Skip to main content
sparsify
Projects
gpt2-e2e
Reports
performance/eval/difference_ce_loss and loss.sparsity.coeff v. sparsity/eval/L_0/blocks.8.hook_resid_pre (24/10/07 12:15:28)
Log in
Sign up
Share
Comment
Star
performance/eval/difference_ce_loss and loss.sparsity.coeff v. sparsity/eval/L_0/blocks.8.hook_resid_pre (24/10/07 12:15:28)
Jordan Taylor
Created on October 7
|
Last edited on October 7
Comment
performance/eval/difference_ce_loss and loss.sparsity.coeff v. sparsity/eval/L_0/blocks.8.hook_resid_pre
performance/eval/difference_ce_loss and loss.sparsity.coeff v. sparsity/eval/L_0/blocks.8.hook_resid_pre
6e-3
1e-2
2e-2
3e-2
4e-2
5e-2
6e-2
1e-1
2e-1
3e-1
4e-1
5e-1
6e-1
1e+0
2e+0
3e+0
4e+0
5e+0
6e+0
1e+1
loss.sparsity.coeff
3e+1
4e+1
5e+1
6e+1
7e+1
8e+1
9e+1
1e+2
2e+2
3e+2
4e+2
5e+2
6e+2
7e+2
8e+2
9e+2
1e+3
sparsity/eval/L_0/blocks.8.hook_resid_pre
-0.3
-0.2
-0.1
-0.09
-0.08
-0.07
-0.06
-0.05
-0.04
-0.03
-0.02
performance/eval/difference_ce_loss
Run set
169
Add a comment