Upload folder using huggingface_hub

alm-edit/csp_backbone/.hydra/config.yaml

@@ -0,0 +1,147 @@
+data_module:
+  _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
+  - _target_: mattergen.common.data.transform.set_composition_count
+    _partial_: true
+  dataset_transforms:
+  - _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+    _partial_: true
+  average_density: 0.05771451654022283
+  root_dir: ${oc.env:PROJECT_ROOT}/../datasets/cache/broader_csp
+  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: 0
+    val: 0
+    test: 0
+  batch_size:
+    train: ${eval:'(512 // ${trainer.accumulate_grad_batches}) // (${trainer.devices}
+      * ${trainer.num_nodes})'}
+    val: 8
+    test: 8
+  max_epochs: 900
+trainer:
+  _target_: pytorch_lightning.Trainer
+  accelerator: gpu
+  devices: 8
+  num_nodes: 9
+  precision: 32
+  max_epochs: ${data_module.max_epochs}
+  accumulate_grad_batches: 1
+  gradient_clip_val: 0.5
+  gradient_clip_algorithm: value
+  check_val_every_n_epoch: 5
+  strategy:
+    _target_: pytorch_lightning.strategies.ddp.DDPStrategy
+    find_unused_parameters: true
+  callbacks:
+  - _target_: pytorch_lightning.callbacks.LearningRateMonitor
+    logging_interval: step
+    log_momentum: false
+  - _target_: pytorch_lightning.callbacks.ModelCheckpoint
+    monitor: loss_val
+    mode: min
+    save_top_k: 1
+    save_last: true
+    verbose: false
+    every_n_epochs: 1
+    filename: '{epoch}-{loss_val:.2f}'
+  - _target_: pytorch_lightning.callbacks.TQDMProgressBar
+    refresh_rate: 50
+  - _target_: mattergen.common.data.callback.SetPropertyScalers
+  max_steps: 200000
+lightning_module:
+  _target_: mattergen.diffusion.lightning_module.DiffusionLightningModule
+  optimizer_partial:
+    lr: 0.0001
+    _target_: torch.optim.Adam
+    _partial_: true
+  scheduler_partials:
+  - scheduler:
+      _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+      factor: 0.6
+      patience: 100
+      min_lr: 1.0e-06
+      _partial_: true
+    interval: epoch
+    frequency: 1
+    monitor: loss_train
+    strict: true
+  diffusion_module:
+    _target_: mattergen.diffusion.diffusion_module.DiffusionModule
+    model:
+      _target_: mattergen.denoiser.GemNetTDenoiser
+      hidden_dim: 512
+      gemnet:
+        _target_: mattergen.common.gemnet.gemnet.GemNetT
+        num_targets: 1
+        latent_dim: ${eval:'${..hidden_dim} * (1 + len(${..property_embeddings}))'}
+        atom_embedding:
+          _target_: mattergen.common.gemnet.layers.embedding_block.AtomEmbedding
+          emb_size: ${...hidden_dim}
+          with_mask_type: ${eval:'${...denoise_atom_types} and "${...atom_type_diffusion}"
+            == "mask"'}
+        emb_size_atom: ${..hidden_dim}
+        emb_size_edge: ${..hidden_dim}
+        max_neighbors: 50
+        max_cell_images_per_dim: 5
+        cutoff: 7.0
+        num_blocks: 4
+        regress_stress: true
+        otf_graph: true
+        scale_file: ${oc.env:PROJECT_ROOT}/common/gemnet/gemnet-dT.json
+      denoise_atom_types: true
+      atom_type_diffusion: mask
+      property_embeddings_adapt: {}
+      property_embeddings: {}
+    corruption:
+      _target_: mattergen.diffusion.corruption.multi_corruption.MultiCorruption
+      sdes:
+        pos:
+          _target_: mattergen.common.diffusion.corruption.NumAtomsVarianceAdjustedWrappedVESDE
+          wrapping_boundary: 1.0
+          sigma_max: 5.0
+          limit_info_key: num_atoms
+        cell:
+          _target_: mattergen.common.diffusion.corruption.LatticeVPSDE.from_vpsde_config
+          vpsde_config:
+            beta_min: 0.1
+            beta_max: 20
+            limit_density: ${data_module.average_density}
+            limit_var_scaling_constant: 0.25
+    loss_fn:
+      _target_: mattergen.common.loss.MaterialsLoss
+      reduce: sum
+      include_pos: true
+      include_cell: true
+      include_atomic_numbers: false
+      weights:
+        cell: 1.0
+        pos: 0.1
+    pre_corruption_fn:
+      _target_: mattergen.property_embeddings.SetEmbeddingType
+      p_unconditional: 0.2
+      dropout_fields_iid: false
+auto_resume: true

alm-edit/csp_backbone/.hydra/hydra.yaml

@@ -0,0 +1,168 @@
+hydra:
+  run:
+    dir: /data/users/sathyae/alm_runs/mg_csp_train_broader
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.run.dir=/data/users/sathyae/alm_runs/mg_csp_train_broader
+    - hydra.mode=RUN
+    task:
+    - data_module=broader_csp
+    - ~trainer.logger
+    - +trainer.max_steps=200000
+    - ++trainer.num_nodes=9
+    - ++trainer.devices=8
+    - ++data_module.batch_size.val=8
+    - ++data_module.batch_size.test=8
+  job:
+    name: run
+    chdir: null
+    override_dirname: ++data_module.batch_size.test=8,++data_module.batch_size.val=8,++trainer.devices=8,++trainer.num_nodes=9,+trainer.max_steps=200000,data_module=broader_csp,~trainer.logger
+    id: ???
+    num: ???
+    config_name: csp
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /data/users/sathyae/mclm/external/mattergen
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /data/users/sathyae/mclm/external/mattergen/mattergen/conf
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /data/users/sathyae/alm_runs/mg_csp_train_broader
+    choices:
+      lightning_module/diffusion_module/corruption: csp
+      lightning_module/diffusion_module/model: mattergen
+      lightning_module/diffusion_module: csp
+      lightning_module: default
+      trainer: default
+      data_module: broader_csp
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

alm-edit/csp_backbone/.hydra/overrides.yaml

@@ -0,0 +1,7 @@
+- data_module=broader_csp
+- ~trainer.logger
+- +trainer.max_steps=200000
+- ++trainer.num_nodes=9
+- ++trainer.devices=8
+- ++data_module.batch_size.val=8
+- ++data_module.batch_size.test=8

alm-edit/csp_backbone/checkpoints/epoch=229-step=197340.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0308d9f5720ee3b4e7e4f7b6f26fc1b76876742273022ff329a0f86ff6b00693
+size 460951163

alm-edit/csp_backbone/config.yaml

@@ -0,0 +1,147 @@
+data_module:
+  _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
+  - _target_: mattergen.common.data.transform.set_composition_count
+    _partial_: true
+  dataset_transforms:
+  - _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+    _partial_: true
+  average_density: 0.05771451654022283
+  root_dir: ${oc.env:PROJECT_ROOT}/../datasets/cache/broader_csp
+  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: 0
+    val: 0
+    test: 0
+  batch_size:
+    train: ${eval:'(512 // ${trainer.accumulate_grad_batches}) // (${trainer.devices}
+      * ${trainer.num_nodes})'}
+    val: 8
+    test: 8
+  max_epochs: 900
+trainer:
+  _target_: pytorch_lightning.Trainer
+  accelerator: gpu
+  devices: 8
+  num_nodes: 9
+  precision: 32
+  max_epochs: ${data_module.max_epochs}
+  accumulate_grad_batches: 1
+  gradient_clip_val: 0.5
+  gradient_clip_algorithm: value
+  check_val_every_n_epoch: 5
+  strategy:
+    _target_: pytorch_lightning.strategies.ddp.DDPStrategy
+    find_unused_parameters: true
+  callbacks:
+  - _target_: pytorch_lightning.callbacks.LearningRateMonitor
+    logging_interval: step
+    log_momentum: false
+  - _target_: pytorch_lightning.callbacks.ModelCheckpoint
+    monitor: loss_val
+    mode: min
+    save_top_k: 1
+    save_last: true
+    verbose: false
+    every_n_epochs: 1
+    filename: '{epoch}-{loss_val:.2f}'
+  - _target_: pytorch_lightning.callbacks.TQDMProgressBar
+    refresh_rate: 50
+  - _target_: mattergen.common.data.callback.SetPropertyScalers
+  max_steps: 200000
+lightning_module:
+  _target_: mattergen.diffusion.lightning_module.DiffusionLightningModule
+  optimizer_partial:
+    lr: 0.0001
+    _target_: torch.optim.Adam
+    _partial_: true
+  scheduler_partials:
+  - scheduler:
+      _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+      factor: 0.6
+      patience: 100
+      min_lr: 1.0e-06
+      _partial_: true
+    interval: epoch
+    frequency: 1
+    monitor: loss_train
+    strict: true
+  diffusion_module:
+    _target_: mattergen.diffusion.diffusion_module.DiffusionModule
+    model:
+      _target_: mattergen.denoiser.GemNetTDenoiser
+      hidden_dim: 512
+      gemnet:
+        _target_: mattergen.common.gemnet.gemnet.GemNetT
+        num_targets: 1
+        latent_dim: ${eval:'${..hidden_dim} * (1 + len(${..property_embeddings}))'}
+        atom_embedding:
+          _target_: mattergen.common.gemnet.layers.embedding_block.AtomEmbedding
+          emb_size: ${...hidden_dim}
+          with_mask_type: ${eval:'${...denoise_atom_types} and "${...atom_type_diffusion}"
+            == "mask"'}
+        emb_size_atom: ${..hidden_dim}
+        emb_size_edge: ${..hidden_dim}
+        max_neighbors: 50
+        max_cell_images_per_dim: 5
+        cutoff: 7.0
+        num_blocks: 4
+        regress_stress: true
+        otf_graph: true
+        scale_file: ${oc.env:PROJECT_ROOT}/common/gemnet/gemnet-dT.json
+      denoise_atom_types: true
+      atom_type_diffusion: mask
+      property_embeddings_adapt: {}
+      property_embeddings: {}
+    corruption:
+      _target_: mattergen.diffusion.corruption.multi_corruption.MultiCorruption
+      sdes:
+        pos:
+          _target_: mattergen.common.diffusion.corruption.NumAtomsVarianceAdjustedWrappedVESDE
+          wrapping_boundary: 1.0
+          sigma_max: 5.0
+          limit_info_key: num_atoms
+        cell:
+          _target_: mattergen.common.diffusion.corruption.LatticeVPSDE.from_vpsde_config
+          vpsde_config:
+            beta_min: 0.1
+            beta_max: 20
+            limit_density: ${data_module.average_density}
+            limit_var_scaling_constant: 0.25
+    loss_fn:
+      _target_: mattergen.common.loss.MaterialsLoss
+      reduce: sum
+      include_pos: true
+      include_cell: true
+      include_atomic_numbers: false
+      weights:
+        cell: 1.0
+        pos: 0.1
+    pre_corruption_fn:
+      _target_: mattergen.property_embeddings.SetEmbeddingType
+      p_unconditional: 0.2
+      dropout_fields_iid: false
+auto_resume: true

alm-edit/csp_backbone/lightning_logs/version_0/checkpoints/epoch=209-loss_val=0.20.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5970cadb72b970d862ff5d59a2b0c905ed20746ae7f0cfec0dc62d0e5ae7d73
+size 460951163

alm-edit/csp_backbone/lightning_logs/version_0/checkpoints/last.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd81a894a7c0158bfe214d0edc0c82258be70c2642b587920ac525b77d89fe8
+size 460951163

alm-edit/csp_backbone/lightning_logs/version_0/config.yaml

@@ -0,0 +1,172 @@
+auto_resume: true
+checkpoint_path: null
+data_module:
+  _recursive_: true
+  _target_: mattergen.common.data.datamodule.CrystDataModule
+  average_density: 0.05771451654022283
+  batch_size:
+    test: 8
+    train: 7
+    val: 8
+  dataset_transforms:
+  - _partial_: true
+    _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+  max_epochs: 900
+  num_workers:
+    test: 0
+    train: 0
+    val: 0
+  properties: []
+  root_dir: /data/users/sathyae/mclm/external/mattergen/mattergen/../datasets/cache/broader_csp
+  test_dataset:
+    _target_: mattergen.common.data.dataset.CrystalDataset.from_cache_path
+    cache_path: /data/users/sathyae/mclm/external/mattergen/mattergen/../datasets/cache/broader_csp/test
+    dataset_transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+    properties: []
+    transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.transform.symmetrize_lattice
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_chemical_system_string
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_composition_count
+  train_dataset:
+    _target_: mattergen.common.data.dataset.CrystalDataset.from_cache_path
+    cache_path: /data/users/sathyae/mclm/external/mattergen/mattergen/../datasets/cache/broader_csp/train
+    dataset_transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+    properties: []
+    transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.transform.symmetrize_lattice
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_chemical_system_string
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_composition_count
+  transforms:
+  - _partial_: true
+    _target_: mattergen.common.data.transform.symmetrize_lattice
+  - _partial_: true
+    _target_: mattergen.common.data.transform.set_chemical_system_string
+  - _partial_: true
+    _target_: mattergen.common.data.transform.set_composition_count
+  val_dataset:
+    _target_: mattergen.common.data.dataset.CrystalDataset.from_cache_path
+    cache_path: /data/users/sathyae/mclm/external/mattergen/mattergen/../datasets/cache/broader_csp/val
+    dataset_transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.dataset_transform.filter_sparse_properties
+    properties: []
+    transforms:
+    - _partial_: true
+      _target_: mattergen.common.data.transform.symmetrize_lattice
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_chemical_system_string
+    - _partial_: true
+      _target_: mattergen.common.data.transform.set_composition_count
+lightning_module:
+  _target_: mattergen.diffusion.lightning_module.DiffusionLightningModule
+  diffusion_module:
+    _target_: mattergen.diffusion.diffusion_module.DiffusionModule
+    corruption:
+      _target_: mattergen.diffusion.corruption.multi_corruption.MultiCorruption
+      sdes:
+        cell:
+          _target_: mattergen.common.diffusion.corruption.LatticeVPSDE.from_vpsde_config
+          vpsde_config:
+            beta_max: 20
+            beta_min: 0.1
+            limit_density: 0.05771451654022283
+            limit_var_scaling_constant: 0.25
+        pos:
+          _target_: mattergen.common.diffusion.corruption.NumAtomsVarianceAdjustedWrappedVESDE
+          limit_info_key: num_atoms
+          sigma_max: 5.0
+          wrapping_boundary: 1.0
+    loss_fn:
+      _target_: mattergen.common.loss.MaterialsLoss
+      include_atomic_numbers: false
+      include_cell: true
+      include_pos: true
+      reduce: sum
+      weights:
+        cell: 1.0
+        pos: 0.1
+    model:
+      _target_: mattergen.denoiser.GemNetTDenoiser
+      atom_type_diffusion: mask
+      denoise_atom_types: true
+      gemnet:
+        _target_: mattergen.common.gemnet.gemnet.GemNetT
+        atom_embedding:
+          _target_: mattergen.common.gemnet.layers.embedding_block.AtomEmbedding
+          emb_size: 512
+          with_mask_type: true
+        cutoff: 7.0
+        emb_size_atom: 512
+        emb_size_edge: 512
+        latent_dim: 512
+        max_cell_images_per_dim: 5
+        max_neighbors: 50
+        num_blocks: 4
+        num_targets: 1
+        otf_graph: true
+        regress_stress: true
+        scale_file: /data/users/sathyae/mclm/external/mattergen/mattergen/common/gemnet/gemnet-dT.json
+      hidden_dim: 512
+      property_embeddings: {}
+      property_embeddings_adapt: {}
+    pre_corruption_fn:
+      _target_: mattergen.property_embeddings.SetEmbeddingType
+      dropout_fields_iid: false
+      p_unconditional: 0.2
+  optimizer_partial:
+    _partial_: true
+    _target_: torch.optim.Adam
+    lr: 0.0001
+  scheduler_partials:
+  - frequency: 1
+    interval: epoch
+    monitor: loss_train
+    scheduler:
+      _partial_: true
+      _target_: torch.optim.lr_scheduler.ReduceLROnPlateau
+      factor: 0.6
+      min_lr: 1.0e-06
+      patience: 100
+    strict: true
+load_original: false
+params: {}
+trainer:
+  _target_: pytorch_lightning.Trainer
+  accelerator: gpu
+  accumulate_grad_batches: 1
+  callbacks:
+  - _target_: pytorch_lightning.callbacks.LearningRateMonitor
+    log_momentum: false
+    logging_interval: step
+  - _target_: pytorch_lightning.callbacks.ModelCheckpoint
+    every_n_epochs: 1
+    filename: '{epoch}-{loss_val:.2f}'
+    mode: min
+    monitor: loss_val
+    save_last: true
+    save_top_k: 1
+    verbose: false
+  - _target_: pytorch_lightning.callbacks.TQDMProgressBar
+    refresh_rate: 50
+  - _target_: mattergen.common.data.callback.SetPropertyScalers
+  check_val_every_n_epoch: 5
+  devices: 8
+  gradient_clip_algorithm: value
+  gradient_clip_val: 0.5
+  max_epochs: 900
+  max_steps: 200000
+  num_nodes: 9
+  precision: 32
+  strategy:
+    _target_: pytorch_lightning.strategies.ddp.DDPStrategy
+    find_unused_parameters: true

alm-edit/csp_backbone/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}