textattack/albert-base-v2-SST-2

Albert-base-v2 model was fine-tuned for sequence classification using TextAttack . The best score the model achieved on this task was 0.9254587155963303, as measured by the eval set accuracy, found after 2 epochs . The model was trained with a cross-entropy loss function . For more information, check out TextAttack on Github and the nlp library on the TextAttack website . For example, TextAttack has a card with a card that says: "The card is the card of the card: The card is a card for the card, the card is an example of a card . The card was created by TextAttack and,