evaluation/1b121b5bc4-results_lm-eval_global_step39672_2022-12-22-07-35-29.csv

task,metric,value,err,version
arc_challenge,acc,0.20563139931740615,0.011810745260742566,0
arc_challenge,acc_norm,0.257679180887372,0.012780770562768403,0
arc_easy,acc,0.5029461279461279,0.010259605416237574,0
arc_easy,acc_norm,0.43897306397306396,0.010183076012972064,0
boolq,acc,0.5620795107033639,0.008677388652709261,1
copa,acc,0.7,0.046056618647183814,0
hellaswag,acc,0.3540131447918741,0.004772358395130456,0
hellaswag,acc_norm,0.43198566022704643,0.00494340089288106,0
piqa,acc,0.7013057671381937,0.01067855639814924,0
piqa,acc_norm,0.705658324265506,0.01063331147034751,0
rte,acc,0.5415162454873647,0.029992535385373314,0
sciq,acc,0.762,0.013473586661967227,0
sciq,acc_norm,0.676,0.014806864733738857,0
winogrande,acc,0.5146014206787688,0.014046492383275834,0