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

766 lines
21 KiB
JSON

{
"model_dir": "models/openllama-3b",
"distribution_id": "math_hard",
"timestamp": "2023-10-20 01:17:51",
"eval_loss": 0.697236180305481,
"eval_score": -0.2523743212223053,
"eval_brier_score": 0.2523743021061832,
"eval_average_probability": 0.49799789528052013,
"eval_accuracy": 0.6506666666666666,
"eval_probabilities": [
0.5118269324302673,
0.5117036700248718,
0.5116192102432251,
0.5023179054260254,
0.5004062652587891,
0.4979900121688843,
0.5030120611190796,
0.5039452910423279,
0.5007646083831787,
0.499487966299057,
0.4961891174316406,
0.4979303181171417,
0.5036739706993103,
0.50372314453125,
0.5054787993431091,
0.5023196339607239,
0.5038008093833923,
0.5050631761550903,
0.5008430480957031,
0.5011290311813354,
0.5005520582199097,
0.46878209710121155,
0.4687691628932953,
0.4692709743976593,
0.503454327583313,
0.5006722807884216,
0.5017990469932556,
0.5105144381523132,
0.5131642818450928,
0.5091376900672913,
0.5013976097106934,
0.5026435256004333,
0.5011765956878662,
0.5001668334007263,
0.49925515055656433,
0.4979747235774994,
0.5008518099784851,
0.5012384057044983,
0.5003740191459656,
0.49928775429725647,
0.5001110434532166,
0.5011179447174072,
0.501758873462677,
0.5030794739723206,
0.5014632344245911,
0.5017181634902954,
0.5011054873466492,
0.500623345375061,
0.4644926190376282,
0.4756001830101013,
0.45927587151527405,
0.5025123953819275,
0.502926766872406,
0.5042934417724609,
0.39938241243362427,
0.40034350752830505,
0.4000280499458313,
0.49897199869155884,
0.5008808970451355,
0.49774813652038574,
0.5026252865791321,
0.5036307573318481,
0.502453088760376,
0.509809672832489,
0.5090102553367615,
0.5055467486381531,
0.5019415616989136,
0.5026867389678955,
0.5021476745605469,
0.4988865852355957,
0.5002287030220032,
0.49982044100761414,
0.5116435885429382,
0.5109914541244507,
0.5087786912918091,
0.5030952095985413,
0.5040630102157593,
0.5035992860794067,
0.49625054001808167,
0.4995564818382263,
0.5072323083877563,
0.49892544746398926,
0.49895596504211426,
0.4985485076904297,
0.5120850205421448,
0.51576167345047,
0.5036633610725403,
0.5018223524093628,
0.5033509135246277,
0.5019826889038086,
0.5012945532798767,
0.5016359090805054,
0.5013529062271118,
0.501599133014679,
0.5020447373390198,
0.5024375319480896,
0.4885326623916626,
0.47909674048423767,
0.4793422222137451,
0.5025666952133179,
0.5030110478401184,
0.5036756992340088,
0.50084388256073,
0.5015429854393005,
0.5009251236915588,
0.5028867125511169,
0.5022519826889038,
0.5028859376907349,
0.4991511404514313,
0.4982491731643677,
0.4995523691177368,
0.5009356141090393,
0.4999960958957672,
0.4991222023963928,
0.5005190968513489,
0.5008738040924072,
0.5009239315986633,
0.500596821308136,
0.49940529465675354,
0.5006148219108582,
0.5042572021484375,
0.5060918927192688,
0.5053836107254028,
0.500751793384552,
0.5037107467651367,
0.5028291344642639,
0.5003493428230286,
0.4999171495437622,
0.49969080090522766,
0.4994063377380371,
0.4991651177406311,
0.49865493178367615,
0.5001052021980286,
0.5000398755073547,
0.4993040859699249,
0.499894380569458,
0.5004361867904663,
0.49990755319595337,
0.49713706970214844,
0.500124454498291,
0.5023578405380249,
0.5002656579017639,
0.49977242946624756,
0.5034225583076477,
0.504183828830719,
0.49762189388275146,
0.5009187459945679,
0.44206276535987854,
0.4437168538570404,
0.44318854808807373,
0.5050651431083679,
0.5035790801048279,
0.5041719079017639,
0.5011246204376221,
0.5021439790725708,
0.5018787980079651,
0.501844584941864,
0.5017201900482178,
0.5010454654693604,
0.49966052174568176,
0.49796998500823975,
0.4984380006790161,
0.5017521977424622,
0.5000317096710205,
0.5003252625465393,
0.5000232458114624,
0.4998321831226349,
0.5008386969566345,
0.5125305652618408,
0.5055444240570068,
0.5115044713020325,
0.49977970123291016,
0.4986732006072998,
0.4997980296611786,
0.49799567461013794,
0.5004239082336426,
0.49975427985191345,
0.5022830963134766,
0.5016414523124695,
0.5025763511657715,
0.5007308125495911,
0.4996309280395508,
0.4995768964290619,
0.5003312230110168,
0.49979549646377563,
0.5007071495056152,
0.5026471614837646,
0.503585934638977,
0.5029346942901611,
0.39883947372436523,
0.40109753608703613,
0.3986903727054596,
0.4965547025203705,
0.49578866362571716,
0.49455422163009644,
0.5028331875801086,
0.50162273645401,
0.502753496170044,
0.5047776103019714,
0.5044161677360535,
0.5050838589668274,
0.4981447756290436,
0.4987589418888092,
0.5007152557373047,
0.4572000503540039,
0.4584907293319702,
0.45888906717300415,
0.5043012499809265,
0.5007683038711548,
0.504422664642334,
0.4997047483921051,
0.4984018802642822,
0.49982789158821106,
0.5083137154579163,
0.5110461115837097,
0.510277271270752,
0.5014405846595764,
0.5007862448692322,
0.5012764930725098,
0.5008189678192139,
0.5011038184165955,
0.5012680888175964,
0.5019235610961914,
0.5010635256767273,
0.5023922324180603,
0.5017781257629395,
0.5021666288375854,
0.5020577907562256,
0.5035513639450073,
0.5031957626342773,
0.5039314031600952,
0.5002542734146118,
0.4988568127155304,
0.5004834532737732,
0.5002773404121399,
0.49931100010871887,
0.5001908540725708,
0.5004724264144897,
0.5027835965156555,
0.5034379959106445,
0.45227715373039246,
0.454122394323349,
0.4533941447734833,
0.5028168559074402,
0.5023524761199951,
0.5014626979827881,
0.5017344951629639,
0.5007197260856628,
0.502683699131012,
0.5054354071617126,
0.5058729648590088,
0.5042516589164734,
0.4995008111000061,
0.4994463622570038,
0.5004168748855591,
0.497423380613327,
0.49956223368644714,
0.49898791313171387,
0.5014851093292236,
0.5007235407829285,
0.5013412237167358,
0.5000227689743042,
0.5001505613327026,
0.5000898241996765,
0.499862939119339,
0.5037066340446472,
0.49983713030815125,
0.5008748769760132,
0.49818336963653564,
0.5069687366485596,
0.4971817433834076,
0.49652817845344543,
0.5000552535057068,
0.4954063594341278,
0.4897831678390503,
0.49395760893821716,
0.49980419874191284,
0.49916839599609375,
0.49486875534057617,
0.5003262758255005,
0.4978519380092621,
0.49753624200820923,
0.5048179030418396,
0.5056191086769104,
0.5069740414619446,
0.5059781670570374,
0.5042646527290344,
0.5079313516616821,
0.49925920367240906,
0.500167191028595,
0.49971717596054077,
0.501478374004364,
0.5019039511680603,
0.5022726655006409,
0.502903938293457,
0.49486231803894043,
0.489914208650589,
0.5003610849380493,
0.500436544418335,
0.5000671148300171,
0.5035677552223206,
0.5052205920219421,
0.5052878856658936,
0.5019816756248474,
0.5022100210189819,
0.5024012923240662,
0.4999144971370697,
0.5001264810562134,
0.4978044927120209,
0.4998208284378052,
0.4996722340583801,
0.5032349228858948,
0.5059970617294312,
0.5090477466583252,
0.5018458366394043,
0.5012685060501099,
0.5056227445602417,
0.49511489272117615,
0.5052827596664429,
0.5045791864395142,
0.5017173886299133,
0.5018156170845032,
0.4968791604042053,
0.5083858966827393,
0.4971615970134735,
0.500810980796814,
0.5002074837684631,
0.5001842975616455,
0.5006864666938782,
0.5009660124778748,
0.5032780170440674,
0.5037169456481934,
0.5041077733039856,
0.5008531808853149,
0.49927544593811035,
0.5010461807250977,
0.5002080202102661,
0.5002215504646301,
0.5006267428398132,
0.5083122253417969,
0.5081535577774048,
0.5053319931030273,
0.5035131573677063,
0.502204954624176,
0.5010372996330261,
0.4912964701652527,
0.4962308704853058,
0.49785545468330383,
0.5035989880561829,
0.5026911497116089,
0.5022835731506348,
0.49952489137649536,
0.5033833980560303,
0.5010479092597961,
0.5070618987083435,
0.5051270127296448,
0.5005172491073608,
0.49933743476867676,
0.4999030530452728,
0.5004624724388123,
0.5016360282897949,
0.5037422180175781,
0.5026264786720276,
0.5013505816459656,
0.5041592717170715,
0.502718448638916,
0.5058973431587219,
0.505913257598877,
0.5064799189567566,
0.49798402190208435,
0.49960771203041077,
0.5002766847610474,
0.4996388852596283,
0.49978238344192505,
0.4997383952140808,
0.4997040927410126,
0.502035915851593,
0.5002564191818237,
0.5032758116722107,
0.5031561255455017,
0.5044355392456055,
0.5034672021865845,
0.5046464204788208,
0.5036282539367676,
0.5056444406509399,
0.506179928779602,
0.5060855150222778,
0.499580055475235,
0.49996522068977356,
0.499955415725708,
0.49939706921577454,
0.5019042491912842,
0.500669002532959,
0.5008808970451355,
0.49722719192504883,
0.5013298988342285,
0.49915724992752075,
0.49901247024536133,
0.4997873604297638,
0.5059399008750916,
0.5002383589744568,
0.4939456284046173,
0.5018280148506165,
0.5043241381645203,
0.5060401558876038,
0.4077431559562683,
0.4296938180923462,
0.4453360140323639,
0.501190721988678,
0.5005092024803162,
0.5014989376068115,
0.49946045875549316,
0.4994412660598755,
0.5007282495498657,
0.5041948556900024,
0.505698561668396,
0.5064664483070374,
0.4982691705226898,
0.4976383447647095,
0.5044783353805542,
0.5018336176872253,
0.5022810697555542,
0.502670407295227,
0.4997049868106842,
0.4999231696128845,
0.49986523389816284,
0.5005083084106445,
0.5003774166107178,
0.5007076859474182,
0.501376211643219,
0.507193386554718,
0.5036787390708923,
0.4978429675102234,
0.4990524351596832,
0.49806198477745056,
0.5054458379745483,
0.5044532418251038,
0.5042263865470886,
0.5000266432762146,
0.5006366968154907,
0.5002830624580383,
0.5003980398178101,
0.5006653070449829,
0.5018952488899231,
0.51031494140625,
0.507949709892273,
0.5087388157844543,
0.5029681324958801,
0.5034680366516113,
0.5031079053878784,
0.49415311217308044,
0.49887189269065857,
0.4973743259906769,
0.5045160055160522,
0.5053192377090454,
0.5066564083099365,
0.5041276216506958,
0.5043938159942627,
0.504742443561554,
0.5043972134590149,
0.5078039765357971,
0.5061914920806885,
0.5003113746643066,
0.5002411603927612,
0.5001781582832336,
0.49830392003059387,
0.49911636114120483,
0.49823519587516785,
0.4989784061908722,
0.4989207684993744,
0.4980361759662628,
0.5009055137634277,
0.5005582571029663,
0.5014445781707764,
0.49754008650779724,
0.49551084637641907,
0.49885156750679016,
0.5041805505752563,
0.5033367872238159,
0.5040394067764282,
0.5006035566329956,
0.5013513565063477,
0.5029681921005249,
0.5032199025154114,
0.5052865147590637,
0.5031136870384216,
0.49949830770492554,
0.49927130341529846,
0.4985034167766571,
0.5023645162582397,
0.502378523349762,
0.50069260597229,
0.5011492967605591,
0.5004440546035767,
0.49919506907463074,
0.5188749432563782,
0.5099179148674011,
0.5331451296806335,
0.4983888566493988,
0.49931198358535767,
0.4997674226760864,
0.49993959069252014,
0.5001193284988403,
0.5003134608268738,
0.49992987513542175,
0.49971285462379456,
0.4996362030506134,
0.5029059052467346,
0.502920389175415,
0.5022585988044739,
0.5010925531387329,
0.4984000623226166,
0.5021820664405823,
0.49973469972610474,
0.4995351731777191,
0.4997482895851135,
0.5002910494804382,
0.5050249695777893,
0.5010432600975037,
0.5126259922981262,
0.5070919394493103,
0.5095546841621399,
0.5028166174888611,
0.5019388794898987,
0.502439022064209,
0.4999959170818329,
0.49920251965522766,
0.5007016062736511,
0.503699004650116,
0.5015842914581299,
0.5016142129898071,
0.5004971623420715,
0.5040141940116882,
0.5051127076148987,
0.5014700889587402,
0.5088062286376953,
0.5092113018035889,
0.5049742460250854,
0.5053015351295471,
0.5047686100006104,
0.5021789073944092,
0.5011422038078308,
0.5020480155944824,
0.4984416961669922,
0.49390608072280884,
0.5035723447799683,
0.49979037046432495,
0.49961456656455994,
0.49977734684944153,
0.4999224543571472,
0.499367356300354,
0.5001361966133118,
0.5033594369888306,
0.5027021169662476,
0.5011929869651794,
0.5010319948196411,
0.5034201145172119,
0.5007275342941284,
0.5019257664680481,
0.4998387396335602,
0.5015994906425476,
0.49712705612182617,
0.49765467643737793,
0.4980999529361725,
0.4909394383430481,
0.496622771024704,
0.49237746000289917,
0.5003517270088196,
0.50123530626297,
0.5003926157951355,
0.4980020225048065,
0.49433547258377075,
0.4928945302963257,
0.5055643320083618,
0.5082194805145264,
0.5065723657608032,
0.49995073676109314,
0.4997936189174652,
0.5000987648963928,
0.47563469409942627,
0.4741927683353424,
0.4754185974597931,
0.5005922913551331,
0.5003976225852966,
0.5007275938987732,
0.5032758116722107,
0.5041925311088562,
0.5033535361289978,
0.5009925961494446,
0.500275194644928,
0.5009390711784363,
0.43745940923690796,
0.4077581465244293,
0.4053519368171692,
0.5023294687271118,
0.5017364025115967,
0.5004358887672424,
0.4986271560192108,
0.49931326508522034,
0.4983643591403961,
0.4985273480415344,
0.5010501146316528,
0.5005672574043274,
0.5024938583374023,
0.5026940107345581,
0.5024402737617493,
0.30496901273727417,
0.30531010031700134,
0.3058073818683624,
0.5001399517059326,
0.5013347864151001,
0.5011909604072571,
0.4991615414619446,
0.4990450441837311,
0.5005619525909424,
0.50384920835495,
0.5046872496604919,
0.5047869682312012,
0.5000689625740051,
0.50118488073349,
0.501803994178772,
0.5000280141830444,
0.4998398721218109,
0.49965667724609375,
0.5041406750679016,
0.4997020661830902,
0.5017220377922058,
0.4067486822605133,
0.41388773918151855,
0.4115007817745209,
0.5041688680648804,
0.5031463503837585,
0.5039153695106506,
0.4995962381362915,
0.4996379017829895,
0.5003054738044739,
0.4982895851135254,
0.49917927384376526,
0.4989558458328247,
0.49734342098236084,
0.49770841002464294,
0.4986380934715271,
0.5022308826446533,
0.5010474324226379,
0.5009644031524658,
0.5062248706817627,
0.5066684484481812,
0.5066229104995728,
0.4996669590473175,
0.4998275935649872,
0.5003016591072083,
0.4990556240081787,
0.4996318817138672,
0.4997934103012085,
0.4970579743385315,
0.4992362856864929,
0.4991414546966553,
0.5059750080108643,
0.5061400532722473,
0.5089628100395203,
0.5026978850364685,
0.5010683536529541,
0.5021372437477112,
0.5019595623016357,
0.5018102526664734,
0.5018981099128723,
0.5008358955383301,
0.5009790062904358,
0.5007709264755249,
0.5009658336639404,
0.5010848045349121,
0.5040868520736694,
0.5003681182861328,
0.49976518750190735,
0.49921920895576477,
0.5019269585609436,
0.4994918704032898,
0.5015665292739868,
0.5005104541778564,
0.5005168318748474,
0.49981406331062317,
0.5093018412590027,
0.507337749004364,
0.5050452351570129,
0.5044658184051514,
0.5035539865493774,
0.5018183588981628,
0.5147806406021118,
0.503251314163208,
0.5366829037666321,
0.5032684803009033,
0.5031995177268982,
0.5038666725158691,
0.5018258094787598,
0.5013566017150879,
0.5014522671699524,
0.5000419020652771,
0.4997023940086365,
0.49956807494163513,
0.5015588402748108,
0.49722158908843994,
0.4964878261089325,
0.4995269775390625,
0.49960029125213623,
0.5005115866661072,
0.4993768632411957,
0.49937203526496887,
0.4996309280395508,
0.4924338757991791,
0.4916263222694397,
0.4912527799606323,
0.4981186091899872,
0.49833500385284424,
0.498732328414917,
0.5039032101631165,
0.5037981271743774,
0.5014682412147522,
0.4915093183517456,
0.4917883574962616,
0.49006131291389465,
0.49877384305000305,
0.49950021505355835,
0.4992385506629944,
0.4994252622127533,
0.49996837973594666,
0.4994683265686035,
0.49900761246681213,
0.5040145516395569,
0.5028517842292786,
0.49874237179756165,
0.49799028038978577,
0.49907252192497253,
0.5014593005180359,
0.5013299584388733,
0.5016478300094604,
0.5039477944374084,
0.5022582411766052,
0.5042136907577515,
0.5064887404441833,
0.5055172443389893,
0.5042034387588501,
0.5055631995201111,
0.5089074969291687,
0.5052967667579651,
0.500012218952179,
0.5014239549636841,
0.502220094203949,
0.5001025795936584,
0.49919596314430237,
0.49860522150993347
],
"eval_runtime": 49.8602,
"eval_samples_per_second": 15.042,
"eval_steps_per_second": 0.481,
"eval_rms_calibration_error": 0.0010106232115017488
}