1b121b21b/evaluation/lm1-1b1-21b-results_lm-eval_global_step39672_2022-12-03-10-25-38.csv

task,metric,value,err,version
arc_challenge,acc,0.19539249146757678,0.01158690718995291,0
arc_challenge,acc_norm,0.24573378839590443,0.012581033453730107,0
arc_easy,acc,0.47895622895622897,0.01025069260202259,0
arc_easy,acc_norm,0.43013468013468015,0.010159130445178497,0
boolq,acc,0.5700305810397553,0.008658853690729258,1
hellaswag,acc,0.31099382593108943,0.004619542392006404,0
hellaswag,acc_norm,0.35600477992431784,0.004778380758851136,0
sciq,acc,0.79,0.012886662332274531,0
sciq,acc_norm,0.712,0.01432694179723156,0