textattack/bert-base-uncased-yelp-polarity

The model was fine-tuned for sequence classification using TextAttack and the yelp_polarity dataset . It was trained with a cross-entropy loss function . The best score the model achieved on this task was 0.9699473683684210527, as measured by the eval set accuracy, found after 4 epochs . For more information, check out TextAttack on Github and the nlp library on the TextAttack model card on the current version of the model card below: [TextAttack Model Card.], or read the original version of this article by Andrew Keen and Andrew Keen. The card is now available to download and use in the U.S,