Fix finetuning notebook augmentation #2071
Merged
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
julian-risch
approved these changes
Jan 26, 2022
There was a problem hiding this comment.
LGTM! 👍 Please try to run the notebook on colab as a final test: https://colab.research.google.com/github/deepset-ai/haystack/blob/fix-finetuning-notebook-augmentation/tutorials/Tutorial2_Finetune_a_model_on_your_data.ipynb#scrollTo=lHkSOXjBd0fS (with !pip install git+https://github.com/deepset-ai/haystack.git@fix-finetuning-notebook-augmentation
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Outdated suggestions cannot be applied.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.
Proposed changes:
Previously, the data augmentation and model distillation parts of the finetuning tutorial were not working due to 2 issues:
LanguageModels could actually return hidden states and attentionsThis PR fixes those and uses a different dataset for model distillation in the tutorial to decrease notebook runtime (more than 1 h for distillation before).
Status (please check what you already did):