
|
| 789 |
},
|
| 790 |
"UC": {
|
| 791 |
+
"accuracy": 0.989247311827957,
|
| 792 |
"count": 186
|
| 793 |
},
|
| 794 |
"US": {
|
| 795 |
+
"accuracy": 1.0,
|
| 796 |
"count": 223
|
| 797 |
}
|
| 798 |
}
|
| 799 |
},
|
| 800 |
"add_S4": {
|
| 801 |
+
"full_accuracy": 0.88,
|
| 802 |
"n_examples": 100,
|
| 803 |
"per_subtask": {
|
| 804 |
"SA": {
|
|
|
|
| 814 |
"count": 23
|
| 815 |
},
|
| 816 |
"UC": {
|
| 817 |
+
"accuracy": 0.925,
|
| 818 |
"count": 160
|
| 819 |
},
|
| 820 |
"US": {
|
| 821 |
+
"accuracy": 1.0,
|
| 822 |
"count": 307
|
| 823 |
}
|
| 824 |
}
|
| 825 |
},
|
| 826 |
"add_S5": {
|
| 827 |
+
"full_accuracy": 0.54,
|
| 828 |
"n_examples": 100,
|
| 829 |
"per_subtask": {
|
| 830 |
"SA": {
|
|
|
|
| 836 |
"count": 100
|
| 837 |
},
|
| 838 |
"UC": {
|
| 839 |
+
"accuracy": 0.66,
|
| 840 |
"count": 100
|
| 841 |
},
|
| 842 |
"US": {
|
| 843 |
+
"accuracy": 0.89,
|
| 844 |
"count": 400
|
| 845 |
}
|
| 846 |
}
|
| 847 |
},
|
| 848 |
"add_S6": {
|
| 849 |
+
"full_accuracy": 0.98,
|
| 850 |
"n_examples": 100,
|
| 851 |
"per_subtask": {
|
| 852 |
"SC": {
|
|
|
|
| 854 |
"count": 100
|
| 855 |
},
|
| 856 |
"UC": {
|
| 857 |
+
"accuracy": 0.99,
|
| 858 |
"count": 100
|
| 859 |
},
|
| 860 |
"US": {
|
| 861 |
+
"accuracy": 0.994,
|
| 862 |
"count": 500
|
| 863 |
}
|
| 864 |
}
|
| 865 |
},
|
| 866 |
"add_random": {
|
| 867 |
+
"full_accuracy": 1.0,
|
| 868 |
"n_examples": 200,
|
| 869 |
"per_subtask": {
|
| 870 |
"SA": {
|
| 871 |
+
"accuracy": 1.0,
|
| 872 |
"count": 447
|
| 873 |
},
|
| 874 |
"SC": {
|
| 875 |
+
"accuracy": 1.0,
|
| 876 |
"count": 320
|
| 877 |
},
|
| 878 |
"SS": {
|
|
|
|
| 880 |
"count": 56
|
| 881 |
},
|
| 882 |
"UC": {
|
| 883 |
+
"accuracy": 1.0,
|
| 884 |
"count": 529
|
| 885 |
},
|
| 886 |
"US": {
|
|
|
|
| 890 |
}
|
| 891 |
},
|
| 892 |
"add_C3": {
|
| 893 |
+
"full_accuracy": 1.0,
|
| 894 |
"n_examples": 100,
|
| 895 |
"per_subtask": {
|
| 896 |
"SA": {
|
|
|
|
| 902 |
"count": 100
|
| 903 |
},
|
| 904 |
"UC": {
|
| 905 |
+
"accuracy": 1.0,
|
| 906 |
"count": 193
|
| 907 |
},
|
| 908 |
"US": {
|
|
|
|
| 912 |
}
|
| 913 |
},
|
| 914 |
"add_C4": {
|
| 915 |
+
"full_accuracy": 0.95,
|
| 916 |
"n_examples": 100,
|
| 917 |
"per_subtask": {
|
| 918 |
"SA": {
|
|
|
|
| 924 |
"count": 100
|
| 925 |
},
|
| 926 |
"UC": {
|
| 927 |
+
"accuracy": 0.98046875,
|
| 928 |
"count": 256
|
| 929 |
},
|
| 930 |
"US": {
|
|
|
|
| 934 |
}
|
| 935 |
},
|
| 936 |
"add_C5": {
|
| 937 |
+
"full_accuracy": 0.91,
|
| 938 |
"n_examples": 100,
|
| 939 |
"per_subtask": {
|
| 940 |
"SA": {
|
|
|
|
| 946 |
"count": 100
|
| 947 |
},
|
| 948 |
"UC": {
|
| 949 |
+
"accuracy": 0.9738562091503268,
|
| 950 |
"count": 306
|
| 951 |
},
|
| 952 |
"US": {
|
| 953 |
+
"accuracy": 0.9896907216494846,
|
| 954 |
"count": 194
|
| 955 |
}
|
| 956 |
}
|
| 957 |
},
|
| 958 |
"add_C6": {
|
| 959 |
+
"full_accuracy": 1.0,
|
| 960 |
"n_examples": 100,
|
| 961 |
"per_subtask": {
|
| 962 |
"SC": {
|
|
|
|
| 964 |
"count": 100
|
| 965 |
},
|
| 966 |
"UC": {
|
| 967 |
+
"accuracy": 1.0,
|
| 968 |
"count": 366
|
| 969 |
},
|
| 970 |
"US": {
|
| 971 |
+
"accuracy": 1.0,
|
| 972 |
"count": 234
|
| 973 |
}
|
| 974 |
}
|
| 975 |
},
|
| 976 |
"sub_M0": {
|
| 977 |
+
"full_accuracy": 1.0,
|
| 978 |
"n_examples": 100,
|
| 979 |
"per_subtask": {
|
| 980 |
"MD": {
|
| 981 |
+
"accuracy": 1.0,
|
| 982 |
"count": 601
|
| 983 |
},
|
| 984 |
"ME": {
|
|
|
|
| 988 |
}
|
| 989 |
},
|
| 990 |
"sub_M1": {
|
| 991 |
+
"full_accuracy": 1.0,
|
| 992 |
"n_examples": 100,
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
+
"accuracy": 1.0,
|
| 996 |
"count": 279
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
+
"accuracy": 1.0,
|
| 1000 |
"count": 145
|
| 1001 |
},
|
| 1002 |
"ME": {
|
|
|
|
| 1010 |
}
|
| 1011 |
},
|
| 1012 |
"sub_M2": {
|
| 1013 |
+
"full_accuracy": 1.0,
|
| 1014 |
"n_examples": 100,
|
| 1015 |
"per_subtask": {
|
| 1016 |
"MD": {
|
| 1017 |
+
"accuracy": 1.0,
|
| 1018 |
"count": 213
|
| 1019 |
},
|
| 1020 |
"MB": {
|
| 1021 |
+
"accuracy": 1.0,
|
| 1022 |
"count": 113
|
| 1023 |
},
|
| 1024 |
"ME": {
|
|
|
|
| 1026 |
"count": 85
|
| 1027 |
},
|
| 1028 |
"UB": {
|
| 1029 |
+
"accuracy": 1.0,
|
| 1030 |
"count": 181
|
| 1031 |
},
|
| 1032 |
"UD": {
|
|
|
|
| 1036 |
}
|
| 1037 |
},
|
| 1038 |
"sub_M3": {
|
| 1039 |
+
"full_accuracy": 1.0,
|
| 1040 |
"n_examples": 100,
|
| 1041 |
"per_subtask": {
|
| 1042 |
"MD": {
|
|
|
|
| 1052 |
"count": 56
|
| 1053 |
},
|
| 1054 |
"UB": {
|
| 1055 |
+
"accuracy": 1.0,
|
| 1056 |
"count": 149
|
| 1057 |
},
|
| 1058 |
"UD": {
|
|
|
|
| 1062 |
}
|
| 1063 |
},
|
| 1064 |
"sub_M4": {
|
| 1065 |
+
"full_accuracy": 0.56,
|
| 1066 |
"n_examples": 100,
|
| 1067 |
"per_subtask": {
|
| 1068 |
"MD": {
|
|
|
|
| 1074 |
"count": 100
|
| 1075 |
},
|
| 1076 |
"UB": {
|
| 1077 |
+
"accuracy": 0.57,
|
| 1078 |
"count": 100
|
| 1079 |
},
|
| 1080 |
"UD": {
|
| 1081 |
+
"accuracy": 0.9933333333333333,
|
| 1082 |
"count": 300
|
| 1083 |
}
|
| 1084 |
}
|
| 1085 |
},
|
| 1086 |
"sub_M5": {
|
| 1087 |
+
"full_accuracy": 0.34,
|
| 1088 |
"n_examples": 100,
|
| 1089 |
"per_subtask": {
|
| 1090 |
"MD": {
|
|
|
|
| 1096 |
"count": 100
|
| 1097 |
},
|
| 1098 |
"UB": {
|
| 1099 |
+
"accuracy": 0.57,
|
| 1100 |
"count": 100
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
+
"accuracy": 0.87,
|
| 1104 |
"count": 400
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
},
|
| 1108 |
"sub_random": {
|
| 1109 |
+
"full_accuracy": 1.0,
|
| 1110 |
"n_examples": 200,
|
| 1111 |
"per_subtask": {
|
| 1112 |
"MD": {
|
| 1113 |
+
"accuracy": 1.0,
|
| 1114 |
"count": 600
|
| 1115 |
},
|
| 1116 |
"MB": {
|
| 1117 |
+
"accuracy": 1.0,
|
| 1118 |
"count": 267
|
| 1119 |
},
|
| 1120 |
"ME": {
|
|
|
|
| 1122 |
"count": 53
|
| 1123 |
},
|
| 1124 |
"UB": {
|
| 1125 |
+
"accuracy": 1.0,
|
| 1126 |
"count": 439
|
| 1127 |
},
|
| 1128 |
"UD": {
|
|
|
|
| 1132 |
}
|
| 1133 |
},
|
| 1134 |
"sub_B3": {
|
| 1135 |
+
"full_accuracy": 0.98,
|
| 1136 |
"n_examples": 100,
|
| 1137 |
"per_subtask": {
|
| 1138 |
"MD": {
|
| 1139 |
+
"accuracy": 0.9933333333333333,
|
| 1140 |
"count": 300
|
| 1141 |
},
|
| 1142 |
"MB": {
|
|
|
|
| 1144 |
"count": 100
|
| 1145 |
},
|
| 1146 |
"UB": {
|
| 1147 |
+
"accuracy": 1.0,
|
| 1148 |
"count": 197
|
| 1149 |
},
|
| 1150 |
"UD": {
|
|
|
|
| 1154 |
}
|
| 1155 |
},
|
| 1156 |
"sub_B4": {
|
| 1157 |
+
"full_accuracy": 0.93,
|
| 1158 |
"n_examples": 100,
|
| 1159 |
"per_subtask": {
|
| 1160 |
"MD": {
|
| 1161 |
+
"accuracy": 0.995,
|
| 1162 |
"count": 200
|
| 1163 |
},
|
| 1164 |
"MB": {
|
|
|
|
| 1166 |
"count": 100
|
| 1167 |
},
|
| 1168 |
"UB": {
|
| 1169 |
+
"accuracy": 0.9757085020242915,
|
| 1170 |
"count": 247
|
| 1171 |
},
|
| 1172 |
"UD": {
|
| 1173 |
+
"accuracy": 1.0,
|
| 1174 |
"count": 153
|
| 1175 |
}
|
| 1176 |
}
|
| 1177 |
},
|
| 1178 |
"sub_B5": {
|
| 1179 |
+
"full_accuracy": 0.95,
|
| 1180 |
"n_examples": 100,
|
| 1181 |
"per_subtask": {
|
| 1182 |
"MD": {
|
|
|
|
| 1188 |
"count": 100
|
| 1189 |
},
|
| 1190 |
"UB": {
|
| 1191 |
+
"accuracy": 0.9832214765100671,
|
| 1192 |
"count": 298
|
| 1193 |
},
|
| 1194 |
"UD": {
|
| 1195 |
+
"accuracy": 0.9900990099009901,
|
| 1196 |
"count": 202
|
| 1197 |
}
|
| 1198 |
}
|
| 1199 |
}
|
| 1200 |
},
|
| 1201 |
"summary": {
|
| 1202 |
+
"overall_accuracy": 0.91625,
|
| 1203 |
"total_examples": 2400,
|
| 1204 |
"n_splits": 22
|
| 1205 |
}
|
add_sub_baseline_25K/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 650266922
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d7ab48f0344d25830b9a8818aa6cf65292c8bc68b1f095b24821da0db40daaa
|
| 3 |
size 650266922
|
add_sub_baseline_25K/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": 162490082,
|
| 71 |
"run_name": "add_sub_baseline_25K",
|
| 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": 162490082,
|
| 71 |
"run_name": "add_sub_baseline_25K",
|
| 72 |
+
"git_commit": "8d5ee5420119746ef4e2c87570eb250c9718f643",
|
| 73 |
+
"timestamp": "2026-04-12T20:43:04.597818+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": "qsa0vus4",
|
| 80 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/qsa0vus4",
|
| 81 |
+
"final_accuracy": 0.91625,
|
| 82 |
+
"sft_accuracy": 0.91625,
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|