textattack/bert-base-cased-STS-B

The best score the model achieved on this task was 0.824444429996636282, as measured by the eval set pearson correlation, found after 2 epochs . The model was fine-tuned for 3 epochs with a batch size of 128, a learning rate of 1e-05, and a maximum sequence length of 128 . For more information, check out [TextAttack on Github[https://://://github.com/QData/TextAttack] and the glue dataset was loaded using the `nlp` library . For example, the model was trained with a mean squared error loss function, and the data was trained using the mean,