chaning learning rate back to default of 1e-3#156
Merged
sfluegel05 merged 3 commits intodevfrom Mar 18, 2026
Merged
Conversation
…1e-4 for OPT fine-tuning experiments
Collaborator
|
Thanks for fixing this. I took the chance to delete a redundant pretraining config and fix some other parameters. Also, there are 5 toxicity electra configs. You have changed one learning rate to 1e-3, the others are 1e-5. Is there a reason for (a) having 5 different toxicity electra configs (but none for other OPT finetuning tasks) and (b) for having different learning rates? |
Collaborator
Author
|
They are used for different fine-tuning tasks (classification vs regression) and using different parameters, however, have deleted some of them. The remaining should stay. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
For model config files the default is now set to 1e-3.
Solves issue 150