TextAttack Model Cardand the glue dataset loaded using the nlp library. The model was fine-tuned
for 5 epochs with a batch size of 32, a learning rate of 3e-05, and a maximum sequence length of 128. Since this was a classification task, the model was trained with a cross-entropy loss function. The best score the model achieved on this task was 0.8245445829338447, as measured by the eval set accuracy, found after 2 epochs.
For more information, check out TextAttack on Github.