Questions about training data

[L-xiaolu]

Hello, thank you for your open source work. It has been of great help to me who is new to seismology. I have a few questions about this. I would like to ask: whether the model training data can be in seed or sac format. In addition, I saw that the dataset file contains data and csv that can be used for training, but the csv file is different from the csv file in test_data. Why is there such a difference?
Thanks for your reply and best wishes!