lm5-2b8-55b-c4 / evaluation /rankeval_x_denoiser /checkpoints_2b855b55bc4ul2ndfixnew_0.csv
Muennighoff's picture
Add files
79391b8
raw
history blame
No virus
1.04 kB
task,metric,value,err,version
anli_r1,acc,0.338,0.014965960710224473,0
anli_r2,acc,0.333,0.01491084616422986,0
anli_r3,acc,0.335,0.01363087184382148,0
arc_challenge,acc,0.181740614334471,0.011269198948880236,0
arc_challenge,acc_norm,0.22098976109215018,0.012124929206818258,0
arc_easy,acc,0.43434343434343436,0.010170943451269425,0
arc_easy,acc_norm,0.382996632996633,0.009974920384536472,0
boolq,acc,0.5935779816513761,0.008590531708882188,1
cb,acc,0.4107142857142857,0.0663363415035954,1
cb,f1,0.1940928270042194,,1
copa,acc,0.63,0.048523658709391,0
hellaswag,acc,0.29725154351722766,0.004561141293448468,0
hellaswag,acc_norm,0.3256323441545509,0.004676529200753,0
piqa,acc,0.6300326441784548,0.011264415223415281,0
piqa,acc_norm,0.6322089227421109,0.011250616646678792,0
rte,acc,0.5234657039711191,0.03006330041190266,0
sciq,acc,0.736,0.013946271849440472,0
sciq,acc_norm,0.668,0.014899597242811476,0
storycloze_2016,acc,0.5916622127204704,0.011366477562142522,0
winogrande,acc,0.5090765588003157,0.01405017009449771,0