Philip May
commited on
Commit
·
43a7d0e
1
Parent(s):
1cac1d8
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,7 @@ The training was conducted with the following hyperparameters:
|
|
| 32 |
- warmup_ratio: 0.3
|
| 33 |
- number of train epochs: 10
|
| 34 |
- gradient accumulation steps: 2
|
|
|
|
| 35 |
|
| 36 |
## Datasets and Preprocessing
|
| 37 |
|
|
|
|
| 32 |
- warmup_ratio: 0.3
|
| 33 |
- number of train epochs: 10
|
| 34 |
- gradient accumulation steps: 2
|
| 35 |
+
- learning rate: 5e-5
|
| 36 |
|
| 37 |
## Datasets and Preprocessing
|
| 38 |
|