evaluation_small/2b855b9bc4-results_lm-eval_global_step52452_2022-12-23-23-13-03.csv

task,metric,value,err,version
arc_challenge,acc,0.25,0.012653835621466646,0
arc_challenge,acc_norm,0.28071672354948807,0.013131238126975578,0
arc_easy,acc,0.5458754208754208,0.010216507710244106,0
arc_easy,acc_norm,0.49074074074074076,0.010258024147860673,0
boolq,acc,0.5963302752293578,0.008581220435616816,1
copa,acc,0.72,0.04512608598542127,0
hellaswag,acc,0.4334793865763792,0.004945424771611596,0
hellaswag,acc_norm,0.560744871539534,0.0049528205388318985,0
piqa,acc,0.7399347116430903,0.0102348932490613,0
piqa,acc_norm,0.7426550598476604,0.01019992106479251,0
rte,acc,0.5487364620938628,0.029953149241808943,0
sciq,acc,0.814,0.012310790208412803,0
sciq,acc_norm,0.711,0.014341711358296177,0
winogrande,acc,0.5461720599842147,0.013992441563707068,0