Update README.md

README.md

@@ -21,6 +21,7 @@ The training for the distilled model (student model) is designed to be the close
 * 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.
 
 The final loss function is a combination of these three loss functions. We use the following ponderation:
+
 *Loss = 0.5 DistilLoss + 0.2 MLMLoss + 0.3 CosineLoss*
 
 Dataset