Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,7 @@ Hyperparameters:
|
|
| 20 |
- Batch size of 4 (2 real x 2 accumulated)
|
| 21 |
- Maximum of 5 epochs, early stopping (visual observation), stopped after 3
|
| 22 |
- Gradient clipping norm value of 1.0
|
|
|
|
| 23 |
|
| 24 |
Training prompt format:
|
| 25 |
|
|
|
|
| 20 |
- Batch size of 4 (2 real x 2 accumulated)
|
| 21 |
- Maximum of 5 epochs, early stopping (visual observation), stopped after 3
|
| 22 |
- Gradient clipping norm value of 1.0
|
| 23 |
+
- PRO beta of 4
|
| 24 |
|
| 25 |
Training prompt format:
|
| 26 |
|