diff --git a/README.md b/README.md
index 69f153e..b283908 100755
--- a/README.md
+++ b/README.md
@@ -129,6 +129,7 @@ Some additional flags you can pass are:
 
 ## To-Do
 
+* reduce load time for creating / preparing dataloaders.
 * properly pass in `modules` names to `weight_quantization` and `activation_quantization`.
 * train and release a model.
 * extend to multiple languages (VALL-E X) and extend to SpeechX features.
diff --git a/vall_e/config.py b/vall_e/config.py
index 341e088..fcb3a4d 100755
--- a/vall_e/config.py
+++ b/vall_e/config.py
@@ -467,7 +467,7 @@ try:
 	# cached_property stopped working...
 	if cfg.dataset.use_hdf5:
 		try:
-			cfg.hdf5 = h5py.File(f'{cfg.cfg_path}/{cfg.dataset.hdf5_name}', 'r' if cfg.distributed else 'a')
+			cfg.hdf5 = h5py.File(f'{cfg.cfg_path}/{cfg.dataset.hdf5_name}', 'r' if cfg.distributed else 'a') # to-do, have an easy to set flag that determines if training or creating the dataset
 		except Exception as e:
 			print("Error while opening HDF5 file:", f'{cfg.cfg_path}/{cfg.dataset.hdf5_name}', str(e))
 			cfg.dataset.use_hdf5 = False
diff --git a/vall_e/data.py b/vall_e/data.py
index 382c36a..4338250 100755
--- a/vall_e/data.py
+++ b/vall_e/data.py
@@ -466,9 +466,9 @@ def create_train_val_dataloader():
 	train_dataset.sample_type = cfg.dataset.sample_type #"speaker"
 
 	subtrain_dataset = copy.deepcopy(train_dataset)
-	subtrain_dataset.head_(cfg.evaluation.size)
-	subtrain_dataset.interleaved_reorder_(cfg.get_spkr)
-	#subtrain_dataset.training_(False)
+	if subtrain_dataset.sample_type == "path":
+		subtrain_dataset.head_(cfg.evaluation.size)
+		subtrain_dataset.interleaved_reorder_(cfg.get_spkr)
 
 	train_dl = _create_dataloader(train_dataset, training=True)
 	val_dl = _create_dataloader(val_dataset, training=False)
@@ -564,8 +564,19 @@ def create_dataset_hdf5():
 	hf.close()
 
 if __name__ == "__main__":
-	create_dataset_hdf5()
+	import argparse
+
+	parser = argparse.ArgumentParser("Save trained model to path.")
+	parser.add_argument("--create-hdf5", action="store_true")
+	args = parser.parse_args()
+
+	if args.create_hdf5:
+		create_dataset_hdf5()
 
 	train_dl, subtrain_dl, val_dl = create_train_val_dataloader()
-	sample = train_dl.dataset[0]
-	print(sample)
+	print("Training DL:", next(iter(train_dl)))
+	print("Training DL:", next(iter(train_dl)))
+	print("Evaluation DL:", next(iter(subtrain_dl)))
+	print("Evaluation DL:", next(iter(subtrain_dl)))
+	print("Validation DL:", next(iter(val_dl)))
+	print("Validation DL:", next(iter(val_dl)))