deploy: 06869ab

_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

@@ -1,17 +1,17 @@
-2024-05-11 01:12:43 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+2024-05-13 01:51:15 (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(
-2024-05-11 01:12:45 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-05-11 01:12:45 (INFO): amp: true
+2024-05-13 01:51:17 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-13 01:51:17 (INFO): amp: true
 cmd:
-  checkpoint_dir: fine-tuning/checkpoints/2024-05-11-01-12-32-ft-oxides
-  commit: 42ae7ad
+  checkpoint_dir: fine-tuning/checkpoints/2024-05-13-01-50-56-ft-oxides
+  commit: 06869ab
   identifier: ft-oxides
-  logs_dir: fine-tuning/logs/tensorboard/2024-05-11-01-12-32-ft-oxides
+  logs_dir: fine-tuning/logs/tensorboard/2024-05-13-01-50-56-ft-oxides
   print_every: 10
-  results_dir: fine-tuning/results/2024-05-11-01-12-32-ft-oxides
+  results_dir: fine-tuning/results/2024-05-13-01-50-56-ft-oxides
   seed: 0
-  timestamp_id: 2024-05-11-01-12-32-ft-oxides
+  timestamp_id: 2024-05-13-01-50-56-ft-oxides
 dataset:
   a2g_args:
     r_energy: true
@@ -142,34 +142,34 @@ val_dataset:
     r_forces: true
   src: val.db
 
-2024-05-11 01:12:45 (INFO): Loading dataset: ase_db
-2024-05-11 01:12:45 (INFO): rank: 0: Sampler created...
-2024-05-11 01:12:45 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-11 01:12:45 (INFO): rank: 0: Sampler created...
-2024-05-11 01:12:45 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-11 01:12:45 (INFO): rank: 0: Sampler created...
-2024-05-11 01:12:45 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-11 01:12:45 (INFO): Loading model: gemnet_oc
-2024-05-11 01:12:45 (WARNING): Unrecognized arguments: ['symmetric_edge_symmetrization']
-2024-05-11 01:12:47 (INFO): Loaded GemNetOC with 38864438 parameters.
-2024-05-11 01:12:47 (WARNING): Model gradient logging to tensorboard not yet supported.
-2024-05-11 01:12:47 (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.
-2024-05-11 01:12:48 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gnoc_oc22_oc20_all_s2ef.pt
-2024-05-11 01:12:48 (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. 
+2024-05-13 01:51:17 (INFO): Loading dataset: ase_db
+2024-05-13 01:51:17 (INFO): rank: 0: Sampler created...
+2024-05-13 01:51:17 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-13 01:51:17 (INFO): rank: 0: Sampler created...
+2024-05-13 01:51:17 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-13 01:51:17 (INFO): rank: 0: Sampler created...
+2024-05-13 01:51:17 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-13 01:51:17 (INFO): Loading model: gemnet_oc
+2024-05-13 01:51:17 (WARNING): Unrecognized arguments: ['symmetric_edge_symmetrization']
+2024-05-13 01:51:19 (INFO): Loaded GemNetOC with 38864438 parameters.
+2024-05-13 01:51:19 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-13 01:51:19 (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.
+2024-05-13 01:51:20 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gnoc_oc22_oc20_all_s2ef.pt
+2024-05-13 01:51:20 (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(
-2024-05-11 01:13:10 (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
-2024-05-11 01:13:11 (INFO): Evaluating on val.
+2024-05-13 01:51:43 (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
+2024-05-13 01:51:44 (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,  4.84s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.65s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.88s/it]
-2024-05-11 01:13:19 (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
+device 0:  50%|█████     | 1/2 [00:04<00:04,  4.82s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.77s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.98s/it]
+2024-05-13 01:51:52 (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()

_downloads/819e10305ddd6839cd7da05935b17060/mass-inference.txt

@@ -1,17 +1,17 @@
-2024-05-11 01:15:20 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+2024-05-13 01:54:07 (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(
-2024-05-11 01:15:22 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-05-11 01:15:22 (INFO): amp: true
+2024-05-13 01:54:08 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-13 01:54:08 (INFO): amp: true
 cmd:
-  checkpoint_dir: ./checkpoints/2024-05-11-01-14-40
-  commit: 42ae7ad
+  checkpoint_dir: ./checkpoints/2024-05-13-01-55-12
+  commit: 06869ab
   identifier: ''
-  logs_dir: ./logs/tensorboard/2024-05-11-01-14-40
+  logs_dir: ./logs/tensorboard/2024-05-13-01-55-12
   print_every: 10
-  results_dir: ./results/2024-05-11-01-14-40
+  results_dir: ./results/2024-05-13-01-55-12
   seed: 0
-  timestamp_id: 2024-05-11-01-14-40
+  timestamp_id: 2024-05-13-01-55-12
 dataset:
   a2g_args:
     r_energy: false
@@ -121,25 +121,25 @@ test_dataset:
 trainer: ocp
 val_dataset: null
 
-2024-05-11 01:15:22 (INFO): Loading dataset: ase_db
-2024-05-11 01:15:22 (INFO): rank: 0: Sampler created...
-2024-05-11 01:15:22 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-11 01:15:22 (INFO): rank: 0: Sampler created...
-2024-05-11 01:15:22 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-11 01:15:22 (INFO): Loading model: gemnet_t
-2024-05-11 01:15:23 (INFO): Loaded GemNetT with 31671825 parameters.
-2024-05-11 01:15:23 (WARNING): Model gradient logging to tensorboard not yet supported.
-2024-05-11 01:15:24 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
-2024-05-11 01:15:24 (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. 
-2024-05-11 01:15:24 (WARNING): Scale factor comment not found in model
-2024-05-11 01:15:24 (INFO): Predicting on test.
+2024-05-13 01:54:08 (INFO): Loading dataset: ase_db
+2024-05-13 01:54:08 (INFO): rank: 0: Sampler created...
+2024-05-13 01:54:08 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-13 01:54:08 (INFO): rank: 0: Sampler created...
+2024-05-13 01:54:08 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-13 01:54:08 (INFO): Loading model: gemnet_t
+2024-05-13 01:54:10 (INFO): Loaded GemNetT with 31671825 parameters.
+2024-05-13 01:54:10 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-13 01:54:10 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
+2024-05-13 01:54:11 (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. 
+2024-05-13 01:54:11 (WARNING): Scale factor comment not found in model
+2024-05-13 01:54:11 (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 [00:02<00:05,  2.82s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:05<00:02,  2.59s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.21s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.34s/it]
-2024-05-11 01:15:31 (INFO): Writing results to ./results/2024-05-11-01-14-40/ocp_predictions.npz
-2024-05-11 01:15:31 (INFO): Total time taken: 7.17962908744812
-Elapsed time = 13.5 seconds
+device 0:  33%|███████████▋                       | 1/3 [00:03<00:07,  3.81s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:06<00:02,  2.89s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.06s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.38s/it]
+2024-05-13 01:54:18 (INFO): Writing results to ./results/2024-05-13-01-55-12/ocp_predictions.npz
+2024-05-13 01:54:18 (INFO): Total time taken: 7.292580604553223
+Elapsed time = 14.0 seconds

_sources/autoapi/ocpneb/core/autoframe/index.rst

@@ -115,7 +115,7 @@ Functions
 
 
 
-.. py:class:: AutoFrameDissociation(reaction: fairchem.applications.ocpneb.core.Reaction, reactant_system: ase.Atoms, product1_systems: list, product1_energies: list, product2_systems: list, product2_energies: list, r_product1_max: float = None, r_product2_max: float = None, r_product2_min: float = None)
+.. py:class:: AutoFrameDissociation(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, reactant_system: ase.Atoms, product1_systems: list, product1_energies: list, product2_systems: list, product2_energies: list, r_product1_max: float = None, r_product2_max: float = None, r_product2_min: float = None)
 
 
    Bases: :py:obj:`AutoFrame`
@@ -213,7 +213,7 @@ Functions
 
 
 
-.. py:class:: AutoFrameTransfer(reaction: fairchem.applications.ocpneb.core.Reaction, reactant1_systems: list, reactant2_systems: list, reactant1_energies: list, reactant2_energies: list, product1_systems: list, product1_energies: list, product2_systems: list, product2_energies: list, r_traverse_max: float, r_react_max: float, r_react_min: float)
+.. py:class:: AutoFrameTransfer(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, reactant1_systems: list, reactant2_systems: list, reactant1_energies: list, reactant2_energies: list, product1_systems: list, product1_energies: list, product2_systems: list, product2_energies: list, r_traverse_max: float, r_react_max: float, r_react_min: float)
 
 
    Bases: :py:obj:`AutoFrame`
@@ -270,7 +270,7 @@ Functions
 
 
 
-.. py:class:: AutoFrameDesorption(reaction: fairchem.applications.ocpneb.core.Reaction, reactant_systems: list, reactant_energies: list, z_desorption: float)
+.. py:class:: AutoFrameDesorption(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, reactant_systems: list, reactant_energies: list, z_desorption: float)
 
 
    Bases: :py:obj:`AutoFrame`
@@ -303,7 +303,7 @@ Functions
 
 
 
-.. py:function:: interpolate_and_correct_frames(initial: ase.Atoms, final: ase.Atoms, n_frames: int, reaction: fairchem.applications.ocpneb.core.Reaction, map_idx: int)
+.. py:function:: interpolate_and_correct_frames(initial: ase.Atoms, final: ase.Atoms, n_frames: int, reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, map_idx: int)
 
    Given the initial and final frames, perform the following:
    (1) Unwrap the final frame if it is wrapped around the cell
@@ -338,7 +338,7 @@ Functions
    :rtype: (ase.Atoms)
 
 
-.. py:function:: traverse_adsorbate_transfer(reaction: fairchem.applications.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms, edge_list_final: list)
+.. py:function:: traverse_adsorbate_transfer(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms, edge_list_final: list)
 
    Traverse reactant 1, reactant 2, product 1 and product 2 in a depth first search of
    the bond graph. Unwrap the atoms to minimize the distance over the bonds. This ensures
@@ -364,7 +364,7 @@ Functions
    :rtype: (ase.Atoms)
 
 
-.. py:function:: traverse_adsorbate_dissociation(reaction: fairchem.applications.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms, edge_list_final: int)
+.. py:function:: traverse_adsorbate_dissociation(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms, edge_list_final: int)
 
    Traverse reactant 1, product 1 and product 2 in a depth first search of
    the bond graph. Unwrap the atoms to minimize the distance over the bonds. This ensures
@@ -390,7 +390,7 @@ Functions
    :rtype: (ase.Atoms)
 
 
-.. py:function:: traverse_adsorbate_desorption(reaction: fairchem.applications.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms)
+.. py:function:: traverse_adsorbate_desorption(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, initial: ase.Atoms, final: ase.Atoms, initial_tiled: ase.Atoms, final_tiled: ase.Atoms)
 
    Traverse reactant 1 and  product 1 in a depth first search of
    the bond graph. Unwrap the atoms to minimize the distance over the bonds. This ensures
@@ -416,7 +416,7 @@ Functions
    :rtype: (ase.Atoms)
 
 
-.. py:function:: get_product2_idx(reaction: fairchem.applications.ocpneb.core.Reaction, edge_list_final: list, traversal_rxt1_final: list)
+.. py:function:: get_product2_idx(reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, edge_list_final: list, traversal_rxt1_final: list)
 
    For dissociation only. Use the information about the initial edge list and final edge
    list to determine which atom in product 2 lost a bond in the reaction and use this
@@ -459,7 +459,7 @@ Functions
    :rtype: (ase.Atoms)
 
 
-.. py:function:: unwrap_atoms(initial: ase.Atoms, final: ase.Atoms, reaction: fairchem.applications.ocpneb.core.Reaction, map_idx: int)
+.. py:function:: unwrap_atoms(initial: ase.Atoms, final: ase.Atoms, reaction: fairchem.applications.CatTSunami.ocpneb.core.Reaction, map_idx: int)
 
    Make corrections to the final frame so it is no longer wrapped around the cell,
    if it has jumpped over the pbc. Ensure that for each adsorbate moity, absolute bond distances

_sources/index.md

@@ -17,10 +17,10 @@ this repo:
 * [Open Catalyst Project (OCP)](https://opencatalystproject.org/)
 * [Open Direct Air Capture (OpenDAC)](https://open-dac.github.io/)
 
-:::{note}
+```{note}
 We re-organized and rebranded the repository in 2024 (previously the `fairchem` repo) to reflect the increasingly
 general usability of these models beyond catalysis, including things like direct air capture.
-:::
+```
 
 ### Datasets in `fairchem`:
 `fairchem` provides training and evaluation code for tasks and models that take arbitrary