Use embedding_dim as the default norm for weight min/max in BaseEmbeddingConfig #3623
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Outdated suggestions cannot be applied.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.
Summary:
Context
In
BaseEmbeddingConfig, the default value of weight min/max is now determined bysqrt(1 / self.embedding_dim), Previously it wassqrt(1 / self.num_embeddings)but it may become super small if the number of embeddings become large.References
See more discussions in the Github PR.
Differential Revision: D89562350