Nequip-OAM-L
Discovery: energy and convex hull diagnostics
Missing preds: 0
Loading formation energy parity data...
Per-element convex hull distance errors
1 H 0.14
2 He Helium
3 Li 0.03
4 Be 0.02
5 B 0.06
6 C 0.05
7 N 0.07
8 O 0.11
9 F 0.11
10 Ne Neon
11 Na 0.03
12 Mg 0.04
13 Al 0.05
14 Si 0.06
15 P 0.05
16 S 0.07
17 Cl 0.09
18 Ar Argon
19 K 0.03
20 Ca 0.04
21 Sc 0.03
22 Ti 0.04
23 V 0.06
24 Cr 0.08
25 Mn 0.11
26 Fe 0.09
27 Co 0.05
28 Ni 0.04
29 Cu 0.04
30 Zn 0.04
31 Ga 0.04
32 Ge 0.05
33 As 0.05
34 Se 0.09
35 Br 0.07
36 Kr Krypton
37 Rb 0.03
38 Sr 0.03
39 Y 0.04
40 Zr 0.04
41 Nb 0.05
42 Mo 0.05
43 Tc 0.04
44 Ru 0.05
45 Rh 0.05
46 Pd 0.04
47 Ag 0.03
48 Cd 0.03
49 In 0.05
50 Sn 0.04
51 Sb 0.05
52 Te 0.11
53 I 0.06
54 Xe 0.07
55 Cs 0.03
56 Ba 0.03
57 La 0.03
58 Ce 0.03
59 Pr 0.03
60 Nd 0.03
61 Pm 0.03
62 Sm 0.03
63 Eu 0.06
64 Gd 0.04
65 Tb 0.03
66 Dy 0.03
67 Ho 0.03
68 Er 0.03
69 Tm 0.03
70 Yb 0.05
71 Lu 0.03
72 Hf 0.04
73 Ta 0.07
74 W 0.04
75 Re 0.04
76 Os 0.05
77 Ir 0.06
78 Pt 0.05
79 Au 0.06
80 Hg 0.03
81 Tl 0.03
82 Pb 0.05
83 Bi 0.04
84 Po Polonium
85 At Astatine
86 Rn Radon
87 Fr Francium
88 Ra Radium
89 Ac 0.03
90 Th 0.04
91 Pa 0.05
92 U 0.06
93 Np 0.09
94 Pu 0.20
95 Am Americium
96 Cm Curium
97 Bk Berkelium
98 Cf Californium
99 Es Einsteinium
100 Fm Fermium
101 Md Mendelevium
102 No Nobelium
103 Lr Lawrencium
104 Rf Rutherfordium
105 Db Dubnium
106 Sg Seaborgium
107 Bh Bohrium
108 Hs Hassium
109 Mt Meitnerium
110 Ds Darmstadtium
111 Rg Roentgenium
112 Cn Copernicum
113 Nh Nihonium
114 Fl Flerovium
115 Mc Moscovium
116 Lv Livermorium
117 Ts Tennessine
118 Og Oganesson
57-71 La-Lu Lanthanides
89-103 Ac-Lr Actinides
ML vs DFT Lattice Thermal Conductivity
Loading κ parity data...
Model Authors
- Seán R. Kavanagh Center for the Environment, Harvard University & MIR Group, Harvard University
- Chuin Wei Tan MIR Group, Harvard University
- Albert Musaelian MIR Group, Harvard University & Mirian Technologies
- William C. Witt MIR Group, Harvard University
- Gabriel de Miranda Nascimento MIR Group, Harvard University & MIT
- Ulrik Unneberg MIR Group, Harvard University & MIT
- Marc L. Descoteaux MIR Group, Harvard University
- Boris Kozinsky MIR Group, Harvard University
Trained By
Model Info
- Version 0.1
- Role Interatomic potential
- Architecture gnn
- Targets EFSG
- Openness OSOD
- Discovery Train Task S2EFS
- Discovery Test Task IS2RE-SR
Training Set
MPtrj: 1.58M structures from 146k materials
OMat24: 101M structures from 3.23M materials
Subsampled Alexandria: 10.4M structures from 3.23M materials
description
Large NequIP foundation potential; see https://www.nequip.net/models/mir-group/NequIP-OAM-L:0.1 for details and https://arxiv.org/abs/2504.16068 for model/training infrastructure.
steps
Training performed by: (1) pre-training on OMat24; (2) fine-tuning on MPtrj+sAlex, with a reduced learning rate (1e-4), energy-loss-upweighting (1:1:0.01 instead of 1:5:0.01) and StochasticWeightAveraging (SWA).
Hyperparams
- evaluation:
{"max_force":0.05,"max_steps":500,"ase_optimizer":"GOQN","cell_filter":"FrechetCellFilter","kappa":{"protocol":"phonondb-v1","displacement_distance":0.03,"save_forces":true}} - architecture:
{"graph_construction_radius":6,"n_layers":6} - training:
{"batch_size":640,"initial_learning_rate":0.005,"epochs":30,"optimizer":"AdamW"} - upstream_config:
{"weight_decay":1e-8,"sph_harmonics_l_max":3,"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,"force":5,"stress":0.01},"gradient_clip_val":1,"learning_rate_schedule":"ReduceLROnPlateau - factor=0.1, patience=10, min_lr=1e-6"}