How to use the test set in those beginner examples?

Beginners
1

Hi, maybe a stupid question but I cant find the answer ether in Doc or on Google.

In these examples notebooks/text_classification.ipynb at master · huggingface/notebooks · GitHub
the datasets contain a test set, but the examples finished after how to train and evaluate(on validation set if I understand it correctly).

But how about test set? Is there a convenient way to test it on test set? Like the one line command for trainer.evaluate().

Thanks.

2

trainer.evaluate takes a dataset, so you can pass the test split if you want to evaluate on the test set.
Or there is trainer.predict if you just want the predictions.