Problems in the process of potential model training

[BALIZU]

I encountered this error log when training a potential model.
" raise ValueError("The passed save_path is not a valid checkpoint: " +
ValueError: The passed save_path is not a valid checkpoint: /media/6.9T/media/zj/Na-K-Mg-La/train/n"
The screenshot shows the relevant error.

The version of Deep-kit is v2.1.3
This error is similar to "Error when freezing a model #270", regrettably, no suggested answers.
I tested for a long time, but it didn't work. Thank you for your replies.
Sincerely!

[BALIZU]

The dp train command followed by -in caused this problem, thank you all.