robinsmits
commited on
Commit
•
cca8d18
1
Parent(s):
e18c885
Update README.md
Browse files
README.md
CHANGED
@@ -83,6 +83,8 @@ The used dataset does not allow commercial usage.
|
|
83 |
|
84 |
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)
|
85 |
|
|
|
|
|
86 |
It achieves the following results on the evaluation set:
|
87 |
- Loss: 0.2610
|
88 |
- Rewards/chosen: -0.7248
|
|
|
83 |
|
84 |
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)
|
85 |
|
86 |
+
Training was performed with Google Colab PRO on a A100 - 40GB and lasted around 4 hours.
|
87 |
+
|
88 |
It achieves the following results on the evaluation set:
|
89 |
- Loss: 0.2610
|
90 |
- Rewards/chosen: -0.7248
|