kev / evaluation.json
skundu42's picture
Add held-out evaluation report
c959822 verified
Raw History Blame Contribute Delete
143 kB
{
"uncalibrated": {
"overall": {
"count": 17476,
"accuracy": 0.7985809109636073,
"log_loss": 0.49230193969031993,
"brier_score": 0.2802096009227025,
"ece_15": 0.038409021587914594,
"ordinal_mae": 0.3727614025515071,
"ordinal_count": 997
},
"source/tasksource/zero-shot-label-nli": {
"count": 1979,
"accuracy": 0.7281455280444669,
"log_loss": 0.5161915449429214,
"brier_score": 0.34877216174971326,
"ece_15": 0.03029219201220161,
"ordinal_mae": null,
"ordinal_count": 0
},
"kind/choice": {
"count": 15651,
"accuracy": 0.8008433965880775,
"log_loss": 0.4911452188629626,
"brier_score": 0.2776828999683597,
"ece_15": 0.04135510104840071,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/rotten_tomatoes": {
"count": 9,
"accuracy": 0.8888888888888888,
"log_loss": 0.14167306317777614,
"brier_score": 0.08184373427295029,
"ece_15": 0.11150019862956809,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/imdb": {
"count": 14,
"accuracy": 0.8571428571428571,
"log_loss": 0.21830981536265165,
"brier_score": 0.16696657124912387,
"ece_15": 0.118122814216601,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-bias": {
"count": 10,
"accuracy": 0.9,
"log_loss": 0.39026031647009146,
"brier_score": 0.23003624954290774,
"ece_15": 0.20450311132194052,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/Touche23-ValueEval": {
"count": 20,
"accuracy": 0.9,
"log_loss": 0.3233971118028126,
"brier_score": 0.18881968524422515,
"ece_15": 0.08769103723618404,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/virtue": {
"count": 18,
"accuracy": 0.7777777777777778,
"log_loss": 0.5544695183167773,
"brier_score": 0.3652606273704724,
"ece_15": 0.10809417467394164,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/humicroedit/subtask-2": {
"count": 17,
"accuracy": 0.5294117647058824,
"log_loss": 0.668951978682478,
"brier_score": 0.47482126017314447,
"ece_15": 0.16151028778090645,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/meld_e": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.8179600033579704,
"brier_score": 0.5634823152418934,
"ece_15": 0.27792269420872395,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/citation_intent": {
"count": 13,
"accuracy": 0.8461538461538461,
"log_loss": 0.37321650182444965,
"brier_score": 0.23476206589777396,
"ece_15": 0.1905081909317456,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lex_glue/ledgar": {
"count": 21,
"accuracy": 0.9047619047619048,
"log_loss": 0.18487318912761527,
"brier_score": 0.1086545636781901,
"ece_15": 0.10578723136936816,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynasent/dynabench.dynasent.r2.all/r2": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.43822894539076496,
"brier_score": 0.29223347262844424,
"ece_15": 0.20536942079615883,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/CogALexV": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.2960173657259703,
"brier_score": 0.17517309267135275,
"ece_15": 0.16361508328550184,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/emotion": {
"count": 16,
"accuracy": 0.875,
"log_loss": 0.3250099827855003,
"brier_score": 0.1961210928353625,
"ece_15": 0.1414621010277033,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/K&H+N": {
"count": 10,
"accuracy": 0.6,
"log_loss": 0.6013651803805745,
"brier_score": 0.43527929901669477,
"ece_15": 0.27235183004676355,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scientific-exaggeration-detection": {
"count": 15,
"accuracy": 0.7333333333333333,
"log_loss": 0.6091250021294122,
"brier_score": 0.4206860016677024,
"ece_15": 0.1931308925775061,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/yahoo_answers_topics": {
"count": 21,
"accuracy": 0.7142857142857143,
"log_loss": 0.3979357796020941,
"brier_score": 0.28076482273611164,
"ece_15": 0.1575586305221374,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/poem_sentiment": {
"count": 17,
"accuracy": 0.8235294117647058,
"log_loss": 0.4892394735777189,
"brier_score": 0.3079320811058927,
"ece_15": 0.17455293996237675,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_climate": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.4607512786626419,
"brier_score": 0.2834526827558238,
"ece_15": 0.1385072554219914,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/fever-evidence-related/mwong--fever-related": {
"count": 19,
"accuracy": 0.7894736842105263,
"log_loss": 0.45571088042165764,
"brier_score": 0.3202707326941488,
"ece_15": 0.23132931629501974,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-message": {
"count": 16,
"accuracy": 0.6875,
"log_loss": 0.5445516633163114,
"brier_score": 0.3702129694579478,
"ece_15": 0.16434371890461308,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynasent/dynabench.dynasent.r1.all/r1": {
"count": 16,
"accuracy": 0.875,
"log_loss": 0.577321434866638,
"brier_score": 0.29168608956427977,
"ece_15": 0.2081726800260979,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/dyda_e": {
"count": 17,
"accuracy": 1.0,
"log_loss": 0.04417400938285737,
"brier_score": 0.01049226002997129,
"ece_15": 0.0411027576308009,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/CREAK": {
"count": 21,
"accuracy": 0.7619047619047619,
"log_loss": 0.5081726325635354,
"brier_score": 0.3382906391791713,
"ece_15": 0.09373480466526815,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/sarcasm": {
"count": 18,
"accuracy": 0.6111111111111112,
"log_loss": 0.6475117416011661,
"brier_score": 0.45836110899326993,
"ece_15": 0.13452855984046247,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/medical_questions_pairs": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.36597250380759194,
"brier_score": 0.23097038476200957,
"ece_15": 0.2543400198938318,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_abortion": {
"count": 16,
"accuracy": 0.4375,
"log_loss": 0.7966763529688047,
"brier_score": 0.5956783941266531,
"ece_15": 0.2849024303717077,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ade_corpus_v2/Ade_corpus_v2_classification": {
"count": 18,
"accuracy": 0.7222222222222222,
"log_loss": 0.6441245473797038,
"brier_score": 0.4343455078371591,
"ece_15": 0.14182715422618286,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/commonsense_qa_2.0": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.5386296120023389,
"brier_score": 0.35158860663198394,
"ece_15": 0.18069320401090017,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/health_fact": {
"count": 17,
"accuracy": 0.8823529411764706,
"log_loss": 0.35314175664603786,
"brier_score": 0.20542471251149838,
"ece_15": 0.17937437947794535,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-audience": {
"count": 23,
"accuracy": 0.7391304347826086,
"log_loss": 0.44126636866706553,
"brier_score": 0.3076290607438106,
"ece_15": 0.16927721154721653,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/circa": {
"count": 21,
"accuracy": 0.9523809523809523,
"log_loss": 0.17487753470794917,
"brier_score": 0.0969496651837543,
"ece_15": 0.07673876434393226,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/iemocap": {
"count": 16,
"accuracy": 0.625,
"log_loss": 0.7674579983255659,
"brier_score": 0.5285902666037299,
"ece_15": 0.22058308451926445,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/hate": {
"count": 16,
"accuracy": 0.75,
"log_loss": 0.5499020705139512,
"brier_score": 0.3777113004448934,
"ece_15": 0.26087078278341785,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/pdtb": {
"count": 11,
"accuracy": 0.6363636363636364,
"log_loss": 0.5389450349140293,
"brier_score": 0.3730469555705936,
"ece_15": 0.286182776842427,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/winowhy": {
"count": 20,
"accuracy": 0.55,
"log_loss": 0.7217310268719503,
"brier_score": 0.5257732183182033,
"ece_15": 0.14832649091392353,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hyperpartisan_news": {
"count": 11,
"accuracy": 0.5454545454545454,
"log_loss": 0.5724618118848079,
"brier_score": 0.3963810444435573,
"ece_15": 0.345359107422761,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sms_spam": {
"count": 12,
"accuracy": 1.0,
"log_loss": 0.15591444971315802,
"brier_score": 0.05822512919236534,
"ece_15": 0.13856703643280263,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/ROOT09": {
"count": 21,
"accuracy": 0.8571428571428571,
"log_loss": 0.3115086911529061,
"brier_score": 0.18724904604270268,
"ece_15": 0.14582605427705903,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/clcd-english": {
"count": 20,
"accuracy": 0.7,
"log_loss": 0.6090553041710016,
"brier_score": 0.4203566531073464,
"ece_15": 0.25239511329769826,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/FLUTE": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.4635781105583847,
"brier_score": 0.29311804417501836,
"ece_15": 0.1613151453046786,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/starcon": {
"count": 19,
"accuracy": 0.8421052631578947,
"log_loss": 0.42956188709408466,
"brier_score": 0.25480182501422116,
"ece_15": 0.20063538134058986,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/BLESS": {
"count": 19,
"accuracy": 0.631578947368421,
"log_loss": 0.568139522399679,
"brier_score": 0.415679190690983,
"ece_15": 0.16235339286504047,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/EVALution": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.46706913753823237,
"brier_score": 0.3032777955181034,
"ece_15": 0.1317683024034402,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dbpedia_14/dbpedia_14": {
"count": 14,
"accuracy": 0.9285714285714286,
"log_loss": 0.19040692206536286,
"brier_score": 0.12194336591971146,
"ece_15": 0.07310429325647583,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/strategy-qa": {
"count": 17,
"accuracy": 0.29411764705882354,
"log_loss": 0.8134835468674985,
"brier_score": 0.6126713601774318,
"ece_15": 0.30389505654336374,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/cycic_classification": {
"count": 7,
"accuracy": 0.7142857142857143,
"log_loss": 0.8237531568397871,
"brier_score": 0.5738292388403493,
"ece_15": 0.44225242947398896,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/horoscope": {
"count": 16,
"accuracy": 0.5625,
"log_loss": 0.7103671536543629,
"brier_score": 0.5150540398567833,
"ece_15": 0.12915423131437648,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hlgd": {
"count": 18,
"accuracy": 0.6666666666666666,
"log_loss": 0.7925086268074288,
"brier_score": 0.5117570747556701,
"ece_15": 0.24723375372753698,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/paws/labeled_swap": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.46255405644875314,
"brier_score": 0.28576216579627756,
"ece_15": 0.2280659681104869,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/numer_sense": {
"count": 15,
"accuracy": 0.8,
"log_loss": 0.5182146573314791,
"brier_score": 0.341236979869189,
"ece_15": 0.21908882828849408,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/implicit-hate-stg1": {
"count": 16,
"accuracy": 0.6875,
"log_loss": 0.4412295744117953,
"brier_score": 0.30427166604263833,
"ece_15": 0.17399885005107582,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/EffectiveFeedbackStudentWriting": {
"count": 10,
"accuracy": 0.8,
"log_loss": 0.5356834301708717,
"brier_score": 0.3553012292049021,
"ece_15": 0.13878485714701003,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/phrase_similarity": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.6814736880041121,
"brier_score": 0.4792470195625156,
"ece_15": 0.441747697803359,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_atheism": {
"count": 10,
"accuracy": 0.5,
"log_loss": 0.8255945009056708,
"brier_score": 0.5845605262844571,
"ece_15": 0.24144561635953998,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/airline-sentiment": {
"count": 11,
"accuracy": 0.6363636363636364,
"log_loss": 0.5446367639402901,
"brier_score": 0.35765991765527444,
"ece_15": 0.26122333622495864,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/MOH": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5153571138040285,
"brier_score": 0.33742353736125585,
"ece_15": 0.20412131492735272,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sciie": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.8314393459971987,
"brier_score": 0.5786453770583999,
"ece_15": 0.378816718076871,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hate_speech18": {
"count": 17,
"accuracy": 0.8823529411764706,
"log_loss": 0.35098353326806153,
"brier_score": 0.16684662240672746,
"ece_15": 0.09149497019400032,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/racial-bias": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 0.6729198869772895,
"brier_score": 0.48518633705933073,
"ece_15": 0.24780157500450792,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/sst2": {
"count": 9,
"accuracy": 1.0,
"log_loss": 0.07587211415392216,
"brier_score": 0.016622639892638576,
"ece_15": 0.07129822842265623,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/gender-bias": {
"count": 15,
"accuracy": 0.6,
"log_loss": 0.6330231511718478,
"brier_score": 0.445120766841519,
"ece_15": 0.1321457824391712,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/offensive": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.3086426051529111,
"brier_score": 0.19313031718169363,
"ece_15": 0.21991847304366222,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hate_speech_offensive": {
"count": 18,
"accuracy": 0.8888888888888888,
"log_loss": 0.26692246435495076,
"brier_score": 0.146252902331788,
"ece_15": 0.2140092753771897,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/twentyquestions": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 0.7863899140869128,
"brier_score": 0.5693055100196097,
"ece_15": 0.3859411291748407,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sem_eval_2010_task_8": {
"count": 16,
"accuracy": 0.8125,
"log_loss": 0.3996555875111849,
"brier_score": 0.25605901210945087,
"ece_15": 0.18615987789449007,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/financial_phrasebank/sentences_allagree": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.19532664943719388,
"brier_score": 0.0976891539875525,
"ece_15": 0.159810553354925,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mc_taco": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.4918275492699584,
"brier_score": 0.318327135230503,
"ece_15": 0.1905441900764415,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/super_glue/multirc": {
"count": 8,
"accuracy": 0.5,
"log_loss": 0.8395761053104731,
"brier_score": 0.6120797215797903,
"ece_15": 0.3703628653515052,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/TuringBench": {
"count": 15,
"accuracy": 0.4,
"log_loss": 0.7876375806922853,
"brier_score": 0.5877657092216583,
"ece_15": 0.20133805519841522,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/reasoning_1hop": {
"count": 8,
"accuracy": 0.375,
"log_loss": 0.705131461885386,
"brier_score": 0.5120830362291584,
"ece_15": 0.18119689832014074,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/tweet_global_warming": {
"count": 15,
"accuracy": 0.8,
"log_loss": 0.45691246043190875,
"brier_score": 0.2930775236041658,
"ece_15": 0.039754718700293394,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/job": {
"count": 13,
"accuracy": 0.8461538461538461,
"log_loss": 0.4896731651022517,
"brier_score": 0.277322197588766,
"ece_15": 0.1664699023552833,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/parade": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6041612653771861,
"brier_score": 0.42148357587305535,
"ece_15": 0.2672736630080111,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/usnli": {
"count": 16,
"accuracy": 0.5,
"log_loss": 0.6970241928212817,
"brier_score": 0.5038938014379373,
"ece_15": 0.11153967395721691,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/stac": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.6373027001525201,
"brier_score": 0.4681664654492462,
"ece_15": 0.3194477579022656,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/quarel": {
"count": 22,
"accuracy": 0.6363636363636364,
"log_loss": 0.6680580043439217,
"brier_score": 0.4756395629333436,
"ece_15": 0.1924572440766058,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/sem": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.257659043060115,
"brier_score": 0.15573092676816191,
"ece_15": 0.11588068084121134,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/hate-speech": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.7467696547349584,
"brier_score": 0.5031488969649504,
"ece_15": 0.27745748869804604,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/economic-news": {
"count": 20,
"accuracy": 0.75,
"log_loss": 0.5875703099242824,
"brier_score": 0.39278005942839317,
"ece_15": 0.13077425949314292,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/liar": {
"count": 10,
"accuracy": 0.5,
"log_loss": 0.6702011498813479,
"brier_score": 0.4791324983234736,
"ece_15": 0.364678412565017,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scruples": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5525189547682415,
"brier_score": 0.3742025558600413,
"ece_15": 0.16808849030944462,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/open_question_type": {
"count": 14,
"accuracy": 0.8571428571428571,
"log_loss": 0.44054199934121685,
"brier_score": 0.2807151850718378,
"ece_15": 0.16344026702352524,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/emoji": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.7343610660765305,
"brier_score": 0.5178709306592536,
"ece_15": 0.22189528876068587,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/wiki_qa": {
"count": 16,
"accuracy": 1.0,
"log_loss": 0.04169329802889373,
"brier_score": 0.010874643608876468,
"ece_15": 0.03844825357482926,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/natural-language-satisfiability": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.578444131719973,
"brier_score": 0.38733621113648636,
"ece_15": 0.2427885602385805,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/CONDAQA": {
"count": 17,
"accuracy": 0.6470588235294118,
"log_loss": 0.5951169650796073,
"brier_score": 0.41033868774347326,
"ece_15": 0.26642448846837385,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/language-identification": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.42384018461880796,
"brier_score": 0.2803045664685451,
"ece_15": 0.17692982997019557,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/vitaminc/tals--vitaminc": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.45626478957065486,
"brier_score": 0.2861453831609383,
"ece_15": 0.0859758103256129,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/irony": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5228722650263381,
"brier_score": 0.34404978418690924,
"ece_15": 0.2718382842793733,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/gender": {
"count": 11,
"accuracy": 0.7272727272727273,
"log_loss": 0.5896380725264474,
"brier_score": 0.40044867814080026,
"ece_15": 0.1388151449891998,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/mrda": {
"count": 17,
"accuracy": 0.7647058823529411,
"log_loss": 0.7416070769184169,
"brier_score": 0.45154940044308006,
"ece_15": 0.2760789099491041,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/VUAC": {
"count": 18,
"accuracy": 0.6666666666666666,
"log_loss": 0.6580406052753286,
"brier_score": 0.4605314283736277,
"ece_15": 0.10592446095767183,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/amazon_polarity/amazon_polarity": {
"count": 15,
"accuracy": 0.9333333333333333,
"log_loss": 0.09676652474564765,
"brier_score": 0.05376743286256003,
"ece_15": 0.07718896617307063,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/logical-fallacy": {
"count": 20,
"accuracy": 0.65,
"log_loss": 0.6000571609782204,
"brier_score": 0.40973396030472814,
"ece_15": 0.13523861749452926,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/cognitive-bias": {
"count": 19,
"accuracy": 0.5789473684210527,
"log_loss": 0.6804829751636511,
"brier_score": 0.48658278546119615,
"ece_15": 0.08672749800220603,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ambient": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 1.3109700976109495,
"brier_score": 0.7692203938115867,
"ece_15": 0.4665314623211159,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/oasis": {
"count": 15,
"accuracy": 0.6666666666666666,
"log_loss": 0.6131139310199565,
"brier_score": 0.42661919548069555,
"ece_15": 0.2289723109249147,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/linguistic-bias": {
"count": 17,
"accuracy": 0.7058823529411765,
"log_loss": 0.6184210521930569,
"brier_score": 0.42646724969310634,
"ece_15": 0.25905190135106876,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/PARARULE-Plus": {
"count": 14,
"accuracy": 1.0,
"log_loss": 0.002119395660066006,
"brier_score": 2.6377197870509784e-05,
"ece_15": 0.0021127606343479704,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/gum": {
"count": 13,
"accuracy": 0.46153846153846156,
"log_loss": 0.8234103971631198,
"brier_score": 0.6025361902920193,
"ece_15": 0.2599970093900183,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/switchboard": {
"count": 12,
"accuracy": 0.6666666666666666,
"log_loss": 0.37015870067339823,
"brier_score": 0.2443803213052876,
"ece_15": 0.1955360920426917,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/verifiability": {
"count": 17,
"accuracy": 1.0,
"log_loss": 0.15912427424830505,
"brier_score": 0.054983714027949625,
"ece_15": 0.14251798180618064,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/spartqa-yn": {
"count": 9,
"accuracy": 0.6666666666666666,
"log_loss": 0.5597459563256386,
"brier_score": 0.38204556729291295,
"ece_15": 0.13762189918384532,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/emergent": {
"count": 12,
"accuracy": 0.5,
"log_loss": 0.6070243840348454,
"brier_score": 0.4284615369134999,
"ece_15": 0.22299769517653592,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/emo/emo2019": {
"count": 9,
"accuracy": 0.8888888888888888,
"log_loss": 0.3658150239277364,
"brier_score": 0.2065425984591287,
"ece_15": 0.2893026374183485,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/mrpc": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6277204213966494,
"brier_score": 0.4380964850075013,
"ece_15": 0.22060985146456685,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/I2D2": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.47881604087521096,
"brier_score": 0.31511683776573124,
"ece_15": 0.1891178288470162,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_hillary": {
"count": 9,
"accuracy": 0.4444444444444444,
"log_loss": 0.9571559606183246,
"brier_score": 0.7026308961160336,
"ece_15": 0.3367666766835902,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/political-bias": {
"count": 22,
"accuracy": 0.6818181818181818,
"log_loss": 0.6247059822518992,
"brier_score": 0.4337157656151254,
"ece_15": 0.09944228350518652,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/insincere-questions": {
"count": 12,
"accuracy": 1.0,
"log_loss": 0.03788952637977832,
"brier_score": 0.0050523037056264515,
"ece_15": 0.03653778849951328,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/discovery/discovery": {
"count": 18,
"accuracy": 0.6111111111111112,
"log_loss": 0.5954361333409931,
"brier_score": 0.41142857572844194,
"ece_15": 0.165418858470979,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/justice": {
"count": 12,
"accuracy": 0.4166666666666667,
"log_loss": 0.8168401025841542,
"brier_score": 0.6171549802608335,
"ece_15": 0.2661442010375547,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/cola": {
"count": 5,
"accuracy": 1.0,
"log_loss": 0.38696686980348943,
"brier_score": 0.20869269766165122,
"ece_15": 0.3189900777296757,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/banking77": {
"count": 17,
"accuracy": 0.9411764705882353,
"log_loss": 0.24170933298917752,
"brier_score": 0.1393861937489721,
"ece_15": 0.12330359707361695,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/cladder": {
"count": 12,
"accuracy": 0.6666666666666666,
"log_loss": 0.6236875694643325,
"brier_score": 0.4316312028961662,
"ece_15": 0.18048006360986793,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/commonsense": {
"count": 15,
"accuracy": 0.4666666666666667,
"log_loss": 0.7447986138193108,
"brier_score": 0.5514197683196601,
"ece_15": 0.28991239771096083,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scicite": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.4318331251125241,
"brier_score": 0.2762478171410345,
"ece_15": 0.21646846654982987,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/dyda_da": {
"count": 10,
"accuracy": 0.9,
"log_loss": 0.22769926066223617,
"brier_score": 0.1448665318240736,
"ece_15": 0.10335780417472865,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ag_news": {
"count": 15,
"accuracy": 0.8666666666666667,
"log_loss": 0.3464048347622382,
"brier_score": 0.20780113035510264,
"ece_15": 0.11026379618878748,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/maptask": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.5758575083844282,
"brier_score": 0.38075886257747904,
"ece_15": 0.23066958122332948,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynahate": {
"count": 12,
"accuracy": 0.5,
"log_loss": 0.8759301272164728,
"brier_score": 0.6438679618411262,
"ece_15": 0.3719697093628312,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/reasoning_2hop": {
"count": 13,
"accuracy": 0.46153846153846156,
"log_loss": 0.689490939631528,
"brier_score": 0.49638137510895075,
"ece_15": 0.07074967470947083,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/counterfactually-augmented-imdb": {
"count": 10,
"accuracy": 1.0,
"log_loss": 0.012876311703912841,
"brier_score": 0.0009432784254639257,
"ece_15": 0.012631961883189113,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweets_hate_speech_detection": {
"count": 18,
"accuracy": 1.0,
"log_loss": 0.07311481581271477,
"brier_score": 0.027589875296408786,
"ece_15": 0.06404904284035837,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/deontology": {
"count": 11,
"accuracy": 0.2727272727272727,
"log_loss": 0.9967284322203667,
"brier_score": 0.7783652246620442,
"ece_15": 0.4382173972135583,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hope_edi/english": {
"count": 10,
"accuracy": 1.0,
"log_loss": 0.007112887410789044,
"brier_score": 0.00014214220236576544,
"ece_15": 0.007077070666527696,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/text-level-bias": {
"count": 12,
"accuracy": 0.75,
"log_loss": 0.6438488726507172,
"brier_score": 0.44387673831099117,
"ece_15": 0.25993005223611526,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/paws/labeled_final": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.7584004733638848,
"brier_score": 0.5533706523188272,
"ece_15": 0.37515675293369316,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/avicenna": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.5898905853457523,
"brier_score": 0.4025616557756032,
"ece_15": 0.16434217157825676,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/subjectivity": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.6410537686048884,
"brier_score": 0.4486384856450565,
"ece_15": 0.2284194604768063,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/v1/gen_train234_test2to10": {
"count": 16,
"accuracy": 0.8125,
"log_loss": 0.64033753288312,
"brier_score": 0.4220114421078465,
"ece_15": 0.2872270031041739,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/folio": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.21804968262827318,
"brier_score": 0.12450894983540306,
"ece_15": 0.1703584617231207,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/text_emotion": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.49266944052826606,
"brier_score": 0.3406614797217879,
"ece_15": 0.1506212859141982,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/sentiment_nuclear_power": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.17467028431924653,
"brier_score": 0.05137043313221998,
"ece_15": 0.1602661514530047,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/corporate-messaging": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.5497931414193065,
"brier_score": 0.39431896296190316,
"ece_15": 0.30576164545191603,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/meld_s": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.5254718465987288,
"brier_score": 0.34742950351040947,
"ece_15": 0.20713230311421363,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/args_me": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5202640528301214,
"brier_score": 0.34560271922615027,
"ece_15": 0.11076116933396576,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/super_glue/wic": {
"count": 9,
"accuracy": 0.4444444444444444,
"log_loss": 0.7233159938786649,
"brier_score": 0.5321372605648536,
"ece_15": 0.2835889936225653,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/qqp": {
"count": 9,
"accuracy": 0.6666666666666666,
"log_loss": 0.472860533209498,
"brier_score": 0.32954043690628915,
"ece_15": 0.3062769937571913,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/rumoureval_2019/RumourEval2019": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.3280483704036526,
"brier_score": 0.2006143734456156,
"ece_15": 0.24064342766884242,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/fake-news": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6709165309235322,
"brier_score": 0.4706277677626032,
"ece_15": 0.29453356629512945,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethos/binary": {
"count": 10,
"accuracy": 0.7,
"log_loss": 0.46177562071673295,
"brier_score": 0.3461469149331206,
"ece_15": 0.2671010778814704,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_feminist": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.6382088354794687,
"brier_score": 0.44395124565715416,
"ece_15": 0.15887413713861823,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/trec": {
"count": 10,
"accuracy": 0.8,
"log_loss": 0.5096994058320339,
"brier_score": 0.3342729797729512,
"ece_15": 0.1847118449499415,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/snips_built_in_intents": {
"count": 4,
"accuracy": 0.5,
"log_loss": 0.8273618963676559,
"brier_score": 0.6364052931549977,
"ece_15": 0.41655744331081146,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/tasksource-instruct-v0": {
"count": 997,
"accuracy": 0.7121364092276831,
"log_loss": 0.6544185656310946,
"brier_score": 0.3905858788701158,
"ece_15": 0.027067872892760816,
"ordinal_mae": 0.3727614025515071,
"ordinal_count": 997
},
"kind/score": {
"count": 997,
"accuracy": 0.7121364092276831,
"log_loss": 0.6544185656310946,
"brier_score": 0.3905858788701158,
"ece_15": 0.027067872892760816,
"ordinal_mae": 0.3727614025515071,
"ordinal_count": 997
},
"task/tasksource/tasksource-instruct-v0/yelp_review_full/yelp_review_full": {
"count": 497,
"accuracy": 0.6841046277665996,
"log_loss": 0.7308296192021128,
"brier_score": 0.4283989024747208,
"ece_15": 0.054685767322741385,
"ordinal_mae": 0.3974469604936274,
"ordinal_count": 497
},
"task/tasksource/tasksource-instruct-v0/tweet_eval/sentiment": {
"count": 500,
"accuracy": 0.74,
"log_loss": 0.5784659783815007,
"brier_score": 0.3529997334071374,
"ece_15": 0.04281764922557473,
"ordinal_mae": 0.34822395795703953,
"ordinal_count": 500
},
"source/nyu-mll/multi_nli": {
"count": 2000,
"accuracy": 0.907,
"log_loss": 0.2503782744702875,
"brier_score": 0.1398590301676452,
"ece_15": 0.009440014677003127,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/nyu-mll/multi_nli/nyu-mll/multi_nli/default": {
"count": 2000,
"accuracy": 0.907,
"log_loss": 0.2503782744702875,
"brier_score": 0.1398590301676452,
"ece_15": 0.009440014677003127,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/facebook/anli": {
"count": 2000,
"accuracy": 0.5785,
"log_loss": 1.0241603772169452,
"brier_score": 0.598273250581322,
"ece_15": 0.1877582769905423,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/facebook/anli/facebook/anli/plain_text": {
"count": 2000,
"accuracy": 0.5785,
"log_loss": 1.0241603772169452,
"brier_score": 0.598273250581322,
"ece_15": 0.1877582769905423,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/defeasible-nli": {
"count": 2000,
"accuracy": 0.8745,
"log_loss": 0.2953982323779266,
"brier_score": 0.18100591800831833,
"ece_15": 0.01850405280593437,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/social": {
"count": 1217,
"accuracy": 0.9063270336894002,
"log_loss": 0.21867233719694193,
"brier_score": 0.13097456920549835,
"ece_15": 0.019611015496954282,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/atomic": {
"count": 542,
"accuracy": 0.8173431734317343,
"log_loss": 0.42832116177766,
"brier_score": 0.26720082054403005,
"ece_15": 0.0544780985763878,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/snli": {
"count": 241,
"accuracy": 0.8423236514522822,
"log_loss": 0.38390938051320106,
"brier_score": 0.23980473260863053,
"ece_15": 0.0641852458826681,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/FOL-nli": {
"count": 2000,
"accuracy": 0.834,
"log_loss": 0.41933690098607834,
"brier_score": 0.2384377747731735,
"ece_15": 0.013194922042872767,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/FOL-nli/tasksource/FOL-nli/default": {
"count": 2000,
"accuracy": 0.834,
"log_loss": 0.41933690098607834,
"brier_score": 0.2384377747731735,
"ece_15": 0.013194922042872767,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/doc-nli": {
"count": 1776,
"accuracy": 0.8693693693693694,
"log_loss": 0.4702459141944009,
"brier_score": 0.21602108515578877,
"ece_15": 0.09066421378716669,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/doc-nli/tasksource/doc-nli/default": {
"count": 1776,
"accuracy": 0.8693693693693694,
"log_loss": 0.4702459141944009,
"brier_score": 0.21602108515578877,
"ece_15": 0.09066421378716669,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/bigbench": {
"count": 1896,
"accuracy": 0.7600210970464135,
"log_loss": 0.5945892380200355,
"brier_score": 0.29760266888297954,
"ece_15": 0.027778599832484385,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/vitaminc_fact_verification": {
"count": 262,
"accuracy": 0.8625954198473282,
"log_loss": 0.35488678574675664,
"brier_score": 0.19865901558972499,
"ece_15": 0.05097064656617047,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/mnist_ascii": {
"count": 349,
"accuracy": 0.8223495702005731,
"log_loss": 0.6204249369841943,
"brier_score": 0.269407626056375,
"ece_15": 0.05139675194333151,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cs_algorithms": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.8318294957033027,
"brier_score": 0.4208567256331556,
"ece_15": 0.3591375294684862,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/language_identification": {
"count": 39,
"accuracy": 0.2564102564102564,
"log_loss": 2.1488308328863375,
"brier_score": 0.8601207639550233,
"ece_15": 0.13212908193304784,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/unit_conversion": {
"count": 73,
"accuracy": 0.8493150684931506,
"log_loss": 0.3697982174579797,
"brier_score": 0.18315480409037768,
"ece_15": 0.08730104979681678,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/bbq_lite_json": {
"count": 61,
"accuracy": 0.9836065573770492,
"log_loss": 0.09371779188813445,
"brier_score": 0.03888321894138145,
"ece_15": 0.023381337788408445,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/movie_dialog_same_or_different": {
"count": 197,
"accuracy": 0.7563451776649747,
"log_loss": 0.48856434791550046,
"brier_score": 0.32186388472172084,
"ece_15": 0.04205984419347936,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/fact_checker": {
"count": 34,
"accuracy": 0.8235294117647058,
"log_loss": 0.44331493864485316,
"brier_score": 0.2873391048539894,
"ece_15": 0.11020671559400137,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/social_support": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.8493375201806352,
"brier_score": 0.6007501590788596,
"ece_15": 0.4889538706042209,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/hyperbaton": {
"count": 179,
"accuracy": 1.0,
"log_loss": 0.0030401693947674866,
"brier_score": 0.0010691606906897185,
"ece_15": 0.0027256753758118967,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/formal_fallacies_syllogisms_negation": {
"count": 70,
"accuracy": 0.7714285714285715,
"log_loss": 0.43476594877696134,
"brier_score": 0.2832662727357645,
"ece_15": 0.08273752659285324,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/contextual_parametric_knowledge_conflicts": {
"count": 72,
"accuracy": 1.0,
"log_loss": 0.001405064876897654,
"brier_score": 0.0001308076321174364,
"ece_15": 0.001370854595172991,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/abstract_narrative_understanding": {
"count": 5,
"accuracy": 0.0,
"log_loss": 2.2986971420332334,
"brier_score": 0.9845303400186026,
"ece_15": 0.29150496136292425,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/goal_step_wikihow": {
"count": 34,
"accuracy": 0.7941176470588235,
"log_loss": 0.4565665629357099,
"brier_score": 0.2735529756554902,
"ece_15": 0.18219847221859173,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/real_or_fake_text": {
"count": 47,
"accuracy": 0.3404255319148936,
"log_loss": 1.8897484761287116,
"brier_score": 0.7925847597712499,
"ece_15": 0.1648527176909287,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/symbol_interpretation": {
"count": 5,
"accuracy": 0.0,
"log_loss": 1.7534130977801385,
"brier_score": 0.8562569910857161,
"ece_15": 0.30216957340215506,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/arithmetic": {
"count": 74,
"accuracy": 1.0,
"log_loss": 0.0005265116178442115,
"brier_score": 1.4785713576490667e-05,
"ece_15": 0.000522639379963306,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/timedial": {
"count": 18,
"accuracy": 1.0,
"log_loss": 0.056595530228390686,
"brier_score": 0.027228992776938025,
"ece_15": 0.0432306484665529,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/discourse_marker_prediction": {
"count": 4,
"accuracy": 0.0,
"log_loss": 2.5476397296930466,
"brier_score": 0.962763556742865,
"ece_15": 0.284402084812965,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/strategyqa": {
"count": 10,
"accuracy": 0.7,
"log_loss": 0.6883938512526012,
"brier_score": 0.4935897073703076,
"ece_15": 0.2764223308076861,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/parsinlu_qa": {
"count": 9,
"accuracy": 0.2222222222222222,
"log_loss": 1.4908273487862438,
"brier_score": 0.7630356272411518,
"ece_15": 0.2220835161829854,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_deduction": {
"count": 9,
"accuracy": 0.3333333333333333,
"log_loss": 1.1460686227267756,
"brier_score": 0.6042348683137022,
"ece_15": 0.40142515454530364,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/elementary_math_qa": {
"count": 159,
"accuracy": 0.3836477987421384,
"log_loss": 1.3701805967852991,
"brier_score": 0.6855753610097235,
"ece_15": 0.11133990684516334,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/tracking_shuffled_objects": {
"count": 20,
"accuracy": 0.25,
"log_loss": 1.6748300871561934,
"brier_score": 0.824427439519923,
"ece_15": 0.21041502870187445,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/snarks": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.6623853823577757,
"brier_score": 0.46924813208835703,
"ece_15": 0.4843800842769844,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/color": {
"count": 18,
"accuracy": 0.3333333333333333,
"log_loss": 1.699628632517954,
"brier_score": 0.7839887278297692,
"ece_15": 0.08018102142059981,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/play_dialog_same_or_different": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5488956218068058,
"brier_score": 0.36429207498555916,
"ece_15": 0.15198860578167028,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/indic_cause_and_effect": {
"count": 2,
"accuracy": 0.0,
"log_loss": 0.8892930303171471,
"brier_score": 0.6901270572143436,
"ece_15": 0.5834873901945349,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logic_grid_puzzle": {
"count": 10,
"accuracy": 0.5,
"log_loss": 1.0825882747004594,
"brier_score": 0.576639404561162,
"ece_15": 0.2571618241351024,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/sports_understanding": {
"count": 4,
"accuracy": 0.0,
"log_loss": 0.7403959729739352,
"brier_score": 0.5469476216808751,
"ece_15": 0.5220811721202167,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/fantasy_reasoning": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.4869129516784711,
"brier_score": 0.3205736473455824,
"ece_15": 0.3623005127202489,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/question_selection": {
"count": 7,
"accuracy": 1.0,
"log_loss": 0.1005091247472382,
"brier_score": 0.022610158498892124,
"ece_15": 0.09004107013490147,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/code_line_description": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.19319191191923257,
"brier_score": 0.04155747507791947,
"ece_15": 0.175676238596981,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/kanji_ascii": {
"count": 2,
"accuracy": 0.5,
"log_loss": 1.367799367061274,
"brier_score": 0.6712085426601548,
"ece_15": 0.43753104493362033,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/analogical_similarity": {
"count": 2,
"accuracy": 0.0,
"log_loss": 2.4516314896323568,
"brier_score": 0.9782674612330993,
"ece_15": 0.2038757832150454,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/winowhy": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.3915310422191835,
"brier_score": 0.24404242409037566,
"ece_15": 0.28511325502240886,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/salient_translation_error_detection": {
"count": 3,
"accuracy": 0.3333333333333333,
"log_loss": 1.9328707468356596,
"brier_score": 0.8719910893343025,
"ece_15": 0.12157010695826635,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/rhyming": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.11396708983298824,
"brier_score": 0.024563529505863907,
"ece_15": 0.10573112993952138,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/movie_recommendation": {
"count": 3,
"accuracy": 1.0,
"log_loss": 0.1659423715133119,
"brier_score": 0.0542555458314919,
"ece_15": 0.14416865959328237,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/analytic_entailment": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.2709319997053973,
"brier_score": 0.12174154730231448,
"ece_15": 0.23304139330699092,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_fallacy_detection": {
"count": 7,
"accuracy": 0.7142857142857143,
"log_loss": 0.7197091284961428,
"brier_score": 0.4175653521370116,
"ece_15": 0.18212288959487993,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/temporal_sequences": {
"count": 3,
"accuracy": 1.0,
"log_loss": 0.028569655708020506,
"brier_score": 0.002255009734825616,
"ece_15": 0.027881549094308806,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/kannada": {
"count": 3,
"accuracy": 0.3333333333333333,
"log_loss": 1.2825517804250592,
"brier_score": 0.7064254366841242,
"ece_15": 0.45584604797760275,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/navigate": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.7699403206031636,
"brier_score": 0.5760357935969403,
"ece_15": 0.5348180127394855,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/social_iqa": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.38270773166685323,
"brier_score": 0.204426476469744,
"ece_15": 0.09899626749410305,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/implicatures": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.2609504935782483,
"brier_score": 0.16289221358059233,
"ece_15": 0.20433333601916398,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/penguins_in_a_table": {
"count": 2,
"accuracy": 0.0,
"log_loss": 2.0413339243079247,
"brier_score": 1.0164700566040343,
"ece_15": 0.37641428086742673,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/epistemic_reasoning": {
"count": 8,
"accuracy": 1.0,
"log_loss": 0.062205730006655614,
"brier_score": 0.014921854794889326,
"ece_15": 0.05791584386090702,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/reasoning_about_colored_objects": {
"count": 5,
"accuracy": 0.6,
"log_loss": 1.3339993281042424,
"brier_score": 0.22112079410333524,
"ece_15": 0.01418309048427211,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/strange_stories": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8259394198788436,
"brier_score": 0.6320848362963996,
"ece_15": 0.5621765008857981,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/what_is_the_tao": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8981232641398401,
"brier_score": 0.7025073974022347,
"ece_15": 0.5926665999540697,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/international_phonetic_alphabet_nli": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.412482580110375,
"brier_score": 0.8372991364600517,
"ece_15": 0.44100307405613826,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/hindu_knowledge": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.610034782202861,
"brier_score": 0.29091329010914513,
"ece_15": 0.4566680295369835,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cryobiology_spanish": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.16372883995909746,
"brier_score": 0.045618793949402325,
"ece_15": 0.15102780199255084,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/intent_recognition": {
"count": 4,
"accuracy": 1.0,
"log_loss": 0.17035605618560726,
"brier_score": 0.07253454942435356,
"ece_15": 0.12823069900149586,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/metaphor_boolean": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.14047367234871594,
"brier_score": 0.05006837749950187,
"ece_15": 0.1257659278458747,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/suicide_risk": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.308353365222305,
"brier_score": 0.7170367594867829,
"ece_15": 0.3062500465196527,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_args": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.973522639380097,
"brier_score": 0.5083220596275099,
"ece_15": 0.6222499854758178,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/ruin_names": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.621400668411321,
"brier_score": 0.9226563278646717,
"ece_15": 0.4740698200688341,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/causal_judgment": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8888923460403997,
"brier_score": 0.6935808166729854,
"ece_15": 0.588889130767832,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/english_proverbs": {
"count": 1,
"accuracy": 0.0,
"log_loss": 3.6431405937707138,
"brier_score": 1.8141796471839273,
"ece_15": 0.9297606479356774,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/empirical_judgments": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.4260709410856809,
"brier_score": 0.9580650403082998,
"ece_15": 0.5946270117054103,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/physical_intuition": {
"count": 2,
"accuracy": 0.5,
"log_loss": 1.1295488932551905,
"brier_score": 0.6208961702353901,
"ece_15": 0.45723326676247267,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/similarities_abstraction": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.5405214594683632,
"brier_score": 0.3087070153736353,
"ece_15": 0.41755554800320716,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/swahili_english_proverbs": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.5899544056173409,
"brier_score": 0.29824981962565655,
"ece_15": 0.44564744047896465,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/date_understanding": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.07117941218959864,
"brier_score": 0.007270133709711194,
"ece_15": 0.06870520849960926,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/medical_questions_russian": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.3484445810050557,
"brier_score": 0.1731248996897365,
"ece_15": 0.29421497216298875,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/anachronisms": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8888923460403997,
"brier_score": 0.6935808166729854,
"ece_15": 0.588889130767832,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/simple_ethical_questions": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.5109795748836918,
"brier_score": 1.0218176323160264,
"ece_15": 0.6557421165739532,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/dark_humor_detection": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.4246305677439776,
"brier_score": 0.2394162871587119,
"ece_15": 0.34598864660470574,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/irony_identification": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.0110184794041372,
"brier_score": 0.8076268693054449,
"ece_15": 0.6345343098156068,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/geometric_shapes": {
"count": 2,
"accuracy": 0.0,
"log_loss": 2.4923691485595008,
"brier_score": 0.691683099863767,
"ece_15": 0.16429964806133548,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cause_and_effect": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.06384292136816497,
"brier_score": 0.007650263214002998,
"ece_15": 0.0618476483546585,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/moral_permissibility": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8084917378836574,
"brier_score": 0.6148749930268649,
"ece_15": 0.5544704649604273,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/phrase_relatedness": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.0628781310584738,
"brier_score": 0.7868765837267643,
"ece_15": 0.5969015237378581,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/crass_ai": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.42296553932806247,
"brier_score": 0.18061264404143007,
"ece_15": 0.3448987920493549,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/figure_of_speech_detection": {
"count": 1,
"accuracy": 1.0,
"log_loss": 1.3302745577462225,
"brier_score": 0.6255954829711331,
"ece_15": 0.7355953430134712,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/Rowan/hellaswag": {
"count": 2000,
"accuracy": 0.86,
"log_loss": 0.36216262199223165,
"brier_score": 0.19636745240119854,
"ece_15": 0.024481463629632053,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/Rowan/hellaswag/Rowan/hellaswag/default": {
"count": 2000,
"accuracy": 0.86,
"log_loss": 0.36216262199223165,
"brier_score": 0.19636745240119854,
"ece_15": 0.024481463629632053,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/google/boolq": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.31896083051883756,
"brier_score": 0.19506497232710848,
"ece_15": 0.02807812588868236,
"ordinal_mae": null,
"ordinal_count": 0
},
"kind/noul": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.31896083051883756,
"brier_score": 0.19506497232710848,
"ece_15": 0.02807812588868236,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/google/boolq/google/boolq/default": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.31896083051883756,
"brier_score": 0.19506497232710848,
"ece_15": 0.02807812588868236,
"ordinal_mae": null,
"ordinal_count": 0
}
},
"calibrated": {
"overall": {
"count": 17476,
"accuracy": 0.7985809109636073,
"log_loss": 0.4746148257879429,
"brier_score": 0.2768548946790544,
"ece_15": 0.014261655942813945,
"ordinal_mae": 0.3923422177916232,
"ordinal_count": 997
},
"source/tasksource/zero-shot-label-nli": {
"count": 1979,
"accuracy": 0.7281455280444669,
"log_loss": 0.5150510230997565,
"brier_score": 0.3481778900388312,
"ece_15": 0.029566299660355483,
"ordinal_mae": null,
"ordinal_count": 0
},
"kind/choice": {
"count": 15651,
"accuracy": 0.8008433965880775,
"log_loss": 0.4706446079609039,
"brier_score": 0.273581528978314,
"ece_15": 0.01438703174072128,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/rotten_tomatoes": {
"count": 9,
"accuracy": 0.8888888888888888,
"log_loss": 0.17256064504520743,
"brier_score": 0.09563495675656403,
"ece_15": 0.13803715628650462,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/imdb": {
"count": 14,
"accuracy": 0.8571428571428571,
"log_loss": 0.2043680763935434,
"brier_score": 0.1437798160522632,
"ece_15": 0.12940505043211167,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-bias": {
"count": 10,
"accuracy": 0.9,
"log_loss": 0.43756013769150537,
"brier_score": 0.2636482502143494,
"ece_15": 0.1966197457049946,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/Touche23-ValueEval": {
"count": 20,
"accuracy": 0.9,
"log_loss": 0.3125276783455419,
"brier_score": 0.18798907051468547,
"ece_15": 0.08847487206515645,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/virtue": {
"count": 18,
"accuracy": 0.7777777777777778,
"log_loss": 0.5693555002594094,
"brier_score": 0.3792036244270036,
"ece_15": 0.10372804291821851,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/humicroedit/subtask-2": {
"count": 17,
"accuracy": 0.5294117647058824,
"log_loss": 0.6614352674072255,
"brier_score": 0.46932479738971483,
"ece_15": 0.14464434923043992,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/meld_e": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.7276548672981771,
"brier_score": 0.5187603945589412,
"ece_15": 0.2354493050902806,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/citation_intent": {
"count": 13,
"accuracy": 0.8461538461538461,
"log_loss": 0.3789059143915369,
"brier_score": 0.2373359117317879,
"ece_15": 0.1456462518045907,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lex_glue/ledgar": {
"count": 21,
"accuracy": 0.9047619047619048,
"log_loss": 0.22369106570247702,
"brier_score": 0.12306482765477454,
"ece_15": 0.1387134117209304,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynasent/dynabench.dynasent.r2.all/r2": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.44162271765029093,
"brier_score": 0.28828683621645124,
"ece_15": 0.22975229357153953,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/CogALexV": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.3456359878981195,
"brier_score": 0.19870445498302056,
"ece_15": 0.20165815414173383,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/emotion": {
"count": 16,
"accuracy": 0.875,
"log_loss": 0.34376986287818917,
"brier_score": 0.20519079535877968,
"ece_15": 0.09514125326433424,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/K&H+N": {
"count": 10,
"accuracy": 0.6,
"log_loss": 0.5915581669101454,
"brier_score": 0.4184836288171258,
"ece_15": 0.20255649840006762,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scientific-exaggeration-detection": {
"count": 15,
"accuracy": 0.7333333333333333,
"log_loss": 0.608794267993121,
"brier_score": 0.42107799414180797,
"ece_15": 0.19003799809500752,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/yahoo_answers_topics": {
"count": 21,
"accuracy": 0.7142857142857143,
"log_loss": 0.40972729243384864,
"brier_score": 0.274516712427393,
"ece_15": 0.2544248655305512,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/poem_sentiment": {
"count": 17,
"accuracy": 0.8235294117647058,
"log_loss": 0.4880403183118992,
"brier_score": 0.3122694095068833,
"ece_15": 0.17964045266648512,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_climate": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.4937934037550049,
"brier_score": 0.31101628048908425,
"ece_15": 0.15890521099601174,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/fever-evidence-related/mwong--fever-related": {
"count": 19,
"accuracy": 0.7894736842105263,
"log_loss": 0.4462165797874618,
"brier_score": 0.3025353854526682,
"ece_15": 0.18205539811734292,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-message": {
"count": 16,
"accuracy": 0.6875,
"log_loss": 0.5322535589767222,
"brier_score": 0.3600028819062956,
"ece_15": 0.1757269370396578,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynasent/dynabench.dynasent.r1.all/r1": {
"count": 16,
"accuracy": 0.875,
"log_loss": 0.5440966465171441,
"brier_score": 0.312700084493129,
"ece_15": 0.24713472824159738,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/dyda_e": {
"count": 17,
"accuracy": 1.0,
"log_loss": 0.08485858032401881,
"brier_score": 0.02269360542409514,
"ece_15": 0.07813653093721144,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/CREAK": {
"count": 21,
"accuracy": 0.7619047619047619,
"log_loss": 0.5212072206379214,
"brier_score": 0.34474082324692085,
"ece_15": 0.10817107814667283,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/sarcasm": {
"count": 18,
"accuracy": 0.6111111111111112,
"log_loss": 0.6513613301144051,
"brier_score": 0.46036234567780565,
"ece_15": 0.09331768953710873,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/medical_questions_pairs": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.39699502358732586,
"brier_score": 0.2447779016438637,
"ece_15": 0.29395786878235175,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_abortion": {
"count": 16,
"accuracy": 0.4375,
"log_loss": 0.7542367894281041,
"brier_score": 0.5588060530610977,
"ece_15": 0.2452767656184259,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ade_corpus_v2/Ade_corpus_v2_classification": {
"count": 18,
"accuracy": 0.7222222222222222,
"log_loss": 0.6171563916332724,
"brier_score": 0.4215355870058244,
"ece_15": 0.15156889948056576,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/commonsense_qa_2.0": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.5740248261648443,
"brier_score": 0.3835991030942798,
"ece_15": 0.32305103202107044,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/health_fact": {
"count": 17,
"accuracy": 0.8823529411764706,
"log_loss": 0.3799747233587511,
"brier_score": 0.224673327341037,
"ece_15": 0.1908523220665037,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/political-media-audience": {
"count": 23,
"accuracy": 0.7391304347826086,
"log_loss": 0.43048470514871817,
"brier_score": 0.28836578407327723,
"ece_15": 0.1571658196702359,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/circa": {
"count": 21,
"accuracy": 0.9523809523809523,
"log_loss": 0.20207630546593036,
"brier_score": 0.10456373037407377,
"ece_15": 0.09698853597682473,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/iemocap": {
"count": 16,
"accuracy": 0.625,
"log_loss": 0.7001973280574378,
"brier_score": 0.4951080252788981,
"ece_15": 0.2636215449282059,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/hate": {
"count": 16,
"accuracy": 0.75,
"log_loss": 0.5694836129910303,
"brier_score": 0.3894436624529705,
"ece_15": 0.24167276881353353,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/pdtb": {
"count": 11,
"accuracy": 0.6363636363636364,
"log_loss": 0.532122988581282,
"brier_score": 0.36069207135217235,
"ece_15": 0.30326938420735305,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/winowhy": {
"count": 20,
"accuracy": 0.55,
"log_loss": 0.7096738763478374,
"brier_score": 0.5155209107452766,
"ece_15": 0.10611770381653915,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hyperpartisan_news": {
"count": 11,
"accuracy": 0.5454545454545454,
"log_loss": 0.5872962153868201,
"brier_score": 0.4030972043390918,
"ece_15": 0.22812215434209018,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sms_spam": {
"count": 12,
"accuracy": 1.0,
"log_loss": 0.22336569340935367,
"brier_score": 0.09830953739400583,
"ece_15": 0.1928052185190914,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/ROOT09": {
"count": 21,
"accuracy": 0.8571428571428571,
"log_loss": 0.34481671708972744,
"brier_score": 0.20432472138559268,
"ece_15": 0.1817675430094532,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/clcd-english": {
"count": 20,
"accuracy": 0.7,
"log_loss": 0.6079546676739491,
"brier_score": 0.41969306964493824,
"ece_15": 0.2599639978279463,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/FLUTE": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.503953454241523,
"brier_score": 0.32290160753793595,
"ece_15": 0.20688674773850485,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/starcon": {
"count": 19,
"accuracy": 0.8421052631578947,
"log_loss": 0.43205797035036947,
"brier_score": 0.26577317068670275,
"ece_15": 0.2114098705290565,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/BLESS": {
"count": 19,
"accuracy": 0.631578947368421,
"log_loss": 0.5485365214517407,
"brier_score": 0.3922055910234009,
"ece_15": 0.14428404474177733,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/lexical_relation_classification/EVALution": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.5028670202095411,
"brier_score": 0.3287551982178271,
"ece_15": 0.14850521170441494,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dbpedia_14/dbpedia_14": {
"count": 14,
"accuracy": 0.9285714285714286,
"log_loss": 0.1646743941344153,
"brier_score": 0.10731982458567148,
"ece_15": 0.0855197860968244,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/strategy-qa": {
"count": 17,
"accuracy": 0.29411764705882354,
"log_loss": 0.7739829588226838,
"brier_score": 0.5780573034881167,
"ece_15": 0.27884182704283283,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/cycic_classification": {
"count": 7,
"accuracy": 0.7142857142857143,
"log_loss": 0.7615217863587221,
"brier_score": 0.5467664666024626,
"ece_15": 0.48724005573840085,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/horoscope": {
"count": 16,
"accuracy": 0.5625,
"log_loss": 0.70312389399091,
"brier_score": 0.5091651624818514,
"ece_15": 0.10277775046397664,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hlgd": {
"count": 18,
"accuracy": 0.6666666666666666,
"log_loss": 0.665548193664473,
"brier_score": 0.459200508879798,
"ece_15": 0.19218950828833686,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/paws/labeled_swap": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.47379592260540593,
"brier_score": 0.29994824552097865,
"ece_15": 0.14454836482459182,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/numer_sense": {
"count": 15,
"accuracy": 0.8,
"log_loss": 0.5487459369316212,
"brier_score": 0.36478416406515213,
"ece_15": 0.24484791355395863,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/implicit-hate-stg1": {
"count": 16,
"accuracy": 0.6875,
"log_loss": 0.45532596051155305,
"brier_score": 0.3066070325732828,
"ece_15": 0.15563287814807833,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/EffectiveFeedbackStudentWriting": {
"count": 10,
"accuracy": 0.8,
"log_loss": 0.5593083756911487,
"brier_score": 0.3728686199107414,
"ece_15": 0.19650588370107785,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/phrase_similarity": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.6638284934547569,
"brier_score": 0.4683562540606814,
"ece_15": 0.372191892469806,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_atheism": {
"count": 10,
"accuracy": 0.5,
"log_loss": 0.7712825057315981,
"brier_score": 0.5584408107276222,
"ece_15": 0.19657111926256307,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/airline-sentiment": {
"count": 11,
"accuracy": 0.6363636363636364,
"log_loss": 0.504217406339039,
"brier_score": 0.3403436184092216,
"ece_15": 0.25837740839156303,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/MOH": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5184869174698761,
"brier_score": 0.3384519536101372,
"ece_15": 0.03818929864206088,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sciie": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.739317525450631,
"brier_score": 0.5301462318947524,
"ece_15": 0.3740972458097762,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hate_speech18": {
"count": 17,
"accuracy": 0.8823529411764706,
"log_loss": 0.3055792437907351,
"brier_score": 0.16390553409019631,
"ece_15": 0.11131489439705457,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/racial-bias": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 0.6668270016040504,
"brier_score": 0.4768621467322268,
"ece_15": 0.16915274372880487,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/sst2": {
"count": 9,
"accuracy": 1.0,
"log_loss": 0.13307086083993702,
"brier_score": 0.04123792653245642,
"ece_15": 0.12120467744046365,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/gender-bias": {
"count": 15,
"accuracy": 0.6,
"log_loss": 0.6340322301697444,
"brier_score": 0.44419804227259274,
"ece_15": 0.1629476255627217,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/offensive": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.3479413973594366,
"brier_score": 0.2050944519651372,
"ece_15": 0.2641495187945257,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hate_speech_offensive": {
"count": 18,
"accuracy": 0.8888888888888888,
"log_loss": 0.3248894852475989,
"brier_score": 0.17968244222627072,
"ece_15": 0.20077340451462125,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/twentyquestions": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 0.7419794581550404,
"brier_score": 0.5402742994409466,
"ece_15": 0.2076968861636773,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/sem_eval_2010_task_8": {
"count": 16,
"accuracy": 0.8125,
"log_loss": 0.4168383098254916,
"brier_score": 0.26005519515773223,
"ece_15": 0.19464997819238283,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/financial_phrasebank/sentences_allagree": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.2541730803323668,
"brier_score": 0.12703388344390798,
"ece_15": 0.20992331258846403,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mc_taco": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.5286052625031235,
"brier_score": 0.345736530537952,
"ece_15": 0.19028143098212277,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/super_glue/multirc": {
"count": 8,
"accuracy": 0.5,
"log_loss": 0.7497257850039698,
"brier_score": 0.5525588126457335,
"ece_15": 0.30062444358463974,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/TuringBench": {
"count": 15,
"accuracy": 0.4,
"log_loss": 0.755570140823358,
"brier_score": 0.5599130360453907,
"ece_15": 0.17511077151692198,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/reasoning_1hop": {
"count": 8,
"accuracy": 0.375,
"log_loss": 0.7002876889848436,
"brier_score": 0.507186821840337,
"ece_15": 0.1660644275894566,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/tweet_global_warming": {
"count": 15,
"accuracy": 0.8,
"log_loss": 0.48046953916293555,
"brier_score": 0.30678919869459836,
"ece_15": 0.08317878036201325,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/job": {
"count": 13,
"accuracy": 0.8461538461538461,
"log_loss": 0.4845011136674931,
"brier_score": 0.2922380296429058,
"ece_15": 0.20668850581035178,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/parade": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6116721008417533,
"brier_score": 0.4262192980752779,
"ece_15": 0.37234850254621005,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/usnli": {
"count": 16,
"accuracy": 0.5,
"log_loss": 0.6942498287600838,
"brier_score": 0.5011157867188752,
"ece_15": 0.09139235953725697,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/stac": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.6075320848599852,
"brier_score": 0.43642140096598586,
"ece_15": 0.3123764525706635,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/quarel": {
"count": 22,
"accuracy": 0.6363636363636364,
"log_loss": 0.6705165299568191,
"brier_score": 0.47774899633371637,
"ece_15": 0.08448330542479274,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/sem": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.3028548623319954,
"brier_score": 0.17471542514637128,
"ece_15": 0.15350588550710553,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/hate-speech": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6807910535063487,
"brier_score": 0.4781335908625496,
"ece_15": 0.2713823688645954,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/economic-news": {
"count": 20,
"accuracy": 0.75,
"log_loss": 0.5695123143105041,
"brier_score": 0.3859877059568563,
"ece_15": 0.10402211902773444,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/liar": {
"count": 10,
"accuracy": 0.5,
"log_loss": 0.6719751854867054,
"brier_score": 0.4797907271676448,
"ece_15": 0.2054697944539603,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scruples": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5358296051036985,
"brier_score": 0.36056924979934973,
"ece_15": 0.16934656436484802,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/open_question_type": {
"count": 14,
"accuracy": 0.8571428571428571,
"log_loss": 0.48088832706134627,
"brier_score": 0.3084783132314986,
"ece_15": 0.20295393910421425,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/emoji": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.6960605920906769,
"brier_score": 0.4981118938561514,
"ece_15": 0.3050876474074211,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/wiki_qa": {
"count": 16,
"accuracy": 1.0,
"log_loss": 0.07824049212788226,
"brier_score": 0.021876355194432068,
"ece_15": 0.07166085390505572,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/natural-language-satisfiability": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.6065755987974197,
"brier_score": 0.4142264368460539,
"ece_15": 0.26288215715344726,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/CONDAQA": {
"count": 17,
"accuracy": 0.6470588235294118,
"log_loss": 0.5837376367623567,
"brier_score": 0.4017227845941354,
"ece_15": 0.23452599065352353,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/language-identification": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.45379567540134363,
"brier_score": 0.2932768026204425,
"ece_15": 0.18667756246177625,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/vitaminc/tals--vitaminc": {
"count": 18,
"accuracy": 0.8333333333333334,
"log_loss": 0.47203846596688986,
"brier_score": 0.297187389628483,
"ece_15": 0.0878862234493985,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/irony": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5515458134943322,
"brier_score": 0.36624592117848087,
"ece_15": 0.2885674774751862,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/blog_authorship_corpus/gender": {
"count": 11,
"accuracy": 0.7272727272727273,
"log_loss": 0.6122869423340265,
"brier_score": 0.4208829038736505,
"ece_15": 0.16182430406149323,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/mrda": {
"count": 17,
"accuracy": 0.7647058823529411,
"log_loss": 0.6856584872938489,
"brier_score": 0.4527214858038554,
"ece_15": 0.2619543427574546,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/VUAC": {
"count": 18,
"accuracy": 0.6666666666666666,
"log_loss": 0.6458246720007003,
"brier_score": 0.45230615062560264,
"ece_15": 0.05141111909454679,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/amazon_polarity/amazon_polarity": {
"count": 15,
"accuracy": 0.9333333333333333,
"log_loss": 0.12440397615807373,
"brier_score": 0.06418420580476111,
"ece_15": 0.10147991404532762,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/logical-fallacy": {
"count": 20,
"accuracy": 0.65,
"log_loss": 0.6174449749719677,
"brier_score": 0.42561461216146634,
"ece_15": 0.16475898322491966,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/cognitive-bias": {
"count": 19,
"accuracy": 0.5789473684210527,
"log_loss": 0.6811803427938817,
"brier_score": 0.4877731123629733,
"ece_15": 0.09707078374896291,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ambient": {
"count": 13,
"accuracy": 0.5384615384615384,
"log_loss": 1.050939217577183,
"brier_score": 0.7093245442917232,
"ece_15": 0.47989727258855513,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/oasis": {
"count": 15,
"accuracy": 0.6666666666666666,
"log_loss": 0.6027792104843198,
"brier_score": 0.41900378992981374,
"ece_15": 0.1381713707335758,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/linguistic-bias": {
"count": 17,
"accuracy": 0.7058823529411765,
"log_loss": 0.6363254560348328,
"brier_score": 0.4436806488028217,
"ece_15": 0.2834689949984072,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/PARARULE-Plus": {
"count": 14,
"accuracy": 1.0,
"log_loss": 0.009673455202396824,
"brier_score": 0.0003681445782566941,
"ece_15": 0.009579687906687744,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/gum": {
"count": 13,
"accuracy": 0.46153846153846156,
"log_loss": 0.767310153459787,
"brier_score": 0.5644133418636972,
"ece_15": 0.22708194869411405,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/switchboard": {
"count": 12,
"accuracy": 0.6666666666666666,
"log_loss": 0.40478602623769727,
"brier_score": 0.25692537989150854,
"ece_15": 0.2267872271489166,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/verifiability": {
"count": 17,
"accuracy": 1.0,
"log_loss": 0.23518077760555234,
"brier_score": 0.09756131460038968,
"ece_15": 0.20506767586415756,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/spartqa-yn": {
"count": 9,
"accuracy": 0.6666666666666666,
"log_loss": 0.5676751197048884,
"brier_score": 0.38533629695032,
"ece_15": 0.13912224681162666,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/pragmeval/emergent": {
"count": 12,
"accuracy": 0.5,
"log_loss": 0.6111088725023022,
"brier_score": 0.4290625309158527,
"ece_15": 0.31663531554368235,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/emo/emo2019": {
"count": 9,
"accuracy": 0.8888888888888888,
"log_loss": 0.42614535757080696,
"brier_score": 0.2503727442041888,
"ece_15": 0.23545003274854517,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/mrpc": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6378576657757951,
"brier_score": 0.44652269763177543,
"ece_15": 0.14463994537525376,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/I2D2": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.5054673132064631,
"brier_score": 0.33029559589126845,
"ece_15": 0.09966654246438969,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_hillary": {
"count": 9,
"accuracy": 0.4444444444444444,
"log_loss": 0.8658022715769922,
"brier_score": 0.6474565692275834,
"ece_15": 0.29779621458669236,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/political-bias": {
"count": 22,
"accuracy": 0.6818181818181818,
"log_loss": 0.6335086946180227,
"brier_score": 0.44177940486849887,
"ece_15": 0.0823299365370308,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/insincere-questions": {
"count": 12,
"accuracy": 1.0,
"log_loss": 0.08262838482918003,
"brier_score": 0.01685672667749119,
"ece_15": 0.07796318727667327,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/discovery/discovery": {
"count": 18,
"accuracy": 0.6111111111111112,
"log_loss": 0.604818229646948,
"brier_score": 0.41748359341081676,
"ece_15": 0.1119937267120168,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/justice": {
"count": 12,
"accuracy": 0.4166666666666667,
"log_loss": 0.7692328606429664,
"brier_score": 0.5740434104662295,
"ece_15": 0.27459737711342325,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/cola": {
"count": 5,
"accuracy": 1.0,
"log_loss": 0.4554031251730509,
"brier_score": 0.26898307875387517,
"ece_15": 0.36456669670412484,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/banking77": {
"count": 17,
"accuracy": 0.9411764705882353,
"log_loss": 0.26310132240224576,
"brier_score": 0.14710494648723688,
"ece_15": 0.1479224266903446,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/cladder": {
"count": 12,
"accuracy": 0.6666666666666666,
"log_loss": 0.6383773535828748,
"brier_score": 0.44573822453017636,
"ece_15": 0.19868288408674398,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/commonsense": {
"count": 15,
"accuracy": 0.4666666666666667,
"log_loss": 0.7222854271704464,
"brier_score": 0.5294455524416476,
"ece_15": 0.1669058650348188,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/scicite": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.4302728752121489,
"brier_score": 0.2737731770623155,
"ece_15": 0.12187626014610493,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/dyda_da": {
"count": 10,
"accuracy": 0.9,
"log_loss": 0.24368784840394295,
"brier_score": 0.14213311052398495,
"ece_15": 0.12499038798163886,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ag_news": {
"count": 15,
"accuracy": 0.8666666666666667,
"log_loss": 0.34417277741508734,
"brier_score": 0.20884121246772364,
"ece_15": 0.14968292141421494,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/maptask": {
"count": 14,
"accuracy": 0.7857142857142857,
"log_loss": 0.576703165188172,
"brier_score": 0.3865996142094653,
"ece_15": 0.21486179026733052,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/dynahate": {
"count": 12,
"accuracy": 0.5,
"log_loss": 0.8023888055892886,
"brier_score": 0.5950265892214276,
"ece_15": 0.34611284147608473,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/probability_words_nli/reasoning_2hop": {
"count": 13,
"accuracy": 0.46153846153846156,
"log_loss": 0.6897876920393469,
"brier_score": 0.496656026620018,
"ece_15": 0.062024000009732703,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/counterfactually-augmented-imdb": {
"count": 10,
"accuracy": 1.0,
"log_loss": 0.03535720124076549,
"brier_score": 0.004582551541392156,
"ece_15": 0.03413162057049359,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweets_hate_speech_detection": {
"count": 18,
"accuracy": 1.0,
"log_loss": 0.11627279465981405,
"brier_score": 0.043156980154768626,
"ece_15": 0.1023424561559228,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethics/deontology": {
"count": 11,
"accuracy": 0.2727272727272727,
"log_loss": 0.8992056796275404,
"brier_score": 0.6966724955226067,
"ece_15": 0.3611926596753911,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/hope_edi/english": {
"count": 10,
"accuracy": 1.0,
"log_loss": 0.025750615328779498,
"brier_score": 0.0015933906032583975,
"ece_15": 0.02534241466376912,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/text-level-bias": {
"count": 12,
"accuracy": 0.75,
"log_loss": 0.645664087173354,
"brier_score": 0.45022585255060155,
"ece_15": 0.2595347474914672,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/paws/labeled_final": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.7152394239930173,
"brier_score": 0.5217685252680689,
"ece_15": 0.23679016783961698,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/avicenna": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.6078684183403206,
"brier_score": 0.4175087172361987,
"ece_15": 0.17735747579387287,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/subjectivity": {
"count": 15,
"accuracy": 0.5333333333333333,
"log_loss": 0.6519663098510241,
"brier_score": 0.4591549547589198,
"ece_15": 0.31788769332366407,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/v1/gen_train234_test2to10": {
"count": 16,
"accuracy": 0.8125,
"log_loss": 0.6188050539540328,
"brier_score": 0.4208129480832215,
"ece_15": 0.23228472415974305,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/folio": {
"count": 8,
"accuracy": 0.875,
"log_loss": 0.2677357935535888,
"brier_score": 0.1448126082478087,
"ece_15": 0.112157406048406,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/text_emotion": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.496909940808505,
"brier_score": 0.33467897383452594,
"ece_15": 0.13903555138204005,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/sentiment_nuclear_power": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.2619316649787558,
"brier_score": 0.10619770027406616,
"ece_15": 0.23043638994354732,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/crowdflower/corporate-messaging": {
"count": 8,
"accuracy": 0.625,
"log_loss": 0.5323242138008609,
"brier_score": 0.3727744578383365,
"ece_15": 0.30640486312610843,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/silicone/meld_s": {
"count": 9,
"accuracy": 0.7777777777777778,
"log_loss": 0.5356984575781174,
"brier_score": 0.3548463671047433,
"ece_15": 0.24604507501044123,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/args_me": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5475327467413906,
"brier_score": 0.3646842886592681,
"ece_15": 0.13029259831640638,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/super_glue/wic": {
"count": 9,
"accuracy": 0.4444444444444444,
"log_loss": 0.7035378312578746,
"brier_score": 0.51191034723418,
"ece_15": 0.23020335772164124,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/glue/qqp": {
"count": 9,
"accuracy": 0.6666666666666666,
"log_loss": 0.47250813086259197,
"brier_score": 0.32133322820796006,
"ece_15": 0.2840312548127259,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/rumoureval_2019/RumourEval2019": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.3720467245852239,
"brier_score": 0.2202019886218846,
"ece_15": 0.2852043573129455,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/mbib-base/fake-news": {
"count": 13,
"accuracy": 0.6923076923076923,
"log_loss": 0.6709572258784231,
"brier_score": 0.4751351390273223,
"ece_15": 0.2365343477443919,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/ethos/binary": {
"count": 10,
"accuracy": 0.7,
"log_loss": 0.43184881082816523,
"brier_score": 0.309938587022881,
"ece_15": 0.2232269241486753,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/tweet_eval/stance_feminist": {
"count": 13,
"accuracy": 0.6153846153846154,
"log_loss": 0.6342819838699137,
"brier_score": 0.4424172212355806,
"ece_15": 0.14458215186956272,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/trec": {
"count": 10,
"accuracy": 0.8,
"log_loss": 0.5161872273300505,
"brier_score": 0.33878326849020457,
"ece_15": 0.1306445247432167,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/zero-shot-label-nli/snips_built_in_intents": {
"count": 4,
"accuracy": 0.5,
"log_loss": 0.7041056924421092,
"brier_score": 0.5439060873890396,
"ece_15": 0.4048079387580852,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/tasksource-instruct-v0": {
"count": 997,
"accuracy": 0.7121364092276831,
"log_loss": 0.6653333170635247,
"brier_score": 0.3952071519663628,
"ece_15": 0.05664073959338466,
"ordinal_mae": 0.3923422177916232,
"ordinal_count": 997
},
"kind/score": {
"count": 997,
"accuracy": 0.7121364092276831,
"log_loss": 0.6653333170635247,
"brier_score": 0.3952071519663628,
"ece_15": 0.05664073959338466,
"ordinal_mae": 0.3923422177916232,
"ordinal_count": 997
},
"task/tasksource/tasksource-instruct-v0/yelp_review_full/yelp_review_full": {
"count": 497,
"accuracy": 0.6841046277665996,
"log_loss": 0.7242680913247214,
"brier_score": 0.42545976597607615,
"ece_15": 0.057978752215053074,
"ordinal_mae": 0.41514169051418587,
"ordinal_count": 497
},
"task/tasksource/tasksource-instruct-v0/tweet_eval/sentiment": {
"count": 500,
"accuracy": 0.74,
"log_loss": 0.6067521514478951,
"brier_score": 0.36513605364070745,
"ece_15": 0.08562278138075635,
"ordinal_mae": 0.36967954190539737,
"ordinal_count": 500
},
"source/nyu-mll/multi_nli": {
"count": 2000,
"accuracy": 0.907,
"log_loss": 0.2676430728353943,
"brier_score": 0.14473967691300926,
"ece_15": 0.04730422129633431,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/nyu-mll/multi_nli/nyu-mll/multi_nli/default": {
"count": 2000,
"accuracy": 0.907,
"log_loss": 0.2676430728353943,
"brier_score": 0.14473967691300926,
"ece_15": 0.04730422129633431,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/facebook/anli": {
"count": 2000,
"accuracy": 0.5785,
"log_loss": 0.9133303232149986,
"brier_score": 0.5611027917633463,
"ece_15": 0.12427056134727293,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/facebook/anli/facebook/anli/plain_text": {
"count": 2000,
"accuracy": 0.5785,
"log_loss": 0.9133303232149986,
"brier_score": 0.5611027917633463,
"ece_15": 0.12427056134727293,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/defeasible-nli": {
"count": 2000,
"accuracy": 0.8745,
"log_loss": 0.29925963680728324,
"brier_score": 0.18316015565997798,
"ece_15": 0.030345176892877232,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/social": {
"count": 1217,
"accuracy": 0.9063270336894002,
"log_loss": 0.2348862683045523,
"brier_score": 0.13656258793990758,
"ece_15": 0.04400942188398399,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/atomic": {
"count": 542,
"accuracy": 0.8173431734317343,
"log_loss": 0.410304647453951,
"brier_score": 0.26318781545244285,
"ece_15": 0.026093150776035075,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/defeasible-nli/tasksource/defeasible-nli/snli": {
"count": 241,
"accuracy": 0.8423236514522822,
"log_loss": 0.37459571024018584,
"brier_score": 0.23848898681272002,
"ece_15": 0.055863559554963346,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/FOL-nli": {
"count": 2000,
"accuracy": 0.834,
"log_loss": 0.425081312444918,
"brier_score": 0.24203185420889972,
"ece_15": 0.04191806881829498,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/FOL-nli/tasksource/FOL-nli/default": {
"count": 2000,
"accuracy": 0.834,
"log_loss": 0.425081312444918,
"brier_score": 0.24203185420889972,
"ece_15": 0.04191806881829498,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/doc-nli": {
"count": 1776,
"accuracy": 0.8693693693693694,
"log_loss": 0.3776345216910134,
"brier_score": 0.20410689079041464,
"ece_15": 0.0721990192199759,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/doc-nli/tasksource/doc-nli/default": {
"count": 1776,
"accuracy": 0.8693693693693694,
"log_loss": 0.3776345216910134,
"brier_score": 0.20410689079041464,
"ece_15": 0.0721990192199759,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/tasksource/bigbench": {
"count": 1896,
"accuracy": 0.7600210970464135,
"log_loss": 0.602894896267623,
"brier_score": 0.30396554743519166,
"ece_15": 0.051980339698730865,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/vitaminc_fact_verification": {
"count": 262,
"accuracy": 0.8625954198473282,
"log_loss": 0.38103699033453386,
"brier_score": 0.2065051915031934,
"ece_15": 0.0698970798648587,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/mnist_ascii": {
"count": 349,
"accuracy": 0.8223495702005731,
"log_loss": 0.6002663987026644,
"brier_score": 0.27309327740513434,
"ece_15": 0.06774433340107733,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cs_algorithms": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.8575062151344007,
"brier_score": 0.4532760049039597,
"ece_15": 0.3781438391405416,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/language_identification": {
"count": 39,
"accuracy": 0.2564102564102564,
"log_loss": 2.1649805091983163,
"brier_score": 0.8619812329717212,
"ece_15": 0.1358268585099441,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/unit_conversion": {
"count": 73,
"accuracy": 0.8493150684931506,
"log_loss": 0.36995943925993446,
"brier_score": 0.1866371071631526,
"ece_15": 0.05945917663230087,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/bbq_lite_json": {
"count": 61,
"accuracy": 0.9836065573770492,
"log_loss": 0.08452322072671453,
"brier_score": 0.039917098456269604,
"ece_15": 0.02783921016342632,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/movie_dialog_same_or_different": {
"count": 197,
"accuracy": 0.7563451776649747,
"log_loss": 0.5080503638241864,
"brier_score": 0.3337124207277505,
"ece_15": 0.08204405870728061,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/fact_checker": {
"count": 34,
"accuracy": 0.8235294117647058,
"log_loss": 0.4767798367145815,
"brier_score": 0.3083461651144789,
"ece_15": 0.14877917479205238,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/social_support": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.8251933250191481,
"brier_score": 0.5548595671266254,
"ece_15": 0.14197386779891208,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/hyperbaton": {
"count": 179,
"accuracy": 1.0,
"log_loss": 0.004903228693345848,
"brier_score": 0.0018520925829598126,
"ece_15": 0.004331813434934797,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/formal_fallacies_syllogisms_negation": {
"count": 70,
"accuracy": 0.7714285714285715,
"log_loss": 0.45451433761223536,
"brier_score": 0.2946976779111536,
"ece_15": 0.11341918148766668,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/contextual_parametric_knowledge_conflicts": {
"count": 72,
"accuracy": 1.0,
"log_loss": 0.0042866319339874,
"brier_score": 0.0005254734725362953,
"ece_15": 0.004144034953844518,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/abstract_narrative_understanding": {
"count": 5,
"accuracy": 0.0,
"log_loss": 2.182878684561412,
"brier_score": 0.9354408520477367,
"ece_15": 0.24853771093466848,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/goal_step_wikihow": {
"count": 34,
"accuracy": 0.7941176470588235,
"log_loss": 0.49479223842360004,
"brier_score": 0.2877662889272723,
"ece_15": 0.16590714907316742,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/real_or_fake_text": {
"count": 47,
"accuracy": 0.3404255319148936,
"log_loss": 1.9372676073860116,
"brier_score": 0.8089350704681822,
"ece_15": 0.16654496730804147,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/symbol_interpretation": {
"count": 5,
"accuracy": 0.0,
"log_loss": 1.702859572644817,
"brier_score": 0.8365272431417929,
"ece_15": 0.2729845705211645,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/arithmetic": {
"count": 74,
"accuracy": 1.0,
"log_loss": 0.0023194179326578098,
"brier_score": 0.00013419920934465068,
"ece_15": 0.002281276141992805,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/timedial": {
"count": 18,
"accuracy": 1.0,
"log_loss": 0.07928157485328463,
"brier_score": 0.034307814118185,
"ece_15": 0.0622587201655115,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/discourse_marker_prediction": {
"count": 4,
"accuracy": 0.0,
"log_loss": 2.4306903551873225,
"brier_score": 0.9289598264151548,
"ece_15": 0.22414781204482565,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/strategyqa": {
"count": 10,
"accuracy": 0.7,
"log_loss": 0.6869369322369993,
"brier_score": 0.4932013000680217,
"ece_15": 0.20385124503140437,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/parsinlu_qa": {
"count": 9,
"accuracy": 0.2222222222222222,
"log_loss": 1.451704763169901,
"brier_score": 0.760643095262711,
"ece_15": 0.21571830832056527,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_deduction": {
"count": 9,
"accuracy": 0.3333333333333333,
"log_loss": 1.221485929293065,
"brier_score": 0.6323103192433218,
"ece_15": 0.1821726581221277,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/elementary_math_qa": {
"count": 159,
"accuracy": 0.3836477987421384,
"log_loss": 1.3876589979872005,
"brier_score": 0.6968919950560583,
"ece_15": 0.09392527333242497,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/tracking_shuffled_objects": {
"count": 20,
"accuracy": 0.25,
"log_loss": 1.6349046079611906,
"brier_score": 0.8099753150778438,
"ece_15": 0.21079594187432807,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/snarks": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.6706533963836379,
"brier_score": 0.47751007423155717,
"ece_15": 0.48862566154038467,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/color": {
"count": 18,
"accuracy": 0.3333333333333333,
"log_loss": 1.7783889808890854,
"brier_score": 0.7970015392145402,
"ece_15": 0.1187786881257698,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/play_dialog_same_or_different": {
"count": 13,
"accuracy": 0.7692307692307693,
"log_loss": 0.5788119394124831,
"brier_score": 0.3900014955595719,
"ece_15": 0.18119994447526416,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/indic_cause_and_effect": {
"count": 2,
"accuracy": 0.0,
"log_loss": 0.8312477787808272,
"brier_score": 0.6358515687361226,
"ece_15": 0.5616070340233159,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logic_grid_puzzle": {
"count": 10,
"accuracy": 0.5,
"log_loss": 1.0919949027727796,
"brier_score": 0.5934883790906896,
"ece_15": 0.2704396563566979,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/sports_understanding": {
"count": 4,
"accuracy": 0.0,
"log_loss": 0.7269933870476967,
"brier_score": 0.5337326190175753,
"ece_15": 0.5161231174582996,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/fantasy_reasoning": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.5214277745228033,
"brier_score": 0.3419025017278519,
"ece_15": 0.39183793332375344,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/question_selection": {
"count": 7,
"accuracy": 1.0,
"log_loss": 0.19811367912696262,
"brier_score": 0.06229089079281506,
"ece_15": 0.16586570675181198,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/code_line_description": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.36158380919531635,
"brier_score": 0.12343516415240563,
"ece_15": 0.30342778552770255,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/kanji_ascii": {
"count": 2,
"accuracy": 0.5,
"log_loss": 1.4074804405969101,
"brier_score": 0.6997439808808856,
"ece_15": 0.45538844816565466,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/analogical_similarity": {
"count": 2,
"accuracy": 0.0,
"log_loss": 2.3086273693996944,
"brier_score": 0.948241005725639,
"ece_15": 0.1860990001165002,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/winowhy": {
"count": 11,
"accuracy": 0.8181818181818182,
"log_loss": 0.42986333340721655,
"brier_score": 0.26663166172968483,
"ece_15": 0.32416977772655126,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/salient_translation_error_detection": {
"count": 3,
"accuracy": 0.3333333333333333,
"log_loss": 1.8902870767525537,
"brier_score": 0.8617747844320157,
"ece_15": 0.2633205079199103,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/rhyming": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.23330346438826027,
"brier_score": 0.0696860547200071,
"ece_15": 0.20505438771128126,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/movie_recommendation": {
"count": 3,
"accuracy": 1.0,
"log_loss": 0.26687648197103836,
"brier_score": 0.10742139218011508,
"ece_15": 0.2183625085602264,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/analytic_entailment": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.35013435893296785,
"brier_score": 0.18017772919742275,
"ece_15": 0.2919846820851146,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_fallacy_detection": {
"count": 7,
"accuracy": 0.7142857142857143,
"log_loss": 0.6406785108889849,
"brier_score": 0.4129053998268808,
"ece_15": 0.18843710231941754,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/temporal_sequences": {
"count": 3,
"accuracy": 1.0,
"log_loss": 0.07794021767803416,
"brier_score": 0.01268107216367032,
"ece_15": 0.07355045308205117,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/kannada": {
"count": 3,
"accuracy": 0.3333333333333333,
"log_loss": 1.3006808984223028,
"brier_score": 0.7120416307206603,
"ece_15": 0.24751795970738236,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/navigate": {
"count": 2,
"accuracy": 0.5,
"log_loss": 0.7477827162954784,
"brier_score": 0.5543502814305443,
"ece_15": 0.5254655042868934,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/social_iqa": {
"count": 6,
"accuracy": 0.8333333333333334,
"log_loss": 0.4710002326713407,
"brier_score": 0.24511733914828068,
"ece_15": 0.31748993112750223,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/implicatures": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.29114841850337103,
"brier_score": 0.1848048112365155,
"ece_15": 0.22521257977661313,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/penguins_in_a_table": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.8681423074955834,
"brier_score": 0.9430615120285668,
"ece_15": 0.3352266991055912,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/epistemic_reasoning": {
"count": 8,
"accuracy": 1.0,
"log_loss": 0.11367371724241075,
"brier_score": 0.032920414619740636,
"ece_15": 0.10397969315830892,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/reasoning_about_colored_objects": {
"count": 5,
"accuracy": 0.6,
"log_loss": 1.3896145496587025,
"brier_score": 0.22839843219080186,
"ece_15": 0.03217754574682143,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/strange_stories": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.7882933324627114,
"brier_score": 0.594878647792511,
"ece_15": 0.5453799812023316,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/what_is_the_tao": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.8389522505125051,
"brier_score": 0.644877524180415,
"ece_15": 0.5678369150471,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/international_phonetic_alphabet_nli": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.3104032474546674,
"brier_score": 0.7900247964738226,
"ece_15": 0.4155741342002613,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/hindu_knowledge": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.7721442631822523,
"brier_score": 0.3961432110812999,
"ece_15": 0.5379786898887589,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cryobiology_spanish": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.250356414371715,
"brier_score": 0.09810389561034243,
"ece_15": 0.22147674326026023,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/intent_recognition": {
"count": 4,
"accuracy": 1.0,
"log_loss": 0.2597150154532919,
"brier_score": 0.10887130602372279,
"ece_15": 0.18532926980517667,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/metaphor_boolean": {
"count": 2,
"accuracy": 1.0,
"log_loss": 0.20662987494224797,
"brier_score": 0.08727285038621402,
"ece_15": 0.17974473959147763,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/suicide_risk": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.3264746679558475,
"brier_score": 0.7232677834141499,
"ece_15": 0.2906997711235214,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/logical_args": {
"count": 1,
"accuracy": 1.0,
"log_loss": 1.1110180549275812,
"brier_score": 0.5793923955231951,
"ece_15": 0.6707763773236444,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/ruin_names": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.5341818824557079,
"brier_score": 0.8525589486207359,
"ece_15": 0.4077467459606056,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/causal_judgment": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.832508254593555,
"brier_score": 0.638547332378019,
"ece_15": 0.5650430657826088,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/english_proverbs": {
"count": 1,
"accuracy": 0.0,
"log_loss": 2.781201698586805,
"brier_score": 1.5820386121155834,
"ece_15": 0.8338373784186494,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/empirical_judgments": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.307122276207722,
"brier_score": 0.8484497113675799,
"ece_15": 0.5234588750535261,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/physical_intuition": {
"count": 2,
"accuracy": 0.5,
"log_loss": 1.1893217893074914,
"brier_score": 0.6509848835545445,
"ece_15": 0.46917544098255437,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/similarities_abstraction": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.6525461359947428,
"brier_score": 0.3729023778458806,
"ece_15": 0.47928173205594216,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/swahili_english_proverbs": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.7400190729452648,
"brier_score": 0.3898876550220091,
"ece_15": 0.5228951843597804,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/date_understanding": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.17162464733203386,
"brier_score": 0.03664889324545113,
"ece_15": 0.15770472838199245,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/medical_questions_russian": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.42450806234604666,
"brier_score": 0.23930541087430027,
"ece_15": 0.34590852177584486,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/anachronisms": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.832508254593555,
"brier_score": 0.638547332378019,
"ece_15": 0.5650430657826088,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/simple_ethical_questions": {
"count": 2,
"accuracy": 0.0,
"log_loss": 1.3579175779081794,
"brier_score": 0.8773437550179706,
"ece_15": 0.567649431212691,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/dark_humor_detection": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.4879816784771691,
"brier_score": 0.2982018358548382,
"ece_15": 0.38613588013472555,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/irony_identification": {
"count": 2,
"accuracy": 0.0,
"log_loss": 0.9167286611010234,
"brier_score": 0.7197503784706804,
"ece_15": 0.5993355757900248,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/geometric_shapes": {
"count": 2,
"accuracy": 0.0,
"log_loss": 2.4355956963191123,
"brier_score": 0.6772767270890805,
"ece_15": 0.1439518167239653,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/cause_and_effect": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.1293535690995136,
"brier_score": 0.029445217467256986,
"ece_15": 0.12133675755363049,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/moral_permissibility": {
"count": 1,
"accuracy": 0.0,
"log_loss": 0.7759487385429391,
"brier_score": 0.5826236366569683,
"ece_15": 0.5397330991596533,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/phrase_relatedness": {
"count": 1,
"accuracy": 0.0,
"log_loss": 1.0318610171233211,
"brier_score": 0.7033854687035427,
"ece_15": 0.5306299056956488,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/crass_ai": {
"count": 1,
"accuracy": 1.0,
"log_loss": 0.5795727772062687,
"brier_score": 0.28276648319040115,
"ece_15": 0.43986238098681774,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/tasksource/bigbench/tasksource/bigbench/figure_of_speech_detection": {
"count": 1,
"accuracy": 1.0,
"log_loss": 1.538657543538069,
"brier_score": 0.7019273087810161,
"ece_15": 0.7853309080139531,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/Rowan/hellaswag": {
"count": 2000,
"accuracy": 0.86,
"log_loss": 0.3611882300149126,
"brier_score": 0.19594949629069483,
"ece_15": 0.022342067811566196,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/Rowan/hellaswag/Rowan/hellaswag/default": {
"count": 2000,
"accuracy": 0.86,
"log_loss": 0.3611882300149126,
"brier_score": 0.19594949629069483,
"ece_15": 0.022342067811566196,
"ordinal_mae": null,
"ordinal_count": 0
},
"source/google/boolq": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.32001524053340347,
"brier_score": 0.19621992616078116,
"ece_15": 0.03950134207516404,
"ordinal_mae": null,
"ordinal_count": 0
},
"kind/noul": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.32001524053340347,
"brier_score": 0.19621992616078116,
"ece_15": 0.03950134207516404,
"ordinal_mae": null,
"ordinal_count": 0
},
"task/google/boolq/google/boolq/default": {
"count": 828,
"accuracy": 0.8599033816425121,
"log_loss": 0.32001524053340347,
"brier_score": 0.19621992616078116,
"ece_15": 0.03950134207516404,
"ordinal_mae": null,
"ordinal_count": 0
}
},
"temperature": 1.3734692667114208,
"data_sha256": "8442fc4dbeb740baab4603a0ebc079f5fa53474e7b5bba9b4f82a206d5a65dc7",
"checkpoint": "/workspace/kev-run/runs/train-20260924-185636/final",
"notes": "Accuracy accepts any positive target. ECE uses gold probability mass, not any-positive accuracy. Ordinal MAE uses zero-based level indices."
}