textattack/albert-base-v2-yelp-polarity

Albert-base-v2 model was fine-tuned for sequence classification using TextAttack and the yelp_polarity dataset . The best score the model achieved on this task was 0.975078947368421, as measured by the eval set accuracy, found after 3 epochs . The model was trained with a cross-entropy loss function and a learning rate of 3e-05 . For more information, check out TextAttack on Github and the TextAttack model is available on the site of the nlp library, and the model is described as 'glyglygly' and 'glyphic' by the author of this article, and it,