Use accuracy as default metric for text classification Evaluator #128
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 documentation is not available anymore as the PR was closed or merged. |
lewtun
commented
Jun 8, 2022
| from datasets import Dataset, load_dataset, load_metric | ||
| from transformers import AutoTokenizer, BertForSequenceClassification, pipeline | ||
| from datasets import load_dataset | ||
| from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline |
There was a problem hiding this comment.
I took the liberty of cleaning this up a bit to follow the conventions in transformers (use autoclasses over model-specific ones where possible)
lewtun
commented
Jun 8, 2022
|
|
||
|
|
||
| class TestEvaluator(TestCase): | ||
| def setUp(self): | ||
| self.data = Dataset.from_dict(load_dataset("imdb")["test"][:2]) | ||
| self.data = load_dataset("imdb", split="test[:2]") |
There was a problem hiding this comment.
I took the liberty of using something more datasets-like here
|
LGTM! 🚀 |
lvwerra
approved these changes
Jun 8, 2022
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Outdated suggestions cannot be applied.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 replaces the current default metric in the text classification
Evaluatorfromf1toaccuracy.The reason for doing so is that the
Evaluatorfails when the dataset is multiclass because the default average inf1isbinary. Although there are well known limitations with using accuracy as the only metric, I think it's better to have defaults that "just work"Remark: it probably would make sense to expand the unit tests to test the evaluator on binary / multiclass / multilabel datasets. I'm happy to implement that if you think that's useful.