Muennighoff's picture
PP
35f9bea
raw
history blame contribute delete
No virus
1.06 kB
task,metric,value,err,version
anli_r1,acc,0.316,0.014709193056057121,0
anli_r2,acc,0.324,0.014806864733738856,0
anli_r3,acc,0.3358333333333333,0.013639261190932887,0
arc_challenge,acc,0.22440273037542663,0.012191404938603843,0
arc_challenge,acc_norm,0.2568259385665529,0.0127669237941168,0
arc_easy,acc,0.5429292929292929,0.010221897564256052,0
arc_easy,acc_norm,0.5096801346801347,0.010257860554461127,0
boolq,acc,0.55565749235474,0.00869070599067338,1
cb,acc,0.48214285714285715,0.06737697508644648,1
cb,f1,0.3373075012419274,,1
copa,acc,0.75,0.04351941398892446,0
hellaswag,acc,0.3617805218084047,0.004795337009118191,0
hellaswag,acc_norm,0.44234216291575384,0.0049564940598648966,0
piqa,acc,0.6980413492927094,0.010711732891588357,0
piqa,acc_norm,0.691512513601741,0.010776164678037155,0
rte,acc,0.5306859205776173,0.03003973059219781,0
sciq,acc,0.885,0.010093407594904628,0
sciq,acc_norm,0.853,0.011203415395160336,0
storycloze_2016,acc,0.6221272047033671,0.01121221988713706,0
winogrande,acc,0.5169692186266772,0.014044390401612978,0