scale the bench
Created on August 23|Last edited on September 9
Comment
base metrics
plast_proportion
n_hidden
606
2_palindrome_dataset_vary_length
491
102
clip_weights
534
2_palindrome_dataset_vary_length
419
216
effective_lr,
606
2_palindrome_dataset_vary_length
491
102
plotting effective_lr
344
2_palindrome_dataset_vary_length
397
102
3_palindrome_dataset_vary_length
154
491
102
only the best. For this visualization, I see which hyperparameters the best runs had.
344
2_palindrome_dataset_vary_length
491
102
specific questions
What are the parameters of the actual top performers?
3_palindrome_dataset_vary_length
123
2_palindrome_dataset_vary_length
141
What does plast_clip do? Does it make things explode? If so, when? Is there a min. value for which it can use memory at all? For simplicity, we fix clip_weights. We also fix plast_proportion and n_hidden.
3_palindrome_dataset_vary_length
33
ok, now, what's the effect of clip_weights
3_palindrome_dataset_vary_length
23
3_palindrome_dataset_vary_length
123
Add a comment