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

762 lines
21 KiB
JSON

{
"model_dir": "models/llama-7b",
"distribution_id": "code_hard",
"timestamp": "2023-10-14 00:06:13",
"eval_score": -0.27119261092729446,
"eval_brier_score": 0.27119261092729446,
"eval_average_probability": 0.5719051013486147,
"eval_accuracy": 0.608,
"eval_probabilities": [
0.8357455174262569,
0.836089264067936,
0.6276084382513512,
0.93107972524585,
0.7994910956357882,
0.6586566055995844,
0.2458204768756772,
0.8375288671978727,
0.4095007351637321,
0.6511122414112798,
0.44472237707385676,
0.974015687127958,
0.7620438407919738,
0.20339936051832808,
0.5294973459344936,
0.5720659084629155,
0.8600120362282934,
0.17342028933301912,
0.7167575269019426,
0.7399721676104644,
0.7024477722302273,
0.8561833120515334,
0.6150542798079021,
0.9064931756075635,
0.849859482592017,
0.6738252825473473,
0.5992693119679243,
0.0723249497293389,
0.7865967803789563,
0.6326775357302594,
0.5826896798426975,
0.6012316689349655,
0.4889293742173796,
0.5156496556950082,
0.15306727822340727,
0.5425942762578918,
0.4297608171261077,
0.11142673268170045,
0.38159082552711776,
0.4267333582613423,
0.5450843126375005,
0.9398429909871452,
0.6382553931815587,
0.5343736779634911,
0.34830106578815706,
0.9965753600731438,
0.22886167299774662,
0.37752902345612716,
0.9907826839515522,
0.35797164412307136,
0.7965873867256011,
0.27614784245165863,
0.8153178677287526,
0.19079183611943162,
0.13177274034776498,
0.030565454194152464,
0.033896548641692115,
0.14858446771159117,
0.8588829309811313,
0.8789125696415703,
0.34827809576019875,
0.7315410107596814,
0.7245684288223015,
0.9976941652699775,
0.9816073355379272,
0.9831448493187777,
0.1701757828847601,
0.8067388715196161,
0.16316453761435712,
0.2099434435329638,
0.32037859858880147,
0.602089239141967,
0.6862396755975833,
0.4837089340038554,
0.9176194634448656,
0.876939547507505,
0.13987945033716542,
0.4493641781050885,
0.4236603282704873,
0.056016839248035244,
0.8868218286594577,
0.8555247870844341,
0.9963529538792648,
0.44451579802320074,
0.3635103023006342,
0.44961104444811784,
0.7946138347375296,
0.4322168902403445,
0.6759370544954004,
0.40635293221572677,
0.9080224273538602,
0.9321452328362936,
0.8779163334772788,
0.018028207555206954,
0.10124951649656078,
0.07513502165628723,
0.3571416961499956,
0.9427143753617283,
0.7913867928673873,
0.9867027409092824,
0.7423816334839765,
0.13909450522530697,
0.9358791767560958,
0.4606456667734037,
0.798321483643171,
0.05905246139779596,
0.8872103979468128,
0.2879680269702827,
0.06935121356167884,
0.8352621494706713,
0.9589115281459404,
0.6739639647165181,
0.29790020189190336,
0.7164191703441796,
0.1935101942812908,
0.192600817870768,
0.16545610222098373,
0.5115788914192619,
0.3567164346376971,
0.3372131177361226,
0.2185636696846276,
0.42897886998130563,
0.496444838315653,
0.963938682057028,
0.6444846651578581,
0.8313167623952611,
0.6454231947219631,
0.6438741839539119,
0.9232124925367275,
0.5152990462976755,
0.18809569785217506,
0.7180019562754691,
0.9593745352386811,
0.9289749888587002,
0.941501921912239,
0.9489511805634663,
0.9391852089353662,
0.7865944182907167,
0.0420306114425929,
0.18430651012070387,
0.2450607613789354,
0.06817090797580938,
0.7540525894992721,
0.8174888553153719,
0.9190870284986794,
0.9600616314419439,
0.85898675481624,
0.6362074359190693,
0.7093921996037456,
0.6301684335301865,
0.7213297635313733,
0.7799174784439016,
0.966710404575456,
0.3335043958890678,
0.797869050422612,
0.3666199012443285,
0.512064736365244,
0.2704147571514509,
0.08100717896550624,
0.10871482793899068,
0.06849226067359604,
0.018541692673919807,
0.2269564266792482,
0.5351312343702677,
0.9415563381444202,
0.3937103095923816,
0.8299943892551815,
0.744209940112963,
0.8799123879352718,
0.9780330595210273,
0.08818371449776907,
0.7641114670686378,
0.7403271344205794,
0.4594376801276595,
0.5412376580353639,
0.15596546688714874,
0.16432713139963295,
0.9118155706522162,
0.6900418755782468,
0.422534964746619,
0.9772716019049701,
0.9551430906394826,
0.8609908713684883,
0.7551355701996214,
0.10209757215991545,
0.17852920917205917,
0.9408779459481024,
0.8744386840936663,
0.9075555346419729,
0.11687313804473298,
0.9864755835216406,
0.1278153070554897,
0.9892564918411488,
0.2097285257677689,
0.19179470453146372,
0.30580501541998995,
0.3667225089635723,
0.7896838265509989,
0.6737763980845944,
0.0783582395848833,
0.1898793710863499,
0.36765599331129173,
0.3576531298245958,
0.12600964795740877,
0.29317561112158763,
0.5973886580231351,
0.26362997664177723,
0.4024892533485155,
0.12135603271681072,
0.4328614512984077,
0.07289919170936188,
0.0770087632713834,
0.07999769981652316,
0.5026321976004839,
0.1609650989709116,
0.8043332346151173,
0.25657746951230165,
0.8168672594300874,
0.6311019780857248,
0.6721963287033521,
0.6550181204293856,
0.8276640743550903,
0.44858931686953996,
0.3427207321043899,
0.47697788449328066,
0.9862696635804239,
0.7492941942596714,
0.8249180298502305,
0.18336053771148353,
0.5364347346748173,
0.21917833614276883,
0.9873853854673709,
0.9204216336160957,
0.9843165584031467,
0.22315893444420876,
0.28965826849304166,
0.23134715317467314,
0.6786861374176156,
0.8879018198924156,
0.8301208011992395,
0.939892632877674,
0.9917446067273462,
0.9357159543824817,
0.820005043350852,
0.39811951198826845,
0.41392268272706245,
0.3078910543353446,
0.7182931162051891,
0.25809303107603854,
0.9098054809892897,
0.9926222610526364,
0.6880295552930658,
0.8998017587462939,
0.8589253804981444,
0.8486448577797802,
0.49026275079250525,
0.11180350235525849,
0.4055864242565292,
0.4486836593982849,
0.14261477336274775,
0.1272670567056522,
0.46192128976803537,
0.4139395051652811,
0.5466470818089044,
0.9531189153896122,
0.37971160313334673,
0.45994352596702165,
0.9412619191719267,
0.9152009018708194,
0.9537940987523656,
0.7540608616559554,
0.9670481714285432,
0.8351566737151246,
0.8646858282406097,
0.4303982463822209,
0.2419286681852474,
0.8554036501987936,
0.6509335228664941,
0.8921251222980096,
0.8756307238206879,
0.811881491856821,
0.832702726505638,
0.8065627756327384,
0.8073397277938458,
0.8659085817917885,
0.6725311909697542,
0.6170786569492954,
0.5838513982985085,
0.9686610099426536,
0.799583287874813,
0.9779174737445262,
0.4959318582089956,
0.39949542310291664,
0.8554806071790235,
0.646330460009171,
0.22655020449270957,
0.7987107995243355,
0.46507511471578655,
0.4469913773927586,
0.5124752219814912,
0.8701568389873587,
0.6990359308469821,
0.7719558447977237,
0.7597370166970101,
0.18757191856964373,
0.6733183847264225,
0.06697045850914263,
0.333808558187127,
0.5703816278686177,
0.9862022746384314,
0.42540852902069826,
0.814466844053512,
0.3532176710516324,
0.2476966430351546,
0.8062702149926461,
0.9100408312286102,
0.28860393651000205,
0.8308502175219631,
0.7311577742233922,
0.3831644615074582,
0.908387677566529,
0.18964781531053088,
0.6257370950729899,
0.5405718520552099,
0.8586059747978784,
0.051919873286526474,
0.04559387565085726,
0.5194014072881106,
0.6499064363103082,
0.9946542519247331,
0.06178583845632801,
0.6216932942214975,
0.06977333438016675,
0.9345305795284358,
0.37541601783704537,
0.882313808103292,
0.6120147896786352,
0.2419390753400066,
0.06113538024302834,
0.08379334485054157,
0.48601514848433497,
0.2560006482585854,
0.5164520685740321,
0.7559211453663723,
0.7902567388086358,
0.0500888857031806,
0.2105208687159284,
0.047069501123579105,
0.747233882422504,
0.8815786712624843,
0.6662477508876652,
0.4037526657479955,
0.3679413029081833,
0.597172851913712,
0.06788300094413213,
0.058671661541517595,
0.2550217743477106,
0.7389714382465442,
0.9239838662389472,
0.8670551817864703,
0.6052028782739308,
0.6496399870425487,
0.6858674318432338,
0.880016435633601,
0.011008551363291152,
0.055672588829093095,
0.8249578528186712,
0.9608095524285913,
0.9604822582847696,
0.4018899272380976,
0.9572054576715208,
0.9801151849369264,
0.3721117590385651,
0.8256430821614243,
0.7469748676418402,
0.2659373460516451,
0.792475222444214,
0.1752502396665544,
0.6294369103119182,
0.289583275372884,
0.06914596150545871,
0.8323901434390619,
0.9480685723539943,
0.9328388592403,
0.952053679837976,
0.054124564652869966,
0.8498407837090928,
0.6708337921240388,
0.9734734813282165,
0.9575103954024227,
0.9720464241279574,
0.9563904001738127,
0.9748699224131689,
0.03920638531323073,
0.6149923577933964,
0.6574168376384056,
0.8312186256898109,
0.6874642392270387,
0.8342865807798004,
0.7807175766525211,
0.6735661010159906,
0.9314114677484335,
0.289936392098761,
0.5680246115898685,
0.9132106102184583,
0.96619318629184,
0.9868723166634081,
0.8642299880627909,
0.7609678637875951,
0.5885219986690537,
0.6673785822324938,
0.8637297483813596,
0.8878871301538904,
0.5888801967905842,
0.7511129648467394,
0.5948991625749499,
0.7834955468930228,
0.5294778552475042,
0.9039884355558162,
0.08190503468402599,
0.7442376940834216,
0.9219332644157273,
0.8522606564609911,
0.9848092271381963,
0.9091264605391192,
0.9399849898041593,
0.608270684450136,
0.5842304413939204,
0.5859822402712267,
0.28550000716137114,
0.19290404265301542,
0.5606416083033088,
0.799643092943632,
0.22023088370507438,
0.723817294664869,
0.87882718422213,
0.6033511763544357,
0.81133560799616,
0.03587567819994508,
0.0334526004951996,
0.035751959947917245,
0.18961530001568527,
0.6252122767259469,
0.17195228886805236,
0.5999657523915308,
0.24037594905291815,
0.2600723109031001,
0.18563608413199206,
0.12789282960735004,
0.8816202451485984,
0.24023082520375655,
0.7561605219345944,
0.31190194218872125,
0.7821848920189417,
0.5012063955543594,
0.9630590800092316,
0.9543764040413355,
0.9454563673429884,
0.9739900240761188,
0.43330131684923523,
0.48935701933085696,
0.8990106711247702,
0.5405885944101441,
0.8929032942579508,
0.9567331261096762,
0.9366332277305832,
0.9167589340664294,
0.7183926178822023,
0.23281017295501502,
0.6074321293246652,
0.14973449856472867,
0.6161221323299623,
0.47768365592460615,
0.14737345027866577,
0.17790371180158637,
0.40690718280222826,
0.9880704496758644,
0.5342902817105115,
0.6875864429109769,
0.8527980743208604,
0.9828748533968906,
0.11718787629088179,
0.9936079439870571,
0.6701643796129999,
0.6997926758697522,
0.5900529355152493,
0.44242252537019156,
0.1067540811647395,
0.41262232153808787,
0.8691876842761692,
0.1478342940694093,
0.8864572696934945,
0.6829730758075717,
0.3838473427802027,
0.5120000967109766,
0.3161876692902489,
0.7872994292705445,
0.9621314066730013,
0.22710183130377748,
0.22664212840362818,
0.518254368398482,
0.08547673866176442,
0.45077886424263236,
0.9167459071233582,
0.27567612778170014,
0.4364971625381987,
0.28866490494420227,
0.5268283036437094,
0.23554901280909324,
0.6656583851312663,
0.667370885485506,
0.6554280644491407,
0.14802031021162676,
0.8467579178703932,
0.5705576451734723,
0.12216201310517327,
0.5614797612376535,
0.6940260765560378,
0.5231039542564608,
0.9776007641531468,
0.30075260276530913,
0.9271908847254954,
0.4834853609628794,
0.43739130309090857,
0.622052238779679,
0.25467145816064873,
0.060718383856829594,
0.061326301014366424,
0.8673762278316212,
0.4179326526537328,
0.6944472599221919,
0.962757309554056,
0.4366781945940041,
0.20891924863107525,
0.03670563196220866,
0.16300094886227984,
0.03920250075289888,
0.45978563537114975,
0.09412387237321362,
0.12363570110964925,
0.7298202115508282,
0.7308245934740356,
0.40869674957427704,
0.4498594379098577,
0.08942275686762813,
0.6338952608166836,
0.5301880993620152,
0.306914712776403,
0.59389199640804,
0.7371747269883973,
0.9575875205968376,
0.721850248313272,
0.854110107015266,
0.8334608198957469,
0.787133533640972,
0.9130379639618613,
0.9392622447084666,
0.6943520188418402,
0.9715801066760689,
0.8387990876269253,
0.810412293648805,
0.8489296638965538,
0.9131946844760553,
0.8733409720332277,
0.1371657137749983,
0.5017151399811811,
0.19542873619694778,
0.4653265600218742,
0.3535120591263693,
0.3270575779122289,
0.8267216536824517,
0.9244703654711226,
0.6771286871308552,
0.13809511090690285,
0.3100834798790597,
0.758484254766692,
0.4604307186784697,
0.22337046095021207,
0.10709621028017058,
0.9576174008010124,
0.9124981559724843,
0.8702677087652102,
0.5724621862654579,
0.9774517833666334,
0.7371783145469323,
0.5133050262157914,
0.5629053309934007,
0.2302798568122283,
0.01908139655828378,
0.07938505125926065,
0.02187380983075371,
0.7061410201281275,
0.9381124549482204,
0.8508762445151457,
0.905256056477385,
0.8576658953649142,
0.8786941219644391,
0.7710326891578997,
0.787310743666191,
0.8444626260571592,
0.8408237515166981,
0.16535374749484189,
0.5281737713609395,
0.5914435380005681,
0.11422656422911637,
0.9674318551482394,
0.42573474620458573,
0.9337570261431034,
0.9706868551606519,
0.2993216592569965,
0.7966317521211218,
0.8026521566062564,
0.629768423232497,
0.5840736155504833,
0.28076340308550074,
0.16469934117125085,
0.6283197761114531,
0.13589523974824524,
0.7237791132239655,
0.7527502444929692,
0.9339193848052761,
0.5731056945073423,
0.7571973017501843,
0.9560703942264726,
0.5321658090488,
0.8361009600429077,
0.6461900212561026,
0.994838706880102,
0.7921021430127398,
0.9635553850114839,
0.09935252142421173,
0.6275086978539701,
0.6734451235628185,
0.12523799193741036,
0.13028677270554367,
0.4342443705434175,
0.475794339276838,
0.5575658511248194,
0.6136398751591132,
0.7027897873034181,
0.28368018021505403,
0.7877995223096127,
0.6074666843298215,
0.5659122258035032,
0.989507581610056,
0.46625128733933674,
0.5914463676793735,
0.0727674746227076,
0.20586439193482864,
0.7667975453031944,
0.5701452400075419,
0.9393418233648503,
0.7851231264206545,
0.5549733554094304,
0.267198888703583,
0.6290776854872071,
0.5959981872531172,
0.41698392573055326,
0.46140558900026674,
0.22686222962441405,
0.7580407055620967,
0.9080069822003203,
0.8960508471269587,
0.3685439894176966,
0.6895913878372524,
0.6588512270492041,
0.6593726110102597,
0.8255967477958092,
0.8221398646101132,
0.21452701793571227,
0.08936124390633449,
0.3674088663044339,
0.42606168024616553,
0.1563476077155319,
0.24065592282801085,
0.4592464393126218,
0.7485316773533501,
0.4356816847635504,
0.8631460827902773,
0.9763182109832295,
0.9123445523601448,
0.7948958709131826,
0.4713308653118785,
0.8171976761702442,
0.5216142548551737,
0.5994795884484252,
0.9282132056868871,
0.07376515397338734,
0.04625262683834852,
0.7985941422296972,
0.6875683000709932,
0.6853129945238007,
0.7389907863959149,
0.7882064578902439,
0.7638382748438256,
0.41697423705252445,
0.5043485734026273,
0.6602300657169501,
0.6871932831022852,
0.22988375020684007,
0.04372477198717717,
0.04181422188605266,
0.5021252001228247,
0.553563048759563,
0.945552572167599,
0.2854125716028657,
0.03114799308299243,
0.20179193013914354,
0.8352103762008266,
0.3712434620535186,
0.6087491186631837,
0.7536992509733071,
0.8009381228716327,
0.9200337014684253,
0.33905313963399775,
0.17809414752668362,
0.7414832323778597,
0.7365163511932525,
0.73905697209392,
0.25028771451678455,
0.33301469208318124,
0.8286102818253441,
0.8025673666907615,
0.2396886541069313,
0.611552336752346,
0.1739150542459439,
0.13845528227909487,
0.6292019370356522,
0.6219936769941173,
0.735430076488474,
0.18326721384234276,
0.03527316135895975,
0.9650458183669987,
0.8695315060868737,
0.9981694854419321,
0.8931575500140283,
0.981430589390468,
0.8426734519044865,
0.16918751860368741,
0.5602651317777001,
0.6502214880102595,
0.5322616854256683,
0.698530465448613,
0.49592434017986475,
0.4048189136322845,
0.113628497506155,
0.44446066110178484,
0.30634426481159654,
0.32697889058415686,
0.08329019804840176
],
"eval_rms_calibration_error": 0.2849196377739891
}