Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ license: apache-2.0
|
|
| 16 |
|
| 17 |
### Technical Metrics
|
| 18 |
- Using a slightly modified vocabulary of the Qwen2.5 series to support multilingual capabilities
|
| 19 |
-
- Trained for approximately `100` hours on `L40*7` devices, with
|
| 20 |
- Main training parameters:
|
| 21 |
- Batch Size: 1792
|
| 22 |
- Learning Rate: 5e-04
|
|
|
|
| 16 |
|
| 17 |
### Technical Metrics
|
| 18 |
- Using a slightly modified vocabulary of the Qwen2.5 series to support multilingual capabilities
|
| 19 |
+
- Trained for approximately `100` hours on `L40*7` devices, with about `60B` tokens
|
| 20 |
- Main training parameters:
|
| 21 |
- Batch Size: 1792
|
| 22 |
- Learning Rate: 5e-04
|