textattack/bert-base-uncased-ag-news

The model was fine-tuned for sequence classification using TextAttack and the ag_news dataset . The best score the model achieved on this task was 0.9514473683684210526, as measured by the eval set accuracy, found after 3 epochs . For more information, check out TextAttack on Github and the nlp library on the TextAttack model card . For example, the model was trained with a cross-entropy loss function and a learning rate of 3e-05, and a maximum sequence length of 128. For example: The model achieved an accuracy score of 0.96% on the best set of 5 epochs and 0.97%,