Update app.py

app.py

@@ -13,7 +13,6 @@ tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
 
 labels = [label for label in dataset['train'].features.keys() if label not in ['text']]
 
-console.log( labels )
 def preprocess_data(examples):
   # take a batch of texts
   text = examples["text"]
@@ -31,9 +30,10 @@ def preprocess_data(examples):
   
   return encoding
 
+encoded_dataset = dataset.map(preprocess_data, batched=True, remove_columns=dataset['train'].column_names)
 
-
-
+example = encoded_dataset['train'][0]
+console.log(example.keys())