Update README.md

README.md

@@ -20,7 +20,7 @@ tags:
 This is a tiny 20.75M parameter model showing how small models can perform on a little bunch of data.
 
 ## Training data
-We used the first 100 million tokens of the 10BT Sample of Fineweb-Edu to train this model for 5000 steps for a final loss of ~4.0 and a val loss of 4.1566.
+We used the first 100 million tokens of the 10BT Sample of Fineweb-Edu to train this model for 5000 steps for a final loss of 4.2044 and a val loss of 4.1566.
 
 ## Training specs
 - Architecture: nanoGPT