task,metric,value,err,version
anli_r1,acc,0.312,0.014658474370509007,0
anli_r2,acc,0.342,0.01500870618212173,0
anli_r3,acc,0.32166666666666666,0.013490095282989521,0
arc_challenge,acc,0.2235494880546075,0.012174896631202607,0
arc_challenge,acc_norm,0.26023890784982934,0.012821930225112556,0
arc_easy,acc,0.5475589225589226,0.01021326586017139,0
arc_easy,acc_norm,0.5256734006734006,0.010246249665591229,0
boolq,acc,0.5256880733944954,0.008733506027183658,1
cb,acc,0.42857142857142855,0.06672848092813058,1
cb,f1,0.3971014492753624,,1
copa,acc,0.72,0.04512608598542127,0
hellaswag,acc,0.3690499900418243,0.0048156131443854,0
hellaswag,acc_norm,0.4477195777733519,0.004962429881904027,0
piqa,acc,0.7034820457018498,0.010656078922661153,0
piqa,acc_norm,0.7029379760609358,0.010661725404814778,0
rte,acc,0.47653429602888087,0.03006330041190266,0
sciq,acc,0.89,0.009899393819724444,0
sciq,acc_norm,0.889,0.009938701010583726,0
storycloze_2016,acc,0.6413682522715125,0.011090657465688191,0
winogrande,acc,0.5438042620363063,0.013998453610924324,0