{ "model_dir": "models/llama-7b", "distribution_id": "counterfactual_python", "timestamp": "2023-10-14 00:01:10", "eval_score": -0.1741718582977794, "eval_brier_score": 0.1741718582977794, "eval_average_probability": 0.6932057476608959, "eval_accuracy": 0.736, "eval_probabilities": [ 0.7002755494508828, 0.5651353570053743, 0.4680493024798681, 0.8670978878996684, 0.11231297314582613, 0.6666897697145636, 0.9669580538487665, 0.9354411208828165, 0.9686260159426312, 0.8979633340913015, 0.926314811127332, 0.8927195713519366, 0.708897090739126, 0.28895958292537766, 0.2775257355270395, 0.9239324248305024, 0.9649277432846113, 0.1971218210155258, 0.2473766479202403, 0.8760372118198565, 0.8251655745489265, 0.9741964927235814, 0.9802196067515676, 0.9872397255780967, 0.8016114070580832, 0.7101000813889908, 0.3822777848532373, 0.11803232908003924, 0.06100269197449833, 0.11464975462142146, 0.9844155345481266, 0.12497043962241236, 0.9316604350502944, 0.9687551461386713, 0.7758442727641239, 0.2549401881173178, 0.4790931883622605, 0.5424199075799441, 0.5235697459567571, 0.7061069120639023, 0.671604821930911, 0.269926594862498, 0.28152345554022606, 0.19846307812871844, 0.15020234121715315, 0.7119139053899275, 0.423160910302295, 0.6672090205745005, 0.36569792664818157, 0.8413041145754476, 0.981291926618221, 0.32589555354532906, 0.5743608350720004, 0.6396467107449486, 0.26698804752666055, 0.37536646639566273, 0.14826641529745233, 0.9270836853152662, 0.9380304190514328, 0.7048508860831431, 0.9950147646045686, 0.9715399378700159, 0.5242978596350476, 0.10768610006515988, 0.2435679054628328, 0.9231883499785795, 0.8824851544685592, 0.7376607253160014, 0.36894710667398367, 0.9359293914040822, 0.9021545863104021, 0.2695264990492969, 0.8010109751131737, 0.9831094501032513, 0.7885850593407764, 0.5379063229445218, 0.2784370547457639, 0.1851295730732908, 0.3742387051188156, 0.9907947875540621, 0.3830821080853374, 0.7757514349022266, 0.8475304292801313, 0.9799319361290018, 0.8958892745330038, 0.4203421948681591, 0.9201283471256158, 0.6200959510712934, 0.5823133655773062, 0.7724862021632855, 0.9900772926944792, 0.5772789442364427, 0.9480787078574834, 0.8115204600034027, 0.3249089450256021, 0.934107010313393, 0.9798139022965601, 0.9608920028130085, 0.9631143590939183, 0.9757284400505281, 0.41289960389279123, 0.9158084049121868, 0.8177840146998419, 0.47813534971569227, 0.7499251580170021, 0.9890814921392369, 0.9814647613589638, 0.9873363044756481, 0.6274443102370129, 0.6692570786992342, 0.6251808885486166, 0.9960912041389594, 0.9828716919868716, 0.9565304404155536, 0.9481730408105211, 0.8245253421425809, 0.5307421770583756, 0.7727802282339173, 0.8994879353681587, 0.6855398814979691, 0.964179625618933, 0.9837042750860981, 0.9758358379444547, 0.9639375466510218, 0.9835816425081693, 0.9947349457030615, 0.8738845458011693, 0.2630248544282775, 0.49042432114829226, 0.23052943817402452, 0.4638782418984954, 0.5256454470277114, 0.32701546281607846, 0.40584670654883637, 0.6600070039465946, 0.4059611166053672, 0.8999091311262386, 0.4907318586918762, 0.9045033950466531, 0.8132720083749092, 0.14115233973709168, 0.6308499723682789, 0.9949858151235799, 0.9851290708647377, 0.27236301801046026, 0.5391701290329051, 0.34070922055283265, 0.976655548779613, 0.31761222157735525, 0.24284035690073935, 0.7006965237437965, 0.22779563141206852, 0.955582328322826, 0.5360102076220458, 0.473484344365357, 0.4960750662561044, 0.23343402476376496, 0.21485871114614385, 0.24449946971138525, 0.14590114331903795, 0.5663009739357744, 0.4495837284107455, 0.7669793038500461, 0.7984148545182737, 0.9054549224367789, 0.8872216686599599, 0.7119744557713882, 0.5516966777303671, 0.33645443094214544, 0.36323196473896907, 0.9307917513325731, 0.7354884359961364, 0.7185388506704067, 0.8852538932511926, 0.6112007852478141, 0.7924700479346962, 0.4755693185847448, 0.8062011866332339, 0.98789250993949, 0.7221719324819712, 0.8740073678631499, 0.3564320779113565, 0.9228494524514022, 0.9853245493312502, 0.9694501434117074, 0.9973090818783165, 0.7950221610332707, 0.7297340940961335, 0.5993051267583294, 0.3882520768014076, 0.8152297611819531, 0.9954839203131746, 0.962824857331114, 0.9409321486024967, 0.9742785777639986, 0.17991514123080576, 0.9887518404372874, 0.37100741582562563, 0.38996632999548203, 0.9776454643489758, 0.39722223026085557, 0.6571422004149754, 0.9866412903013709, 0.9441939019199626, 0.9321188571092405, 0.9414167286110949, 0.874809388239011, 0.986096333046412, 0.9198432172202342, 0.15248356297993085, 0.3397671661055153, 0.4943206657048409, 0.6197606962352504, 0.5950551054240445, 0.10209490958071754, 0.09992020920219156, 0.9811136654654927, 0.3834507584919793, 0.9939614888053515, 0.9855960587672424, 0.9988310648649493, 0.9943414908312453, 0.7725574837314465, 0.9183802068283202, 0.843332376759955, 0.8837351545915085, 0.9738230199110262, 0.8304410361024156, 0.9502786794361738, 0.8180163694275192, 0.855701557363995, 0.2726210865088722, 0.4528790457865923, 0.3746290118044097, 0.9787920708274624, 0.9914212329003339, 0.9758540585662221, 0.9446087509465361, 0.952400627202449, 0.9687910529362938, 0.9991198634850662, 0.9990004228825908, 0.9874655071550109, 0.6634190408157515, 0.8828617615707209, 0.07712779632822993, 0.9858879491300443, 0.9802408364233254, 0.9383288803223644, 0.9593516246848454, 0.15507335874395659, 0.18131362347088567, 0.8105325058247551, 0.8623911070159063, 0.5891507086792241, 0.743639647480704, 0.9164162161160366, 0.5878341987632298, 0.9120584896530685, 0.4102137239343736, 0.8648555461875848, 0.9666963097920533, 0.9697938702911227, 0.8925256387036903, 0.9400090691280725, 0.5697477445502784, 0.8615583710379091, 0.9090163620448073, 0.958486582405349, 0.7836312987355163, 0.9913490311438872, 0.08158883786023396, 0.9960505834800041, 0.5970650850203174, 0.7048075310439548, 0.29306185317149847, 0.9725705617409717, 0.9568374007504292, 0.9709761448211442, 0.5306453483594386, 0.3394466570649324, 0.080526592817419, 0.18691719472600293, 0.3201264413379875, 0.5029361453327197, 0.894874783835395, 0.655263707778754, 0.7816062780922957, 0.9249626532749841, 0.9933810619091374, 0.37730620018255967, 0.8847932426292465, 0.928277179738713, 0.6330465291947999, 0.7651397366231711, 0.766929034442933, 0.9188006666779501, 0.8721904573851609, 0.7926001251276923, 0.6640368473875409, 0.6420468905901718, 0.10238745726949568, 0.8564723966473264, 0.918114756532904, 0.9353536170759031, 0.6156505420920637, 0.6751299796788123, 0.09073461329025144, 0.38922052191066325, 0.5653846198572566, 0.5872501425487964, 0.9873192692297256, 0.9824529404732584, 0.23667266743515558, 0.9528196739484505, 0.9841763414441514, 0.9899193617271483, 0.9355990248813355, 0.8744585984792195, 0.967424132093656, 0.8991692070845686, 0.9003262038887997, 0.8747054311959866, 0.7897042692969528, 0.5649449553771927, 0.9742097315936163, 0.11517233752182054, 0.8177242325951533, 0.17101770107368897, 0.5903528038456566, 0.4747706702005993, 0.9742317835181789, 0.9432188887046726, 0.5596207157909736, 0.3223652581899798, 0.410662181447798, 0.9822752407714925, 0.9915047195191908, 0.45143191160755675, 0.9698047987363938, 0.9006484196967643, 0.9536644756364887, 0.1775277984172361, 0.11774370904338628, 0.08402290715310583, 0.43839497007285205, 0.39872590938352337, 0.6041074579870681, 0.8683110568935907, 0.13646145286982184, 0.6088753863010999, 0.8702448664378746, 0.9122024432066929, 0.7677322551099092, 0.29500690796263235, 0.8216871137834425, 0.6125676222686145, 0.6725263755474673, 0.9465978285275267, 0.7537094935366262, 0.4200439912707071, 0.2442305670463205, 0.5336613963196297, 0.9914256663044564, 0.9477292492196631, 0.8283782500472869, 0.8759022106985251, 0.7095750818744571, 0.4367031618722645, 0.34975168658425726, 0.39734885284854926, 0.08884599645301856, 0.7743275870161959, 0.8478328468924804, 0.8712847253539925, 0.7777558040394185, 0.8394875427950248, 0.5986738946929829, 0.8935676662693073, 0.5920792299520841, 0.9685086929752538, 0.0456914221695226, 0.38351240241099727, 0.0343443971426793, 0.9106287749215339, 0.9179779226266412, 0.8891024368462049, 0.10424186457437667, 0.17336905167153338, 0.31499260827956826, 0.2252118681003894, 0.8392253218013473, 0.32168379695921034, 0.7360482696786922, 0.9116615205016295, 0.9057718553842538, 0.9553044006118915, 0.3530276495699104, 0.4312396000047023, 0.524429336512451, 0.9378620282962313, 0.9798210529697503, 0.7009378699244545, 0.4089715810812261, 0.650098811551059, 0.9960916498916954, 0.9947557323816146, 0.9961762339500897, 0.15207340233974942, 0.1449865754950932, 0.13310803552695039, 0.9722460960231261, 0.9031749941323011, 0.8783398191294471, 0.9962273648203385, 0.7388203665851438, 0.997671909440874, 0.7252639160635567, 0.80585979225472, 0.8372120281164042, 0.6030929935964386, 0.5365050979223966, 0.5631857983972779, 0.9085702249245923, 0.9531032378626904, 0.9739915590990671, 0.9971519557294345, 0.9181700045104967, 0.837344959912748, 0.5277766970035652, 0.9640221315980354, 0.6478132080854023, 0.9933979379290582, 0.9090110110243014, 0.981247115013658, 0.903518757595072, 0.8368268391872778, 0.9728788025529648, 0.10388288278634944, 0.31627116262573113, 0.7367376538874542, 0.1420877553038713, 0.33191777895745683, 0.8048335177104791, 0.8785252397850193, 0.9343737634150964, 0.9379471508110364, 0.9986928918202125, 0.9846492319020933, 0.9922703047608921, 0.9875250693595635, 0.9815798777187168, 0.10526081870398178, 0.5554629801827529, 0.6778408096565823, 0.39778878568245946, 0.9343247813120069, 0.9306019252699684, 0.8246061272269684, 0.12271521284959704, 0.4303424220405855, 0.970469158187509, 0.84830332449681, 0.9927557404550011, 0.8773450248886764, 0.9474081491425098, 0.9571204242022856, 0.9635341128516403, 0.5063458991794764, 0.8645546039593306, 0.2078999518375957, 0.7481047941906903, 0.8196267172082016, 0.6272175536067777, 0.9826138243849516, 0.8088372894590319, 0.5993553665998047, 0.8984506270865305, 0.8351332395683834, 0.95291954966145, 0.9328125369554351, 0.995487440531523, 0.9863512395559256, 0.08473606162672664, 0.5059795270953321, 0.24030024266162323, 0.5728236919447849, 0.7241605375834663, 0.5623271456423898, 0.8882247734416945, 0.7721740058583951, 0.7154566469091695, 0.33483930339600115, 0.9926327571523298, 0.8854131039068044, 0.9267493724780185, 0.4182292563650386, 0.4683442196417129, 0.1865125650876887, 0.33944074703935, 0.6986204355291861, 0.9880470611919054, 0.9561097491844963, 0.3561481456752228, 0.9581380938423786, 0.3398599286818024, 0.9647450932814664, 0.8430468782517605, 0.6919449309561331, 0.7515011532204174, 0.9057351518805, 0.5500003160687899, 0.5625594511386015, 0.7864508479372989, 0.19872815037386915, 0.9201032822569623, 0.9053144702062446, 0.9549325980183268, 0.8778437112298924, 0.867613081984981, 0.835580946368038, 0.7726963964035655, 0.34846135722392346, 0.9045770395909797, 0.9333589363402628, 0.9985625696356355, 0.9958457522708404, 0.9941302135713567, 0.9919820813362217, 0.9413902843030728, 0.9798933971238526, 0.669437372880883, 0.7473203715234638, 0.5452328367931984, 0.973569764010786, 0.9715127899677694, 0.9679788117626464, 0.3005173730290883, 0.9810654447439534, 0.9886869906654449, 0.7365689143973592, 0.8871055352668838, 0.771162090835281, 0.9939892363831946, 0.9867833712658552, 0.7353827489290764, 0.08953187330427059, 0.8734440248850177, 0.8823767512996115, 0.25419195891635626, 0.8662859836515463, 0.49103322758956985, 0.7299985687427313, 0.8120184271728307, 0.6514588890259572, 0.7325832647182334, 0.9580449609477661, 0.496465883592515, 0.1328100139699625, 0.4509974743407165, 0.4815826256899581, 0.9815450257531444, 0.9800836656527278, 0.941235483705549, 0.8525241989762684, 0.7877274383528682, 0.9572924124289837, 0.871894045607493, 0.9014157966238134, 0.7883641581680029, 0.9570212666842681, 0.8941761679582062, 0.8703453258598455, 0.8592628868446185, 0.9937862097155299, 0.9803585493359762, 0.9428987896512021, 0.9889961743013022, 0.9908801884754461, 0.9823210667667697, 0.9788506290803441, 0.991356830219052, 0.7152683754456076, 0.9654710615135186, 0.9239382136019831, 0.19140053110870375, 0.6253956886620529, 0.8330144615036557, 0.8286909833390095, 0.5207907614187908, 0.6114387738960633, 0.993346601212787, 0.9912305368097732, 0.933269501760659, 0.6813679057092138, 0.8174629522221105, 0.8385102081863772, 0.5477899959696633, 0.6989037395775299, 0.9621028572316744, 0.9106717349680188, 0.09471691575053337, 0.39688660899127803, 0.4622296259051981, 0.6617392280590757, 0.42687078107088106, 0.8594391015942691, 0.9183581005109295, 0.8453584339748206, 0.9936710462101732, 0.8887324959180073, 0.9782621081443565, 0.8953911988846551, 0.9763399212899977, 0.9754039242527179, 0.10087519455129693, 0.1081087212398951, 0.10011594843651735, 0.14611610593832589, 0.5628124018305815, 0.5631804191373113, 0.42645611146796913, 0.23500867614798102, 0.23571338819943016, 0.8845101192749911, 0.9020895659528465, 0.2276014710599622, 0.44207334457296077, 0.7876755844564447, 0.6567363025516675, 0.38732467142223004, 0.15113792235301315, 0.4383458941615897, 0.4825475661664893, 0.6102542858731218, 0.3828264429027116, 0.9944583213309401, 0.9972408062728458, 0.9803741818125064, 0.4039693494672231, 0.6012052598786986, 0.6396926552658082, 0.9899139847027254, 0.9986120048676957, 0.9270744165241682, 0.9069797989145247, 0.333432225734915, 0.2612800975432744, 0.8172141100981887, 0.9254627504654427, 0.9221547674353656, 0.3741609719985145, 0.3759924050711085, 0.6596875392384286, 0.6396847676523643, 0.7105477676017732, 0.882778256379049, 0.5260955063423622, 0.42732817590100375, 0.37410272463617195, 0.7846442601014568, 0.8455326363991313, 0.728641462814231, 0.5614812099482875, 0.8823395198372121, 0.8495276309851183, 0.2526573870711499, 0.06616525660037825, 0.10997444576733462, 0.5028967223283564, 0.16561799546807662, 0.12390394270693936, 0.8687315916969323, 0.4157126059075126, 0.6316708552091043, 0.1867503829674693, 0.6512820260037848, 0.7102254487748092, 0.6688869377074751, 0.5748240237508266, 0.7609378787257037, 0.7423095014292587, 0.7239746510991593, 0.9230787936231245, 0.9590222569629047, 0.9383154590588417, 0.6999759355482444, 0.5525480758257334, 0.5607396069154549, 0.7498764261674574, 0.07610787621933246, 0.22210968013535973, 0.5781867014044819, 0.6424221030855957, 0.8283599283496068, 0.09673061394368263, 0.619493179450269, 0.14547057130504082, 0.16911845578005702, 0.7459117835676546, 0.405781272319102, 0.8251441839333107, 0.21375112760147108, 0.13329581019854353, 0.23351000731983945, 0.9899189798939454, 0.9601380533201916, 0.4180264512226718, 0.9840645738073058, 0.7042976955525521, 0.9474082536642912, 0.43715465480314075, 0.6868350200551696, 0.6387225323487689, 0.3329394044949287, 0.5089025454020072, 0.3429611760507493, 0.9399625564790963, 0.9852167702547573, 0.9339039756953184, 0.2032016898871535, 0.886670487331828, 0.860987812642676, 0.9758153773657788, 0.8015185772740205, 0.6037448423266123, 0.82890591485178, 0.9450377921238888, 0.9636904924756896, 0.9733289044819671, 0.9624667820448829, 0.9746014727767054, 0.967355024290868, 0.9885672637282957, 0.6302367091370091, 0.6641432347881604, 0.9774858752130937, 0.8858296172792236, 0.47749249540257893, 0.8886741999224331, 0.8316687478991125, 0.9226020178556821, 0.9465689473981289, 0.8856051711969872, 0.9619180131736448, 0.8304588966126767, 0.9352312129834387, 0.706813123207101, 0.9359366517637588, 0.8020830054683445 ], "eval_rms_calibration_error": 0.29396100252265095 }