task,metric,value,err,version
anli_r1,acc,0.334,0.014922019523732977,0
anli_r2,acc,0.351,0.015100563798316407,0
anli_r3,acc,0.32083333333333336,0.013480882752851543,0
arc_challenge,acc,0.3003412969283277,0.013395909309956995,0
arc_challenge,acc_norm,0.3225255972696246,0.013659980894277373,0
arc_easy,acc,0.6258417508417509,0.009929516948977627,0
arc_easy,acc_norm,0.6022727272727273,0.010042861602178058,0
boolq,acc,0.6073394495412844,0.008541161248702913,1
cb,acc,0.42857142857142855,0.06672848092813058,1
cb,f1,0.2943692088382039,,1
copa,acc,0.77,0.04229525846816506,0
hellaswag,acc,0.472814180442143,0.004982400368939667,0
hellaswag,acc_norm,0.6304521011750648,0.00481695881772609,0
piqa,acc,0.7513601741022851,0.010084511234296852,0
piqa,acc_norm,0.7687704026115343,0.009837063180625336,0
rte,acc,0.5415162454873647,0.029992535385373314,0
sciq,acc,0.914,0.008870325962594766,0
sciq,acc_norm,0.901,0.009449248027662734,0
storycloze_2016,acc,0.7188669160876536,0.0103958360916281,0
winogrande,acc,0.5911602209944752,0.0138169542951357,0