task,metric,value,err,version anli_r1,acc,0.335,0.014933117490932573,0 anli_r2,acc,0.334,0.014922019523732954,0 anli_r3,acc,0.3425,0.013704669762934727,0 arc_challenge,acc,0.2935153583617747,0.01330725044494113,0 arc_challenge,acc_norm,0.32764505119453924,0.013715847940719346,0 arc_easy,acc,0.6224747474747475,0.009947227833469432,0 arc_easy,acc_norm,0.6047979797979798,0.010031894052790978,0 boolq,acc,0.6048929663608563,0.0085504542482809,1 cb,acc,0.39285714285714285,0.0658538889806635,1 cb,f1,0.258008658008658,,1 copa,acc,0.83,0.03775251680686371,0 hellaswag,acc,0.4801832304321848,0.0049858608534276315,0 hellaswag,acc_norm,0.6342362079267079,0.004806593424942264,0 piqa,acc,0.7546245919477693,0.010039831320422401,0 piqa,acc_norm,0.7622415669205659,0.009932525779525492,0 rte,acc,0.5703971119133574,0.02979666882912467,0 sciq,acc,0.913,0.008916866630745908,0 sciq,acc_norm,0.897,0.009616833339695798,0 storycloze_2016,acc,0.72367717797969,0.010340939873166822,0 winogrande,acc,0.6029992107340174,0.013751092519806702,0