Commit
•
f9ddff8
1
Parent(s):
c7dabed
Update README.md
Browse files
README.md
CHANGED
|
@@ -49,7 +49,8 @@ with `<s>` and the end of one by `</s>`
|
|
| 49 |
|
| 50 |
### Pretraining
|
| 51 |
|
| 52 |
-
The model was trained on 2 V100 GPUs for 500K steps with a batch size of 128 and a sequence length of 512.
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Contributions
|
|
|
|
| 49 |
|
| 50 |
### Pretraining
|
| 51 |
|
| 52 |
+
The model was trained on 2 V100 GPUs for 500K steps with a batch size of 128 and a sequence length of 512. MLM probability - 15%, num_attention_heads=12,
|
| 53 |
+
num_hidden_layers=6.
|
| 54 |
|
| 55 |
|
| 56 |
### Contributions
|