robinsmits
commited on
Commit
•
1c1ad28
1
Parent(s):
014a7af
Update README.md
Browse files
README.md
CHANGED
@@ -79,6 +79,8 @@ More information needed
|
|
79 |
|
80 |
## Training and evaluation data
|
81 |
|
|
|
|
|
82 |
It achieves the following results on the evaluation set:
|
83 |
- Loss: 0.2610
|
84 |
- Rewards/chosen: -0.7248
|
|
|
79 |
|
80 |
## Training and evaluation data
|
81 |
|
82 |
+
The training notebook is available at the following link: [Qwen1_5_7B_Dutch_Chat_DPO](https://github.com/RobinSmits/Dutch-LLMs/blob/main/Qwen1_5_7B_Dutch_Chat_DPO.ipynb)
|
83 |
+
|
84 |
It achieves the following results on the evaluation set:
|
85 |
- Loss: 0.2610
|
86 |
- Rewards/chosen: -0.7248
|