Commit
•
2baa52b
1
Parent(s):
cc14f8f
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,9 @@ The model shows improved proficiency with the Catalan language.
|
|
| 33 |
The model achieves a loss rate of 0.8528 on the validation dataset after two epochs.
|
| 34 |
|
| 35 |
**NOTE:** The model was trained for one epoch on the `train` split of dataset and after manual evaluation, I decided to go for another epoch.
|
|
|
|
| 36 |
The first epoch logs every 100 steps while the second epoch logs every 200 steps, but I am pasting the train and eval losses for both epochs bellow.
|
|
|
|
| 37 |
*The `train` split of the dataset was shuffled before the second epoch. The `test` split dataset is identical in both epochs without shuffling*
|
| 38 |
|
| 39 |
|
|
|
|
| 33 |
The model achieves a loss rate of 0.8528 on the validation dataset after two epochs.
|
| 34 |
|
| 35 |
**NOTE:** The model was trained for one epoch on the `train` split of dataset and after manual evaluation, I decided to go for another epoch.
|
| 36 |
+
|
| 37 |
The first epoch logs every 100 steps while the second epoch logs every 200 steps, but I am pasting the train and eval losses for both epochs bellow.
|
| 38 |
+
|
| 39 |
*The `train` split of the dataset was shuffled before the second epoch. The `test` split dataset is identical in both epochs without shuffling*
|
| 40 |
|
| 41 |
|