Update README.md

README.md

@@ -62,7 +62,7 @@ If you want to use the lora model from guanaco-7b-leh-v2-adapter/ , remember to
 
 ## Training Setup
 * 2x3090 with model parallel
-* batch size = bsz 2 * grad acc 64 = 128
+* batch size = bsz 8 * grad acc 16 = 128
 * ctx cut off length = 1024
 * only train on output (with loss mask)
 * enable group of len