Update README.md

README.md

@@ -13,6 +13,10 @@ These models are intended to be used as foundational models that can be e.g. ins
 
 
 
+All models are trained for 300B steps.
+
+
+
 **Parameters**
 | Model | Layers | Dim  | Heads | Params |
 |--------|--------|------|-------|--------|