task,metric,value,err,version anli_r1,acc,0.314,0.014683991951087962,0 anli_r2,acc,0.342,0.015008706182121734,0 anli_r3,acc,0.32416666666666666,0.013517438120881636,0 arc_challenge,acc,0.29180887372013653,0.013284525292403503,0 arc_challenge,acc_norm,0.3046075085324232,0.01344952210993249,0 arc_easy,acc,0.6342592592592593,0.00988298806941883,0 arc_easy,acc_norm,0.6212121212121212,0.00995373765654204,0 boolq,acc,0.599388379204893,0.008570545612096372,1 cb,acc,0.4107142857142857,0.0663363415035954,1 cb,f1,0.37437732746529967,,1 copa,acc,0.79,0.040936018074033256,0 hellaswag,acc,0.4823740290778729,0.004986680048438317,0 hellaswag,acc_norm,0.6320454092810197,0.004812633280078256,0 piqa,acc,0.7600652883569097,0.009963625892809544,0 piqa,acc_norm,0.7633297062023939,0.009916841655042809,0 rte,acc,0.5306859205776173,0.030039730592197812,0 sciq,acc,0.917,0.00872852720607479,0 sciq,acc_norm,0.902,0.009406619184621236,0 storycloze_2016,acc,0.7215392838054516,0.010365521460604417,0 winogrande,acc,0.5887924230465666,0.013829128358676878,0