| _target_: onescience.datapipes.materials.mattergen.datamodule.CrystDataModule | |
| _recursive_: true | |
| properties: [] | |
| # Supported properties: | |
| # - dft_bulk_modulus | |
| # - dft_band_gap | |
| # - dft_mag_density | |
| # - ml_bulk_modulus | |
| # - hhi_score | |
| # - space_group | |
| # - energy_above_hull | |
| dataset_transforms: | |
| - _target_: onescience.datapipes.materials.mattergen.dataset_transform.filter_sparse_properties | |
| _partial_: true | |
| transforms: | |
| - _target_: onescience.datapipes.materials.mattergen.transform.symmetrize_lattice | |
| _partial_: true | |
| - _target_: onescience.datapipes.materials.mattergen.transform.set_chemical_system_string | |
| _partial_: true | |
| average_density: 0.05771451654022283 # atoms/Angstrom**3 : this is used in models/scripts/run.py to set lattice_limit_density | |
| root_dir: ${oc.env:ONESCIENCE_DATASETS_DIR,/public/share/sugonhpcapp01/onestore/onedatasets}/matchem/mattergen/cache/alex_mp_20 | |
| train_dataset: | |
| _target_: onescience.datapipes.materials.mattergen.dataset.CrystalDataset.from_cache_path | |
| cache_path: ${data_module.root_dir}/train | |
| properties: ${data_module.properties} | |
| transforms: ${data_module.transforms} | |
| dataset_transforms: ${data_module.dataset_transforms} | |
| val_dataset: | |
| _target_: onescience.datapipes.materials.mattergen.dataset.CrystalDataset.from_cache_path | |
| cache_path: ${data_module.root_dir}/val | |
| properties: ${data_module.properties} | |
| transforms: ${data_module.transforms} | |
| dataset_transforms: ${data_module.dataset_transforms} | |
| num_workers: | |
| train: 0 | |
| val: 0 | |
| batch_size: | |
| # total batch size of 512, adjust for number of devices, nodes, and gradient accumulation | |
| train: ${eval:'(512 // ${trainer.accumulate_grad_batches}) // (${trainer.devices} * ${trainer.num_nodes})'} | |
| val: ${eval:'(512 // ${trainer.accumulate_grad_batches}) // (${trainer.devices} * ${trainer.num_nodes})'} | |
| max_epochs: 2200 | |