task,metric,value,err,version
anli_r1,acc,0.323,0.01479492784334864,0
anli_r2,acc,0.35,0.015090650341444233,0
anli_r3,acc,0.3441666666666667,0.013720551062295755,0
arc_challenge,acc,0.2790102389078498,0.013106784883601336,0
arc_challenge,acc_norm,0.3046075085324232,0.01344952210993249,0
arc_easy,acc,0.5989057239057239,0.01005705110653437,0
arc_easy,acc_norm,0.5425084175084175,0.010222638127749496,0
boolq,acc,0.5886850152905199,0.008606395426309208,1
cb,acc,0.3392857142857143,0.06384226561930825,1
cb,f1,0.26343091936312274,,1
copa,acc,0.72,0.04512608598542127,0
hellaswag,acc,0.475502887870942,0.004983788992681198,0
hellaswag,acc_norm,0.6266679944234216,0.004827006520802888,0
piqa,acc,0.7551686615886833,0.010032309105568793,0
piqa,acc_norm,0.763873775843308,0.009908965890558216,0
rte,acc,0.5631768953068592,0.02985524739031495,0
sciq,acc,0.849,0.011328165223341671,0
sciq,acc_norm,0.757,0.013569640199177451,0
storycloze_2016,acc,0.7156600748262961,0.01043161412866525,0
winogrande,acc,0.5761641673243884,0.013888492389944508,0