| 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 869 tasks in prompt | |
| multiple_choice_score: selecting 750 random tasks from 869 tasks available | |
| multiple_choice_score: preparing task data...done | |
| multiple_choice_score : calculating TruthfulQA score over 750 tasks. | |
| task acc_norm | |
| 1 100.00000000 | |
| 2 100.00000000 | |
| 3 100.00000000 | |
| 4 75.00000000 | |
| 5 80.00000000 | |
| 6 83.33333333 | |
| 7 85.71428571 | |
| 8 87.50000000 | |
| 9 77.77777778 | |
| 10 80.00000000 | |
| 11 72.72727273 | |
| 12 75.00000000 | |
| 13 69.23076923 | |
| 14 71.42857143 | |
| 15 73.33333333 | |
| 16 75.00000000 | |
| 17 76.47058824 | |
| 18 72.22222222 | |
| 19 68.42105263 | |
| 20 65.00000000 | |
| 21 66.66666667 | |
| 22 68.18181818 | |
| 23 69.56521739 | |
| 24 70.83333333 | |
| 25 68.00000000 | |
| 26 65.38461538 | |
| 27 66.66666667 | |
| 28 64.28571429 | |
| 29 65.51724138 | |
| 30 63.33333333 | |
| 31 61.29032258 | |
| 32 59.37500000 | |
| 33 57.57575758 | |
| 34 55.88235294 | |
| 35 57.14285714 | |
| 36 55.55555556 | |
| 37 56.75675676 | |
| 38 55.26315789 | |
| 39 56.41025641 | |
| 40 55.00000000 | |
| 41 56.09756098 | |
| 42 54.76190476 | |
| 43 53.48837209 | |
| 44 52.27272727 | |
| 45 53.33333333 | |
| 46 54.34782609 | |
| 47 55.31914894 | |
| 48 56.25000000 | |
| 49 57.14285714 | |
| 50 56.00000000 | |
| 51 54.90196078 | |
| 52 55.76923077 | |
| 53 54.71698113 | |
| 54 53.70370370 | |
| 55 52.72727273 | |
| 56 53.57142857 | |
| 57 54.38596491 | |
| 58 55.17241379 | |
| 59 55.93220339 | |
| 60 56.66666667 | |
| 61 57.37704918 | |
| 62 56.45161290 | |
| 63 57.14285714 | |
| 64 57.81250000 | |
| 65 56.92307692 | |
| 66 57.57575758 | |
| 67 58.20895522 | |
| 68 58.82352941 | |
| 69 59.42028986 | |
| 70 58.57142857 | |
| 71 57.74647887 | |
| 72 56.94444444 | |
| 73 57.53424658 | |
| 74 58.10810811 | |
| 75 58.66666667 | |
| 76 59.21052632 | |
| 77 59.74025974 | |
| 78 60.25641026 | |
| 79 59.49367089 | |
| 80 60.00000000 | |
| 81 59.25925926 | |
| 82 59.75609756 | |
| 83 59.03614458 | |
| 84 59.52380952 | |
| 85 60.00000000 | |
| 86 60.46511628 | |
| 87 60.91954023 | |
| 88 61.36363636 | |
| 89 61.79775281 | |
| 90 62.22222222 | |
| 91 62.63736264 | |
| 92 63.04347826 | |
| 93 62.36559140 | |
| 94 61.70212766 | |
| 95 62.10526316 | |
| 96 62.50000000 | |
| 97 61.85567010 | |
| 98 61.22448980 | |
| 99 61.61616162 | |
| 100 62.00000000 | |
| 101 61.38613861 | |
| 102 61.76470588 | |
| 103 61.16504854 | |
| 104 60.57692308 | |
| 105 60.95238095 | |
| 106 60.37735849 | |
| 107 60.74766355 | |
| 108 60.18518519 | |
| 109 59.63302752 | |
| 110 60.00000000 | |
| 111 60.36036036 | |
| 112 60.71428571 | |
| 113 60.17699115 | |
| 114 60.52631579 | |
| 115 60.86956522 | |
| 116 61.20689655 | |
| 117 60.68376068 | |
| 118 61.01694915 | |
| 119 60.50420168 | |
| 120 60.83333333 | |
| 121 60.33057851 | |
| 122 60.65573770 | |
| 123 60.97560976 | |
| 124 60.48387097 | |
| 125 60.80000000 | |
| 126 61.11111111 | |
| 127 61.41732283 | |
| 128 61.71875000 | |
| 129 61.24031008 | |
| 130 60.76923077 | |
| 131 61.06870229 | |
| 132 61.36363636 | |
| 133 61.65413534 | |
| 134 61.19402985 | |
| 135 60.74074074 | |
| 136 60.29411765 | |
| 137 60.58394161 | |
| 138 60.86956522 | |
| 139 61.15107914 | |
| 140 61.42857143 | |
| 141 60.99290780 | |
| 142 61.26760563 | |
| 143 61.53846154 | |
| 144 61.11111111 | |
| 145 61.37931034 | |
| 146 60.95890411 | |
| 147 61.22448980 | |
| 148 61.48648649 | |
| 149 61.74496644 | |
| 150 62.00000000 | |
| 151 61.58940397 | |
| 152 61.84210526 | |
| 153 62.09150327 | |
| 154 61.68831169 | |
| 155 61.29032258 | |
| 156 61.53846154 | |
| 157 61.78343949 | |
| 158 61.39240506 | |
| 159 61.63522013 | |
| 160 61.25000000 | |
| 161 61.49068323 | |
| 162 61.72839506 | |
| 163 61.34969325 | |
| 164 61.58536585 | |
| 165 61.81818182 | |
| 166 62.04819277 | |
| 167 61.67664671 | |
| 168 61.90476190 | |
| 169 61.53846154 | |
| 170 61.76470588 | |
| 171 61.98830409 | |
| 172 61.62790698 | |
| 173 61.84971098 | |
| 174 62.06896552 | |
| 175 61.71428571 | |
| 176 61.93181818 | |
| 177 62.14689266 | |
| 178 62.35955056 | |
| 179 62.56983240 | |
| 180 62.77777778 | |
| 181 62.43093923 | |
| 182 62.63736264 | |
| 183 62.29508197 | |
| 184 61.95652174 | |
| 185 62.16216216 | |
| 186 62.36559140 | |
| 187 62.56684492 | |
| 188 62.23404255 | |
| 189 61.90476190 | |
| 190 61.57894737 | |
| 191 61.78010471 | |
| 192 61.97916667 | |
| 193 62.17616580 | |
| 194 62.37113402 | |
| 195 62.56410256 | |
| 196 62.75510204 | |
| 197 62.94416244 | |
| 198 62.62626263 | |
| 199 62.31155779 | |
| 200 62.50000000 | |
| 201 62.68656716 | |
| 202 62.37623762 | |
| 203 62.56157635 | |
| 204 62.74509804 | |
| 205 62.43902439 | |
| 206 62.13592233 | |
| 207 61.83574879 | |
| 208 62.01923077 | |
| 209 62.20095694 | |
| 210 62.38095238 | |
| 211 62.55924171 | |
| 212 62.26415094 | |
| 213 62.44131455 | |
| 214 62.61682243 | |
| 215 62.79069767 | |
| 216 62.50000000 | |
| 217 62.67281106 | |
| 218 62.38532110 | |
| 219 62.55707763 | |
| 220 62.27272727 | |
| 221 62.44343891 | |
| 222 62.16216216 | |
| 223 61.88340807 | |
| 224 62.05357143 | |
| 225 61.77777778 | |
| 226 61.50442478 | |
| 227 61.67400881 | |
| 228 61.84210526 | |
| 229 62.00873362 | |
| 230 62.17391304 | |
| 231 61.90476190 | |
| 232 61.63793103 | |
| 233 61.80257511 | |
| 234 61.53846154 | |
| 235 61.27659574 | |
| 236 61.01694915 | |
| 237 60.75949367 | |
| 238 60.92436975 | |
| 239 61.08786611 | |
| 240 61.25000000 | |
| 241 61.41078838 | |
| 242 61.57024793 | |
| 243 61.72839506 | |
| 244 61.47540984 | |
| 245 61.63265306 | |
| 246 61.38211382 | |
| 247 61.53846154 | |
| 248 61.69354839 | |
| 249 61.44578313 | |
| 250 61.60000000 | |
| 251 61.75298805 | |
| 252 61.90476190 | |
| 253 62.05533597 | |
| 254 61.81102362 | |
| 255 61.96078431 | |
| 256 62.10937500 | |
| 257 61.86770428 | |
| 258 62.01550388 | |
| 259 61.77606178 | |
| 260 61.92307692 | |
| 261 62.06896552 | |
| 262 62.21374046 | |
| 263 62.35741445 | |
| 264 62.50000000 | |
| 265 62.64150943 | |
| 266 62.40601504 | |
| 267 62.54681648 | |
| 268 62.31343284 | |
| 269 62.45353160 | |
| 270 62.59259259 | |
| 271 62.73062731 | |
| 272 62.50000000 | |
| 273 62.27106227 | |
| 274 62.04379562 | |
| 275 61.81818182 | |
| 276 61.95652174 | |
| 277 62.09386282 | |
| 278 61.87050360 | |
| 279 62.00716846 | |
| 280 62.14285714 | |
| 281 62.27758007 | |
| 282 62.41134752 | |
| 283 62.19081272 | |
| 284 62.32394366 | |
| 285 62.45614035 | |
| 286 62.58741259 | |
| 287 62.36933798 | |
| 288 62.50000000 | |
| 289 62.28373702 | |
| 290 62.41379310 | |
| 291 62.54295533 | |
| 292 62.67123288 | |
| 293 62.79863481 | |
| 294 62.58503401 | |
| 295 62.71186441 | |
| 296 62.83783784 | |
| 297 62.96296296 | |
| 298 63.08724832 | |
| 299 63.21070234 | |
| 300 63.33333333 | |
| 301 63.12292359 | |
| 302 63.24503311 | |
| 303 63.36633663 | |
| 304 63.15789474 | |
| 305 63.27868852 | |
| 306 63.07189542 | |
| 307 63.19218241 | |
| 308 63.31168831 | |
| 309 63.43042071 | |
| 310 63.54838710 | |
| 311 63.66559486 | |
| 312 63.78205128 | |
| 313 63.89776358 | |
| 314 63.69426752 | |
| 315 63.49206349 | |
| 316 63.60759494 | |
| 317 63.72239748 | |
| 318 63.52201258 | |
| 319 63.32288401 | |
| 320 63.12500000 | |
| 321 63.23987539 | |
| 322 63.35403727 | |
| 323 63.46749226 | |
| 324 63.27160494 | |
| 325 63.38461538 | |
| 326 63.49693252 | |
| 327 63.30275229 | |
| 328 63.41463415 | |
| 329 63.52583587 | |
| 330 63.33333333 | |
| 331 63.44410876 | |
| 332 63.55421687 | |
| 333 63.66366366 | |
| 334 63.77245509 | |
| 335 63.58208955 | |
| 336 63.69047619 | |
| 337 63.79821958 | |
| 338 63.60946746 | |
| 339 63.71681416 | |
| 340 63.82352941 | |
| 341 63.92961877 | |
| 342 63.74269006 | |
| 343 63.84839650 | |
| 344 63.95348837 | |
| 345 63.76811594 | |
| 346 63.87283237 | |
| 347 63.68876081 | |
| 348 63.50574713 | |
| 349 63.61031519 | |
| 350 63.42857143 | |
| 351 63.53276353 | |
| 352 63.63636364 | |
| 353 63.73937677 | |
| 354 63.55932203 | |
| 355 63.38028169 | |
| 356 63.48314607 | |
| 357 63.58543417 | |
| 358 63.68715084 | |
| 359 63.50974930 | |
| 360 63.61111111 | |
| 361 63.71191136 | |
| 362 63.81215470 | |
| 363 63.63636364 | |
| 364 63.46153846 | |
| 365 63.56164384 | |
| 366 63.38797814 | |
| 367 63.21525886 | |
| 368 63.31521739 | |
| 369 63.41463415 | |
| 370 63.51351351 | |
| 371 63.34231806 | |
| 372 63.17204301 | |
| 373 63.27077748 | |
| 374 63.36898396 | |
| 375 63.46666667 | |
| 376 63.29787234 | |
| 377 63.12997347 | |
| 378 63.22751323 | |
| 379 63.06068602 | |
| 380 63.15789474 | |
| 381 62.99212598 | |
| 382 62.82722513 | |
| 383 62.66318538 | |
| 384 62.76041667 | |
| 385 62.85714286 | |
| 386 62.95336788 | |
| 387 62.79069767 | |
| 388 62.62886598 | |
| 389 62.46786632 | |
| 390 62.30769231 | |
| 391 62.40409207 | |
| 392 62.50000000 | |
| 393 62.59541985 | |
| 394 62.69035533 | |
| 395 62.78481013 | |
| 396 62.62626263 | |
| 397 62.72040302 | |
| 398 62.56281407 | |
| 399 62.65664160 | |
| 400 62.75000000 | |
| 401 62.59351621 | |
| 402 62.43781095 | |
| 403 62.53101737 | |
| 404 62.62376238 | |
| 405 62.71604938 | |
| 406 62.80788177 | |
| 407 62.89926290 | |
| 408 62.99019608 | |
| 409 62.83618582 | |
| 410 62.92682927 | |
| 411 63.01703163 | |
| 412 63.10679612 | |
| 413 62.95399516 | |
| 414 63.04347826 | |
| 415 62.89156627 | |
| 416 62.98076923 | |
| 417 62.82973621 | |
| 418 62.91866029 | |
| 419 62.76849642 | |
| 420 62.85714286 | |
| 421 62.70783848 | |
| 422 62.79620853 | |
| 423 62.88416076 | |
| 424 62.73584906 | |
| 425 62.82352941 | |
| 426 62.67605634 | |
| 427 62.76346604 | |
| 428 62.61682243 | |
| 429 62.70396270 | |
| 430 62.55813953 | |
| 431 62.64501160 | |
| 432 62.73148148 | |
| 433 62.58660508 | |
| 434 62.67281106 | |
| 435 62.75862069 | |
| 436 62.84403670 | |
| 437 62.92906178 | |
| 438 62.78538813 | |
| 439 62.87015945 | |
| 440 62.72727273 | |
| 441 62.58503401 | |
| 442 62.44343891 | |
| 443 62.30248307 | |
| 444 62.16216216 | |
| 445 62.24719101 | |
| 446 62.33183857 | |
| 447 62.41610738 | |
| 448 62.50000000 | |
| 449 62.58351893 | |
| 450 62.44444444 | |
| 451 62.30598670 | |
| 452 62.38938053 | |
| 453 62.25165563 | |
| 454 62.33480176 | |
| 455 62.19780220 | |
| 456 62.28070175 | |
| 457 62.36323851 | |
| 458 62.44541485 | |
| 459 62.52723312 | |
| 460 62.60869565 | |
| 461 62.68980477 | |
| 462 62.77056277 | |
| 463 62.63498920 | |
| 464 62.50000000 | |
| 465 62.58064516 | |
| 466 62.66094421 | |
| 467 62.74089936 | |
| 468 62.60683761 | |
| 469 62.47334755 | |
| 470 62.55319149 | |
| 471 62.63269639 | |
| 472 62.50000000 | |
| 473 62.36786469 | |
| 474 62.44725738 | |
| 475 62.52631579 | |
| 476 62.60504202 | |
| 477 62.68343816 | |
| 478 62.76150628 | |
| 479 62.83924843 | |
| 480 62.91666667 | |
| 481 62.78586279 | |
| 482 62.86307054 | |
| 483 62.93995859 | |
| 484 63.01652893 | |
| 485 63.09278351 | |
| 486 63.16872428 | |
| 487 63.03901437 | |
| 488 63.11475410 | |
| 489 62.98568507 | |
| 490 62.85714286 | |
| 491 62.72912424 | |
| 492 62.80487805 | |
| 493 62.67748479 | |
| 494 62.75303644 | |
| 495 62.62626263 | |
| 496 62.70161290 | |
| 497 62.57545272 | |
| 498 62.65060241 | |
| 499 62.72545090 | |
| 500 62.80000000 | |
| 501 62.67465070 | |
| 502 62.74900398 | |
| 503 62.82306163 | |
| 504 62.89682540 | |
| 505 62.97029703 | |
| 506 62.84584980 | |
| 507 62.72189349 | |
| 508 62.59842520 | |
| 509 62.47544204 | |
| 510 62.35294118 | |
| 511 62.23091977 | |
| 512 62.30468750 | |
| 513 62.18323587 | |
| 514 62.25680934 | |
| 515 62.13592233 | |
| 516 62.20930233 | |
| 517 62.28239845 | |
| 518 62.35521236 | |
| 519 62.42774566 | |
| 520 62.30769231 | |
| 521 62.38003839 | |
| 522 62.45210728 | |
| 523 62.33269598 | |
| 524 62.21374046 | |
| 525 62.09523810 | |
| 526 61.97718631 | |
| 527 61.85958254 | |
| 528 61.74242424 | |
| 529 61.62570888 | |
| 530 61.69811321 | |
| 531 61.58192090 | |
| 532 61.65413534 | |
| 533 61.72607880 | |
| 534 61.61048689 | |
| 535 61.49532710 | |
| 536 61.56716418 | |
| 537 61.63873371 | |
| 538 61.71003717 | |
| 539 61.78107607 | |
| 540 61.66666667 | |
| 541 61.73752311 | |
| 542 61.80811808 | |
| 543 61.69429098 | |
| 544 61.76470588 | |
| 545 61.83486239 | |
| 546 61.72161172 | |
| 547 61.60877514 | |
| 548 61.67883212 | |
| 549 61.74863388 | |
| 550 61.81818182 | |
| 551 61.70598911 | |
| 552 61.59420290 | |
| 553 61.66365280 | |
| 554 61.73285199 | |
| 555 61.80180180 | |
| 556 61.69064748 | |
| 557 61.75942549 | |
| 558 61.64874552 | |
| 559 61.71735242 | |
| 560 61.78571429 | |
| 561 61.85383244 | |
| 562 61.92170819 | |
| 563 61.98934281 | |
| 564 62.05673759 | |
| 565 61.94690265 | |
| 566 62.01413428 | |
| 567 61.90476190 | |
| 568 61.97183099 | |
| 569 61.86291740 | |
| 570 61.75438596 | |
| 571 61.82136602 | |
| 572 61.71328671 | |
| 573 61.78010471 | |
| 574 61.84668990 | |
| 575 61.73913043 | |
| 576 61.80555556 | |
| 577 61.87175043 | |
| 578 61.93771626 | |
| 579 62.00345423 | |
| 580 61.89655172 | |
| 581 61.79001721 | |
| 582 61.68384880 | |
| 583 61.74957118 | |
| 584 61.81506849 | |
| 585 61.88034188 | |
| 586 61.94539249 | |
| 587 62.01022147 | |
| 588 62.07482993 | |
| 589 62.13921902 | |
| 590 62.20338983 | |
| 591 62.26734349 | |
| 592 62.16216216 | |
| 593 62.05733558 | |
| 594 62.12121212 | |
| 595 62.01680672 | |
| 596 61.91275168 | |
| 597 61.80904523 | |
| 598 61.70568562 | |
| 599 61.76961603 | |
| 600 61.66666667 | |
| 601 61.73044925 | |
| 602 61.62790698 | |
| 603 61.52570481 | |
| 604 61.42384106 | |
| 605 61.48760331 | |
| 606 61.55115512 | |
| 607 61.61449753 | |
| 608 61.67763158 | |
| 609 61.57635468 | |
| 610 61.63934426 | |
| 611 61.53846154 | |
| 612 61.60130719 | |
| 613 61.50081566 | |
| 614 61.56351792 | |
| 615 61.46341463 | |
| 616 61.36363636 | |
| 617 61.42625608 | |
| 618 61.48867314 | |
| 619 61.38933764 | |
| 620 61.45161290 | |
| 621 61.51368760 | |
| 622 61.41479100 | |
| 623 61.31621188 | |
| 624 61.21794872 | |
| 625 61.12000000 | |
| 626 61.02236422 | |
| 627 61.08452951 | |
| 628 61.14649682 | |
| 629 61.04928458 | |
| 630 61.11111111 | |
| 631 61.17274168 | |
| 632 61.07594937 | |
| 633 60.97946288 | |
| 634 61.04100946 | |
| 635 61.10236220 | |
| 636 61.16352201 | |
| 637 61.06750392 | |
| 638 61.12852665 | |
| 639 61.18935837 | |
| 640 61.09375000 | |
| 641 61.15444618 | |
| 642 61.05919003 | |
| 643 60.96423017 | |
| 644 61.02484472 | |
| 645 60.93023256 | |
| 646 60.99071207 | |
| 647 61.05100464 | |
| 648 61.11111111 | |
| 649 61.01694915 | |
| 650 61.07692308 | |
| 651 61.13671275 | |
| 652 61.19631902 | |
| 653 61.10260337 | |
| 654 61.16207951 | |
| 655 61.06870229 | |
| 656 60.97560976 | |
| 657 60.88280061 | |
| 658 60.79027356 | |
| 659 60.69802731 | |
| 660 60.75757576 | |
| 661 60.66565809 | |
| 662 60.72507553 | |
| 663 60.78431373 | |
| 664 60.84337349 | |
| 665 60.90225564 | |
| 666 60.81081081 | |
| 667 60.86956522 | |
| 668 60.77844311 | |
| 669 60.68759342 | |
| 670 60.74626866 | |
| 671 60.65573770 | |
| 672 60.71428571 | |
| 673 60.62407132 | |
| 674 60.53412463 | |
| 675 60.44444444 | |
| 676 60.35502959 | |
| 677 60.41358936 | |
| 678 60.47197640 | |
| 679 60.53019146 | |
| 680 60.58823529 | |
| 681 60.49926579 | |
| 682 60.41055718 | |
| 683 60.32210835 | |
| 684 60.38011696 | |
| 685 60.43795620 | |
| 686 60.34985423 | |
| 687 60.26200873 | |
| 688 60.31976744 | |
| 689 60.23222061 | |
| 690 60.28985507 | |
| 691 60.34732272 | |
| 692 60.40462428 | |
| 693 60.46176046 | |
| 694 60.51873199 | |
| 695 60.43165468 | |
| 696 60.34482759 | |
| 697 60.25824964 | |
| 698 60.17191977 | |
| 699 60.22889843 | |
| 700 60.28571429 | |
| 701 60.34236805 | |
| 702 60.25641026 | |
| 703 60.31294452 | |
| 704 60.36931818 | |
| 705 60.42553191 | |
| 706 60.48158640 | |
| 707 60.53748232 | |
| 708 60.59322034 | |
| 709 60.64880113 | |
| 710 60.70422535 | |
| 711 60.75949367 | |
| 712 60.81460674 | |
| 713 60.86956522 | |
| 714 60.78431373 | |
| 715 60.69930070 | |
| 716 60.75418994 | |
| 717 60.66945607 | |
| 718 60.58495822 | |
| 719 60.50069541 | |
| 720 60.55555556 | |
| 721 60.61026352 | |
| 722 60.66481994 | |
| 723 60.71922545 | |
| 724 60.63535912 | |
| 725 60.68965517 | |
| 726 60.60606061 | |
| 727 60.52269601 | |
| 728 60.57692308 | |
| 729 60.63100137 | |
| 730 60.68493151 | |
| 731 60.73871409 | |
| 732 60.79234973 | |
| 733 60.84583902 | |
| 734 60.89918256 | |
| 735 60.95238095 | |
| 736 61.00543478 | |
| 737 60.92265943 | |
| 738 60.97560976 | |
| 739 60.89309878 | |
| 740 60.81081081 | |
| 741 60.86369771 | |
| 742 60.78167116 | |
| 743 60.83445491 | |
| 744 60.75268817 | |
| 745 60.80536913 | |
| 746 60.85790885 | |
| 747 60.77643909 | |
| 748 60.69518717 | |
| 749 60.61415220 | |
| 750 60.66666667 | |
| Final result: 60.6667 +/- 1.7849 | |
| Random chance: 25.0083 +/- 1.5824 | |