textattack/roberta-base-MRPC

The model was fine-tuned for sequence classification using TextAttack and the glue dataset loaded using the nlp library . The best score the model achieved on this task was 0.911764707058823529, as measured by the eval set accuracy, found after 2 epochs . For more information, check out TextAttack on Github and the model is available on the site of the TextAttack app . 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 256 . The model is now available to purchase on the website of TextAttack . For further information, visit TextAttack,