batch size when training

[tengjiayan20]

Batch size is said to be 256 in the article. But why batch size in run.sh is 32? And why batch size in run_ddp_master.sh is 4?

[gasvn]

32 is for one GPU. 256 = 32 X 8

[tengjiayan20]

Thank you!

[ILLLLUSION]

Does setting different batch-sizes on a single gpu have a big impact on the final result?

[gasvn]

We align the batch size with the DiT, so we didn't try other settings.