Test gd_bugfix and gd_bugfix_rapid_q branches of diffsky#41
Merged
Conversation
Also, enable test_all_diffsky_u_param_grads_stay_nonzero_multistep now so that gd_bugfix branch of diffsky can be tested for zero grads
…n zero grad param list
to avoid: A single bad training step where the optimizer sees a huge gradient, takes a massive step, and throws your model parameters into a region they'll never recover from.
gd_bugfix and gd_bugfix_rapid_q branches of diffsky
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR extensively tested the following branches in
diffskywhich are now merged into main:obs_mags-->obs_mags_weighted, utilized in gradient descents