Update README.md
Browse files
README.md
CHANGED
@@ -57,7 +57,7 @@ datasets:
|
|
57 |
|
58 |
0.5 Epoch completed of dataset [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) with learning_rate=8e-6
|
59 |
|
60 |
-
Result seems pretty good even with half epoch and low learning rate, the effect is smoother and less pronounced
|
61 |
|
62 |
Outputs are more compliant and verbose, less sloppy and safety aligned.
|
63 |
|
|
|
57 |
|
58 |
0.5 Epoch completed of dataset [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) with learning_rate=8e-6
|
59 |
|
60 |
+
Result seems pretty good even with half epoch and low learning rate, the effect is smoother and less pronounced but its probably not *optimal*.
|
61 |
|
62 |
Outputs are more compliant and verbose, less sloppy and safety aligned.
|
63 |
|