Files
GENIES/results/evaluations/zero_shot/openllama-3b-math/math.json
T
2023-11-11 19:44:09 +00:00

765 lines
21 KiB
JSON

{
"model_dir": "models/openllama-3b",
"distribution_id": "math",
"timestamp": "2023-10-20 01:11:52",
"eval_loss": 0.6977721452713013,
"eval_score": -0.2529262602329254,
"eval_brier_score": 0.2529262602329254,
"eval_average_probability": 0.49775928258895874,
"eval_accuracy": 0.6773333333333333,
"eval_probabilities": [
0.5034704804420471,
0.502443253993988,
0.5036406517028809,
0.5089196562767029,
0.5080461502075195,
0.5083891749382019,
0.5094168782234192,
0.5019370913505554,
0.5049015879631042,
0.49703553318977356,
0.48216691613197327,
0.4821471869945526,
0.5058363080024719,
0.5013266205787659,
0.5019235014915466,
0.49939629435539246,
0.500809907913208,
0.49960973858833313,
0.4939156174659729,
0.5101466178894043,
0.50341796875,
0.4990556240081787,
0.4996318817138672,
0.4997934103012085,
0.49720633029937744,
0.4984622299671173,
0.4971908926963806,
0.4996547996997833,
0.49885162711143494,
0.49853622913360596,
0.4993768632411957,
0.49937203526496887,
0.4996309280395508,
0.4996669590473175,
0.4998275935649872,
0.5003016591072083,
0.5019415616989136,
0.5026867389678955,
0.5021476745605469,
0.49973469972610474,
0.4995351731777191,
0.4997482895851135,
0.5013495683670044,
0.501486599445343,
0.500169038772583,
0.5004439353942871,
0.49930539727211,
0.5011695623397827,
0.5021997094154358,
0.5070109963417053,
0.4996178448200226,
0.5020907521247864,
0.5024436712265015,
0.5016773343086243,
0.5045482516288757,
0.5040876865386963,
0.5034411549568176,
0.5025504231452942,
0.5021657943725586,
0.502610981464386,
0.4996422529220581,
0.5004652738571167,
0.49965184926986694,
0.48719483613967896,
0.4882241189479828,
0.5016627311706543,
0.4967329502105713,
0.5006956458091736,
0.5001470446586609,
0.502546489238739,
0.5026717185974121,
0.5027854442596436,
0.5015588402748108,
0.49722158908843994,
0.4964878261089325,
0.5009829998016357,
0.498322993516922,
0.5010243654251099,
0.49877384305000305,
0.49950021505355835,
0.4992385506629944,
0.5006088614463806,
0.4981401264667511,
0.500298798084259,
0.5020299553871155,
0.5023171305656433,
0.5025922060012817,
0.4974461793899536,
0.5002530813217163,
0.5016016364097595,
0.5012178421020508,
0.498186320066452,
0.5018169283866882,
0.49938327074050903,
0.5199859142303467,
0.5046569108963013,
0.4971076548099518,
0.4973582625389099,
0.49748632311820984,
0.5042060613632202,
0.5044822692871094,
0.5044389963150024,
0.5003931522369385,
0.499937504529953,
0.5001923441886902,
0.5006035566329956,
0.5013513565063477,
0.5029681921005249,
0.5007444620132446,
0.5026026368141174,
0.5014494061470032,
0.5005701184272766,
0.49801164865493774,
0.4988645613193512,
0.4994291365146637,
0.4999465048313141,
0.49888765811920166,
0.5039847493171692,
0.5028044581413269,
0.5041533708572388,
0.5071457624435425,
0.5035627484321594,
0.5011879205703735,
0.27819645404815674,
0.27866891026496887,
0.2783893346786499,
0.4923909902572632,
0.46986135840415955,
0.46511605381965637,
0.3703002631664276,
0.3694427013397217,
0.3697376251220703,
0.5120269060134888,
0.5135841369628906,
0.5127730369567871,
0.4984152615070343,
0.49835485219955444,
0.5006183385848999,
0.5018397569656372,
0.5049078464508057,
0.5047508478164673,
0.4998725652694702,
0.5001406669616699,
0.5006133913993835,
0.4996473789215088,
0.5005207657814026,
0.500308096408844,
0.5042368769645691,
0.5018472671508789,
0.5059038996696472,
0.4073773920536041,
0.46641409397125244,
0.40705761313438416,
0.5000689625740051,
0.50118488073349,
0.501803994178772,
0.499085932970047,
0.49989569187164307,
0.5005720257759094,
0.4991042912006378,
0.49834996461868286,
0.4992538094520569,
0.498940110206604,
0.5055358409881592,
0.49766916036605835,
0.5182417631149292,
0.488452672958374,
0.5053372979164124,
0.49994465708732605,
0.49869367480278015,
0.5002590417861938,
0.49949830770492554,
0.49927130341529846,
0.4985034167766571,
0.49884742498397827,
0.5000630021095276,
0.49771639704704285,
0.4990788698196411,
0.5043149590492249,
0.5004991292953491,
0.49974846839904785,
0.4998705983161926,
0.4996354281902313,
0.5233086347579956,
0.5048919916152954,
0.5200716257095337,
0.501682698726654,
0.5031076073646545,
0.5037926435470581,
0.5038768649101257,
0.505611002445221,
0.5042534470558167,
0.5007330179214478,
0.49949896335601807,
0.4983339011669159,
0.5009925961494446,
0.500275194644928,
0.5009390711784363,
0.5018028020858765,
0.5006496906280518,
0.5017224550247192,
0.5015744566917419,
0.5017526745796204,
0.5021160244941711,
0.5003833770751953,
0.500350832939148,
0.49982547760009766,
0.5016658306121826,
0.5022935271263123,
0.5018628239631653,
0.5001399517059326,
0.5013347864151001,
0.5011909604072571,
0.49847882986068726,
0.4993051588535309,
0.4996175169944763,
0.49980026483535767,
0.49864333868026733,
0.5005444884300232,
0.4956664741039276,
0.5019102692604065,
0.4979172646999359,
0.49798402190208435,
0.49960771203041077,
0.5002766847610474,
0.5081536769866943,
0.504501461982727,
0.5108461976051331,
0.5051500797271729,
0.5076544880867004,
0.5204787254333496,
0.49206414818763733,
0.5037489533424377,
0.49868348240852356,
0.2355576902627945,
0.2356065809726715,
0.23511098325252533,
0.500259280204773,
0.5012845993041992,
0.5006637573242188,
0.5017510652542114,
0.500835120677948,
0.4986235797405243,
0.505018949508667,
0.5048702359199524,
0.505578875541687,
0.49925920367240906,
0.500167191028595,
0.49971717596054077,
0.5032122135162354,
0.5026955008506775,
0.49986034631729126,
0.5013505816459656,
0.5041592717170715,
0.502718448638916,
0.5036671161651611,
0.5037294030189514,
0.5035555362701416,
0.4993791878223419,
0.49987858533859253,
0.4998302161693573,
0.5015885233879089,
0.5009291172027588,
0.5014345049858093,
0.5079432725906372,
0.5049604177474976,
0.5053533911705017,
0.5016552209854126,
0.5024722218513489,
0.5015197992324829,
0.5012655258178711,
0.5010697245597839,
0.5001093745231628,
0.5002081990242004,
0.5004696846008301,
0.49982669949531555,
0.4994266927242279,
0.5028033256530762,
0.5032446980476379,
0.5055631995201111,
0.5089074969291687,
0.5052967667579651,
0.5028168559074402,
0.5023524761199951,
0.5014626979827881,
0.5034757256507874,
0.5004289746284485,
0.5007418990135193,
0.5079226493835449,
0.5064875483512878,
0.5076013803482056,
0.5027967095375061,
0.5031786561012268,
0.5030374526977539,
0.508521318435669,
0.5081111192703247,
0.5054713487625122,
0.5014234185218811,
0.5014233589172363,
0.49948230385780334,
0.5188221335411072,
0.5008295178413391,
0.5012413263320923,
0.5002249479293823,
0.5003131628036499,
0.5002867579460144,
0.5008430480957031,
0.5011290311813354,
0.5005520582199097,
0.500511884689331,
0.5015271902084351,
0.4995979070663452,
0.4842030107975006,
0.4888615608215332,
0.4845004677772522,
0.4936767518520355,
0.49589845538139343,
0.4968489110469818,
0.5078551769256592,
0.5086590647697449,
0.5048800706863403,
0.50406414270401,
0.49928075075149536,
0.5003625750541687,
0.5017848014831543,
0.5189229249954224,
0.5038735270500183,
0.5045825242996216,
0.5098202228546143,
0.5070176720619202,
0.49605315923690796,
0.4971486032009125,
0.5007787942886353,
0.5017072558403015,
0.5011970400810242,
0.5030479431152344,
0.5027934908866882,
0.5036808252334595,
0.4968360364437103,
0.5040469765663147,
0.5022206902503967,
0.5096515417098999,
0.5043824911117554,
0.5040714144706726,
0.5043060779571533,
0.5006923079490662,
0.49846476316452026,
0.5004470348358154,
0.5049837231636047,
0.5036110281944275,
0.5030596852302551,
0.4982118308544159,
0.5012333393096924,
0.5001330971717834,
0.4997049868106842,
0.4999231696128845,
0.49986523389816284,
0.5049334764480591,
0.5041648745536804,
0.5041124820709229,
0.5035684108734131,
0.5004119277000427,
0.5048140287399292,
0.5001837015151978,
0.4992787837982178,
0.49768564105033875,
0.507669985294342,
0.5105788111686707,
0.5089437365531921,
0.5039477944374084,
0.5022582411766052,
0.5042136907577515,
0.49817514419555664,
0.508592963218689,
0.5008941888809204,
0.44206276535987854,
0.4437168538570404,
0.44318854808807373,
0.5041830539703369,
0.5022867321968079,
0.5060319900512695,
0.4994913637638092,
0.50017249584198,
0.5020331144332886,
0.5064359903335571,
0.49314361810684204,
0.49485448002815247,
0.5069650411605835,
0.5038386583328247,
0.5044161081314087,
0.5027592182159424,
0.5045888423919678,
0.5005211234092712,
0.5040276050567627,
0.5049864649772644,
0.505202054977417,
0.5015010237693787,
0.5025143027305603,
0.5026828646659851,
0.49612998962402344,
0.49778321385383606,
0.4957836866378784,
0.5143561959266663,
0.49974146485328674,
0.5070925354957581,
0.49652713537216187,
0.5015208125114441,
0.4980009198188782,
0.5105144381523132,
0.5131642818450928,
0.5091376900672913,
0.5017421841621399,
0.5024477243423462,
0.4986189901828766,
0.5075944066047668,
0.5033717155456543,
0.5015316009521484,
0.4993704557418823,
0.5016908645629883,
0.5002565979957581,
0.5047227740287781,
0.5032293200492859,
0.5034161806106567,
0.5036770701408386,
0.4993160367012024,
0.5007126331329346,
0.5023313760757446,
0.5023145079612732,
0.5023640394210815,
0.5061475038528442,
0.5052024722099304,
0.5061601400375366,
0.5007445216178894,
0.5021946430206299,
0.5014325976371765,
0.5027159452438354,
0.5006595253944397,
0.5012496709823608,
0.5023611783981323,
0.5014529824256897,
0.5004270672798157,
0.5023684501647949,
0.5013670325279236,
0.4995388090610504,
0.5012362003326416,
0.500850260257721,
0.5008846521377563,
0.5021237134933472,
0.501030683517456,
0.5016361474990845,
0.506416380405426,
0.5068535804748535,
0.5057557821273804,
0.5039985179901123,
0.5020614862442017,
0.500257670879364,
0.5002756714820862,
0.4977220892906189,
0.5006091594696045,
0.43745940923690796,
0.4077581465244293,
0.4053519368171692,
0.5032687783241272,
0.502895712852478,
0.5037598609924316,
0.5040551424026489,
0.4951910972595215,
0.5011709928512573,
0.49963995814323425,
0.5004476308822632,
0.5001348257064819,
0.39938241243362427,
0.40034350752830505,
0.4000280499458313,
0.48087620735168457,
0.4813370108604431,
0.4803813397884369,
0.5019484758377075,
0.5001928210258484,
0.5027226805686951,
0.4999104142189026,
0.5004981160163879,
0.5001547932624817,
0.5009893774986267,
0.5010690093040466,
0.4989389181137085,
0.5035240650177002,
0.4988476037979126,
0.5006241798400879,
0.5007290840148926,
0.5000448822975159,
0.5008657574653625,
0.5018539428710938,
0.49878251552581787,
0.5015383362770081,
0.5006456971168518,
0.49966728687286377,
0.5023677945137024,
0.4997034966945648,
0.4997830390930176,
0.5006301403045654,
0.5012157559394836,
0.4961499571800232,
0.5012690424919128,
0.5004507303237915,
0.5005264282226562,
0.5008752346038818,
0.5000213980674744,
0.5008606314659119,
0.5011395215988159,
0.5003611445426941,
0.5011079907417297,
0.4991888701915741,
0.49992337822914124,
0.5012452006340027,
0.5022249221801758,
0.4998299777507782,
0.5003123879432678,
0.5053354501724243,
0.5208922028541565,
0.5050783157348633,
0.5207609534263611,
0.49463436007499695,
0.4935159683227539,
0.493554949760437,
0.4988822638988495,
0.499745637178421,
0.5024524927139282,
0.49841147661209106,
0.5024174451828003,
0.5011166930198669,
0.500542938709259,
0.49886542558670044,
0.5028678178787231,
0.5018333792686462,
0.5013818740844727,
0.5012350082397461,
0.5013997554779053,
0.5016891360282898,
0.5020401477813721,
0.5010888576507568,
0.49972909688949585,
0.49901509284973145,
0.5082398056983948,
0.5062258243560791,
0.5023532509803772,
0.5062061548233032,
0.5053995251655579,
0.5034598112106323,
0.5003113746643066,
0.5002411603927612,
0.5001781582832336,
0.5006527304649353,
0.498649924993515,
0.500649631023407,
0.5006489157676697,
0.5007699728012085,
0.5000425577163696,
0.5057221055030823,
0.5027864575386047,
0.5029193758964539,
0.5014356374740601,
0.5028032660484314,
0.5017217397689819,
0.49795225262641907,
0.49835827946662903,
0.49949032068252563,
0.4995008111000061,
0.4994463622570038,
0.5004168748855591,
0.5027284026145935,
0.5032662749290466,
0.5030547976493835,
0.533958375453949,
0.4980399012565613,
0.49890485405921936,
0.5010877251625061,
0.5011864900588989,
0.5011339783668518,
0.4949474334716797,
0.5000326633453369,
0.5034968852996826,
0.5007457733154297,
0.5006121397018433,
0.503190279006958,
0.5070618987083435,
0.5051270127296448,
0.5005172491073608,
0.5010647177696228,
0.5039560198783875,
0.5037128329277039,
0.4987918436527252,
0.49975618720054626,
0.49937164783477783,
0.5019383430480957,
0.4996417760848999,
0.4997383654117584,
0.49907341599464417,
0.4982518255710602,
0.4970652461051941,
0.5025706887245178,
0.5028623342514038,
0.5013836026191711,
0.5072746276855469,
0.5009099841117859,
0.5201862454414368,
0.4882237911224365,
0.5010094046592712,
0.5024037957191467,
0.4998489320278168,
0.5016745328903198,
0.4983702600002289,
0.5022308826446533,
0.5010474324226379,
0.5009644031524658,
0.5064887404441833,
0.5055172443389893,
0.5042034387588501,
0.49966251850128174,
0.4940527081489563,
0.49394795298576355,
0.5030872225761414,
0.5012555122375488,
0.501176118850708,
0.5005190968513489,
0.5008738040924072,
0.5009239315986633,
0.49819737672805786,
0.49820613861083984,
0.49875983595848083,
0.514876663684845,
0.5121185779571533,
0.5166328549385071,
0.4994341731071472,
0.50213223695755,
0.501872718334198,
0.5018616318702698,
0.5026934742927551,
0.5031939744949341,
0.5025720596313477,
0.5009868741035461,
0.5015935897827148,
0.5007317066192627,
0.5023176074028015,
0.5000432729721069,
0.5125305652618408,
0.5055444240570068,
0.5115044713020325,
0.5144338607788086,
0.5125062465667725,
0.5123624801635742,
0.49957773089408875,
0.49949324131011963,
0.49994248151779175,
0.5040303468704224,
0.5038051009178162,
0.5019189119338989,
0.46203550696372986,
0.47100797295570374,
0.46453431248664856,
0.5012258291244507,
0.500784158706665,
0.5011463761329651,
0.4999781548976898,
0.4988826811313629,
0.5079778432846069,
0.501827597618103,
0.5016264915466309,
0.5008383989334106,
0.4993819296360016,
0.49937179684638977,
0.49781179428100586,
0.5079683661460876,
0.5085542798042297,
0.5052259564399719,
0.5183073878288269,
0.5168085098266602,
0.4974302053451538,
0.49854934215545654,
0.49868473410606384,
0.49897438287734985,
0.5013867616653442,
0.5007686614990234,
0.4997693598270416,
0.5066291093826294,
0.5057343244552612,
0.503917396068573,
0.5014853477478027,
0.50079745054245,
0.5004928112030029,
0.4768587648868561,
0.47687220573425293,
0.48154735565185547,
0.503122866153717,
0.5085811614990234,
0.5036104917526245,
0.5000232458114624,
0.4998321831226349,
0.5008386969566345,
0.5017136335372925,
0.5033923983573914,
0.5035961270332336,
0.5000640153884888,
0.49949321150779724,
0.4989066421985626,
0.49915650486946106,
0.4998423159122467,
0.4994902014732361,
0.5013976097106934,
0.5026435256004333,
0.5011765956878662,
0.504183828830719,
0.49762189388275146,
0.5009187459945679,
0.4945077896118164,
0.5040197372436523,
0.499714732170105,
0.5208457708358765,
0.5131959319114685,
0.5103714466094971,
0.5014894604682922,
0.5021999478340149,
0.4997304081916809,
0.5019921660423279,
0.5020192861557007,
0.5020343661308289,
0.5013508200645447,
0.5017462372779846,
0.5026276111602783,
0.4999312460422516,
0.5005260705947876,
0.4990251958370209,
0.5043284296989441,
0.5046857595443726,
0.5039535760879517,
0.5208460688591003,
0.5090281963348389,
0.5091184973716736,
0.5003681182861328,
0.49976518750190735,
0.49921920895576477,
0.49964669346809387,
0.4995255768299103,
0.49908772110939026,
0.4996289908885956,
0.500732421875,
0.5004409551620483,
0.5030120611190796,
0.5039452910423279,
0.5007646083831787
],
"eval_runtime": 47.0377,
"eval_samples_per_second": 15.945,
"eval_steps_per_second": 0.51
}