task,metric,value,err,version
anli_r1,acc,0.319,0.014746404865473486,0
anli_r2,acc,0.33,0.01487687202745673,0
anli_r3,acc,0.32,0.013471620929769142,0
arc_challenge,acc,0.33276450511945393,0.01376986304619231,0
arc_challenge,acc_norm,0.3643344709897611,0.014063260279882415,0
arc_easy,acc,0.6784511784511784,0.00958409157564062,0
arc_easy,acc_norm,0.6607744107744108,0.00971491720776585,0
boolq,acc,0.6590214067278287,0.00829097981816109,1
cb,acc,0.42857142857142855,0.06672848092813058,1
cb,f1,0.3049446887911502,,1
copa,acc,0.82,0.038612291966536955,0
hellaswag,acc,0.5259908384783908,0.004983035420235712,0
hellaswag,acc_norm,0.7002589125672177,0.004572081656965643,0
piqa,acc,0.7780195865070729,0.009696120744662019,0
piqa,acc_norm,0.7872687704026116,0.009548223123047352,0
rte,acc,0.5812274368231047,0.02969666108123484,0
sciq,acc,0.93,0.008072494358323499,0
sciq,acc_norm,0.91,0.009054390204866442,0
storycloze_2016,acc,0.7616247995724211,0.009853267441685421,0
winogrande,acc,0.6266771902131019,0.013594002763035516,0