task,metric,value,err,version
anli_r1,acc,0.35,0.015090650341444236,0
anli_r2,acc,0.32,0.01475865230357488,0
anli_r3,acc,0.33416666666666667,0.013622434813136783,0
arc_challenge,acc,0.19539249146757678,0.01158690718995291,0
arc_challenge,acc_norm,0.22781569965870307,0.012256708602326903,0
arc_easy,acc,0.39436026936026936,0.010028176038392995,0
arc_easy,acc_norm,0.35395622895622897,0.00981237064417441,0
boolq,acc,0.5675840978593272,0.008664798701065799,1
cb,acc,0.44642857142857145,0.067031892279424,1
cb,f1,0.30886196246139225,,1
copa,acc,0.61,0.04902071300001975,0
hellaswag,acc,0.2802230631348337,0.004481902637505665,0
hellaswag,acc_norm,0.2960565624377614,0.00455583246277459,0
piqa,acc,0.6311207834602829,0.011257546676908804,0
piqa,acc_norm,0.6207834602829162,0.011320331012905077,0
rte,acc,0.4548736462093863,0.029973636495415252,0
sciq,acc,0.681,0.01474640486547349,0
sciq,acc_norm,0.645,0.015139491543780532,0
storycloze_2016,acc,0.569748797434527,0.011449379528209637,0
winogrande,acc,0.505130228887135,0.014051745961790516,0