dev

app.py

@@ -90,7 +90,7 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
                 examples['text'], 
                 max_length=max_length,  # Set to None for dynamic padding
                 truncation=True,
-                padding='max_length',
+                padding='longest',
                 return_tensors='pt', 
             )
         
@@ -99,8 +99,8 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
                 examples['target'], 
                 max_length=max_length,  # Set to None for dynamic padding
                 truncation=True,
-                padding='max_length',
-                text_target=examples['target'],
+                padding='longest',
+                #text_target=examples['target'],
                 return_tensors='pt', 
             )
         
@@ -131,9 +131,7 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             )            
         except:                                            
             tokenizer = AutoTokenizer.from_pretrained('google/t5-efficient-tiny-nh8')
-            # Tokenize the dataset
-            
-        
+            # Tokenize the dataset                    
             first_half = dataset['train'].select(range(half_size))
             tokenized_half = tokenize_function(first_half)