task,metric,value,err,version anli_r1,acc,0.318,0.014734079309311903,0 anli_r2,acc,0.344,0.015029633724408947,0 anli_r3,acc,0.30916666666666665,0.013346684134591958,0 arc_challenge,acc,0.22696245733788395,0.01224049153613287,0 arc_challenge,acc_norm,0.2568259385665529,0.0127669237941168,0 arc_easy,acc,0.5488215488215489,0.010210757101073475,0 arc_easy,acc_norm,0.5244107744107744,0.010247548905242272,0 boolq,acc,0.5596330275229358,0.0086826356676869,1 cb,acc,0.5,0.06741998624632421,1 cb,f1,0.3583652618135376,,1 copa,acc,0.7,0.046056618647183814,0 hellaswag,acc,0.36436964748058154,0.004802694106203663,0 hellaswag,acc_norm,0.44901414060944034,0.004963771168672096,0 piqa,acc,0.7023939064200218,0.010667353792388213,0 piqa,acc_norm,0.6991294885745375,0.010700745724145972,0 rte,acc,0.48375451263537905,0.030080573208738064,0 sciq,acc,0.886,0.010055103435823328,0 sciq,acc_norm,0.876,0.010427498872343966,0 storycloze_2016,acc,0.6365579903794762,0.01112284144205971,0 winogrande,acc,0.5209155485398579,0.014040185494212943,0