Update README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
## TextAttack Model Card
|
| 2 |
+
This `roberta-base` model was fine-tuned for sequence classification using TextAttack
|
| 3 |
+
and the glue dataset loaded using the `nlp` library. The model was fine-tuned
|
| 4 |
+
for 5 epochs with a batch size of 8, a learning
|
| 5 |
+
rate of 2e-05, and a maximum sequence length of 128.
|
| 6 |
+
Since this was a regression task, the model was trained with a mean squared error loss function.
|
| 7 |
+
The best score the model achieved on this task was 0.9108696741479216, as measured by the
|
| 8 |
+
eval set pearson correlation, found after 4 epochs.
|
| 9 |
+
|
| 10 |
+
For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).
|