live trading options

NN/models/advanced_transformer_trading.py

@@ -1051,6 +1051,12 @@ class TradingTransformerTrainer:
         
         # Move model to device
         self.model.to(self.device)
+        logger.info(f"✅ Model moved to device: {self.device}")
+        
+        # Log GPU info if available
+        if torch.cuda.is_available():
+            logger.info(f"   GPU: {torch.cuda.get_device_name(0)}")
+            logger.info(f"   GPU Memory: {torch.cuda.get_device_properties(0).total_memory / 1024**3:.2f} GB")
         
         # MEMORY OPTIMIZATION: Enable gradient checkpointing if configured
         # This trades 20% compute for 30-40% memory savings
@@ -1512,9 +1518,19 @@ class TradingTransformerTrainer:
                     del batch[key]
             del batch
             
-            # Clear CUDA cache
+            # Clear CUDA cache and log GPU memory usage
             if torch.cuda.is_available():
                 torch.cuda.empty_cache()
+                
+                # Log GPU memory usage periodically (every 10 steps)
+                if not hasattr(self, '_step_counter'):
+                    self._step_counter = 0
+                self._step_counter += 1
+                
+                if self._step_counter % 10 == 0:
+                    allocated = torch.cuda.memory_allocated() / 1024**2
+                    reserved = torch.cuda.memory_reserved() / 1024**2
+                    logger.debug(f"GPU Memory: {allocated:.1f}MB allocated, {reserved:.1f}MB reserved")
             
             return result