task,metric,value,err,version
arc_challenge,acc,0.25,0.012653835621466646,0
arc_challenge,acc_norm,0.2841296928327645,0.013179442447653886,0
arc_easy,acc,0.5723905723905723,0.010151683397430677,0
arc_easy,acc_norm,0.5067340067340067,0.010258852980991825,0
boolq,acc,0.590519877675841,0.008600549751320916,1
copa,acc,0.75,0.04351941398892446,0
hellaswag,acc,0.43636725751842265,0.004949207947265915,0
hellaswag,acc_norm,0.5636327424815774,0.004949207947265913,0
piqa,acc,0.7448313384113167,0.010171571592521822,0
piqa,acc_norm,0.7519042437431991,0.010077118315574706,0
rte,acc,0.5451263537906137,0.029973636495415255,0
sciq,acc,0.812,0.012361586015103754,0
sciq,acc_norm,0.727,0.014095022868717584,0
winogrande,acc,0.5509076558800315,0.01397945938914085,0