Update README.md

README.md

@@ -31,6 +31,10 @@ New for v6:
 
 And of course yay Unsloth for letting this all train on a single A100 with variable (wildly variable) context length. 
 
+Here's what the train/eval loss looked like (eval is orange, train is blue). I think that's not terrible, but :shrug:.
+
+![Here's what the train/eval loss looked like](https://cdn-uploads.huggingface.co/production/uploads/662c17b252e194d5d436c708/Xa86cb6scFWqxWSKzt5R0.png)
+
 It was trained with the following settings:
 
 ```