task,metric,value,err,version
anli_r1,acc,0.333,0.014910846164229864,0
anli_r2,acc,0.334,0.014922019523732967,0
anli_r3,acc,0.35,0.013774667009018552,0
arc_challenge,acc,0.27474402730375425,0.013044617212771227,0
arc_challenge,acc_norm,0.2883959044368601,0.013238394422428164,0
arc_easy,acc,0.5816498316498316,0.010122061470742853,0
arc_easy,acc_norm,0.571969696969697,0.010152943316426265,0
boolq,acc,0.5990825688073395,0.008571628711617004,1
cb,acc,0.5,0.06741998624632421,1
cb,f1,0.30857142857142855,,1
copa,acc,0.76,0.04292346959909283,0
hellaswag,acc,0.43925512846046605,0.004952820538831887,0
hellaswag,acc_norm,0.5730930093606851,0.00493617678463196,0
piqa,acc,0.735038084874864,0.010296557993316049,0
piqa,acc_norm,0.733949945593036,0.010310039263352824,0
rte,acc,0.4657039711191336,0.030025579819366422,0
sciq,acc,0.869,0.010674874844837956,0
sciq,acc_norm,0.85,0.011297239823409291,0
storycloze_2016,acc,0.6937466595403528,0.010659088460112756,0
winogrande,acc,0.5509076558800315,0.013979459389140834,0