Commit
•
d6b0289
1
Parent(s):
b6b8cc7
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ For training data, we generate long contexts by augmenting [SlimPajama](https://
|
|
| 40 |
| Steps | 30 | 24 |
|
| 41 |
| Total Tokens | 63 M | 101 M |
|
| 42 |
| Learning Rate | 2.00E-05 | 2.00E-05 |
|
| 43 |
-
| # GPUs |
|
| 44 |
| GPU Type | NVIDIA L40S| NVIDIA L40S|
|
| 45 |
|
| 46 |
## The Gradient AI Team
|
|
|
|
| 40 |
| Steps | 30 | 24 |
|
| 41 |
| Total Tokens | 63 M | 101 M |
|
| 42 |
| Learning Rate | 2.00E-05 | 2.00E-05 |
|
| 43 |
+
| # GPUs | 32 | 32 |
|
| 44 |
| GPU Type | NVIDIA L40S| NVIDIA L40S|
|
| 45 |
|
| 46 |
## The Gradient AI Team
|