|
task,metric,value,err,version
|
|
anli_r1,acc,0.33,0.014876872027456732,0
|
|
anli_r2,acc,0.351,0.015100563798316405,0
|
|
anli_r3,acc,0.3375,0.013655897185463658,0
|
|
arc_challenge,acc,0.2593856655290102,0.012808273573927095,0
|
|
arc_challenge,acc_norm,0.2883959044368601,0.013238394422428175,0
|
|
arc_easy,acc,0.5778619528619529,0.010134620524592271,0
|
|
arc_easy,acc_norm,0.5635521885521886,0.010176569980111044,0
|
|
boolq,acc,0.6103975535168196,0.008529228894936293,1
|
|
cb,acc,0.42857142857142855,0.06672848092813058,1
|
|
cb,f1,0.29390681003584224,,1
|
|
copa,acc,0.8,0.040201512610368445,0
|
|
hellaswag,acc,0.42949611631149176,0.004939925958728869,0
|
|
hellaswag,acc_norm,0.5636327424815774,0.004949207947265914,0
|
|
piqa,acc,0.736126224156692,0.010282996367695562,0
|
|
piqa,acc_norm,0.7377584330794341,0.010262502565172443,0
|
|
rte,acc,0.5306859205776173,0.030039730592197812,0
|
|
sciq,acc,0.886,0.010055103435823332,0
|
|
sciq,acc_norm,0.873,0.010534798620855762,0
|
|
storycloze_2016,acc,0.6932121859967931,0.010664275190473634,0
|
|
winogrande,acc,0.5643251775848461,0.013935709739615713,0
|
|
|