| task,metric,value,err,version | |
| anli_r1,acc,0.324,0.014806864733738863,0 | |
| anli_r2,acc,0.348,0.01507060460376841,0 | |
| anli_r3,acc,0.35083333333333333,0.013782212417178195,0 | |
| arc_challenge,acc,0.3293515358361775,0.013734057652635473,0 | |
| arc_challenge,acc_norm,0.3430034129692833,0.013872423223718169,0 | |
| arc_easy,acc,0.664983164983165,0.009685160765932357,0 | |
| arc_easy,acc_norm,0.6506734006734006,0.009782853449399293,0 | |
| boolq,acc,0.618960244648318,0.008493937524439337,1 | |
| cb,acc,0.5535714285714286,0.06703189227942395,1 | |
| cb,f1,0.39031339031339024,,1 | |
| copa,acc,0.84,0.0368452949177471,0 | |
| hellaswag,acc,0.4969129655447122,0.004989686307484557,0 | |
| hellaswag,acc_norm,0.6625174268074089,0.004718846448021788,0 | |
| piqa,acc,0.7627856365614799,0.00992469493358637,0 | |
| piqa,acc_norm,0.7622415669205659,0.009932525779525492,0 | |
| rte,acc,0.49458483754512633,0.030094698123239966,0 | |
| sciq,acc,0.924,0.008384169266796387,0 | |
| sciq,acc_norm,0.918,0.008680515615523745,0 | |
| storycloze_2016,acc,0.7471940138963121,0.010050543909878586,0 | |
| winogrande,acc,0.6298342541436464,0.013570454689603911,0 | |