-
Notifications
You must be signed in to change notification settings - Fork 3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
New config #371
New config #371
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the update.
I've made some suggestions for changes one could consider.
@@ -13,7 +13,7 @@ ensemble: | |||
duration: <DURATION> # fs | |||
n_inner: 100 # compiled innner steps |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should we increase n_inner to like 500 or 1000?
r_min: 0.5 | ||
name: bessel | ||
n_basis: 16 | ||
r_max: 6.5 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
rmax 6.5 is rarely needed in my experience. Most of the time 5-6 is fine. I would suggest 5 as a default.
emb_lr: 0.01 | ||
nn_lr: 0.01 | ||
scale_lr: 0.001 | ||
shift_lr: 0.05 | ||
shift_lr: 0.03 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would suggest to lower the lrs by a factor of 10 or so
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LRs this high are rarely stable
No description provided.