| task,metric,value,err,version | |
| anli_r1,acc,0.313,0.014671272822977888,0 | |
| anli_r2,acc,0.356,0.015149042659306628,0 | |
| anli_r3,acc,0.335,0.013630871843821472,0 | |
| arc_challenge,acc,0.31569965870307165,0.013582571095815291,0 | |
| arc_challenge,acc_norm,0.3387372013651877,0.013830568927974332,0 | |
| arc_easy,acc,0.6384680134680135,0.00985850654316206,0 | |
| arc_easy,acc_norm,0.6195286195286195,0.00996230599205857,0 | |
| boolq,acc,0.6311926605504588,0.00843865607975907,1 | |
| cb,acc,0.42857142857142855,0.06672848092813058,1 | |
| cb,f1,0.4014346362172449,,1 | |
| copa,acc,0.85,0.03588702812826371,0 | |
| hellaswag,acc,0.4993029277036447,0.00498977656227611,0 | |
| hellaswag,acc_norm,0.6642103166699861,0.0047130060728077195,0 | |
| piqa,acc,0.7616974972796517,0.009940334245876207,0 | |
| piqa,acc_norm,0.7720348204570185,0.009788093832324908,0 | |
| rte,acc,0.5523465703971119,0.02993107036293953,0 | |
| sciq,acc,0.923,0.008434580140240662,0 | |
| sciq,acc_norm,0.913,0.00891686663074589,0 | |
| storycloze_2016,acc,0.738107963655799,0.010167174759499612,0 | |
| winogrande,acc,0.6006314127861089,0.013764933546717612,0 | |