evaluation/1b121b3bc4-results_lm-eval_global_step39672_2022-12-22-07-35-29.csv

task,metric,value,err,version
arc_challenge,acc,0.2175767918088737,0.012057262020972506,0
arc_challenge,acc_norm,0.2568259385665529,0.012766923794116798,0
arc_easy,acc,0.4823232323232323,0.010253369805698957,0
arc_easy,acc_norm,0.4276094276094276,0.010151683397430687,0
boolq,acc,0.5302752293577981,0.008729009003964297,1
copa,acc,0.69,0.04648231987117316,0
hellaswag,acc,0.35241983668591914,0.004767475366689781,0
hellaswag,acc_norm,0.4287990440151364,0.004938930143234467,0
piqa,acc,0.690968443960827,0.01078141946440698,0
piqa,acc_norm,0.6936887921653971,0.010754970032367323,0
rte,acc,0.5379061371841155,0.030009848912529117,0
sciq,acc,0.761,0.013493000446937591,0
sciq,acc_norm,0.66,0.014987482264363937,0
winogrande,acc,0.5090765588003157,0.0140501700944977,0