| 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 | |
| 1 100.00000000 | |
| 2 50.00000000 | |
| 3 33.33333333 | |
| 4 50.00000000 | |
| 5 40.00000000 | |
| 6 33.33333333 | |
| 7 42.85714286 | |
| 8 50.00000000 | |
| 9 44.44444444 | |
| 10 40.00000000 | |
| 11 36.36363636 | |
| 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 42.85714286 | |
| 22 40.90909091 | |
| 23 39.13043478 | |
| 24 37.50000000 | |
| 25 40.00000000 | |
| 26 38.46153846 | |
| 27 40.74074074 | |
| 28 39.28571429 | |
| 29 41.37931034 | |
| 30 43.33333333 | |
| 31 45.16129032 | |
| 32 46.87500000 | |
| 33 45.45454545 | |
| 34 47.05882353 | |
| 35 48.57142857 | |
| 36 47.22222222 | |
| 37 45.94594595 | |
| 38 47.36842105 | |
| 39 46.15384615 | |
| 40 45.00000000 | |
| 41 46.34146341 | |
| 42 45.23809524 | |
| 43 46.51162791 | |
| 44 45.45454545 | |
| 45 46.66666667 | |
| 46 45.65217391 | |
| 47 44.68085106 | |
| 48 45.83333333 | |
| 49 46.93877551 | |
| 50 46.00000000 | |
| 51 45.09803922 | |
| 52 44.23076923 | |
| 53 43.39622642 | |
| 54 42.59259259 | |
| 55 43.63636364 | |
| 56 44.64285714 | |
| 57 43.85964912 | |
| 58 44.82758621 | |
| 59 45.76271186 | |
| 60 45.00000000 | |
| 61 44.26229508 | |
| 62 43.54838710 | |
| 63 42.85714286 | |
| 64 42.18750000 | |
| 65 41.53846154 | |
| 66 42.42424242 | |
| 67 41.79104478 | |
| 68 41.17647059 | |
| 69 40.57971014 | |
| 70 41.42857143 | |
| 71 42.25352113 | |
| 72 41.66666667 | |
| 73 41.09589041 | |
| 74 41.89189189 | |
| 75 42.66666667 | |
| 76 43.42105263 | |
| 77 44.15584416 | |
| 78 44.87179487 | |
| 79 44.30379747 | |
| 80 45.00000000 | |
| 81 45.67901235 | |
| 82 45.12195122 | |
| 83 45.78313253 | |
| 84 46.42857143 | |
| 85 47.05882353 | |
| 86 46.51162791 | |
| 87 47.12643678 | |
| 88 47.72727273 | |
| 89 47.19101124 | |
| 90 46.66666667 | |
| 91 46.15384615 | |
| 92 45.65217391 | |
| 93 45.16129032 | |
| 94 45.74468085 | |
| 95 45.26315789 | |
| 96 45.83333333 | |
| 97 45.36082474 | |
| 98 44.89795918 | |
| 99 45.45454545 | |
| 100 45.00000000 | |
| 101 45.54455446 | |
| 102 45.09803922 | |
| 103 44.66019417 | |
| 104 45.19230769 | |
| 105 45.71428571 | |
| 106 46.22641509 | |
| 107 45.79439252 | |
| 108 46.29629630 | |
| 109 46.78899083 | |
| 110 46.36363636 | |
| 111 45.94594595 | |
| 112 46.42857143 | |
| 113 46.01769912 | |
| 114 46.49122807 | |
| 115 46.95652174 | |
| 116 46.55172414 | |
| 117 46.15384615 | |
| 118 45.76271186 | |
| 119 45.37815126 | |
| 120 45.00000000 | |
| 121 45.45454545 | |
| 122 45.90163934 | |
| 123 45.52845528 | |
| 124 45.16129032 | |
| 125 45.60000000 | |
| 126 45.23809524 | |
| 127 44.88188976 | |
| 128 44.53125000 | |
| 129 44.18604651 | |
| 130 43.84615385 | |
| 131 44.27480916 | |
| 132 43.93939394 | |
| 133 43.60902256 | |
| 134 43.28358209 | |
| 135 42.96296296 | |
| 136 43.38235294 | |
| 137 43.79562044 | |
| 138 43.47826087 | |
| 139 43.88489209 | |
| 140 44.28571429 | |
| 141 43.97163121 | |
| 142 44.36619718 | |
| 143 44.75524476 | |
| 144 44.44444444 | |
| 145 44.13793103 | |
| 146 44.52054795 | |
| 147 44.21768707 | |
| 148 44.59459459 | |
| 149 44.96644295 | |
| 150 44.66666667 | |
| 151 44.37086093 | |
| 152 44.73684211 | |
| 153 44.44444444 | |
| 154 44.15584416 | |
| 155 43.87096774 | |
| 156 43.58974359 | |
| 157 43.94904459 | |
| 158 44.30379747 | |
| 159 44.02515723 | |
| 160 44.37500000 | |
| 161 44.09937888 | |
| 162 43.82716049 | |
| 163 43.55828221 | |
| 164 43.29268293 | |
| 165 43.63636364 | |
| 166 43.37349398 | |
| 167 43.71257485 | |
| 168 43.45238095 | |
| 169 43.78698225 | |
| 170 43.52941176 | |
| 171 43.85964912 | |
| 172 43.60465116 | |
| 173 43.35260116 | |
| 174 43.10344828 | |
| 175 42.85714286 | |
| 176 42.61363636 | |
| 177 42.37288136 | |
| 178 42.13483146 | |
| 179 42.45810056 | |
| 180 42.22222222 | |
| 181 41.98895028 | |
| 182 41.75824176 | |
| 183 42.07650273 | |
| 184 41.84782609 | |
| 185 42.16216216 | |
| 186 42.47311828 | |
| 187 42.24598930 | |
| 188 42.02127660 | |
| 189 42.32804233 | |
| 190 42.10526316 | |
| 191 41.88481675 | |
| 192 41.66666667 | |
| 193 41.45077720 | |
| 194 41.23711340 | |
| 195 41.53846154 | |
| 196 41.32653061 | |
| 197 41.62436548 | |
| 198 41.41414141 | |
| 199 41.20603015 | |
| 200 41.00000000 | |
| 201 40.79601990 | |
| 202 40.59405941 | |
| 203 40.39408867 | |
| 204 40.19607843 | |
| 205 40.48780488 | |
| 206 40.29126214 | |
| 207 40.57971014 | |
| 208 40.38461538 | |
| 209 40.19138756 | |
| 210 40.00000000 | |
| 211 40.28436019 | |
| 212 40.09433962 | |
| 213 39.90610329 | |
| 214 39.71962617 | |
| 215 40.00000000 | |
| 216 40.27777778 | |
| 217 40.09216590 | |
| 218 40.36697248 | |
| 219 40.63926941 | |
| 220 40.90909091 | |
| 221 41.17647059 | |
| 222 40.99099099 | |
| 223 41.25560538 | |
| 224 41.51785714 | |
| 225 41.77777778 | |
| 226 42.03539823 | |
| 227 41.85022026 | |
| 228 42.10526316 | |
| 229 41.92139738 | |
| 230 41.73913043 | |
| 231 41.55844156 | |
| 232 41.81034483 | |
| 233 41.63090129 | |
| 234 41.88034188 | |
| 235 41.70212766 | |
| 236 41.52542373 | |
| 237 41.35021097 | |
| 238 41.17647059 | |
| 239 41.00418410 | |
| 240 41.25000000 | |
| 241 41.07883817 | |
| 242 41.32231405 | |
| 243 41.56378601 | |
| 244 41.39344262 | |
| 245 41.63265306 | |
| 246 41.46341463 | |
| 247 41.70040486 | |
| 248 41.93548387 | |
| 249 41.76706827 | |
| 250 41.60000000 | |
| 251 41.43426295 | |
| 252 41.26984127 | |
| 253 41.10671937 | |
| 254 40.94488189 | |
| 255 40.78431373 | |
| 256 40.62500000 | |
| 257 40.85603113 | |
| 258 40.69767442 | |
| 259 40.54054054 | |
| 260 40.38461538 | |
| 261 40.22988506 | |
| 262 40.07633588 | |
| 263 39.92395437 | |
| 264 40.15151515 | |
| 265 40.37735849 | |
| 266 40.22556391 | |
| 267 40.07490637 | |
| 268 39.92537313 | |
| 269 40.14869888 | |
| 270 40.37037037 | |
| 271 40.22140221 | |
| 272 40.44117647 | |
| 273 40.29304029 | |
| 274 40.14598540 | |
| 275 40.00000000 | |
| 276 40.21739130 | |
| 277 40.43321300 | |
| 278 40.64748201 | |
| 279 40.50179211 | |
| 280 40.71428571 | |
| 281 40.56939502 | |
| 282 40.42553191 | |
| 283 40.28268551 | |
| 284 40.14084507 | |
| 285 40.00000000 | |
| 286 39.86013986 | |
| 287 40.06968641 | |
| 288 39.93055556 | |
| 289 39.79238754 | |
| 290 40.00000000 | |
| 291 40.20618557 | |
| 292 40.41095890 | |
| 293 40.61433447 | |
| 294 40.47619048 | |
| 295 40.33898305 | |
| 296 40.20270270 | |
| 297 40.06734007 | |
| 298 40.26845638 | |
| 299 40.46822742 | |
| 300 40.66666667 | |
| 301 40.53156146 | |
| 302 40.72847682 | |
| 303 40.59405941 | |
| 304 40.46052632 | |
| 305 40.65573770 | |
| 306 40.52287582 | |
| 307 40.71661238 | |
| 308 40.58441558 | |
| 309 40.45307443 | |
| 310 40.64516129 | |
| 311 40.51446945 | |
| 312 40.70512821 | |
| 313 40.89456869 | |
| 314 41.08280255 | |
| 315 41.26984127 | |
| 316 41.13924051 | |
| 317 41.32492114 | |
| 318 41.19496855 | |
| 319 41.37931034 | |
| 320 41.25000000 | |
| 321 41.12149533 | |
| 322 40.99378882 | |
| 323 40.86687307 | |
| 324 40.74074074 | |
| 325 40.92307692 | |
| 326 40.79754601 | |
| 327 40.97859327 | |
| 328 40.85365854 | |
| 329 40.72948328 | |
| 330 40.60606061 | |
| 331 40.48338369 | |
| 332 40.66265060 | |
| 333 40.54054054 | |
| 334 40.41916168 | |
| 335 40.59701493 | |
| 336 40.77380952 | |
| 337 40.65281899 | |
| 338 40.53254438 | |
| 339 40.41297935 | |
| 340 40.58823529 | |
| 341 40.76246334 | |
| 342 40.93567251 | |
| 343 40.81632653 | |
| 344 40.69767442 | |
| 345 40.57971014 | |
| 346 40.75144509 | |
| 347 40.92219020 | |
| 348 40.80459770 | |
| 349 40.97421203 | |
| 350 41.14285714 | |
| 351 41.02564103 | |
| 352 40.90909091 | |
| 353 41.07648725 | |
| 354 41.24293785 | |
| 355 41.12676056 | |
| 356 41.29213483 | |
| 357 41.45658263 | |
| 358 41.62011173 | |
| 359 41.50417827 | |
| 360 41.66666667 | |
| 361 41.55124654 | |
| 362 41.71270718 | |
| 363 41.87327824 | |
| 364 41.75824176 | |
| 365 41.64383562 | |
| 366 41.80327869 | |
| 367 41.68937330 | |
| 368 41.57608696 | |
| 369 41.46341463 | |
| 370 41.62162162 | |
| 371 41.77897574 | |
| 372 41.66666667 | |
| 373 41.55495979 | |
| 374 41.71122995 | |
| 375 41.86666667 | |
| 376 41.75531915 | |
| 377 41.64456233 | |
| 378 41.79894180 | |
| 379 41.68865435 | |
| 380 41.57894737 | |
| 381 41.73228346 | |
| 382 41.88481675 | |
| 383 42.03655352 | |
| 384 41.92708333 | |
| 385 42.07792208 | |
| 386 41.96891192 | |
| 387 41.86046512 | |
| 388 41.75257732 | |
| 389 41.90231362 | |
| 390 42.05128205 | |
| 391 42.19948849 | |
| 392 42.34693878 | |
| 393 42.23918575 | |
| 394 42.13197970 | |
| 395 42.27848101 | |
| 396 42.42424242 | |
| 397 42.56926952 | |
| 398 42.46231156 | |
| 399 42.60651629 | |
| 400 42.50000000 | |
| 401 42.64339152 | |
| 402 42.53731343 | |
| 403 42.43176179 | |
| 404 42.32673267 | |
| 405 42.22222222 | |
| 406 42.11822660 | |
| 407 42.01474201 | |
| 408 41.91176471 | |
| 409 42.05378973 | |
| 410 41.95121951 | |
| 411 41.84914842 | |
| 412 41.74757282 | |
| 413 41.64648910 | |
| 414 41.54589372 | |
| 415 41.68674699 | |
| 416 41.82692308 | |
| 417 41.72661871 | |
| 418 41.62679426 | |
| 419 41.76610979 | |
| 420 41.90476190 | |
| 421 41.80522565 | |
| 422 41.70616114 | |
| 423 41.60756501 | |
| 424 41.74528302 | |
| 425 41.88235294 | |
| 426 42.01877934 | |
| 427 41.92037471 | |
| 428 41.82242991 | |
| 429 41.95804196 | |
| 430 41.86046512 | |
| 431 41.99535963 | |
| 432 42.12962963 | |
| 433 42.03233256 | |
| 434 41.93548387 | |
| 435 41.83908046 | |
| 436 41.74311927 | |
| 437 41.64759725 | |
| 438 41.78082192 | |
| 439 41.91343964 | |
| 440 41.81818182 | |
| 441 41.72335601 | |
| 442 41.62895928 | |
| 443 41.53498871 | |
| 444 41.44144144 | |
| 445 41.34831461 | |
| 446 41.25560538 | |
| 447 41.38702461 | |
| 448 41.29464286 | |
| 449 41.20267261 | |
| 450 41.33333333 | |
| 451 41.24168514 | |
| 452 41.37168142 | |
| 453 41.28035320 | |
| 454 41.18942731 | |
| 455 41.09890110 | |
| 456 41.22807018 | |
| 457 41.35667396 | |
| 458 41.26637555 | |
| 459 41.17647059 | |
| 460 41.30434783 | |
| 461 41.21475054 | |
| 462 41.12554113 | |
| 463 41.03671706 | |
| 464 41.16379310 | |
| 465 41.07526882 | |
| 466 40.98712446 | |
| 467 41.11349036 | |
| 468 41.02564103 | |
| 469 41.15138593 | |
| 470 41.06382979 | |
| 471 40.97664544 | |
| 472 40.88983051 | |
| 473 40.80338266 | |
| 474 40.71729958 | |
| 475 40.63157895 | |
| 476 40.75630252 | |
| 477 40.67085954 | |
| 478 40.79497908 | |
| 479 40.91858038 | |
| 480 41.04166667 | |
| 481 40.95634096 | |
| 482 40.87136929 | |
| 483 40.78674948 | |
| 484 40.70247934 | |
| 485 40.61855670 | |
| 486 40.53497942 | |
| 487 40.65708419 | |
| 488 40.57377049 | |
| 489 40.49079755 | |
| 490 40.61224490 | |
| 491 40.52953157 | |
| 492 40.44715447 | |
| 493 40.36511156 | |
| 494 40.48582996 | |
| 495 40.60606061 | |
| 496 40.72580645 | |
| 497 40.64386318 | |
| 498 40.56224900 | |
| 499 40.48096192 | |
| 500 40.40000000 | |
| 501 40.31936128 | |
| 502 40.23904382 | |
| 503 40.15904573 | |
| 504 40.27777778 | |
| 505 40.19801980 | |
| 506 40.31620553 | |
| 507 40.23668639 | |
| 508 40.35433071 | |
| 509 40.27504912 | |
| 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 39.96478873 | |
| 569 39.89455185 | |
| 570 40.00000000 | |
| 571 39.92994746 | |
| 572 40.03496503 | |
| 573 39.96509599 | |
| 574 39.89547038 | |
| 575 39.82608696 | |
| 576 39.93055556 | |
| 577 40.03466205 | |
| 578 39.96539792 | |
| 579 39.89637306 | |
| 580 40.00000000 | |
| 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 40.00000000 | |
| 616 40.09740260 | |
| 617 40.03241491 | |
| 618 40.12944984 | |
| 619 40.06462036 | |
| 620 40.00000000 | |
| 621 39.93558776 | |
| 622 40.03215434 | |
| 623 39.96789727 | |
| 624 39.90384615 | |
| 625 39.84000000 | |
| 626 39.93610224 | |
| 627 39.87240829 | |
| 628 39.80891720 | |
| 629 39.90461049 | |
| 630 39.84126984 | |
| 631 39.93660856 | |
| 632 40.03164557 | |
| 633 39.96840442 | |
| 634 39.90536278 | |
| 635 39.84251969 | |
| 636 39.77987421 | |
| 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 39.53846154 | |
| 651 39.47772657 | |
| 652 39.57055215 | |
| 653 39.50995406 | |
| 654 39.60244648 | |
| 655 39.54198473 | |
| 656 39.63414634 | |
| 657 39.57382040 | |
| 658 39.66565350 | |
| 659 39.60546282 | |
| 660 39.54545455 | |
| 661 39.48562784 | |
| 662 39.42598187 | |
| 663 39.36651584 | |
| 664 39.45783133 | |
| 665 39.54887218 | |
| 666 39.48948949 | |
| 667 39.58020990 | |
| 668 39.67065868 | |
| 669 39.76083707 | |
| 670 39.70149254 | |
| 671 39.64232489 | |
| 672 39.58333333 | |
| 673 39.52451709 | |
| 674 39.46587537 | |
| 675 39.40740741 | |
| 676 39.34911243 | |
| 677 39.29098966 | |
| 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 38.79310345 | |
| 697 38.73744620 | |
| 698 38.68194842 | |
| 699 38.76967096 | |
| 700 38.71428571 | |
| 701 38.80171184 | |
| 702 38.88888889 | |
| 703 38.97581792 | |
| 704 38.92045455 | |
| 705 38.86524823 | |
| 706 38.81019830 | |
| 707 38.75530410 | |
| 708 38.70056497 | |
| 709 38.78702398 | |
| 710 38.87323944 | |
| 711 38.95921238 | |
| 712 38.90449438 | |
| 713 38.99018233 | |
| 714 39.07563025 | |
| 715 39.02097902 | |
| 716 38.96648045 | |
| 717 38.91213389 | |
| 718 38.85793872 | |
| 719 38.94297636 | |
| 720 38.88888889 | |
| 721 38.83495146 | |
| 722 38.91966759 | |
| 723 39.00414938 | |
| 724 38.95027624 | |
| 725 39.03448276 | |
| 726 38.98071625 | |
| 727 38.92709766 | |
| 728 38.87362637 | |
| 729 38.82030178 | |
| 730 38.76712329 | |
| 731 38.71409029 | |
| 732 38.79781421 | |
| 733 38.88130969 | |
| 734 38.96457766 | |
| 735 38.91156463 | |
| 736 38.85869565 | |
| 737 38.94165536 | |
| 738 38.88888889 | |
| 739 38.97158322 | |
| 740 38.91891892 | |
| 741 39.00134953 | |
| 742 39.08355795 | |
| 743 39.03095559 | |
| 744 39.11290323 | |
| 745 39.06040268 | |
| 746 39.00804290 | |
| 747 38.95582329 | |
| 748 38.90374332 | |
| 749 38.85180240 | |
| 750 38.93333333 | |
| Final result: 38.9333 +/- 1.7816 | |
| Random chance: 25.0000 +/- 1.5822 | |