Files
GENIES/results/evaluations/mms/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": "2023-10-13 23:46:54",
"eval_score": -0.16861424089731947,
"eval_brier_score": 0.16861424089731947,
"eval_average_probability": 0.7266872604766456,
"eval_accuracy": 0.756,
"eval_probabilities": [
0.8271909918256686,
0.3868681591773714,
0.31134551749212236,
0.9981319296976515,
0.9717917884920042,
0.8299830152439092,
0.961640411024032,
0.948022819658201,
0.9516580362784137,
0.9951605030440197,
0.9996164606725111,
0.9994409844431756,
0.8396769828842974,
0.711800417752201,
0.6464751467316352,
0.2792567137227292,
0.45702476052191177,
0.676552712125343,
0.4149899267692432,
0.7834591268814024,
0.9836686291789123,
0.9828151895031266,
0.9885051088056638,
0.9998215907371903,
0.3097095170837444,
0.7136531125320039,
0.1363711911118003,
0.14417075006506552,
0.10169528670552741,
0.11785773712841396,
0.9971771357215194,
0.03234434530426943,
0.9958107850257368,
0.9936352255650331,
0.6667470911406115,
0.8121193132443806,
0.8922638310659805,
0.9034885377789477,
0.7667231480943311,
0.929187026245596,
0.6133766986777873,
0.5232426261791813,
0.9559059377754616,
0.7873751509918231,
0.5382722524793975,
0.4432199021962273,
0.37843462017697016,
0.8796960665964307,
0.3452013228749791,
0.702385612709937,
0.9595703637341891,
0.006220146347455824,
0.9663704263048171,
0.1384809128669232,
0.8761252092636407,
0.21032707586953292,
0.05937763232653448,
0.9938536144923569,
0.9437099197047765,
0.9869569645918618,
0.9999503882648622,
0.9999103173870031,
0.9214313441148299,
0.4078596395176638,
0.9994250724823688,
0.9999229541444861,
0.9543422764667212,
0.8699977869836383,
0.6934346161730371,
0.837223407907235,
0.9014753342274415,
0.2952286342182935,
0.9945735646722339,
0.9937450199068543,
0.9936014588625011,
0.543638040686977,
0.9364180836936126,
0.7533946889373254,
0.4206382383546806,
0.9999704508523561,
0.853385052873389,
0.9934355936688458,
0.9986415720146801,
0.9999746434995614,
0.6670586594335937,
0.9148804007030942,
0.929387794309306,
0.3330416263084894,
0.33713678177549644,
0.3576440745120333,
0.9999718646368412,
0.9256852470847966,
0.999729686493395,
0.21181131258081087,
0.9884940926491917,
0.8971073675651385,
0.7406797370836046,
0.28960413774012383,
0.47092817505866125,
0.9999215555231246,
0.29458109650577835,
0.9936473075090525,
0.48533686627028977,
0.3395717981236434,
0.15475652691607578,
0.240949457574691,
0.5870828036924617,
0.7349697170999469,
0.8662786292407286,
0.9016298760192449,
0.8618873390318856,
0.9999833212164101,
0.9999084112150561,
0.9990627472892888,
0.5404682247763288,
0.888029863631916,
0.4624390711409675,
0.5122239330151978,
0.2545191563351694,
0.16757416888602064,
0.9967667180141557,
0.9986272031428572,
0.9987788239027938,
0.9971904526608932,
0.9997194944054524,
0.9995548501442626,
0.5412296382788432,
0.7392423161276755,
0.6847105978013683,
0.522959346106651,
0.9624567513198996,
0.2755992161695845,
0.7075045631086817,
0.9861424244383651,
0.970995851696698,
0.4099602682000121,
0.8559670838334703,
0.8218719886177404,
0.34607316878856986,
0.9925049640944532,
0.8153069590702109,
0.5827416695153418,
0.999970980421488,
0.9997475327321849,
0.187898943062069,
0.24703810480400273,
0.8384313772545219,
0.8500485286765527,
0.9658310218731286,
0.12287800327241738,
0.16762832087610147,
0.07766924331576427,
0.9977947869483469,
0.3222732455306605,
0.8828315922723345,
0.4864992383739555,
0.2962809996057428,
0.3199048777606125,
0.2780623049246894,
0.9338665990154925,
0.813294527035072,
0.9974951964519367,
0.6765244027207462,
0.32580179655933716,
0.9673120192389724,
0.8129309476624139,
0.40961568870538095,
0.13311297114363618,
0.7939168525472736,
0.261129131155159,
0.9786684611414793,
0.9190379699782074,
0.9715958915636875,
0.9109636877959472,
0.5273654273057459,
0.4123911102389817,
0.6941727381112761,
0.9610051576660736,
0.998151517215017,
0.8810589468615263,
0.8787998992268425,
0.3004190055428064,
0.3457324169217272,
0.999849534803479,
0.9999114842314495,
0.9998872043378314,
0.6392249364413095,
0.7948161192424106,
0.9317779374799563,
0.18786237694334382,
0.8447506715693713,
0.9976851063784308,
0.6690443286485783,
0.6019612133649183,
0.5565245709142398,
0.5694859956979593,
0.8903710440938557,
0.7933980240383816,
0.9716731102518957,
0.997394678171175,
0.8083642300815574,
0.6677642292260652,
0.9934230603853835,
0.9905994417794072,
0.9989545805861147,
0.9993881167050137,
0.998844312017254,
0.9991318759244828,
0.2897776086704391,
0.5766900969972668,
0.15257572861410507,
0.10922048841525356,
0.5611425073500458,
0.7650406775805974,
0.660225736024375,
0.32979161048244143,
0.992468490372779,
0.952760113726798,
0.9814194982420834,
0.998805063755531,
0.999937703665094,
0.9996887709951612,
0.9273504761570442,
0.9661064141842,
0.9404397974489804,
0.9430819165922352,
0.9982054215038051,
0.990840787935696,
0.2308772575413609,
0.07885596771554733,
0.4710810402286364,
0.6584534091342206,
0.8830245987298078,
0.4352926128998594,
0.9020425066277171,
0.99795854485927,
0.9360126777531066,
0.9476126894941179,
0.6464031489179408,
0.7350030260190301,
0.999999682892577,
0.9999982147408498,
0.9999782472812246,
0.02662928664600952,
0.570170653623549,
0.5106707781188257,
0.9981522311457138,
0.999960440958993,
0.9993371857890507,
0.8553563124424209,
0.020551962670930582,
0.4234087779726218,
0.9926901445388631,
0.5734548468193544,
0.9943802661732862,
0.9995594622288508,
0.9725631284397777,
0.9958630230142497,
0.35741666027038743,
0.9597040579692213,
0.9923131065394849,
0.998689997467403,
0.9944853086167037,
0.9983095259632181,
0.2619498270785825,
0.8680273500228289,
0.9386171051347146,
0.9995423583006513,
0.9991017523321555,
0.9962910201253897,
0.9990674423699466,
0.23158549421267793,
0.9999729405224341,
0.5235393619197694,
0.28042694420385433,
0.5260404512664828,
0.9971215836551419,
0.999498641515254,
0.9665612332868581,
0.40553507601946337,
0.2003919404141551,
0.206430459180244,
0.9131088690663375,
0.8949035030073224,
0.9809541993090917,
0.9998306600595498,
0.9950191527784349,
0.9959004526997747,
0.9983078270663995,
0.9999517666745772,
0.6492409608146064,
0.9982129351301205,
0.9778036316233993,
0.8550948054440514,
0.8372035283509413,
0.801833903729729,
0.5301764763229154,
0.9178998319838556,
0.9929610683872097,
0.7403001703092305,
0.9924514703016879,
0.0025530626356816033,
0.9991062468375392,
0.8027618421029058,
0.1241976994447897,
0.56921483883725,
0.24605522996002105,
0.500559289122976,
0.029578961663446382,
0.8733380363415133,
0.64773916475177,
0.2639929011038118,
0.98058285111707,
0.024762184901446993,
0.923604603008106,
0.9868260888467079,
0.9968035391674924,
0.9908748980303014,
0.974237777493049,
0.9997009775959574,
0.9993756950663731,
0.29219589250048505,
0.5321178617634927,
0.20876504525167575,
0.9991452478305867,
0.9998371194712022,
0.7228233441667328,
0.8016588939437582,
0.0037595738719550242,
0.17349453324340564,
0.9985963289667511,
0.9988765368864823,
0.9985717496332617,
0.38303778148253337,
0.2680485156368549,
0.27494092416955657,
0.9975103894298453,
0.9954305993658125,
0.8873772597520622,
0.9986276102593874,
0.9961817000803885,
0.9955385385307548,
0.019174928637904067,
0.11642708728483285,
0.3698888116629071,
0.9505334506654683,
0.9789784873465348,
0.9796879482710352,
0.9951741037085192,
0.7148073724032189,
0.9699311554194064,
0.33783608451876806,
0.6093124131330664,
0.5546787023272812,
0.5927195168995139,
0.0818874174500791,
0.44582239821201525,
0.9907536481485094,
0.9962041491811322,
0.8274410853423488,
0.18981616035884666,
0.3826772409384609,
0.8086852245074663,
0.9997993562711611,
0.7858401603462382,
0.9592074363855856,
0.9951829136266102,
0.7414704894828473,
0.9856753671339044,
0.06907725032292933,
0.163204963259102,
0.14660241761670245,
0.646558792989581,
0.5784694327304089,
0.6981913027379825,
0.9633783657171466,
0.9757907309436292,
0.8830892321439838,
0.7924242864507758,
0.5013457816793873,
0.8969214335158778,
0.1514713617306652,
0.9877814201741574,
0.2149956321538027,
0.5319725802934323,
0.7615459182875987,
0.870528276666408,
0.4299896397331616,
0.9480098827996905,
0.9412960467215067,
0.6705346386411583,
0.041020910196779004,
0.39892329133610127,
0.8332885038421732,
0.7814823474495707,
0.6963427573492156,
0.8774265902272729,
0.9316259023595427,
0.47969602190561844,
0.999782255889488,
0.9995912551706684,
0.9816355020282589,
0.9182487998396387,
0.9233709729989581,
0.9883382132033794,
0.99997164551145,
0.9999130330264671,
0.9998699932714377,
0.8239330194960853,
0.863856903155239,
0.8676940079590947,
0.5895642228319447,
0.4568659058648012,
0.9255036315492879,
0.9962332263977332,
0.2261164275560622,
0.9906251514394708,
0.7027103714281798,
0.2632918795643051,
0.15519617209947212,
0.6897411818557815,
0.9811325157713287,
0.967471815323032,
0.1368854026590402,
0.99128017462451,
0.6885945796629922,
0.9967950298547655,
0.9932020078945352,
0.9575170172603115,
0.8274907698704922,
0.9969964155562064,
0.8303937438114554,
0.9997862488046881,
0.9802200689453586,
0.9995373036841081,
0.9998900216296186,
0.9999498776112294,
0.999913916215737,
0.27206637530521527,
0.9511923961393642,
0.7824240676941282,
0.3003878709667283,
0.3200918334849425,
0.7384333149636546,
0.998536330466569,
0.9966848571827261,
0.5192277810486987,
0.999683285991309,
0.9999164008159455,
0.9999203152834962,
0.9981715822006825,
0.99908753820561,
0.8434613457041236,
0.7671033796518583,
0.550842675466223,
0.07505431237683263,
0.7305010772616196,
0.6135972295318157,
0.5340146018766336,
0.699102131529226,
0.37243826047155404,
0.9916358835258494,
0.285883083894546,
0.9957071092531665,
0.9732192887200054,
0.9993697357398932,
0.998750908233596,
0.9998971486143917,
0.954069400328351,
0.25179767601143405,
0.7807478752779863,
0.22797743340745205,
0.5202276007911936,
0.42229367939216145,
0.9984278648204135,
0.9800163312451058,
0.9998763594610994,
0.9964876671031729,
0.9182640273953819,
0.9976616478424348,
0.9994226602777193,
0.9999592725590036,
0.9995921477893928,
0.9433763265387155,
0.8005550852656212,
0.9182019433896729,
0.6536212420236944,
0.6065476461884938,
0.6514690423035833,
0.9344745059643258,
0.9680557842000076,
0.18701408158197386,
0.858766901229546,
0.9998444442775147,
0.9350650096150371,
0.941481012043951,
0.22989050597354088,
0.5738854681667196,
0.7106105353468041,
0.3721880462734593,
0.18447900166409562,
0.5951423490919174,
0.9600890548085926,
0.8311979982821908,
0.9829701082392949,
0.8927765368781518,
0.9952446334995703,
0.18037415766797102,
0.1774926493637633,
0.23179517307754172,
0.38990468489198626,
0.8313768222721629,
0.916471098343676,
0.7491126284717979,
0.09672425377013999,
0.9881178865487991,
0.9774821666988979,
0.9939099283567417,
0.9968894321215881,
0.9053963293296212,
0.8310830504680925,
0.8391456295885815,
0.22495106026011358,
0.9035495730547519,
0.829712798046959,
0.9999832535981918,
0.9999894769123776,
0.9999857527968871,
0.9999530907483345,
0.9961522008922765,
0.9993949506833854,
0.45066971289803814,
0.47071729745089474,
0.5822005659212839,
0.961246927411501,
0.9512564258400371,
0.9366179393162083,
0.19771028254021727,
0.9986931689621441,
0.9988675286571732,
0.09721459976200438,
0.7637139525780952,
0.14549166410933756,
0.9989956898541228,
0.999841286882901,
0.6902140749959702,
0.5897261899007915,
0.6079436304664352,
0.9319708019667496,
0.8786553909641666,
0.9378811809275572,
0.16961961715457896,
0.997212658710174,
0.07395705775374217,
0.9654410144082302,
0.09610231000364045,
0.8369158690853167,
0.12703325189572545,
0.05869234976357618,
0.4542202655763474,
0.6678673878502555,
0.9983197577211085,
0.9870021647415436,
0.9979446563394592,
0.4393151509708172,
0.34720830294788785,
0.9407432122179602,
0.9998920808823486,
0.9991120416675933,
0.9987661541659809,
0.6649755596294242,
0.9206125253757642,
0.8226778286958414,
0.9999536794125367,
0.9999086221515755,
0.999993465754195,
0.9974211303265585,
0.9858637389639221,
0.9995854574259595,
0.9994720483048439,
0.9692240406320649,
0.9996785580736087,
0.5607974519009908,
0.8365197208454656,
0.5598691319089801,
0.6783371578586095,
0.06189278835635284,
0.9844337598164703,
0.997796565284917,
0.9953089853921514,
0.9862161501912511,
0.9997193828083707,
0.9998219863114229,
0.9994244662269932,
0.9575092524577857,
0.9595996837703381,
0.9669321621202519,
0.6850758477515614,
0.9700297935147982,
0.9984370800681365,
0.9997639491126958,
0.1595593534904375,
0.9205221416865652,
0.4452931375829168,
0.2929532130236627,
0.21579697965690642,
0.6423641136011198,
0.22308428228228225,
0.17730877078771712,
0.7418314869569917,
0.7550606277903028,
0.98012658024104,
0.9034652527636255,
0.9674524662142272,
0.9691824346453924,
0.2756531973028838,
0.4717837660893966,
0.0731924665863598,
0.1380098406675554,
0.7606566893571337,
0.6508627903430144,
0.7770007841232447,
0.7221212732129254,
0.7342909071994699,
0.9998097235941588,
0.9991656991322091,
0.015245543460690372,
0.9398977407814626,
0.7756463012591239,
0.9796591896009644,
0.20263392759583465,
0.2707167616972862,
0.8859412895491624,
0.27220483709684407,
0.6661863145770416,
0.6961759673964824,
0.9999982469389885,
0.999993635808418,
0.9999345457212546,
0.12133517310570936,
0.23441421359240566,
0.15139960817122466,
0.9883753268396982,
0.9997713860082762,
0.9186769445276721,
0.6470134658682651,
0.047105459573223506,
0.0832997530902505,
0.93402103062433,
0.9556284263503394,
0.9526806525809018,
0.043271180297743905,
0.04846412004021414,
0.07337318859056463,
0.6176437642157677,
0.7650282738827958,
0.8858387450641471,
0.9243900378018327,
0.7172440227054311,
0.48456541078941595,
0.8362824901686488,
0.9050089767638052,
0.47257512436912386,
0.23058311401426937,
0.9973783014865227,
0.8883647257118794,
0.7406970239769891,
0.8840035265008235,
0.8398381116243518,
0.9461991210816338,
0.32637768746272267,
0.8524841303747195,
0.0733106167935141,
0.8333653342551146,
0.9217533564683777,
0.1614379563888939,
0.9420973900970155,
0.9482745178087773,
0.9839344890885848,
0.9799620869090179,
0.9982114433848629,
0.9856096883388331,
0.8371507737171098,
0.9402116884945501,
0.9993368337226494,
0.9995707354848712,
0.9960953123647385,
0.4114775711308332,
0.5836423123938146,
0.35449772650286815,
0.007855052572250078,
0.7258884165468096,
0.8748596162303408,
0.7647901535743382,
0.8085057073922837,
0.7069060902588691,
0.4627360008789661,
0.977238965962789,
0.12296371661272087,
0.257982968813537,
0.38679984479810614,
0.6544080462339684,
0.16152209438691661,
0.10230385751510017,
0.1125004324003912,
0.9767120340551098,
0.868469553346564,
0.5240598253302242,
0.9977917383441742,
0.8636159539678273,
0.740277894133397,
0.6859146691174186,
0.7437533454646711,
0.8267826067010255,
0.7954672439325506,
0.8732207139805912,
0.9444101289725866,
0.8140954360571842,
0.8840129090651916,
0.9421935448537497,
0.44159737018361134,
0.5193469480207286,
0.45781299767782124,
0.8120927615801491,
0.8111807066523897,
0.719385420222851,
0.8854916550499747,
0.6904655560751961,
0.998122129353188,
0.8670046911882856,
0.6591743813970637,
0.8144126078884113,
0.9802561661352952,
0.9982122225544151,
0.9582588553584158,
0.4766975014731776,
0.9998368523013856,
0.9702959686074838,
0.9510534676492647,
0.8917369515486644,
0.7890136201303444,
0.998200184713704,
0.9991147125676215,
0.9966433969962515,
0.9989506332850813,
0.9989414637961227,
0.9894245009370244,
0.8913101920691615,
0.960866284865079,
0.9719921629170835
]
}