Add output to finetuning prompt #20
Closed
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
|
Hi, thanks for your interest. The prompt part only specifies how to format the instruction and input. You're right, we concat the output with the instruction+input. We included the boilerplate for every example during training and inference. |
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Outdated suggestions cannot be applied.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 adds the output to the fine-tuning prompt, which is presumably needed to train the model.
A question I have is: did you include the
Below is an instruction that describes a task. Write a response that appropriately completes the request.in every example or is that just for inference? Naively I would have guessed including it in training would make the model memorize this prompt, but perhaps that's actually useful in the end :)