task,metric,value,err,version
anli_r1,acc,0.337,0.014955087918653591,0
anli_r2,acc,0.347,0.015060472031706618,0
anli_r3,acc,0.3233333333333333,0.01350837286730022,0
arc_challenge,acc,0.1825938566552901,0.011289730684565,0
arc_challenge,acc_norm,0.2295221843003413,0.012288926760890797,0
arc_easy,acc,0.3952020202020202,0.010031894052790978,0
arc_easy,acc_norm,0.36826599326599324,0.009897286209010894,0
boolq,acc,0.5614678899082569,0.008678720482001873,1
cb,acc,0.375,0.06527912098338669,1
cb,f1,0.2554143126177024,,1
copa,acc,0.63,0.04852365870939099,0
hellaswag,acc,0.279326827325234,0.004477514681328155,0
hellaswag,acc_norm,0.2956582354112727,0.0045540545376920125,0
piqa,acc,0.6294885745375408,0.011267826475447665,0
piqa,acc_norm,0.6322089227421109,0.01125061664667879,0
rte,acc,0.5379061371841155,0.030009848912529117,0
sciq,acc,0.686,0.014683991951087955,0
sciq,acc_norm,0.635,0.015231776226264903,0
storycloze_2016,acc,0.5750935328701229,0.011431286492205844,0
winogrande,acc,0.5114443567482242,0.014048804199859325,0