task,metric,value,err,version anli_r1,acc,0.32,0.014758652303574888,0 anli_r2,acc,0.341,0.0149981313484027,0 anli_r3,acc,0.3308333333333333,0.013588208070708992,0 arc_challenge,acc,0.3054607508532423,0.013460080478002496,0 arc_challenge,acc_norm,0.33447098976109213,0.013787460322441375,0 arc_easy,acc,0.640993265993266,0.009843424713072176,0 arc_easy,acc_norm,0.6233164983164983,0.009942848077476165,0 boolq,acc,0.6226299694189602,0.008477957863309996,1 cb,acc,0.3392857142857143,0.06384226561930825,1 cb,f1,0.18571428571428572,,1 copa,acc,0.84,0.0368452949177471,0 hellaswag,acc,0.4788886675960964,0.004985331652408344,0 hellaswag,acc_norm,0.6372236606253734,0.0047981844631563575,0 piqa,acc,0.7546245919477693,0.010039831320422398,0 piqa,acc_norm,0.7709466811751904,0.009804509865175505,0 rte,acc,0.51985559566787,0.030072723167317177,0 sciq,acc,0.915,0.00882342636694232,0 sciq,acc_norm,0.906,0.009233052000787736,0 storycloze_2016,acc,0.7300908605024051,0.010265413503221462,0 winogrande,acc,0.6227308602999211,0.013622567928799501,0