Update README.md
Browse files
README.md
CHANGED
|
@@ -52,7 +52,7 @@ The model was trained on high-quality parallel corpora:
|
|
| 52 |
- **Framework:** Hugging Face Transformers
|
| 53 |
- **Batch size:** 128
|
| 54 |
- **Learning rate:** 2e-5
|
| 55 |
-
- **Epochs:**
|
| 56 |
- **Max sequence length:** 128 tokens
|
| 57 |
|
| 58 |
### Data Preprocessing
|
|
|
|
| 52 |
- **Framework:** Hugging Face Transformers
|
| 53 |
- **Batch size:** 128
|
| 54 |
- **Learning rate:** 2e-5
|
| 55 |
+
- **Epochs:** 3
|
| 56 |
- **Max sequence length:** 128 tokens
|
| 57 |
|
| 58 |
### Data Preprocessing
|