Update README.md

README.md

@@ -10,6 +10,10 @@ This is the 26 categorical finetune of nomic-bert-2048's encoder.
 
 253,952,000 - 77 token samples with 20% mask rate
 
+775,000,000 - 144-256 token samples with 30% mask rate
+
+Total samples > 1bil
+
 The model has learned to categorize certain masked patterns with their categories and special tokens.
 
 ```