Changing default b1 & b2 values.#166
Open
foersterrobert wants to merge 1 commit intoeriklindernoren:masterfrom
foersterrobert:patch-1
Open
Changing default b1 & b2 values.#166foersterrobert wants to merge 1 commit intoeriklindernoren:masterfrom foersterrobert:patch-1
foersterrobert wants to merge 1 commit intoeriklindernoren:masterfrom
foersterrobert:patch-1
Conversation
In the paper, the proposed betas of Adam were set to 0.0 & 0.9, so I guess it makes sense to use those as default here as well. I also got more stable results during training using these. But maybe you tweaked the betas on purpose, and the old ones make more sense to you. TY for your implementations btw :).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In the paper, the proposed betas of Adam were set to 0.0 & 0.9, so I guess it makes sense to use those as default here as well. I also got more stable results during training using these. But maybe you tweaked the betas on purpose, and the old ones make more sense to you. TY for your implementations btw :).