GitLab

Changes resume_model_weights_only flag in train_openfold to reload weights only, without parsing a time step.

This adds workers=True to the Lightning seed_everything function which guarantees different random states across all processes in distributed training. Prior to that some processes on different GPUs with the same worker ID could share the same random state.

Note that this will break reproducibility between runs prior to and after this change.

Also removes the seed and supress_output modules that were not used anymore in OpenFold.

Changes resume_model_weights_only flag in train_openfold to reload weights only, without parsing a time step.

update train_openfold to handle val_mmcif_cache;update datamodule to handle if validation mmcif cache is not provided

Fixes for memory usage in multimer dataloader, spatial cropping, and tensor type conversions within model.