File size: 679 Bytes
567a273 |
1 2 3 4 5 6 7 8 9 10 11 12 |
## distilbert-base-uncased fine-tuned with TextAttack on the glue dataset
This `distilbert-base-uncased` 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 64, 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 0.8235858101629914, as measured by the
eval set accuracy, found after 2 epochs.
For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).
|