Berk/assay-0.6b
0101
1{2 "overall": {3 "count": 6113,4 "accuracy": 0.705054801243252,5 "brier": 0.39068303174557184,6 "brier_soft": 0.36485200542432994,7 "nll": 0.7435078762316807,8 "nll_soft": 0.7539368565298866,9 "ece": 0.030412426160708377,10 "mean_confidence": 0.7254209476637835,11 "confident_error_rate": 0.01930312448879437,12 "score_mae": 0.6191286255856765,13 "evidence_auc": 0.996310177448874114 },15 "by_type": {16 "bool": {17 "count": 1898,18 "accuracy": 0.8108535300316122,19 "brier": 0.26805662687023524,20 "brier_soft": 0.2639773107878006,21 "nll": 0.4338549421061354,22 "nll_soft": 0.43754843965694995,23 "ece": 0.04707414445089357,24 "mean_confidence": 0.8579276744825058,25 "confident_error_rate": 0.038461538461538464,26 "evidence_auc": 0.991567617084621627 },28 "choice": {29 "count": 3248,30 "accuracy": 0.6736453201970444,31 "brier": 0.4267776942434168,32 "brier_soft": 0.4015465270646481,33 "nll": 0.8669136499375315,34 "nll_soft": 0.8772741819689498,35 "ece": 0.045373296227665255,36 "mean_confidence": 0.7086789911375205,37 "confident_error_rate": 0.013854679802955665,38 "evidence_auc": 0.999686862289775539 },40 "score": {41 "count": 967,42 "accuracy": 0.6028955532574974,43 "brier": 0.5101343788607614,44 "brier_soft": 0.43959488456846546,45 "nll": 0.9367853488001198,46 "nll_soft": 0.9606644492897173,47 "ece": 0.0857255052436744,48 "mean_confidence": 0.5215741092929117,49 "confident_error_rate": 0.0,50 "score_mae": 0.619128625585676551 }52 },53 "by_source": {54 "ag_news": {55 "count": 100,56 "accuracy": 0.9,57 "brier": 0.17167430940678405,58 "brier_soft": 0.17167430940678405,59 "nll": 0.336887603212825,60 "nll_soft": 0.336887603212825,61 "ece": 0.07163243215848891,62 "mean_confidence": 0.9219929393584567,63 "confident_error_rate": 0.0664 },65 "amazon_polarity": {66 "count": 100,67 "accuracy": 0.94,68 "brier": 0.08580480427527387,69 "brier_soft": 0.08580480427527387,70 "nll": 0.13534072911744766,71 "nll_soft": 0.13534072911744766,72 "ece": 0.060871109033524766,73 "mean_confidence": 0.9416013850702707,74 "confident_error_rate": 0.0175 },76 "amazon_stars": {77 "count": 100,78 "accuracy": 0.56,79 "brier": 0.5696269202129539,80 "brier_soft": 0.5696269202129539,81 "nll": 1.0261049502969477,82 "nll_soft": 1.0261049502969477,83 "ece": 0.12194184749343116,84 "mean_confidence": 0.47691471251232365,85 "confident_error_rate": 0.0,86 "score_mae": 0.61423956704289987 },88 "anli": {89 "count": 100,90 "accuracy": 0.43,91 "brier": 0.8086471157013881,92 "brier_soft": 0.8086471157013881,93 "nll": 1.398779746391494,94 "nll_soft": 1.398779746391494,95 "ece": 0.31853672993302656,96 "mean_confidence": 0.727838441783572,97 "confident_error_rate": 0.0998 },99 "arc_challenge": {100 "count": 100,101 "accuracy": 0.66,102 "brier": 0.46429933197227446,103 "brier_soft": 0.46429933197227446,104 "nll": 0.8642889474810811,105 "nll_soft": 0.8642889474810811,106 "ece": 0.15669435497659792,107 "mean_confidence": 0.7235336333706962,108 "confident_error_rate": 0.02109 },110 "arc_easy": {111 "count": 100,112 "accuracy": 0.85,113 "brier": 0.1940937298338349,114 "brier_soft": 0.1940937298338349,115 "nll": 0.39064179191107024,116 "nll_soft": 0.39064179191107024,117 "ece": 0.07900940316304368,118 "mean_confidence": 0.8062375951757056,119 "confident_error_rate": 0.0120 },121 "banking77": {122 "count": 100,123 "accuracy": 0.67,124 "brier": 0.4784721751139965,125 "brier_soft": 0.4784721751139965,126 "nll": 1.5601690451301173,127 "nll_soft": 1.5601690451301173,128 "ece": 0.12808546873118945,129 "mean_confidence": 0.6846104644283264,130 "confident_error_rate": 0.03131 },132 "boolq": {133 "count": 125,134 "accuracy": 0.664,135 "brier": 0.5824374662242449,136 "brier_soft": 0.5824374662242449,137 "nll": 1.1200996870048703,138 "nll_soft": 1.1200996870048703,139 "ece": 0.25503892261697847,140 "mean_confidence": 0.9009889255438389,141 "confident_error_rate": 0.24,142 "evidence_auc": 1.0143 },144 "cb": {145 "count": 28,146 "accuracy": 0.8928571428571429,147 "brier": 0.11845201944614438,148 "brier_soft": 0.11845201944614438,149 "nll": 0.23775217633412454,150 "nll_soft": 0.23775217633412454,151 "ece": 0.1078101710685394,152 "mean_confidence": 0.8733159887773345,153 "confident_error_rate": 0.0154 },155 "civil_comments_severity": {156 "count": 100,157 "accuracy": 0.83,158 "brier": 0.30853567636963153,159 "brier_soft": 0.20466550090702357,160 "nll": 0.6146090606073197,161 "nll_soft": 0.7049566039180744,162 "ece": 0.19732957498121775,163 "mean_confidence": 0.652800302888791,164 "confident_error_rate": 0.0,165 "score_mae": 0.48844389755448875166 },167 "civil_comments_toxic": {168 "count": 100,169 "accuracy": 0.92,170 "brier": 0.13107340592724387,171 "brier_soft": 0.05364798668263418,172 "nll": 0.234533996986214,173 "nll_soft": 0.3046365805006745,174 "ece": 0.06177327425323237,175 "mean_confidence": 0.8792147122777147,176 "confident_error_rate": 0.01177 },178 "clinc150": {179 "count": 100,180 "accuracy": 0.69,181 "brier": 0.4673241163352339,182 "brier_soft": 0.4673241163352339,183 "nll": 1.7998103678930273,184 "nll_soft": 1.7998103678930273,185 "ece": 0.10405707152125332,186 "mean_confidence": 0.7034346459910751,187 "confident_error_rate": 0.01188 },189 "cola": {190 "count": 100,191 "accuracy": 0.64,192 "brier": 0.45212164375689284,193 "brier_soft": 0.45212164375689284,194 "nll": 0.6450283149218293,195 "nll_soft": 0.6450283149218293,196 "ece": 0.11530711181948869,197 "mean_confidence": 0.7540596079177964,198 "confident_error_rate": 0.02199 },200 "commonsense_qa": {201 "count": 100,202 "accuracy": 0.68,203 "brier": 0.44878207901084366,204 "brier_soft": 0.44878207901084366,205 "nll": 0.8815806784626246,206 "nll_soft": 0.8815806784626246,207 "ece": 0.06865873042756807,208 "mean_confidence": 0.6821657773971803,209 "confident_error_rate": 0.01210 },211 "cosmos_qa": {212 "count": 120,213 "accuracy": 0.5833333333333334,214 "brier": 0.5723719210693715,215 "brier_soft": 0.5723719210693715,216 "nll": 1.0851163899122087,217 "nll_soft": 1.0851163899122087,218 "ece": 0.09618159223747698,219 "mean_confidence": 0.662741275142061,220 "confident_error_rate": 0.0,221 "evidence_auc": 0.9953125222 },223 "dates": {224 "count": 300,225 "accuracy": 0.8466666666666667,226 "brier": 0.1952099468621781,227 "brier_soft": 0.1952099468621781,228 "nll": 0.30503634674823765,229 "nll_soft": 0.30503634674823765,230 "ece": 0.043387396134385074,231 "mean_confidence": 0.84625525258766,232 "confident_error_rate": 0.0033333333333333335,233 "score_mae": 0.3230317969202634234 },235 "dbpedia": {236 "count": 100,237 "accuracy": 1.0,238 "brier": 0.0008420663170771253,239 "brier_soft": 0.0008420663170771253,240 "nll": 0.00918498596266742,241 "nll_soft": 0.00918498596266742,242 "ece": 0.008904030823745671,243 "mean_confidence": 0.9910959691762545,244 "confident_error_rate": 0.0245 },246 "dynasent": {247 "count": 100,248 "accuracy": 0.49,249 "brier": 0.5884531231040632,250 "brier_soft": 0.4423489537858375,251 "nll": 0.9879611872627133,252 "nll_soft": 1.0010951533157162,253 "ece": 0.1554664898909139,254 "mean_confidence": 0.5607612162644048,255 "confident_error_rate": 0.0,256 "score_mae": 0.6325307416076793257 },258 "enron_spam": {259 "count": 100,260 "accuracy": 0.95,261 "brier": 0.0750898751455318,262 "brier_soft": 0.0750898751455318,263 "nll": 0.13481450114911914,264 "nll_soft": 0.13481450114911914,265 "ece": 0.058760900159834276,266 "mean_confidence": 0.936686700660227,267 "confident_error_rate": 0.01268 },269 "go_emotions": {270 "count": 100,271 "accuracy": 0.47,272 "brier": 0.718367046561157,273 "brier_soft": 0.28923457335271163,274 "nll": 1.926955163826314,275 "nll_soft": 2.2635551312922435,276 "ece": 0.17175697839494763,277 "mean_confidence": 0.33183864668198176,278 "confident_error_rate": 0.0279 },280 "hellaswag": {281 "count": 100,282 "accuracy": 0.62,283 "brier": 0.49074184637761903,284 "brier_soft": 0.49074184637761903,285 "nll": 0.9305013577650898,286 "nll_soft": 0.9305013577650898,287 "ece": 0.11862829019667494,288 "mean_confidence": 0.6534043868116024,289 "confident_error_rate": 0.0290 },291 "imdb": {292 "count": 100,293 "accuracy": 0.96,294 "brier": 0.08795359522078826,295 "brier_soft": 0.08795359522078826,296 "nll": 0.1703674822113271,297 "nll_soft": 0.1703674822113271,298 "ece": 0.040475760842537414,299 "mean_confidence": 0.940735768754548,300 "confident_error_rate": 0.03301 },302 "ledgar": {303 "count": 100,304 "accuracy": 0.68,305 "brier": 0.40614986096299754,306 "brier_soft": 0.40614986096299754,307 "nll": 1.4404445803485642,308 "nll_soft": 1.4404445803485642,309 "ece": 0.12459564932621359,310 "mean_confidence": 0.675806081562592,311 "confident_error_rate": 0.01312 },313 "liar": {314 "count": 100,315 "accuracy": 0.26,316 "brier": 0.7933185274153484,317 "brier_soft": 0.7933185274153484,318 "nll": 1.6679028813048031,319 "nll_soft": 1.6679028813048031,320 "ece": 0.06507736504717265,321 "mean_confidence": 0.24634068079277538,322 "confident_error_rate": 0.0,323 "score_mae": 1.2559342591277523324 },325 "measuring_hate_speech": {326 "count": 100,327 "accuracy": 0.81,328 "brier": 0.3396697348224549,329 "brier_soft": 0.19080407243559158,330 "nll": 0.6206328985442651,331 "nll_soft": 0.7308991184362474,332 "ece": 0.17923612715118986,333 "mean_confidence": 0.6307638728488102,334 "confident_error_rate": 0.0,335 "score_mae": 0.6545338061589748336 },337 "medqa": {338 "count": 100,339 "accuracy": 0.46,340 "brier": 0.6830794095906169,341 "brier_soft": 0.6830794095906169,342 "nll": 1.260217965022958,343 "nll_soft": 1.260217965022958,344 "ece": 0.10410187965371252,345 "mean_confidence": 0.40546563669920876,346 "confident_error_rate": 0.0347 },348 "mnli": {349 "count": 100,350 "accuracy": 0.86,351 "brier": 0.2461392504105252,352 "brier_soft": 0.2461392504105252,353 "nll": 0.4500251998903584,354 "nll_soft": 0.4500251998903584,355 "ece": 0.07792265817164262,356 "mean_confidence": 0.809569663745306,357 "confident_error_rate": 0.01358 },359 "mrpc": {360 "count": 100,361 "accuracy": 0.85,362 "brier": 0.23254436799651235,363 "brier_soft": 0.23254436799651235,364 "nll": 0.37406467998561715,365 "nll_soft": 0.37406467998561715,366 "ece": 0.06513814925679627,367 "mean_confidence": 0.8063140117596898,368 "confident_error_rate": 0.0369 },370 "multirc": {371 "count": 125,372 "accuracy": 0.688,373 "brier": 0.5150958140330812,374 "brier_soft": 0.5150958140330812,375 "nll": 0.9321397083694551,376 "nll_soft": 0.9321397083694551,377 "ece": 0.22299498214130758,378 "mean_confidence": 0.8800483904643696,379 "confident_error_rate": 0.176,380 "evidence_auc": 0.9813333333333333381 },382 "openbookqa": {383 "count": 100,384 "accuracy": 0.65,385 "brier": 0.4791117350116674,386 "brier_soft": 0.4791117350116674,387 "nll": 0.8580094565143226,388 "nll_soft": 0.8580094565143226,389 "ece": 0.11261566906175771,390 "mean_confidence": 0.6988737716957278,391 "confident_error_rate": 0.01392 },393 "piqa": {394 "count": 100,395 "accuracy": 0.62,396 "brier": 0.4606743696961655,397 "brier_soft": 0.4606743696961655,398 "nll": 0.6937551993329675,399 "nll_soft": 0.6937551993329675,400 "ece": 0.11593196583580467,401 "mean_confidence": 0.7223726310067928,402 "confident_error_rate": 0.04403 },404 "policy_application": {405 "count": 150,406 "accuracy": 0.8,407 "brier": 0.25790714562174005,408 "brier_soft": 0.25790714562174005,409 "nll": 0.41907410837426357,410 "nll_soft": 0.41907410837426357,411 "ece": 0.05254626318981812,412 "mean_confidence": 0.8000413443765387,413 "confident_error_rate": 0.013333333333333334,414 "evidence_auc": 0.9849574885546108415 },416 "policy_hard": {417 "count": 300,418 "accuracy": 0.7166666666666667,419 "brier": 0.36013972381824627,420 "brier_soft": 0.36013972381824627,421 "nll": 0.5704760559630674,422 "nll_soft": 0.5704760559630674,423 "ece": 0.06747979684035946,424 "mean_confidence": 0.7642620234200053,425 "confident_error_rate": 0.006666666666666667,426 "evidence_auc": 0.9403935185185185427 },428 "qqp": {429 "count": 100,430 "accuracy": 0.87,431 "brier": 0.21255833780443303,432 "brier_soft": 0.21255833780443303,433 "nll": 0.3375497168485568,434 "nll_soft": 0.3375497168485568,435 "ece": 0.08248226236243893,436 "mean_confidence": 0.8207414940051179,437 "confident_error_rate": 0.01438 },439 "race": {440 "count": 125,441 "accuracy": 0.608,442 "brier": 0.491455314176186,443 "brier_soft": 0.491455314176186,444 "nll": 0.9626818782840941,445 "nll_soft": 0.9626818782840941,446 "ece": 0.14182781184836327,447 "mean_confidence": 0.7493741312243011,448 "confident_error_rate": 0.016,449 "evidence_auc": 0.9938666666666667450 },451 "rotten_tomatoes": {452 "count": 100,453 "accuracy": 0.9,454 "brier": 0.14275234295049224,455 "brier_soft": 0.14275234295049224,456 "nll": 0.23282286234383792,457 "nll_soft": 0.23282286234383792,458 "ece": 0.051450218466265296,459 "mean_confidence": 0.9054416516058115,460 "confident_error_rate": 0.01461 },462 "rte": {463 "count": 100,464 "accuracy": 0.82,465 "brier": 0.2653727111837063,466 "brier_soft": 0.2653727111837063,467 "nll": 0.4042521882397484,468 "nll_soft": 0.4042521882397484,469 "ece": 0.0661314421326466,470 "mean_confidence": 0.8619884639516752,471 "confident_error_rate": 0.03472 },473 "scotus": {474 "count": 100,475 "accuracy": 0.23,476 "brier": 0.8951972916507671,477 "brier_soft": 0.8951972916507671,478 "nll": 2.4117270185815007,479 "nll_soft": 2.4117270185815007,480 "ece": 0.07217207065841522,481 "mean_confidence": 0.1915051363038614,482 "confident_error_rate": 0.0483 },484 "shp": {485 "count": 100,486 "accuracy": 0.45,487 "brier": 0.5093176162653404,488 "brier_soft": 0.11894177950737726,489 "nll": 0.7026835810861257,490 "nll_soft": 0.702593694000663,491 "ece": 0.1111520075280236,492 "mean_confidence": 0.5543252050630872,493 "confident_error_rate": 0.0494 },495 "sms_spam": {496 "count": 100,497 "accuracy": 0.98,498 "brier": 0.02870347214535624,499 "brier_soft": 0.02870347214535624,500 "nll": 0.06499826507213281,501 "nll_soft": 0.06499826507213281,502 "ece": 0.03372488679107602,503 "mean_confidence": 0.9658248068090167,504 "confident_error_rate": 0.01505 },506 "snli": {507 "count": 100,508 "accuracy": 0.85,509 "brier": 0.22331515795857343,510 "brier_soft": 0.22331515795857343,511 "nll": 0.39539320777824905,512 "nll_soft": 0.39539320777824905,513 "ece": 0.0926695947746054,514 "mean_confidence": 0.8633797733330062,515 "confident_error_rate": 0.0516 },517 "social_iqa": {518 "count": 100,519 "accuracy": 0.65,520 "brier": 0.474283631912417,521 "brier_soft": 0.474283631912417,522 "nll": 0.8302148480877927,523 "nll_soft": 0.8302148480877927,524 "ece": 0.11975901245282002,525 "mean_confidence": 0.7186295344419724,526 "confident_error_rate": 0.03527 },528 "sst2": {529 "count": 100,530 "accuracy": 0.91,531 "brier": 0.15220591437374925,532 "brier_soft": 0.15220591437374925,533 "nll": 0.27066277966821617,534 "nll_soft": 0.27066277966821617,535 "ece": 0.0584594702815044,536 "mean_confidence": 0.9584594702815042,537 "confident_error_rate": 0.05538 },539 "sst5": {540 "count": 100,541 "accuracy": 0.58,542 "brier": 0.5692131000511924,543 "brier_soft": 0.5692131000511924,544 "nll": 1.0482270625207641,545 "nll_soft": 1.0482270625207641,546 "ece": 0.14522475165356238,547 "mean_confidence": 0.45230109896773846,548 "confident_error_rate": 0.0,549 "score_mae": 0.579621455718889550 },551 "stance_abortion": {552 "count": 60,553 "accuracy": 0.6166666666666667,554 "brier": 0.5206953339555322,555 "brier_soft": 0.5206953339555322,556 "nll": 0.8491090429716367,557 "nll_soft": 0.8491090429716367,558 "ece": 0.17060325898737938,559 "mean_confidence": 0.6450970316412057,560 "confident_error_rate": 0.0561 },562 "stance_atheism": {563 "count": 60,564 "accuracy": 0.7166666666666667,565 "brier": 0.36611641733676126,566 "brier_soft": 0.36611641733676126,567 "nll": 0.6162604565119774,568 "nll_soft": 0.6162604565119774,569 "ece": 0.16375666437063566,570 "mean_confidence": 0.7601322048943361,571 "confident_error_rate": 0.016666666666666666572 },573 "stance_feminist": {574 "count": 60,575 "accuracy": 0.6,576 "brier": 0.4934844463221146,577 "brier_soft": 0.4934844463221146,578 "nll": 0.7795586115289036,579 "nll_soft": 0.7795586115289036,580 "ece": 0.14911099146600104,581 "mean_confidence": 0.6214280468288923,582 "confident_error_rate": 0.0583 },584 "stance_hillary": {585 "count": 60,586 "accuracy": 0.65,587 "brier": 0.47389946504890085,588 "brier_soft": 0.47389946504890085,589 "nll": 0.8025726614249472,590 "nll_soft": 0.8025726614249472,591 "ece": 0.0704082089812596,592 "mean_confidence": 0.6720211955303614,593 "confident_error_rate": 0.0594 },595 "stsb": {596 "count": 100,597 "accuracy": 0.5,598 "brier": 0.6192029968172934,599 "brier_soft": 0.3359260941784888,600 "nll": 1.1508243053734646,601 "nll_soft": 1.1679874778521313,602 "ece": 0.11060553235669754,603 "mean_confidence": 0.47404663542874836,604 "confident_error_rate": 0.0,605 "score_mae": 0.646867863215795606 },607 "subjectivity": {608 "count": 100,609 "accuracy": 0.92,610 "brier": 0.09541205703283434,611 "brier_soft": 0.09541205703283434,612 "nll": 0.15057303108214104,613 "nll_soft": 0.15057303108214104,614 "ece": 0.04798439182160856,615 "mean_confidence": 0.9302849687736618,616 "confident_error_rate": 0.0617 },618 "swag": {619 "count": 100,620 "accuracy": 0.58,621 "brier": 0.5463578569460535,622 "brier_soft": 0.5463578569460535,623 "nll": 0.9887063359616937,624 "nll_soft": 0.9887063359616937,625 "ece": 0.08753140963152978,626 "mean_confidence": 0.6505128614902675,627 "confident_error_rate": 0.0628 },629 "trec": {630 "count": 100,631 "accuracy": 0.95,632 "brier": 0.08204722818910742,633 "brier_soft": 0.08204722818910742,634 "nll": 0.17559393951295343,635 "nll_soft": 0.17559393951295343,636 "ece": 0.02264209411714494,637 "mean_confidence": 0.9500299020554932,638 "confident_error_rate": 0.01639 },640 "tweet_hate": {641 "count": 100,642 "accuracy": 0.51,643 "brier": 0.5928009007159826,644 "brier_soft": 0.5928009007159826,645 "nll": 0.8151179633209827,646 "nll_soft": 0.8151179633209827,647 "ece": 0.21335525395842544,648 "mean_confidence": 0.7233552539584255,649 "confident_error_rate": 0.0650 },651 "tweet_sentiment": {652 "count": 100,653 "accuracy": 0.69,654 "brier": 0.43698091004984074,655 "brier_soft": 0.43698091004984074,656 "nll": 0.7345815927827489,657 "nll_soft": 0.7345815927827489,658 "ece": 0.13993783321704267,659 "mean_confidence": 0.5500621667829574,660 "confident_error_rate": 0.0,661 "score_mae": 0.3860652139710619662 },663 "vitaminc": {664 "count": 100,665 "accuracy": 0.71,666 "brier": 0.40905484004391957,667 "brier_soft": 0.40905484004391957,668 "nll": 0.7271544604990626,669 "nll_soft": 0.7271544604990626,670 "ece": 0.10385044249306388,671 "mean_confidence": 0.672572792332177,672 "confident_error_rate": 0.01673 },674 "wic": {675 "count": 100,676 "accuracy": 0.65,677 "brier": 0.43751322905741524,678 "brier_soft": 0.43751322905741524,679 "nll": 0.6263084664151242,680 "nll_soft": 0.6263084664151242,681 "ece": 0.05545881046082848,682 "mean_confidence": 0.6287045484026507,683 "confident_error_rate": 0.0684 },685 "winogrande": {686 "count": 100,687 "accuracy": 0.49,688 "brier": 0.6104376541011685,689 "brier_soft": 0.6104376541011685,690 "nll": 0.8506372185576656,691 "nll_soft": 0.8506372185576656,692 "ece": 0.2290845274269612,693 "mean_confidence": 0.7190845274269612,694 "confident_error_rate": 0.05695 },696 "yelp": {697 "count": 100,698 "accuracy": 0.57,699 "brier": 0.5254606229663639,700 "brier_soft": 0.5254606229663639,701 "nll": 0.8989841552777672,702 "nll_soft": 0.8989841552777672,703 "ece": 0.10490958010393049,704 "mean_confidence": 0.5356457346476723,705 "confident_error_rate": 0.0,706 "score_mae": 0.5123057010793745707 }708 },709 "reliability": [710 {711 "bin": "0.0-0.1",712 "count": 3,713 "confidence": 0.06146846781302175,714 "accuracy": 0.0715 },716 {717 "bin": "0.1-0.2",718 "count": 97,719 "confidence": 0.16869521945608792,720 "accuracy": 0.23711340206185566721 },722 {723 "bin": "0.2-0.3",724 "count": 171,725 "confidence": 0.24612851557121382,726 "accuracy": 0.25146198830409355727 },728 {729 "bin": "0.3-0.4",730 "count": 293,731 "confidence": 0.3580441095895981,732 "accuracy": 0.4129692832764505733 },734 {735 "bin": "0.4-0.5",736 "count": 590,737 "confidence": 0.4550973981822978,738 "accuracy": 0.4745762711864407739 },740 {741 "bin": "0.5-0.6",742 "count": 775,743 "confidence": 0.5489073426772118,744 "accuracy": 0.52745 },746 {747 "bin": "0.6-0.7",748 "count": 690,749 "confidence": 0.6466276273117183,750 "accuracy": 0.6260869565217392751 },752 {753 "bin": "0.7-0.8",754 "count": 714,755 "confidence": 0.753869082660997,756 "accuracy": 0.6988795518207283757 },758 {759 "bin": "0.8-0.9",760 "count": 818,761 "confidence": 0.8513946637045477,762 "accuracy": 0.812958435207824763 },764 {765 "bin": "0.9-1.0",766 "count": 1962,767 "confidence": 0.9664467037858544,768 "accuracy": 0.9398572884811417769 }770 ],771 "seconds": 16.7630455493927,772 "model": "runs/assay-0.6b-v4",773 "data": "data/v4/dev.jsonl"774}