task,metric,value,err,version
anli_r1,acc,0.357,0.015158521721486774,0
anli_r2,acc,0.334,0.014922019523732967,0
anli_r3,acc,0.37416666666666665,0.01397501560175897,0
arc_challenge,acc,0.2568259385665529,0.0127669237941168,0
arc_challenge,acc_norm,0.31399317406143346,0.013562691224726297,0
arc_easy,acc,0.5307239057239057,0.010240395584815237,0
arc_easy,acc_norm,0.5084175084175084,0.010258329515226462,0
boolq,acc,0.517125382262997,0.008739923994130054,1
cb,acc,0.39285714285714285,0.0658538889806635,1
cb,f1,0.26788664379209554,,1
copa,acc,0.75,0.04351941398892446,0
hellaswag,acc,0.45339573790081655,0.004968058944472161,0
hellaswag,acc_norm,0.5857398924517029,0.004915870966174404,0
piqa,acc,0.7399347116430903,0.010234893249061303,0
piqa,acc_norm,0.7328618063112078,0.01032344049261243,0
rte,acc,0.4657039711191336,0.030025579819366422,0
sciq,acc,0.799,0.012679107214617328,0
sciq,acc_norm,0.751,0.0136816002787023,0
storycloze_2016,acc,0.6878674505611972,0.010715220346279681,0
winogrande,acc,0.5509076558800315,0.01397945938914086,0