Update app.py

app.py

@@ -62,7 +62,11 @@ dataset = load_dataset(
     streaming=True
 )
 
-dataset_size = len(dataset)
+#dataset_size = len(dataset)
+try:
+    dataset_size = dataset.info.splits['train'].num_examples
+except (AttributeError, KeyError):
+    dataset_size = 25000
 
 # Load gpt and modifed weights for captions
 gpt = GPT2LMHeadModel.from_pretrained('gpt2')