Update README.md
Browse files
README.md
CHANGED
|
@@ -56,7 +56,6 @@ The following hyperparameters were used during training:
|
|
| 56 |
- subword regularization p = 0.0 (= trained without subword regularization)
|
| 57 |
|
| 58 |
And we add the sentences following the input sentence in the original dataset. Therefore, it cannot be reproduced from the dataset published on huggingface.
|
| 59 |
-
For detail in [our github repository](https://github.com/4ldk/CoNLL2003_Choices/blob/develop/src/utils.py)).
|
| 60 |
|
| 61 |
### Training results
|
| 62 |
|
|
|
|
| 56 |
- subword regularization p = 0.0 (= trained without subword regularization)
|
| 57 |
|
| 58 |
And we add the sentences following the input sentence in the original dataset. Therefore, it cannot be reproduced from the dataset published on huggingface.
|
|
|
|
| 59 |
|
| 60 |
### Training results
|
| 61 |
|