diff --git a/studio/backend/routes/export.py b/studio/backend/routes/export.py
index 6b335bc139..7f18f50eaa 100644
--- a/studio/backend/routes/export.py
+++ b/studio/backend/routes/export.py
@@ -86,6 +86,14 @@ async def load_checkpoint(
             if trn.is_training_active():
                 logger.info("Stopping active training to free GPU memory for export")
                 trn.stop_training()
+                # Wait for training subprocess to actually exit before proceeding,
+                # otherwise it may still hold GPU memory when export tries to load.
+                for _ in range(60):  # up to 30s
+                    if not trn.is_training_active():
+                        break
+                    import time; time.sleep(0.5)
+                else:
+                    logger.warning("Training subprocess did not exit within 30s, proceeding anyway")
         except Exception as e:
             logger.warning("Could not stop training: %s", e)
 
diff --git a/studio/backend/routes/training.py b/studio/backend/routes/training.py
index c0ee6deff7..84315291a9 100644
--- a/studio/backend/routes/training.py
+++ b/studio/backend/routes/training.py
@@ -304,6 +304,7 @@ async def reset_training(
             )
 
         logger.info("Reset training state: clearing runtime + metric history")
+        backend._should_stop = False  # Clear stop flag so status returns to idle
         backend.trainer._update_progress(
             is_training=False, is_completed=False, error=None,
             status_message="Ready to train", step=0, loss=0.0, epoch=0,