Update preprocess Dataset

preprocess Dataset

@@ -1,7 +1,7 @@
 from datasets import load_dataset
 
 # Load your custom dataset (ensure it's in the proper format)
-dataset = load_dataset('text', data_files={'train': 'train.txt', 'test': 'test.txt'})
+dataset = load_dataset('EU_Regulation_261_2004', data_files={'train': 'train.txt', 'test': 'test.txt'})
 
 # Load the GPT-2 tokenizer
 from transformers import GPT2Tokenizer
@@ -10,6 +10,6 @@ tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
 
 # Preprocess the dataset
 def preprocess_function(examples):
-    return tokenizer(examples['text'], padding='max_length', truncation=True)
+    return tokenizer(examples['EU_Regulation_261_2004'], padding='max_length', truncation=True)
 
 encoded_dataset = dataset.map(preprocess_function, batched=True)