task,metric,value,err,version
anli_r1,acc,0.352,0.015110404505648661,0
anli_r2,acc,0.327,0.014842213153411242,0
anli_r3,acc,0.33,0.013579531277800925,0
arc_challenge,acc,0.28242320819112626,0.013155456884097222,0
arc_challenge,acc_norm,0.30716723549488056,0.013481034054980945,0
arc_easy,acc,0.6262626262626263,0.009927267058259626,0
arc_easy,acc_norm,0.6123737373737373,0.009997307914447608,0
boolq,acc,0.5834862385321101,0.008622288020674008,1
cb,acc,0.5,0.06741998624632421,1
cb,f1,0.355846042120552,,1
copa,acc,0.77,0.04229525846816506,0
hellaswag,acc,0.45130452101175067,0.0049660609953150634,0
hellaswag,acc_norm,0.5881298546106354,0.0049116598845061485,0
piqa,acc,0.7377584330794341,0.010262502565172447,0
piqa,acc_norm,0.7404787812840044,0.010227939888173929,0
rte,acc,0.5306859205776173,0.030039730592197812,0
sciq,acc,0.903,0.009363689373248123,0
sciq,acc_norm,0.891,0.009859828407037186,0
storycloze_2016,acc,0.6819882415820417,0.010769343495248548,0
winogrande,acc,0.5493291239147593,0.01398392886904024,0