Files
GENIES/results/evaluations/cra/llama-7b-counterfactual_python/counterfactual_python.json
T
2023-11-11 19:44:09 +00:00

761 lines
21 KiB
JSON

{
"model_dir": "models/llama-7b",
"distribution_id": "counterfactual_python",
"timestamp": "2023-10-16 02:12:59",
"eval_score": -0.21098263953257218,
"eval_brier_score": 0.21098263953257218,
"eval_average_probability": 0.5906618588659239,
"eval_accuracy": 0.6773333333333333,
"eval_probabilities": [
0.4124119898597177,
0.44230170654297596,
0.524360296963333,
0.283036418037575,
0.5686440350981036,
0.2717567334799905,
0.903815811058543,
0.9100330387177841,
0.9110139780951496,
0.47836082838905,
0.43929188743208764,
0.5316528207832084,
0.8111710523013342,
0.8615113510881397,
0.7111418572012729,
0.6773792359997268,
0.7632464018280067,
0.7239940213091207,
0.24894404749557275,
0.26734056825207,
0.18829913404706894,
0.7674518924627304,
0.7899139982887158,
0.7580720727970652,
0.5029619244432787,
0.5543316039641988,
0.6372197212142758,
0.785785902164971,
0.8228805883758773,
0.8008023900102925,
0.8164278462616411,
0.7671461876224385,
0.7997387285708458,
0.7224239314375329,
0.16319706787013788,
0.47730658770855855,
0.7084341117415278,
0.7435383391837163,
0.7078933002535178,
0.8109402567908897,
0.15595703695402863,
0.7061574875503491,
0.7839280349616783,
0.8562843532084646,
0.7331719276411552,
0.5241553129961567,
0.6747112534808266,
0.45563262443261615,
0.418233323821424,
0.446918111979821,
0.36059516402772285,
0.6397210521182056,
0.4852202191452081,
0.5966078416607534,
0.2648930189085744,
0.24415316955274025,
0.21257384627465903,
0.6912972465095967,
0.3916301999691947,
0.3997583602839485,
0.7738503993986295,
0.47439960900514416,
0.3195513555228118,
0.13116332563755861,
0.34938524548075034,
0.4595372565279552,
0.6582569566398044,
0.5668720878604452,
0.39943076667159416,
0.4068209933999343,
0.5164200090714554,
0.7430289049112908,
0.7769365660085077,
0.8747958919461121,
0.6404483075061513,
0.23489391822808403,
0.6561309628266841,
0.3850361131282116,
0.06796478698254649,
0.8231427967861655,
0.25825487187311913,
0.5316591139176854,
0.7350635691723333,
0.33271100919411517,
0.5985919416737173,
0.7520202387952206,
0.5246963089663278,
0.5566433952898506,
0.5047475918102194,
0.5895936394305467,
0.4525384387222097,
0.12981570123774966,
0.3411084166966711,
0.7193100723966241,
0.25267135139304703,
0.7959765773921732,
0.654634490547727,
0.8549830085904548,
0.601552758554321,
0.20593215272304877,
0.2180281711140445,
0.24219350715614285,
0.526707215906423,
0.477908628760728,
0.4922225425696248,
0.9538934024847348,
0.9498009065498061,
0.9483326058438574,
0.9658122644694541,
0.9693268265421495,
0.97074772821191,
0.37197290275040884,
0.3943659724202863,
0.5967690195616211,
0.22855661253661091,
0.29314295285927167,
0.7891522792945087,
0.7679822187339204,
0.7179171149431668,
0.6098290328741263,
0.3693415313797854,
0.8832101481297313,
0.7457966390967732,
0.8369108931090045,
0.8791172029936948,
0.8426836847739044,
0.6004422956341622,
0.6062844601130177,
0.5953362135917823,
0.5072850166629107,
0.8064908475171091,
0.8486473892167514,
0.4355265090913036,
0.4580649140418235,
0.6992317823766961,
0.5391244707730907,
0.3436732094563144,
0.6470309124820222,
0.6458487023476078,
0.320352923896809,
0.7059397347872479,
0.8241071887322771,
0.5225316144690543,
0.70178068431593,
0.18240306625057445,
0.356110321864445,
0.5018645633109274,
0.4763826318028337,
0.5823636513187919,
0.6613393156596596,
0.6185114155339474,
0.5625700984418702,
0.6679047808698957,
0.6958638062955224,
0.843430687800722,
0.8468674619477827,
0.7824867001798382,
0.8170382438737401,
0.7817188187938817,
0.5965752096252324,
0.7244121009100563,
0.7552964065820251,
0.7367829200539711,
0.4394583017171728,
0.6400867961547614,
0.2612288943694976,
0.3753215135439283,
0.2411443166973103,
0.28241933867749874,
0.19115746074454143,
0.609622357296046,
0.8833165066959685,
0.703172301874586,
0.7728683337077131,
0.6719092631425354,
0.5502735733379619,
0.7257632742770516,
0.7638909159269948,
0.331123625027933,
0.6435048334004463,
0.32290407321953396,
0.3783686991202901,
0.36169190977504145,
0.5992261492352142,
0.3785220085350651,
0.35923285298596874,
0.4332929206045141,
0.4913466193515638,
0.580203224816367,
0.5275187333061312,
0.4226941898169734,
0.6057698817901831,
0.822059279629055,
0.8595463188881735,
0.8589150369941436,
0.41479620227582237,
0.3650836221450561,
0.578394377852396,
0.559206382680661,
0.5415360960819131,
0.6010554473025451,
0.8577472614861299,
0.7664825581027401,
0.6148922667994938,
0.5996008512327248,
0.5412034660518261,
0.37299793088824373,
0.42715117215534215,
0.6351257943120384,
0.1528074995140094,
0.6457347077557308,
0.6276785315881825,
0.6708504725822543,
0.6361513531070003,
0.632583763351648,
0.564507027054304,
0.3492788944323495,
0.5198803320277523,
0.8590882253474628,
0.6086997405944629,
0.775801218718522,
0.7883680254126797,
0.37475844787559986,
0.40771598169743917,
0.42809768424372757,
0.7423112955200232,
0.7340938845345686,
0.6301659798265435,
0.6792027389451758,
0.6150343165380034,
0.7204593947225572,
0.7269502700013062,
0.6675482438170107,
0.5307557050318604,
0.9416124555990087,
0.946502037922715,
0.9456752504344955,
0.8303837828504503,
0.724479629874932,
0.8264962823005663,
0.7809086297587559,
0.8603945192727872,
0.8461645076301648,
0.551528934361627,
0.8116446490777327,
0.3697560570251469,
0.29515633469341973,
0.3442664841483218,
0.7222180414751208,
0.25754109348842325,
0.5116919044071552,
0.2130925971828428,
0.49525139179536937,
0.4380789108761264,
0.39677101157992045,
0.7937669379100974,
0.3529733390214962,
0.7174210354516874,
0.4847424361372983,
0.4053420474498163,
0.6000618682232913,
0.8176774249952051,
0.8603681078373738,
0.7588103527674929,
0.7064052901522299,
0.4875477316879484,
0.6029003496375073,
0.7714653564880971,
0.8305303204752994,
0.7874504754256543,
0.5316763796451671,
0.5331439634440764,
0.7738599258766393,
0.19628063606290874,
0.2864080036867853,
0.7112726978444575,
0.5004470127298607,
0.4575960529410811,
0.4476730656099174,
0.66997700182022,
0.5270317212278305,
0.7903017517521351,
0.6306951897564552,
0.6672505748464479,
0.6939619954252887,
0.5731121529149906,
0.359427360776554,
0.21087538022873226,
0.5450239856888324,
0.5266845989083804,
0.7378313989647293,
0.23516918144915622,
0.7044280131861058,
0.8627984415152138,
0.879284846409625,
0.9256973801714479,
0.9305899351365692,
0.7317838585242304,
0.73070051668468,
0.6629370878240954,
0.551284361621971,
0.4834155296613342,
0.5525019071522785,
0.24077845004255327,
0.39361159218805464,
0.5796414716906122,
0.5529359179734298,
0.4297088542892819,
0.3485769420531062,
0.24134078076839394,
0.25061712375505757,
0.5862893879428388,
0.7573237457919209,
0.6946651527774673,
0.34059249127206354,
0.18377564292127413,
0.38583722055350245,
0.3186518233680968,
0.31952669672501127,
0.5426659984771182,
0.7153909337949613,
0.3065660378036206,
0.29942772481687946,
0.2695277143429733,
0.33303476928266407,
0.5254723315264302,
0.56928611058656,
0.8295588437262603,
0.7499790522832346,
0.7738950806585753,
0.16041710867738668,
0.29938497300029987,
0.1499164732262268,
0.7304938826629449,
0.6928265009008102,
0.7626770439950428,
0.5861465766999427,
0.6379654010254923,
0.5474579125932214,
0.6206406873298734,
0.34416357307486556,
0.7548717967046711,
0.5502538834860828,
0.5027561761484635,
0.5470868059859839,
0.6221846374139478,
0.6541877337868486,
0.23359690586837378,
0.42202445565370883,
0.4127383933848101,
0.5685159101740999,
0.4346402706845543,
0.5270815112371503,
0.3745883605027476,
0.6681714404121435,
0.7529429079207539,
0.565137057846816,
0.513562710553634,
0.761180559200408,
0.7400941543857559,
0.23454460946293754,
0.3417239133403634,
0.5184363385787905,
0.6217488548119035,
0.65818387647938,
0.6789536099294292,
0.47960332083811574,
0.7026827990346732,
0.6743882032846008,
0.5046562252182791,
0.5023761874270203,
0.4123313520514298,
0.6853331505864326,
0.732253270261419,
0.6476773055074737,
0.9100729419780401,
0.9266447094058521,
0.910499103951144,
0.3293600157883314,
0.22651567762533453,
0.7661546307580013,
0.2521369087902962,
0.38503549934124703,
0.24095643051484295,
0.9031440648057495,
0.8994443236640293,
0.8955457153844077,
0.6290907033550504,
0.6283190812657072,
0.29703431389749946,
0.4879708148533236,
0.6664671354149192,
0.5624129658562766,
0.26851200486547533,
0.4029920554402229,
0.34429160718056095,
0.3382237966978445,
0.4384365666574056,
0.33586799483462126,
0.3591035732642854,
0.5000254580649721,
0.3814148845580153,
0.9181840794065238,
0.9234462852357019,
0.9317344746397628,
0.7427664347260036,
0.7447831064046834,
0.8507955259455595,
0.8703466558632768,
0.8612879823463576,
0.867371887015794,
0.17881731632303458,
0.6565076591838024,
0.32453885646632036,
0.8016820676767271,
0.6232934251343758,
0.7770790864497275,
0.21918651553917579,
0.7075382654699951,
0.6811164702662299,
0.709123703312425,
0.5195220773260741,
0.4020533107427699,
0.94469013015834,
0.9310905419325225,
0.8730660799938971,
0.6575648880617736,
0.8606997428036833,
0.5397678405467308,
0.37693811548367645,
0.7760929086624099,
0.8630552103533645,
0.5792035917974598,
0.6396058123143298,
0.6244802966288321,
0.85740054942294,
0.8647331496005767,
0.8953921241935222,
0.6298156685128283,
0.3294758280132377,
0.567932591801583,
0.47869423632721686,
0.36308583696470836,
0.5124421044602792,
0.37019521009552525,
0.6706333996468099,
0.5441580892477922,
0.799289411519278,
0.8685840448276606,
0.7773676535560156,
0.7496678432006568,
0.465936857563394,
0.272716439800878,
0.34130350301236123,
0.5502815920216603,
0.4153720272282532,
0.878542909992761,
0.8532682580295462,
0.8001264106106275,
0.6120781964484588,
0.5170034091954859,
0.5561145580542447,
0.3245596297512203,
0.6119528955621147,
0.409752935256393,
0.13844983972494807,
0.16755294703949364,
0.1351186503804879,
0.8832849280981344,
0.8370614719844912,
0.8658121779320028,
0.5521054759295733,
0.5340893028681996,
0.3521975991296703,
0.6284563373977498,
0.6046869169360267,
0.5071600872002092,
0.6309548823440996,
0.5504167391281276,
0.357817303202834,
0.5795708881281405,
0.31442317219522986,
0.4018913300820046,
0.5712319982212751,
0.4541604683854019,
0.7191953089961711,
0.5446758915848415,
0.5444912200425517,
0.5552459397861007,
0.8468479634891164,
0.8377076502477844,
0.3049237079746381,
0.7300603919516148,
0.6496775304522039,
0.3508407164310068,
0.6355610530383436,
0.6962882898979389,
0.6086946120145516,
0.731567251463501,
0.8371658100256752,
0.7378260086283878,
0.7954802023212141,
0.7770155665253015,
0.536996010227951,
0.5334527230076649,
0.6660037310031659,
0.5641725951465832,
0.3754043234614124,
0.3534392443040181,
0.3721350555508094,
0.4389373509914569,
0.31594421792563065,
0.2467026991861176,
0.3831510262680241,
0.4185916138587923,
0.7212603152894136,
0.7901759077658608,
0.6853286469268849,
0.6538279165601162,
0.9390892309904115,
0.9555410021983239,
0.951348948940766,
0.6217483975938985,
0.26387125430606134,
0.28625244017605933,
0.7456778494389659,
0.6314148935915037,
0.7961631308741074,
0.4503918714428074,
0.29722443669639614,
0.6807277230922104,
0.9111158182340454,
0.8913487512698729,
0.9381817194028643,
0.9046184146596512,
0.866223657118071,
0.911899820382904,
0.8523797857548303,
0.8224461655316746,
0.3631304564910165,
0.8360512174432777,
0.786608276458464,
0.8324071876397278,
0.7048864011831375,
0.6095893528141467,
0.6857626990570342,
0.3196213533769593,
0.6420911521971898,
0.5281796289381119,
0.3403770785277809,
0.5258142468309406,
0.4902890758561824,
0.5560080146355418,
0.508080343359018,
0.6156847224647378,
0.5841199694751167,
0.40640417278478014,
0.5723719322621741,
0.7073690708198499,
0.7748739690798403,
0.8979723417835935,
0.6994027969654194,
0.7085491489543158,
0.7835429351400849,
0.6224167293354376,
0.5946047635538708,
0.6860555706981295,
0.21491548984402464,
0.3062049392630076,
0.4397988709712597,
0.48292219628941385,
0.5563002768039305,
0.3705823929419315,
0.7901687088659959,
0.7638601479562526,
0.8644970045470612,
0.6454136441366216,
0.4928220507561265,
0.6060004535321698,
0.49953881124663047,
0.7095591746417036,
0.749219054231638,
0.7697829850913962,
0.8181916069773716,
0.9220306034448806,
0.43518260857028,
0.2822365895149559,
0.2979291194926531,
0.29174136987842003,
0.27414683480610796,
0.20198977968245974,
0.6172191023311334,
0.32236168897111916,
0.5437722671965598,
0.6513098485653831,
0.5905681737486645,
0.6165148267977688,
0.6820622916504222,
0.6411978715573817,
0.6542323406168071,
0.5733487329034681,
0.4524770645501195,
0.915326651170172,
0.583453194993649,
0.5010411897337526,
0.29753468290768337,
0.9426074369160202,
0.9461582604346416,
0.9384131818592333,
0.3429330283683659,
0.33527659361964934,
0.7190366903099474,
0.3138260405066181,
0.2901811639353069,
0.3268881285106794,
0.6198302624923524,
0.44613245359824816,
0.4800099176877493,
0.3116808029746488,
0.5063676705285353,
0.7920301282685475,
0.5591248775220831,
0.5764142881713263,
0.5769113623737337,
0.6010289874539672,
0.4287903384434575,
0.6283576309708738,
0.9321427285818513,
0.9090299723604739,
0.9371852086164955,
0.5223075175405144,
0.40526983985203635,
0.6118358213350106,
0.41963120666958176,
0.4880656626974031,
0.3006757230714885,
0.5932565713711613,
0.7029236012680117,
0.8431633272175051,
0.9102125153897707,
0.9383758594800455,
0.9216721236233198,
0.5374642504360261,
0.6701899326839964,
0.6606140540625371,
0.8546924243060499,
0.7501940400300873,
0.7844833044852176,
0.6948593035294723,
0.775007707852083,
0.7467181200655607,
0.2056590927818822,
0.18238518765905765,
0.20210591043849674,
0.8960537898792811,
0.8608291762289171,
0.9248900763037315,
0.9109640185086426,
0.2488901657432369,
0.13707643014197543,
0.5511955496821034,
0.6490795049769748,
0.6189931183147662,
0.7033463228622353,
0.5758317457662102,
0.5480991957284557,
0.45061999484097315,
0.7180338656177043,
0.7951743332047262,
0.8030482120255691,
0.45871941415420014,
0.7487861539213725,
0.6481566131891958,
0.451445470554604,
0.3831691417242411,
0.7010293512607229,
0.7953611730484024,
0.840121227658206,
0.23222803959878577,
0.3110307255814806,
0.819510470925514,
0.41424129525633285,
0.812895228162469,
0.6165619044469989,
0.8663775287761112,
0.8269411728743155,
0.6945224874956744,
0.5727681482300407,
0.5778883221024045,
0.4207958197172639,
0.7331207061822728,
0.582647446542603,
0.3152001408818048,
0.5017795892342903,
0.49191730808314066,
0.6601652812150749,
0.8947156179238421,
0.7476703691618117,
0.8213027445077928,
0.40679378264854665,
0.5876911462586402,
0.5141211054366105,
0.447546641680829,
0.20565224051949232,
0.3173410311802396,
0.7116845558063458,
0.23083598037254313,
0.834861919072773,
0.6851923329510132,
0.2863262909208715,
0.47139707073274867,
0.8292972696254213,
0.8485194677659615,
0.834020185788565,
0.7810346377454593,
0.8060054085857905,
0.7891223012109294,
0.38535640632463647,
0.5334570777436142,
0.5074215996791328,
0.672332878708773,
0.713511955373779,
0.6936269357129635,
0.646161546377537,
0.7248137601277237,
0.6235584938419871,
0.7566311850648846,
0.4498315979880372,
0.5731218677660119,
0.9408080385108225,
0.9369727221502577,
0.933654547979885,
0.5687174722903549,
0.7039684389281873,
0.5116432019711716,
0.845307760633229,
0.4751316088148503,
0.865916798049131,
0.7965665807042156,
0.8067072608633293,
0.7486681351128137,
0.23201255895775008,
0.5618445146540211,
0.24505050674754225,
0.6423447701135425,
0.20814926088775143,
0.5639591431964848,
0.3754702727189907,
0.627068752715867,
0.691738131690099
]
}