attempts to identify callbacks bug or trainer bug

trainer.py

@@ -94,22 +94,26 @@ class SmolLM3Trainer:
                     eval_loss = metrics.get('eval_loss', 'N/A')
                     print(f"📊 Evaluation at step {step}: eval_loss={eval_loss}")
         
-        # Add simple console callback
-        callbacks.append(SimpleConsoleCallback())
-        logger.info("Added simple console monitoring callback")
+        # Temporarily disable callbacks to debug the issue
+        callbacks = []
+        logger.info("Callbacks disabled for debugging")
         
-        # Try to add Trackio callback if available
-        if self.monitor and self.monitor.enable_tracking:
-            try:
-                trackio_callback = self.monitor.create_monitoring_callback()
-                if trackio_callback:
-                    callbacks.append(trackio_callback)
-                    logger.info("Added Trackio monitoring callback")
-                else:
-                    logger.warning("Failed to create Trackio callback")
-            except Exception as e:
-                logger.error(f"Error creating Trackio callback: {e}")
-                logger.info("Continuing with console monitoring only")
+        # # Add simple console callback
+        # callbacks.append(SimpleConsoleCallback())
+        # logger.info("Added simple console monitoring callback")
+        # 
+        # # Try to add Trackio callback if available
+        # if self.monitor and self.monitor.enable_tracking:
+        #     try:
+        #         trackio_callback = self.monitor.create_monitoring_callback()
+        #         if trackio_callback:
+        #         callbacks.append(trackio_callback)
+        #         logger.info("Added Trackio monitoring callback")
+        #     else:
+        #         logger.warning("Failed to create Trackio callback")
+        # except Exception as e:
+        #     logger.error(f"Error creating Trackio callback: {e}")
+        #     logger.info("Continuing with console monitoring only")
         
         # Try standard Trainer first (more stable with callbacks)
         try:
@@ -181,6 +185,7 @@ class SmolLM3Trainer:
         
         # Start training
         try:
+            logger.info("About to start trainer.train()")
             train_result = self.trainer.train()
             
             # Save the final model