textattack/roberta-base-RTE

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 0.7942238267148014, as measured by the eval set accuracy, found after 3 epochs . Since this was a classification task, the model was trained with a cross-entropy loss function . For more information, check out TextAttack on Github and the model is available on the site of the TextAttack Cardio on http://://www.textAttack.org//glues-loaded-to-the-measurement-quality-search-ability-search/cardio-quality,