init

app.py

@@ -25,7 +25,7 @@ def fine_tune_model(model_name, dataset_name, hub_id, num_epochs, batch_size, lr
         # Tokenize the dataset
         def tokenize_function(examples):
             max_length = 256
-            return tokenizer(examples['text'], padding=max_length, truncation=True)
+            return tokenizer(examples['text'], padding='longest', max_length=max_length, truncation=True)
     
         tokenized_datasets = dataset.map(tokenize_function, batched=True)