fixing the clm-prompt-tuning that was causing unequal lengths in the label token id #487
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
The code snippet needs a correction in the line: labels["input_ids"][i] = [-100] * (max_length - len(sample_input_ids)) + label_input_ids Change it to: labels["input_ids"][i] = [-100] * (max_length - len(label_input_ids)) + label_input_ids This adjustment ensures that the label token ids are padded or truncated based on their own length, aligning with Hugging Face's recommended practice and avoiding issues with unequal lengths in input and label token ids. The same changes need to be corrected in documentation as well is been mentioned in the https://huggingface.co/docs/peft/main/en/task_guides/prompt_based_methods and https://huggingface.co/docs/peft/main/en/task_guides/clm-prompt-tuning
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
Does anyone got chance to have check on this PR and review request. |
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Outdated suggestions cannot be applied.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.
The code snippet needs a correction in the line:
labels["input_ids"][i] = [-100] * (max_length - len(sample_input_ids)) + label_input_ids Change it to:
labels["input_ids"][i] = [-100] * (max_length - len(label_input_ids)) + label_input_ids This adjustment ensures that the label token ids are padded or truncated based on their own length, aligning with Hugging Face's recommended practice and avoiding issues with unequal lengths in input and label token ids. The same changes need to be corrected in documentation as well is been mentioned in the https://huggingface.co/docs/peft/main/en/task_guides/prompt_based_methods and https://huggingface.co/docs/peft/main/en/task_guides/clm-prompt-tuning
What does this PR do?
The Pull Request (PR) corrects a code snippet that pads or truncates label token ids based on their own length, aligning with best practices recommended in the Hugging Face documentation for prompt-based methods and CLM prompt tuning. This correction ensures compatibility with transformer models and resolves issues related to unequal lengths in input and label token ids
huggingface_hub: @muellerzr, @LysandreJik