diff --git a/utils/donut_dataset_stream.py b/utils/donut_dataset_stream.py
index f295c8d..e10a0fa 100644
--- a/utils/donut_dataset_stream.py
+++ b/utils/donut_dataset_stream.py
@@ -48,6 +48,7 @@ class DonutDataset(Dataset):
         self.added_tokens = added_tokens
 
         self.dataset = load_dataset(dataset_name_or_path, split=self.split, streaming=True).with_format("torch")
+        print(self.dataset)
         self.dataset_length = len(self.dataset)
 
         self.gt_token_sequences = []