Update README.md

README.md

@@ -3,6 +3,8 @@ license: mit
 ---
 # This is NOT A GUIDE for LoRA training, and you should NEVER treat it as.
 
-# This serves as a onging project that I share some of the interesting findings where I learned or discovered during my journey in LoRA training.
+# This serves as a onging project that I share some of the personal opinions or interesting findings where I learned or discovered during my journey in LoRA training.
 
-- To start with, LoRA training could be easy and quick with proper dataset preparation and training setup; but I'm sure most would not be satisfied with a LoRA that is barely useable.
+### To start with, LoRA training could be easy and quick with proper dataset preparation and training setup; but I'm sure most would not be satisfied with a LoRA that is barely useable.
+
+- **Everyone has their own standard about what a good LoRA should be. And to train a quality driven LoRA, dataset preparation is the first step that I'd put special care on.**