| task,metric,value,err,version | |
| anli_r1,acc,0.348,0.015070604603768408,0 | |
| anli_r2,acc,0.338,0.01496596071022449,0 | |
| anli_r3,acc,0.33666666666666667,0.013647602942406406,0 | |
| arc_challenge,acc,0.22781569965870307,0.01225670860232691,0 | |
| arc_challenge,acc_norm,0.25597269624573377,0.01275301324124451,0 | |
| arc_easy,acc,0.5252525252525253,0.01024669004258386,0 | |
| arc_easy,acc_norm,0.5105218855218855,0.010257511546488227,0 | |
| boolq,acc,0.5024464831804282,0.008744950292567371,1 | |
| cb,acc,0.5178571428571429,0.06737697508644648,1 | |
| cb,f1,0.35883040935672517,,1 | |
| copa,acc,0.69,0.04648231987117316,0 | |
| hellaswag,acc,0.35371439952200756,0.004771447244095127,0 | |
| hellaswag,acc_norm,0.43845847440748853,0.004951840978219677,0 | |
| piqa,acc,0.6898803046789989,0.01079187656684305,0 | |
| piqa,acc_norm,0.6877040261153428,0.010812581599154424,0 | |
| rte,acc,0.49458483754512633,0.030094698123239966,0 | |
| sciq,acc,0.897,0.009616833339695796,0 | |
| sciq,acc_norm,0.887,0.010016552866696863,0 | |
| storycloze_2016,acc,0.6264029930518439,0.011186849693644696,0 | |
| winogrande,acc,0.5193370165745856,0.014041972733712974,0 | |