| task,metric,value,err,version | |
| anli_r1,acc,0.34,0.014987482264363937,0 | |
| anli_r2,acc,0.326,0.014830507204541028,0 | |
| anli_r3,acc,0.3541666666666667,0.01381193349957096,0 | |
| arc_challenge,acc,0.27474402730375425,0.013044617212771227,0 | |
| arc_challenge,acc_norm,0.3037542662116041,0.01343890918477876,0 | |
| arc_easy,acc,0.5968013468013468,0.010065668576794803,0 | |
| arc_easy,acc_norm,0.5913299663299664,0.01008717449876288,0 | |
| boolq,acc,0.5562691131498471,0.008689501105367413,1 | |
| cb,acc,0.42857142857142855,0.06672848092813058,1 | |
| cb,f1,0.36324786324786323,,1 | |
| copa,acc,0.75,0.04351941398892446,0 | |
| hellaswag,acc,0.4411471818362876,0.004955095096264714,0 | |
| hellaswag,acc_norm,0.5774746066520613,0.004929517011508216,0 | |
| piqa,acc,0.7295973884657236,0.010363167031620784,0 | |
| piqa,acc_norm,0.7334058759521219,0.010316749863541365,0 | |
| rte,acc,0.5234657039711191,0.030063300411902652,0 | |
| sciq,acc,0.887,0.010016552866696846,0 | |
| sciq,acc_norm,0.882,0.01020686926438179,0 | |
| storycloze_2016,acc,0.6830571886691609,0.010759650951452121,0 | |
| winogrande,acc,0.5595895816890292,0.013952330311915603,0 | |