Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 pull request adds two new arguments to adjust word embedding initialization:
--adjust-word-embedding-initwhich enables reading a std value from a new different variable,and
--word-embedding-init-stdwhich controls the init std if above flag is set.I chose to have the enable flag so that we do not break any existing functionality in a case where a script is changing normal init std and thus the word embedding init std too. This way we retain that functionality as
--adjust-word-embedding-initdefaults to False if not set.This does not adjust positional embeddings and they are currently initialized with the default initialization method.