Skip to content

Doc: update readme and task name #364

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 15, 2025
Merged

Doc: update readme and task name #364

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,11 +31,10 @@ The optional dependencies are required for the corresponding models.

## Usage

To reproduce the results locally or test a custom model, please refer to the `ASEModel.evaluate` method.
To reproduce the results locally or test a custom model, please refer to the `ASEModel.evaluate` method. The test data can be found [here](https://aissquare.com/datasets/detail?pageType=datasets&name=LAMBench-DatasetCards&id=336).

- For direct prediction tasks, you can use the staticmethod `run_ase_dptest(calc: Calculator, test_data: Path) -> dict`. The test data can be found [here](https://www.aissquare.com/datasets/detail?pageType=datasets&name=LAMBench-TestData-v1&id=295).
- For direct prediction tasks, you can use the staticmethod `run_ase_dptest(calc: Calculator, test_data: Path) -> dict`.
- For calculator tasks, you can use the corresponding scripts provided in `lambench.tasks.calculator`.
- The phonon test data can be found [here](https://www.aissquare.com/datasets/detail?pageType=datasets&name=LAMBench-Phonon-MDR&id=310).
- An `ASEModel` object is needed for such tasks; you can create a dummy model as follows:

```python
Expand Down
8 changes: 4 additions & 4 deletions lambench/metrics/results/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,7 +643,7 @@
"DISPLAY_NAME":"Generalizability Tests (Property Calculation)",
"DESCRIPTION": "Evaluation metrics for domain specific property calculation tasks when utilizing the LAM as the force field.",
"phonon_mdr": {
"DISPLAY_NAME": "Phonon Properties",
"DISPLAY_NAME": "Phonon MDR",
"DESCRIPTION": "Evaluation metrics based on phonon calculations.",
"mae_entropy": {
"DISPLAY_NAME": "Entropy MAE (J/K/mol)",
Expand All @@ -667,7 +667,7 @@
}
},
"torsionnet": {
"DISPLAY_NAME": "Torsional Barrier",
"DISPLAY_NAME": "TorsionNet500",
"DESCRIPTION": "Evaluation of torsional barrier related metrics on the TorsionNet-500 dataset at the CCSD(T)/CBS level.",
"MAE": {
"DISPLAY_NAME": "MAE (kcal/mol)",
Expand All @@ -687,8 +687,8 @@
}
},
"neb": {
"DISPLAY_NAME": "NEB",
"DESCRIPTION": "Evaluation of NEB related metrics on the OC20NEB-OOD dataset. The dataset contains 460 NEB trajectories over 3 types of reactions: desorption, dissociation, and transfer. For details, please refer to https://arxiv.org/abs/2405.02078. The energy barrier height is calculated with single point energy prediction on DFT relaxed structures using the LAM model without performing NEB optimization.",
"DISPLAY_NAME": "OC20NEB-OOD",
"DESCRIPTION": "Evaluation of energy barrier related metrics on the OC20NEB-OOD dataset. The dataset contains 460 NEB trajectories over 3 types of reactions: desorption, dissociation, and transfer. For details, please refer to https://arxiv.org/abs/2405.02078. The energy barrier height is calculated with single point energy prediction on DFT relaxed structures using the LAM model without performing NEB optimization.",
Copy link

Copilot AI Aug 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[nitpick] The description should use "NEB-related" instead of "energy barrier related" to maintain consistency with the original "NEB related metrics" terminology used elsewhere in the codebase.

Suggested change
"DESCRIPTION": "Evaluation of energy barrier related metrics on the OC20NEB-OOD dataset. The dataset contains 460 NEB trajectories over 3 types of reactions: desorption, dissociation, and transfer. For details, please refer to https://arxiv.org/abs/2405.02078. The energy barrier height is calculated with single point energy prediction on DFT relaxed structures using the LAM model without performing NEB optimization.",
"DESCRIPTION": "Evaluation of NEB-related metrics on the OC20NEB-OOD dataset. The dataset contains 460 NEB trajectories over 3 types of reactions: desorption, dissociation, and transfer. For details, please refer to https://arxiv.org/abs/2405.02078. The energy barrier height is calculated with single point energy prediction on DFT relaxed structures using the LAM model without performing NEB optimization.",

Copilot uses AI. Check for mistakes.
"MAE_Ea": {
"DISPLAY_NAME": "MAE_Ea (eV)",
"DESCRIPTION": "The mean absolute error of the energy barrier prediction across all OOD trajectories."
Expand Down