task,metric,value,err,version
anli_r1,acc,0.349,0.0150806639915631,0
anli_r2,acc,0.335,0.014933117490932566,0
anli_r3,acc,0.34833333333333333,0.013759437498874075,0
arc_challenge,acc,0.26791808873720135,0.012942030195136421,0
arc_challenge,acc_norm,0.3054607508532423,0.013460080478002501,0
arc_easy,acc,0.5294612794612794,0.010241957728409683,0
arc_easy,acc_norm,0.5105218855218855,0.010257511546488227,0
boolq,acc,0.5137614678899083,0.008741742106878655,1
cb,acc,0.375,0.06527912098338669,1
cb,f1,0.25396825396825395,,1
copa,acc,0.74,0.044084400227680794,0
hellaswag,acc,0.45797649870543716,0.004972126523031945,0
hellaswag,acc_norm,0.5928101971718781,0.004903066639761946,0
piqa,acc,0.7328618063112078,0.010323440492612437,0
piqa,acc_norm,0.7377584330794341,0.010262502565172447,0
rte,acc,0.4981949458483754,0.030096267148976626,0
sciq,acc,0.799,0.012679107214617331,0
sciq,acc_norm,0.778,0.013148721948877366,0
storycloze_2016,acc,0.6857295563869589,0.010735132285108176,0
winogrande,acc,0.5651144435674822,0.013932814110418013,0