Files
GENIES/results/evaluations/cra/llama-30b-counterfactual_python/counterfactual_python.json
T
2023-11-11 19:44:09 +00:00

761 lines
21 KiB
JSON

{
"model_dir": "models/llama-30b",
"distribution_id": "counterfactual_python",
"timestamp": "2023-10-16 03:05:33",
"eval_score": -0.16323448897336373,
"eval_brier_score": 0.16323448897336373,
"eval_average_probability": 0.702592302539051,
"eval_accuracy": 0.76,
"eval_probabilities": [
0.6710502163485684,
0.6601707870616113,
0.45269631269209964,
0.8220421219059303,
0.6577043825696585,
0.631402395024353,
0.921844841845161,
0.900110903919532,
0.9006678386196854,
0.7305761236358528,
0.704116885283646,
0.6393148147280443,
0.9488722472090444,
0.9634350069359872,
0.7267468873641235,
0.8051542058525117,
0.7324720396579696,
0.6892818000253025,
0.7719647966490472,
0.6177452359098294,
0.2629486958361489,
0.9865109119616137,
0.9153600464347713,
0.7947773567658332,
0.21338891035911234,
0.6867838278999219,
0.6016930667596533,
0.7939093024719565,
0.947134608389865,
0.9776860016372625,
0.896527043973451,
0.8937835929868615,
0.8577503627673675,
0.2548703381219517,
0.3674352525566027,
0.34800568261270937,
0.9648349626524136,
0.9230407468292606,
0.9270382375936261,
0.9426464073674138,
0.3016409503424894,
0.18080471511971974,
0.9529910008119025,
0.9276243492061118,
0.7879806468046047,
0.6814627330984868,
0.49616942479856585,
0.9589538116561107,
0.6508478303395933,
0.7319822483696994,
0.5354155768986013,
0.2380730591842113,
0.6163742939492148,
0.3965310919273761,
0.31858154227645735,
0.3765499244555238,
0.19160623859047032,
0.9315594939095178,
0.20626983318378833,
0.8005394515094011,
0.9926254728314452,
0.9583911421990062,
0.8625477816149572,
0.03116219042116586,
0.7581575026047709,
0.4303633473672722,
0.9953468865151899,
0.9892267571921305,
0.9485425353189756,
0.767350930942694,
0.8221534676780871,
0.9470349711909418,
0.5330328727242092,
0.7115273200357866,
0.6032844778782862,
0.30530486957921843,
0.3734887458302084,
0.584084528463571,
0.029429878600259474,
0.9935253243539531,
0.16416294083157335,
0.7855308501924947,
0.9899402379706151,
0.8854278665196114,
0.6050232808386765,
0.8297845290670542,
0.14678906782313017,
0.8636571328395669,
0.8844793536114295,
0.7502996263290516,
0.9966548731650604,
0.1431276228721814,
0.9983952632648081,
0.7090652786942652,
0.9153297054568448,
0.6554808545243198,
0.8802737884420143,
0.9691799335045844,
0.8993840140090579,
0.8505539431169933,
0.8585388795193661,
0.7577810610956183,
0.8496096874765104,
0.8979398179612258,
0.8660898454324563,
0.9994627216995932,
0.9993229793353401,
0.9996015034734035,
0.999529221672409,
0.9997334752932331,
0.9995925546719564,
0.9536966436104057,
0.8163445963777883,
0.7197898942841583,
0.4788453482934637,
0.30330962922735877,
0.9055980507509811,
0.9979268155153311,
0.9955539668276094,
0.9947013608078299,
0.8736796100522032,
0.9969830850034481,
0.70015374635214,
0.9246367005377131,
0.8178184662386158,
0.9653332689384506,
0.6588529295912056,
0.7484412341773685,
0.7758197536422108,
0.22877246371661566,
0.9088543322872493,
0.7315253709059446,
0.9503071778670037,
0.9426474591967697,
0.9815071146588977,
0.4595428423632651,
0.32501057769255043,
0.3946780006586531,
0.3292082783480491,
0.7688170400953775,
0.935616902924211,
0.8733379716309723,
0.9856579327453382,
0.7069114628122062,
0.7678265676082949,
0.22740477440578755,
0.14553003602749104,
0.8999051507604411,
0.9580766666973548,
0.8703553295913299,
0.8458670455216172,
0.8310537475563434,
0.6896343064103821,
0.998018393906226,
0.9914375238788331,
0.9984767663853413,
0.6202745050766779,
0.675287355265314,
0.5989680105871918,
0.8212874523819195,
0.4862614052166765,
0.9954798356538685,
0.9506556849326553,
0.8720311099521414,
0.9268695163199009,
0.7668079448154538,
0.31298513260774474,
0.6502489680106143,
0.6213300369887615,
0.1329951720679644,
0.7279158689141978,
0.8543003829143128,
0.7717180408130401,
0.8717645320189567,
0.873735957817309,
0.911660253116262,
0.6626012123542878,
0.6030128076507024,
0.9636017294468773,
0.5241206681664752,
0.3690673247240862,
0.907251071994553,
0.3589891889041353,
0.6769640414979657,
0.989271373077927,
0.5486509208518263,
0.6791944817122587,
0.8125363092622764,
0.43293272432831104,
0.9134835620507267,
0.21527996211092837,
0.8924839569804259,
0.5554142701787542,
0.7265740228461119,
0.5818502022191433,
0.6229870591312235,
0.8988499233310305,
0.7931695903473275,
0.3809583878970181,
0.9432251928210214,
0.8325909746460559,
0.7485589078715319,
0.6807830525799645,
0.836434127317611,
0.9515943522204028,
0.9922059246096603,
0.9776016969758924,
0.5562610376343409,
0.7891039439364491,
0.6450494621963,
0.5485986811780368,
0.6921199035742339,
0.36214583245355725,
0.7458250498921715,
0.882414268903119,
0.6189518356045798,
0.34932661182247726,
0.9594771532022575,
0.9913360622861177,
0.9972921160352022,
0.9992659541536919,
0.5930601126017598,
0.8391777183085078,
0.9256977002512861,
0.911114057495472,
0.9446739032922702,
0.8513402705720096,
0.8230837606165591,
0.44229218366192025,
0.9263206117363896,
0.6443940031702805,
0.5072111480125897,
0.21621658221495704,
0.22337786378237973,
0.6904276847737407,
0.7970095538576073,
0.7133979314947096,
0.9396909107774178,
0.9743578990345315,
0.9961039727348919,
0.9995207484691845,
0.9994944119259865,
0.9968357954169038,
0.35395626165734695,
0.9061663777067817,
0.5308983731891679,
0.6128462542124036,
0.9623395489313621,
0.8277809635170457,
0.8948077025221612,
0.7807344802290865,
0.6521059381060701,
0.4643255401089904,
0.6884345503287101,
0.6457656391682072,
0.8836586991630447,
0.2608624103705999,
0.9017434273088671,
0.8282346015932794,
0.8684684220817946,
0.9639561423825178,
0.9593123946801587,
0.7137694309519178,
0.8915266477613256,
0.8843050506927651,
0.29314676324017286,
0.4781980956038573,
0.8656787053797422,
0.8199045568213175,
0.7670574324041974,
0.9527420746609262,
0.46642889145260213,
0.7726168340731865,
0.2690587437815388,
0.5343060638300925,
0.4924063297255183,
0.9048729724720241,
0.7066796438722422,
0.2961046995066382,
0.2856229482082603,
0.3400589052691794,
0.2375659361825977,
0.8591045263319861,
0.7055902538624104,
0.7189414298115757,
0.9871533254680985,
0.8985030209096461,
0.9398781323425426,
0.7055192585197577,
0.8500817331596947,
0.8457892873542996,
0.9815187255677518,
0.7836678323042197,
0.6624875622361368,
0.9943317276698677,
0.9858745227817314,
0.9852412407363094,
0.9916123002560372,
0.9911457286995912,
0.9817303847655894,
0.9826559904478698,
0.015731763146285393,
0.9924314030515874,
0.2026433206996493,
0.7642122497110461,
0.35407268809930004,
0.553468724716669,
0.556603612478825,
0.6660540941750108,
0.5389835723180625,
0.4474281641439401,
0.631993357243982,
0.9959039712464235,
0.07026128463836918,
0.971633367342047,
0.6410478908865724,
0.8212667701899721,
0.6360904575835873,
0.6902443001554798,
0.9448835480999586,
0.7091850624536237,
0.5553285376100697,
0.5021651453289274,
0.4895593086273302,
0.9068674917045649,
0.8704494619303622,
0.37817777511623646,
0.9633343677384316,
0.9694086788002425,
0.9608170628412931,
0.043233461031072395,
0.7186405811626534,
0.450656550894998,
0.45770494956171764,
0.3237562987655557,
0.23650668966698618,
0.9671984395345249,
0.8738684957099172,
0.9274460345669031,
0.35299916217847144,
0.8463094321860092,
0.258518930736918,
0.6065188700788526,
0.4109634544554035,
0.34359295308696547,
0.6446964810642076,
0.5059288742328246,
0.32717133702768164,
0.8227567194572972,
0.8668608745390628,
0.9063884765157715,
0.17735251290487491,
0.1879885898126017,
0.20128540398993638,
0.7193497492304293,
0.9409004532108781,
0.5942709347365247,
0.9692912337844481,
0.9939078371060134,
0.3675564855144534,
0.38888949415914753,
0.1965012295889575,
0.4613417906802748,
0.9932439858395394,
0.7771679192357356,
0.9237565541937467,
0.478750741105053,
0.7389271012142391,
0.47551820820642654,
0.8840990141626912,
0.9911892350999544,
0.8357900557491404,
0.7246722107996348,
0.6612750427326908,
0.7916039028562559,
0.7919973589795862,
0.9551108892003923,
0.7585389635320507,
0.5547263948745649,
0.8053391558535408,
0.9285930753735597,
0.6221300832192781,
0.9753585671106032,
0.9371044329636594,
0.9975729171124188,
0.9955002739594186,
0.9938384981365378,
0.5608390502693588,
0.9014331682244954,
0.976574770388111,
0.2856353376267291,
0.8012244514838581,
0.2272445232176754,
0.27451668357850234,
0.3501519541630873,
0.5381203752768168,
0.6875465735372548,
0.5293736975147532,
0.5053680734843816,
0.9606919662992848,
0.9628204206450669,
0.11456313120577943,
0.9958042948750556,
0.9954055494347663,
0.9924925403042703,
0.9986283086595722,
0.999283518205286,
0.9986297794106676,
0.9434359275544029,
0.8781323855389263,
0.9148955239220297,
0.3581264020039202,
0.9258868590896813,
0.3769809448363437,
0.8817481340426682,
0.3458074455763548,
0.7686970617101618,
0.5407506307448008,
0.6744073217446163,
0.39996700354211,
0.3197482094556275,
0.27201475895050214,
0.6098691663479868,
0.9983229292593861,
0.9994653313074836,
0.9974680941825717,
0.9056583280908439,
0.9658774239173195,
0.3373112557876988,
0.9333336616385695,
0.9685169201222625,
0.9246538402221973,
0.9066062145573626,
0.6692086102168822,
0.8650686278438459,
0.5088133651879179,
0.4225330977285051,
0.875910873409075,
0.34268145181765824,
0.2905526710497419,
0.7786809857685639,
0.27233736047460266,
0.8090726517417828,
0.6865096399848538,
0.14407077601616747,
0.5368630909790388,
0.3627941495252124,
0.7589621694833059,
0.9990729611254844,
0.9990533250178362,
0.7435917866125321,
0.9537314881900465,
0.807966194562908,
0.690383423754581,
0.67079859910665,
0.8640657180939991,
0.9240042191937916,
0.9763842186376124,
0.6510675049582852,
0.7354771433927446,
0.6420366004608524,
0.932715679863626,
0.31408557566954054,
0.2451371807669006,
0.5647447805149394,
0.7259763570154197,
0.7470913304778304,
0.8437959088468061,
0.994728979223619,
0.9908125729619012,
0.9987821183506833,
0.07370446941332633,
0.03457577288212299,
0.05538837884021697,
0.9934007013063515,
0.8772087670867217,
0.9960784830544963,
0.7363799923454076,
0.34419681133180535,
0.966857255493569,
0.7459079745307793,
0.9863152965709391,
0.831407463876675,
0.15319730655291708,
0.24090356391613277,
0.23449635486355164,
0.9957972116228189,
0.9946502415833972,
0.995465735982993,
0.936405502321048,
0.9829904330651115,
0.8651490232618279,
0.6963178233851033,
0.7140502115223704,
0.9457999688695538,
0.9299478355532355,
0.7698445556669749,
0.919065867278144,
0.07232789690370545,
0.12071017196482636,
0.09040334039664275,
0.80820305669986,
0.8816933349317563,
0.24317195619152143,
0.986747877128993,
0.2785752889001063,
0.8752416696181686,
0.3595418220720884,
0.29742971748306946,
0.32108476981196055,
0.5870672396792365,
0.7402151781247478,
0.33031835933059317,
0.17525854791727224,
0.3591326874456337,
0.8107600411701829,
0.8568678892336982,
0.9177986610144553,
0.8518159882696565,
0.984006443799948,
0.9814353699250901,
0.9868948312996861,
0.2024286983320622,
0.3144242737741213,
0.6214483463995901,
0.9986853358954131,
0.9993802271893177,
0.9989768147235252,
0.9884011091147968,
0.9947304320711113,
0.9962180806012141,
0.9909588222638778,
0.9126793689922704,
0.9940605215931283,
0.9986508556507488,
0.9981142986762197,
0.9985440126381492,
0.9322353349418382,
0.9609774069223146,
0.9545556835446197,
0.9993960644414052,
0.9993103783631255,
0.9992513963746413,
0.9762376675470504,
0.9589351166727691,
0.8822895012483946,
0.17779326961326858,
0.9544921230808767,
0.9013095682890591,
0.41397275462956173,
0.9328100513113506,
0.14795148267660052,
0.6525974367656356,
0.4579086086925551,
0.7129692740275381,
0.5365785526080936,
0.3289972121897655,
0.50860344377719,
0.5883123613078731,
0.603917750069987,
0.9925968004563711,
0.8648140968192355,
0.6872774352370201,
0.847358905991283,
0.9748446304725101,
0.9786091303704793,
0.97950679642367,
0.6484467009919328,
0.8201259526184974,
0.8554846820998065,
0.6328357419663752,
0.6989841126919624,
0.7845812647170547,
0.9982182225844441,
0.9978887263700739,
0.9787598633084087,
0.20124147866943187,
0.38451846557746105,
0.7367705934321384,
0.9785679781458169,
0.7574012173887338,
0.8732549373252565,
0.9966708376729239,
0.9975592993603587,
0.9980799994720586,
0.10270460916170121,
0.15146859236046717,
0.06408811988278085,
0.7597500882462613,
0.5578109299373059,
0.6793494906935227,
0.9941640471963746,
0.9966881501278974,
0.9276730428608316,
0.37617536346929636,
0.5442754540581054,
0.3980450294735206,
0.519623658791246,
0.941798304923259,
0.904013028931919,
0.07747716402978946,
0.020862715074031035,
0.49899337043976494,
0.29431143527460524,
0.32179144465409865,
0.33263024362131755,
0.9545178817018315,
0.9585969627903017,
0.8611160114384516,
0.5122936069770732,
0.28754236688429724,
0.6853963163583625,
0.6398780831297148,
0.8385971618469259,
0.7455605116298122,
0.5318377503796653,
0.6444082735891723,
0.5096491355234746,
0.273296555439,
0.4872382540769524,
0.255103251449418,
0.6239660176750609,
0.6571679112031877,
0.6600761250528213,
0.6792935279375243,
0.260893030958548,
0.015505955704723018,
0.9995794510217102,
0.9896186149637815,
0.9995579079346525,
0.9352143395624674,
0.3074831228663536,
0.7283938570357075,
0.3691677522980604,
0.9987862512020749,
0.09911987920100714,
0.9988973288288799,
0.999368457241488,
0.999256475485583,
0.8614438595090713,
0.9941604238632951,
0.9897254572910434,
0.3988841116302216,
0.9205481829187597,
0.5228120660436566,
0.8261032464247762,
0.2757136100021318,
0.4105704233347134,
0.8188186413128985,
0.8186351772989423,
0.7963223071964873,
0.8541453802854553,
0.7649016793757352,
0.7732646875269811,
0.9963850082077567,
0.9921252363655664,
0.9967069803027068,
0.6802939509868583,
0.20675762779162202,
0.5741558495614859,
0.8035897074389059,
0.2985125980029629,
0.3097760068844867,
0.8450301261134703,
0.9045249045764975,
0.18716790937305783,
0.9784080870621013,
0.9427218209690111,
0.9084591068230767,
0.9979261035304459,
0.8829698842192589,
0.9929786843473268,
0.43457968523489354,
0.8430087700959024,
0.5184576808752341,
0.9979959511060965,
0.9971892315986012,
0.9972232691494323,
0.7939439452906947,
0.08028239792745231,
0.31617053396446715,
0.9289788791046844,
0.8811535910148939,
0.8227180067707612,
0.9982012760531189,
0.9980662863737472,
0.9845344197965993,
0.1805988816639007,
0.34112799777061353,
0.2799624152338574,
0.1744205127684989,
0.3129442918006772,
0.19427830214291986,
0.4684750911859019,
0.6279073094633436,
0.619386683986811,
0.523602625382102,
0.765831870150579,
0.9694065316225168,
0.567369207117786,
0.7028509723916277,
0.5297592337304444,
0.18707673525141943,
0.28135485545741623,
0.4734669017978595,
0.6281357178503196,
0.9328409289329755,
0.8911280683357391,
0.5267225010115311,
0.10307522976060202,
0.9517520951403465,
0.9872612405979041,
0.9765205545862593,
0.9935160387179035,
0.9051174676945299,
0.9316817824774701,
0.8915595407695298,
0.675924060056998,
0.45727255592348337,
0.7605026425261122,
0.3367358756813845,
0.2006215474201879,
0.17741316987296019,
0.5915404809556786,
0.7752921022078009,
0.900809892383981,
0.36893174736611334,
0.5743172427236612,
0.7098451164015951,
0.9994709984702312,
0.9994501278392641,
0.9989620997012604,
0.7494466451811835,
0.9176418930425017,
0.4605311495058454,
0.945743754962162,
0.8753465239126945,
0.9510279482842628,
0.7528518467941349,
0.6268214073992748,
0.5257195114506544,
0.8260327834943744,
0.8456810222211808,
0.688748870552637,
0.048712862502248266,
0.44436449209210793,
0.026119140302834687,
0.6813924324835563,
0.8981806951121273,
0.9735218981455314
]
}