albert-base-v2 fine-tuned with TextAttack on the glue dataset
This albert-base-v2 model was fine-tuned for sequence classification using TextAttack
and the glue dataset loaded using the nlp library. The model was fine-tuned
for 5 epochs with a batch size of 32, a learning
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 0.8245445829338447, as measured by the
eval set accuracy, found after 2 epochs.
For more information, check out TextAttack on Github.