evaluation/1b121b10bc4-results_lm-eval_global_step39672_2022-12-22-07-35-19.csv

task,metric,value,err,version
arc_challenge,acc,0.2175767918088737,0.012057262020972504,0
arc_challenge,acc_norm,0.2551194539249147,0.012739038695202104,0
arc_easy,acc,0.49242424242424243,0.010258605792153321,0
arc_easy,acc_norm,0.43897306397306396,0.010183076012972067,0
boolq,acc,0.5235474006116208,0.008735351675636605,1
copa,acc,0.72,0.04512608598542127,0
hellaswag,acc,0.3556064528978291,0.0047771835089498215,0
hellaswag,acc_norm,0.4304919338777136,0.004941331215598556,0
piqa,acc,0.70620239390642,0.010627574080514797,0
piqa,acc_norm,0.7013057671381937,0.010678556398149226,0
rte,acc,0.5379061371841155,0.030009848912529117,0
sciq,acc,0.754,0.013626065817750638,0
sciq,acc_norm,0.666,0.01492201952373297,0
winogrande,acc,0.5288082083662194,0.014029141615909615,0