Upload 7 files

mp_20_sinc100/.hydra/config.yaml

@@ -0,0 +1,184 @@
+expname: mp_20_sinc100
+core:
+  version: 0.0.1
+  tags:
+  - ${now:%Y-%m-%d}
+data:
+  root_path: ${oc.env:PROJECT_ROOT}/data/mp_20
+  prop: xrd
+  num_targets: 1
+  niggli: true
+  primitive: false
+  graph_method: crystalnn
+  xrd_filter: both
+  lattice_scale_method: scale_length
+  preprocess_workers: 30
+  readout: mean
+  max_atoms: 20
+  otf_graph: false
+  eval_model_name: mp20
+  nanomaterial_size_angstrom: 100
+  n_presubsample: 4096
+  n_postsubsample: 512
+  wavesource: CuKa
+  train_max_epochs: 1000
+  early_stopping_patience: 100000
+  teacher_forcing_max_epoch: 500
+  datamodule:
+    _target_: cdvae.pl_data.datamodule.CrystDataModule
+    datasets:
+      train:
+        _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy train
+        path: ${data.root_path}/train.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+      val:
+      - _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy val
+        path: ${data.root_path}/val.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+      test:
+      - _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy test
+        path: ${data.root_path}/test.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+    num_workers:
+      train: 0
+      val: 0
+      test: 0
+    batch_size:
+      train: 128
+      val: 256
+      test: 256
+logging:
+  val_check_interval: 5
+  progress_bar_refresh_rate: 20
+  wandb:
+    name: ${expname}
+    project: crystal_generation_xrd
+    entity: null
+    log_model: true
+    mode: online
+    group: ${expname}
+  wandb_watch:
+    log: all
+    log_freq: 500
+  lr_monitor:
+    logging_interval: step
+    log_momentum: false
+model:
+  encoder:
+    _target_: cdvae.pl_modules.gnn.DimeNetPlusPlusWrap
+    num_targets: ${data.num_targets}
+    hidden_channels: 128
+    num_blocks: 4
+    int_emb_size: 64
+    basis_emb_size: 8
+    out_emb_channels: 256
+    num_spherical: 7
+    num_radial: 6
+    otf_graph: ${data.otf_graph}
+    cutoff: 7.0
+    max_num_neighbors: 20
+    envelope_exponent: 5
+    num_before_skip: 1
+    num_after_skip: 2
+    num_output_layers: 3
+    readout: ${data.readout}
+  decoder:
+    _target_: cdvae.pl_modules.decoder.GemNetTDecoder
+    hidden_dim: 128
+    latent_dim: ${model.latent_dim}
+    max_neighbors: ${model.max_neighbors}
+    radius: ${model.radius}
+    scale_file: ${oc.env:PROJECT_ROOT}/cdvae/pl_modules/gemnet/gemnet-dT.json
+  _target_: cdvae.pl_modules.model.CDVAE
+  hidden_dim: 256
+  latent_dim: 256
+  fc_num_layers: 1
+  max_atoms: ${data.max_atoms}
+  cost_natom: 1.0
+  cost_coord: 10.0
+  cost_type: 1.0
+  cost_lattice: 10.0
+  cost_composition: 1.0
+  cost_edge: 10.0
+  cost_property: 1.0
+  beta: 0.01
+  teacher_forcing_lattice: true
+  teacher_forcing_max_epoch: ${data.teacher_forcing_max_epoch}
+  max_neighbors: 20
+  radius: 7.0
+  sigma_begin: 10.0
+  sigma_end: 0.01
+  type_sigma_begin: 5.0
+  type_sigma_end: 0.01
+  num_noise_level: 50
+  predict_property: true
+  prop_arch: dense
+optim:
+  optimizer:
+    _target_: torch.optim.Adam
+    lr: 0.0005
+    betas:
+    - 0.9
+    - 0.999
+    eps: 1.0e-08
+    weight_decay: 0
+  use_lr_scheduler: true
+  lr_scheduler:
+    _target_: torch.optim.lr_scheduler.CosineAnnealingWarmRestarts
+    T_0: 65
+    T_mult: 2
+    eta_min: 1.0e-06
+train:
+  deterministic: false
+  random_seed: 42
+  pl_trainer:
+    fast_dev_run: false
+    num_nodes: 1
+    precision: 32
+    max_epochs: ${data.train_max_epochs}
+    accumulate_grad_batches: 1
+    num_sanity_val_steps: 2
+    gradient_clip_val: 0.5
+    gradient_clip_algorithm: value
+    profiler: simple
+  monitor_metric: val_loss
+  monitor_metric_mode: min
+  early_stopping:
+    patience: ${data.early_stopping_patience}
+    verbose: false
+  model_checkpoints:
+    save_top_k: 1
+    verbose: false

mp_20_sinc100/.hydra/hydra.yaml

@@ -0,0 +1,166 @@
+hydra:
+  run:
+    dir: ${oc.env:HYDRA_JOBS}/singlerun/${now:%Y-%m-%d}/${expname}/
+  sweep:
+    dir: ${oc.env:HYDRA_JOBS}/multirun/${now:%Y-%m-%d}/${expname}/
+    subdir: ${hydra.job.num}_${hydra.job.id}
+  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.mode=RUN
+    task:
+    - data=mp_20_sinc100
+    - expname=mp_20_sinc100
+    - model.predict_property=True
+  job:
+    name: run
+    chdir: null
+    override_dirname: data=mp_20_sinc100,expname=mp_20_sinc100,model.predict_property=True
+    id: ???
+    num: ???
+    config_name: default
+    env_set:
+      WANDB_START_METHOD: thread
+      WANDB_DIR: ${oc.env:WABDB_DIR}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /home/gabeguo/cdvae_xrd
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/gabeguo/cdvae_xrd/conf
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/gabeguo/cdvae_xrd/outputs/singlerun/2024-09-11/mp_20_sinc100
+    choices:
+      train: default
+      optim: alt
+      model: vae
+      model/decoder: gemnet
+      model/encoder: dimenet
+      logging: default
+      data: mp_20_sinc100
+      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

mp_20_sinc100/.hydra/overrides.yaml

@@ -0,0 +1,3 @@
+- data=mp_20_sinc100
+- expname=mp_20_sinc100
+- model.predict_property=True

mp_20_sinc100/epoch=954-step=304645.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddff14ab8e4c05ea8442ebdc25a7908979155c0a8742565e4c26def0f004d631
+size 60596273

mp_20_sinc100/hparams.yaml

@@ -0,0 +1,184 @@
+expname: mp_20_sinc100
+core:
+  version: 0.0.1
+  tags:
+  - ${now:%Y-%m-%d}
+data:
+  root_path: ${oc.env:PROJECT_ROOT}/data/mp_20
+  prop: xrd
+  num_targets: 1
+  niggli: true
+  primitive: false
+  graph_method: crystalnn
+  xrd_filter: both
+  lattice_scale_method: scale_length
+  preprocess_workers: 30
+  readout: mean
+  max_atoms: 20
+  otf_graph: false
+  eval_model_name: mp20
+  nanomaterial_size_angstrom: 100
+  n_presubsample: 4096
+  n_postsubsample: 512
+  wavesource: CuKa
+  train_max_epochs: 1000
+  early_stopping_patience: 100000
+  teacher_forcing_max_epoch: 500
+  datamodule:
+    _target_: cdvae.pl_data.datamodule.CrystDataModule
+    datasets:
+      train:
+        _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy train
+        path: ${data.root_path}/train.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+      val:
+      - _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy val
+        path: ${data.root_path}/val.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+      test:
+      - _target_: cdvae.pl_data.dataset.CrystDataset
+        name: Formation energy test
+        path: ${data.root_path}/test.csv
+        prop: ${data.prop}
+        niggli: ${data.niggli}
+        primitive: ${data.primitive}
+        graph_method: ${data.graph_method}
+        xrd_filter: ${data.xrd_filter}
+        lattice_scale_method: ${data.lattice_scale_method}
+        preprocess_workers: ${data.preprocess_workers}
+        nanomaterial_size_angstrom: ${data.nanomaterial_size_angstrom}
+        n_presubsample: ${data.n_presubsample}
+        n_postsubsample: ${data.n_postsubsample}
+        wavesource: ${data.wavesource}
+    num_workers:
+      train: 0
+      val: 0
+      test: 0
+    batch_size:
+      train: 128
+      val: 256
+      test: 256
+logging:
+  val_check_interval: 5
+  progress_bar_refresh_rate: 20
+  wandb:
+    name: ${expname}
+    project: crystal_generation_xrd
+    entity: null
+    log_model: true
+    mode: online
+    group: ${expname}
+  wandb_watch:
+    log: all
+    log_freq: 500
+  lr_monitor:
+    logging_interval: step
+    log_momentum: false
+model:
+  encoder:
+    _target_: cdvae.pl_modules.gnn.DimeNetPlusPlusWrap
+    num_targets: ${data.num_targets}
+    hidden_channels: 128
+    num_blocks: 4
+    int_emb_size: 64
+    basis_emb_size: 8
+    out_emb_channels: 256
+    num_spherical: 7
+    num_radial: 6
+    otf_graph: ${data.otf_graph}
+    cutoff: 7.0
+    max_num_neighbors: 20
+    envelope_exponent: 5
+    num_before_skip: 1
+    num_after_skip: 2
+    num_output_layers: 3
+    readout: ${data.readout}
+  decoder:
+    _target_: cdvae.pl_modules.decoder.GemNetTDecoder
+    hidden_dim: 128
+    latent_dim: ${model.latent_dim}
+    max_neighbors: ${model.max_neighbors}
+    radius: ${model.radius}
+    scale_file: ${oc.env:PROJECT_ROOT}/cdvae/pl_modules/gemnet/gemnet-dT.json
+  _target_: cdvae.pl_modules.model.CDVAE
+  hidden_dim: 256
+  latent_dim: 256
+  fc_num_layers: 1
+  max_atoms: ${data.max_atoms}
+  cost_natom: 1.0
+  cost_coord: 10.0
+  cost_type: 1.0
+  cost_lattice: 10.0
+  cost_composition: 1.0
+  cost_edge: 10.0
+  cost_property: 1.0
+  beta: 0.01
+  teacher_forcing_lattice: true
+  teacher_forcing_max_epoch: ${data.teacher_forcing_max_epoch}
+  max_neighbors: 20
+  radius: 7.0
+  sigma_begin: 10.0
+  sigma_end: 0.01
+  type_sigma_begin: 5.0
+  type_sigma_end: 0.01
+  num_noise_level: 50
+  predict_property: true
+  prop_arch: dense
+optim:
+  optimizer:
+    _target_: torch.optim.Adam
+    lr: 0.0005
+    betas:
+    - 0.9
+    - 0.999
+    eps: 1.0e-08
+    weight_decay: 0
+  use_lr_scheduler: true
+  lr_scheduler:
+    _target_: torch.optim.lr_scheduler.CosineAnnealingWarmRestarts
+    T_0: 65
+    T_mult: 2
+    eta_min: 1.0e-06
+train:
+  deterministic: false
+  random_seed: 42
+  pl_trainer:
+    fast_dev_run: false
+    num_nodes: 1
+    precision: 32
+    max_epochs: ${data.train_max_epochs}
+    accumulate_grad_batches: 1
+    num_sanity_val_steps: 2
+    gradient_clip_val: 0.5
+    gradient_clip_algorithm: value
+    profiler: simple
+  monitor_metric: val_loss
+  monitor_metric_mode: min
+  early_stopping:
+    patience: ${data.early_stopping_patience}
+    verbose: false
+  model_checkpoints:
+    save_top_k: 1
+    verbose: false

mp_20_sinc100/lattice_scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4018cd5d5015b57796c7cdd9408ba11ab94a35bb4cc414e5f38a5e7ebe164af6
+size 1091

mp_20_sinc100/run.log

@@ -0,0 +1,12 @@
+[2024-09-11 15:38:35,401][hydra.utils][INFO] - Instantiating <cdvae.pl_data.datamodule.CrystDataModule>
+[2024-09-11 16:02:35,727][hydra.utils][INFO] - Instantiating <cdvae.pl_modules.model.CDVAE>
+[2024-09-11 16:02:35,768][torch.distributed.nn.jit.instantiator][INFO] - Created a temporary directory at /tmp/tmpobad8_vl
+[2024-09-11 16:02:35,769][torch.distributed.nn.jit.instantiator][INFO] - Writing /tmp/tmpobad8_vl/_remote_module_non_scriptable.py
+[2024-09-11 16:02:52,343][hydra.utils][INFO] - Adding callback <LearningRateMonitor>
+[2024-09-11 16:02:52,343][hydra.utils][INFO] - Adding callback <EarlyStopping>
+[2024-09-11 16:02:52,344][hydra.utils][INFO] - Adding callback <ModelCheckpoint>
+[2024-09-11 16:02:52,346][hydra.utils][INFO] - Instantiating <WandbLogger>
+[2024-09-11 16:02:52,348][hydra.utils][INFO] - W&B is now watching <{cfg.logging.wandb_watch.log}>!
+[2024-09-11 16:02:59,851][hydra.utils][INFO] - Instantiating the Trainer
+[2024-09-11 16:02:59,898][hydra.utils][INFO] - Starting training!
+[2024-09-12 22:07:43,568][hydra.utils][INFO] - Starting testing!