task,metric,value,err,version
anli_r1,acc,0.309,0.014619600977206491,0
anli_r2,acc,0.343,0.015019206922356953,0
anli_r3,acc,0.3333333333333333,0.013613950010225601,0
arc_challenge,acc,0.19112627986348124,0.011490055292778592,0
arc_challenge,acc_norm,0.2167235494880546,0.012040156713481189,0
arc_easy,acc,0.3888888888888889,0.01000324833531376,0
arc_easy,acc_norm,0.36237373737373735,0.009863468202583789,0
boolq,acc,0.4938837920489297,0.00874440068189347,1
cb,acc,0.35714285714285715,0.0646095738380922,1
cb,f1,0.24743230625583568,,1
copa,acc,0.57,0.04975698519562428,0
hellaswag,acc,0.2835092611033659,0.004497803024345142,0
hellaswag,acc_norm,0.2983469428400717,0.004565974937793714,0
piqa,acc,0.6251360174102285,0.011294565805619017,0
piqa,acc_norm,0.6218715995647442,0.011313980666854535,0
rte,acc,0.516245487364621,0.030080573208738064,0
sciq,acc,0.672,0.014853842487270334,0
sciq,acc_norm,0.627,0.015300493622922814,0
storycloze_2016,acc,0.5628006413682523,0.011470867061664471,0
winogrande,acc,0.5011838989739542,0.014052446290529015,0