Single-Output Regression¶

Train a model that predicts a single scalar property (formation energy, bandgap, bulk modulus, …).

Command¶

train_alignn.py \
  --root_dir "alignn/examples/sample_data" \
  --config "alignn/examples/sample_data/config_example.json" \
  --output_dir=temp

What you need¶

A dataset directory with structures and id_prop.csv — see Dataset Format.
A config JSON, e.g. config_example.json.

The bundled sample_data trains OPT-bandgap on 50 JARVIS-DFT materials. The data was generated by generate_sample_data_reg.py — adapt it to build a larger dataset or use your own structures.

Output¶

After training finishes, --output_dir contains:

best_model.pt — the model checkpoint with the lowest validation loss
history_train.json, history_val.json — per-epoch metrics
prediction_results_test_set.csv — predictions on the held-out test set

CLI reference¶

train_alignn.py -h

Tips¶

Use batch_size: 32 or 64 in the config for real trainings.
If you need to train on one set and evaluate on another, set n_train, n_val, n_test and keep_data_order: true.
For datasets hosted by jarvis-tools, the alignn/scripts/ directory has ready-to-run scripts that download and train in one step.