Muennighoff's picture
Add eval
9e5d26a
raw
history blame
No virus
1.06 kB
task,metric,value,err,version
anli_r1,acc,0.351,0.015100563798316402,0
anli_r2,acc,0.352,0.015110404505648668,0
anli_r3,acc,0.36833333333333335,0.013930121355353778,0
arc_challenge,acc,0.2986348122866894,0.013374078615068756,0
arc_challenge,acc_norm,0.3310580204778157,0.013752062419817836,0
arc_easy,acc,0.6456228956228957,0.009815004030251746,0
arc_easy,acc_norm,0.6464646464646465,0.0098097289481515,0
boolq,acc,0.6070336391437309,0.008542335147970564,1
cb,acc,0.48214285714285715,0.0673769750864465,1
cb,f1,0.3366858237547892,,1
copa,acc,0.76,0.04292346959909283,0
hellaswag,acc,0.4567815176259709,0.0049711062650465545,0
hellaswag,acc_norm,0.602370045807608,0.004884079750433882,0
piqa,acc,0.7410228509249184,0.010220966031405609,0
piqa,acc_norm,0.7431991294885746,0.010192864802278042,0
rte,acc,0.5667870036101083,0.02982676408213828,0
sciq,acc,0.922,0.008484573530118581,0
sciq,acc_norm,0.929,0.008125578442487917,0
storycloze_2016,acc,0.7156600748262961,0.010431614128665242,0
winogrande,acc,0.5595895816890292,0.013952330311915603,0