|
task,metric,value,err,version
|
|
anli_r1,acc,0.34,0.014987482264363937,0
|
|
anli_r2,acc,0.309,0.014619600977206491,0
|
|
anli_r3,acc,0.3233333333333333,0.01350837286730021,0
|
|
arc_challenge,acc,0.2431740614334471,0.012536554144587087,0
|
|
arc_challenge,acc_norm,0.2645051194539249,0.012889272949313368,0
|
|
arc_easy,acc,0.5336700336700336,0.010236494647406476,0
|
|
arc_easy,acc_norm,0.5193602693602694,0.010252089491165522,0
|
|
boolq,acc,0.5146788990825688,0.008741285568667916,1
|
|
cb,acc,0.5178571428571429,0.06737697508644647,1
|
|
cb,f1,0.36467236467236464,,1
|
|
copa,acc,0.67,0.04725815626252607,0
|
|
hellaswag,acc,0.36367257518422624,0.0048007281387923775,0
|
|
hellaswag,acc_norm,0.4482174865564629,0.004962949784236045,0
|
|
piqa,acc,0.690968443960827,0.01078141946440698,0
|
|
piqa,acc_norm,0.6942328618063112,0.010749627366141646,0
|
|
rte,acc,0.516245487364621,0.030080573208738064,0
|
|
sciq,acc,0.895,0.009698921026024963,0
|
|
sciq,acc_norm,0.893,0.00977991035984717,0
|
|
storycloze_2016,acc,0.632816675574559,0.011147041781368654,0
|
|
winogrande,acc,0.5217048145224941,0.014039239216484636,0
|
|
|