Update README.md

README.md

@@ -23,7 +23,7 @@ inference:
 Using RLHF (Reinforcement Learning from Human Feedback) to finetune [mrm8488/bloom-560m-finetuned-sd-prompts](https://hf.co/mrm8488/bloom-560m-finetuned-sd-prompts) further for SD2.0
 ```
 batch_size = 16
-learning_rate = 0.001
+learning_rate = 0.001 # this is why I didn't have to spend _forever_ on it
 ```
 
 Generate extension with "\<s>Prompt: " and whatever your normal prompt is.