Update README.md

README.md

@@ -12,13 +12,13 @@ At the very core of the development of this model is the desire to make sure tha
 
 Test this out and see if you find anything interesting or intriguing. I will keep iterating more versions but this one seems like a fun and useful way to start.
 
-## Training
+## Training (Done on the First Draft V1 of the dataset)
 ```
 
 key: str = "system", key2: str = "instruction"
 
 batch_size=1
-epochs=10 (I let it keep going until it finally converged)
+epochs=10 (Don't do this for the current version of the dataset, your model WILL overfit. It's very potent.)
 r=16
 lora_alpha=32 
 lora_dropout=0.001