task,metric,value,err,version
anli_r1,acc,0.317,0.014721675438880227,0
anli_r2,acc,0.34,0.014987482264363935,0
anli_r3,acc,0.34,0.01368049572576779,0
arc_challenge,acc,0.3455631399317406,0.013896938461145683,0
arc_challenge,acc_norm,0.37372013651877134,0.014137708601759095,0
arc_easy,acc,0.6864478114478114,0.009519779157242258,0
arc_easy,acc_norm,0.6696127946127947,0.009651430216428182,0
boolq,acc,0.6571865443425077,0.008301676410578645,1
cb,acc,0.39285714285714285,0.0658538889806635,1
cb,f1,0.3421735552883094,,1
copa,acc,0.83,0.03775251680686371,0
hellaswag,acc,0.5375423222465644,0.004975696076240845,0
hellaswag,acc_norm,0.7132045409281019,0.004513409114983847,0
piqa,acc,0.7742110990206746,0.00975498067091731,0
piqa,acc_norm,0.7840043525571273,0.009601236303553543,0
rte,acc,0.5342960288808665,0.03002557981936643,0
sciq,acc,0.933,0.007910345983177549,0
sciq,acc_norm,0.93,0.0080724943583235,0
storycloze_2016,acc,0.7669695350080171,0.00977630189854803,0
winogrande,acc,0.6448303078137332,0.013450047479569256,0