INNER CODE UNIT · Python
_hours
Guitaricet/relora · pretokenize.py:74
_hours = (time.time() - _time) / 3600
logger.info(f"Tokenization and chunking took {_hours:.2f} hours")
dataset.save_to_disk(save_path)
logger.info(f"Saved the dataset to {save_path}")
with open(os.path.join(save_path, "args.json"), "w") as f:
json.dump(vars(args), f, indent=4)
print("In main")
if __name__ == "__main__":
print("Starting the script")
args = parse_args()
main(args)