Add multicontext training #359
Open
Conversation
This file contains 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
Including a labelled shakespeare_char_punct which has code for converting labels per character (in this case vowel, punctuation, consonant or other, but can also be POS). Currently we default to averaging the losses for each lm_head. Also this only has two streams and no method for selecting the head to inference from. This allows for concurrent lables of the
This allows us to view the separate losses for a and b context streams. Note, this is currently essentially equivalent to position embeddings. We can add simple NLP Based means now like vowel vs consonant, and maybe position embeddings within the word itself.
10 tasks
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Outdated suggestions cannot be applied.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 is a prototype for muitple simultaneous contexts.