Files
GENIES/results/evaluations/cra/llama-13b-counterfactual_python/counterfactual_python.json
T
2023-11-11 19:44:09 +00:00

761 lines
21 KiB
JSON

{
"model_dir": "models/llama-13b",
"distribution_id": "counterfactual_python",
"timestamp": "2023-10-16 02:36:49",
"eval_score": -0.18836491233212593,
"eval_brier_score": 0.18836491233212593,
"eval_average_probability": 0.6467742181511937,
"eval_accuracy": 0.7213333333333334,
"eval_probabilities": [
0.26860499530933424,
0.4545325055018037,
0.2664791966350384,
0.673262793156005,
0.6013380055112875,
0.8665210542914298,
0.9105861385727488,
0.8988125971942831,
0.897055114667926,
0.6577025876113727,
0.7489363421819278,
0.620581177751848,
0.8423481559352348,
0.6803594333663522,
0.4095095241827969,
0.539834656350176,
0.6630478437765137,
0.6927432784219371,
0.62113873498916,
0.48376366155935735,
0.5576879772993267,
0.6453316330716846,
0.4553502644924702,
0.25602509235175996,
0.8021981461510541,
0.585580456792926,
0.17154482428833479,
0.8729676128157131,
0.8669136018010769,
0.9513010709232299,
0.7404501353654263,
0.4286011508730645,
0.5361756447555088,
0.4253465127755399,
0.3623545348646171,
0.19441000291171595,
0.8273105428948044,
0.9017411033887542,
0.8849393632759006,
0.8503389923553729,
0.40934679667263063,
0.9049564891827212,
0.6169097445478999,
0.6355713994194142,
0.727505809019126,
0.17180923270737994,
0.541509992502281,
0.2049331186446297,
0.5774949144520635,
0.5221352161309285,
0.7210617271667945,
0.7480939192612233,
0.8013683014019192,
0.6129403856650167,
0.2662333204028437,
0.20261578817911707,
0.23310513341231687,
0.8308852978631386,
0.860564571353531,
0.7661265673538231,
0.9054117422739231,
0.6631906980837399,
0.6992839430436645,
0.2863709517308468,
0.7148801668656292,
0.29912770921585063,
0.7430931306704789,
0.7995869907502947,
0.547511638785989,
0.9380454043452969,
0.8137293521949411,
0.9254579080197011,
0.5503763490602362,
0.7948207190560487,
0.707452775654175,
0.6812730820530091,
0.18399515764054142,
0.6726667179155654,
0.06623197065308117,
0.9012350521800117,
0.1060820695285043,
0.7464480111874932,
0.8133049430097716,
0.8663120379494015,
0.3423827706811542,
0.8964732797119825,
0.2756816064033476,
0.784807951348085,
0.814154848541534,
0.5320044912587292,
0.8339842255116101,
0.1284350443626885,
0.623518518368007,
0.10613277191138584,
0.8095954741350162,
0.5374096574961539,
0.8117974623832079,
0.8230981539614667,
0.8888013847812009,
0.19895945005369908,
0.15581580987482158,
0.21861361527651457,
0.5058007956554809,
0.5313509092492968,
0.5207597472794533,
0.9899739148005258,
0.988205026752601,
0.9921525542887065,
0.9902051633603989,
0.9861098261020009,
0.9906342089817715,
0.3188545509922843,
0.6893266302817947,
0.6938353515736222,
0.6597578238167925,
0.09931095743574977,
0.7844637933688778,
0.9295147966391097,
0.9310844739471419,
0.9447133658835126,
0.5200069107366313,
0.8802880312632768,
0.38095119297735336,
0.976235944228921,
0.9490584715751484,
0.974752226813689,
0.7728209536811929,
0.38530862922599185,
0.611072784343432,
0.6958980260037457,
0.9610067384715945,
0.9692785275959687,
0.6295772563260202,
0.36194612135702153,
0.802687685033352,
0.2891121382441631,
0.7241123382794697,
0.6589756617453151,
0.5613226452635216,
0.4913274065292065,
0.7775236847385183,
0.6257859485226257,
0.6079231789695786,
0.8389448558232917,
0.6021610269565086,
0.4872678900452111,
0.47755065895843574,
0.570655574179618,
0.8519695851742112,
0.7605673796343168,
0.5195105463628654,
0.5575178330939373,
0.6309808321232683,
0.9864754779694848,
0.9515319198540528,
0.9944258727768274,
0.13937121225445398,
0.16478448967413645,
0.19288657701603643,
0.32839441744730324,
0.25139246061090625,
0.8614347103491463,
0.7830189739961906,
0.8033898749583646,
0.8382762547646803,
0.43470474845947626,
0.4084155901722162,
0.3426644399169483,
0.5764170131146403,
0.2851242348854077,
0.5411913091253021,
0.7245048147521027,
0.8260781014081602,
0.8196462421269181,
0.5549127265144705,
0.4560418739818122,
0.24025442799447772,
0.6094633368448235,
0.7876346073620166,
0.6877372002184807,
0.48953452137846165,
0.6235249035175359,
0.3872048215437127,
0.9501072494671975,
0.7702962726677421,
0.9503657249834334,
0.11336850329269547,
0.38605846315244013,
0.7318313963872802,
0.8100226433490608,
0.4371118628126296,
0.7989407559485188,
0.8214249850702229,
0.6360579533481331,
0.820933192733444,
0.48891089602817994,
0.2060825866860035,
0.8339866465333278,
0.7982555687366619,
0.7842660107058252,
0.6272643809860485,
0.5045407800214022,
0.6716798755502529,
0.44112493186454504,
0.800038491772715,
0.7335435380420405,
0.7856010355915561,
0.5828008237372371,
0.6766421362870729,
0.8468691893696869,
0.617318782838757,
0.5746157323892578,
0.39703617116224965,
0.6490127403660849,
0.6852143154679956,
0.5886241277383829,
0.39813834805299264,
0.803329292299996,
0.7316251049658786,
0.9166777639851282,
0.9645981824364764,
0.8918420848750465,
0.3864935512264219,
0.5900426115570756,
0.26025040568968977,
0.771573870397966,
0.7738118069882639,
0.8085095241953029,
0.29222338363862355,
0.25706082783620976,
0.21949802179308395,
0.7501816857373839,
0.594976779255654,
0.767954963205805,
0.8353230142888848,
0.8767869205481414,
0.8695464466206307,
0.9066009996370736,
0.8350312230387392,
0.960946884266495,
0.9515166399705277,
0.9463666300687373,
0.7849744287162201,
0.33019006481587654,
0.7215188072551527,
0.2811072555937945,
0.6781530622469566,
0.5542525722144327,
0.8973387033751739,
0.6443486421660558,
0.07817376340746357,
0.1419168678707745,
0.370236763584157,
0.6894645930321734,
0.7483903341600033,
0.8866367470495714,
0.6725859076552293,
0.743568351425334,
0.818358981335816,
0.40930681367912425,
0.5093949310729056,
0.6355900748949214,
0.540861364752965,
0.4787409035303417,
0.7492390757759926,
0.6451017461983533,
0.43424144751475025,
0.5850595936332417,
0.639543056228761,
0.5819881799803186,
0.6217573253049384,
0.7195104341247203,
0.8367125905799094,
0.6398953096722265,
0.5109318608533238,
0.2924988266961123,
0.2405696285232565,
0.4586130165219315,
0.46554158406389656,
0.6745934349510851,
0.5312846258281803,
0.6015536926610083,
0.4709427295955722,
0.6264220800603428,
0.5185616566282192,
0.8811974000273155,
0.5955012887578227,
0.36554971009401505,
0.6537973088735496,
0.711872879388417,
0.21473294571373847,
0.9080605575636456,
0.7260715607358886,
0.7306586044470769,
0.9860644054686846,
0.986244855198844,
0.99045580455752,
0.8909155877549086,
0.9193868558829311,
0.9190588699600923,
0.9682926932020223,
0.23578353427653487,
0.9178276028685716,
0.8302665466898331,
0.868152338501801,
0.3901527229412187,
0.7649473312708044,
0.2376088663393625,
0.672737136479881,
0.4982202132334228,
0.4365062224594631,
0.6042893202222328,
0.3277589296414769,
0.3340284446659344,
0.44553113944113476,
0.7775204078940449,
0.8266880201339172,
0.8771603613483338,
0.8671024564033618,
0.8969257935666625,
0.5501845690474371,
0.2203610397041239,
0.48409938111115525,
0.44305830566423915,
0.1759376986018979,
0.3547350731865282,
0.1224737249938827,
0.893020771940269,
0.7823164055980983,
0.8271766770667596,
0.5888758039299414,
0.8364238426699255,
0.7077548155855641,
0.571969804028002,
0.4461245696664754,
0.5507966484961664,
0.9068265540903154,
0.9124592457095149,
0.6906357726420359,
0.7807202152846453,
0.4331600896236411,
0.4571361605531804,
0.5823828034082548,
0.6228451533459829,
0.6566480411469118,
0.63818780385821,
0.5756407933327945,
0.5488602983075515,
0.39425318603017245,
0.17210043139840203,
0.09267187992622085,
0.9177394929187345,
0.9064910033117979,
0.80193469648517,
0.48818997097823524,
0.6982015677172964,
0.17057190230086652,
0.7834451602306234,
0.9331277702716835,
0.9464186373896045,
0.8986129880601179,
0.7978060803246022,
0.664360525826382,
0.9704324177598843,
0.8466178801767248,
0.8704764338081655,
0.5827266541712625,
0.5864062770034201,
0.8479624117501201,
0.966610517503415,
0.988799469772119,
0.9452729591188558,
0.8814634939418271,
0.8827367710547913,
0.89031978145098,
0.8726323047537731,
0.8694329269913144,
0.8525582569454905,
0.6418359760978943,
0.7815355709175845,
0.8930945777964201,
0.38930159684125426,
0.7949104951052138,
0.6175170974654473,
0.9895047846692855,
0.9918357778825074,
0.9937260248842739,
0.552575710197955,
0.22849980713684032,
0.6607312035321862,
0.5272919377505034,
0.20136851842233616,
0.2203373411711742,
0.6672476121540198,
0.7144874540917744,
0.7797829974678995,
0.5952474238505452,
0.6530271496673672,
0.4163698032354839,
0.7587604162250448,
0.6965119572996622,
0.6508241223655409,
0.8013522190780799,
0.7984631352274443,
0.8952892928426813,
0.9713181718363053,
0.9545696018249389,
0.943540542969143,
0.9458320028157641,
0.9437834868622396,
0.9499271160417952,
0.12309629625341992,
0.5305090356806721,
0.5675784123702032,
0.7170234792423162,
0.2538580543195623,
0.424501239895721,
0.4679565681797552,
0.5579560419826988,
0.6824968116938596,
0.6965692464994035,
0.840566582351156,
0.607168074409045,
0.9947599008692295,
0.9855306248056334,
0.9942234146753997,
0.862037050601615,
0.7497060699335008,
0.7954081317741647,
0.08619638716330817,
0.1797365413210846,
0.37345908272323936,
0.7587822871144401,
0.8179515123816867,
0.8612760892044784,
0.43283935903565307,
0.4231103368040282,
0.5704173064094084,
0.40017935135697835,
0.7332156810388626,
0.8322968342279797,
0.18306758838931625,
0.17004355372112542,
0.4077547991373135,
0.6874650898315589,
0.7552440345647888,
0.4960510346241599,
0.6452901046630318,
0.9513422338080028,
0.9522305907641458,
0.8609682522887776,
0.8497317911804859,
0.6452638661587851,
0.08396206855898747,
0.3661705281800942,
0.8133006313766367,
0.9183519836868816,
0.9597597698078909,
0.8255564645478768,
0.6589094600810871,
0.4054907506214603,
0.5793871553277439,
0.3201065796768652,
0.7409080279665915,
0.8508726853023284,
0.7880814394963036,
0.6709633533433983,
0.7672158169247155,
0.987932713058016,
0.9581238329281843,
0.9792325665027382,
0.5844151486456276,
0.6786601353747655,
0.7123755363325874,
0.8808877586265167,
0.800616490874682,
0.6761589739154668,
0.551489977727488,
0.12421122831149212,
0.35921609491951473,
0.8619559522821083,
0.8899299534945675,
0.8385259623166481,
0.8555377468902945,
0.8594808282648454,
0.7432388718929717,
0.9646350275343617,
0.9561577652778486,
0.9360137359301277,
0.9060852232376736,
0.8461169049720981,
0.28712660502750675,
0.534390978324408,
0.8745100393469045,
0.44316869645105034,
0.37928759699267345,
0.40973886843382645,
0.4631084730500525,
0.8397389613536855,
0.5713736946081791,
0.09204462816177315,
0.8907165526668832,
0.9034859152150397,
0.46506810612240534,
0.6183534890926095,
0.7582162730463797,
0.6074359475537303,
0.13395111486916422,
0.13688108940773713,
0.1375194367010032,
0.3459583804173506,
0.21266456773804487,
0.19644334808691344,
0.5384837456337752,
0.4660150684852518,
0.9093102778326878,
0.7685343391671978,
0.7592235053012315,
0.6888214875749862,
0.9640252335620026,
0.9854717954100765,
0.9815984362335345,
0.8033604117822379,
0.47987337358078,
0.7922926470866832,
0.9237710649797635,
0.9415039000879473,
0.9468125488849014,
0.9299524432679162,
0.9434898573583952,
0.5071984785226782,
0.9839667813079016,
0.9766634937681533,
0.9856218907837669,
0.992905696196292,
0.9798946456191059,
0.9854608625443857,
0.16294788911445948,
0.21455060075124843,
0.8454896927145877,
0.9552702327567556,
0.8993140581706909,
0.9627314766046473,
0.9029508193841352,
0.7762604423627106,
0.9092527417713017,
0.5737810412632742,
0.7740284832421206,
0.5040618894693523,
0.7143278001123186,
0.9003248387336829,
0.10540779424810887,
0.32248123716504085,
0.4740902137651869,
0.22465041489544801,
0.6877733953389332,
0.8853684014888162,
0.6285485766908661,
0.7421620115191383,
0.6572180466233898,
0.9899155856742402,
0.655109564979748,
0.6977574337050532,
0.8175026887499656,
0.7448242761402201,
0.7327659331432813,
0.769440181751192,
0.6219211708374234,
0.5390543014903558,
0.5636041677813236,
0.5721434120188698,
0.5664579404314949,
0.6532701665845326,
0.8551751944656212,
0.8231719466642868,
0.6272085577576827,
0.7586525053960047,
0.7089678730458024,
0.5654203373631072,
0.34975411161605696,
0.569670158072792,
0.4649996563843766,
0.9846637081716685,
0.992885872278502,
0.9927876655101169,
0.10491560963279611,
0.06559117488284916,
0.33021971491049196,
0.8569342140857208,
0.6277094463150769,
0.659489547588333,
0.9508702879235311,
0.8890450214630286,
0.8101559148531913,
0.6136131470692963,
0.633222484103755,
0.7159585742028144,
0.9620654272417714,
0.9744420047300143,
0.9842890676658096,
0.7974476123839221,
0.2804276621442072,
0.4012560894070079,
0.10094680908204101,
0.22625927365894286,
0.6762907381265135,
0.947909872348938,
0.9338491647197849,
0.9295587148462819,
0.6210261393058849,
0.6961572507223037,
0.8000901963236228,
0.2988839787993046,
0.12391985268852079,
0.6613831076602145,
0.5939507106232025,
0.7008745310977367,
0.4713164600175191,
0.474922223795234,
0.33819771822667766,
0.5813546184412615,
0.8479386142909088,
0.8622826077048443,
0.8626017318114348,
0.859711918164952,
0.8373041714597724,
0.23615399716175667,
0.9861434077550871,
0.9084281041992596,
0.9684777795050589,
0.4163806081207274,
0.1959662991383032,
0.791703401100202,
0.8681504181420128,
0.9948338656387198,
0.8607363348375627,
0.9381356590798405,
0.9274453489129059,
0.8883803485569625,
0.8335248275534963,
0.9888296595395399,
0.9850353339818612,
0.6634510391103853,
0.9029343031053653,
0.8839618054873755,
0.6838381260845436,
0.4105814231938447,
0.7047960979145522,
0.952859672025855,
0.8569785449974606,
0.8138287233536325,
0.698467352175834,
0.6764999719902507,
0.5887443900390037,
0.988476419671767,
0.9897250994064896,
0.9909903535329101,
0.7055481845117578,
0.2231714399825999,
0.409973196081891,
0.8517418038286257,
0.8643029506880352,
0.7216006385749673,
0.5642906841815962,
0.25694123021717136,
0.5358337754379725,
0.57811486009786,
0.25731786881760677,
0.42616615383581835,
0.7044987950196528,
0.8229427166399821,
0.38926550553908756,
0.41204238622419775,
0.14433209178625428,
0.15536218217578115,
0.9897207988705677,
0.9801360276844112,
0.9871400579076438,
0.41950560028854,
0.05396108697596599,
0.13275736801317714,
0.2830043138792135,
0.17103005967448265,
0.7977935435159831,
0.9415358861191538,
0.961664696226178,
0.8148087867850715,
0.7334386175325274,
0.5407886296874773,
0.3899691592570243,
0.3187576676216379,
0.6569157493858412,
0.442615176357113,
0.4365801133869871,
0.6037519535177317,
0.560626423977952,
0.6744365696871483,
0.3887882983602743,
0.6058316601410012,
0.25162956327867514,
0.3439859864753934,
0.49266603248891494,
0.2789588341933602,
0.14420484528769237,
0.3140391609314398,
0.33668188945949246,
0.4030262394003022,
0.7842452559083417,
0.44704933739283237,
0.5706151114287392,
0.1362877445626667,
0.9132753648904806,
0.6190915850431812,
0.9220127370938327,
0.9117461556095467,
0.9046377933928962,
0.9182762866226026,
0.4854636130247138,
0.2907459785864883,
0.6825875340503715,
0.48274744935547464,
0.588566612039154,
0.4308762374425669,
0.12914903184820603,
0.24349626138900238,
0.2294684103933866,
0.393090307718155,
0.9089500978570035,
0.1302087553149861,
0.9909375172493025,
0.9924143118248988,
0.9940030666025573,
0.7843240251131769,
0.8722020099062968,
0.7026724688509407,
0.8262340550521887,
0.7124959449308392,
0.9125703009648174,
0.7909306946819572,
0.8879185027044959,
0.9337700858530246,
0.34040656936650876,
0.4063594074198042,
0.1194701710974515,
0.19637116694430867,
0.5050430306138998,
0.28822919551568016,
0.8739710467307997,
0.9017200991736961,
0.8363266905453354
]
}