textattack/xlnet-base-cased-CoLA

The best score the model achieved on this task was 0.797696989453499521, as measured by the eval set accuracy, found after 2 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 model is available on the site of the app for $1,000 . For example, TextAttack has a model card with a model that was trained on 5 epochs with a batch size of 32 and a maximum sequence length of 128 . The card is based on TextAttack’s model for a classification task, as well as other features,