| task,metric,value,err,version | |
| anli_r1,acc,0.311,0.014645596385722692,0 | |
| anli_r2,acc,0.356,0.015149042659306626,0 | |
| anli_r3,acc,0.3425,0.013704669762934727,0 | |
| arc_challenge,acc,0.2960750853242321,0.013340916085246258,0 | |
| arc_challenge,acc_norm,0.3122866894197952,0.013542598541688065,0 | |
| arc_easy,acc,0.6292087542087542,0.009911292822056921,0 | |
| arc_easy,acc_norm,0.6153198653198653,0.009983171707008999,0 | |
| boolq,acc,0.6103975535168196,0.008529228894936293,1 | |
| cb,acc,0.5535714285714286,0.06703189227942397,1 | |
| cb,f1,0.49967511371020135,,1 | |
| copa,acc,0.79,0.040936018074033256,0 | |
| hellaswag,acc,0.4714200358494324,0.004981623292196191,0 | |
| hellaswag,acc_norm,0.6261700856403107,0.004828305041904401,0 | |
| piqa,acc,0.7578890097932536,0.009994371269104376,0 | |
| piqa,acc_norm,0.764417845484222,0.009901067586473886,0 | |
| rte,acc,0.5342960288808665,0.03002557981936643,0 | |
| sciq,acc,0.911,0.009008893392651535,0 | |
| sciq,acc_norm,0.892,0.009820001651345693,0 | |
| storycloze_2016,acc,0.729021913415286,0.010278188399635043,0 | |
| winogrande,acc,0.6006314127861089,0.013764933546717612,0 | |