Fix typo in the learning rate of Stage 2
Browse files
README.md
CHANGED
@@ -47,7 +47,7 @@ AMPLIFY is an efficient, state-of-the-art protein language model pre-trained usi
|
|
47 |
| `max-steps` | 1000000 | 25000 (120M) or 50000 (350M) |
|
48 |
| `max-length` | 512 | 2048 |
|
49 |
| `optimizer` | adamw | adamw |
|
50 |
-
| `lr` | 0.001 |
|
51 |
| `betas` | (0.9, 0.95) | (0.9, 0.95) |
|
52 |
| `eps` | 1.0e-08 | 1.0e-08 |
|
53 |
| `weight-decay` | 0.01 | 0.01 |
|
|
|
47 |
| `max-steps` | 1000000 | 25000 (120M) or 50000 (350M) |
|
48 |
| `max-length` | 512 | 2048 |
|
49 |
| `optimizer` | adamw | adamw |
|
50 |
+
| `lr` | 0.001 | 0.0001 |
|
51 |
| `betas` | (0.9, 0.95) | (0.9, 0.95) |
|
52 |
| `eps` | 1.0e-08 | 1.0e-08 |
|
53 |
| `weight-decay` | 0.01 | 0.01 |
|