Jirui Jin

Thanks a lot for answering so fast @bdecost, but I think when you trained the model for the material project dataset, it should be a larger dataset than me. And...

The dataset I am using is from oqmd, half of them (12000) only have 5 five atoms. In the rest of the dataset, the range for atoms number is from...

Thank you@knc6, I will try it now!

I got the exact same error when I lower the batch size to 5 or 8.

 Thank you for the information. Above is the slurm configuration I am using. And the problem is: 

I am using the default setting: num_workers: int = 4. I will decrease it and retry. Thank you!

Still have the same problem. I will wait for the fixing.

I used get_primitive_structure function in Pymatgen for all my cif files and set num_workers = 10 in the config file, then the problem is solved!