Update actual training steps to 29k

README.md

@@ -20,7 +20,7 @@ This model is trained with [ACT (Action Chunking with Transformers)](https://arx
 | **Policy** | ACT (Action Chunking with Transformers) |
 | **Dataset** | 31 episodes, ~27K frames |
 | **Cameras** | 2× USB cameras (front + wrist), 640×480 |
-| **Training Time** | ~100K steps on NVIDIA RTX 5070 Ti |
+| **Training Time** | ~29K steps on NVIDIA RTX 5070 Ti |
 | **Final Loss** | ~0.057 |
 
 ## Usage