| task,metric,value,err,version | |
| anli_r1,acc,0.325,0.014818724459095526,0 | |
| anli_r2,acc,0.318,0.0147340793093119,0 | |
| anli_r3,acc,0.3408333333333333,0.013688600793296936,0 | |
| arc_challenge,acc,0.25853242320819114,0.01279455375428868,0 | |
| arc_challenge,acc_norm,0.2713310580204778,0.012993807727545792,0 | |
| arc_easy,acc,0.5702861952861953,0.010157908005763676,0 | |
| arc_easy,acc_norm,0.5244107744107744,0.010247548905242269,0 | |
| boolq,acc,0.5969418960244648,0.008579113210566456,1 | |
| cb,acc,0.5,0.06741998624632421,1 | |
| cb,f1,0.35276653171390016,,1 | |
| copa,acc,0.72,0.04512608598542128,0 | |
| hellaswag,acc,0.43766182035451107,0.004950848456984546,0 | |
| hellaswag,acc_norm,0.5681139215295757,0.004943264339868656,0 | |
| piqa,acc,0.7334058759521219,0.010316749863541367,0 | |
| piqa,acc_norm,0.735038084874864,0.010296557993316044,0 | |
| rte,acc,0.5451263537906137,0.029973636495415252,0 | |
| sciq,acc,0.844,0.011480235006122358,0 | |
| sciq,acc_norm,0.799,0.012679107214617326,0 | |
| storycloze_2016,acc,0.6953500801710315,0.010643426988646804,0 | |
| winogrande,acc,0.5453827940015785,0.01399448102706599,0 | |