| task,metric,value,err,version | |
| anli_r1,acc,0.329,0.014865395385928354,0 | |
| anli_r2,acc,0.353,0.015120172605483694,0 | |
| anli_r3,acc,0.3375,0.01365589718546366,0 | |
| arc_challenge,acc,0.22696245733788395,0.012240491536132865,0 | |
| arc_challenge,acc_norm,0.2627986348122867,0.012862523175351333,0 | |
| arc_easy,acc,0.49747474747474746,0.010259652668783474,0 | |
| arc_easy,acc_norm,0.43813131313131315,0.010180937100600078,0 | |
| boolq,acc,0.4923547400611621,0.0087440326197193,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.24617886178861784,,1 | |
| copa,acc,0.7,0.046056618647183814,0 | |
| hellaswag,acc,0.3990240987851026,0.004886969266944278,0 | |
| hellaswag,acc_norm,0.4960167297351125,0.00498962306877881,0 | |
| piqa,acc,0.6953210010881393,0.010738889044325161,0 | |
| piqa,acc_norm,0.7094668117519043,0.010592765034696536,0 | |
| rte,acc,0.48014440433212996,0.0300727231673172,0 | |
| sciq,acc,0.72,0.014205696104091503,0 | |
| sciq,acc_norm,0.627,0.015300493622922814,0 | |
| storycloze_2016,acc,0.6536611437733832,0.011002874026446419,0 | |
| winogrande,acc,0.5169692186266772,0.014044390401612972,0 | |