| task,metric,value,err,version | |
| anli_r1,acc,0.341,0.014998131348402695,0 | |
| anli_r2,acc,0.348,0.015070604603768408,0 | |
| anli_r3,acc,0.3408333333333333,0.01368860079329693,0 | |
| arc_challenge,acc,0.3037542662116041,0.01343890918477875,0 | |
| arc_challenge,acc_norm,0.3191126279863481,0.0136216961191733,0 | |
| arc_easy,acc,0.6397306397306397,0.009851002584732383,0 | |
| arc_easy,acc_norm,0.6157407407407407,0.009981120724601436,0 | |
| boolq,acc,0.6116207951070336,0.008524357307908785,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.2506410256410256,,1 | |
| copa,acc,0.83,0.03775251680686371,0 | |
| hellaswag,acc,0.4731129257120096,0.004982561815214125,0 | |
| hellaswag,acc_norm,0.6352320254929297,0.004803812631994968,0 | |
| piqa,acc,0.749183895538629,0.010113869547069044,0 | |
| piqa,acc_norm,0.7600652883569097,0.009963625892809545,0 | |
| rte,acc,0.49458483754512633,0.030094698123239966,0 | |
| sciq,acc,0.921,0.008534156773333438,0 | |
| sciq,acc_norm,0.916,0.008776162089491132,0 | |
| storycloze_2016,acc,0.729021913415286,0.010278188399635048,0 | |
| winogrande,acc,0.595895816890292,0.01379161066467086,0 | |