task,metric,value,err,version
anli_r1,acc,0.329,0.014865395385928369,0
anli_r2,acc,0.356,0.015149042659306625,0
anli_r3,acc,0.31666666666666665,0.013434078660827386,0
arc_challenge,acc,0.2380546075085324,0.012445770028026201,0
arc_challenge,acc_norm,0.26621160409556316,0.012915774781523223,0
arc_easy,acc,0.4692760942760943,0.010240395584815239,0
arc_easy,acc_norm,0.4473905723905724,0.010202832385415642,0
boolq,acc,0.5085626911314984,0.008743772513106856,1
cb,acc,0.5535714285714286,0.06703189227942395,1
cb,f1,0.3779862414008755,,1
copa,acc,0.68,0.04688261722621504,0
hellaswag,acc,0.3783110934076877,0.004839746491523513,0
hellaswag,acc_norm,0.45130452101175067,0.004966060995315058,0
piqa,acc,0.691512513601741,0.01077616467803716,0
piqa,acc_norm,0.6860718171926007,0.01082792813418964,0
rte,acc,0.49458483754512633,0.030094698123239966,0
sciq,acc,0.715,0.014282120955200485,0
sciq,acc_norm,0.687,0.01467127282297789,0
storycloze_2016,acc,0.6386958845537146,0.011108686479432282,0
winogrande,acc,0.49171270718232046,0.014050555322824194,0