model_name: Nequip-MP-L # required (this must match the model's label which is the 3rd arg in the matbench_discovery.preds.Model enum) model_key: nequip-MP-L-0.1 # this should match the name of the YAML file and determines the URL /models/ on which details of the model are displayed on the website model_version: '0.1' date_added: '2025-09-08' date_published: '2025-08-28' authors: - name: Seán R. Kavanagh affiliation: Center for the Environment, Harvard University & MIR Group, Harvard University email: skavanagh@seas.harvard.edu orcid: https://orcid.org/0000-0003-4577-9647 url: https://seankavanagh.com corresponding: true - name: Chuin Wei Tan affiliation: MIR Group, Harvard University - name: Albert Musaelian affiliation: MIR Group, Harvard University & Mirian Technologies - name: William C. Witt affiliation: MIR Group, Harvard University - name: Gabriel de Miranda Nascimento affiliation: MIR Group, Harvard University & MIT - name: Ulrik Unneberg affiliation: MIR Group, Harvard University & MIT - name: Marc L. Descoteaux affiliation: MIR Group, Harvard University - name: Boris Kozinsky affiliation: MIR Group, Harvard University trained_by: - name: Seán R. Kavanagh affiliation: Center for the Environment, Harvard University & MIR Group, Harvard University email: skavanagh@seas.harvard.edu orcid: https://orcid.org/0000-0003-4577-9647 url: https://seankavanagh.com corresponding: true repo: https://github.com/mir-group/nequip url: https://nequip.readthedocs.io/en/latest/ doi: https://doi.org/10.5281/zenodo.16980200 paper: https://arxiv.org/abs/2504.16068 # To be updated... checkpoint_url: https://www.nequip.net/models/mir-group/NequIP-MP-L:0.1 pr_url: https://github.com/janosh/matbench-discovery/pull/282 openness: OSOD # see `Open` enum in matbench_discovery/enums.py train_task: S2EFS # see `Task` enum in matbench_discovery/enums.py test_task: IS2RE-SR # see `Task` enum in matbench_discovery/enums.py targets: EFS_G # see `Targets` enum in matbench_discovery/enums.py model_type: UIP # see `ModelType` enum in matbench_discovery/enums.py model_params: 9_600_000 trained_for_benchmark: true n_estimators: 1 license: code: MIT code_url: https://github.com/mir-group/nequip/blob/main/LICENSE checkpoint: CC-BY-4.0 checkpoint_url: https://creativecommons.org/licenses/by/4.0/legalcode hyperparams: max_force: 0.05 max_steps: 500 ase_optimizer: GOQN # faster than FIRE with same results; see SI of https://doi.org/10.1088/2515-7655/ade916 cell_filter: FrechetCellFilter optimizer: AdamW weight_decay: 1e-3 graph_construction_radius: 6.0 sph_harmonics_l_max: 3 n_layers: 6 n_features: 128 (l=0 scalars), 64 (l=1 vectors), 32 (l=2,3 tensors) parity: false zbl_potential: true type_embed_num_features: 48 polynomial_cutoff: 5 n_radial_bessel_basis: 8 loss: Huber - delta=0.01 for energy, delta=0.1 for stress, stratified delta (0.01, 0.007, 0.004, 0.001) for force loss_weights: energy: 1.0 force: 5.0 stress: 0.01 batch_size: 640 # 4 (gpus) * 160 (batch per gpu) = 640 (total batch size) initial_learning_rate: 0.02 gradient_clip_val: 0.01 learning_rate_schedule: ReduceLROnPlateau - factor=0.1, patience=100, min_lr=1e-6 epochs: 300 max_neighbors: .inf training_cost: Nvidia H100 GPUs: { amount: 4, hours: 72, cost: 288 } requirements: torch: '2' nequip: '>=0.7.0' # >=0.14.0 recommended training_set: [MPtrj] notes: Description: Large 'compliant' NequIP foundation potential; see for details and for model/training infrastructure. Steps: | Single training run on MPtrj with specified parameters. metrics: phonons: kappa_103: pred_file: models/nequip/nequip-MP-L-0.1/2025-08-27-kappa-103-FIRE-dist=0.03-fmax=0.0001-symprec=1e-05.json.gz pred_file_url: https://figshare.com/files/57576187 κ_SRME: 0.4517 κ_SRE: 0.3065 geo_opt: pred_file: models/nequip/nequip-MP-L-0.1/2025-08-27-wbm-IS2RE-GOQN.jsonl.gz pred_file_url: https://figshare.com/files/57810907 struct_col: nequip_structure # same for NequIP/Allegro symprec=1e-2: rmsd: 0.0856 # unitless n_sym_ops_mae: 1.8175 # unitless symmetry_decrease: 0.0592 # fraction symmetry_match: 0.8109 # fraction symmetry_increase: 0.1227 # fraction n_structures: 256963 # count analysis_file: models/nequip/nequip-MP-L-0.1/2025-08-27-wbm-IS2RE-GOQN-symprec=1e-2-moyo=0.4.4.csv.gz analysis_file_url: https://figshare.com/files/57731038 symprec=1e-5: rmsd: 0.0856 # unitless n_sym_ops_mae: 1.9003 # unitless symmetry_decrease: 0.0788 # fraction symmetry_match: 0.7163 # fraction symmetry_increase: 0.1982 # fraction n_structures: 256963 # count analysis_file: models/nequip/nequip-MP-L-0.1/2025-08-27-wbm-IS2RE-GOQN-symprec=1e-5-moyo=0.4.4.csv.gz analysis_file_url: https://figshare.com/files/57731041 discovery: pred_file: models/nequip/nequip-MP-L-0.1/2025-08-27-wbm-IS2RE.csv.gz pred_file_url: https://figshare.com/files/57574483 pred_col: e_form_per_atom_nequip # same for NequIP/Allegro full_test_set: F1: 0.752 # fraction DAF: 4.136 # dimensionless Precision: 0.71 # fraction Recall: 0.8 # fraction Accuracy: 0.909 # fraction TPR: 0.8 # fraction FPR: 0.068 # fraction TNR: 0.932 # fraction FNR: 0.2 # fraction TP: 35263.0 # count FP: 14430.0 # count TN: 198441.0 # count FN: 8829.0 # count MAE: 0.041 # eV/atom RMSE: 0.083 # eV/atom R2: 0.787 # dimensionless missing_preds: 2 # count unique_prototypes: F1: 0.761 # fraction DAF: 4.704 # dimensionless Precision: 0.719 # fraction Recall: 0.809 # fraction Accuracy: 0.921 # fraction TPR: 0.809 # fraction FPR: 0.058 # fraction TNR: 0.942 # fraction FNR: 0.191 # fraction TP: 27002.0 # count FP: 10546.0 # count TN: 171568.0 # count FN: 6372.0 # count MAE: 0.043 # eV/atom RMSE: 0.084 # eV/atom R2: 0.791 # dimensionless missing_preds: 0 # count most_stable_10k: F1: 0.957 # fraction DAF: 6.0 # dimensionless Precision: 0.917 # fraction Recall: 1.0 # fraction Accuracy: 0.917 # fraction TPR: 1.0 # fraction FPR: 1.0 # fraction TNR: 0.0 # fraction FNR: 0.0 # fraction TP: 9172.0 # count FP: 828.0 # count TN: 0.0 # count FN: 0.0 # count MAE: 0.044 # eV/atom RMSE: 0.096 # eV/atom R2: 0.812 # dimensionless missing_preds: 0 # count