task,metric,value,err,version
anli_r1,acc,0.345,0.015039986742055235,0
anli_r2,acc,0.362,0.015204840912919501,0
anli_r3,acc,0.31583333333333335,0.013424568830356443,0
arc_challenge,acc,0.24744027303754265,0.012610352663292673,0
arc_challenge,acc_norm,0.25170648464163825,0.012682496334042963,0
arc_easy,acc,0.4739057239057239,0.01024580199024005,0
arc_easy,acc_norm,0.4494949494949495,0.010207308833916035,0
boolq,acc,0.5064220183486239,0.00874433361394033,1
cb,acc,0.5,0.06741998624632421,1
cb,f1,0.3176319176319176,,1
copa,acc,0.67,0.04725815626252609,0
hellaswag,acc,0.376319458275244,0.004834715814208109,0
hellaswag,acc_norm,0.45140410276837284,0.004966158142645416,0
piqa,acc,0.6670293797606094,0.010995648822619067,0
piqa,acc_norm,0.676278563656148,0.010916765010708767,0
rte,acc,0.5270758122743683,0.030052303463143706,0
sciq,acc,0.708,0.014385511563477343,0
sciq,acc_norm,0.689,0.014645596385722694,0
storycloze_2016,acc,0.6392303580972741,0.011105110530046359,0
winogrande,acc,0.489344909234412,0.014049294536290403,0