init

app.py

@@ -40,7 +40,7 @@ def fine_tune_model(model_name, dataset_name, hub_id, api_key, num_epochs, batch
     
         # Tokenize the dataset
         def tokenize_function(examples):
-            max_length = 128
+            max_length = 64
             # Assuming 'text' is the input and 'target' is the expected output
             model_inputs = tokenizer(
                 examples['text'], 
@@ -50,14 +50,13 @@ def fine_tune_model(model_name, dataset_name, hub_id, api_key, num_epochs, batch
             )
         
             # Setup the decoder input IDs (shifted right)
-            with tokenizer.as_target_tokenizer():
-                labels = tokenizer(
-                    examples['target'], 
-                    max_length=max_length,  # Set to None for dynamic padding
-                    padding=False,     # Disable padding here, we will handle it later
-                    truncation=True,
-                
-                )
+            labels = tokenizer(
+                examples['target'], 
+                max_length=max_length,  # Set to None for dynamic padding
+                padding=False,     # Disable padding here, we will handle it later
+                truncation=True,
+                text_target=examples['target']  # Use text_target for target text
+            )
         
             # Add labels to the model inputs
             model_inputs["labels"] = labels["input_ids"]