task,metric,value,err,version anli_r1,acc,0.34,0.014987482264363937,0 anli_r2,acc,0.321,0.014770821817934644,0 anli_r3,acc,0.34,0.013680495725767803,0 arc_challenge,acc,0.29266211604095566,0.013295916103619417,0 arc_challenge,acc_norm,0.32337883959044367,0.013669421630012132,0 arc_easy,acc,0.6262626262626263,0.009927267058259628,0 arc_easy,acc_norm,0.5917508417508418,0.01008556619579125,0 boolq,acc,0.5948012232415902,0.008586427929715515,1 cb,acc,0.375,0.06527912098338669,1 cb,f1,0.32099491681373216,,1 copa,acc,0.77,0.04229525846816506,0 hellaswag,acc,0.48078072097191793,0.004986093791041653,0 hellaswag,acc_norm,0.6337382991435969,0.004807975515446487,0 piqa,acc,0.7622415669205659,0.009932525779525489,0 piqa,acc_norm,0.763873775843308,0.009908965890558218,0 rte,acc,0.5740072202166066,0.029764956741777645,0 sciq,acc,0.904,0.009320454434783227,0 sciq,acc_norm,0.885,0.01009340759490462,0 storycloze_2016,acc,0.7204703367183325,0.01037770209970486,0 winogrande,acc,0.590370955011839,0.013821049109655453,0