| task,metric,value,err,version | |
| anli_r1,acc,0.315,0.014696631960792508,0 | |
| anli_r2,acc,0.341,0.014998131348402699,0 | |
| anli_r3,acc,0.3275,0.013553211167251951,0 | |
| arc_challenge,acc,0.2235494880546075,0.012174896631202607,0 | |
| arc_challenge,acc_norm,0.257679180887372,0.012780770562768412,0 | |
| arc_easy,acc,0.5488215488215489,0.010210757101073475,0 | |
| arc_easy,acc_norm,0.5298821548821548,0.010241444322886432,0 | |
| boolq,acc,0.5474006116207951,0.008705669190431184,1 | |
| cb,acc,0.5714285714285714,0.06672848092813058,1 | |
| cb,f1,0.5046621652657205,,1 | |
| copa,acc,0.75,0.04351941398892446,0 | |
| hellaswag,acc,0.3670583549093806,0.004810175357871104,0 | |
| hellaswag,acc_norm,0.44682334196375223,0.004961481380023777,0 | |
| piqa,acc,0.7002176278563657,0.01068968696713809,0 | |
| piqa,acc_norm,0.6969532100108814,0.010722648689531501,0 | |
| rte,acc,0.49097472924187724,0.030091559826331334,0 | |
| sciq,acc,0.875,0.010463483381956722,0 | |
| sciq,acc_norm,0.875,0.010463483381956722,0 | |
| storycloze_2016,acc,0.6445750935328701,0.01106852845239988,0 | |
| winogrande,acc,0.5335438042620363,0.014020826677598101,0 | |