| task,metric,value,err,version | |
| anli_r1,acc,0.342,0.01500870618212173,0 | |
| anli_r2,acc,0.341,0.014998131348402693,0 | |
| anli_r3,acc,0.3258333333333333,0.013535422043417455,0 | |
| arc_challenge,acc,0.3046075085324232,0.01344952210993249,0 | |
| arc_challenge,acc_norm,0.318259385665529,0.013611993916971451,0 | |
| arc_easy,acc,0.6313131313131313,0.009899640855681043,0 | |
| arc_easy,acc_norm,0.6077441077441077,0.010018744689650043,0 | |
| boolq,acc,0.5712538226299694,0.008655800332760227,1 | |
| cb,acc,0.44642857142857145,0.06703189227942398,1 | |
| cb,f1,0.31446540880503143,,1 | |
| copa,acc,0.83,0.037752516806863715,0 | |
| hellaswag,acc,0.46285600477992433,0.004975993795562032,0 | |
| hellaswag,acc_norm,0.6171081457876917,0.004850988215167544,0 | |
| piqa,acc,0.7399347116430903,0.010234893249061303,0 | |
| piqa,acc_norm,0.7426550598476604,0.01019992106479251,0 | |
| rte,acc,0.555956678700361,0.029907396333795987,0 | |
| sciq,acc,0.885,0.010093407594904628,0 | |
| sciq,acc_norm,0.875,0.010463483381956722,0 | |
| storycloze_2016,acc,0.7129877071084981,0.010460934115933265,0 | |
| winogrande,acc,0.5990528808208366,0.013773974554948028,0 | |