textattack/distilbert-base-uncased-imdb

The best score the model achieved on this task was 0.88, as measured by the eval set accuracy, found after 2 epochs . The model was fine-tuned for 5 epochs with a learning rate of 2e-05 and a maximum sequence length of 128 . For more information, check out TextAttack on Github and the nlp library on the TextAttack app for the latest code on the Appararable Apparable.io . For example, the apparable model was trained with a cross-entropy loss function. For example: The model had a learning rate of 2-05, and a learning curve of 2E-05. For,