619m22b22b/evaluation/rankeval/lm1-619m-22b-results_lm-eval_global_step41007_2023-01-24-13-57-03_3shots.csv

task,metric,value,err,version
anli_r1,acc,0.326,0.014830507204541024,0
anli_r2,acc,0.358,0.015167928865407557,0
anli_r3,acc,0.3375,0.013655897185463665,0
arc_challenge,acc,0.2226962457337884,0.012158314774829924,0
arc_challenge,acc_norm,0.25170648464163825,0.012682496334042961,0
arc_easy,acc,0.4882154882154882,0.010256933475911015,0
arc_easy,acc_norm,0.4671717171717172,0.010237645778853851,0
boolq,acc,0.5299694189602446,0.0087293318183149,1
cb,acc,0.35714285714285715,0.0646095738380922,1
cb,f1,0.23561507936507933,,1
copa,acc,0.69,0.04648231987117316,0
hellaswag,acc,0.30233021310495917,0.004583289072937737,0
hellaswag,acc_norm,0.3353913563035252,0.004711622011148457,0
piqa,acc,0.6436343852013058,0.011174109865864703,0
piqa,acc_norm,0.6436343852013058,0.011174109865864729,0
rte,acc,0.5415162454873647,0.029992535385373314,0
sciq,acc,0.834,0.011772110370812192,0
sciq,acc_norm,0.809,0.012436787112179486,0
storycloze_2016,acc,0.6002137894174239,0.011327813397531862,0
winogrande,acc,0.5193370165745856,0.01404197273371297,0