| task,metric,value,err,version | |
| anli_r1,acc,0.31,0.014632638658632903,0 | |
| anli_r2,acc,0.357,0.015158521721486769,0 | |
| anli_r3,acc,0.3475,0.013751753243291854,0 | |
| arc_challenge,acc,0.3122866894197952,0.013542598541688065,0 | |
| arc_challenge,acc_norm,0.3378839590443686,0.013822047922283516,0 | |
| arc_easy,acc,0.6662457912457912,0.009676065683575473,0 | |
| arc_easy,acc_norm,0.6696127946127947,0.009651430216428194,0 | |
| boolq,acc,0.5278287461773701,0.008731499445069577,1 | |
| cb,acc,0.375,0.06527912098338669,1 | |
| cb,f1,0.33730158730158727,,1 | |
| copa,acc,0.83,0.03775251680686371,0 | |
| hellaswag,acc,0.468034256124278,0.004979573765575858,0 | |
| hellaswag,acc_norm,0.6170085640310695,0.004851227527070881,0 | |
| piqa,acc,0.7568008705114254,0.010009611953858919,0 | |
| piqa,acc_norm,0.7704026115342764,0.009812682950815183,0 | |
| rte,acc,0.5451263537906137,0.029973636495415252,0 | |
| sciq,acc,0.916,0.008776162089491129,0 | |
| sciq,acc_norm,0.921,0.00853415677333344,0 | |
| storycloze_2016,acc,0.7194013896312133,0.010389809647288825,0 | |
| winogrande,acc,0.5974743488555643,0.013782866831703046,0 | |