Update README.md

README.md

@@ -62,7 +62,7 @@ Use the following resolution for the best results:
 The model has been trained on a tag-balanced dataset of 2k best pixiv illustrations, at resolution of 768, for 856 eopchs (214 epochs * 4 repeats per epoch). 
 
 
-The training takes about 4 days on a 8 x H100 cluster. By the time training ends the loss is still consistently going down, so further training could be beneficial.
+The training takes about 3 days on a 8 x H100 cluster. By the time training ends the loss is still consistently going down, so further training could be beneficial.