| task,metric,value,err,version | |
| anli_r1,acc,0.334,0.014922019523732967,0 | |
| anli_r2,acc,0.343,0.015019206922356951,0 | |
| anli_r3,acc,0.3408333333333333,0.013688600793296939,0 | |
| arc_challenge,acc,0.2551194539249147,0.0127390386952021,0 | |
| arc_challenge,acc_norm,0.2960750853242321,0.013340916085246263,0 | |
| arc_easy,acc,0.5955387205387206,0.010070746648278783,0 | |
| arc_easy,acc_norm,0.5660774410774411,0.010169795770462103,0 | |
| boolq,acc,0.519571865443425,0.008738352682962235,1 | |
| cb,acc,0.5178571428571429,0.06737697508644647,1 | |
| cb,f1,0.3312577833125778,,1 | |
| copa,acc,0.79,0.040936018074033256,0 | |
| hellaswag,acc,0.43238398725353516,0.00494394506961146,0 | |
| hellaswag,acc_norm,0.5674168492332204,0.004944215937021384,0 | |
| piqa,acc,0.7388465723612623,0.010248738649935573,0 | |
| piqa,acc_norm,0.7448313384113167,0.010171571592521831,0 | |
| rte,acc,0.44765342960288806,0.029931070362939526,0 | |
| sciq,acc,0.892,0.0098200016513457,0 | |
| sciq,acc_norm,0.888,0.00997775303139724,0 | |
| storycloze_2016,acc,0.6830571886691609,0.010759650951452121,0 | |
| winogrande,acc,0.5422257300710339,0.014002284504422435,0 | |