textattack/bert-base-uncased-RTE

1## TextAttack Model Card2This `bert-base-uncased` model was fine-tuned for sequence classification using TextAttack 3and the glue dataset loaded using the `nlp` library. The model was fine-tuned 4for 5 epochs with a batch size of 8, a learning 5rate of 2e-05, and a maximum sequence length of 128. 6Since this was a classification task, the model was trained with a cross-entropy loss function. 7The best score the model achieved on this task was 0.7256317689530686, as measured by the 8eval set accuracy, found after 2 epochs.9 10For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).11