Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,8 @@ alephbert.eval()
|
|
| 38 |
|
| 39 |
Trained on a DGX machine (8 V100 GPUs) using the standard huggingface training procedure.
|
| 40 |
|
|
|
|
|
|
|
| 41 |
To optimize training time we split the data into 4 sections based on max number of tokens:
|
| 42 |
|
| 43 |
1. num tokens < 32 (70M sentences)
|
|
|
|
| 38 |
|
| 39 |
Trained on a DGX machine (8 V100 GPUs) using the standard huggingface training procedure.
|
| 40 |
|
| 41 |
+
Since the larger part of our training data is based on tweets we decided to start by optimizing using Masked Language Model loss only.
|
| 42 |
+
|
| 43 |
To optimize training time we split the data into 4 sections based on max number of tokens:
|
| 44 |
|
| 45 |
1. num tokens < 32 (70M sentences)
|