[V0.2.3] optimize the api of adalcomponent, and optimize the text-grad to not stuck with local minimum #219
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
…ch to be more consistent with naming, purpose and format with prepare_task, prepare_eval, prepare_loss, discover potential of the text-grad stuck in the local minimum of the training by following the same format but rather it should make a larger change on momentum/learning rate
…tput, loss with text_grad and the graph with demo
Sylph-AI
approved these changes
Sep 20, 2024
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Outdated suggestions cannot be applied.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.
make the use of bbh benchmark easier, update the adalcomponent api su…ch to be more consistent with naming, purpose and format with prepare_task, prepare_eval, prepare_loss, discover potential of the text-grad stuck in the local minimum of the training by following the same format but rather it should make a larger change on momentum/learning rate.
Debug mode will have much better report style (trainer.debug=True)
