deploy: af82609

.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: ad184163ed18f9ae867121d9a28f54ab
+config: 798fcda09776c00173518fd6e6e6aaa7
 tags: 645f666f9bcd5a90fca523b33c5a78b7

_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

@@ -1 +1,186 @@
-python: can't open file '/home/runner/work/fairchem/fairchem/src/fairchem/main.py': [Errno 2] No such file or directory
+2024-05-10 20:06:03 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:126: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
+  warnings.warn(
+2024-05-10 20:06:04 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-10 20:06:04 (INFO): amp: true
+cmd:
+  checkpoint_dir: fine-tuning/checkpoints/2024-05-10-20-05-20-ft-oxides
+  commit: af82609
+  identifier: ft-oxides
+  logs_dir: fine-tuning/logs/tensorboard/2024-05-10-20-05-20-ft-oxides
+  print_every: 10
+  results_dir: fine-tuning/results/2024-05-10-20-05-20-ft-oxides
+  seed: 0
+  timestamp_id: 2024-05-10-20-05-20-ft-oxides
+dataset:
+  a2g_args:
+    r_energy: true
+    r_forces: true
+  format: ase_db
+  key_mapping:
+    force: forces
+    y: energy
+  src: train.db
+eval_metrics:
+  metrics:
+    energy:
+    - mae
+    forces:
+    - forcesx_mae
+    - forcesy_mae
+    - forcesz_mae
+    - mae
+    - cosine_similarity
+    - magnitude_error
+    misc:
+    - energy_forces_within_threshold
+gpus: 0
+logger: tensorboard
+loss_fns:
+- energy:
+    coefficient: 1
+    fn: mae
+- forces:
+    coefficient: 1
+    fn: l2mae
+model: gemnet_oc
+model_attributes:
+  activation: silu
+  atom_edge_interaction: true
+  atom_interaction: true
+  cbf:
+    name: spherical_harmonics
+  cutoff: 12.0
+  cutoff_aeaint: 12.0
+  cutoff_aint: 12.0
+  cutoff_qint: 12.0
+  direct_forces: true
+  edge_atom_interaction: true
+  emb_size_aint_in: 64
+  emb_size_aint_out: 64
+  emb_size_atom: 256
+  emb_size_cbf: 16
+  emb_size_edge: 512
+  emb_size_quad_in: 32
+  emb_size_quad_out: 32
+  emb_size_rbf: 16
+  emb_size_sbf: 32
+  emb_size_trip_in: 64
+  emb_size_trip_out: 64
+  envelope:
+    exponent: 5
+    name: polynomial
+  extensive: true
+  forces_coupled: false
+  max_neighbors: 30
+  max_neighbors_aeaint: 20
+  max_neighbors_aint: 1000
+  max_neighbors_qint: 8
+  num_after_skip: 2
+  num_atom: 3
+  num_atom_emb_layers: 2
+  num_before_skip: 2
+  num_blocks: 4
+  num_concat: 1
+  num_global_out_layers: 2
+  num_output_afteratom: 3
+  num_radial: 128
+  num_spherical: 7
+  otf_graph: true
+  output_init: HeOrthogonal
+  qint_tags:
+  - 1
+  - 2
+  quad_interaction: true
+  rbf:
+    name: gaussian
+  regress_forces: true
+  sbf:
+    name: legendre_outer
+  symmetric_edge_symmetrization: false
+noddp: false
+optim:
+  batch_size: 4
+  clip_grad_norm: 10
+  ema_decay: 0.999
+  energy_coefficient: 1
+  eval_batch_size: 16
+  eval_every: 10
+  factor: 0.8
+  force_coefficient: 1
+  load_balancing: atoms
+  loss_energy: mae
+  lr_initial: 0.0005
+  max_epochs: 1
+  mode: min
+  num_workers: 2
+  optimizer: AdamW
+  optimizer_params:
+    amsgrad: true
+  patience: 3
+  scheduler: ReduceLROnPlateau
+  weight_decay: 0
+outputs:
+  energy:
+    level: system
+  forces:
+    eval_on_free_atoms: true
+    level: atom
+    train_on_free_atoms: false
+slurm: {}
+task:
+  dataset: ase_db
+test_dataset:
+  a2g_args:
+    r_energy: false
+    r_forces: false
+  src: test.db
+trainer: ocp
+val_dataset:
+  a2g_args:
+    r_energy: true
+    r_forces: true
+  src: val.db
+
+2024-05-10 20:06:04 (INFO): Loading dataset: ase_db
+2024-05-10 20:06:05 (INFO): rank: 0: Sampler created...
+2024-05-10 20:06:05 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 20:06:05 (INFO): rank: 0: Sampler created...
+2024-05-10 20:06:05 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 20:06:05 (INFO): rank: 0: Sampler created...
+2024-05-10 20:06:05 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 20:06:05 (INFO): Loading model: gemnet_oc
+2024-05-10 20:06:05 (WARNING): Unrecognized arguments: ['symmetric_edge_symmetrization']
+2024-05-10 20:06:07 (INFO): Loaded GemNetOC with 38864438 parameters.
+2024-05-10 20:06:07 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-10 20:06:07 (WARNING): Using `weight_decay` from `optim` instead of `optim.optimizer_params`.Please update your config to use `optim.optimizer_params.weight_decay`.`optim.weight_decay` will soon be deprecated.
+2024-05-10 20:06:07 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gnoc_oc22_oc20_all_s2ef.pt
+2024-05-10 20:06:07 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint. 
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/amp/autocast_mode.py:250: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
+  warnings.warn(
+2024-05-10 20:06:31 (INFO): energy_forces_within_threshold: 0.00e+00, energy_mae: 6.77e+00, forcesx_mae: 4.11e-02, forcesy_mae: 3.63e-02, forcesz_mae: 5.26e-02, forces_mae: 4.33e-02, forces_cosine_similarity: 8.24e-02, forces_magnitude_error: 7.42e-02, loss: 6.86e+00, lr: 5.00e-04, epoch: 1.69e-01, step: 1.00e+01
+2024-05-10 20:06:31 (INFO): Evaluating on val.
+device 0:   0%|          | 0/2 [00:00<?, ?it/s]/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+device 0:  50%|█████     | 1/2 [00:04<00:04,  4.77s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.63s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.86s/it]
+2024-05-10 20:06:39 (INFO): energy_forces_within_threshold: 0.0000, energy_mae: 8.7333, forcesx_mae: 0.0231, forcesy_mae: 0.0188, forcesz_mae: 0.0198, forces_mae: 0.0206, forces_cosine_similarity: -0.0317, forces_magnitude_error: 0.0290, loss: 8.6590, epoch: 0.1695
+Traceback (most recent call last):
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/../../main.py", line 8, in <module>
+    main()
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/core/_cli.py", line 89, in main
+    Runner()(config)
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/core/_cli.py", line 41, in __call__
+    self.task.run()
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/core/tasks/task.py", line 51, in run
+    self.trainer.train(
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/core/trainers/ocp_trainer.py", line 201, in train
+    self.update_best(
+  File "/home/runner/work/fairchem/fairchem/src/fairchem/core/trainers/base_trainer.py", line 671, in update_best
+    "mae" in primary_metric
+TypeError: argument of type 'NoneType' is not iterable

_downloads/819e10305ddd6839cd7da05935b17060/mass-inference.txt

@@ -0,0 +1,145 @@
+2024-05-10 20:08:47 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:126: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
+  warnings.warn(
+2024-05-10 20:08:49 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-10 20:08:49 (INFO): amp: true
+cmd:
+  checkpoint_dir: ./checkpoints/2024-05-10-20-09-36
+  commit: af82609
+  identifier: ''
+  logs_dir: ./logs/tensorboard/2024-05-10-20-09-36
+  print_every: 10
+  results_dir: ./results/2024-05-10-20-09-36
+  seed: 0
+  timestamp_id: 2024-05-10-20-09-36
+dataset:
+  a2g_args:
+    r_energy: false
+    r_forces: false
+  format: ase_db
+  key_mapping:
+    force: forces
+    y: energy
+  select_args:
+    selection: natoms>5,xc=PBE
+  src: data.db
+eval_metrics:
+  metrics:
+    energy:
+    - mae
+    forces:
+    - forcesx_mae
+    - forcesy_mae
+    - forcesz_mae
+    - mae
+    - cosine_similarity
+    - magnitude_error
+    misc:
+    - energy_forces_within_threshold
+gpus: 0
+logger: tensorboard
+loss_fns:
+- energy:
+    coefficient: 1
+    fn: mae
+- forces:
+    coefficient: 1
+    fn: l2mae
+model: gemnet_t
+model_attributes:
+  activation: silu
+  cbf:
+    name: spherical_harmonics
+  cutoff: 6.0
+  direct_forces: true
+  emb_size_atom: 512
+  emb_size_bil_trip: 64
+  emb_size_cbf: 16
+  emb_size_edge: 512
+  emb_size_rbf: 16
+  emb_size_trip: 64
+  envelope:
+    exponent: 5
+    name: polynomial
+  extensive: true
+  max_neighbors: 50
+  num_after_skip: 2
+  num_atom: 3
+  num_before_skip: 1
+  num_blocks: 3
+  num_concat: 1
+  num_radial: 128
+  num_spherical: 7
+  otf_graph: true
+  output_init: HeOrthogonal
+  rbf:
+    name: gaussian
+  regress_forces: true
+noddp: false
+optim:
+  batch_size: 16
+  clip_grad_norm: 10
+  ema_decay: 0.999
+  energy_coefficient: 1
+  eval_batch_size: 16
+  eval_every: 5000
+  force_coefficient: 1
+  loss_energy: mae
+  loss_force: atomwisel2
+  lr_gamma: 0.8
+  lr_initial: 0.0005
+  lr_milestones:
+  - 64000
+  - 96000
+  - 128000
+  - 160000
+  - 192000
+  max_epochs: 80
+  num_workers: 2
+  optimizer: AdamW
+  optimizer_params:
+    amsgrad: true
+  warmup_steps: -1
+outputs:
+  energy:
+    level: system
+  forces:
+    eval_on_free_atoms: true
+    level: atom
+    train_on_free_atoms: false
+slurm: {}
+task:
+  dataset: ase_db
+  prediction_dtype: float32
+test_dataset:
+  a2g_args:
+    r_energy: false
+    r_forces: false
+  select_args:
+    selection: natoms>5,xc=PBE
+  src: data.db
+trainer: ocp
+val_dataset: null
+
+2024-05-10 20:08:49 (INFO): Loading dataset: ase_db
+2024-05-10 20:08:49 (INFO): rank: 0: Sampler created...
+2024-05-10 20:08:49 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 20:08:49 (INFO): rank: 0: Sampler created...
+2024-05-10 20:08:49 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 20:08:49 (INFO): Loading model: gemnet_t
+2024-05-10 20:08:51 (INFO): Loaded GemNetT with 31671825 parameters.
+2024-05-10 20:08:51 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-10 20:08:51 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
+2024-05-10 20:08:51 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint. 
+2024-05-10 20:08:51 (WARNING): Scale factor comment not found in model
+2024-05-10 20:08:51 (INFO): Predicting on test.
+device 0:   0%|                                           | 0/3 [00:00<?, ?it/s]/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
+  storage = elem.storage()._new_shared(numel)
+/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/amp/autocast_mode.py:250: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
+  warnings.warn(
+device 0:  33%|███████████▋                       | 1/3 [00:03<00:07,  3.53s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:05<00:02,  2.60s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:06<00:00,  1.78s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:06<00:00,  2.10s/it]
+2024-05-10 20:08:58 (INFO): Writing results to ./results/2024-05-10-20-09-36/ocp_predictions.npz
+2024-05-10 20:08:58 (INFO): Total time taken: 6.454441070556641
+Elapsed time = 13.1 seconds