Update README.md
Browse files
README.md
CHANGED
@@ -59,7 +59,7 @@ In training stage 1 we first introduce Spanish to the model. The objective is to
|
|
59 |
|
60 |
|
61 |
### Training-stage 2 (learning Nahuatl)
|
62 |
-
We use the pretrained Spanish-English model to learn Spanish-Nahuatl. Since the amount of Nahuatl pairs is limited, we also add to our dataset 20,000 samples from the English-Spanish Anki dataset. This two-task-
|
63 |
|
64 |
### Training setup
|
65 |
We train the models on the same datasets for 660k steps using batch size = 16 and 2e-5 learning rate.
|
|
|
59 |
|
60 |
|
61 |
### Training-stage 2 (learning Nahuatl)
|
62 |
+
We use the pretrained Spanish-English model to learn Spanish-Nahuatl. Since the amount of Nahuatl pairs is limited, we also add to our dataset 20,000 samples from the English-Spanish Anki dataset. This two-task-training avoids overfitting end makes the model more robust.
|
63 |
|
64 |
### Training setup
|
65 |
We train the models on the same datasets for 660k steps using batch size = 16 and 2e-5 learning rate.
|