| common_init_from_params: setting dry_penalty_last_n to ctx_size = 768 | |
| common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) | |
| system_info: n_threads = 6 (n_threads_batch = 6) / 12 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 | | |
| multiple_choice_score: there are 1548 tasks in prompt | |
| multiple_choice_score: selecting 750 random tasks from 1548 tasks available | |
| multiple_choice_score: preparing task data...done | |
| multiple_choice_score : calculating TruthfulQA score over 750 tasks. | |
| task acc_norm | |
| 1 0.00000000 | |
| 2 0.00000000 | |
| 3 0.00000000 | |
| 4 25.00000000 | |
| 5 20.00000000 | |
| 6 16.66666667 | |
| 7 28.57142857 | |
| 8 37.50000000 | |
| 9 33.33333333 | |
| 10 30.00000000 | |
| 11 27.27272727 | |
| 12 33.33333333 | |
| 13 38.46153846 | |
| 14 35.71428571 | |
| 15 33.33333333 | |
| 16 37.50000000 | |
| 17 41.17647059 | |
| 18 38.88888889 | |
| 19 42.10526316 | |
| 20 45.00000000 | |
| 21 47.61904762 | |
| 22 45.45454545 | |
| 23 43.47826087 | |
| 24 41.66666667 | |
| 25 44.00000000 | |
| 26 42.30769231 | |
| 27 44.44444444 | |
| 28 46.42857143 | |
| 29 48.27586207 | |
| 30 50.00000000 | |
| 31 51.61290323 | |
| 32 53.12500000 | |
| 33 51.51515152 | |
| 34 52.94117647 | |
| 35 54.28571429 | |
| 36 52.77777778 | |
| 37 54.05405405 | |
| 38 55.26315789 | |
| 39 53.84615385 | |
| 40 52.50000000 | |
| 41 53.65853659 | |
| 42 52.38095238 | |
| 43 53.48837209 | |
| 44 52.27272727 | |
| 45 53.33333333 | |
| 46 52.17391304 | |
| 47 51.06382979 | |
| 48 52.08333333 | |
| 49 53.06122449 | |
| 50 52.00000000 | |
| 51 50.98039216 | |
| 52 50.00000000 | |
| 53 49.05660377 | |
| 54 48.14814815 | |
| 55 49.09090909 | |
| 56 50.00000000 | |
| 57 49.12280702 | |
| 58 50.00000000 | |
| 59 50.84745763 | |
| 60 50.00000000 | |
| 61 49.18032787 | |
| 62 48.38709677 | |
| 63 47.61904762 | |
| 64 46.87500000 | |
| 65 46.15384615 | |
| 66 46.96969697 | |
| 67 46.26865672 | |
| 68 45.58823529 | |
| 69 44.92753623 | |
| 70 45.71428571 | |
| 71 46.47887324 | |
| 72 45.83333333 | |
| 73 45.20547945 | |
| 74 45.94594595 | |
| 75 46.66666667 | |
| 76 47.36842105 | |
| 77 48.05194805 | |
| 78 48.71794872 | |
| 79 48.10126582 | |
| 80 48.75000000 | |
| 81 49.38271605 | |
| 82 48.78048780 | |
| 83 49.39759036 | |
| 84 50.00000000 | |
| 85 50.58823529 | |
| 86 50.00000000 | |
| 87 50.57471264 | |
| 88 51.13636364 | |
| 89 50.56179775 | |
| 90 50.00000000 | |
| 91 49.45054945 | |
| 92 48.91304348 | |
| 93 48.38709677 | |
| 94 48.93617021 | |
| 95 48.42105263 | |
| 96 48.95833333 | |
| 97 48.45360825 | |
| 98 47.95918367 | |
| 99 47.47474747 | |
| 100 47.00000000 | |
| 101 47.52475248 | |
| 102 47.05882353 | |
| 103 46.60194175 | |
| 104 47.11538462 | |
| 105 47.61904762 | |
| 106 48.11320755 | |
| 107 47.66355140 | |
| 108 48.14814815 | |
| 109 47.70642202 | |
| 110 47.27272727 | |
| 111 46.84684685 | |
| 112 47.32142857 | |
| 113 46.90265487 | |
| 114 47.36842105 | |
| 115 47.82608696 | |
| 116 48.27586207 | |
| 117 47.86324786 | |
| 118 47.45762712 | |
| 119 47.89915966 | |
| 120 47.50000000 | |
| 121 47.93388430 | |
| 122 48.36065574 | |
| 123 47.96747967 | |
| 124 47.58064516 | |
| 125 48.00000000 | |
| 126 47.61904762 | |
| 127 47.24409449 | |
| 128 46.87500000 | |
| 129 46.51162791 | |
| 130 46.15384615 | |
| 131 46.56488550 | |
| 132 46.21212121 | |
| 133 45.86466165 | |
| 134 45.52238806 | |
| 135 45.18518519 | |
| 136 45.58823529 | |
| 137 45.98540146 | |
| 138 45.65217391 | |
| 139 46.04316547 | |
| 140 46.42857143 | |
| 141 46.09929078 | |
| 142 46.47887324 | |
| 143 46.85314685 | |
| 144 46.52777778 | |
| 145 46.89655172 | |
| 146 47.26027397 | |
| 147 46.93877551 | |
| 148 47.29729730 | |
| 149 47.65100671 | |
| 150 47.33333333 | |
| 151 47.01986755 | |
| 152 47.36842105 | |
| 153 47.05882353 | |
| 154 46.75324675 | |
| 155 46.45161290 | |
| 156 46.15384615 | |
| 157 46.49681529 | |
| 158 46.83544304 | |
| 159 46.54088050 | |
| 160 46.87500000 | |
| 161 46.58385093 | |
| 162 46.29629630 | |
| 163 46.01226994 | |
| 164 45.73170732 | |
| 165 46.06060606 | |
| 166 45.78313253 | |
| 167 46.10778443 | |
| 168 45.83333333 | |
| 169 46.15384615 | |
| 170 45.88235294 | |
| 171 45.61403509 | |
| 172 45.34883721 | |
| 173 45.08670520 | |
| 174 45.40229885 | |
| 175 45.14285714 | |
| 176 44.88636364 | |
| 177 44.63276836 | |
| 178 44.38202247 | |
| 179 44.69273743 | |
| 180 44.44444444 | |
| 181 44.19889503 | |
| 182 43.95604396 | |
| 183 44.26229508 | |
| 184 44.02173913 | |
| 185 44.32432432 | |
| 186 44.62365591 | |
| 187 44.38502674 | |
| 188 44.14893617 | |
| 189 44.44444444 | |
| 190 44.21052632 | |
| 191 43.97905759 | |
| 192 43.75000000 | |
| 193 43.52331606 | |
| 194 43.29896907 | |
| 195 43.58974359 | |
| 196 43.36734694 | |
| 197 43.14720812 | |
| 198 42.92929293 | |
| 199 42.71356784 | |
| 200 42.50000000 | |
| 201 42.28855721 | |
| 202 42.07920792 | |
| 203 41.87192118 | |
| 204 41.66666667 | |
| 205 41.95121951 | |
| 206 41.74757282 | |
| 207 42.02898551 | |
| 208 41.82692308 | |
| 209 41.62679426 | |
| 210 41.42857143 | |
| 211 41.70616114 | |
| 212 41.50943396 | |
| 213 41.31455399 | |
| 214 41.12149533 | |
| 215 41.39534884 | |
| 216 41.66666667 | |
| 217 41.47465438 | |
| 218 41.74311927 | |
| 219 42.00913242 | |
| 220 42.27272727 | |
| 221 42.53393665 | |
| 222 42.34234234 | |
| 223 42.60089686 | |
| 224 42.85714286 | |
| 225 43.11111111 | |
| 226 43.36283186 | |
| 227 43.17180617 | |
| 228 43.42105263 | |
| 229 43.23144105 | |
| 230 43.04347826 | |
| 231 42.85714286 | |
| 232 43.10344828 | |
| 233 42.91845494 | |
| 234 43.16239316 | |
| 235 42.97872340 | |
| 236 42.79661017 | |
| 237 42.61603376 | |
| 238 42.43697479 | |
| 239 42.25941423 | |
| 240 42.50000000 | |
| 241 42.32365145 | |
| 242 42.56198347 | |
| 243 42.79835391 | |
| 244 42.62295082 | |
| 245 42.85714286 | |
| 246 42.68292683 | |
| 247 42.91497976 | |
| 248 43.14516129 | |
| 249 42.97188755 | |
| 250 42.80000000 | |
| 251 42.62948207 | |
| 252 42.46031746 | |
| 253 42.29249012 | |
| 254 42.12598425 | |
| 255 41.96078431 | |
| 256 41.79687500 | |
| 257 42.02334630 | |
| 258 41.86046512 | |
| 259 41.69884170 | |
| 260 41.53846154 | |
| 261 41.37931034 | |
| 262 41.22137405 | |
| 263 41.06463878 | |
| 264 41.28787879 | |
| 265 41.13207547 | |
| 266 41.35338346 | |
| 267 41.19850187 | |
| 268 41.04477612 | |
| 269 41.26394052 | |
| 270 41.48148148 | |
| 271 41.32841328 | |
| 272 41.17647059 | |
| 273 41.02564103 | |
| 274 40.87591241 | |
| 275 40.72727273 | |
| 276 40.94202899 | |
| 277 41.15523466 | |
| 278 41.36690647 | |
| 279 41.21863799 | |
| 280 41.42857143 | |
| 281 41.28113879 | |
| 282 41.13475177 | |
| 283 40.98939929 | |
| 284 40.84507042 | |
| 285 40.70175439 | |
| 286 40.55944056 | |
| 287 40.76655052 | |
| 288 40.62500000 | |
| 289 40.48442907 | |
| 290 40.68965517 | |
| 291 40.89347079 | |
| 292 41.09589041 | |
| 293 41.29692833 | |
| 294 41.15646259 | |
| 295 41.01694915 | |
| 296 40.87837838 | |
| 297 40.74074074 | |
| 298 40.93959732 | |
| 299 41.13712375 | |
| 300 41.33333333 | |
| 301 41.19601329 | |
| 302 41.39072848 | |
| 303 41.25412541 | |
| 304 41.11842105 | |
| 305 41.31147541 | |
| 306 41.17647059 | |
| 307 41.36807818 | |
| 308 41.23376623 | |
| 309 41.10032362 | |
| 310 41.29032258 | |
| 311 41.47909968 | |
| 312 41.66666667 | |
| 313 41.85303514 | |
| 314 42.03821656 | |
| 315 42.22222222 | |
| 316 42.08860759 | |
| 317 42.27129338 | |
| 318 42.13836478 | |
| 319 42.31974922 | |
| 320 42.18750000 | |
| 321 42.05607477 | |
| 322 41.92546584 | |
| 323 41.79566563 | |
| 324 41.66666667 | |
| 325 41.84615385 | |
| 326 41.71779141 | |
| 327 41.89602446 | |
| 328 42.07317073 | |
| 329 41.94528875 | |
| 330 41.81818182 | |
| 331 41.69184290 | |
| 332 41.86746988 | |
| 333 41.74174174 | |
| 334 41.61676647 | |
| 335 41.79104478 | |
| 336 41.96428571 | |
| 337 41.83976261 | |
| 338 41.71597633 | |
| 339 41.59292035 | |
| 340 41.76470588 | |
| 341 41.93548387 | |
| 342 42.10526316 | |
| 343 41.98250729 | |
| 344 41.86046512 | |
| 345 41.73913043 | |
| 346 41.90751445 | |
| 347 42.07492795 | |
| 348 41.95402299 | |
| 349 42.12034384 | |
| 350 42.28571429 | |
| 351 42.16524217 | |
| 352 42.04545455 | |
| 353 42.20963173 | |
| 354 42.37288136 | |
| 355 42.25352113 | |
| 356 42.41573034 | |
| 357 42.29691877 | |
| 358 42.45810056 | |
| 359 42.33983287 | |
| 360 42.50000000 | |
| 361 42.38227147 | |
| 362 42.54143646 | |
| 363 42.42424242 | |
| 364 42.30769231 | |
| 365 42.19178082 | |
| 366 42.34972678 | |
| 367 42.23433243 | |
| 368 42.11956522 | |
| 369 42.00542005 | |
| 370 42.16216216 | |
| 371 42.31805930 | |
| 372 42.20430108 | |
| 373 42.09115282 | |
| 374 42.24598930 | |
| 375 42.40000000 | |
| 376 42.28723404 | |
| 377 42.17506631 | |
| 378 42.32804233 | |
| 379 42.21635884 | |
| 380 42.10526316 | |
| 381 42.25721785 | |
| 382 42.40837696 | |
| 383 42.55874674 | |
| 384 42.44791667 | |
| 385 42.59740260 | |
| 386 42.48704663 | |
| 387 42.37726098 | |
| 388 42.26804124 | |
| 389 42.41645244 | |
| 390 42.56410256 | |
| 391 42.71099744 | |
| 392 42.85714286 | |
| 393 42.74809160 | |
| 394 42.63959391 | |
| 395 42.78481013 | |
| 396 42.92929293 | |
| 397 43.07304786 | |
| 398 42.96482412 | |
| 399 43.10776942 | |
| 400 43.00000000 | |
| 401 43.14214464 | |
| 402 43.03482587 | |
| 403 42.92803970 | |
| 404 42.82178218 | |
| 405 42.71604938 | |
| 406 42.61083744 | |
| 407 42.50614251 | |
| 408 42.40196078 | |
| 409 42.54278729 | |
| 410 42.43902439 | |
| 411 42.33576642 | |
| 412 42.23300971 | |
| 413 42.13075061 | |
| 414 42.02898551 | |
| 415 42.16867470 | |
| 416 42.06730769 | |
| 417 41.96642686 | |
| 418 41.86602871 | |
| 419 42.00477327 | |
| 420 42.14285714 | |
| 421 42.04275534 | |
| 422 41.94312796 | |
| 423 41.84397163 | |
| 424 41.98113208 | |
| 425 42.11764706 | |
| 426 42.25352113 | |
| 427 42.15456674 | |
| 428 42.05607477 | |
| 429 42.19114219 | |
| 430 42.09302326 | |
| 431 42.22737819 | |
| 432 42.36111111 | |
| 433 42.26327945 | |
| 434 42.16589862 | |
| 435 42.06896552 | |
| 436 41.97247706 | |
| 437 41.87643021 | |
| 438 42.00913242 | |
| 439 42.14123007 | |
| 440 42.04545455 | |
| 441 41.95011338 | |
| 442 41.85520362 | |
| 443 41.76072235 | |
| 444 41.66666667 | |
| 445 41.57303371 | |
| 446 41.47982063 | |
| 447 41.61073826 | |
| 448 41.51785714 | |
| 449 41.42538976 | |
| 450 41.55555556 | |
| 451 41.46341463 | |
| 452 41.59292035 | |
| 453 41.72185430 | |
| 454 41.62995595 | |
| 455 41.53846154 | |
| 456 41.66666667 | |
| 457 41.79431072 | |
| 458 41.70305677 | |
| 459 41.61220044 | |
| 460 41.73913043 | |
| 461 41.64859002 | |
| 462 41.55844156 | |
| 463 41.46868251 | |
| 464 41.59482759 | |
| 465 41.50537634 | |
| 466 41.41630901 | |
| 467 41.54175589 | |
| 468 41.45299145 | |
| 469 41.57782516 | |
| 470 41.48936170 | |
| 471 41.40127389 | |
| 472 41.31355932 | |
| 473 41.22621564 | |
| 474 41.13924051 | |
| 475 41.05263158 | |
| 476 41.17647059 | |
| 477 41.09014675 | |
| 478 41.21338912 | |
| 479 41.33611691 | |
| 480 41.45833333 | |
| 481 41.37214137 | |
| 482 41.28630705 | |
| 483 41.20082816 | |
| 484 41.11570248 | |
| 485 41.03092784 | |
| 486 40.94650206 | |
| 487 41.06776181 | |
| 488 40.98360656 | |
| 489 40.89979550 | |
| 490 41.02040816 | |
| 491 40.93686354 | |
| 492 40.85365854 | |
| 493 40.77079108 | |
| 494 40.89068826 | |
| 495 41.01010101 | |
| 496 41.12903226 | |
| 497 41.04627767 | |
| 498 40.96385542 | |
| 499 40.88176353 | |
| 500 40.80000000 | |
| 501 40.71856287 | |
| 502 40.63745020 | |
| 503 40.55666004 | |
| 504 40.67460317 | |
| 505 40.59405941 | |
| 506 40.71146245 | |
| 507 40.63116371 | |
| 508 40.55118110 | |
| 509 40.47151277 | |
| 510 40.39215686 | |
| 511 40.31311155 | |
| 512 40.23437500 | |
| 513 40.15594542 | |
| 514 40.07782101 | |
| 515 40.00000000 | |
| 516 40.11627907 | |
| 517 40.23210832 | |
| 518 40.34749035 | |
| 519 40.46242775 | |
| 520 40.57692308 | |
| 521 40.49904031 | |
| 522 40.42145594 | |
| 523 40.34416826 | |
| 524 40.45801527 | |
| 525 40.38095238 | |
| 526 40.30418251 | |
| 527 40.41745731 | |
| 528 40.34090909 | |
| 529 40.26465028 | |
| 530 40.37735849 | |
| 531 40.30131827 | |
| 532 40.22556391 | |
| 533 40.15009381 | |
| 534 40.07490637 | |
| 535 40.18691589 | |
| 536 40.11194030 | |
| 537 40.22346369 | |
| 538 40.33457249 | |
| 539 40.25974026 | |
| 540 40.18518519 | |
| 541 40.11090573 | |
| 542 40.22140221 | |
| 543 40.14732965 | |
| 544 40.07352941 | |
| 545 40.00000000 | |
| 546 39.92673993 | |
| 547 40.03656307 | |
| 548 40.14598540 | |
| 549 40.07285974 | |
| 550 40.00000000 | |
| 551 40.10889292 | |
| 552 40.03623188 | |
| 553 39.96383363 | |
| 554 40.07220217 | |
| 555 40.00000000 | |
| 556 40.10791367 | |
| 557 40.03590664 | |
| 558 40.14336918 | |
| 559 40.07155635 | |
| 560 40.00000000 | |
| 561 39.92869875 | |
| 562 40.03558719 | |
| 563 40.14209591 | |
| 564 40.07092199 | |
| 565 40.17699115 | |
| 566 40.10600707 | |
| 567 40.03527337 | |
| 568 40.14084507 | |
| 569 40.07029877 | |
| 570 40.17543860 | |
| 571 40.10507881 | |
| 572 40.20979021 | |
| 573 40.13961606 | |
| 574 40.06968641 | |
| 575 40.00000000 | |
| 576 40.10416667 | |
| 577 40.20797227 | |
| 578 40.13840830 | |
| 579 40.06908463 | |
| 580 40.17241379 | |
| 581 40.10327022 | |
| 582 40.03436426 | |
| 583 40.13722127 | |
| 584 40.23972603 | |
| 585 40.17094017 | |
| 586 40.27303754 | |
| 587 40.20442930 | |
| 588 40.13605442 | |
| 589 40.06791171 | |
| 590 40.00000000 | |
| 591 39.93231810 | |
| 592 39.86486486 | |
| 593 39.79763912 | |
| 594 39.89898990 | |
| 595 39.83193277 | |
| 596 39.93288591 | |
| 597 39.86599665 | |
| 598 39.79933110 | |
| 599 39.89983306 | |
| 600 39.83333333 | |
| 601 39.93344426 | |
| 602 39.86710963 | |
| 603 39.96683250 | |
| 604 39.90066225 | |
| 605 40.00000000 | |
| 606 39.93399340 | |
| 607 40.03294893 | |
| 608 39.96710526 | |
| 609 39.90147783 | |
| 610 39.83606557 | |
| 611 39.93453355 | |
| 612 39.86928105 | |
| 613 39.80424144 | |
| 614 39.90228013 | |
| 615 39.83739837 | |
| 616 39.93506494 | |
| 617 39.87034036 | |
| 618 39.96763754 | |
| 619 39.90306947 | |
| 620 39.83870968 | |
| 621 39.77455717 | |
| 622 39.87138264 | |
| 623 39.80738363 | |
| 624 39.74358974 | |
| 625 39.68000000 | |
| 626 39.77635783 | |
| 627 39.71291866 | |
| 628 39.64968153 | |
| 629 39.74562798 | |
| 630 39.68253968 | |
| 631 39.77812995 | |
| 632 39.87341772 | |
| 633 39.81042654 | |
| 634 39.74763407 | |
| 635 39.68503937 | |
| 636 39.62264151 | |
| 637 39.71742543 | |
| 638 39.65517241 | |
| 639 39.74960876 | |
| 640 39.84375000 | |
| 641 39.78159126 | |
| 642 39.87538941 | |
| 643 39.81337481 | |
| 644 39.90683230 | |
| 645 39.84496124 | |
| 646 39.78328173 | |
| 647 39.72179289 | |
| 648 39.66049383 | |
| 649 39.59938367 | |
| 650 39.69230769 | |
| 651 39.63133641 | |
| 652 39.72392638 | |
| 653 39.66309342 | |
| 654 39.75535168 | |
| 655 39.69465649 | |
| 656 39.78658537 | |
| 657 39.72602740 | |
| 658 39.81762918 | |
| 659 39.75720789 | |
| 660 39.69696970 | |
| 661 39.63691377 | |
| 662 39.57703927 | |
| 663 39.51734540 | |
| 664 39.60843373 | |
| 665 39.69924812 | |
| 666 39.63963964 | |
| 667 39.73013493 | |
| 668 39.82035928 | |
| 669 39.91031390 | |
| 670 39.85074627 | |
| 671 39.79135618 | |
| 672 39.73214286 | |
| 673 39.67310550 | |
| 674 39.61424332 | |
| 675 39.55555556 | |
| 676 39.49704142 | |
| 677 39.43870015 | |
| 678 39.38053097 | |
| 679 39.32253314 | |
| 680 39.41176471 | |
| 681 39.50073421 | |
| 682 39.44281525 | |
| 683 39.38506589 | |
| 684 39.32748538 | |
| 685 39.27007299 | |
| 686 39.21282799 | |
| 687 39.15574964 | |
| 688 39.09883721 | |
| 689 39.04208999 | |
| 690 38.98550725 | |
| 691 39.07380608 | |
| 692 39.01734104 | |
| 693 38.96103896 | |
| 694 38.90489914 | |
| 695 38.84892086 | |
| 696 38.93678161 | |
| 697 39.02439024 | |
| 698 38.96848138 | |
| 699 39.05579399 | |
| 700 39.00000000 | |
| 701 39.08701854 | |
| 702 39.17378917 | |
| 703 39.26031294 | |
| 704 39.20454545 | |
| 705 39.14893617 | |
| 706 39.09348442 | |
| 707 39.03818953 | |
| 708 38.98305085 | |
| 709 39.06911142 | |
| 710 39.15492958 | |
| 711 39.24050633 | |
| 712 39.18539326 | |
| 713 39.27068724 | |
| 714 39.35574230 | |
| 715 39.30069930 | |
| 716 39.38547486 | |
| 717 39.33054393 | |
| 718 39.27576602 | |
| 719 39.22114047 | |
| 720 39.16666667 | |
| 721 39.11234397 | |
| 722 39.19667590 | |
| 723 39.28077455 | |
| 724 39.22651934 | |
| 725 39.31034483 | |
| 726 39.25619835 | |
| 727 39.20220083 | |
| 728 39.14835165 | |
| 729 39.09465021 | |
| 730 39.04109589 | |
| 731 38.98768810 | |
| 732 39.07103825 | |
| 733 39.15416098 | |
| 734 39.23705722 | |
| 735 39.18367347 | |
| 736 39.13043478 | |
| 737 39.21302578 | |
| 738 39.15989160 | |
| 739 39.24221922 | |
| 740 39.18918919 | |
| 741 39.13630229 | |
| 742 39.21832884 | |
| 743 39.16554509 | |
| 744 39.24731183 | |
| 745 39.19463087 | |
| 746 39.14209115 | |
| 747 39.08969210 | |
| 748 39.03743316 | |
| 749 38.98531375 | |
| 750 39.06666667 | |
| Final result: 39.0667 +/- 1.7827 | |
| Random chance: 25.0000 +/- 1.5822 | |