Update README.md

README.md

@@ -44,7 +44,7 @@ The fine-tuning process used **0.4 trillion tokens**, using AlphaFold database w
 - **Hardware**: 64 NVIDIA A100 80GB GPUs
 - **Learning Rate**: Max learning rate of 1e-4
 - **Scheduler**: Cosine decay with 2.5% warmup
-- **Tokens Trained**: 4T tokens
+- **Tokens Trained**: 0.4T tokens
 - **Training steps**: 200k steps
 
 ## Tokenization