Muennighoff's picture
Add eval
d522938
task,metric,value,err,version
anli_r1,acc,0.331,0.01488827258820394,0
anli_r2,acc,0.349,0.015080663991563098,0
anli_r3,acc,0.3308333333333333,0.013588208070708999,0
arc_challenge,acc,0.2636518771331058,0.01287592915129705,0
arc_challenge,acc_norm,0.27474402730375425,0.013044617212771227,0
arc_easy,acc,0.5896464646464646,0.01009353125576546,0
arc_easy,acc_norm,0.5534511784511784,0.010200990076245305,0
boolq,acc,0.5984709480122324,0.008573784490094752,1
cb,acc,0.375,0.06527912098338669,1
cb,f1,0.2628346843527389,,1
copa,acc,0.77,0.04229525846816506,0
hellaswag,acc,0.42999402509460266,0.004940631135803533,0
hellaswag,acc_norm,0.5637323242381995,0.0049490803348160245,0
piqa,acc,0.7328618063112078,0.010323440492612431,0
piqa,acc_norm,0.7295973884657236,0.01036316703162078,0
rte,acc,0.5090252707581228,0.030091559826331334,0
sciq,acc,0.87,0.010640169792499347,0
sciq,acc_norm,0.838,0.011657267771304413,0
storycloze_2016,acc,0.6857295563869589,0.01073513228510818,0
winogrande,acc,0.5572217837411207,0.013960157350784994,0