Update README.md
Browse files
README.md
CHANGED
|
@@ -14,10 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [lvwerra/gpt2-imdb](https://huggingface.co/lvwerra/gpt2-imdb) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
-
|
|
|
|
| 18 |
- Rewards/chosen: -0.0805
|
| 19 |
- Rewards/rejected: -0.4417
|
| 20 |
-
- Rewards/accuracies: 0.
|
| 21 |
- Rewards/margins: 0.3612
|
| 22 |
- Logps/rejected: -268.1027
|
| 23 |
- Logps/chosen: -236.0704
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [lvwerra/gpt2-imdb](https://huggingface.co/lvwerra/gpt2-imdb) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Step: 6500
|
| 18 |
+
- Loss: 11.7007
|
| 19 |
- Rewards/chosen: -0.0805
|
| 20 |
- Rewards/rejected: -0.4417
|
| 21 |
+
- Rewards/accuracies: 0.9000
|
| 22 |
- Rewards/margins: 0.3612
|
| 23 |
- Logps/rejected: -268.1027
|
| 24 |
- Logps/chosen: -236.0704
|