Commit
•
a13f385
1
Parent(s):
b0e3850
Update README.md
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ language:
|
|
8 |
BERT base (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work [Scaling Laws for BERT in Low-Resource Settings]() at ACL2023 Findings.
|
9 |
|
10 |
The model has 124M parameters (12L), and a vocab size of 50K.
|
11 |
-
It was trained for 500K steps with a sequence length of 512 tokens.
|
12 |
|
13 |
Results
|
14 |
-----------
|
|
|
8 |
BERT base (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work [Scaling Laws for BERT in Low-Resource Settings]() at ACL2023 Findings.
|
9 |
|
10 |
The model has 124M parameters (12L), and a vocab size of 50K.
|
11 |
+
It was trained for 500K steps with a sequence length of 512 tokens and batch-size of 256.
|
12 |
|
13 |
Results
|
14 |
-----------
|