Nobuhiro Ueda
commited on
Commit
•
3d802fd
1
Parent(s):
b2326b3
add acknowledgments
Browse files
README.md
CHANGED
@@ -58,3 +58,8 @@ The following hyperparameters were used during pre-training:
|
|
58 |
- lr_scheduler_type: linear schedule with warmup
|
59 |
- training_steps: 330000
|
60 |
- warmup_steps: 10000
|
|
|
|
|
|
|
|
|
|
|
|
58 |
- lr_scheduler_type: linear schedule with warmup
|
59 |
- training_steps: 330000
|
60 |
- warmup_steps: 10000
|
61 |
+
|
62 |
+
## Acknowledgments
|
63 |
+
|
64 |
+
This work was supported by Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) through General Collaboration Project no. jh221004, "Developing a Platform for Constructing and Sharing of Large-Scale Japanese Language Models".
|
65 |
+
For training models, we used the mdx: a platform for the data-driven future.
|