laurabernardy
commited on
Commit
·
b220bd2
1
Parent(s):
a9ca440
Update README.md
Browse files
README.md
CHANGED
@@ -38,8 +38,8 @@ GPT-2 model for Text Generation in luxembourgish language, trained on 711 MB of
|
|
38 |
The training took place on a 32 GB Nvidia Tesla V100
|
39 |
- with One Cycle policy for the learning rate
|
40 |
- with the help of fastai's LR finder
|
41 |
-
- for
|
42 |
-
- for
|
43 |
- using the fastai library
|
44 |
|
45 |
|
|
|
38 |
The training took place on a 32 GB Nvidia Tesla V100
|
39 |
- with One Cycle policy for the learning rate
|
40 |
- with the help of fastai's LR finder
|
41 |
+
- for 49.2 hours
|
42 |
+
- for 18 epochs and 8 cycles
|
43 |
- using the fastai library
|
44 |
|
45 |
|