Fixing the wattage using the training

README.md

@@ -109,8 +109,8 @@ To Be added
 ### Training Dynamics
 
 - **GPU Utilization**: Stable at ~N/A% during training
-- **GPU Memory**: \~20% allocated (~4GB / 12GB) (Math is not mathing??)
-- **Power Usage**: ~50W average
+- **GPU Memory**: \~20% allocated (\~4GB / 12GB) (Math is not mathing??)
+- **Power Usage**: ~250W average
 - **Throughput**: ~300 tokens/sec
 
 ### Performance Metrics