debugging why predictions are not comming

model.py

@@ -20,41 +20,43 @@ class BertClassifier(LabelStudioMLBase):
         self._model = None
         self.tokenizer = None
 
-    def predict(self, tasks, context=None, **kwargs):
-        """
-        tasks: Label Studio tasks in JSON format
-        context: Label Studio context in JSON format (for interactive labeling)
-        returns: predictions array in JSON format
-        """
+    def predict(self, tasks, **kwargs):
+        """Make predictions for tasks"""
         predictions = []
         
         try:
-            # Process each task
+            logger.info("=== PREDICT METHOD CALLED ===")
+            logger.info(f"Number of tasks received: {len(tasks)}")
+            
             for task in tasks:
-                # Get text from the task
+                logger.info(f"Processing task ID: {task.get('id')}")
+                logger.info(f"Task content: {json.dumps(task, indent=2)}")
+                
+                # Get the text to classify
                 text = task['data'].get('text', '')
-                if not text:
-                    continue
-                    
-                # Make prediction
+                logger.info(f"Text to predict: {text[:100]}...")
+                
                 prediction = {
                     'result': [{
-                        'from_name': 'sentiment',  # must match your labeling config
-                        'to_name': 'text',         # must match your labeling config
+                        'from_name': 'sentiment',
+                        'to_name': 'text',
                         'type': 'choices',
                         'value': {
-                            'choices': ['some_label']  # your predicted label
+                            'choices': ['brand']
                         }
                     }],
-                    'score': 0.0,  # confidence score between 0 and 1
-                    'model_version': self.model_dir
+                    'score': 0.5,
+                    'model_version': 'v1'
                 }
+                logger.info(f"Generated prediction: {json.dumps(prediction, indent=2)}")
                 predictions.append(prediction)
                 
         except Exception as e:
-            print(f"Error in predict: {str(e)}")
+            logger.error(f"Error in predict: {str(e)}")
+            logger.error("Full error details:", exc_info=True)
             return []
         
+        logger.info(f"Returning {len(predictions)} predictions")
         return predictions
 
     def fit(self, completions, workdir=None, **kwargs):