1b58b88b8/1b58b88b8pile/evaluation/rankeval/lm1-1b5-8b8-results_lm-eval_global_step16765_2023-01-23-18-55-43_1shots.csv

task,metric,value,err,version
anli_r1,acc,0.328,0.014853842487270334,0
anli_r2,acc,0.328,0.014853842487270338,0
anli_r3,acc,0.32666666666666666,0.013544340907003665,0
arc_challenge,acc,0.197098976109215,0.011625047669880624,0
arc_challenge,acc_norm,0.24744027303754265,0.012610352663292673,0
arc_easy,acc,0.4494949494949495,0.010207308833916047,0
arc_easy,acc_norm,0.4208754208754209,0.010130502164066328,0
boolq,acc,0.5363914373088685,0.008721861424877861,1
cb,acc,0.48214285714285715,0.06737697508644648,1
cb,f1,0.3421052631578947,,1
copa,acc,0.64,0.04824181513244218,0
hellaswag,acc,0.28818960366460866,0.0045199417165083435,0
hellaswag,acc_norm,0.30701055566620195,0.004603111343213066,0
piqa,acc,0.6153427638737758,0.011351177743205584,0
piqa,acc_norm,0.6175190424374319,0.011339019654272347,0
rte,acc,0.5306859205776173,0.03003973059219781,0
sciq,acc,0.771,0.013294199326613583,0
sciq,acc_norm,0.735,0.013963164754809947,0
storycloze_2016,acc,0.5660074826296099,0.011461234645182191,0
winogrande,acc,0.5067087608524072,0.014051220692330352,0