deploy: 7a758b9

_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

@@ -1,17 +1,17 @@
-2024-04-13 22:06:21 (INFO): Project root: /home/runner/work/ocp/ocp
+2024-04-13 23:48:41 (INFO): Project root: /home/runner/work/ocp/ocp
 /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(
-2024-04-13 22:06:23 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-04-13 22:06:23 (INFO): amp: true
+2024-04-13 23:48:43 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-04-13 23:48:43 (INFO): amp: true
 cmd:
-  checkpoint_dir: fine-tuning/checkpoints/2024-04-13-22-06-56-ft-oxides
-  commit: f048fb9
+  checkpoint_dir: fine-tuning/checkpoints/2024-04-13-23-49-20-ft-oxides
+  commit: 7a758b9
   identifier: ft-oxides
-  logs_dir: fine-tuning/logs/wandb/2024-04-13-22-06-56-ft-oxides
+  logs_dir: fine-tuning/logs/wandb/2024-04-13-23-49-20-ft-oxides
   print_every: 10
-  results_dir: fine-tuning/results/2024-04-13-22-06-56-ft-oxides
+  results_dir: fine-tuning/results/2024-04-13-23-49-20-ft-oxides
   seed: 0
-  timestamp_id: 2024-04-13-22-06-56-ft-oxides
+  timestamp_id: 2024-04-13-23-49-20-ft-oxides
 dataset:
   a2g_args:
     r_energy: true

_sources/core/datasets/oc20.md

@@ -1,10 +1,10 @@
 
-## Open Catalyst 2020 (OC20)
+# Open Catalyst 2020 (OC20)
 
 *NOTE: Data files for all tasks / splits were updated on Feb 10, 2021 due to minor bugs (affecting < 1% of the data) in earlier versions. If you downloaded data before Feb 10, 2021, please re-download the data.*
 
 
-### Download and preprocess the dataset
+## Download and preprocess the dataset
 
 IS2* datasets are stored as LMDB files and are ready to be used upon download.
 S2EF train+val datasets require an additional preprocessing step.
@@ -58,7 +58,7 @@ and IS2RE/IS2RS task splits. If you used the above `download_data.py` script to
 download and preprocess the data, you are good to go and can stop reading here!
 
 
-### Structure to Energy and Forces (S2EF) task
+## Structure to Energy and Forces (S2EF) task
 
 For this task’s train and validation sets, we provide compressed trajectory files with the input structures and output energies and forces.  We provide precomputed LMDBs for the test sets. To use the train and validation datasets, first download the files and uncompress them. The uncompressed files are used to generate LMDBs, which are in turn used by the dataloaders to train the ML models. Code for the dataloaders and generating the LMDBs may be found in the Github repository.
 
@@ -94,7 +94,7 @@ Each tarball has a README file containing details about file formats, number of
 
 
 
-### Initial Structure to Relaxed Structure (IS2RS) and Initial Structure to Relaxed Energy (IS2RE) tasks
+## Initial Structure to Relaxed Structure (IS2RS) and Initial Structure to Relaxed Energy (IS2RE) tasks
 
 For the IS2RS and IS2RE tasks, we are providing:
 
@@ -116,9 +116,9 @@ Each tarball has README file containing details about file formats, number of st
 
 
 
-### Relaxation Trajectories
+## Relaxation Trajectories
 
-#### Adsorbate+catalyst system trajectories (optional download)
+### Adsorbate+catalyst system trajectories (optional download)
 
 |Split     |Size of compressed version (in bytes)    |Size of uncompressed version (in bytes)    | MD5 checksum (download link)    |
 |---    |---    |---    |---    |
@@ -132,27 +132,27 @@ Each tarball has README file containing details about file formats, number of st
 
 
 
-##### Per-adsorbate trajectories (optional download)
+#### Per-adsorbate trajectories (optional download)
 
 Adsorbate+catalyst trajectories on a per adsorbate basis are provided [here](./DATASET_PER_ADSORBATE.md) to avoid having to download all systems. Note - a few adsorbates are intentionally left out for the test splits.
 
 
 
-#### Catalyst system trajectories (optional download)
+### Catalyst system trajectories (optional download)
 
 |Number    |Size of compressed version (in bytes)    |Size of uncompressed version (in bytes)    |MD5 checksum (download link)    |
 |---    |---    |---    |---    |
 |294k systems    |20G    |151G    | [347f4183465810e9b384e7a033baefc7](https://dl.fbaipublicfiles.com/opencatalystproject/data/slab_trajectories.tar)    |
 
 
-### Bader charge data
+## Bader charge data
 We provide Bader charge data for all final frames of our train + validation systems in OC20 (for both S2EF and IS2RE/RS tasks). A `.tar.gz` file, when downloaded and uncompressed will contain several directories with unique system-ids (of the format `random<XYZ>` where `XYZ` is an integer). Each directory will contain raw Bader charge analysis outputs. For more details on the Bader charge analysis, see https://theory.cm.utexas.edu/henkelman/research/bader/.
 
 Downloadable link: https://dl.fbaipublicfiles.com/opencatalystproject/data/oc20_bader_data.tar (MD5 checksum: `aecc5e23542de49beceb4b7e44c153b9`)
 
-### OC20 mappings
+## OC20 mappings
 
-#### Data mapping information
+### Data mapping information
 
 We provide a Python pickle file containing information about the slab and adsorbates for each of the systems in OC20 dataset. Loading the pickle file will load a Python dictionary. The keys of this dictionary are the adsorbate+catalyst system-ids (of the format `random<XYZ>`  where `XYZ` is an integer), and the corresponding value of each key is a dictionary with information about:
 
@@ -203,7 +203,7 @@ An example entry is
 
 
 
-### Adsorbate-catalyst system to catalyst system mapping information
+## Adsorbate-catalyst system to catalyst system mapping information
 
 We provide a Python pickle file containing information about the mapping from adsorbate-catalyst systems to their corresponding catalyst systems. Loading the pickle file will load a Python dictionary. The keys of this dictionary are the adsorbate+catalyst system-ids (of the format `random<XYZ>`  where `XYZ` is an integer), and values will be the catalyst system-ids (of the format `random<PQR>` where `PQR` is an integer).
 
@@ -221,18 +221,18 @@ An example entry is
 
 
 
-### Dataset changelog
+## Dataset changelog
 
-#### September 2021
+### September 2021
 
 * Released IS2RE `test-challenge` data for the [Open Catalyst Challenge 2021](https://opencatalystproject.org/challenge.html)
 
-#### March 2021
+### March 2021
 
 * Modified the pickle corresponding to data mapping information. Now the pickle includes extra information about `miller_index`, `shift`, `top` and `adsorption_site`.
 * Added Molecular Dynamics (MD) and rattled data for S2EF task.
 
-#### Version 2, Feb 2021
+### Version 2, Feb 2021
 
 Modifications:
 
@@ -276,7 +276,7 @@ Total IS2RE and IS2RS systems:
     * test_ood_cat: 24967 → 24965
     * test_ood_both: 24986 → 24985
 
-#### Version 1, Oct 2020
+### Version 1, Oct 2020
 
 Total S2EF frames:
 
@@ -310,7 +310,7 @@ Total IS2RE and IS2RS systems:
     * test_ood_cat: 24967
     * test_ood_both: 24986
 
-### Citing OC20
+## Citing OC20
 
 The Open Catalyst 2020 (OC20) dataset is licensed under a [Creative Commons Attribution 4.0 License](https://creativecommons.org/licenses/by/4.0/legalcode).
 
@@ -329,7 +329,7 @@ Please consider citing the following paper in any research manuscript using the
 ```
 
 
-## Per-adsorbate trajectories
+# Per-adsorbate trajectories
 
 |Adsorbate symbol	|Size	|MD5 checksum (download link)	|
 |---	|---	|---	|

_sources/core/fine-tuning/fine-tuning-oxides.md

@@ -338,12 +338,3 @@ There are also other models you could consider. Newer models tend to be more acc
 
 +++
 
-# Next steps
-
-You might want to check out the [gotchas](../gotchas) notebook. It has some examples of things we have seen go wrong before.
-
-The [advanced](../advanced) folder contains several concepts that are more advanced. These include:
-
-1. [Mass inference](../advanced/mass-inference) which is more efficient than the ASE calculator
-2. [Working with embeddings](../advanced/embeddings) which shows some ways to use the embeddings from OCP
-3. [Fine-tuning in python](../advanced/fine-tuning-in-python)

_sources/core/gotchas.md

@@ -164,7 +164,10 @@ calc = OCPCalculator(checkpoint_path=checkpoint_path)
 ```
 
 ```{code-cell} ipython3
+%%capture
 from ase.build import molecule
+import numpy as np
+
 atoms = molecule('H2O')
 atoms.set_tags(np.ones(len(atoms)))
 atoms.set_calculator(calc)
@@ -186,6 +189,7 @@ calc = OCPCalculator(checkpoint_path=checkpoint_path)
 ```
 
 ```{code-cell} ipython3
+%%capture
 atoms = molecule('CH4')
 atoms.set_calculator(calc)
 atoms.get_potential_energy()  # error
@@ -201,7 +205,6 @@ atoms.get_potential_energy()
 Not all models require tags though. This EquiformerV2 model does not use them. This is another detail that is important to keep in mind.
 
 ```{code-cell} ipython3
-%%capture
 from ocpmodels.common.relaxation.ase_utils import OCPCalculator
 from ocpmodels.models.model_registry import model_name_to_local_file
 import os

_sources/core/inference.md

@@ -40,7 +40,7 @@ import numpy as np
 
 with ase.db.connect('full_data.db') as full_db:
   with ase.db.connect('data.db') as subset_db:
-    for i in range(100):
+    for i in range(1, 100):
       subset_db.write(full_db.get_atoms(i))
 
 ```

_sources/core/ocpapi.md

@@ -122,14 +122,16 @@ Calls to `find_adsorbate_binding_sites()` will, by default, show the user all pe
 Run relaxations for all slabs that are generated:
 
 ```{code-cell} ipython3
+---
+tags: ["skip-execution"]
+---
 from ocpapi import find_adsorbate_binding_sites, keep_all_slabs
 
 results = await find_adsorbate_binding_sites(
     adsorbate="*OH",
     bulk="mp-126",
     adslab_filter=keep_all_slabs(),
 )
-print(results)
 ```
 
 Run relaxations only for slabs with Miller Indices in the input set:
@@ -173,10 +175,6 @@ Relaxation results can be viewed in a web UI. For example, https://open-catalyst
 Extending the examples above, the URLs to visualize the results of relaxations on each Pt surface can be obtained with:
 
 ```{code-cell} ipython3
-urls = [
-    slab.ui_url
-    for slab in results.slabs
-]
 print([
     slab.ui_url
     for slab in results.slabs
@@ -200,6 +198,8 @@ results = await find_adsorbate_binding_sites(
     adsorbate="*OH",
     bulk="mp-126",
     model="gemnet_oc_base_s2ef_all_md",
+    adslab_filter=keep_slabs_with_miller_indices([(1, 1, 1)]),
+
 )
 print([
     slab.ui_url

_sources/core/quickstart.md

@@ -14,7 +14,7 @@ kernelspec:
 Using pre-trained models in ASE
 ----------
 
-1. First, install OCP in a fresh python environment using one of the approaches in [installation documentation](INSTALL).
+1. First, install OCP in a fresh python environment using one of the approaches in [installation documentation](install).
 2. See what pre-trained potentials are available 
 
 ```{code-cell} ipython3

_sources/tutorials/adsorbml_walkthrough.md

@@ -36,14 +36,14 @@ from x3dase.visualize import view_x3d_n
 
 +++
 
-Be sure to set the path to the bulk and adsorbate pickle files in `ocdata/configs/paths.py` or pass the paths as an argument. The database pickles can be found in `ocdata/databases/pkls`. AdsorbML incorporates random placement, which is especially useful for more complicated adsorbates which may have many degrees of freedom. I have opted sample a few random placements and a few heuristic. Here I am using *CO on copper (1,1,1) as an example.
+AdsorbML incorporates random placement, which is especially useful for more complicated adsorbates which may have many degrees of freedom. I have opted sample a few random placements and a few heuristic. Here I am using *CO on copper (1,1,1) as an example.
 
 ```{code-cell} ipython3
 bulk_src_id = "mp-30"
 adsorbate_smiles = "*CO"
 
-bulk = Bulk(bulk_src_id_from_db = bulk_src_id, bulk_db_path = "your-path-here.pkl")
-adsorbate = Adsorbate(adsorbate_smiles_from_db=adsorbate_smiles, adsorbate_db_path = "your-path-here.pkl")
+bulk = Bulk(bulk_src_id_from_db = bulk_src_id)
+adsorbate = Adsorbate(adsorbate_smiles_from_db=adsorbate_smiles)
 slabs = Slab.from_bulk_get_specific_millers(bulk = bulk, specific_millers=(1,1,1))
 
 # There may be multiple slabs with this miller index.
@@ -71,7 +71,12 @@ There are 2 options for how to do this.
 You need to provide the calculator with a path to a model checkpoint file. That can be downloaded [here](https://github.com/Open-Catalyst-Project/ocp/blob/main/MODELS.md)
 
 ```{code-cell} ipython3
-checkpoint_path = "your-path-here.pt"
+from ocpmodels.common.relaxation.ase_utils import OCPCalculator
+from ocpmodels.models.model_registry import model_name_to_local_file
+import os
+
+checkpoint_path = model_name_to_local_file('EquiformerV2 (31M) All+MD', local_cache='/tmp/ocp_checkpoints/')
+
 os.makedirs(f"data/{bulk}_{adsorbate}", exist_ok=True)
 
 # Define the calculator

autoapi/index.html

@@ -204,6 +204,7 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../core/datasets/oc22.html">Open Catalyst 2022 (OC22)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../core/datasets/odac.html">Open Direct Air Capture 2023 (ODAC23)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../core/model_checkpoints.html">Pretrained model checkpoints</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Making your own datasets</span></p>
 <ul class="nav bd-sidenav">
@@ -220,7 +221,6 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../core/fine-tuning/fine-tuning-oxides.html">Fine tuning a model</a></li>
 
-
 <li class="toctree-l1"><a class="reference internal" href="../core/model_faq.html">Model FAQ</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Videos and Talks</span></p>
@@ -254,7 +254,7 @@
 
 </ul>
 </li>
-<li class="toctree-l1 has-children"><a class="reference internal" href="../tutorials/advanced/fine-tuning-toc.html">Advanced example: Fine-tuning</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 has-children"><a class="reference internal" href="../tutorials/advanced/advanced_toc.html">Advanced OCP usage</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="../tutorials/advanced/fine-tuning-in-python.html">Fine-tuning with Python</a></li>
 
 

autoapi/ocpmodels/common/data_parallel/index.html

@@ -204,6 +204,7 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc22.html">Open Catalyst 2022 (OC22)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/odac.html">Open Direct Air Capture 2023 (ODAC23)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../core/model_checkpoints.html">Pretrained model checkpoints</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Making your own datasets</span></p>
 <ul class="nav bd-sidenav">
@@ -220,7 +221,6 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/fine-tuning/fine-tuning-oxides.html">Fine tuning a model</a></li>
 
-
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/model_faq.html">Model FAQ</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Videos and Talks</span></p>
@@ -254,7 +254,7 @@
 
 </ul>
 </li>
-<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-toc.html">Advanced example: Fine-tuning</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/advanced_toc.html">Advanced OCP usage</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-in-python.html">Fine-tuning with Python</a></li>
 
 

autoapi/ocpmodels/common/distutils/index.html

@@ -204,6 +204,7 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc22.html">Open Catalyst 2022 (OC22)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/odac.html">Open Direct Air Capture 2023 (ODAC23)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../core/model_checkpoints.html">Pretrained model checkpoints</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Making your own datasets</span></p>
 <ul class="nav bd-sidenav">
@@ -220,7 +221,6 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/fine-tuning/fine-tuning-oxides.html">Fine tuning a model</a></li>
 
-
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/model_faq.html">Model FAQ</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Videos and Talks</span></p>
@@ -254,7 +254,7 @@
 
 </ul>
 </li>
-<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-toc.html">Advanced example: Fine-tuning</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/advanced_toc.html">Advanced OCP usage</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-in-python.html">Fine-tuning with Python</a></li>
 
 

autoapi/ocpmodels/common/flags/index.html

@@ -204,6 +204,7 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/oc22.html">Open Catalyst 2022 (OC22)</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/datasets/odac.html">Open Direct Air Capture 2023 (ODAC23)</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../core/model_checkpoints.html">Pretrained model checkpoints</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Making your own datasets</span></p>
 <ul class="nav bd-sidenav">
@@ -220,7 +221,6 @@
 
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/fine-tuning/fine-tuning-oxides.html">Fine tuning a model</a></li>
 
-
 <li class="toctree-l1"><a class="reference internal" href="../../../../core/model_faq.html">Model FAQ</a></li>
 </ul>
 <p aria-level="2" class="caption" role="heading"><span class="caption-text">Videos and Talks</span></p>
@@ -254,7 +254,7 @@
 
 </ul>
 </li>
-<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-toc.html">Advanced example: Fine-tuning</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
+<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../tutorials/advanced/advanced_toc.html">Advanced OCP usage</a><input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/><label class="toctree-toggle" for="toctree-checkbox-2"><i class="fa-solid fa-chevron-down"></i></label><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/advanced/fine-tuning-in-python.html">Fine-tuning with Python</a></li>