|
task,metric,value,err,version
|
|
anli_r1,acc,0.325,0.014818724459095524,0
|
|
anli_r2,acc,0.331,0.014888272588203928,0
|
|
anli_r3,acc,0.3225,0.013499258621103245,0
|
|
arc_challenge,acc,0.24232081911262798,0.012521593295800116,0
|
|
arc_challenge,acc_norm,0.24658703071672355,0.01259572626879013,0
|
|
arc_easy,acc,0.4671717171717172,0.010237645778853848,0
|
|
arc_easy,acc_norm,0.4166666666666667,0.010116282977781239,0
|
|
boolq,acc,0.5094801223241591,0.008743482951361247,1
|
|
cb,acc,0.48214285714285715,0.0673769750864465,1
|
|
cb,f1,0.3461538461538461,,1
|
|
copa,acc,0.66,0.04760952285695238,0
|
|
hellaswag,acc,0.37552280422226647,0.004832679188788792,0
|
|
hellaswag,acc_norm,0.4534953196574388,0.004968151878211054,0
|
|
piqa,acc,0.6947769314472253,0.01074426704560648,0
|
|
piqa,acc_norm,0.6947769314472253,0.01074426704560648,0
|
|
rte,acc,0.48375451263537905,0.030080573208738064,0
|
|
sciq,acc,0.703,0.0144568322948011,0
|
|
sciq,acc_norm,0.628,0.015292149942040577,0
|
|
storycloze_2016,acc,0.6419027258150721,0.011087006809925713,0
|
|
winogrande,acc,0.5359116022099447,0.014016193433958308,0
|
|
|