dev

app.py

@@ -108,7 +108,7 @@ def fine_tune_model(model_name, dataset_name, hub_id, api_key, num_epochs, batch
                 model_inputs["labels"] = labels["input_ids"]
                 return model_inputs
         
-            tokenized_datasets = dataset.map(tokenize_function, batched=True, batch_size=32)
+            tokenized_datasets = dataset.map(tokenize_function, batched=True)
             
             tokenized_datasets['train'].save_to_disk(f'/data/{hub_id.strip()}_train_dataset')
             tokenized_datasets['test'].save_to_disk(f'/data/{hub_id.strip()}_test_dataset')