textattack/albert-base-v2-ag-news

Albert-base-v2 model was fine-tuned for sequence classification using TextAttack and the nlp library . The model was trained with a cross-entropy loss function . The best score the model achieved on this task was 0.9471052631578948, as measured by the eval set accuracy, found after 3 epochs . For more information, check out TextAttack on Github and the model is available on the site of the TextAttack card . For example, the card was created using the nLP library . For the card, it was created with the help of TextAttack, and the data was loaded using the library's TextAttack. It is available,