deploy: 7a0ae57

_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

@@ -1,17 +1,17 @@
-2024-05-10 22:12:36 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+2024-05-10 22:54:58 (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 22:12:37 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-05-10 22:12:37 (INFO): amp: true
+2024-05-10 22:55:00 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-10 22:55:00 (INFO): amp: true
 cmd:
-  checkpoint_dir: fine-tuning/checkpoints/2024-05-10-22-13-20-ft-oxides
-  commit: 7195b74
+  checkpoint_dir: fine-tuning/checkpoints/2024-05-10-22-56-00-ft-oxides
+  commit: 7a0ae57
   identifier: ft-oxides
-  logs_dir: fine-tuning/logs/tensorboard/2024-05-10-22-13-20-ft-oxides
+  logs_dir: fine-tuning/logs/tensorboard/2024-05-10-22-56-00-ft-oxides
   print_every: 10
-  results_dir: fine-tuning/results/2024-05-10-22-13-20-ft-oxides
+  results_dir: fine-tuning/results/2024-05-10-22-56-00-ft-oxides
   seed: 0
-  timestamp_id: 2024-05-10-22-13-20-ft-oxides
+  timestamp_id: 2024-05-10-22-56-00-ft-oxides
 dataset:
   a2g_args:
     r_energy: true
@@ -142,34 +142,34 @@ val_dataset:
     r_forces: true
   src: val.db
 
-2024-05-10 22:12:37 (INFO): Loading dataset: ase_db
-2024-05-10 22:12:38 (INFO): rank: 0: Sampler created...
-2024-05-10 22:12:38 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-10 22:12:38 (INFO): rank: 0: Sampler created...
-2024-05-10 22:12:38 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-10 22:12:38 (INFO): rank: 0: Sampler created...
-2024-05-10 22:12:38 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-10 22:12:38 (INFO): Loading model: gemnet_oc
-2024-05-10 22:12:38 (WARNING): Unrecognized arguments: ['symmetric_edge_symmetrization']
-2024-05-10 22:12:40 (INFO): Loaded GemNetOC with 38864438 parameters.
-2024-05-10 22:12:40 (WARNING): Model gradient logging to tensorboard not yet supported.
-2024-05-10 22:12:40 (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 22:12:40 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gnoc_oc22_oc20_all_s2ef.pt
-2024-05-10 22:12:40 (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 22:55:00 (INFO): Loading dataset: ase_db
+2024-05-10 22:55:00 (INFO): rank: 0: Sampler created...
+2024-05-10 22:55:00 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 22:55:00 (INFO): rank: 0: Sampler created...
+2024-05-10 22:55:00 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 22:55:00 (INFO): rank: 0: Sampler created...
+2024-05-10 22:55:00 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 22:55:00 (INFO): Loading model: gemnet_oc
+2024-05-10 22:55:00 (WARNING): Unrecognized arguments: ['symmetric_edge_symmetrization']
+2024-05-10 22:55:03 (INFO): Loaded GemNetOC with 38864438 parameters.
+2024-05-10 22:55:03 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-10 22:55:03 (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 22:55:03 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gnoc_oc22_oc20_all_s2ef.pt
+2024-05-10 22:55:03 (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 22:13:03 (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 22:13:04 (INFO): Evaluating on val.
+2024-05-10 22:55:27 (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 22:55:28 (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,  4.66s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.61s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.82s/it]
-2024-05-10 22:13:11 (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,  4.91s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.71s/it]device 0: 100%|██████████| 2/2 [00:07<00:00,  3.93s/it]
+2024-05-10 22:55:36 (INFO): energy_forces_within_threshold: 0.0000, energy_mae: 8.7334, 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: 8.6591, 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 @@
-2024-05-10 22:15:12 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
+2024-05-10 22:57:42 (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 22:15:13 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-05-10 22:15:13 (INFO): amp: true
+2024-05-10 22:57:43 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-05-10 22:57:43 (INFO): amp: true
 cmd:
-  checkpoint_dir: ./checkpoints/2024-05-10-22-15-28
-  commit: 7195b74
+  checkpoint_dir: ./checkpoints/2024-05-10-22-58-08
+  commit: 7a0ae57
   identifier: ''
-  logs_dir: ./logs/tensorboard/2024-05-10-22-15-28
+  logs_dir: ./logs/tensorboard/2024-05-10-22-58-08
   print_every: 10
-  results_dir: ./results/2024-05-10-22-15-28
+  results_dir: ./results/2024-05-10-22-58-08
   seed: 0
-  timestamp_id: 2024-05-10-22-15-28
+  timestamp_id: 2024-05-10-22-58-08
 dataset:
   a2g_args:
     r_energy: false
@@ -121,25 +121,25 @@ test_dataset:
 trainer: ocp
 val_dataset: null
 
-2024-05-10 22:15:13 (INFO): Loading dataset: ase_db
-2024-05-10 22:15:13 (INFO): rank: 0: Sampler created...
-2024-05-10 22:15:13 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-10 22:15:13 (INFO): rank: 0: Sampler created...
-2024-05-10 22:15:13 (INFO): Batch balancing is disabled for single GPU training.
-2024-05-10 22:15:13 (INFO): Loading model: gemnet_t
-2024-05-10 22:15:15 (INFO): Loaded GemNetT with 31671825 parameters.
-2024-05-10 22:15:15 (WARNING): Model gradient logging to tensorboard not yet supported.
-2024-05-10 22:15:15 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
-2024-05-10 22:15:15 (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 22:15:15 (WARNING): Scale factor comment not found in model
-2024-05-10 22:15:16 (INFO): Predicting on test.
+2024-05-10 22:57:43 (INFO): Loading dataset: ase_db
+2024-05-10 22:57:43 (INFO): rank: 0: Sampler created...
+2024-05-10 22:57:43 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 22:57:43 (INFO): rank: 0: Sampler created...
+2024-05-10 22:57:43 (INFO): Batch balancing is disabled for single GPU training.
+2024-05-10 22:57:43 (INFO): Loading model: gemnet_t
+2024-05-10 22:57:45 (INFO): Loaded GemNetT with 31671825 parameters.
+2024-05-10 22:57:45 (WARNING): Model gradient logging to tensorboard not yet supported.
+2024-05-10 22:57:46 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
+2024-05-10 22:57:46 (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 22:57:46 (WARNING): Scale factor comment not found in model
+2024-05-10 22:57:46 (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,  2.66s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:05<00:02,  2.55s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.27s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00,  2.37s/it]
-2024-05-10 22:15:23 (INFO): Writing results to ./results/2024-05-10-22-15-28/ocp_predictions.npz
-2024-05-10 22:15:23 (INFO): Total time taken: 7.2499964237213135
-Elapsed time = 13.4 seconds
+device 0:  33%|███████████▋                       | 1/3 [00:03<00:07,  3.63s/it]device 0:  67%|███████████████████████▎           | 2/3 [00:06<00:02,  2.97s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:09<00:00,  3.04s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:09<00:00,  3.09s/it]
+2024-05-10 22:57:55 (INFO): Writing results to ./results/2024-05-10-22-58-08/ocp_predictions.npz
+2024-05-10 22:57:55 (INFO): Total time taken: 9.435298919677734
+Elapsed time = 16.0 seconds

_sources/core/lmdb_dataset_creation.md

@@ -19,7 +19,7 @@ recommended option for the majority of fairchem use cases, but has since been de
 This notebook provides an overview of how to create LMDB datasets to be used with the FAIRChem repo. This tutorial is intended
 for those who wish to use FAIRChem to train on their own datasets. Those interested in just using FAIRChem data need not worry
 about these steps as they've been automated as part of this
-[download script](https://github.com/FAIR-Chem/fairchem/blob/master/src/core/scripts/download_data.py).
+[download script](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/scripts/download_data.py).
 
 ```{code-cell} ipython3
 from fairchem.core.preprocessing import AtomsToGraphs

_sources/core/model_faq.md

@@ -18,7 +18,7 @@ Moreover, results may be different between GPU and CPU
 executions [[3](https://pytorch.org/docs/stable/notes/randomness.html)].
 
 To get deterministic results on GPU, use [`torch.use_deterministic_algorithms`](https://pytorch.org/docs/stable/generated/torch.use_deterministic_algorithms.html#torch.use_deterministic_algorithms)
-where available (for example, see [`scatter_det`](https://github.com/FAIR-Chem/fairchem/blob/main/ocpmodels/common/utils.py#L1112)). Note that deterministic operations are often slower
+where available (for example, see [`scatter_det`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/common/utils.py#L1112)). Note that deterministic operations are often slower
 than non-deterministic operations, so while this may be worth using for testing
 and debugging, this is not recommended for large-scale training and inference.
 
@@ -54,7 +54,7 @@ dataset:
 
 The OC20 reference pickle file containing the energy necessary to convert
 adsorption energy values to total energy is [available for download
-here](https://github.com/FAIR-Chem/fairchem/blob/main/DATASET.md#oc20-reference-information).
+here](https://fair-chem.github.io/core/datasets/oc20.html).
 
 To test if your setup is correct, try the following:
 

_sources/core/model_training.md

@@ -73,7 +73,7 @@ dataset:
   test:
     src: [Path to test data]
 ```
-You can find examples configuration files in [`configs/is2re`](https://github.com/FAIR-Chem/fairchem/tree/main/configs/is2re).
+You can find examples configuration files in [`configs/is2re`](https://github.com/FAIR-Chem/fairchem/tree/main/src/fairchem/core/configs/is2re).
 
 To train a SchNet model for the IS2RE task on the 10k split, run:
 ```bash
@@ -153,7 +153,7 @@ dataset:
   test:
     src: [Path to test data]
 ```
-You can find examples configuration files in [`configs/s2ef`](https://github.com/FAIR-Chem/fairchem/tree/main/configs/s2ef).
+You can find examples configuration files in [`configs/s2ef`](https://github.com/FAIR-Chem/fairchem/tree/main/src/fairchem/core/configs/s2ef).
 
 To train a SchNet model for the S2EF task on the 2M split using 2 GPUs, run:
 

_sources/index.md

@@ -1,7 +1,7 @@
 # `fairchem` repository for atomistic AI/ML models in chemistry
 
 ![tests](https://github.com/FAIR-Chem/fairchem/actions/workflows/test.yml/badge.svg?branch=main)
-[![codecov](https://codecov.io/gh/Open-Catalyst-Project/ocp/graph/badge.svg?token=M606LH5LK6)](https://codecov.io/gh/Open-Catalyst-Project/ocp)
+[![codecov](https://codecov.io/gh/FAIR-Chem/fairchem/badge.svg)](https://codecov.io/gh/FAIR-Chem/fairchem)
 
 `fairchem` is the FAIR Chemistry team's library of state-of-the-art machine learning algorithms for chemistry and materials. Collaborative projects that contribute or use the models and approaches in this repo:
 * [Open Catalyst Project (OCP)](https://opencatalystproject.org/)
@@ -33,14 +33,14 @@ Projects and models built on `ocp`:
 
 - SchNet [[`arXiv`](https://arxiv.org/abs/1706.08566)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/schnet.py)]
 - DimeNet++ [[`arXiv`](https://arxiv.org/abs/2011.14115)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/dimenet_plus_plus.py)]
-- GemNet-dT [[`arXiv`](https://arxiv.org/abs/2106.08903)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/gemnet)]
-- PaiNN [[`arXiv`](https://arxiv.org/abs/2102.03150)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/painn)]
-- Graph Parallelism [[`arXiv`](https://arxiv.org/abs/2203.09697)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/gemnet_gp)]
-- GemNet-OC [[`arXiv`](https://arxiv.org/abs/2204.02782)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/gemnet_oc)]
-- SCN [[`arXiv`](https://arxiv.org/abs/2206.14331)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/scn)]
+- GemNet-dT [[`arXiv`](https://arxiv.org/abs/2106.08903)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/gemnet)]
+- PaiNN [[`arXiv`](https://arxiv.org/abs/2102.03150)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/painn)]
+- Graph Parallelism [[`arXiv`](https://arxiv.org/abs/2203.09697)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/gemnet_gp)]
+- GemNet-OC [[`arXiv`](https://arxiv.org/abs/2204.02782)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/gemnet_oc)]
+- SCN [[`arXiv`](https://arxiv.org/abs/2206.14331)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/scn)]
 - AdsorbML [[`arXiv`](https://arxiv.org/abs/2211.16486)] [[`code`](https://github.com/FAIR-Chem/fairchem/tree/main/src/fairchem/applications/AdsorbML)]
-- eSCN [[`arXiv`](https://arxiv.org/abs/2302.03655)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/escn)]
-- EquiformerV2 [[`arXiv`](https://arxiv.org/abs/2306.12059)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/tree/fairchem/core/models/equiformer_v2)]
+- eSCN [[`arXiv`](https://arxiv.org/abs/2302.03655)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/escn)]
+- EquiformerV2 [[`arXiv`](https://arxiv.org/abs/2306.12059)] [[`code`](https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/models/equiformer_v2)]
 
 Older model implementations that are no longer supported: