| 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 40.00000000 | |
| 16 43.75000000 | |
| 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 37.03703704 | |
| 28 39.28571429 | |
| 29 41.37931034 | |
| 30 43.33333333 | |
| 31 45.16129032 | |
| 32 43.75000000 | |
| 33 42.42424242 | |
| 34 44.11764706 | |
| 35 45.71428571 | |
| 36 44.44444444 | |
| 37 43.24324324 | |
| 38 42.10526316 | |
| 39 41.02564103 | |
| 40 42.50000000 | |
| 41 41.46341463 | |
| 42 40.47619048 | |
| 43 39.53488372 | |
| 44 38.63636364 | |
| 45 37.77777778 | |
| 46 36.95652174 | |
| 47 36.17021277 | |
| 48 37.50000000 | |
| 49 38.77551020 | |
| 50 40.00000000 | |
| 51 39.21568627 | |
| 52 40.38461538 | |
| 53 39.62264151 | |
| 54 38.88888889 | |
| 55 40.00000000 | |
| 56 41.07142857 | |
| 57 42.10526316 | |
| 58 41.37931034 | |
| 59 40.67796610 | |
| 60 40.00000000 | |
| 61 40.98360656 | |
| 62 40.32258065 | |
| 63 39.68253968 | |
| 64 39.06250000 | |
| 65 38.46153846 | |
| 66 37.87878788 | |
| 67 38.80597015 | |
| 68 38.23529412 | |
| 69 37.68115942 | |
| 70 38.57142857 | |
| 71 39.43661972 | |
| 72 38.88888889 | |
| 73 38.35616438 | |
| 74 39.18918919 | |
| 75 40.00000000 | |
| 76 40.78947368 | |
| 77 41.55844156 | |
| 78 42.30769231 | |
| 79 41.77215190 | |
| 80 41.25000000 | |
| 81 41.97530864 | |
| 82 41.46341463 | |
| 83 42.16867470 | |
| 84 42.85714286 | |
| 85 42.35294118 | |
| 86 41.86046512 | |
| 87 42.52873563 | |
| 88 43.18181818 | |
| 89 42.69662921 | |
| 90 42.22222222 | |
| 91 41.75824176 | |
| 92 41.30434783 | |
| 93 40.86021505 | |
| 94 40.42553191 | |
| 95 41.05263158 | |
| 96 41.66666667 | |
| 97 41.23711340 | |
| 98 40.81632653 | |
| 99 40.40404040 | |
| 100 40.00000000 | |
| 101 40.59405941 | |
| 102 40.19607843 | |
| 103 39.80582524 | |
| 104 40.38461538 | |
| 105 40.95238095 | |
| 106 40.56603774 | |
| 107 40.18691589 | |
| 108 39.81481481 | |
| 109 39.44954128 | |
| 110 39.09090909 | |
| 111 38.73873874 | |
| 112 39.28571429 | |
| 113 38.93805310 | |
| 114 39.47368421 | |
| 115 40.00000000 | |
| 116 39.65517241 | |
| 117 40.17094017 | |
| 118 39.83050847 | |
| 119 39.49579832 | |
| 120 39.16666667 | |
| 121 39.66942149 | |
| 122 39.34426230 | |
| 123 39.02439024 | |
| 124 38.70967742 | |
| 125 39.20000000 | |
| 126 38.88888889 | |
| 127 38.58267717 | |
| 128 38.28125000 | |
| 129 37.98449612 | |
| 130 37.69230769 | |
| 131 37.40458015 | |
| 132 37.87878788 | |
| 133 37.59398496 | |
| 134 37.31343284 | |
| 135 37.03703704 | |
| 136 36.76470588 | |
| 137 36.49635036 | |
| 138 36.23188406 | |
| 139 35.97122302 | |
| 140 36.42857143 | |
| 141 36.87943262 | |
| 142 37.32394366 | |
| 143 37.76223776 | |
| 144 37.50000000 | |
| 145 37.93103448 | |
| 146 38.35616438 | |
| 147 38.09523810 | |
| 148 38.51351351 | |
| 149 38.25503356 | |
| 150 38.66666667 | |
| 151 38.41059603 | |
| 152 38.15789474 | |
| 153 37.90849673 | |
| 154 37.66233766 | |
| 155 37.41935484 | |
| 156 37.17948718 | |
| 157 37.57961783 | |
| 158 37.34177215 | |
| 159 37.10691824 | |
| 160 37.50000000 | |
| 161 37.26708075 | |
| 162 37.03703704 | |
| 163 37.42331288 | |
| 164 37.80487805 | |
| 165 38.18181818 | |
| 166 37.95180723 | |
| 167 38.32335329 | |
| 168 38.09523810 | |
| 169 38.46153846 | |
| 170 38.23529412 | |
| 171 38.59649123 | |
| 172 38.37209302 | |
| 173 38.15028902 | |
| 174 37.93103448 | |
| 175 37.71428571 | |
| 176 37.50000000 | |
| 177 37.28813559 | |
| 178 37.07865169 | |
| 179 37.43016760 | |
| 180 37.22222222 | |
| 181 37.01657459 | |
| 182 36.81318681 | |
| 183 37.15846995 | |
| 184 36.95652174 | |
| 185 37.29729730 | |
| 186 37.63440860 | |
| 187 37.43315508 | |
| 188 37.76595745 | |
| 189 37.56613757 | |
| 190 37.36842105 | |
| 191 37.17277487 | |
| 192 36.97916667 | |
| 193 36.78756477 | |
| 194 37.11340206 | |
| 195 37.43589744 | |
| 196 37.75510204 | |
| 197 37.56345178 | |
| 198 37.87878788 | |
| 199 37.68844221 | |
| 200 38.00000000 | |
| 201 37.81094527 | |
| 202 37.62376238 | |
| 203 37.43842365 | |
| 204 37.25490196 | |
| 205 37.56097561 | |
| 206 37.37864078 | |
| 207 37.68115942 | |
| 208 37.50000000 | |
| 209 37.32057416 | |
| 210 37.14285714 | |
| 211 37.44075829 | |
| 212 37.26415094 | |
| 213 37.08920188 | |
| 214 36.91588785 | |
| 215 37.20930233 | |
| 216 37.03703704 | |
| 217 36.86635945 | |
| 218 36.69724771 | |
| 219 36.98630137 | |
| 220 36.81818182 | |
| 221 36.65158371 | |
| 222 36.48648649 | |
| 223 36.77130045 | |
| 224 37.05357143 | |
| 225 37.33333333 | |
| 226 37.61061947 | |
| 227 37.44493392 | |
| 228 37.71929825 | |
| 229 37.55458515 | |
| 230 37.39130435 | |
| 231 37.22943723 | |
| 232 37.50000000 | |
| 233 37.33905579 | |
| 234 37.17948718 | |
| 235 37.02127660 | |
| 236 36.86440678 | |
| 237 36.70886076 | |
| 238 36.55462185 | |
| 239 36.40167364 | |
| 240 36.25000000 | |
| 241 36.09958506 | |
| 242 36.36363636 | |
| 243 36.62551440 | |
| 244 36.47540984 | |
| 245 36.73469388 | |
| 246 36.58536585 | |
| 247 36.84210526 | |
| 248 36.69354839 | |
| 249 36.54618474 | |
| 250 36.40000000 | |
| 251 36.25498008 | |
| 252 36.11111111 | |
| 253 35.96837945 | |
| 254 35.82677165 | |
| 255 36.07843137 | |
| 256 36.32812500 | |
| 257 36.57587549 | |
| 258 36.43410853 | |
| 259 36.67953668 | |
| 260 36.92307692 | |
| 261 36.78160920 | |
| 262 37.02290076 | |
| 263 37.26235741 | |
| 264 37.12121212 | |
| 265 36.98113208 | |
| 266 36.84210526 | |
| 267 36.70411985 | |
| 268 36.56716418 | |
| 269 36.80297398 | |
| 270 36.66666667 | |
| 271 36.53136531 | |
| 272 36.76470588 | |
| 273 36.63003663 | |
| 274 36.49635036 | |
| 275 36.36363636 | |
| 276 36.59420290 | |
| 277 36.82310469 | |
| 278 36.69064748 | |
| 279 36.55913978 | |
| 280 36.78571429 | |
| 281 36.65480427 | |
| 282 36.52482270 | |
| 283 36.39575972 | |
| 284 36.26760563 | |
| 285 36.49122807 | |
| 286 36.36363636 | |
| 287 36.23693380 | |
| 288 36.11111111 | |
| 289 35.98615917 | |
| 290 36.20689655 | |
| 291 36.42611684 | |
| 292 36.64383562 | |
| 293 36.51877133 | |
| 294 36.39455782 | |
| 295 36.27118644 | |
| 296 36.14864865 | |
| 297 36.02693603 | |
| 298 36.24161074 | |
| 299 36.12040134 | |
| 300 36.33333333 | |
| 301 36.21262458 | |
| 302 36.42384106 | |
| 303 36.30363036 | |
| 304 36.51315789 | |
| 305 36.72131148 | |
| 306 36.60130719 | |
| 307 36.80781759 | |
| 308 36.68831169 | |
| 309 36.56957929 | |
| 310 36.45161290 | |
| 311 36.65594855 | |
| 312 36.85897436 | |
| 313 37.06070288 | |
| 314 36.94267516 | |
| 315 36.82539683 | |
| 316 36.70886076 | |
| 317 36.90851735 | |
| 318 36.79245283 | |
| 319 36.99059561 | |
| 320 36.87500000 | |
| 321 36.76012461 | |
| 322 36.64596273 | |
| 323 36.53250774 | |
| 324 36.41975309 | |
| 325 36.61538462 | |
| 326 36.50306748 | |
| 327 36.69724771 | |
| 328 36.58536585 | |
| 329 36.77811550 | |
| 330 36.66666667 | |
| 331 36.55589124 | |
| 332 36.74698795 | |
| 333 36.93693694 | |
| 334 36.82634731 | |
| 335 37.01492537 | |
| 336 36.90476190 | |
| 337 36.79525223 | |
| 338 36.68639053 | |
| 339 36.57817109 | |
| 340 36.76470588 | |
| 341 36.95014663 | |
| 342 37.13450292 | |
| 343 37.02623907 | |
| 344 36.91860465 | |
| 345 36.81159420 | |
| 346 36.99421965 | |
| 347 37.17579251 | |
| 348 37.06896552 | |
| 349 36.96275072 | |
| 350 36.85714286 | |
| 351 36.75213675 | |
| 352 36.64772727 | |
| 353 36.82719547 | |
| 354 36.72316384 | |
| 355 36.61971831 | |
| 356 36.79775281 | |
| 357 36.97478992 | |
| 358 36.87150838 | |
| 359 36.76880223 | |
| 360 36.94444444 | |
| 361 37.11911357 | |
| 362 37.29281768 | |
| 363 37.46556474 | |
| 364 37.36263736 | |
| 365 37.26027397 | |
| 366 37.43169399 | |
| 367 37.32970027 | |
| 368 37.22826087 | |
| 369 37.12737127 | |
| 370 37.29729730 | |
| 371 37.19676550 | |
| 372 37.09677419 | |
| 373 36.99731903 | |
| 374 36.89839572 | |
| 375 37.06666667 | |
| 376 36.96808511 | |
| 377 36.87002653 | |
| 378 37.03703704 | |
| 379 36.93931398 | |
| 380 36.84210526 | |
| 381 37.00787402 | |
| 382 36.91099476 | |
| 383 37.07571802 | |
| 384 36.97916667 | |
| 385 36.88311688 | |
| 386 36.78756477 | |
| 387 36.69250646 | |
| 388 36.59793814 | |
| 389 36.76092545 | |
| 390 36.92307692 | |
| 391 37.08439898 | |
| 392 37.24489796 | |
| 393 37.15012723 | |
| 394 37.05583756 | |
| 395 37.21518987 | |
| 396 37.37373737 | |
| 397 37.53148615 | |
| 398 37.43718593 | |
| 399 37.59398496 | |
| 400 37.50000000 | |
| 401 37.65586035 | |
| 402 37.81094527 | |
| 403 37.71712159 | |
| 404 37.62376238 | |
| 405 37.77777778 | |
| 406 37.68472906 | |
| 407 37.59213759 | |
| 408 37.74509804 | |
| 409 37.89731051 | |
| 410 37.80487805 | |
| 411 37.71289538 | |
| 412 37.62135922 | |
| 413 37.53026634 | |
| 414 37.68115942 | |
| 415 37.83132530 | |
| 416 37.98076923 | |
| 417 37.88968825 | |
| 418 37.79904306 | |
| 419 37.94749403 | |
| 420 37.85714286 | |
| 421 37.76722090 | |
| 422 37.67772512 | |
| 423 37.58865248 | |
| 424 37.73584906 | |
| 425 37.64705882 | |
| 426 37.55868545 | |
| 427 37.47072600 | |
| 428 37.38317757 | |
| 429 37.52913753 | |
| 430 37.44186047 | |
| 431 37.58700696 | |
| 432 37.73148148 | |
| 433 37.64434180 | |
| 434 37.55760369 | |
| 435 37.47126437 | |
| 436 37.38532110 | |
| 437 37.52860412 | |
| 438 37.67123288 | |
| 439 37.81321185 | |
| 440 37.72727273 | |
| 441 37.86848073 | |
| 442 37.78280543 | |
| 443 37.69751693 | |
| 444 37.83783784 | |
| 445 37.75280899 | |
| 446 37.66816143 | |
| 447 37.80760626 | |
| 448 37.72321429 | |
| 449 37.63919822 | |
| 450 37.55555556 | |
| 451 37.69401330 | |
| 452 37.61061947 | |
| 453 37.74834437 | |
| 454 37.66519824 | |
| 455 37.58241758 | |
| 456 37.71929825 | |
| 457 37.63676149 | |
| 458 37.55458515 | |
| 459 37.47276688 | |
| 460 37.60869565 | |
| 461 37.74403471 | |
| 462 37.66233766 | |
| 463 37.79697624 | |
| 464 37.93103448 | |
| 465 37.84946237 | |
| 466 37.76824034 | |
| 467 37.90149893 | |
| 468 37.82051282 | |
| 469 37.73987207 | |
| 470 37.65957447 | |
| 471 37.57961783 | |
| 472 37.50000000 | |
| 473 37.63213531 | |
| 474 37.55274262 | |
| 475 37.47368421 | |
| 476 37.60504202 | |
| 477 37.52620545 | |
| 478 37.65690377 | |
| 479 37.78705637 | |
| 480 37.91666667 | |
| 481 38.04573805 | |
| 482 37.96680498 | |
| 483 38.09523810 | |
| 484 38.22314050 | |
| 485 38.14432990 | |
| 486 38.27160494 | |
| 487 38.39835729 | |
| 488 38.31967213 | |
| 489 38.24130879 | |
| 490 38.36734694 | |
| 491 38.28920570 | |
| 492 38.21138211 | |
| 493 38.13387424 | |
| 494 38.25910931 | |
| 495 38.38383838 | |
| 496 38.50806452 | |
| 497 38.43058350 | |
| 498 38.35341365 | |
| 499 38.47695391 | |
| 500 38.60000000 | |
| 501 38.52295409 | |
| 502 38.44621514 | |
| 503 38.36978131 | |
| 504 38.49206349 | |
| 505 38.41584158 | |
| 506 38.53754941 | |
| 507 38.46153846 | |
| 508 38.58267717 | |
| 509 38.50687623 | |
| 510 38.62745098 | |
| 511 38.55185910 | |
| 512 38.47656250 | |
| 513 38.40155945 | |
| 514 38.32684825 | |
| 515 38.44660194 | |
| 516 38.56589147 | |
| 517 38.49129594 | |
| 518 38.61003861 | |
| 519 38.53564547 | |
| 520 38.46153846 | |
| 521 38.38771593 | |
| 522 38.50574713 | |
| 523 38.43212237 | |
| 524 38.54961832 | |
| 525 38.47619048 | |
| 526 38.40304183 | |
| 527 38.33017078 | |
| 528 38.25757576 | |
| 529 38.18525520 | |
| 530 38.30188679 | |
| 531 38.22975518 | |
| 532 38.15789474 | |
| 533 38.27392120 | |
| 534 38.38951311 | |
| 535 38.50467290 | |
| 536 38.43283582 | |
| 537 38.54748603 | |
| 538 38.66171004 | |
| 539 38.58998145 | |
| 540 38.51851852 | |
| 541 38.44731978 | |
| 542 38.56088561 | |
| 543 38.48987109 | |
| 544 38.41911765 | |
| 545 38.34862385 | |
| 546 38.27838828 | |
| 547 38.20840951 | |
| 548 38.32116788 | |
| 549 38.25136612 | |
| 550 38.18181818 | |
| 551 38.11252269 | |
| 552 38.04347826 | |
| 553 37.97468354 | |
| 554 37.90613718 | |
| 555 37.83783784 | |
| 556 37.94964029 | |
| 557 38.06104129 | |
| 558 38.17204301 | |
| 559 38.28264758 | |
| 560 38.21428571 | |
| 561 38.14616756 | |
| 562 38.07829181 | |
| 563 38.18827709 | |
| 564 38.12056738 | |
| 565 38.23008850 | |
| 566 38.33922261 | |
| 567 38.27160494 | |
| 568 38.20422535 | |
| 569 38.13708260 | |
| 570 38.07017544 | |
| 571 38.00350263 | |
| 572 37.93706294 | |
| 573 37.87085515 | |
| 574 37.80487805 | |
| 575 37.73913043 | |
| 576 37.84722222 | |
| 577 37.95493934 | |
| 578 37.88927336 | |
| 579 37.82383420 | |
| 580 37.93103448 | |
| 581 37.86574871 | |
| 582 37.80068729 | |
| 583 37.90737564 | |
| 584 38.01369863 | |
| 585 38.11965812 | |
| 586 38.05460751 | |
| 587 37.98977853 | |
| 588 37.92517007 | |
| 589 37.86078098 | |
| 590 37.79661017 | |
| 591 37.73265651 | |
| 592 37.66891892 | |
| 593 37.60539629 | |
| 594 37.71043771 | |
| 595 37.64705882 | |
| 596 37.75167785 | |
| 597 37.68844221 | |
| 598 37.62541806 | |
| 599 37.72954925 | |
| 600 37.66666667 | |
| 601 37.60399334 | |
| 602 37.54152824 | |
| 603 37.64510779 | |
| 604 37.58278146 | |
| 605 37.68595041 | |
| 606 37.62376238 | |
| 607 37.72652389 | |
| 608 37.66447368 | |
| 609 37.60262726 | |
| 610 37.54098361 | |
| 611 37.47954173 | |
| 612 37.41830065 | |
| 613 37.52039152 | |
| 614 37.62214984 | |
| 615 37.56097561 | |
| 616 37.66233766 | |
| 617 37.76337115 | |
| 618 37.70226537 | |
| 619 37.64135703 | |
| 620 37.58064516 | |
| 621 37.52012882 | |
| 622 37.45980707 | |
| 623 37.39967897 | |
| 624 37.50000000 | |
| 625 37.44000000 | |
| 626 37.53993610 | |
| 627 37.48006380 | |
| 628 37.42038217 | |
| 629 37.51987281 | |
| 630 37.61904762 | |
| 631 37.71790808 | |
| 632 37.81645570 | |
| 633 37.75671406 | |
| 634 37.69716088 | |
| 635 37.63779528 | |
| 636 37.57861635 | |
| 637 37.51962323 | |
| 638 37.46081505 | |
| 639 37.40219092 | |
| 640 37.50000000 | |
| 641 37.44149766 | |
| 642 37.38317757 | |
| 643 37.32503888 | |
| 644 37.42236025 | |
| 645 37.36434109 | |
| 646 37.30650155 | |
| 647 37.24884080 | |
| 648 37.19135802 | |
| 649 37.13405239 | |
| 650 37.07692308 | |
| 651 37.01996928 | |
| 652 36.96319018 | |
| 653 36.90658499 | |
| 654 37.00305810 | |
| 655 36.94656489 | |
| 656 37.04268293 | |
| 657 36.98630137 | |
| 658 37.08206687 | |
| 659 37.17754173 | |
| 660 37.12121212 | |
| 661 37.06505295 | |
| 662 37.16012085 | |
| 663 37.10407240 | |
| 664 37.04819277 | |
| 665 36.99248120 | |
| 666 36.93693694 | |
| 667 37.03148426 | |
| 668 37.12574850 | |
| 669 37.21973094 | |
| 670 37.16417910 | |
| 671 37.10879285 | |
| 672 37.05357143 | |
| 673 36.99851412 | |
| 674 36.94362018 | |
| 675 36.88888889 | |
| 676 36.83431953 | |
| 677 36.77991137 | |
| 678 36.87315634 | |
| 679 36.81885125 | |
| 680 36.91176471 | |
| 681 37.00440529 | |
| 682 36.95014663 | |
| 683 36.89604685 | |
| 684 36.98830409 | |
| 685 36.93430657 | |
| 686 36.88046647 | |
| 687 36.82678311 | |
| 688 36.77325581 | |
| 689 36.86502177 | |
| 690 36.81159420 | |
| 691 36.75832127 | |
| 692 36.70520231 | |
| 693 36.65223665 | |
| 694 36.59942363 | |
| 695 36.54676259 | |
| 696 36.63793103 | |
| 697 36.58536585 | |
| 698 36.53295129 | |
| 699 36.62374821 | |
| 700 36.57142857 | |
| 701 36.66191155 | |
| 702 36.75213675 | |
| 703 36.69985775 | |
| 704 36.64772727 | |
| 705 36.59574468 | |
| 706 36.54390935 | |
| 707 36.49222065 | |
| 708 36.44067797 | |
| 709 36.38928068 | |
| 710 36.33802817 | |
| 711 36.42756681 | |
| 712 36.51685393 | |
| 713 36.60589060 | |
| 714 36.69467787 | |
| 715 36.64335664 | |
| 716 36.59217877 | |
| 717 36.68061367 | |
| 718 36.62952646 | |
| 719 36.71766342 | |
| 720 36.66666667 | |
| 721 36.61581137 | |
| 722 36.56509695 | |
| 723 36.65283541 | |
| 724 36.74033149 | |
| 725 36.82758621 | |
| 726 36.77685950 | |
| 727 36.72627235 | |
| 728 36.81318681 | |
| 729 36.76268861 | |
| 730 36.71232877 | |
| 731 36.66210670 | |
| 732 36.61202186 | |
| 733 36.69849932 | |
| 734 36.78474114 | |
| 735 36.73469388 | |
| 736 36.68478261 | |
| 737 36.77069199 | |
| 738 36.72086721 | |
| 739 36.80649526 | |
| 740 36.89189189 | |
| 741 36.84210526 | |
| 742 36.79245283 | |
| 743 36.87752355 | |
| 744 36.96236559 | |
| 745 36.91275168 | |
| 746 36.86327078 | |
| 747 36.94779116 | |
| 748 36.89839572 | |
| 749 36.84913218 | |
| 750 36.93333333 | |
| Final result: 36.9333 +/- 1.7635 | |
| Random chance: 25.0000 +/- 1.5822 | |