_target_: mattergen.common.data.datamodule.CrystDataModule
_recursive_: true
properties: []

transforms:
- _target_: mattergen.common.data.transform.symmetrize_lattice
  _partial_: true
- _target_: mattergen.common.data.transform.set_chemical_system_string
  _partial_: true

dataset_transforms:
- _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
  _partial_: true

# Mean nsites / volume over the 73,350 MP-40 training structures.
average_density: 0.061705096895101764
root_dir: ${oc.env:PROJECT_ROOT}/../datasets/cache/mp_40

train_dataset:
  _target_: mattergen.common.data.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_: mattergen.common.data.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}

test_dataset:
  _target_: mattergen.common.data.dataset.CrystalDataset.from_cache_path
  cache_path: ${data_module.root_dir}/test
  properties: ${data_module.properties}
  transforms: ${data_module.transforms}
  dataset_transforms: ${data_module.dataset_transforms}

num_workers:
  train: 8
  val: 4
  test: 4

batch_size:
  train: ${eval:'(512 // ${trainer.accumulate_grad_batches}) // (${trainer.devices} * ${trainer.num_nodes})'}
  val: ${eval:'(64 // (${trainer.devices} * ${trainer.num_nodes}))'}
  test: ${eval:'(64 // (${trainer.devices} * ${trainer.num_nodes}))'}

max_epochs: 900