Files
GENIES/results/evaluations/cra/llama-7b-code/counterfactual_python.json
T
2023-11-11 19:44:09 +00:00

762 lines
21 KiB
JSON

{
"model_dir": "models/llama-7b",
"distribution_id": "counterfactual_python",
"timestamp": "2023-10-16 02:39:45",
"eval_score": -0.22413425940205714,
"eval_brier_score": 0.22413425940205714,
"eval_average_probability": 0.5909104955933082,
"eval_accuracy": 0.6386666666666667,
"eval_probabilities": [
0.32091029398879994,
0.26502119767170096,
0.4880332935757866,
0.18918028717689966,
0.36443103340033167,
0.16584661958670577,
0.9338027821469045,
0.9341575982577945,
0.9390181875860292,
0.5924806023117403,
0.6641987530755336,
0.43507002260843924,
0.6851536084292659,
0.876853926251999,
0.48740524202998836,
0.6362804337569562,
0.7284779529826688,
0.777637056936951,
0.1368032609832388,
0.2271450412052427,
0.16158351359285666,
0.7831041991843808,
0.7521037761281348,
0.6115384762474477,
0.3009586281913479,
0.7431379633137007,
0.7368015700555193,
0.847532299249242,
0.8687331829060132,
0.8475430088581016,
0.7920292361641028,
0.5888648187996052,
0.6911953321397883,
0.771486155979221,
0.1388128146558757,
0.7068663704523095,
0.6034014850149961,
0.7201934646539876,
0.7423370486626502,
0.8432442027139422,
0.095870191672912,
0.8021209995749773,
0.8078245200333327,
0.819615746849307,
0.7298099009438794,
0.5028294548180352,
0.8777870696368187,
0.3405897710150222,
0.587560304881147,
0.6300510473303697,
0.3284109010367653,
0.4901468524462411,
0.3203485949075622,
0.6193070225539823,
0.2046423999118336,
0.27487094630453635,
0.16438049995362014,
0.7334809077144308,
0.3928434484400797,
0.49800833110498327,
0.8609019688790117,
0.3432099606314762,
0.2757045008256879,
0.11302613364310576,
0.24823944314631463,
0.4529777573517415,
0.5723074753228824,
0.32481376242822524,
0.1550149266571087,
0.36151248319397294,
0.533963677433386,
0.8782817899629024,
0.7816310740812971,
0.9154242594420006,
0.6497319521176879,
0.22382533265934043,
0.7885012656266479,
0.6248500637713331,
0.09398143422950478,
0.7536227639404508,
0.23373871005952618,
0.7038673598024405,
0.8313216333656072,
0.3055616743521512,
0.6782955431525574,
0.8769133283702333,
0.45875699210968324,
0.4073339837073172,
0.2875914298317699,
0.42214397286589506,
0.41516440062634513,
0.07813325163867157,
0.3052861830009699,
0.8124423354889786,
0.254549191364936,
0.9024386409412213,
0.7242268011156624,
0.9324576093619107,
0.8131970871068932,
0.18576770232760342,
0.33642258359014465,
0.3755908157030591,
0.7554707182367898,
0.5673086270786516,
0.6084943572318269,
0.9423970987985761,
0.9319807269635545,
0.9313609410521742,
0.9529227005757248,
0.9584522046748117,
0.9528669399423572,
0.5338863546507568,
0.39789144253653147,
0.5048223579091901,
0.319464528470488,
0.2014134645720373,
0.6278819619607701,
0.5139220111132463,
0.3642153442205288,
0.36062955311902045,
0.29324211467597633,
0.8614279947650281,
0.7264107376109443,
0.846687315008847,
0.9063138940341966,
0.739276343190144,
0.5927087557833477,
0.7673291912306743,
0.43738519109728335,
0.5027983567962112,
0.7687388838937607,
0.8427676299429929,
0.22542969864670676,
0.27337812153525265,
0.3791777162586631,
0.6607394154280024,
0.31915409431783925,
0.7235911631127974,
0.468105959883434,
0.15643983027281994,
0.7316230149940863,
0.8695242755811095,
0.5068783054442902,
0.6649393494510195,
0.3378973205311935,
0.3187483328467138,
0.4691580897526729,
0.6415460805781941,
0.6177821046437135,
0.7129733703068333,
0.6317831159671862,
0.5130631588559634,
0.7174472985403759,
0.6500948305434671,
0.73530942778322,
0.82660611846085,
0.8633458869137812,
0.8527215126907598,
0.843140843133588,
0.5007178619657695,
0.6950036845035346,
0.7213344622212244,
0.7200628845089467,
0.3150380198323297,
0.4465513982029954,
0.3564776450100354,
0.239054967093144,
0.21947816249940938,
0.1285251032494282,
0.1144420952286318,
0.6634341642122166,
0.8816767040303114,
0.8112955812475516,
0.8373738610554462,
0.40495206612623874,
0.5106617084784574,
0.6666739539296906,
0.8461535154554995,
0.23123353163829619,
0.8310107723573095,
0.6481105079724875,
0.6494155583091366,
0.6899471456599887,
0.5051582902597105,
0.22083495329911673,
0.2374893863939742,
0.3164171287255507,
0.7021742805541163,
0.43813361814495155,
0.45193929195066024,
0.376265274853292,
0.392184891819747,
0.8065655603599605,
0.8209865668520442,
0.8355312951351921,
0.4586799371344955,
0.177237337555862,
0.7130597813128486,
0.4193562512330392,
0.23220643683857156,
0.589009529569958,
0.89075060733974,
0.8856674066940782,
0.5811055209069974,
0.49059068163513453,
0.483301005843234,
0.4336877417826779,
0.5892076157145452,
0.674177743762684,
0.1661317999859404,
0.5974671397825215,
0.536913492608415,
0.548246382222112,
0.5367534693255503,
0.3862941143775006,
0.38078288215118117,
0.2925645830259199,
0.6445666227437612,
0.9318861195081893,
0.5633346059273063,
0.6927159302491602,
0.7481372419169181,
0.4409633653977314,
0.5039458574479146,
0.4952146301263756,
0.7802979547802729,
0.6334532534080527,
0.7802230815676089,
0.7408702904086788,
0.7604652640677205,
0.7546205509983355,
0.7234708831978456,
0.6290012711330958,
0.5787630126506339,
0.9476502127658326,
0.9505938170264376,
0.9510344500838283,
0.8986632895993714,
0.885453756846255,
0.8765625002516255,
0.7005002285030372,
0.7058471987231674,
0.8981256267332867,
0.4802406907589932,
0.8764597026744833,
0.42383972991390895,
0.30064838932088,
0.36487281643352854,
0.7664467966651504,
0.1947574413279145,
0.37767180990664895,
0.2267872163838851,
0.7236565012737306,
0.5647573036874598,
0.58953910604106,
0.6945059217523915,
0.4267732272074082,
0.6411915949504431,
0.4926254536254566,
0.5054037813401988,
0.5725980599817121,
0.8493679839170433,
0.889548535262129,
0.7321604266199855,
0.6269354322289151,
0.3743155652982404,
0.4031975169617057,
0.6659728424708569,
0.7362569581639542,
0.6918786873088779,
0.551469184103083,
0.6743335365226988,
0.7802890876953928,
0.29118488232360934,
0.6550150065897887,
0.7652527293322429,
0.31039015480753657,
0.24593810420477902,
0.3111636170083655,
0.6833692088771441,
0.7038131792370409,
0.7325030152255272,
0.5345996761866411,
0.5936378463655764,
0.7042781548942257,
0.6664339963799728,
0.41296505083617197,
0.17405546725934695,
0.6670779321813848,
0.7703104689685508,
0.6898255631619508,
0.40112434356198184,
0.5111983860330507,
0.8784752238872638,
0.8323287952072315,
0.8801214137756092,
0.8997690979545725,
0.9148259817056322,
0.8924051500761789,
0.8377442416201741,
0.6206338659482357,
0.5304471319654265,
0.527195697383809,
0.40287790169241466,
0.41623321470666164,
0.5404735551791577,
0.2714649406730493,
0.26686846532310926,
0.15774717388205906,
0.21024805285084414,
0.2072932939729391,
0.5941953269893827,
0.6888585550698344,
0.36104134161284407,
0.19697056293769732,
0.34672793810557057,
0.6568813142917376,
0.35756075371249385,
0.3248455803593089,
0.4943775030134569,
0.7140072700434797,
0.17717427754922177,
0.16334081003925274,
0.12533975088684965,
0.2703481486827798,
0.5781037183338706,
0.3391977126645864,
0.9003497256590228,
0.8532281132365357,
0.8710131205543146,
0.1471479632211231,
0.32420075013700295,
0.09572013577190819,
0.7630032392029888,
0.7661522178117972,
0.8505956535421605,
0.5370407748909536,
0.4651844941675035,
0.39504781283865814,
0.6042691735339768,
0.26018303609509774,
0.803873838320855,
0.5768393019082403,
0.510326217865612,
0.5469321881263451,
0.4151508090174416,
0.6360276482336631,
0.2718030149939846,
0.37070390453787216,
0.35624593127729076,
0.5967248115073254,
0.46587659396848097,
0.5324779086951588,
0.25149167847161663,
0.7903293193178962,
0.7156851006767896,
0.616676442463606,
0.4729187035628283,
0.8169238484329452,
0.7872146169064458,
0.3534075027239477,
0.3196214785348942,
0.6389821442679755,
0.7844535124027973,
0.8796949250909625,
0.7415834634069758,
0.4282780404042946,
0.8206799908315418,
0.46885018455614763,
0.26112262854667,
0.30319832512143596,
0.3161227882552988,
0.7249343644559829,
0.7620049245187046,
0.6501323597831747,
0.9488565131399547,
0.9483234064507811,
0.9474484512811794,
0.25986393082058934,
0.13663781558215626,
0.850702870557567,
0.3067066544754532,
0.38045374897619766,
0.14894900102364428,
0.7827450609148777,
0.7652243832157679,
0.8120714660380773,
0.4591245746746737,
0.6260215610711084,
0.37270478306723787,
0.5118506273543588,
0.6645234395176958,
0.5834689477752124,
0.3216144578738287,
0.4497086013653244,
0.33823341555581665,
0.20822678430279196,
0.2431594219990576,
0.12681230176057023,
0.30606787955891473,
0.39084344260473697,
0.2461577451254363,
0.9631889345311782,
0.9538965625395865,
0.9586726433759856,
0.6970962058185728,
0.7600978157223042,
0.8050714416299197,
0.8414432908118937,
0.8503128414607056,
0.8419840227328452,
0.1820189499631431,
0.8150885676415314,
0.5189596287939885,
0.8140623410092749,
0.8215764554628564,
0.7594022956099089,
0.2774486422540653,
0.8858133386115147,
0.6394026630034653,
0.8227674923869481,
0.7417985827865848,
0.5010262322223387,
0.8968788535554533,
0.9044980173044525,
0.7114252641598336,
0.8791330751184132,
0.8979776288406556,
0.4756676976471544,
0.36197670895190975,
0.6918694878965373,
0.8556630587262112,
0.67816523547217,
0.8578005179708503,
0.7457276290250081,
0.9003313675375072,
0.9030541119227006,
0.928320413893282,
0.5569907433340487,
0.5571126975097805,
0.8907859891559105,
0.5364547948792282,
0.2530734396354511,
0.4027101721042283,
0.7060701412812651,
0.8754312820606771,
0.5085412813699135,
0.8241963943386541,
0.908240520151147,
0.854611338550339,
0.8296200233933355,
0.6613086098890602,
0.23891612664956718,
0.24800370908037428,
0.4865648294265966,
0.27037495960788616,
0.9071287238925846,
0.9122466673080081,
0.824866564935449,
0.6680257284426732,
0.6237201278001069,
0.45424201686063226,
0.27149626536526283,
0.4445438980385079,
0.4140505431793443,
0.12117754574145068,
0.11317488468837311,
0.10295632269111636,
0.927562644404431,
0.8635750146346797,
0.8911770015976948,
0.6476929936110976,
0.5457157826934367,
0.3912492542637135,
0.4767625180363308,
0.5321687073069521,
0.5552057343688849,
0.6023260137159421,
0.4144712204187938,
0.11729453528384337,
0.745281315087765,
0.4332714919507364,
0.5861070053943285,
0.6177709597440295,
0.44209926220063533,
0.6248775351389966,
0.3339919127209172,
0.4076419149846937,
0.41188687778554045,
0.8585738993913106,
0.8385079123018064,
0.26017856223803254,
0.6748661034614768,
0.6895874222341818,
0.20957397623312424,
0.6666759311345466,
0.6602906769777019,
0.6940872271925588,
0.775047688635369,
0.8566038575922628,
0.7369877865137626,
0.8353055254230526,
0.8066899452109969,
0.6575303814893616,
0.6794217163270271,
0.7881584945948441,
0.48149786570521247,
0.29546533990277235,
0.21386195467157187,
0.2634131853891951,
0.6374612197334066,
0.36132200170130135,
0.4886087349230935,
0.26046705915705193,
0.20395926706241152,
0.6890058791475875,
0.8383917383667244,
0.636705642000689,
0.7190892923490031,
0.9414273178707949,
0.950771671775181,
0.9376591354973113,
0.7699365070589005,
0.3009441091214626,
0.40798922928234893,
0.7740395929465266,
0.575395310061117,
0.8321407160985197,
0.49206383909749724,
0.2406593864307463,
0.7485228642881958,
0.9256750046497906,
0.9200465975510393,
0.9506719834757859,
0.7203828840508993,
0.7639759865687981,
0.7819621185521518,
0.752488039273889,
0.7004090140589997,
0.1861076186004813,
0.7944831904430564,
0.5979068309199551,
0.734346490865512,
0.43210544248816557,
0.5872254930961659,
0.6601999999248457,
0.1567668750561434,
0.3957554991455603,
0.6081321298635626,
0.39017678701264635,
0.6018974145932352,
0.2804011561399825,
0.6109967063282606,
0.582532161382669,
0.6644412606554984,
0.43291236643099285,
0.3988632973807349,
0.6963595566493584,
0.8433087881408646,
0.8901940075387353,
0.8388750566223766,
0.6830937613087961,
0.7497499547907143,
0.8836076403485483,
0.7921344184669956,
0.765492095823406,
0.8309393206302111,
0.19742536388835996,
0.23744564004326463,
0.5002434241901449,
0.4779008518108412,
0.6407423009985465,
0.5124673321303223,
0.8506258121419767,
0.8870898589679616,
0.9131615196319631,
0.7864361299034757,
0.6553359055655432,
0.7181302602193311,
0.36220648495650365,
0.8891769502995376,
0.7546708590820327,
0.7365074638054134,
0.7515057221872439,
0.8891514314285573,
0.5057128361758749,
0.4169218033728396,
0.25647031155776534,
0.37057790796973156,
0.2481523494034746,
0.2001927164225152,
0.7062460149431473,
0.2573396791541417,
0.7346908698597185,
0.7170775881324083,
0.5818881523074008,
0.654735630314109,
0.6616014673960398,
0.4309394882659323,
0.46988270915498304,
0.49738014460946217,
0.2091827109700125,
0.9262417266610533,
0.294947840322181,
0.22935885818703977,
0.14560444302567044,
0.954868950186542,
0.9598773692772238,
0.9542769832684085,
0.5799291999626075,
0.32762943878658213,
0.7602644294527139,
0.1474905874152983,
0.18513039200682746,
0.40951286610392035,
0.7141601121322649,
0.48761265744780136,
0.5600583494264276,
0.3662499048771091,
0.43440681760825806,
0.6853887157361196,
0.6490593649592925,
0.5603086987617849,
0.5145351466185205,
0.5508006506659249,
0.4948919538919182,
0.7737066965565248,
0.9412482832300022,
0.8870098955504979,
0.9323027545463533,
0.641875305457739,
0.4876055270769539,
0.6172656199975164,
0.5491832227259689,
0.506313220326643,
0.4108847747142432,
0.5431706347441081,
0.6202922071286356,
0.7697838515738877,
0.9378816512237256,
0.9361390152215325,
0.9433224833449059,
0.6842879079269482,
0.7635437457895643,
0.8482574530023139,
0.7977514648019902,
0.7664576959161535,
0.9022812430423826,
0.7705141108489416,
0.8505160598248579,
0.7737445900666405,
0.22817824083927263,
0.17856470919109746,
0.12269433355742675,
0.8419365431102434,
0.8672970584327342,
0.9221913515934066,
0.9327494600265757,
0.2514659209140111,
0.22711672118674406,
0.6946389807276264,
0.8527515967979904,
0.8252022255221736,
0.47502502354124104,
0.7677297178211169,
0.5041583659294675,
0.5243812225609266,
0.8138308291196646,
0.881743691731764,
0.8225614102702936,
0.35931572445248994,
0.7692364364700377,
0.39737824008147904,
0.3590038054595821,
0.3746680134333951,
0.7213926279675502,
0.7636997414939809,
0.8164676940053246,
0.3313118043419649,
0.40821150847360493,
0.807025479467641,
0.28310123122524355,
0.6838359633869787,
0.4902483909308118,
0.8816775639420614,
0.8665558337605546,
0.6904266234781657,
0.7730547591969178,
0.7743527318367949,
0.665500499909706,
0.32934493512956386,
0.2753330123153993,
0.145548252114173,
0.693482578845283,
0.7647993778721004,
0.7655941075919315,
0.896036466736048,
0.7035124205750809,
0.8427914353737354,
0.3702488865240646,
0.7561128793934885,
0.8426471742162752,
0.37950580503851405,
0.17425698047924226,
0.26225167587249765,
0.8601450011524807,
0.240447081645935,
0.9047880338376687,
0.6873995908541075,
0.43668744394247483,
0.4687820328688061,
0.9382378887818493,
0.9376299631234004,
0.9338774090566669,
0.8283706985386549,
0.9116886889961101,
0.9072212039967645,
0.45856014656957733,
0.3796194511995054,
0.4702192342824828,
0.8141114900804672,
0.9093618927711293,
0.7605954246406122,
0.6556995415921245,
0.607636487392022,
0.5423404470632357,
0.7298424217414692,
0.23987616963800554,
0.5526968936937756,
0.9627852956785194,
0.9592842898528203,
0.9583776796915568,
0.8081272276095415,
0.8797203521063615,
0.7244961417111708,
0.9179214491942121,
0.47247678250135594,
0.9615913741345138,
0.712080004744672,
0.7014569384831455,
0.7168516612154405,
0.12280336309803241,
0.46955606260289734,
0.1690082524261627,
0.6717384527978056,
0.14237613999401788,
0.5640585635517243,
0.5918917678576142,
0.803705220451714,
0.5883251342004877
],
"eval_rms_calibration_error": 0.2692420890346802
}