How to use this model directly from the
from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("textattack/xlnet-base-cased-CoLA") model = AutoModelWithLMHead.from_pretrained("textattack/xlnet-base-cased-CoLA")
rate of 3e-05, and a maximum sequence length of 128. Since this was a classification task, the model was trained with a cross-entropy loss function. The best score the model achieved on this task was 0.7976989453499521, as measured by the eval set accuracy, found after 2 epochs.
For more information, check out TextAttack on Github.