Fancy learning rate - #90
Closed
Pengju-Sheng wants to merge 3 commits into
Closed
Conversation
allevitan
reviewed
Jul 23, 2026
allevitan
left a comment
allevitan
left a comment
Collaborator
There was a problem hiding this comment.
This is a very nice framework, I didn't catch any technical problems. I had a few general comments:
- The docstrings need to be updated
- Test coverage needs to be added
- I think the printout of all the learning rates with each call to optimize() is a bit noisy.
I also want to propose a slightly different framework for doing the adjustment which I think might be simpler from the user side - I will whip up a PR for comparison, curious what you'll think
Collaborator
|
Ah, two more notes! We also need to update SGD_optimize, and model.Adam_optimize/model.SGD_optimize. Stay tuned for a PR :) |
Merged
Collaborator
|
Closed in favor of #91 |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I add new feature to adam that users can adjust learning rate for each parameters and it is compatible with the old style where you can give one single lr to all the parameters.