textattack/xlnet-base-cased-RTE

The model was fine-tuned for sequence classification using TextAttack and the nlp library . The best score the model achieved on this task was 0.711191913357400722, as measured by the eval set accuracy, found after 3 epochs . The model had a learning rate of 2e-05 and a maximum sequence length of 128 . It was trained with a cross-entropy loss function and the glue dataset was loaded using the library nlp . For more information, check out TextAttack on Github and the code is available on the site of the TextAttack app and the library's Github page . The code is based on TextAttack's description of the,