Experimentation with DistillCARP #14
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
added 15 commits
February 3, 2022 14:04
…into DistillCARP
…into DistillCARP
|
Needs to be updated to conform to the new trainer architecture. |
|
|
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Outdated suggestions cannot be applied.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.
DistillCOMET shows a lot of success in conditioning their common sense model by the knowledge provided by GPT3.
I'll be experimenting with applying a similar approach to CARP, prompting GPT-NeoX to generate critiques for a given story. For every element of the story-critique dataset I'll generate 3 - 6 critiques and use that to perform prompt softening during training.
The hope is that this will bring the training objective closer to the inference objective.