Upload add_sub_sorl_v1_abs30_K1_10K_2L1H128d
Browse files
add_sub_sorl_v1_abs30_K1_10K_2L1H128d/metrics.json
CHANGED
|
@@ -63,377 +63,377 @@
|
|
| 63 |
3133
|
| 64 |
],
|
| 65 |
"loss": [
|
| 66 |
-
11.
|
| 67 |
-
9.
|
| 68 |
-
11.
|
| 69 |
-
13.
|
| 70 |
-
12.
|
| 71 |
-
11.
|
| 72 |
-
10.
|
| 73 |
-
9.
|
| 74 |
-
9.
|
| 75 |
-
8.
|
| 76 |
-
7.
|
| 77 |
-
7.
|
| 78 |
-
6.
|
| 79 |
-
6.
|
| 80 |
-
6.
|
| 81 |
-
5.
|
| 82 |
-
5.
|
| 83 |
-
4.
|
| 84 |
-
4.
|
| 85 |
-
4.
|
| 86 |
-
4.
|
| 87 |
-
3.
|
| 88 |
-
3.
|
| 89 |
-
3.
|
| 90 |
-
3.
|
| 91 |
-
3.
|
| 92 |
-
3.
|
| 93 |
-
3.
|
| 94 |
-
3.
|
| 95 |
-
3.
|
| 96 |
-
|
| 97 |
-
3.
|
| 98 |
-
3.
|
| 99 |
-
|
| 100 |
-
3.
|
| 101 |
-
2.
|
| 102 |
-
2.
|
| 103 |
-
2.
|
| 104 |
-
2.
|
| 105 |
-
2.
|
| 106 |
-
2.
|
| 107 |
-
2.
|
| 108 |
-
2.
|
| 109 |
-
2.
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
1.
|
| 114 |
-
1.
|
| 115 |
-
1.
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
0.
|
| 121 |
-
0.
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
0.
|
| 125 |
-
0.
|
| 126 |
],
|
| 127 |
"base_loss": [
|
| 128 |
-
11.
|
| 129 |
-
11.
|
| 130 |
-
|
| 131 |
-
10.
|
| 132 |
-
9.
|
| 133 |
-
9.
|
| 134 |
-
8.
|
| 135 |
-
|
| 136 |
-
7.
|
| 137 |
-
6.
|
| 138 |
-
6.
|
| 139 |
-
6.
|
| 140 |
-
5.
|
| 141 |
-
5.
|
| 142 |
-
4.
|
| 143 |
-
4.
|
| 144 |
-
4.
|
| 145 |
-
3.
|
| 146 |
-
3.
|
| 147 |
-
3.
|
| 148 |
-
3.
|
| 149 |
-
2.
|
| 150 |
-
2.
|
| 151 |
-
2.
|
| 152 |
-
2.
|
| 153 |
-
2.
|
| 154 |
-
2.
|
| 155 |
-
2.
|
| 156 |
-
2.
|
| 157 |
-
2.
|
| 158 |
-
2.
|
| 159 |
-
2.
|
| 160 |
-
2.
|
| 161 |
-
2.
|
| 162 |
-
2.
|
| 163 |
-
2.
|
| 164 |
-
2.
|
| 165 |
-
2.
|
| 166 |
-
2.
|
| 167 |
-
2.
|
| 168 |
-
2.
|
| 169 |
-
2.
|
| 170 |
-
2.
|
| 171 |
-
2.
|
| 172 |
-
2.
|
| 173 |
-
2.
|
| 174 |
-
2.
|
| 175 |
-
2.
|
| 176 |
-
2.
|
| 177 |
-
2.
|
| 178 |
-
2.
|
| 179 |
-
2.
|
| 180 |
-
2.
|
| 181 |
-
2.
|
| 182 |
-
2.
|
| 183 |
-
2.
|
| 184 |
-
2.
|
| 185 |
-
2.
|
| 186 |
-
2.
|
| 187 |
-
2.
|
| 188 |
],
|
| 189 |
"info_loss": [
|
| 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 |
],
|
| 251 |
"abs_loss": [
|
| 252 |
-
3.
|
| 253 |
-
3.
|
| 254 |
-
3.
|
| 255 |
-
3.
|
| 256 |
-
3.
|
| 257 |
-
3.
|
| 258 |
-
3.
|
| 259 |
-
|
| 260 |
-
2.
|
| 261 |
-
2.
|
| 262 |
-
2.
|
| 263 |
-
2.
|
| 264 |
-
2.
|
| 265 |
-
2.
|
| 266 |
-
2.
|
| 267 |
-
2.
|
| 268 |
-
2.
|
| 269 |
-
2.
|
| 270 |
-
2.
|
| 271 |
-
2.
|
| 272 |
-
2.
|
| 273 |
-
2.
|
| 274 |
-
2.
|
| 275 |
-
2.
|
| 276 |
-
2.
|
| 277 |
-
2.
|
| 278 |
-
2.
|
| 279 |
-
2.
|
| 280 |
-
2.
|
| 281 |
-
2.
|
| 282 |
-
2.
|
| 283 |
-
2.
|
| 284 |
-
2.
|
| 285 |
-
2.
|
| 286 |
-
2.
|
| 287 |
-
2.
|
| 288 |
-
2.
|
| 289 |
-
2.
|
| 290 |
-
2.
|
| 291 |
-
2.
|
| 292 |
-
2.
|
| 293 |
-
2.
|
| 294 |
-
2.
|
| 295 |
-
2.
|
| 296 |
-
2.
|
| 297 |
-
2.
|
| 298 |
-
2.
|
| 299 |
-
2.
|
| 300 |
-
2.
|
| 301 |
-
2.
|
| 302 |
-
2.
|
| 303 |
-
2.
|
| 304 |
-
2.
|
| 305 |
-
2.
|
| 306 |
-
2.
|
| 307 |
-
2.
|
| 308 |
-
2.
|
| 309 |
-
2.
|
| 310 |
-
2.
|
| 311 |
-
2.
|
| 312 |
],
|
| 313 |
"zipf_loss": [
|
| 314 |
-
6.
|
| 315 |
-
6.
|
| 316 |
-
5.
|
| 317 |
-
4.
|
| 318 |
-
3.
|
| 319 |
-
2.
|
| 320 |
-
2.
|
| 321 |
-
1.
|
| 322 |
-
1.
|
| 323 |
-
1.
|
| 324 |
-
1.
|
| 325 |
-
1.
|
| 326 |
-
1.
|
| 327 |
-
0.
|
| 328 |
-
0.
|
| 329 |
-
0.
|
| 330 |
-
0.
|
| 331 |
-
0.
|
| 332 |
-
0.
|
| 333 |
-
0.
|
| 334 |
-
0.
|
| 335 |
-
0.
|
| 336 |
-
0.
|
| 337 |
-
0.
|
| 338 |
-
0.
|
| 339 |
-
0.
|
| 340 |
-
0.
|
| 341 |
-
0.
|
| 342 |
-
0.
|
| 343 |
-
0.
|
| 344 |
-
0.
|
| 345 |
-
0.
|
| 346 |
-
0.
|
| 347 |
-
0.
|
| 348 |
-
0.
|
| 349 |
-
0.
|
| 350 |
-
0.
|
| 351 |
-
0.
|
| 352 |
-
0.
|
| 353 |
-
0.
|
| 354 |
-
0.
|
| 355 |
-
0.
|
| 356 |
-
0.
|
| 357 |
-
0.
|
| 358 |
-
0.
|
| 359 |
-
0.
|
| 360 |
-
0.
|
| 361 |
-
0.
|
| 362 |
-
0.
|
| 363 |
-
0.
|
| 364 |
-
0.
|
| 365 |
-
0.
|
| 366 |
-
0.
|
| 367 |
-
0.
|
| 368 |
-
0.
|
| 369 |
-
0.
|
| 370 |
-
0.
|
| 371 |
-
0.
|
| 372 |
-
0.
|
| 373 |
-
0.
|
| 374 |
],
|
| 375 |
"denoise_loss": [],
|
| 376 |
"ortho_loss": [
|
| 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 |
],
|
| 438 |
"lr": [
|
| 439 |
9.800000000000001e-06,
|
|
@@ -521,491 +521,491 @@
|
|
| 521 |
3083
|
| 522 |
],
|
| 523 |
"eval_accuracy": [
|
| 524 |
-
0.0,
|
| 525 |
-
0.0,
|
| 526 |
-
0.0,
|
| 527 |
-
0.0,
|
| 528 |
-
0.0,
|
| 529 |
-
0.0,
|
| 530 |
-
0.0,
|
| 531 |
0.02,
|
| 532 |
-
0.01,
|
| 533 |
-
0.0,
|
| 534 |
-
0.0,
|
| 535 |
-
0.01,
|
| 536 |
-
0.0,
|
| 537 |
-
0.0,
|
| 538 |
0.02,
|
| 539 |
-
0.
|
| 540 |
-
0.
|
| 541 |
-
0.
|
| 542 |
-
0.
|
| 543 |
-
0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 544 |
]
|
| 545 |
},
|
| 546 |
-
"final_accuracy": 0.
|
| 547 |
"sft_eval": {
|
| 548 |
"config": {
|
| 549 |
"ops": "add_sub",
|
| 550 |
"K": null,
|
| 551 |
"mode": "sft",
|
| 552 |
"n_digits": 6,
|
| 553 |
-
"n_per_split":
|
| 554 |
},
|
| 555 |
"splits": {
|
| 556 |
"add_S0": {
|
| 557 |
"full_accuracy": 0.0,
|
| 558 |
-
"digit_accuracy": 0.
|
| 559 |
-
"n_examples":
|
| 560 |
"per_subtask": {
|
| 561 |
"SA": {
|
| 562 |
-
"accuracy": 0.
|
| 563 |
-
"count":
|
| 564 |
},
|
| 565 |
"SS": {
|
| 566 |
-
"accuracy": 0.
|
| 567 |
-
"count":
|
| 568 |
}
|
| 569 |
}
|
| 570 |
},
|
| 571 |
"add_S1": {
|
| 572 |
"full_accuracy": 0.0,
|
| 573 |
-
"digit_accuracy": 0.
|
| 574 |
-
"n_examples":
|
| 575 |
"per_subtask": {
|
| 576 |
"SA": {
|
| 577 |
-
"accuracy": 0.
|
| 578 |
-
"count":
|
| 579 |
},
|
| 580 |
"SC": {
|
| 581 |
-
"accuracy": 0.
|
| 582 |
-
"count":
|
| 583 |
},
|
| 584 |
"SS": {
|
| 585 |
-
"accuracy": 0.
|
| 586 |
-
"count":
|
| 587 |
},
|
| 588 |
"UC": {
|
| 589 |
-
"accuracy": 0.
|
| 590 |
-
"count":
|
| 591 |
}
|
| 592 |
}
|
| 593 |
},
|
| 594 |
"add_S2": {
|
| 595 |
"full_accuracy": 0.0,
|
| 596 |
-
"digit_accuracy": 0.
|
| 597 |
-
"n_examples":
|
| 598 |
"per_subtask": {
|
| 599 |
"SA": {
|
| 600 |
-
"accuracy": 0.
|
| 601 |
-
"count":
|
| 602 |
},
|
| 603 |
"SC": {
|
| 604 |
-
"accuracy": 0.
|
| 605 |
-
"count":
|
| 606 |
},
|
| 607 |
"SS": {
|
| 608 |
-
"accuracy": 0.
|
| 609 |
-
"count":
|
| 610 |
},
|
| 611 |
"UC": {
|
| 612 |
-
"accuracy": 0.
|
| 613 |
-
"count":
|
| 614 |
},
|
| 615 |
"US": {
|
| 616 |
-
"accuracy": 0.
|
| 617 |
-
"count":
|
| 618 |
}
|
| 619 |
}
|
| 620 |
},
|
| 621 |
"add_S3": {
|
| 622 |
"full_accuracy": 0.0,
|
| 623 |
-
"digit_accuracy": 0.
|
| 624 |
-
"n_examples":
|
| 625 |
"per_subtask": {
|
| 626 |
"SA": {
|
| 627 |
-
"accuracy": 0.
|
| 628 |
-
"count":
|
| 629 |
},
|
| 630 |
"SC": {
|
| 631 |
-
"accuracy": 0.
|
| 632 |
-
"count":
|
| 633 |
},
|
| 634 |
"SS": {
|
| 635 |
-
"accuracy": 0.
|
| 636 |
-
"count":
|
| 637 |
},
|
| 638 |
"UC": {
|
| 639 |
-
"accuracy": 0.
|
| 640 |
-
"count":
|
| 641 |
},
|
| 642 |
"US": {
|
| 643 |
-
"accuracy": 0.
|
| 644 |
-
"count":
|
| 645 |
}
|
| 646 |
}
|
| 647 |
},
|
| 648 |
"add_S4": {
|
| 649 |
"full_accuracy": 0.0,
|
| 650 |
-
"digit_accuracy": 0.
|
| 651 |
-
"n_examples":
|
| 652 |
"per_subtask": {
|
| 653 |
"SA": {
|
| 654 |
-
"accuracy": 0.
|
| 655 |
-
"count":
|
| 656 |
},
|
| 657 |
"SC": {
|
| 658 |
-
"accuracy": 0.
|
| 659 |
-
"count":
|
| 660 |
},
|
| 661 |
"SS": {
|
| 662 |
-
"accuracy": 0.
|
| 663 |
-
"count":
|
| 664 |
},
|
| 665 |
"UC": {
|
| 666 |
-
"accuracy": 0.
|
| 667 |
-
"count":
|
| 668 |
},
|
| 669 |
"US": {
|
| 670 |
-
"accuracy": 0.
|
| 671 |
-
"count":
|
| 672 |
}
|
| 673 |
}
|
| 674 |
},
|
| 675 |
"add_S5": {
|
| 676 |
"full_accuracy": 0.0,
|
| 677 |
-
"digit_accuracy": 0.
|
| 678 |
-
"n_examples":
|
| 679 |
"per_subtask": {
|
| 680 |
"SA": {
|
| 681 |
-
"accuracy": 0.
|
| 682 |
-
"count":
|
| 683 |
},
|
| 684 |
"SC": {
|
| 685 |
-
"accuracy": 0.
|
| 686 |
-
"count":
|
| 687 |
},
|
| 688 |
"UC": {
|
| 689 |
"accuracy": 0.12,
|
| 690 |
-
"count":
|
| 691 |
},
|
| 692 |
"US": {
|
| 693 |
-
"accuracy": 0.
|
| 694 |
-
"count":
|
| 695 |
}
|
| 696 |
}
|
| 697 |
},
|
| 698 |
"add_S6": {
|
| 699 |
-
"full_accuracy": 0.
|
| 700 |
-
"digit_accuracy": 0.
|
| 701 |
-
"n_examples":
|
| 702 |
"per_subtask": {
|
| 703 |
"SC": {
|
| 704 |
-
"accuracy": 0.
|
| 705 |
-
"count":
|
| 706 |
},
|
| 707 |
"UC": {
|
| 708 |
-
"accuracy": 0.
|
| 709 |
-
"count":
|
| 710 |
},
|
| 711 |
"US": {
|
| 712 |
-
"accuracy": 0.
|
| 713 |
-
"count":
|
| 714 |
}
|
| 715 |
}
|
| 716 |
},
|
| 717 |
"add_random": {
|
| 718 |
"full_accuracy": 0.0,
|
| 719 |
-
"digit_accuracy": 0.
|
| 720 |
"n_examples": 200,
|
| 721 |
"per_subtask": {
|
| 722 |
"SA": {
|
| 723 |
-
"accuracy": 0.
|
| 724 |
-
"count":
|
| 725 |
},
|
| 726 |
"SC": {
|
| 727 |
-
"accuracy": 0.
|
| 728 |
-
"count":
|
| 729 |
},
|
| 730 |
"SS": {
|
| 731 |
-
"accuracy": 0.
|
| 732 |
-
"count":
|
| 733 |
},
|
| 734 |
"UC": {
|
| 735 |
-
"accuracy": 0.
|
| 736 |
-
"count":
|
| 737 |
},
|
| 738 |
"US": {
|
| 739 |
-
"accuracy": 0.
|
| 740 |
-
"count":
|
| 741 |
}
|
| 742 |
}
|
| 743 |
},
|
| 744 |
"add_C1": {
|
| 745 |
"full_accuracy": 0.0,
|
| 746 |
-
"digit_accuracy": 0.
|
| 747 |
-
"n_examples":
|
| 748 |
"per_subtask": {
|
| 749 |
"SA": {
|
| 750 |
-
"accuracy": 0.
|
| 751 |
-
"count":
|
| 752 |
},
|
| 753 |
"SC": {
|
| 754 |
-
"accuracy": 0.
|
| 755 |
-
"count":
|
| 756 |
},
|
| 757 |
"UC": {
|
| 758 |
"accuracy": 0.0,
|
| 759 |
-
"count":
|
| 760 |
}
|
| 761 |
}
|
| 762 |
},
|
| 763 |
"add_C2": {
|
| 764 |
"full_accuracy": 0.0,
|
| 765 |
-
"digit_accuracy": 0.
|
| 766 |
-
"n_examples":
|
| 767 |
"per_subtask": {
|
| 768 |
"SA": {
|
| 769 |
-
"accuracy": 0.
|
| 770 |
-
"count":
|
| 771 |
},
|
| 772 |
"SC": {
|
| 773 |
-
"accuracy": 0.
|
| 774 |
-
"count":
|
| 775 |
},
|
| 776 |
"UC": {
|
| 777 |
-
"accuracy": 0.
|
| 778 |
-
"count":
|
| 779 |
},
|
| 780 |
"US": {
|
| 781 |
-
"accuracy": 0.
|
| 782 |
-
"count":
|
| 783 |
}
|
| 784 |
}
|
| 785 |
},
|
| 786 |
"add_C3": {
|
| 787 |
"full_accuracy": 0.0,
|
| 788 |
-
"digit_accuracy": 0.
|
| 789 |
-
"n_examples":
|
| 790 |
"per_subtask": {
|
| 791 |
"SA": {
|
| 792 |
-
"accuracy": 0.
|
| 793 |
-
"count":
|
| 794 |
},
|
| 795 |
"SC": {
|
| 796 |
-
"accuracy": 0.
|
| 797 |
-
"count":
|
| 798 |
},
|
| 799 |
"UC": {
|
| 800 |
-
"accuracy": 0.
|
| 801 |
-
"count":
|
| 802 |
},
|
| 803 |
"US": {
|
| 804 |
-
"accuracy": 0.
|
| 805 |
-
"count":
|
| 806 |
}
|
| 807 |
}
|
| 808 |
},
|
| 809 |
"add_C4": {
|
| 810 |
"full_accuracy": 0.0,
|
| 811 |
-
"digit_accuracy": 0.
|
| 812 |
-
"n_examples":
|
| 813 |
"per_subtask": {
|
| 814 |
"SA": {
|
| 815 |
-
"accuracy": 0.
|
| 816 |
-
"count":
|
| 817 |
},
|
| 818 |
"SC": {
|
| 819 |
-
"accuracy": 0.
|
| 820 |
-
"count":
|
| 821 |
},
|
| 822 |
"UC": {
|
| 823 |
-
"accuracy": 0.
|
| 824 |
-
"count":
|
| 825 |
},
|
| 826 |
"US": {
|
| 827 |
-
"accuracy": 0.
|
| 828 |
-
"count":
|
| 829 |
}
|
| 830 |
}
|
| 831 |
},
|
| 832 |
"add_C5": {
|
| 833 |
"full_accuracy": 0.0,
|
| 834 |
-
"digit_accuracy": 0.
|
| 835 |
-
"n_examples":
|
| 836 |
"per_subtask": {
|
| 837 |
"SA": {
|
| 838 |
-
"accuracy": 0.
|
| 839 |
-
"count":
|
| 840 |
},
|
| 841 |
"SC": {
|
| 842 |
-
"accuracy": 0.
|
| 843 |
-
"count":
|
| 844 |
},
|
| 845 |
"UC": {
|
| 846 |
-
"accuracy": 0.
|
| 847 |
-
"count":
|
| 848 |
},
|
| 849 |
"US": {
|
| 850 |
-
"accuracy": 0.
|
| 851 |
-
"count":
|
| 852 |
}
|
| 853 |
}
|
| 854 |
},
|
| 855 |
"add_C6": {
|
| 856 |
"full_accuracy": 0.0,
|
| 857 |
-
"digit_accuracy": 0.
|
| 858 |
-
"n_examples":
|
| 859 |
"per_subtask": {
|
| 860 |
"SC": {
|
| 861 |
-
"accuracy": 0.
|
| 862 |
-
"count":
|
| 863 |
},
|
| 864 |
"UC": {
|
| 865 |
-
"accuracy": 0.
|
| 866 |
-
"count":
|
| 867 |
},
|
| 868 |
"US": {
|
| 869 |
-
"accuracy": 0.
|
| 870 |
-
"count":
|
| 871 |
}
|
| 872 |
}
|
| 873 |
},
|
| 874 |
"sub_M0": {
|
| 875 |
"full_accuracy": 0.0,
|
| 876 |
-
"digit_accuracy": 0.
|
| 877 |
-
"n_examples":
|
| 878 |
"per_subtask": {
|
| 879 |
"MD": {
|
| 880 |
-
"accuracy": 0.
|
| 881 |
-
"count":
|
| 882 |
},
|
| 883 |
"ME": {
|
| 884 |
"accuracy": 1.0,
|
| 885 |
-
"count":
|
| 886 |
}
|
| 887 |
}
|
| 888 |
},
|
| 889 |
"sub_M1": {
|
| 890 |
"full_accuracy": 0.0,
|
| 891 |
-
"digit_accuracy": 0.
|
| 892 |
-
"n_examples":
|
| 893 |
"per_subtask": {
|
| 894 |
"MD": {
|
| 895 |
-
"accuracy": 0.
|
| 896 |
-
"count":
|
| 897 |
},
|
| 898 |
"MB": {
|
| 899 |
"accuracy": 0.0,
|
| 900 |
-
"count":
|
| 901 |
},
|
| 902 |
"ME": {
|
| 903 |
"accuracy": 1.0,
|
| 904 |
-
"count":
|
| 905 |
},
|
| 906 |
"UB": {
|
| 907 |
-
"accuracy": 0.
|
| 908 |
-
"count":
|
| 909 |
}
|
| 910 |
}
|
| 911 |
},
|
| 912 |
"sub_M2": {
|
| 913 |
"full_accuracy": 0.0,
|
| 914 |
-
"digit_accuracy": 0.
|
| 915 |
-
"n_examples":
|
| 916 |
"per_subtask": {
|
| 917 |
"MD": {
|
| 918 |
-
"accuracy": 0.
|
| 919 |
-
"count":
|
| 920 |
},
|
| 921 |
"MB": {
|
| 922 |
"accuracy": 0.0,
|
| 923 |
-
"count":
|
| 924 |
},
|
| 925 |
"ME": {
|
| 926 |
"accuracy": 1.0,
|
| 927 |
-
"count":
|
| 928 |
},
|
| 929 |
"UB": {
|
| 930 |
-
"accuracy": 0.
|
| 931 |
-
"count":
|
| 932 |
},
|
| 933 |
"UD": {
|
| 934 |
"accuracy": 0.0,
|
| 935 |
-
"count":
|
| 936 |
}
|
| 937 |
}
|
| 938 |
},
|
| 939 |
"sub_M3": {
|
| 940 |
"full_accuracy": 0.0,
|
| 941 |
-
"digit_accuracy": 0.
|
| 942 |
-
"n_examples":
|
| 943 |
"per_subtask": {
|
| 944 |
"MD": {
|
| 945 |
-
"accuracy": 0.
|
| 946 |
-
"count":
|
| 947 |
},
|
| 948 |
"MB": {
|
| 949 |
"accuracy": 0.0,
|
| 950 |
-
"count":
|
| 951 |
},
|
| 952 |
"ME": {
|
| 953 |
"accuracy": 1.0,
|
| 954 |
-
"count":
|
| 955 |
},
|
| 956 |
"UB": {
|
| 957 |
-
"accuracy": 0.
|
| 958 |
-
"count":
|
| 959 |
},
|
| 960 |
"UD": {
|
| 961 |
"accuracy": 0.0,
|
| 962 |
-
"count":
|
| 963 |
}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
"sub_M4": {
|
| 967 |
"full_accuracy": 0.0,
|
| 968 |
-
"digit_accuracy": 0.
|
| 969 |
-
"n_examples":
|
| 970 |
"per_subtask": {
|
| 971 |
"MD": {
|
| 972 |
"accuracy": 0.5,
|
| 973 |
-
"count":
|
| 974 |
},
|
| 975 |
"MB": {
|
| 976 |
"accuracy": 0.0,
|
| 977 |
-
"count":
|
| 978 |
},
|
| 979 |
"UB": {
|
| 980 |
-
"accuracy": 0.
|
| 981 |
-
"count":
|
| 982 |
},
|
| 983 |
"UD": {
|
| 984 |
"accuracy": 0.0,
|
| 985 |
-
"count":
|
| 986 |
}
|
| 987 |
}
|
| 988 |
},
|
| 989 |
"sub_M5": {
|
| 990 |
"full_accuracy": 0.0,
|
| 991 |
-
"digit_accuracy": 0.
|
| 992 |
-
"n_examples":
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
"accuracy": 1.0,
|
| 996 |
-
"count":
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
"accuracy": 0.0,
|
| 1000 |
-
"count":
|
| 1001 |
},
|
| 1002 |
"UB": {
|
| 1003 |
-
"accuracy": 0.
|
| 1004 |
-
"count":
|
| 1005 |
},
|
| 1006 |
"UD": {
|
| 1007 |
"accuracy": 0.0,
|
| 1008 |
-
"count":
|
| 1009 |
}
|
| 1010 |
}
|
| 1011 |
},
|
|
@@ -1015,101 +1015,101 @@
|
|
| 1015 |
"n_examples": 200,
|
| 1016 |
"per_subtask": {
|
| 1017 |
"MD": {
|
| 1018 |
-
"accuracy": 0.
|
| 1019 |
-
"count":
|
| 1020 |
},
|
| 1021 |
"MB": {
|
| 1022 |
"accuracy": 0.0,
|
| 1023 |
-
"count":
|
| 1024 |
},
|
| 1025 |
"ME": {
|
| 1026 |
"accuracy": 1.0,
|
| 1027 |
"count": 53
|
| 1028 |
},
|
| 1029 |
"UB": {
|
| 1030 |
-
"accuracy": 0.
|
| 1031 |
-
"count":
|
| 1032 |
},
|
| 1033 |
"UD": {
|
| 1034 |
"accuracy": 0.0,
|
| 1035 |
-
"count":
|
| 1036 |
}
|
| 1037 |
}
|
| 1038 |
},
|
| 1039 |
"sub_B3": {
|
| 1040 |
"full_accuracy": 0.0,
|
| 1041 |
-
"digit_accuracy": 0.
|
| 1042 |
-
"n_examples":
|
| 1043 |
"per_subtask": {
|
| 1044 |
"MD": {
|
| 1045 |
"accuracy": 0.3333333333333333,
|
| 1046 |
-
"count":
|
| 1047 |
},
|
| 1048 |
"MB": {
|
| 1049 |
"accuracy": 0.0,
|
| 1050 |
-
"count":
|
| 1051 |
},
|
| 1052 |
"UB": {
|
| 1053 |
-
"accuracy": 0.
|
| 1054 |
-
"count":
|
| 1055 |
},
|
| 1056 |
"UD": {
|
| 1057 |
"accuracy": 0.0,
|
| 1058 |
-
"count":
|
| 1059 |
}
|
| 1060 |
}
|
| 1061 |
},
|
| 1062 |
"sub_B4": {
|
| 1063 |
"full_accuracy": 0.0,
|
| 1064 |
-
"digit_accuracy": 0.
|
| 1065 |
-
"n_examples":
|
| 1066 |
"per_subtask": {
|
| 1067 |
"MD": {
|
| 1068 |
"accuracy": 0.5,
|
| 1069 |
-
"count":
|
| 1070 |
},
|
| 1071 |
"MB": {
|
| 1072 |
"accuracy": 0.0,
|
| 1073 |
-
"count":
|
| 1074 |
},
|
| 1075 |
"UB": {
|
| 1076 |
-
"accuracy": 0.
|
| 1077 |
-
"count":
|
| 1078 |
},
|
| 1079 |
"UD": {
|
| 1080 |
"accuracy": 0.0,
|
| 1081 |
-
"count":
|
| 1082 |
}
|
| 1083 |
}
|
| 1084 |
},
|
| 1085 |
"sub_B5": {
|
| 1086 |
"full_accuracy": 0.0,
|
| 1087 |
-
"digit_accuracy": 0.
|
| 1088 |
-
"n_examples":
|
| 1089 |
"per_subtask": {
|
| 1090 |
"MD": {
|
| 1091 |
"accuracy": 1.0,
|
| 1092 |
-
"count":
|
| 1093 |
},
|
| 1094 |
"MB": {
|
| 1095 |
"accuracy": 0.0,
|
| 1096 |
-
"count":
|
| 1097 |
},
|
| 1098 |
"UB": {
|
| 1099 |
-
"accuracy": 0.
|
| 1100 |
-
"count":
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
"accuracy": 0.0,
|
| 1104 |
-
"count":
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"summary": {
|
| 1110 |
-
"overall_accuracy": 0.
|
| 1111 |
-
"digit_accuracy": 0.
|
| 1112 |
-
"total_examples":
|
| 1113 |
"n_splits": 24
|
| 1114 |
}
|
| 1115 |
},
|
|
@@ -1119,569 +1119,569 @@
|
|
| 1119 |
"K": 1,
|
| 1120 |
"mode": "sorl",
|
| 1121 |
"n_digits": 6,
|
| 1122 |
-
"n_per_split":
|
| 1123 |
},
|
| 1124 |
"splits": {
|
| 1125 |
"add_S0": {
|
| 1126 |
"full_accuracy": 0.0,
|
| 1127 |
-
"digit_accuracy": 0.
|
| 1128 |
-
"n_examples":
|
| 1129 |
"per_subtask": {
|
| 1130 |
"SA": {
|
| 1131 |
-
"accuracy": 0.
|
| 1132 |
-
"count":
|
| 1133 |
},
|
| 1134 |
"SS": {
|
| 1135 |
-
"accuracy": 0.
|
| 1136 |
-
"count":
|
| 1137 |
}
|
| 1138 |
}
|
| 1139 |
},
|
| 1140 |
"add_S1": {
|
| 1141 |
"full_accuracy": 0.0,
|
| 1142 |
-
"digit_accuracy": 0.
|
| 1143 |
-
"n_examples":
|
| 1144 |
"per_subtask": {
|
| 1145 |
"SA": {
|
| 1146 |
-
"accuracy": 0.
|
| 1147 |
-
"count":
|
| 1148 |
},
|
| 1149 |
"SC": {
|
| 1150 |
-
"accuracy": 0.
|
| 1151 |
-
"count":
|
| 1152 |
},
|
| 1153 |
"SS": {
|
| 1154 |
-
"accuracy": 0.
|
| 1155 |
-
"count":
|
| 1156 |
},
|
| 1157 |
"UC": {
|
| 1158 |
-
"accuracy": 0.
|
| 1159 |
-
"count":
|
| 1160 |
}
|
| 1161 |
}
|
| 1162 |
},
|
| 1163 |
"add_S2": {
|
| 1164 |
-
"full_accuracy": 0.
|
| 1165 |
-
"digit_accuracy": 0.
|
| 1166 |
-
"n_examples":
|
| 1167 |
"per_subtask": {
|
| 1168 |
"SA": {
|
| 1169 |
-
"accuracy": 0.
|
| 1170 |
-
"count":
|
| 1171 |
},
|
| 1172 |
"SC": {
|
| 1173 |
-
"accuracy": 0.
|
| 1174 |
-
"count":
|
| 1175 |
},
|
| 1176 |
"SS": {
|
| 1177 |
-
"accuracy": 0.
|
| 1178 |
-
"count":
|
| 1179 |
},
|
| 1180 |
"UC": {
|
| 1181 |
-
"accuracy": 0.
|
| 1182 |
-
"count":
|
| 1183 |
},
|
| 1184 |
"US": {
|
| 1185 |
-
"accuracy": 0.
|
| 1186 |
-
"count":
|
| 1187 |
}
|
| 1188 |
}
|
| 1189 |
},
|
| 1190 |
"add_S3": {
|
| 1191 |
-
"full_accuracy": 0.
|
| 1192 |
-
"digit_accuracy": 0.
|
| 1193 |
-
"n_examples":
|
| 1194 |
"per_subtask": {
|
| 1195 |
"SA": {
|
| 1196 |
-
"accuracy": 0.
|
| 1197 |
-
"count":
|
| 1198 |
},
|
| 1199 |
"SC": {
|
| 1200 |
-
"accuracy": 0.
|
| 1201 |
-
"count":
|
| 1202 |
},
|
| 1203 |
"SS": {
|
| 1204 |
-
"accuracy": 0.
|
| 1205 |
-
"count":
|
| 1206 |
},
|
| 1207 |
"UC": {
|
| 1208 |
-
"accuracy": 0.
|
| 1209 |
-
"count":
|
| 1210 |
},
|
| 1211 |
"US": {
|
| 1212 |
-
"accuracy": 0.
|
| 1213 |
-
"count":
|
| 1214 |
}
|
| 1215 |
}
|
| 1216 |
},
|
| 1217 |
"add_S4": {
|
| 1218 |
"full_accuracy": 0.0,
|
| 1219 |
-
"digit_accuracy": 0.
|
| 1220 |
-
"n_examples":
|
| 1221 |
"per_subtask": {
|
| 1222 |
"SA": {
|
| 1223 |
-
"accuracy": 0.
|
| 1224 |
-
"count":
|
| 1225 |
},
|
| 1226 |
"SC": {
|
| 1227 |
-
"accuracy": 0.
|
| 1228 |
-
"count":
|
| 1229 |
},
|
| 1230 |
"SS": {
|
| 1231 |
-
"accuracy": 0.
|
| 1232 |
-
"count":
|
| 1233 |
},
|
| 1234 |
"UC": {
|
| 1235 |
-
"accuracy": 0.
|
| 1236 |
-
"count":
|
| 1237 |
},
|
| 1238 |
"US": {
|
| 1239 |
-
"accuracy": 0.
|
| 1240 |
-
"count":
|
| 1241 |
}
|
| 1242 |
}
|
| 1243 |
},
|
| 1244 |
"add_S5": {
|
| 1245 |
"full_accuracy": 0.0,
|
| 1246 |
-
"digit_accuracy": 0.
|
| 1247 |
-
"n_examples":
|
| 1248 |
"per_subtask": {
|
| 1249 |
"SA": {
|
| 1250 |
-
"accuracy": 0.
|
| 1251 |
-
"count":
|
| 1252 |
},
|
| 1253 |
"SC": {
|
| 1254 |
-
"accuracy": 0.
|
| 1255 |
-
"count":
|
| 1256 |
},
|
| 1257 |
"UC": {
|
| 1258 |
-
"accuracy": 0.
|
| 1259 |
-
"count":
|
| 1260 |
},
|
| 1261 |
"US": {
|
| 1262 |
-
"accuracy": 0.
|
| 1263 |
-
"count":
|
| 1264 |
}
|
| 1265 |
}
|
| 1266 |
},
|
| 1267 |
"add_S6": {
|
| 1268 |
-
"full_accuracy": 0.
|
| 1269 |
-
"digit_accuracy": 0.
|
| 1270 |
-
"n_examples":
|
| 1271 |
"per_subtask": {
|
| 1272 |
"SC": {
|
| 1273 |
-
"accuracy": 0.
|
| 1274 |
-
"count":
|
| 1275 |
},
|
| 1276 |
"UC": {
|
| 1277 |
-
"accuracy": 0.
|
| 1278 |
-
"count":
|
| 1279 |
},
|
| 1280 |
"US": {
|
| 1281 |
-
"accuracy": 0.
|
| 1282 |
-
"count":
|
| 1283 |
}
|
| 1284 |
}
|
| 1285 |
},
|
| 1286 |
"add_random": {
|
| 1287 |
"full_accuracy": 0.0,
|
| 1288 |
-
"digit_accuracy": 0.
|
| 1289 |
"n_examples": 200,
|
| 1290 |
"per_subtask": {
|
| 1291 |
"SA": {
|
| 1292 |
-
"accuracy": 0.
|
| 1293 |
-
"count":
|
| 1294 |
},
|
| 1295 |
"SC": {
|
| 1296 |
-
"accuracy": 0.
|
| 1297 |
-
"count":
|
| 1298 |
},
|
| 1299 |
"SS": {
|
| 1300 |
-
"accuracy": 0.
|
| 1301 |
-
"count":
|
| 1302 |
},
|
| 1303 |
"UC": {
|
| 1304 |
-
"accuracy": 0.
|
| 1305 |
-
"count":
|
| 1306 |
},
|
| 1307 |
"US": {
|
| 1308 |
-
"accuracy": 0.
|
| 1309 |
-
"count":
|
| 1310 |
}
|
| 1311 |
}
|
| 1312 |
},
|
| 1313 |
"add_C1": {
|
| 1314 |
"full_accuracy": 0.0,
|
| 1315 |
-
"digit_accuracy": 0.
|
| 1316 |
-
"n_examples":
|
| 1317 |
"per_subtask": {
|
| 1318 |
"SA": {
|
| 1319 |
-
"accuracy": 0.
|
| 1320 |
-
"count":
|
| 1321 |
},
|
| 1322 |
"SC": {
|
| 1323 |
-
"accuracy": 0.
|
| 1324 |
-
"count":
|
| 1325 |
},
|
| 1326 |
"UC": {
|
| 1327 |
-
"accuracy": 0.
|
| 1328 |
-
"count":
|
| 1329 |
}
|
| 1330 |
}
|
| 1331 |
},
|
| 1332 |
"add_C2": {
|
| 1333 |
"full_accuracy": 0.0,
|
| 1334 |
-
"digit_accuracy": 0.
|
| 1335 |
-
"n_examples":
|
| 1336 |
"per_subtask": {
|
| 1337 |
"SA": {
|
| 1338 |
-
"accuracy": 0.
|
| 1339 |
-
"count":
|
| 1340 |
},
|
| 1341 |
"SC": {
|
| 1342 |
-
"accuracy": 0.
|
| 1343 |
-
"count":
|
| 1344 |
},
|
| 1345 |
"UC": {
|
| 1346 |
-
"accuracy": 0.
|
| 1347 |
-
"count":
|
| 1348 |
},
|
| 1349 |
"US": {
|
| 1350 |
-
"accuracy": 0.
|
| 1351 |
-
"count":
|
| 1352 |
}
|
| 1353 |
}
|
| 1354 |
},
|
| 1355 |
"add_C3": {
|
| 1356 |
"full_accuracy": 0.0,
|
| 1357 |
-
"digit_accuracy": 0.
|
| 1358 |
-
"n_examples":
|
| 1359 |
"per_subtask": {
|
| 1360 |
"SA": {
|
| 1361 |
-
"accuracy": 0.
|
| 1362 |
-
"count":
|
| 1363 |
},
|
| 1364 |
"SC": {
|
| 1365 |
-
"accuracy": 0.
|
| 1366 |
-
"count":
|
| 1367 |
},
|
| 1368 |
"UC": {
|
| 1369 |
-
"accuracy": 0.
|
| 1370 |
-
"count":
|
| 1371 |
},
|
| 1372 |
"US": {
|
| 1373 |
-
"accuracy": 0.
|
| 1374 |
-
"count":
|
| 1375 |
}
|
| 1376 |
}
|
| 1377 |
},
|
| 1378 |
"add_C4": {
|
| 1379 |
"full_accuracy": 0.0,
|
| 1380 |
-
"digit_accuracy": 0.
|
| 1381 |
-
"n_examples":
|
| 1382 |
"per_subtask": {
|
| 1383 |
"SA": {
|
| 1384 |
-
"accuracy": 0.
|
| 1385 |
-
"count":
|
| 1386 |
},
|
| 1387 |
"SC": {
|
| 1388 |
-
"accuracy": 0.
|
| 1389 |
-
"count":
|
| 1390 |
},
|
| 1391 |
"UC": {
|
| 1392 |
-
"accuracy": 0.
|
| 1393 |
-
"count":
|
| 1394 |
},
|
| 1395 |
"US": {
|
| 1396 |
-
"accuracy": 0.
|
| 1397 |
-
"count":
|
| 1398 |
}
|
| 1399 |
}
|
| 1400 |
},
|
| 1401 |
"add_C5": {
|
| 1402 |
"full_accuracy": 0.0,
|
| 1403 |
-
"digit_accuracy": 0.
|
| 1404 |
-
"n_examples":
|
| 1405 |
"per_subtask": {
|
| 1406 |
"SA": {
|
| 1407 |
-
"accuracy": 0.
|
| 1408 |
-
"count":
|
| 1409 |
},
|
| 1410 |
"SC": {
|
| 1411 |
-
"accuracy": 0.
|
| 1412 |
-
"count":
|
| 1413 |
},
|
| 1414 |
"UC": {
|
| 1415 |
-
"accuracy": 0.
|
| 1416 |
-
"count":
|
| 1417 |
},
|
| 1418 |
"US": {
|
| 1419 |
-
"accuracy": 0.
|
| 1420 |
-
"count":
|
| 1421 |
}
|
| 1422 |
}
|
| 1423 |
},
|
| 1424 |
"add_C6": {
|
| 1425 |
"full_accuracy": 0.0,
|
| 1426 |
-
"digit_accuracy": 0.
|
| 1427 |
-
"n_examples":
|
| 1428 |
"per_subtask": {
|
| 1429 |
"SC": {
|
| 1430 |
-
"accuracy": 0.
|
| 1431 |
-
"count":
|
| 1432 |
},
|
| 1433 |
"UC": {
|
| 1434 |
-
"accuracy": 0.
|
| 1435 |
-
"count":
|
| 1436 |
},
|
| 1437 |
"US": {
|
| 1438 |
-
"accuracy": 0.
|
| 1439 |
-
"count":
|
| 1440 |
}
|
| 1441 |
}
|
| 1442 |
},
|
| 1443 |
"sub_M0": {
|
| 1444 |
"full_accuracy": 0.0,
|
| 1445 |
-
"digit_accuracy": 0.
|
| 1446 |
-
"n_examples":
|
| 1447 |
"per_subtask": {
|
| 1448 |
"MD": {
|
| 1449 |
-
"accuracy": 0.
|
| 1450 |
-
"count":
|
| 1451 |
},
|
| 1452 |
"ME": {
|
| 1453 |
"accuracy": 1.0,
|
| 1454 |
-
"count":
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"sub_M1": {
|
| 1459 |
"full_accuracy": 0.0,
|
| 1460 |
-
"digit_accuracy": 0.
|
| 1461 |
-
"n_examples":
|
| 1462 |
"per_subtask": {
|
| 1463 |
"MD": {
|
| 1464 |
-
"accuracy": 0.
|
| 1465 |
-
"count":
|
| 1466 |
},
|
| 1467 |
"MB": {
|
| 1468 |
-
"accuracy": 0.
|
| 1469 |
-
"count":
|
| 1470 |
},
|
| 1471 |
"ME": {
|
| 1472 |
"accuracy": 1.0,
|
| 1473 |
-
"count":
|
| 1474 |
},
|
| 1475 |
"UB": {
|
| 1476 |
-
"accuracy": 0.
|
| 1477 |
-
"count":
|
| 1478 |
}
|
| 1479 |
}
|
| 1480 |
},
|
| 1481 |
"sub_M2": {
|
| 1482 |
"full_accuracy": 0.0,
|
| 1483 |
-
"digit_accuracy": 0.
|
| 1484 |
-
"n_examples":
|
| 1485 |
"per_subtask": {
|
| 1486 |
"MD": {
|
| 1487 |
-
"accuracy": 0.
|
| 1488 |
-
"count":
|
| 1489 |
},
|
| 1490 |
"MB": {
|
| 1491 |
-
"accuracy": 0.
|
| 1492 |
-
"count":
|
| 1493 |
},
|
| 1494 |
"ME": {
|
| 1495 |
"accuracy": 1.0,
|
| 1496 |
-
"count":
|
| 1497 |
},
|
| 1498 |
"UB": {
|
| 1499 |
-
"accuracy": 0.
|
| 1500 |
-
"count":
|
| 1501 |
},
|
| 1502 |
"UD": {
|
| 1503 |
-
"accuracy": 0.
|
| 1504 |
-
"count":
|
| 1505 |
}
|
| 1506 |
}
|
| 1507 |
},
|
| 1508 |
"sub_M3": {
|
| 1509 |
"full_accuracy": 0.0,
|
| 1510 |
-
"digit_accuracy": 0.
|
| 1511 |
-
"n_examples":
|
| 1512 |
"per_subtask": {
|
| 1513 |
"MD": {
|
| 1514 |
-
"accuracy": 0.
|
| 1515 |
-
"count":
|
| 1516 |
},
|
| 1517 |
"MB": {
|
| 1518 |
-
"accuracy": 0.
|
| 1519 |
-
"count":
|
| 1520 |
},
|
| 1521 |
"ME": {
|
| 1522 |
"accuracy": 1.0,
|
| 1523 |
-
"count":
|
| 1524 |
},
|
| 1525 |
"UB": {
|
| 1526 |
-
"accuracy": 0.
|
| 1527 |
-
"count":
|
| 1528 |
},
|
| 1529 |
"UD": {
|
| 1530 |
-
"accuracy": 0.
|
| 1531 |
-
"count":
|
| 1532 |
}
|
| 1533 |
}
|
| 1534 |
},
|
| 1535 |
"sub_M4": {
|
| 1536 |
"full_accuracy": 0.0,
|
| 1537 |
-
"digit_accuracy": 0.
|
| 1538 |
-
"n_examples":
|
| 1539 |
"per_subtask": {
|
| 1540 |
"MD": {
|
| 1541 |
"accuracy": 0.54,
|
| 1542 |
-
"count":
|
| 1543 |
},
|
| 1544 |
"MB": {
|
| 1545 |
-
"accuracy": 0.
|
| 1546 |
-
"count":
|
| 1547 |
},
|
| 1548 |
"UB": {
|
| 1549 |
-
"accuracy": 0.
|
| 1550 |
-
"count":
|
| 1551 |
},
|
| 1552 |
"UD": {
|
| 1553 |
"accuracy": 0.0,
|
| 1554 |
-
"count":
|
| 1555 |
}
|
| 1556 |
}
|
| 1557 |
},
|
| 1558 |
"sub_M5": {
|
| 1559 |
"full_accuracy": 0.0,
|
| 1560 |
-
"digit_accuracy": 0.
|
| 1561 |
-
"n_examples":
|
| 1562 |
"per_subtask": {
|
| 1563 |
"MD": {
|
| 1564 |
"accuracy": 1.0,
|
| 1565 |
-
"count":
|
| 1566 |
},
|
| 1567 |
"MB": {
|
| 1568 |
"accuracy": 0.0,
|
| 1569 |
-
"count":
|
| 1570 |
},
|
| 1571 |
"UB": {
|
| 1572 |
-
"accuracy": 0.
|
| 1573 |
-
"count":
|
| 1574 |
},
|
| 1575 |
"UD": {
|
| 1576 |
"accuracy": 0.0,
|
| 1577 |
-
"count":
|
| 1578 |
}
|
| 1579 |
}
|
| 1580 |
},
|
| 1581 |
"sub_random": {
|
| 1582 |
"full_accuracy": 0.0,
|
| 1583 |
-
"digit_accuracy": 0.
|
| 1584 |
"n_examples": 200,
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
| 1587 |
-
"accuracy": 0.
|
| 1588 |
-
"count":
|
| 1589 |
},
|
| 1590 |
"MB": {
|
| 1591 |
-
"accuracy": 0.
|
| 1592 |
-
"count":
|
| 1593 |
},
|
| 1594 |
"ME": {
|
| 1595 |
-
"accuracy":
|
| 1596 |
"count": 53
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
-
"accuracy": 0.
|
| 1600 |
-
"count":
|
| 1601 |
},
|
| 1602 |
"UD": {
|
| 1603 |
-
"accuracy": 0.
|
| 1604 |
-
"count":
|
| 1605 |
}
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_B3": {
|
| 1609 |
"full_accuracy": 0.0,
|
| 1610 |
-
"digit_accuracy": 0.
|
| 1611 |
-
"n_examples":
|
| 1612 |
"per_subtask": {
|
| 1613 |
"MD": {
|
| 1614 |
-
"accuracy": 0.
|
| 1615 |
-
"count":
|
| 1616 |
},
|
| 1617 |
"MB": {
|
| 1618 |
-
"accuracy": 0.
|
| 1619 |
-
"count":
|
| 1620 |
},
|
| 1621 |
"UB": {
|
| 1622 |
-
"accuracy": 0.
|
| 1623 |
-
"count":
|
| 1624 |
},
|
| 1625 |
"UD": {
|
| 1626 |
"accuracy": 0.0,
|
| 1627 |
-
"count":
|
| 1628 |
}
|
| 1629 |
}
|
| 1630 |
},
|
| 1631 |
"sub_B4": {
|
| 1632 |
"full_accuracy": 0.0,
|
| 1633 |
-
"digit_accuracy": 0.
|
| 1634 |
-
"n_examples":
|
| 1635 |
"per_subtask": {
|
| 1636 |
"MD": {
|
| 1637 |
-
"accuracy": 0.
|
| 1638 |
-
"count":
|
| 1639 |
},
|
| 1640 |
"MB": {
|
| 1641 |
-
"accuracy": 0.
|
| 1642 |
-
"count":
|
| 1643 |
},
|
| 1644 |
"UB": {
|
| 1645 |
-
"accuracy": 0.
|
| 1646 |
-
"count":
|
| 1647 |
},
|
| 1648 |
"UD": {
|
| 1649 |
"accuracy": 0.0,
|
| 1650 |
-
"count":
|
| 1651 |
}
|
| 1652 |
}
|
| 1653 |
},
|
| 1654 |
"sub_B5": {
|
| 1655 |
"full_accuracy": 0.0,
|
| 1656 |
-
"digit_accuracy": 0.
|
| 1657 |
-
"n_examples":
|
| 1658 |
"per_subtask": {
|
| 1659 |
"MD": {
|
| 1660 |
"accuracy": 1.0,
|
| 1661 |
-
"count":
|
| 1662 |
},
|
| 1663 |
"MB": {
|
| 1664 |
-
"accuracy": 0.
|
| 1665 |
-
"count":
|
| 1666 |
},
|
| 1667 |
"UB": {
|
| 1668 |
-
"accuracy": 0.
|
| 1669 |
-
"count":
|
| 1670 |
},
|
| 1671 |
"UD": {
|
| 1672 |
"accuracy": 0.0,
|
| 1673 |
-
"count":
|
| 1674 |
}
|
| 1675 |
}
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"summary": {
|
| 1679 |
-
"overall_accuracy": 0.
|
| 1680 |
-
"digit_accuracy": 0.
|
| 1681 |
-
"total_examples":
|
| 1682 |
"n_splits": 24
|
| 1683 |
}
|
| 1684 |
},
|
| 1685 |
-
"sorl_overall_accuracy": 0.
|
| 1686 |
-
"sft_overall_accuracy": 0.
|
| 1687 |
}
|
|
|
|
| 63 |
3133
|
| 64 |
],
|
| 65 |
"loss": [
|
| 66 |
+
11.08719539642334,
|
| 67 |
+
9.882888793945312,
|
| 68 |
+
11.4771728515625,
|
| 69 |
+
13.394209861755371,
|
| 70 |
+
12.636463165283203,
|
| 71 |
+
11.754125595092773,
|
| 72 |
+
10.885461807250977,
|
| 73 |
+
9.980756759643555,
|
| 74 |
+
9.17142391204834,
|
| 75 |
+
8.430733680725098,
|
| 76 |
+
7.6542534828186035,
|
| 77 |
+
7.293120384216309,
|
| 78 |
+
6.862236499786377,
|
| 79 |
+
6.354031562805176,
|
| 80 |
+
6.001899719238281,
|
| 81 |
+
5.606424331665039,
|
| 82 |
+
5.264089584350586,
|
| 83 |
+
4.9789347648620605,
|
| 84 |
+
4.6479172706604,
|
| 85 |
+
4.434387683868408,
|
| 86 |
+
4.143214225769043,
|
| 87 |
+
3.9974446296691895,
|
| 88 |
+
3.7414889335632324,
|
| 89 |
+
3.581064224243164,
|
| 90 |
+
3.542850971221924,
|
| 91 |
+
3.4644646644592285,
|
| 92 |
+
3.242861270904541,
|
| 93 |
+
3.382519245147705,
|
| 94 |
+
3.218432903289795,
|
| 95 |
+
3.201049327850342,
|
| 96 |
+
2.9937853813171387,
|
| 97 |
+
3.0674819946289062,
|
| 98 |
+
3.1582376956939697,
|
| 99 |
+
3.025876522064209,
|
| 100 |
+
3.013111114501953,
|
| 101 |
+
2.821368932723999,
|
| 102 |
+
2.875208854675293,
|
| 103 |
+
2.663424253463745,
|
| 104 |
+
2.536762237548828,
|
| 105 |
+
2.6094765663146973,
|
| 106 |
+
2.504122734069824,
|
| 107 |
+
2.469931125640869,
|
| 108 |
+
2.3832502365112305,
|
| 109 |
+
2.1861073970794678,
|
| 110 |
+
1.937701940536499,
|
| 111 |
+
1.7912967205047607,
|
| 112 |
+
1.3576332330703735,
|
| 113 |
+
1.3698662519454956,
|
| 114 |
+
1.4696470499038696,
|
| 115 |
+
1.02448308467865,
|
| 116 |
+
0.7232930660247803,
|
| 117 |
+
0.8976768255233765,
|
| 118 |
+
0.8781657814979553,
|
| 119 |
+
0.36818739771842957,
|
| 120 |
+
0.5743820667266846,
|
| 121 |
+
0.18251502513885498,
|
| 122 |
+
0.3461122512817383,
|
| 123 |
+
0.08204305171966553,
|
| 124 |
+
0.28174304962158203,
|
| 125 |
+
0.3735370934009552
|
| 126 |
],
|
| 127 |
"base_loss": [
|
| 128 |
+
11.855416297912598,
|
| 129 |
+
11.582043647766113,
|
| 130 |
+
10.906392097473145,
|
| 131 |
+
10.266691207885742,
|
| 132 |
+
9.720009803771973,
|
| 133 |
+
9.272294998168945,
|
| 134 |
+
8.666574478149414,
|
| 135 |
+
8.154210090637207,
|
| 136 |
+
7.616458415985107,
|
| 137 |
+
6.998318195343018,
|
| 138 |
+
6.393656253814697,
|
| 139 |
+
6.0761284828186035,
|
| 140 |
+
5.678290367126465,
|
| 141 |
+
5.230454444885254,
|
| 142 |
+
4.891925811767578,
|
| 143 |
+
4.48134708404541,
|
| 144 |
+
4.189845085144043,
|
| 145 |
+
3.902498245239258,
|
| 146 |
+
3.601158618927002,
|
| 147 |
+
3.3346099853515625,
|
| 148 |
+
3.106675386428833,
|
| 149 |
+
2.981271266937256,
|
| 150 |
+
2.795375347137451,
|
| 151 |
+
2.646695375442505,
|
| 152 |
+
2.5778772830963135,
|
| 153 |
+
2.52484393119812,
|
| 154 |
+
2.3839688301086426,
|
| 155 |
+
2.4521782398223877,
|
| 156 |
+
2.3377792835235596,
|
| 157 |
+
2.3254542350769043,
|
| 158 |
+
2.270014524459839,
|
| 159 |
+
2.2316880226135254,
|
| 160 |
+
2.2519335746765137,
|
| 161 |
+
2.232677698135376,
|
| 162 |
+
2.2708544731140137,
|
| 163 |
+
2.127883195877075,
|
| 164 |
+
2.219191312789917,
|
| 165 |
+
2.1732959747314453,
|
| 166 |
+
2.038266658782959,
|
| 167 |
+
2.107933282852173,
|
| 168 |
+
2.0626580715179443,
|
| 169 |
+
2.143627166748047,
|
| 170 |
+
2.118760585784912,
|
| 171 |
+
2.1483101844787598,
|
| 172 |
+
2.1393425464630127,
|
| 173 |
+
2.1049411296844482,
|
| 174 |
+
2.007964849472046,
|
| 175 |
+
2.0863873958587646,
|
| 176 |
+
2.121614933013916,
|
| 177 |
+
2.1018025875091553,
|
| 178 |
+
2.010502338409424,
|
| 179 |
+
2.0667836666107178,
|
| 180 |
+
2.0408687591552734,
|
| 181 |
+
2.058290958404541,
|
| 182 |
+
2.1121718883514404,
|
| 183 |
+
2.0361921787261963,
|
| 184 |
+
2.0869758129119873,
|
| 185 |
+
2.087939977645874,
|
| 186 |
+
2.131622076034546,
|
| 187 |
+
2.101810932159424
|
| 188 |
],
|
| 189 |
"info_loss": [
|
| 190 |
+
-0.8031711578369141,
|
| 191 |
+
-0.8466024398803711,
|
| 192 |
+
-0.5249614715576172,
|
| 193 |
+
-0.14881229400634766,
|
| 194 |
+
-0.07111930847167969,
|
| 195 |
+
-0.04557037353515625,
|
| 196 |
+
-0.018856048583984375,
|
| 197 |
+
-0.018548965454101562,
|
| 198 |
+
-0.01670694351196289,
|
| 199 |
+
-0.008439064025878906,
|
| 200 |
+
-0.014551639556884766,
|
| 201 |
+
-0.012627601623535156,
|
| 202 |
+
-0.011160850524902344,
|
| 203 |
+
-0.013494491577148438,
|
| 204 |
+
-0.012564659118652344,
|
| 205 |
+
-0.009298324584960938,
|
| 206 |
+
-0.012515544891357422,
|
| 207 |
+
-0.011241912841796875,
|
| 208 |
+
-0.013210296630859375,
|
| 209 |
+
-0.007313251495361328,
|
| 210 |
+
-0.012842655181884766,
|
| 211 |
+
-0.013678312301635742,
|
| 212 |
+
-0.02021336555480957,
|
| 213 |
+
-0.02120494842529297,
|
| 214 |
+
-0.01790618896484375,
|
| 215 |
+
-0.019744157791137695,
|
| 216 |
+
-0.028128623962402344,
|
| 217 |
+
-0.020328998565673828,
|
| 218 |
+
-0.025052547454833984,
|
| 219 |
+
-0.025846242904663086,
|
| 220 |
+
-0.0404818058013916,
|
| 221 |
+
-0.02934575080871582,
|
| 222 |
+
-0.022233009338378906,
|
| 223 |
+
-0.03363370895385742,
|
| 224 |
+
-0.038091421127319336,
|
| 225 |
+
-0.0435643196105957,
|
| 226 |
+
-0.04671955108642578,
|
| 227 |
+
-0.06309247016906738,
|
| 228 |
+
-0.06224644184112549,
|
| 229 |
+
-0.06188392639160156,
|
| 230 |
+
-0.06756675243377686,
|
| 231 |
+
-0.07924365997314453,
|
| 232 |
+
-0.08580851554870605,
|
| 233 |
+
-0.10824298858642578,
|
| 234 |
+
-0.1323099136352539,
|
| 235 |
+
-0.14376580715179443,
|
| 236 |
+
-0.17741644382476807,
|
| 237 |
+
-0.18436694145202637,
|
| 238 |
+
-0.17743921279907227,
|
| 239 |
+
-0.22029244899749756,
|
| 240 |
+
-0.24071002006530762,
|
| 241 |
+
-0.22940337657928467,
|
| 242 |
+
-0.2283191680908203,
|
| 243 |
+
-0.2808573246002197,
|
| 244 |
+
-0.26602745056152344,
|
| 245 |
+
-0.29790258407592773,
|
| 246 |
+
-0.28659355640411377,
|
| 247 |
+
-0.31294679641723633,
|
| 248 |
+
-0.2972530126571655,
|
| 249 |
+
-0.28541290760040283
|
| 250 |
],
|
| 251 |
"abs_loss": [
|
| 252 |
+
3.39985728263855,
|
| 253 |
+
3.386993646621704,
|
| 254 |
+
3.3492507934570312,
|
| 255 |
+
3.2870309352874756,
|
| 256 |
+
3.2153663635253906,
|
| 257 |
+
3.1640560626983643,
|
| 258 |
+
3.0829689502716064,
|
| 259 |
+
2.9905052185058594,
|
| 260 |
+
2.8724257946014404,
|
| 261 |
+
2.830716848373413,
|
| 262 |
+
2.7724239826202393,
|
| 263 |
+
2.7584240436553955,
|
| 264 |
+
2.753511667251587,
|
| 265 |
+
2.706627130508423,
|
| 266 |
+
2.728182554244995,
|
| 267 |
+
2.7566611766815186,
|
| 268 |
+
2.7176859378814697,
|
| 269 |
+
2.729097604751587,
|
| 270 |
+
2.7399768829345703,
|
| 271 |
+
2.7603671550750732,
|
| 272 |
+
2.7478103637695312,
|
| 273 |
+
2.6929080486297607,
|
| 274 |
+
2.698748826980591,
|
| 275 |
+
2.7124502658843994,
|
| 276 |
+
2.729304075241089,
|
| 277 |
+
2.687528610229492,
|
| 278 |
+
2.7349331378936768,
|
| 279 |
+
2.7035627365112305,
|
| 280 |
+
2.699801445007324,
|
| 281 |
+
2.7429096698760986,
|
| 282 |
+
2.7024919986724854,
|
| 283 |
+
2.7189064025878906,
|
| 284 |
+
2.72162127494812,
|
| 285 |
+
2.742133140563965,
|
| 286 |
+
2.687856674194336,
|
| 287 |
+
2.7535006999969482,
|
| 288 |
+
2.7046287059783936,
|
| 289 |
+
2.689242362976074,
|
| 290 |
+
2.695612668991089,
|
| 291 |
+
2.6956450939178467,
|
| 292 |
+
2.6737430095672607,
|
| 293 |
+
2.688300371170044,
|
| 294 |
+
2.730506181716919,
|
| 295 |
+
2.705724000930786,
|
| 296 |
+
2.7161991596221924,
|
| 297 |
+
2.7383010387420654,
|
| 298 |
+
2.731405019760132,
|
| 299 |
+
2.762179136276245,
|
| 300 |
+
2.7152442932128906,
|
| 301 |
+
2.7449119091033936,
|
| 302 |
+
2.6875953674316406,
|
| 303 |
+
2.7378857135772705,
|
| 304 |
+
2.691694974899292,
|
| 305 |
+
2.6705048084259033,
|
| 306 |
+
2.7100117206573486,
|
| 307 |
+
2.737171173095703,
|
| 308 |
+
2.7343177795410156,
|
| 309 |
+
2.7189133167266846,
|
| 310 |
+
2.710089921951294,
|
| 311 |
+
2.7421464920043945
|
| 312 |
],
|
| 313 |
"zipf_loss": [
|
| 314 |
+
6.923504829406738,
|
| 315 |
+
6.428170680999756,
|
| 316 |
+
5.485470294952393,
|
| 317 |
+
4.286938667297363,
|
| 318 |
+
3.3061094284057617,
|
| 319 |
+
2.621128797531128,
|
| 320 |
+
2.099151134490967,
|
| 321 |
+
1.7129861116409302,
|
| 322 |
+
1.4347922801971436,
|
| 323 |
+
1.2337348461151123,
|
| 324 |
+
1.1288714408874512,
|
| 325 |
+
1.0674259662628174,
|
| 326 |
+
1.0202035903930664,
|
| 327 |
+
0.9878593683242798,
|
| 328 |
+
0.9628022909164429,
|
| 329 |
+
0.9423943758010864,
|
| 330 |
+
0.9276311993598938,
|
| 331 |
+
0.9159458875656128,
|
| 332 |
+
0.9048639535903931,
|
| 333 |
+
0.896873414516449,
|
| 334 |
+
0.8901845216751099,
|
| 335 |
+
0.8836656212806702,
|
| 336 |
+
0.8783724308013916,
|
| 337 |
+
0.8751733303070068,
|
| 338 |
+
0.8711051344871521,
|
| 339 |
+
0.8683096170425415,
|
| 340 |
+
0.8666852712631226,
|
| 341 |
+
0.8632747530937195,
|
| 342 |
+
0.861198902130127,
|
| 343 |
+
0.8597666025161743,
|
| 344 |
+
0.8583396673202515,
|
| 345 |
+
0.8573608994483948,
|
| 346 |
+
0.8564719557762146,
|
| 347 |
+
0.8553227186203003,
|
| 348 |
+
0.8543850183486938,
|
| 349 |
+
0.8537788987159729,
|
| 350 |
+
0.8527502417564392,
|
| 351 |
+
0.8521287441253662,
|
| 352 |
+
0.8513987064361572,
|
| 353 |
+
0.8508179187774658,
|
| 354 |
+
0.8497580289840698,
|
| 355 |
+
0.8499106168746948,
|
| 356 |
+
0.8495240807533264,
|
| 357 |
+
0.8496546745300293,
|
| 358 |
+
0.8498386144638062,
|
| 359 |
+
0.8501836061477661,
|
| 360 |
+
0.8506922721862793,
|
| 361 |
+
0.8509303331375122,
|
| 362 |
+
0.8508998155593872,
|
| 363 |
+
0.8511137962341309,
|
| 364 |
+
0.8511313796043396,
|
| 365 |
+
0.8511383533477783,
|
| 366 |
+
0.8513191938400269,
|
| 367 |
+
0.85141921043396,
|
| 368 |
+
0.8514835238456726,
|
| 369 |
+
0.8516315221786499,
|
| 370 |
+
0.8516402244567871,
|
| 371 |
+
0.8516796827316284,
|
| 372 |
+
0.8516421318054199,
|
| 373 |
+
0.8516405820846558
|
| 374 |
],
|
| 375 |
"denoise_loss": [],
|
| 376 |
"ortho_loss": [
|
| 377 |
+
0.6979529857635498,
|
| 378 |
+
0.6298285126686096,
|
| 379 |
+
0.4650823473930359,
|
| 380 |
+
0.36667466163635254,
|
| 381 |
+
0.32546141743659973,
|
| 382 |
+
0.2925472557544708,
|
| 383 |
+
0.31016528606414795,
|
| 384 |
+
0.35216864943504333,
|
| 385 |
+
0.35810449719429016,
|
| 386 |
+
0.3601681888103485,
|
| 387 |
+
0.363854318857193,
|
| 388 |
+
0.3894629180431366,
|
| 389 |
+
0.4043414294719696,
|
| 390 |
+
0.4201587736606598,
|
| 391 |
+
0.4274826645851135,
|
| 392 |
+
0.4372390806674957,
|
| 393 |
+
0.43081748485565186,
|
| 394 |
+
0.42623206973075867,
|
| 395 |
+
0.421860009431839,
|
| 396 |
+
0.42481598258018494,
|
| 397 |
+
0.41381338238716125,
|
| 398 |
+
0.4135570526123047,
|
| 399 |
+
0.41264602541923523,
|
| 400 |
+
0.39332830905914307,
|
| 401 |
+
0.4006246030330658,
|
| 402 |
+
0.39508968591690063,
|
| 403 |
+
0.38602590560913086,
|
| 404 |
+
0.3827188014984131,
|
| 405 |
+
0.3881952464580536,
|
| 406 |
+
0.394728422164917,
|
| 407 |
+
0.39518600702285767,
|
| 408 |
+
0.3969350755214691,
|
| 409 |
+
0.39978182315826416,
|
| 410 |
+
0.4028274714946747,
|
| 411 |
+
0.41307270526885986,
|
| 412 |
+
0.4215640425682068,
|
| 413 |
+
0.4269300401210785,
|
| 414 |
+
0.42162781953811646,
|
| 415 |
+
0.4252450466156006,
|
| 416 |
+
0.44025519490242004,
|
| 417 |
+
0.4450463354587555,
|
| 418 |
+
0.4435034692287445,
|
| 419 |
+
0.4542127251625061,
|
| 420 |
+
0.46466323733329773,
|
| 421 |
+
0.47896111011505127,
|
| 422 |
+
0.4957045316696167,
|
| 423 |
+
0.5050824284553528,
|
| 424 |
+
0.5143278241157532,
|
| 425 |
+
0.5217639207839966,
|
| 426 |
+
0.5282729268074036,
|
| 427 |
+
0.5332797169685364,
|
| 428 |
+
0.5378868579864502,
|
| 429 |
+
0.5416458249092102,
|
| 430 |
+
0.5473858714103699,
|
| 431 |
+
0.5503306984901428,
|
| 432 |
+
0.5527967810630798,
|
| 433 |
+
0.5556142330169678,
|
| 434 |
+
0.5579712390899658,
|
| 435 |
+
0.5602691173553467,
|
| 436 |
+
0.5617437362670898
|
| 437 |
],
|
| 438 |
"lr": [
|
| 439 |
9.800000000000001e-06,
|
|
|
|
| 521 |
3083
|
| 522 |
],
|
| 523 |
"eval_accuracy": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 524 |
0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 525 |
0.02,
|
| 526 |
+
0.02,
|
| 527 |
+
0.02,
|
| 528 |
+
0.02,
|
| 529 |
+
0.02,
|
| 530 |
+
0.02,
|
| 531 |
+
0.02,
|
| 532 |
+
0.02,
|
| 533 |
+
0.02,
|
| 534 |
+
0.02,
|
| 535 |
+
0.02,
|
| 536 |
+
0.02,
|
| 537 |
+
0.02,
|
| 538 |
+
0.02,
|
| 539 |
+
0.02,
|
| 540 |
+
0.02,
|
| 541 |
+
0.02,
|
| 542 |
+
0.02,
|
| 543 |
+
0.02
|
| 544 |
]
|
| 545 |
},
|
| 546 |
+
"final_accuracy": 0.001153846153846154,
|
| 547 |
"sft_eval": {
|
| 548 |
"config": {
|
| 549 |
"ops": "add_sub",
|
| 550 |
"K": null,
|
| 551 |
"mode": "sft",
|
| 552 |
"n_digits": 6,
|
| 553 |
+
"n_per_split": 100
|
| 554 |
},
|
| 555 |
"splits": {
|
| 556 |
"add_S0": {
|
| 557 |
"full_accuracy": 0.0,
|
| 558 |
+
"digit_accuracy": 0.2642857142857143,
|
| 559 |
+
"n_examples": 100,
|
| 560 |
"per_subtask": {
|
| 561 |
"SA": {
|
| 562 |
+
"accuracy": 0.19669421487603306,
|
| 563 |
+
"count": 605
|
| 564 |
},
|
| 565 |
"SS": {
|
| 566 |
+
"accuracy": 0.6947368421052632,
|
| 567 |
+
"count": 95
|
| 568 |
}
|
| 569 |
}
|
| 570 |
},
|
| 571 |
"add_S1": {
|
| 572 |
"full_accuracy": 0.0,
|
| 573 |
+
"digit_accuracy": 0.15571428571428572,
|
| 574 |
+
"n_examples": 100,
|
| 575 |
"per_subtask": {
|
| 576 |
"SA": {
|
| 577 |
+
"accuracy": 0.22549019607843138,
|
| 578 |
+
"count": 204
|
| 579 |
},
|
| 580 |
"SC": {
|
| 581 |
+
"accuracy": 0.1301775147928994,
|
| 582 |
+
"count": 169
|
| 583 |
},
|
| 584 |
"SS": {
|
| 585 |
+
"accuracy": 0.5161290322580645,
|
| 586 |
+
"count": 31
|
| 587 |
},
|
| 588 |
"UC": {
|
| 589 |
+
"accuracy": 0.08445945945945946,
|
| 590 |
+
"count": 296
|
| 591 |
}
|
| 592 |
}
|
| 593 |
},
|
| 594 |
"add_S2": {
|
| 595 |
"full_accuracy": 0.0,
|
| 596 |
+
"digit_accuracy": 0.29285714285714287,
|
| 597 |
+
"n_examples": 100,
|
| 598 |
"per_subtask": {
|
| 599 |
"SA": {
|
| 600 |
+
"accuracy": 0.32515337423312884,
|
| 601 |
+
"count": 163
|
| 602 |
},
|
| 603 |
"SC": {
|
| 604 |
+
"accuracy": 0.13076923076923078,
|
| 605 |
+
"count": 130
|
| 606 |
},
|
| 607 |
"SS": {
|
| 608 |
+
"accuracy": 0.47126436781609193,
|
| 609 |
+
"count": 87
|
| 610 |
},
|
| 611 |
"UC": {
|
| 612 |
+
"accuracy": 0.12315270935960591,
|
| 613 |
+
"count": 203
|
| 614 |
},
|
| 615 |
"US": {
|
| 616 |
+
"accuracy": 0.5897435897435898,
|
| 617 |
+
"count": 117
|
| 618 |
}
|
| 619 |
}
|
| 620 |
},
|
| 621 |
"add_S3": {
|
| 622 |
"full_accuracy": 0.0,
|
| 623 |
+
"digit_accuracy": 0.31857142857142856,
|
| 624 |
+
"n_examples": 100,
|
| 625 |
"per_subtask": {
|
| 626 |
"SA": {
|
| 627 |
+
"accuracy": 0.36363636363636365,
|
| 628 |
+
"count": 121
|
| 629 |
},
|
| 630 |
"SC": {
|
| 631 |
+
"accuracy": 0.10743801652892562,
|
| 632 |
+
"count": 121
|
| 633 |
},
|
| 634 |
"SS": {
|
| 635 |
+
"accuracy": 0.40816326530612246,
|
| 636 |
+
"count": 49
|
| 637 |
},
|
| 638 |
"UC": {
|
| 639 |
+
"accuracy": 0.14516129032258066,
|
| 640 |
+
"count": 186
|
| 641 |
},
|
| 642 |
"US": {
|
| 643 |
+
"accuracy": 0.5336322869955157,
|
| 644 |
+
"count": 223
|
| 645 |
}
|
| 646 |
}
|
| 647 |
},
|
| 648 |
"add_S4": {
|
| 649 |
"full_accuracy": 0.0,
|
| 650 |
+
"digit_accuracy": 0.3242857142857143,
|
| 651 |
+
"n_examples": 100,
|
| 652 |
"per_subtask": {
|
| 653 |
"SA": {
|
| 654 |
+
"accuracy": 0.41346153846153844,
|
| 655 |
+
"count": 104
|
| 656 |
},
|
| 657 |
"SC": {
|
| 658 |
+
"accuracy": 0.11320754716981132,
|
| 659 |
+
"count": 106
|
| 660 |
},
|
| 661 |
"SS": {
|
| 662 |
+
"accuracy": 0.5217391304347826,
|
| 663 |
+
"count": 23
|
| 664 |
},
|
| 665 |
"UC": {
|
| 666 |
+
"accuracy": 0.15625,
|
| 667 |
+
"count": 160
|
| 668 |
},
|
| 669 |
"US": {
|
| 670 |
+
"accuracy": 0.43973941368078173,
|
| 671 |
+
"count": 307
|
| 672 |
}
|
| 673 |
}
|
| 674 |
},
|
| 675 |
"add_S5": {
|
| 676 |
"full_accuracy": 0.0,
|
| 677 |
+
"digit_accuracy": 0.37142857142857144,
|
| 678 |
+
"n_examples": 100,
|
| 679 |
"per_subtask": {
|
| 680 |
"SA": {
|
| 681 |
+
"accuracy": 0.42,
|
| 682 |
+
"count": 100
|
| 683 |
},
|
| 684 |
"SC": {
|
| 685 |
+
"accuracy": 0.15,
|
| 686 |
+
"count": 100
|
| 687 |
},
|
| 688 |
"UC": {
|
| 689 |
"accuracy": 0.12,
|
| 690 |
+
"count": 100
|
| 691 |
},
|
| 692 |
"US": {
|
| 693 |
+
"accuracy": 0.4775,
|
| 694 |
+
"count": 400
|
| 695 |
}
|
| 696 |
}
|
| 697 |
},
|
| 698 |
"add_S6": {
|
| 699 |
+
"full_accuracy": 0.05,
|
| 700 |
+
"digit_accuracy": 0.37857142857142856,
|
| 701 |
+
"n_examples": 100,
|
| 702 |
"per_subtask": {
|
| 703 |
"SC": {
|
| 704 |
+
"accuracy": 0.09,
|
| 705 |
+
"count": 100
|
| 706 |
},
|
| 707 |
"UC": {
|
| 708 |
+
"accuracy": 0.21,
|
| 709 |
+
"count": 100
|
| 710 |
},
|
| 711 |
"US": {
|
| 712 |
+
"accuracy": 0.47,
|
| 713 |
+
"count": 500
|
| 714 |
}
|
| 715 |
}
|
| 716 |
},
|
| 717 |
"add_random": {
|
| 718 |
"full_accuracy": 0.0,
|
| 719 |
+
"digit_accuracy": 0.1692857142857143,
|
| 720 |
"n_examples": 200,
|
| 721 |
"per_subtask": {
|
| 722 |
"SA": {
|
| 723 |
+
"accuracy": 0.24161073825503357,
|
| 724 |
+
"count": 447
|
| 725 |
},
|
| 726 |
"SC": {
|
| 727 |
+
"accuracy": 0.096875,
|
| 728 |
+
"count": 320
|
| 729 |
},
|
| 730 |
"SS": {
|
| 731 |
+
"accuracy": 0.625,
|
| 732 |
+
"count": 56
|
| 733 |
},
|
| 734 |
"UC": {
|
| 735 |
+
"accuracy": 0.0888468809073724,
|
| 736 |
+
"count": 529
|
| 737 |
},
|
| 738 |
"US": {
|
| 739 |
+
"accuracy": 0.3333333333333333,
|
| 740 |
+
"count": 48
|
| 741 |
}
|
| 742 |
}
|
| 743 |
},
|
| 744 |
"add_C1": {
|
| 745 |
"full_accuracy": 0.0,
|
| 746 |
+
"digit_accuracy": 0.13285714285714287,
|
| 747 |
+
"n_examples": 100,
|
| 748 |
"per_subtask": {
|
| 749 |
"SA": {
|
| 750 |
+
"accuracy": 0.178,
|
| 751 |
+
"count": 500
|
| 752 |
},
|
| 753 |
"SC": {
|
| 754 |
+
"accuracy": 0.04,
|
| 755 |
+
"count": 100
|
| 756 |
},
|
| 757 |
"UC": {
|
| 758 |
"accuracy": 0.0,
|
| 759 |
+
"count": 100
|
| 760 |
}
|
| 761 |
}
|
| 762 |
},
|
| 763 |
"add_C2": {
|
| 764 |
"full_accuracy": 0.0,
|
| 765 |
+
"digit_accuracy": 0.16,
|
| 766 |
+
"n_examples": 100,
|
| 767 |
"per_subtask": {
|
| 768 |
"SA": {
|
| 769 |
+
"accuracy": 0.22,
|
| 770 |
+
"count": 400
|
| 771 |
},
|
| 772 |
"SC": {
|
| 773 |
+
"accuracy": 0.07,
|
| 774 |
+
"count": 100
|
| 775 |
},
|
| 776 |
"UC": {
|
| 777 |
+
"accuracy": 0.02564102564102564,
|
| 778 |
+
"count": 156
|
| 779 |
},
|
| 780 |
"US": {
|
| 781 |
+
"accuracy": 0.29545454545454547,
|
| 782 |
+
"count": 44
|
| 783 |
}
|
| 784 |
}
|
| 785 |
},
|
| 786 |
"add_C3": {
|
| 787 |
"full_accuracy": 0.0,
|
| 788 |
+
"digit_accuracy": 0.17142857142857143,
|
| 789 |
+
"n_examples": 100,
|
| 790 |
"per_subtask": {
|
| 791 |
"SA": {
|
| 792 |
+
"accuracy": 0.24333333333333335,
|
| 793 |
+
"count": 300
|
| 794 |
},
|
| 795 |
"SC": {
|
| 796 |
+
"accuracy": 0.06,
|
| 797 |
+
"count": 100
|
| 798 |
},
|
| 799 |
"UC": {
|
| 800 |
+
"accuracy": 0.04020100502512563,
|
| 801 |
+
"count": 199
|
| 802 |
},
|
| 803 |
"US": {
|
| 804 |
+
"accuracy": 0.32673267326732675,
|
| 805 |
+
"count": 101
|
| 806 |
}
|
| 807 |
}
|
| 808 |
},
|
| 809 |
"add_C4": {
|
| 810 |
"full_accuracy": 0.0,
|
| 811 |
+
"digit_accuracy": 0.19285714285714287,
|
| 812 |
+
"n_examples": 100,
|
| 813 |
"per_subtask": {
|
| 814 |
"SA": {
|
| 815 |
+
"accuracy": 0.32,
|
| 816 |
+
"count": 200
|
| 817 |
},
|
| 818 |
"SC": {
|
| 819 |
+
"accuracy": 0.11,
|
| 820 |
+
"count": 100
|
| 821 |
},
|
| 822 |
"UC": {
|
| 823 |
+
"accuracy": 0.03409090909090909,
|
| 824 |
+
"count": 264
|
| 825 |
},
|
| 826 |
"US": {
|
| 827 |
+
"accuracy": 0.375,
|
| 828 |
+
"count": 136
|
| 829 |
}
|
| 830 |
}
|
| 831 |
},
|
| 832 |
"add_C5": {
|
| 833 |
"full_accuracy": 0.0,
|
| 834 |
+
"digit_accuracy": 0.26571428571428574,
|
| 835 |
+
"n_examples": 100,
|
| 836 |
"per_subtask": {
|
| 837 |
"SA": {
|
| 838 |
+
"accuracy": 0.49,
|
| 839 |
+
"count": 100
|
| 840 |
},
|
| 841 |
"SC": {
|
| 842 |
+
"accuracy": 0.11,
|
| 843 |
+
"count": 100
|
| 844 |
},
|
| 845 |
"UC": {
|
| 846 |
+
"accuracy": 0.05806451612903226,
|
| 847 |
+
"count": 310
|
| 848 |
},
|
| 849 |
"US": {
|
| 850 |
+
"accuracy": 0.5684210526315789,
|
| 851 |
+
"count": 190
|
| 852 |
}
|
| 853 |
}
|
| 854 |
},
|
| 855 |
"add_C6": {
|
| 856 |
"full_accuracy": 0.0,
|
| 857 |
+
"digit_accuracy": 0.24142857142857144,
|
| 858 |
+
"n_examples": 100,
|
| 859 |
"per_subtask": {
|
| 860 |
"SC": {
|
| 861 |
+
"accuracy": 0.11,
|
| 862 |
+
"count": 100
|
| 863 |
},
|
| 864 |
"UC": {
|
| 865 |
+
"accuracy": 0.0891891891891892,
|
| 866 |
+
"count": 370
|
| 867 |
},
|
| 868 |
"US": {
|
| 869 |
+
"accuracy": 0.5434782608695652,
|
| 870 |
+
"count": 230
|
| 871 |
}
|
| 872 |
}
|
| 873 |
},
|
| 874 |
"sub_M0": {
|
| 875 |
"full_accuracy": 0.0,
|
| 876 |
+
"digit_accuracy": 0.29285714285714287,
|
| 877 |
+
"n_examples": 100,
|
| 878 |
"per_subtask": {
|
| 879 |
"MD": {
|
| 880 |
+
"accuracy": 0.1951219512195122,
|
| 881 |
+
"count": 615
|
| 882 |
},
|
| 883 |
"ME": {
|
| 884 |
"accuracy": 1.0,
|
| 885 |
+
"count": 85
|
| 886 |
}
|
| 887 |
}
|
| 888 |
},
|
| 889 |
"sub_M1": {
|
| 890 |
"full_accuracy": 0.0,
|
| 891 |
+
"digit_accuracy": 0.22428571428571428,
|
| 892 |
+
"n_examples": 100,
|
| 893 |
"per_subtask": {
|
| 894 |
"MD": {
|
| 895 |
+
"accuracy": 0.3698630136986301,
|
| 896 |
+
"count": 292
|
| 897 |
},
|
| 898 |
"MB": {
|
| 899 |
"accuracy": 0.0,
|
| 900 |
+
"count": 144
|
| 901 |
},
|
| 902 |
"ME": {
|
| 903 |
"accuracy": 1.0,
|
| 904 |
+
"count": 25
|
| 905 |
},
|
| 906 |
"UB": {
|
| 907 |
+
"accuracy": 0.100418410041841,
|
| 908 |
+
"count": 239
|
| 909 |
}
|
| 910 |
}
|
| 911 |
},
|
| 912 |
"sub_M2": {
|
| 913 |
"full_accuracy": 0.0,
|
| 914 |
+
"digit_accuracy": 0.35428571428571426,
|
| 915 |
+
"n_examples": 100,
|
| 916 |
"per_subtask": {
|
| 917 |
"MD": {
|
| 918 |
+
"accuracy": 0.6208530805687204,
|
| 919 |
+
"count": 211
|
| 920 |
},
|
| 921 |
"MB": {
|
| 922 |
"accuracy": 0.0,
|
| 923 |
+
"count": 115
|
| 924 |
},
|
| 925 |
"ME": {
|
| 926 |
"accuracy": 1.0,
|
| 927 |
+
"count": 85
|
| 928 |
},
|
| 929 |
"UB": {
|
| 930 |
+
"accuracy": 0.17679558011049723,
|
| 931 |
+
"count": 181
|
| 932 |
},
|
| 933 |
"UD": {
|
| 934 |
"accuracy": 0.0,
|
| 935 |
+
"count": 108
|
| 936 |
}
|
| 937 |
}
|
| 938 |
},
|
| 939 |
"sub_M3": {
|
| 940 |
"full_accuracy": 0.0,
|
| 941 |
+
"digit_accuracy": 0.3,
|
| 942 |
+
"n_examples": 100,
|
| 943 |
"per_subtask": {
|
| 944 |
"MD": {
|
| 945 |
+
"accuracy": 0.7597765363128491,
|
| 946 |
+
"count": 179
|
| 947 |
},
|
| 948 |
"MB": {
|
| 949 |
"accuracy": 0.0,
|
| 950 |
+
"count": 103
|
| 951 |
},
|
| 952 |
"ME": {
|
| 953 |
"accuracy": 1.0,
|
| 954 |
+
"count": 56
|
| 955 |
},
|
| 956 |
"UB": {
|
| 957 |
+
"accuracy": 0.12080536912751678,
|
| 958 |
+
"count": 149
|
| 959 |
},
|
| 960 |
"UD": {
|
| 961 |
"accuracy": 0.0,
|
| 962 |
+
"count": 213
|
| 963 |
}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
"sub_M4": {
|
| 967 |
"full_accuracy": 0.0,
|
| 968 |
+
"digit_accuracy": 0.18571428571428572,
|
| 969 |
+
"n_examples": 100,
|
| 970 |
"per_subtask": {
|
| 971 |
"MD": {
|
| 972 |
"accuracy": 0.5,
|
| 973 |
+
"count": 200
|
| 974 |
},
|
| 975 |
"MB": {
|
| 976 |
"accuracy": 0.0,
|
| 977 |
+
"count": 100
|
| 978 |
},
|
| 979 |
"UB": {
|
| 980 |
+
"accuracy": 0.3,
|
| 981 |
+
"count": 100
|
| 982 |
},
|
| 983 |
"UD": {
|
| 984 |
"accuracy": 0.0,
|
| 985 |
+
"count": 300
|
| 986 |
}
|
| 987 |
}
|
| 988 |
},
|
| 989 |
"sub_M5": {
|
| 990 |
"full_accuracy": 0.0,
|
| 991 |
+
"digit_accuracy": 0.18714285714285714,
|
| 992 |
+
"n_examples": 100,
|
| 993 |
"per_subtask": {
|
| 994 |
"MD": {
|
| 995 |
"accuracy": 1.0,
|
| 996 |
+
"count": 100
|
| 997 |
},
|
| 998 |
"MB": {
|
| 999 |
"accuracy": 0.0,
|
| 1000 |
+
"count": 100
|
| 1001 |
},
|
| 1002 |
"UB": {
|
| 1003 |
+
"accuracy": 0.31,
|
| 1004 |
+
"count": 100
|
| 1005 |
},
|
| 1006 |
"UD": {
|
| 1007 |
"accuracy": 0.0,
|
| 1008 |
+
"count": 400
|
| 1009 |
}
|
| 1010 |
}
|
| 1011 |
},
|
|
|
|
| 1015 |
"n_examples": 200,
|
| 1016 |
"per_subtask": {
|
| 1017 |
"MD": {
|
| 1018 |
+
"accuracy": 0.3616666666666667,
|
| 1019 |
+
"count": 600
|
| 1020 |
},
|
| 1021 |
"MB": {
|
| 1022 |
"accuracy": 0.0,
|
| 1023 |
+
"count": 267
|
| 1024 |
},
|
| 1025 |
"ME": {
|
| 1026 |
"accuracy": 1.0,
|
| 1027 |
"count": 53
|
| 1028 |
},
|
| 1029 |
"UB": {
|
| 1030 |
+
"accuracy": 0.12072892938496584,
|
| 1031 |
+
"count": 439
|
| 1032 |
},
|
| 1033 |
"UD": {
|
| 1034 |
"accuracy": 0.0,
|
| 1035 |
+
"count": 41
|
| 1036 |
}
|
| 1037 |
}
|
| 1038 |
},
|
| 1039 |
"sub_B3": {
|
| 1040 |
"full_accuracy": 0.0,
|
| 1041 |
+
"digit_accuracy": 0.19285714285714287,
|
| 1042 |
+
"n_examples": 100,
|
| 1043 |
"per_subtask": {
|
| 1044 |
"MD": {
|
| 1045 |
"accuracy": 0.3333333333333333,
|
| 1046 |
+
"count": 300
|
| 1047 |
},
|
| 1048 |
"MB": {
|
| 1049 |
"accuracy": 0.0,
|
| 1050 |
+
"count": 100
|
| 1051 |
},
|
| 1052 |
"UB": {
|
| 1053 |
+
"accuracy": 0.17766497461928935,
|
| 1054 |
+
"count": 197
|
| 1055 |
},
|
| 1056 |
"UD": {
|
| 1057 |
"accuracy": 0.0,
|
| 1058 |
+
"count": 103
|
| 1059 |
}
|
| 1060 |
}
|
| 1061 |
},
|
| 1062 |
"sub_B4": {
|
| 1063 |
"full_accuracy": 0.0,
|
| 1064 |
+
"digit_accuracy": 0.19428571428571428,
|
| 1065 |
+
"n_examples": 100,
|
| 1066 |
"per_subtask": {
|
| 1067 |
"MD": {
|
| 1068 |
"accuracy": 0.5,
|
| 1069 |
+
"count": 200
|
| 1070 |
},
|
| 1071 |
"MB": {
|
| 1072 |
"accuracy": 0.0,
|
| 1073 |
+
"count": 100
|
| 1074 |
},
|
| 1075 |
"UB": {
|
| 1076 |
+
"accuracy": 0.145748987854251,
|
| 1077 |
+
"count": 247
|
| 1078 |
},
|
| 1079 |
"UD": {
|
| 1080 |
"accuracy": 0.0,
|
| 1081 |
+
"count": 153
|
| 1082 |
}
|
| 1083 |
}
|
| 1084 |
},
|
| 1085 |
"sub_B5": {
|
| 1086 |
"full_accuracy": 0.0,
|
| 1087 |
+
"digit_accuracy": 0.19,
|
| 1088 |
+
"n_examples": 100,
|
| 1089 |
"per_subtask": {
|
| 1090 |
"MD": {
|
| 1091 |
"accuracy": 1.0,
|
| 1092 |
+
"count": 100
|
| 1093 |
},
|
| 1094 |
"MB": {
|
| 1095 |
"accuracy": 0.0,
|
| 1096 |
+
"count": 100
|
| 1097 |
},
|
| 1098 |
"UB": {
|
| 1099 |
+
"accuracy": 0.11073825503355705,
|
| 1100 |
+
"count": 298
|
| 1101 |
},
|
| 1102 |
"UD": {
|
| 1103 |
"accuracy": 0.0,
|
| 1104 |
+
"count": 202
|
| 1105 |
}
|
| 1106 |
}
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"summary": {
|
| 1110 |
+
"overall_accuracy": 0.0019230769230769232,
|
| 1111 |
+
"digit_accuracy": 0.23807692307692307,
|
| 1112 |
+
"total_examples": 2600,
|
| 1113 |
"n_splits": 24
|
| 1114 |
}
|
| 1115 |
},
|
|
|
|
| 1119 |
"K": 1,
|
| 1120 |
"mode": "sorl",
|
| 1121 |
"n_digits": 6,
|
| 1122 |
+
"n_per_split": 100
|
| 1123 |
},
|
| 1124 |
"splits": {
|
| 1125 |
"add_S0": {
|
| 1126 |
"full_accuracy": 0.0,
|
| 1127 |
+
"digit_accuracy": 0.38,
|
| 1128 |
+
"n_examples": 100,
|
| 1129 |
"per_subtask": {
|
| 1130 |
"SA": {
|
| 1131 |
+
"accuracy": 0.3239669421487603,
|
| 1132 |
+
"count": 605
|
| 1133 |
},
|
| 1134 |
"SS": {
|
| 1135 |
+
"accuracy": 0.7368421052631579,
|
| 1136 |
+
"count": 95
|
| 1137 |
}
|
| 1138 |
}
|
| 1139 |
},
|
| 1140 |
"add_S1": {
|
| 1141 |
"full_accuracy": 0.0,
|
| 1142 |
+
"digit_accuracy": 0.31,
|
| 1143 |
+
"n_examples": 100,
|
| 1144 |
"per_subtask": {
|
| 1145 |
"SA": {
|
| 1146 |
+
"accuracy": 0.35294117647058826,
|
| 1147 |
+
"count": 204
|
| 1148 |
},
|
| 1149 |
"SC": {
|
| 1150 |
+
"accuracy": 0.28402366863905326,
|
| 1151 |
+
"count": 169
|
| 1152 |
},
|
| 1153 |
"SS": {
|
| 1154 |
+
"accuracy": 0.4838709677419355,
|
| 1155 |
+
"count": 31
|
| 1156 |
},
|
| 1157 |
"UC": {
|
| 1158 |
+
"accuracy": 0.27702702702702703,
|
| 1159 |
+
"count": 296
|
| 1160 |
}
|
| 1161 |
}
|
| 1162 |
},
|
| 1163 |
"add_S2": {
|
| 1164 |
+
"full_accuracy": 0.01,
|
| 1165 |
+
"digit_accuracy": 0.39,
|
| 1166 |
+
"n_examples": 100,
|
| 1167 |
"per_subtask": {
|
| 1168 |
"SA": {
|
| 1169 |
+
"accuracy": 0.4294478527607362,
|
| 1170 |
+
"count": 163
|
| 1171 |
},
|
| 1172 |
"SC": {
|
| 1173 |
+
"accuracy": 0.34615384615384615,
|
| 1174 |
+
"count": 130
|
| 1175 |
},
|
| 1176 |
"SS": {
|
| 1177 |
+
"accuracy": 0.45977011494252873,
|
| 1178 |
+
"count": 87
|
| 1179 |
},
|
| 1180 |
"UC": {
|
| 1181 |
+
"accuracy": 0.28078817733990147,
|
| 1182 |
+
"count": 203
|
| 1183 |
},
|
| 1184 |
"US": {
|
| 1185 |
+
"accuracy": 0.5213675213675214,
|
| 1186 |
+
"count": 117
|
| 1187 |
}
|
| 1188 |
}
|
| 1189 |
},
|
| 1190 |
"add_S3": {
|
| 1191 |
+
"full_accuracy": 0.02,
|
| 1192 |
+
"digit_accuracy": 0.37285714285714283,
|
| 1193 |
+
"n_examples": 100,
|
| 1194 |
"per_subtask": {
|
| 1195 |
"SA": {
|
| 1196 |
+
"accuracy": 0.45454545454545453,
|
| 1197 |
+
"count": 121
|
| 1198 |
},
|
| 1199 |
"SC": {
|
| 1200 |
+
"accuracy": 0.2892561983471074,
|
| 1201 |
+
"count": 121
|
| 1202 |
},
|
| 1203 |
"SS": {
|
| 1204 |
+
"accuracy": 0.46938775510204084,
|
| 1205 |
+
"count": 49
|
| 1206 |
},
|
| 1207 |
"UC": {
|
| 1208 |
+
"accuracy": 0.24193548387096775,
|
| 1209 |
+
"count": 186
|
| 1210 |
},
|
| 1211 |
"US": {
|
| 1212 |
+
"accuracy": 0.4618834080717489,
|
| 1213 |
+
"count": 223
|
| 1214 |
}
|
| 1215 |
}
|
| 1216 |
},
|
| 1217 |
"add_S4": {
|
| 1218 |
"full_accuracy": 0.0,
|
| 1219 |
+
"digit_accuracy": 0.35714285714285715,
|
| 1220 |
+
"n_examples": 100,
|
| 1221 |
"per_subtask": {
|
| 1222 |
"SA": {
|
| 1223 |
+
"accuracy": 0.49038461538461536,
|
| 1224 |
+
"count": 104
|
| 1225 |
},
|
| 1226 |
"SC": {
|
| 1227 |
+
"accuracy": 0.2358490566037736,
|
| 1228 |
+
"count": 106
|
| 1229 |
},
|
| 1230 |
"SS": {
|
| 1231 |
+
"accuracy": 0.43478260869565216,
|
| 1232 |
+
"count": 23
|
| 1233 |
},
|
| 1234 |
"UC": {
|
| 1235 |
+
"accuracy": 0.26875,
|
| 1236 |
+
"count": 160
|
| 1237 |
},
|
| 1238 |
"US": {
|
| 1239 |
+
"accuracy": 0.3941368078175896,
|
| 1240 |
+
"count": 307
|
| 1241 |
}
|
| 1242 |
}
|
| 1243 |
},
|
| 1244 |
"add_S5": {
|
| 1245 |
"full_accuracy": 0.0,
|
| 1246 |
+
"digit_accuracy": 0.2357142857142857,
|
| 1247 |
+
"n_examples": 100,
|
| 1248 |
"per_subtask": {
|
| 1249 |
"SA": {
|
| 1250 |
+
"accuracy": 0.46,
|
| 1251 |
+
"count": 100
|
| 1252 |
},
|
| 1253 |
"SC": {
|
| 1254 |
+
"accuracy": 0.26,
|
| 1255 |
+
"count": 100
|
| 1256 |
},
|
| 1257 |
"UC": {
|
| 1258 |
+
"accuracy": 0.09,
|
| 1259 |
+
"count": 100
|
| 1260 |
},
|
| 1261 |
"US": {
|
| 1262 |
+
"accuracy": 0.21,
|
| 1263 |
+
"count": 400
|
| 1264 |
}
|
| 1265 |
}
|
| 1266 |
},
|
| 1267 |
"add_S6": {
|
| 1268 |
+
"full_accuracy": 0.0,
|
| 1269 |
+
"digit_accuracy": 0.008571428571428572,
|
| 1270 |
+
"n_examples": 100,
|
| 1271 |
"per_subtask": {
|
| 1272 |
"SC": {
|
| 1273 |
+
"accuracy": 0.0,
|
| 1274 |
+
"count": 100
|
| 1275 |
},
|
| 1276 |
"UC": {
|
| 1277 |
+
"accuracy": 0.01,
|
| 1278 |
+
"count": 100
|
| 1279 |
},
|
| 1280 |
"US": {
|
| 1281 |
+
"accuracy": 0.01,
|
| 1282 |
+
"count": 500
|
| 1283 |
}
|
| 1284 |
}
|
| 1285 |
},
|
| 1286 |
"add_random": {
|
| 1287 |
"full_accuracy": 0.0,
|
| 1288 |
+
"digit_accuracy": 0.3192857142857143,
|
| 1289 |
"n_examples": 200,
|
| 1290 |
"per_subtask": {
|
| 1291 |
"SA": {
|
| 1292 |
+
"accuracy": 0.33557046979865773,
|
| 1293 |
+
"count": 447
|
| 1294 |
},
|
| 1295 |
"SC": {
|
| 1296 |
+
"accuracy": 0.284375,
|
| 1297 |
+
"count": 320
|
| 1298 |
},
|
| 1299 |
"SS": {
|
| 1300 |
+
"accuracy": 0.5178571428571429,
|
| 1301 |
+
"count": 56
|
| 1302 |
},
|
| 1303 |
"UC": {
|
| 1304 |
+
"accuracy": 0.2835538752362949,
|
| 1305 |
+
"count": 529
|
| 1306 |
},
|
| 1307 |
"US": {
|
| 1308 |
+
"accuracy": 0.5625,
|
| 1309 |
+
"count": 48
|
| 1310 |
}
|
| 1311 |
}
|
| 1312 |
},
|
| 1313 |
"add_C1": {
|
| 1314 |
"full_accuracy": 0.0,
|
| 1315 |
+
"digit_accuracy": 0.3585714285714286,
|
| 1316 |
+
"n_examples": 100,
|
| 1317 |
"per_subtask": {
|
| 1318 |
"SA": {
|
| 1319 |
+
"accuracy": 0.408,
|
| 1320 |
+
"count": 500
|
| 1321 |
},
|
| 1322 |
"SC": {
|
| 1323 |
+
"accuracy": 0.3,
|
| 1324 |
+
"count": 100
|
| 1325 |
},
|
| 1326 |
"UC": {
|
| 1327 |
+
"accuracy": 0.17,
|
| 1328 |
+
"count": 100
|
| 1329 |
}
|
| 1330 |
}
|
| 1331 |
},
|
| 1332 |
"add_C2": {
|
| 1333 |
"full_accuracy": 0.0,
|
| 1334 |
+
"digit_accuracy": 0.33285714285714285,
|
| 1335 |
+
"n_examples": 100,
|
| 1336 |
"per_subtask": {
|
| 1337 |
"SA": {
|
| 1338 |
+
"accuracy": 0.3925,
|
| 1339 |
+
"count": 400
|
| 1340 |
},
|
| 1341 |
"SC": {
|
| 1342 |
+
"accuracy": 0.3,
|
| 1343 |
+
"count": 100
|
| 1344 |
},
|
| 1345 |
"UC": {
|
| 1346 |
+
"accuracy": 0.09615384615384616,
|
| 1347 |
+
"count": 156
|
| 1348 |
},
|
| 1349 |
"US": {
|
| 1350 |
+
"accuracy": 0.7045454545454546,
|
| 1351 |
+
"count": 44
|
| 1352 |
}
|
| 1353 |
}
|
| 1354 |
},
|
| 1355 |
"add_C3": {
|
| 1356 |
"full_accuracy": 0.0,
|
| 1357 |
+
"digit_accuracy": 0.36,
|
| 1358 |
+
"n_examples": 100,
|
| 1359 |
"per_subtask": {
|
| 1360 |
"SA": {
|
| 1361 |
+
"accuracy": 0.41333333333333333,
|
| 1362 |
+
"count": 300
|
| 1363 |
},
|
| 1364 |
"SC": {
|
| 1365 |
+
"accuracy": 0.38,
|
| 1366 |
+
"count": 100
|
| 1367 |
},
|
| 1368 |
"UC": {
|
| 1369 |
+
"accuracy": 0.135678391959799,
|
| 1370 |
+
"count": 199
|
| 1371 |
},
|
| 1372 |
"US": {
|
| 1373 |
+
"accuracy": 0.6237623762376238,
|
| 1374 |
+
"count": 101
|
| 1375 |
}
|
| 1376 |
}
|
| 1377 |
},
|
| 1378 |
"add_C4": {
|
| 1379 |
"full_accuracy": 0.0,
|
| 1380 |
+
"digit_accuracy": 0.35428571428571426,
|
| 1381 |
+
"n_examples": 100,
|
| 1382 |
"per_subtask": {
|
| 1383 |
"SA": {
|
| 1384 |
+
"accuracy": 0.46,
|
| 1385 |
+
"count": 200
|
| 1386 |
},
|
| 1387 |
"SC": {
|
| 1388 |
+
"accuracy": 0.33,
|
| 1389 |
+
"count": 100
|
| 1390 |
},
|
| 1391 |
"UC": {
|
| 1392 |
+
"accuracy": 0.13636363636363635,
|
| 1393 |
+
"count": 264
|
| 1394 |
},
|
| 1395 |
"US": {
|
| 1396 |
+
"accuracy": 0.6397058823529411,
|
| 1397 |
+
"count": 136
|
| 1398 |
}
|
| 1399 |
}
|
| 1400 |
},
|
| 1401 |
"add_C5": {
|
| 1402 |
"full_accuracy": 0.0,
|
| 1403 |
+
"digit_accuracy": 0.37857142857142856,
|
| 1404 |
+
"n_examples": 100,
|
| 1405 |
"per_subtask": {
|
| 1406 |
"SA": {
|
| 1407 |
+
"accuracy": 0.56,
|
| 1408 |
+
"count": 100
|
| 1409 |
},
|
| 1410 |
"SC": {
|
| 1411 |
+
"accuracy": 0.28,
|
| 1412 |
+
"count": 100
|
| 1413 |
},
|
| 1414 |
"UC": {
|
| 1415 |
+
"accuracy": 0.16451612903225807,
|
| 1416 |
+
"count": 310
|
| 1417 |
},
|
| 1418 |
"US": {
|
| 1419 |
+
"accuracy": 0.6842105263157895,
|
| 1420 |
+
"count": 190
|
| 1421 |
}
|
| 1422 |
}
|
| 1423 |
},
|
| 1424 |
"add_C6": {
|
| 1425 |
"full_accuracy": 0.0,
|
| 1426 |
+
"digit_accuracy": 0.3842857142857143,
|
| 1427 |
+
"n_examples": 100,
|
| 1428 |
"per_subtask": {
|
| 1429 |
"SC": {
|
| 1430 |
+
"accuracy": 0.18,
|
| 1431 |
+
"count": 100
|
| 1432 |
},
|
| 1433 |
"UC": {
|
| 1434 |
+
"accuracy": 0.25135135135135134,
|
| 1435 |
+
"count": 370
|
| 1436 |
},
|
| 1437 |
"US": {
|
| 1438 |
+
"accuracy": 0.6869565217391305,
|
| 1439 |
+
"count": 230
|
| 1440 |
}
|
| 1441 |
}
|
| 1442 |
},
|
| 1443 |
"sub_M0": {
|
| 1444 |
"full_accuracy": 0.0,
|
| 1445 |
+
"digit_accuracy": 0.3314285714285714,
|
| 1446 |
+
"n_examples": 100,
|
| 1447 |
"per_subtask": {
|
| 1448 |
"MD": {
|
| 1449 |
+
"accuracy": 0.23902439024390243,
|
| 1450 |
+
"count": 615
|
| 1451 |
},
|
| 1452 |
"ME": {
|
| 1453 |
"accuracy": 1.0,
|
| 1454 |
+
"count": 85
|
| 1455 |
}
|
| 1456 |
}
|
| 1457 |
},
|
| 1458 |
"sub_M1": {
|
| 1459 |
"full_accuracy": 0.0,
|
| 1460 |
+
"digit_accuracy": 0.2571428571428571,
|
| 1461 |
+
"n_examples": 100,
|
| 1462 |
"per_subtask": {
|
| 1463 |
"MD": {
|
| 1464 |
+
"accuracy": 0.4006849315068493,
|
| 1465 |
+
"count": 292
|
| 1466 |
},
|
| 1467 |
"MB": {
|
| 1468 |
+
"accuracy": 0.034722222222222224,
|
| 1469 |
+
"count": 144
|
| 1470 |
},
|
| 1471 |
"ME": {
|
| 1472 |
"accuracy": 1.0,
|
| 1473 |
+
"count": 25
|
| 1474 |
},
|
| 1475 |
"UB": {
|
| 1476 |
+
"accuracy": 0.13807531380753138,
|
| 1477 |
+
"count": 239
|
| 1478 |
}
|
| 1479 |
}
|
| 1480 |
},
|
| 1481 |
"sub_M2": {
|
| 1482 |
"full_accuracy": 0.0,
|
| 1483 |
+
"digit_accuracy": 0.39,
|
| 1484 |
+
"n_examples": 100,
|
| 1485 |
"per_subtask": {
|
| 1486 |
"MD": {
|
| 1487 |
+
"accuracy": 0.6445497630331753,
|
| 1488 |
+
"count": 211
|
| 1489 |
},
|
| 1490 |
"MB": {
|
| 1491 |
+
"accuracy": 0.02608695652173913,
|
| 1492 |
+
"count": 115
|
| 1493 |
},
|
| 1494 |
"ME": {
|
| 1495 |
"accuracy": 1.0,
|
| 1496 |
+
"count": 85
|
| 1497 |
},
|
| 1498 |
"UB": {
|
| 1499 |
+
"accuracy": 0.26519337016574585,
|
| 1500 |
+
"count": 181
|
| 1501 |
},
|
| 1502 |
"UD": {
|
| 1503 |
+
"accuracy": 0.009259259259259259,
|
| 1504 |
+
"count": 108
|
| 1505 |
}
|
| 1506 |
}
|
| 1507 |
},
|
| 1508 |
"sub_M3": {
|
| 1509 |
"full_accuracy": 0.0,
|
| 1510 |
+
"digit_accuracy": 0.31285714285714283,
|
| 1511 |
+
"n_examples": 100,
|
| 1512 |
"per_subtask": {
|
| 1513 |
"MD": {
|
| 1514 |
+
"accuracy": 0.7821229050279329,
|
| 1515 |
+
"count": 179
|
| 1516 |
},
|
| 1517 |
"MB": {
|
| 1518 |
+
"accuracy": 0.009708737864077669,
|
| 1519 |
+
"count": 103
|
| 1520 |
},
|
| 1521 |
"ME": {
|
| 1522 |
"accuracy": 1.0,
|
| 1523 |
+
"count": 56
|
| 1524 |
},
|
| 1525 |
"UB": {
|
| 1526 |
+
"accuracy": 0.1476510067114094,
|
| 1527 |
+
"count": 149
|
| 1528 |
},
|
| 1529 |
"UD": {
|
| 1530 |
+
"accuracy": 0.0,
|
| 1531 |
+
"count": 213
|
| 1532 |
}
|
| 1533 |
}
|
| 1534 |
},
|
| 1535 |
"sub_M4": {
|
| 1536 |
"full_accuracy": 0.0,
|
| 1537 |
+
"digit_accuracy": 0.21428571428571427,
|
| 1538 |
+
"n_examples": 100,
|
| 1539 |
"per_subtask": {
|
| 1540 |
"MD": {
|
| 1541 |
"accuracy": 0.54,
|
| 1542 |
+
"count": 200
|
| 1543 |
},
|
| 1544 |
"MB": {
|
| 1545 |
+
"accuracy": 0.06,
|
| 1546 |
+
"count": 100
|
| 1547 |
},
|
| 1548 |
"UB": {
|
| 1549 |
+
"accuracy": 0.36,
|
| 1550 |
+
"count": 100
|
| 1551 |
},
|
| 1552 |
"UD": {
|
| 1553 |
"accuracy": 0.0,
|
| 1554 |
+
"count": 300
|
| 1555 |
}
|
| 1556 |
}
|
| 1557 |
},
|
| 1558 |
"sub_M5": {
|
| 1559 |
"full_accuracy": 0.0,
|
| 1560 |
+
"digit_accuracy": 0.18857142857142858,
|
| 1561 |
+
"n_examples": 100,
|
| 1562 |
"per_subtask": {
|
| 1563 |
"MD": {
|
| 1564 |
"accuracy": 1.0,
|
| 1565 |
+
"count": 100
|
| 1566 |
},
|
| 1567 |
"MB": {
|
| 1568 |
"accuracy": 0.0,
|
| 1569 |
+
"count": 100
|
| 1570 |
},
|
| 1571 |
"UB": {
|
| 1572 |
+
"accuracy": 0.32,
|
| 1573 |
+
"count": 100
|
| 1574 |
},
|
| 1575 |
"UD": {
|
| 1576 |
"accuracy": 0.0,
|
| 1577 |
+
"count": 400
|
| 1578 |
}
|
| 1579 |
}
|
| 1580 |
},
|
| 1581 |
"sub_random": {
|
| 1582 |
"full_accuracy": 0.0,
|
| 1583 |
+
"digit_accuracy": 0.2621428571428571,
|
| 1584 |
"n_examples": 200,
|
| 1585 |
"per_subtask": {
|
| 1586 |
"MD": {
|
| 1587 |
+
"accuracy": 0.37833333333333335,
|
| 1588 |
+
"count": 600
|
| 1589 |
},
|
| 1590 |
"MB": {
|
| 1591 |
+
"accuracy": 0.03745318352059925,
|
| 1592 |
+
"count": 267
|
| 1593 |
},
|
| 1594 |
"ME": {
|
| 1595 |
+
"accuracy": 1.0,
|
| 1596 |
"count": 53
|
| 1597 |
},
|
| 1598 |
"UB": {
|
| 1599 |
+
"accuracy": 0.17539863325740318,
|
| 1600 |
+
"count": 439
|
| 1601 |
},
|
| 1602 |
"UD": {
|
| 1603 |
+
"accuracy": 0.0,
|
| 1604 |
+
"count": 41
|
| 1605 |
}
|
| 1606 |
}
|
| 1607 |
},
|
| 1608 |
"sub_B3": {
|
| 1609 |
"full_accuracy": 0.0,
|
| 1610 |
+
"digit_accuracy": 0.22857142857142856,
|
| 1611 |
+
"n_examples": 100,
|
| 1612 |
"per_subtask": {
|
| 1613 |
"MD": {
|
| 1614 |
+
"accuracy": 0.36333333333333334,
|
| 1615 |
+
"count": 300
|
| 1616 |
},
|
| 1617 |
"MB": {
|
| 1618 |
+
"accuracy": 0.05,
|
| 1619 |
+
"count": 100
|
| 1620 |
},
|
| 1621 |
"UB": {
|
| 1622 |
+
"accuracy": 0.233502538071066,
|
| 1623 |
+
"count": 197
|
| 1624 |
},
|
| 1625 |
"UD": {
|
| 1626 |
"accuracy": 0.0,
|
| 1627 |
+
"count": 103
|
| 1628 |
}
|
| 1629 |
}
|
| 1630 |
},
|
| 1631 |
"sub_B4": {
|
| 1632 |
"full_accuracy": 0.0,
|
| 1633 |
+
"digit_accuracy": 0.21,
|
| 1634 |
+
"n_examples": 100,
|
| 1635 |
"per_subtask": {
|
| 1636 |
"MD": {
|
| 1637 |
+
"accuracy": 0.525,
|
| 1638 |
+
"count": 200
|
| 1639 |
},
|
| 1640 |
"MB": {
|
| 1641 |
+
"accuracy": 0.01,
|
| 1642 |
+
"count": 100
|
| 1643 |
},
|
| 1644 |
"UB": {
|
| 1645 |
+
"accuracy": 0.1659919028340081,
|
| 1646 |
+
"count": 247
|
| 1647 |
},
|
| 1648 |
"UD": {
|
| 1649 |
"accuracy": 0.0,
|
| 1650 |
+
"count": 153
|
| 1651 |
}
|
| 1652 |
}
|
| 1653 |
},
|
| 1654 |
"sub_B5": {
|
| 1655 |
"full_accuracy": 0.0,
|
| 1656 |
+
"digit_accuracy": 0.19285714285714287,
|
| 1657 |
+
"n_examples": 100,
|
| 1658 |
"per_subtask": {
|
| 1659 |
"MD": {
|
| 1660 |
"accuracy": 1.0,
|
| 1661 |
+
"count": 100
|
| 1662 |
},
|
| 1663 |
"MB": {
|
| 1664 |
+
"accuracy": 0.0,
|
| 1665 |
+
"count": 100
|
| 1666 |
},
|
| 1667 |
"UB": {
|
| 1668 |
+
"accuracy": 0.1174496644295302,
|
| 1669 |
+
"count": 298
|
| 1670 |
},
|
| 1671 |
"UD": {
|
| 1672 |
"accuracy": 0.0,
|
| 1673 |
+
"count": 202
|
| 1674 |
}
|
| 1675 |
}
|
| 1676 |
}
|
| 1677 |
},
|
| 1678 |
"summary": {
|
| 1679 |
+
"overall_accuracy": 0.001153846153846154,
|
| 1680 |
+
"digit_accuracy": 0.29637362637362635,
|
| 1681 |
+
"total_examples": 2600,
|
| 1682 |
"n_splits": 24
|
| 1683 |
}
|
| 1684 |
},
|
| 1685 |
+
"sorl_overall_accuracy": 0.001153846153846154,
|
| 1686 |
+
"sft_overall_accuracy": 0.0019230769230769232
|
| 1687 |
}
|
add_sub_sorl_v1_abs30_K1_10K_2L1H128d/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157722580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d4c381a7edfa9205467f1839da87f38a3c53638694a57a1ec4181fe5dc9334
|
| 3 |
size 157722580
|
add_sub_sorl_v1_abs30_K1_10K_2L1H128d/train_config.json
CHANGED
|
@@ -69,16 +69,20 @@
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 39353984,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs30_K1_10K_2L1H128d",
|
| 72 |
-
"git_commit": "
|
| 73 |
-
"timestamp": "2026-04-
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
|
|
|
| 77 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 78 |
"trainer_version": "v1",
|
| 79 |
-
"wandb_run_id": "
|
| 80 |
-
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/
|
| 81 |
-
"
|
| 82 |
-
"
|
|
|
|
|
|
|
|
|
|
| 83 |
"eval_method": "ArithmeticEvaluator"
|
| 84 |
}
|
|
|
|
| 69 |
"no_wandb": false,
|
| 70 |
"n_params": 39353984,
|
| 71 |
"run_name": "add_sub_sorl_v1_abs30_K1_10K_2L1H128d",
|
| 72 |
+
"git_commit": "1d5a160e16a5070d61b881494e832aa88149b15c",
|
| 73 |
+
"timestamp": "2026-04-15T07:41:24.020201+00:00",
|
| 74 |
"tokenizer": "Qwen/Qwen3-0.6B",
|
| 75 |
"dataset_repo": "thoughtworks/arithmetic-sorl-data",
|
| 76 |
"dataset_config": "add_sub_6digit",
|
| 77 |
+
"train_dataset": "fixed_train/train_10K_seed42.pt",
|
| 78 |
"model_repo": "thoughtworks/arithmetic-sorl",
|
| 79 |
"trainer_version": "v1",
|
| 80 |
+
"wandb_run_id": "stx7wi4h",
|
| 81 |
+
"wandb_url": "https://wandb.ai/nlp_and_interpretability/sorl-arithmetic/runs/stx7wi4h",
|
| 82 |
+
"eval_final_dataset": "eval_sets/eval_add_sub_6d_N100_seed42.json",
|
| 83 |
+
"eval_epoch_dataset": "eval_sets/eval_add_sub_6d_N25_seed42.json",
|
| 84 |
+
"eval_hf_repo": "thoughtworks/arithmetic-sorl-data",
|
| 85 |
+
"final_accuracy": 0.001153846153846154,
|
| 86 |
+
"sft_accuracy": 0.0019230769230769232,
|
| 87 |
"eval_method": "ArithmeticEvaluator"
|
| 88 |
}
|