clarify HW usage

README.md

@@ -32,7 +32,7 @@ The model is **very sensitive** to system message. Make sure you're using this s
 ## Q&A
 
 **Hardware used to trained it?**  
-I used a HF space with 4xL40S, trained for 5 hours. Eval loss is about 0.8
+I used a HF space with 4xL40S, trained for 5 hours (v1) and an additional of 6 hours (v2)
 
 **Benchmark?**  
 I don't have time to do it alone. If you can help, please open a discussion!