task,metric,value,err,version
anli_r1,acc,0.31,0.014632638658632902,0
anli_r2,acc,0.31,0.014632638658632905,0
anli_r3,acc,0.3283333333333333,0.013562032919529017,0
arc_challenge,acc,0.2883959044368601,0.013238394422428173,0
arc_challenge,acc_norm,0.3148464163822526,0.01357265770308495,0
arc_easy,acc,0.6262626262626263,0.009927267058259621,0
arc_easy,acc_norm,0.5934343434343434,0.010079056419223527,0
boolq,acc,0.5522935779816514,0.008697094687974059,1
cb,acc,0.3392857142857143,0.06384226561930825,1
cb,f1,0.29749748849204566,,1
copa,acc,0.79,0.040936018074033256,0
hellaswag,acc,0.4803823939454292,0.004985939292819582,0
hellaswag,acc_norm,0.6294562836088429,0.004819633668832538,0
piqa,acc,0.7486398258977149,0.010121156016819259,0
piqa,acc_norm,0.7633297062023939,0.009916841655042809,0
rte,acc,0.44765342960288806,0.02993107036293953,0
sciq,acc,0.892,0.0098200016513457,0
sciq,acc_norm,0.869,0.010674874844837954,0
storycloze_2016,acc,0.7049706039551042,0.010546232606962289,0
winogrande,acc,0.5887924230465666,0.013829128358676874,0