Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,6 @@ The training for the distilled model (student model) is designed to be the close
|
|
| 21 |
* CosineLoss: and finally a cosine embedding loss. This loss function is applied on the last hidden layers of student and teacher models to guarantee a collinearity between them.
|
| 22 |
|
| 23 |
The final loss function is a combination of these three loss functions. We use the following ponderation:
|
| 24 |
-
|
| 25 |
*Loss = 0.5 DistilLoss + 0.2 MLMLoss + 0.3 CosineLoss*
|
| 26 |
|
| 27 |
Dataset
|
|
|
|
| 21 |
* CosineLoss: and finally a cosine embedding loss. This loss function is applied on the last hidden layers of student and teacher models to guarantee a collinearity between them.
|
| 22 |
|
| 23 |
The final loss function is a combination of these three loss functions. We use the following ponderation:
|
|
|
|
| 24 |
*Loss = 0.5 DistilLoss + 0.2 MLMLoss + 0.3 CosineLoss*
|
| 25 |
|
| 26 |
Dataset
|