Trained weights of DecayFormer, a compact hybrid state space / attention model that forecasts a battery cell's full state of health (SOH) trajectory from its first 100 cycles, for all 22 aging-condition-exclusive folds of the BatteryLife benchmark as defined by BatteryMFormer. One model per fold; 791,529 parameters.
Code, reproducibility notebooks and documentation: github.com/ShreyPatel1311/DecayFormer. License: MIT.
Test MAPE (%) from BatteryMFormer's released evaluation (evaluate_model.py,
fp16), on each fold's own test set. Mean ± std across folds:
| Domain | Folds | Test MAPE |
|---|---|---|
| Li-ion | 3 | 2.281 ± 0.089 |
| Zn-ion | 3 | 6.814 ± 0.540 |
| Na-ion | 12 | 0.926 ± 0.282 |
| CALB | 4 | 2.783 ± 2.200 |
| Fold | Test MAPE | Early-stopping patience |
|---|---|---|
Li-ion/seed2021 |
2.375 | 30 |
Li-ion/seed42 |
2.197 | 30 |
Li-ion/seed2024 |
2.272 | 30 |
Zn-ion/seed2021 |
6.248 | 30 |
Zn-ion/seed42 |
6.869 | 30 |
Zn-ion/seed2024 |
7.324 | 30 |
Na-ion/cond400 |
0.660 | 30 |
Na-ion/cond401 |
1.346 | 50 |
Na-ion/cond402 |
0.843 | 50 |
Na-ion/cond403 |
0.834 | 30 |
Na-ion/cond404 |
1.001 | 30 |
Na-ion/cond405 |
0.831 | 30 |
Na-ion/cond406 |
0.487 | 30 |
Na-ion/cond407 |
1.463 | 30 |
Na-ion/cond408 |
1.006 | 30 |
Na-ion/cond409 |
1.138 | 30 |
Na-ion/cond410 |
0.721 | 30 |
Na-ion/cond411 |
0.785 | 30 |
CALB/cond396 |
5.209 | 30 |
CALB/cond397 |
0.946 | 30 |
CALB/cond398 |
0.893 | 30 |
CALB/cond399 |
4.082 | 30 |
All 22 models share one configuration: d_model 96, 3 encoder blocks, 4 attention
heads, dropout 0.1; AdamW at learning rate 5e-4 with a constant schedule; batch
128 (one GPU, equal to BatteryMFormer's 2 x 64 recipe); up to 300 epochs with
early stopping on validation MAPE; fp16; each fold's own seed (2021, 42 or 2024).
The only per-fold difference is early-stopping patience: 50 for Na-ion cond401 and
cond402, 30 for every other fold. Training ran inside BatteryMFormer's released
pipeline (commit febe174) on BatteryLife v11, so data, targets, training loop and
evaluation are common to all models compared with it.
config.json architecture (DecayFormerConfig)
<Domain>/<fold>/
model.safetensors weights, saved from BatteryMFormer's pipeline (keys prefixed "net.")
args.json training arguments in that pipeline
label_scaler label scaler expected by that pipeline's data loader
Domains: Li-ion (seed2021, seed42, seed2024), Zn-ion (seed2021, seed42,
seed2024), Na-ion (cond400 to cond411), CALB (cond396 to cond399).
from decayformer import load_fold # pip install from the DecayFormer repository
model = load_fold("Na-ion/cond400")
# x [B, 100, 300, 4] curves, mask [B, 100], soh [B, 100, 1], cycle_feats [B, 100, 2]
trajectory = model(x, mask, soh, cycle_feats) # [B, 5000] normalised SOH
To reproduce the table above, follow the notebooks in the repository, which evaluate these weights with BatteryMFormer's own pipeline.
CALB/cond396/model.safetensors 5 MBCALB/cond397/model.safetensors 5 MBCALB/cond398/model.safetensors 5 MBCALB/cond399/model.safetensors 5 MBLi-ion/seed2021/model.safetensors 5 MBLi-ion/seed2024/model.safetensors 5 MBLi-ion/seed42/model.safetensors 5 MBNa-ion/cond400/model.safetensors 5 MBNa-ion/cond401/model.safetensors 5 MBNa-ion/cond402/model.safetensors 5 MBNa-ion/cond403/model.safetensors 5 MBNa-ion/cond404/model.safetensors 5 MBNa-ion/cond405/model.safetensors 5 MBNa-ion/cond406/model.safetensors 5 MBNa-ion/cond407/model.safetensors 5 MBNa-ion/cond408/model.safetensors 5 MBNa-ion/cond409/model.safetensors 5 MBNa-ion/cond410/model.safetensors 5 MBNa-ion/cond411/model.safetensors 5 MBZn-ion/seed2021/model.safetensors 5 MBZn-ion/seed2024/model.safetensors 5 MBZn-ion/seed42/model.safetensors 5 MB