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

762 lines
21 KiB
JSON

{
"model_dir": "models/llama-30b",
"distribution_id": "code_hard",
"timestamp": "2023-10-14 01:51:41",
"eval_score": -0.22717749328532136,
"eval_brier_score": 0.22717749328532136,
"eval_average_probability": 0.6409135627137225,
"eval_accuracy": 0.676,
"eval_probabilities": [
0.9835081852099258,
0.6986180634633641,
0.9300249258694078,
0.48131605411370854,
0.17982065892206056,
0.6038228342610791,
0.9278527721900005,
0.45783877089464287,
0.5476273562279252,
0.2375091094687074,
0.4924182141909049,
0.411306451612405,
0.9455327731025689,
0.562514017486568,
0.4924790781682796,
0.6555820251292291,
0.8146411431477896,
0.4372084943047643,
0.20919375401077933,
0.275013604473204,
0.21028192140344704,
0.9614246281800249,
0.868400758798248,
0.9923740310568309,
0.739844787277093,
0.5641933762856811,
0.9485487934299571,
0.8046812860260092,
0.8391422583403643,
0.8156685080436199,
0.8943445139681608,
0.9515260137392488,
0.7994811414105738,
0.9602211103184668,
0.8854876356075548,
0.40336892887861653,
0.34160120093890955,
0.12238285415213346,
0.8314712905820781,
0.6324969134032183,
0.8569183894409885,
0.9302044297784178,
0.794844605348401,
0.7465570702976981,
0.5251567732264452,
0.9956518453845361,
0.5095659124253422,
0.8789502570168136,
0.9895987235977549,
0.9911150594392419,
0.9925695689263894,
0.00899813070085509,
0.8534343783482434,
0.9277832618160631,
0.02544706802423735,
0.029100762785042145,
0.16512604086028324,
0.2777865469572679,
0.9727807232815994,
0.9515455750377572,
0.05414932118455229,
0.17477466790057145,
0.04993644644809725,
0.9940731197989925,
0.9921741662782659,
0.9996774592772136,
0.07270143323472633,
0.3677698775941485,
0.2966330510337249,
0.5147086506994107,
0.9270628526135315,
0.6795226197516513,
0.9024953220516346,
0.9119873835685152,
0.8261138095142819,
0.9907216835343606,
0.9670912110920067,
0.988518261080743,
0.21370432386398905,
0.9356079415125593,
0.9588183539661862,
0.9564861135968683,
0.9898313254184596,
0.9056670516911144,
0.8287976407356454,
0.870224829147354,
0.7275604191873839,
0.9561505371176322,
0.9838872569475159,
0.9473904670791481,
0.655336068775369,
0.7205662513689017,
0.7199689054143716,
0.7598987993761377,
0.7374443065243392,
0.7050272423423232,
0.8975521715118095,
0.9285281761475519,
0.2505746547852409,
0.9733041135720043,
0.9924548720429464,
0.9623462428632968,
0.9385534029783938,
0.8771304273375254,
0.971484067040744,
0.7754452055426642,
0.996503239449481,
0.06792418235725739,
0.4640005751051138,
0.988729107603018,
0.62205232100779,
0.16263790180658533,
0.059277496375349736,
0.3301702602858831,
0.7630411422641169,
0.760235281445923,
0.6482175414160746,
0.26658759286086453,
0.5839189325811563,
0.3177645265298707,
0.20624032131251735,
0.9375211267127731,
0.6558968800675877,
0.8927283178656875,
0.8111270411006201,
0.9759494279186771,
0.9507503867531479,
0.9646737182397565,
0.9830625523278952,
0.7478295205284289,
0.34095330961537135,
0.11551249323455026,
0.9807243477053205,
0.9407357406389815,
0.9805998790592859,
0.8637921261820335,
0.9784409028033569,
0.8632069718820081,
0.07712256487284841,
0.06382607653484917,
0.08054326618312158,
0.13030241912426288,
0.9699506798599216,
0.7926291975251393,
0.945755473309262,
0.9542454453516436,
0.7955036356419437,
0.32996584479322444,
0.26695738134091884,
0.3459373847213074,
0.2936338914992971,
0.6464483649389879,
0.799584522041149,
0.4263433635284153,
0.6600382063217023,
0.8628467017823789,
0.4678662723903109,
0.9255009595745204,
0.9331213664333021,
0.2757423021445301,
0.05754658727689743,
0.2545872774202284,
0.8590232460442097,
0.7568925371104948,
0.8997008423755336,
0.9525693786340538,
0.9880121397081133,
0.6979168894931917,
0.8954707263405436,
0.6354454390506121,
0.8664347299353825,
0.6517206634301334,
0.34276009320821454,
0.6426875666567515,
0.6925592065699223,
0.17109214596839273,
0.5892167116313347,
0.8722617163067932,
0.3536920824297549,
0.9290790162517496,
0.9360652571746253,
0.6175060534957868,
0.2776823438443736,
0.8377580017505517,
0.4377761842408864,
0.9092991144224573,
0.05314402168364374,
0.9798959717912232,
0.8618562637467031,
0.9837348476798354,
0.8066769629425463,
0.919985086946524,
0.7605495062355057,
0.13348053241117508,
0.19290617135198962,
0.8743801829137952,
0.9566096009155919,
0.9753416428492389,
0.938939001472714,
0.7467654233006796,
0.8906924980570312,
0.3309480425966561,
0.019787070443168853,
0.05996669804300803,
0.12770852859938342,
0.8494472471325586,
0.20851593543595093,
0.3159655274787586,
0.2394676607023739,
0.2707799946881446,
0.172325931561836,
0.16174259099557828,
0.20879886004109505,
0.6193211939765575,
0.9533259212903947,
0.7748220539438183,
0.7479598560539328,
0.557159990586628,
0.6825127975336736,
0.9419139754865704,
0.6679376599712172,
0.9118895354732431,
0.9385415227921826,
0.9827034235190931,
0.9736194197913502,
0.9919297952510573,
0.5763651897973588,
0.9599052318137992,
0.7092815494256088,
0.05141364972893048,
0.7471962981335237,
0.4691658990870221,
0.9971413772400688,
0.39234769379739876,
0.6259237106873301,
0.6878316023991902,
0.6132496824532596,
0.8898908093442356,
0.9356425321562751,
0.728136830185351,
0.8019093877330445,
0.9177868579364782,
0.9767362800415256,
0.6710383128375332,
0.5859430055807839,
0.6132335358508958,
0.6842496708534042,
0.9886208694141247,
0.9514026710162135,
0.7773724622621474,
0.9840079084930066,
0.811399419840726,
0.8031389405545633,
0.4703813975733363,
0.7715841034856201,
0.22633185627918084,
0.37423280842517115,
0.46107640663435284,
0.23054313463309595,
0.6545072145710752,
0.5646024028085068,
0.8996056722859156,
0.20921570197964146,
0.8567202824984154,
0.05318057424261391,
0.8147274745424,
0.8682425000776062,
0.8568690312646248,
0.9403314489260559,
0.9680252857969163,
0.9918551992744075,
0.9831320521872874,
0.9089954509385855,
0.7956987723020568,
0.9684650375599931,
0.9825904026849227,
0.6067309037751456,
0.6266331830520853,
0.9051870293929328,
0.8943989338215683,
0.6774320564858937,
0.9053108527958821,
0.9438756572485267,
0.8680304818856631,
0.7931383075590159,
0.8215863625088363,
0.9586392563250816,
0.8753625904266918,
0.9894130790149254,
0.9819916843115748,
0.9385394082967708,
0.25236955225825475,
0.10990306770550828,
0.970345052967231,
0.4890285993017019,
0.16078386702690783,
0.6219437992613126,
0.41685845197184546,
0.9482517720346069,
0.5468646356696997,
0.7248398173677724,
0.9846252543153604,
0.9486692070859479,
0.2782502514641142,
0.05382063004614723,
0.8918320378750839,
0.27104999511190614,
0.299339261106234,
0.9606195733744635,
0.9104169449186396,
0.9431989693415364,
0.910732794562169,
0.6889934977264324,
0.9085458130348679,
0.7580932560298297,
0.9936102265726722,
0.8893291357522537,
0.8018580840616328,
0.603635497611096,
0.7733800778090479,
0.7491490439117462,
0.044531008093115276,
0.6449316389978068,
0.3452407946326643,
0.9695628795788303,
0.5339471260455412,
0.10330853551793484,
0.8348115216980894,
0.48488756546226686,
0.9818472033548132,
0.4886881214633968,
0.9174422229405287,
0.5058338455816671,
0.9160378600626344,
0.11814034684437713,
0.3173513936466156,
0.8776822669630866,
0.7617812234208662,
0.5176637188858181,
0.09574922191136515,
0.3350667381687027,
0.6443085751798314,
0.966468144275767,
0.7673018952544087,
0.9131188938175364,
0.36462475693511154,
0.09857949977894409,
0.0674747765727951,
0.6396272131849301,
0.8967394810987394,
0.4511184021170682,
0.05690028225529431,
0.2778665758229,
0.025663064155162063,
0.05542823737033986,
0.22004492823475635,
0.05733016991121387,
0.8703091969251924,
0.28236314566626614,
0.3247203302065985,
0.16650192331450286,
0.7692087362336215,
0.3239128243868422,
0.8155550995615141,
0.2791257529546586,
0.6739172198619923,
0.5806251925022796,
0.5521282859041554,
0.5820505692312291,
0.8398801812812661,
0.6225988139786319,
0.2217803643705465,
0.08693346719546391,
0.5943810622028813,
0.7355290144428898,
0.6766299282400401,
0.6019814965990412,
0.8777035510341218,
0.18118530559743373,
0.5932739919841216,
0.845767507399041,
0.6588619193227446,
0.9401553992012296,
0.3771042396376798,
0.9746158863646076,
0.3385771657327178,
0.1975912484920448,
0.941981119141104,
0.5925690748433257,
0.9801309314318409,
0.9934310511132746,
0.9956551239535266,
0.9649359719277477,
0.9638174359258085,
0.03985804272388471,
0.8937165884589218,
0.8861697833248763,
0.8278633520931356,
0.923702802201426,
0.7939293709094973,
0.9213430251270038,
0.9325437193759043,
0.7746228345963276,
0.41971379000041553,
0.9775096583551411,
0.9985018619429783,
0.9082201677477549,
0.9435517762437237,
0.150994498474335,
0.2856555631311877,
0.8879401683943484,
0.366927914002388,
0.3589908066957671,
0.1065548155372954,
0.15000672672815696,
0.2771711030576278,
0.5434313805953244,
0.40078109414414187,
0.9593956999165472,
0.1335232574088967,
0.28907550375832036,
0.8648125005991624,
0.8084044510291182,
0.988161398543422,
0.20021356498474963,
0.9555188326474996,
0.638779994804332,
0.9176570275122159,
0.8996364107442707,
0.6959774224209111,
0.4987426420674815,
0.13952366564102414,
0.7541193995770512,
0.9469668087552191,
0.9016780689576283,
0.5973265281987898,
0.864191317705022,
0.2615099650791075,
0.052308619361153164,
0.050118541874962674,
0.25093855341685317,
0.26904169218180196,
0.033248692858112494,
0.3237184997973204,
0.42762336317153393,
0.9918824128237336,
0.9155098633329232,
0.8634395341374013,
0.1753451243235168,
0.9919014492957922,
0.7595173603049888,
0.7794731289035108,
0.9087683545772274,
0.4925355793360996,
0.9615283742501927,
0.6070432466771711,
0.9302040897825176,
0.848977527182518,
0.9752779175790707,
0.6252558258547883,
0.8765726709880693,
0.8053250549600108,
0.12403834908740896,
0.9853889812702934,
0.8340763565176946,
0.49146209139788943,
0.8108214733816459,
0.6551027816422306,
0.812985829131796,
0.9832487484628075,
0.21445042949740034,
0.09404631805184882,
0.007171225690277616,
0.007150487769626124,
0.6949268449376198,
0.904353199613758,
0.9901393136410881,
0.4987873728409849,
0.9616640691584644,
0.9000187583992869,
0.0051558098471576885,
0.9863669501234094,
0.9848986083493968,
0.381988562318882,
0.7856504181013549,
0.6983890378605468,
0.7241384567642368,
0.8478127183239651,
0.6537641562905697,
0.860834525095869,
0.5692122393332978,
0.9656269931446991,
0.875260663812059,
0.6136994100352461,
0.6914307678965713,
0.2988759355361209,
0.743766009383909,
0.8340962858305173,
0.9320385646529383,
0.8944594400217107,
0.8345195615532919,
0.45061015141189087,
0.9919201756798491,
0.9809601874601451,
0.9098578787414773,
0.9477733538562026,
0.26062667852842947,
0.48011468844718197,
0.1968594035017759,
0.27295523362045704,
0.857073275068054,
0.7489920706575834,
0.2106757287645053,
0.9101079667619809,
0.30035893524753443,
0.30365906826623523,
0.6902778034178785,
0.9396693701624519,
0.9424805777587889,
0.9876153841605779,
0.08639212463891877,
0.15832234339292628,
0.4051682508830816,
0.7374571497054697,
0.7901331764995837,
0.1039757840004202,
0.019402143952970352,
0.030974836784043558,
0.7980635183820621,
0.9484419426713934,
0.8668294696703094,
0.9922574860785023,
0.4646806829020532,
0.2407438628126265,
0.032508660655059196,
0.09530814705171381,
0.13698142952884204,
0.3753366131874433,
0.9255971882858364,
0.23803237795693521,
0.9644439160523159,
0.6307343761446758,
0.5535202194672508,
0.28920828565148543,
0.2986466361387181,
0.138824749823645,
0.514310153005076,
0.7694048387896536,
0.9796594392379118,
0.954781273688241,
0.987403761158442,
0.9655985578171912,
0.024859237978263615,
0.7719236976355504,
0.5520916308218677,
0.3029632275165782,
0.07362149080541647,
0.06762805008842043,
0.9974819722046919,
0.9868180477217242,
0.9815964044925085,
0.9471699045340936,
0.9722898604194878,
0.9616868439261737,
0.15725248288658833,
0.5058714073178092,
0.1411932393204276,
0.08419764924452366,
0.8303406491187401,
0.8580651489074467,
0.8740363655779407,
0.41925321165408314,
0.7258737029444394,
0.49796040291805005,
0.14504919493776858,
0.25007574449739756,
0.9024659788671971,
0.9379975394129128,
0.6869480773332385,
0.9162979662264774,
0.9481743616636417,
0.907285193099024,
0.06622364926482771,
0.918230416306122,
0.280871938160424,
0.8729846594430124,
0.6516038030348085,
0.22707670963374582,
0.009254662530666424,
0.05016739395159395,
0.05407463484992568,
0.35346749186820925,
0.18865374480870067,
0.9042383841794069,
0.9654341152326062,
0.3916693358753772,
0.8957706625827334,
0.9491157537349689,
0.855432744863176,
0.7791694435450723,
0.07772567638930827,
0.25940949120185486,
0.2922866668863192,
0.7653313089783985,
0.1421416196914309,
0.9850516718567702,
0.984453929617616,
0.9563168098644562,
0.628183009976627,
0.9618713919093379,
0.6952540766085237,
0.5460095303736158,
0.501790670725064,
0.5039322325315215,
0.5779288625406337,
0.26530594079505376,
0.3406936591059475,
0.669867990132749,
0.5530041711716165,
0.7174966133230881,
0.9039335271270615,
0.8486105388234222,
0.8833246234928922,
0.07190990736571301,
0.7647711022921001,
0.9479278036336073,
0.8361376906691479,
0.9839203460388686,
0.27023298541292773,
0.991611326389611,
0.7827428343553702,
0.9721262441591256,
0.8816970470991209,
0.24945854000650514,
0.05496034870099009,
0.051391689722774636,
0.2920145120579411,
0.7922717532694676,
0.418812106535278,
0.9936186208721965,
0.9411296230395164,
0.8731765436041479,
0.7138513475576858,
0.935476404080117,
0.9996146360299086,
0.4091595548637631,
0.5042239103772268,
0.5799475414523846,
0.8306831745963826,
0.9367879448914485,
0.5550591174943879,
0.8986787347499061,
0.8146858390839019,
0.9262337296214099,
0.8777493406921654,
0.9744338736009422,
0.9803876495386623,
0.7261686418931645,
0.6858660890963764,
0.9493142592589427,
0.9264138599509915,
0.9898884965282635,
0.9909630588430465,
0.9499649446037995,
0.9016250523467447,
0.9831881484682431,
0.44963913705640346,
0.6685902975970837,
0.9123805044032618,
0.46238462599375596,
0.8864557820987153,
0.6006542841058031,
0.6788906843160899,
0.8863598302311181,
0.29536497294488373,
0.4856225150279372,
0.0524476803133348,
0.07422324069279777,
0.15453626727860337,
0.9736725459249059,
0.74030904397483,
0.983117745892074,
0.8911759874392406,
0.96900052812051,
0.8825187608773213,
0.9199167742960846,
0.9941860118173734,
0.06780966800105004,
0.1984312060767854,
0.5663137598304415,
0.5355222741786854,
0.8800970454438831,
0.8334098779318103,
0.9542043479846816,
0.9517282673936777,
0.9524370998538809,
0.30357107404366523,
0.17271353547622148,
0.7827863446569319,
0.3398002721782775,
0.2363649258395686,
0.2538013181634825,
0.3552618558298548,
0.2252181250981422,
0.9745425402912373,
0.7380377114051341,
0.016858831599528057,
0.5938793094467039,
0.7938409428793769,
0.9608989007021314,
0.8103773772394538,
0.9479059136058373,
0.9673318783305594,
0.9609804464026984,
0.9523812404002062,
0.6059719987649775,
0.9815243370472273,
0.6752880906853789,
0.39631709984478947,
0.8145144779355126,
0.885942525669571,
0.7809933310546083,
0.8030599950435039,
0.5727277693299524,
0.8904451445973959,
0.8723490200160082,
0.05078915135216622,
0.29376880739715433,
0.31236145959361583,
0.266579743087177,
0.20648049050889627,
0.04390966223587789,
0.7397796011263955,
0.9820209866718375,
0.9833014372513762,
0.35788730524609,
0.6571653508054549,
0.7903510571146355,
0.31857643200640046,
0.3571613566182236,
0.22922787118758636,
0.5350826214212103,
0.44424130276128443,
0.6120442505280447,
0.40457166040236026,
0.09272435180425165,
0.18252153659196024,
0.668046671417622,
0.6300608835220686,
0.6996260246396441
],
"eval_rms_calibration_error": 0.29652087163465013
}