task,metric,value,err,version anli_r1,acc,0.36,0.015186527932040117,0 anli_r2,acc,0.347,0.015060472031706625,0 anli_r3,acc,0.3625,0.01388303787422552,0 arc_challenge,acc,0.302901023890785,0.013428241573185349,0 arc_challenge,acc_norm,0.32337883959044367,0.013669421630012129,0 arc_easy,acc,0.640993265993266,0.009843424713072174,0 arc_easy,acc_norm,0.6186868686868687,0.009966542497171025,0 boolq,acc,0.545565749235474,0.008708665643758015,1 cb,acc,0.5535714285714286,0.06703189227942395,1 cb,f1,0.4538378958668814,,1 copa,acc,0.79,0.040936018074033256,0 hellaswag,acc,0.45180242979486157,0.004966544724452227,0 hellaswag,acc_norm,0.5955984863572994,0.004897728370737246,0 piqa,acc,0.7578890097932536,0.009994371269104385,0 piqa,acc_norm,0.7752992383025027,0.009738282586548389,0 rte,acc,0.48375451263537905,0.030080573208738064,0 sciq,acc,0.915,0.008823426366942331,0 sciq,acc_norm,0.912,0.008963053962592085,0 storycloze_2016,acc,0.7177979690005345,0.010407834479647672,0 winogrande,acc,0.5706393054459353,0.013911537499969163,0