task,metric,value,err,version
anli_r1,acc,0.323,0.014794927843348635,0
anli_r2,acc,0.346,0.015050266127564443,0
anli_r3,acc,0.3458333333333333,0.013736245342311012,0
arc_challenge,acc,0.3225255972696246,0.013659980894277378,0
arc_challenge,acc_norm,0.3447098976109215,0.01388881628678211,0
arc_easy,acc,0.6679292929292929,0.009663817543072703,0
arc_easy,acc_norm,0.5829124579124579,0.010117738967781993,0
boolq,acc,0.6470948012232416,0.008358060743875672,1
cb,acc,0.4642857142857143,0.06724777654937658,1
cb,f1,0.28451178451178455,,1
copa,acc,0.81,0.03942772444036622,0
hellaswag,acc,0.5323640709022107,0.004979317515432525,0
hellaswag,acc_norm,0.7071300537741486,0.004541492151639238,0
piqa,acc,0.7747551686615887,0.009746643471032155,0
piqa,acc_norm,0.7867247007616975,0.009557121225861342,0
rte,acc,0.5848375451263538,0.029660066290893485,0
sciq,acc,0.894,0.009739551265785138,0
sciq,acc_norm,0.82,0.012155153135511965,0
storycloze_2016,acc,0.7498663816141101,0.010015143382536456,0
winogrande,acc,0.6377269139700079,0.01350885547625251,0