| task,metric,value,err,version | |
| anli_r1,acc,0.315,0.014696631960792487,0 | |
| anli_r2,acc,0.333,0.014910846164229863,0 | |
| anli_r3,acc,0.32666666666666666,0.013544340907003667,0 | |
| arc_challenge,acc,0.3250853242320819,0.013688147309729119,0 | |
| arc_challenge,acc_norm,0.3515358361774744,0.013952413699600938,0 | |
| arc_easy,acc,0.6447811447811448,0.009820245899287117,0 | |
| arc_easy,acc_norm,0.627104377104377,0.009922743197129238,0 | |
| boolq,acc,0.634862385321101,0.008420941009417812,1 | |
| cb,acc,0.39285714285714285,0.0658538889806635,1 | |
| cb,f1,0.3398268398268398,,1 | |
| copa,acc,0.8,0.040201512610368445,0 | |
| hellaswag,acc,0.4982075283808006,0.004989749347461089,0 | |
| hellaswag,acc_norm,0.6702848038239394,0.004691488813032134,0 | |
| piqa,acc,0.763873775843308,0.009908965890558213,0 | |
| piqa,acc_norm,0.7834602829162133,0.009609984714384593,0 | |
| rte,acc,0.5703971119133574,0.02979666882912467,0 | |
| sciq,acc,0.935,0.007799733061832013,0 | |
| sciq,acc_norm,0.933,0.007910345983177549,0 | |
| storycloze_2016,acc,0.7477284874398717,0.010043504206387307,0 | |
| winogrande,acc,0.5935280189423836,0.013804448697753375,0 | |