Skip to content

Omit FOM for non-convergence runs #86

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
michaelmckinsey1 merged 2 commits into from
Jul 16, 2026
Merged

Omit FOM for non-convergence runs #86

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4610cae
remove fom when not converging
michaelmckinsey1 Jul 10, 2026
5e0c39f
Fix artifact
michaelmckinsey1 Jul 16, 2026
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
15 changes: 7 additions & 8 deletions ScaFFold/worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,8 +284,6 @@ def main(kwargs_dict: dict = {}):
outfile_path = trainer.outfile_path
train_data = np.genfromtxt(outfile_path, dtype=float, delimiter=",", names=True)
total_train_time = train_data["epoch_duration"].sum()
fom = 1.0 / total_train_time
adiak_value("FOM", fom)
if "total_optimizer_steps" in train_data.dtype.names:
optimizer_steps = np.atleast_1d(train_data["total_optimizer_steps"])
total_optimizer_steps = int(optimizer_steps[-1])
Expand All @@ -296,15 +294,16 @@ def main(kwargs_dict: dict = {}):
else:
total_optimizer_steps = int(getattr(trainer, "total_optimizer_steps", 0))
adiak_value("total_optimizer_steps", total_optimizer_steps)
log.info(
f"FOM = {fom} (1 / total_train_time={total_train_time:.6f} seconds). "
f"This FOM is specific to problem_scale={config.problem_scale}, "
f"target_dice={config.target_dice}, seed={config.seed}, "
f"total_optimizer_steps={total_optimizer_steps}."
)
epochs = np.atleast_1d(train_data["epoch"])
total_epochs = int(epochs[-1])
if config.epochs == -1:
fom = 1.0 / total_train_time
adiak_value("FOM", fom)
log.info(
f"FOM = {fom} (1 / total_train_time={total_train_time:.6f} seconds). "
f"This FOM is specific to problem_scale={config.problem_scale}, "
f"target_dice={config.target_dice}, seed={config.seed}."
)
extra_msg = f"Trained to >= {config.target_dice} validation dice score in {total_train_time:.2f} seconds, {total_epochs} epochs, {total_optimizer_steps} optimizer steps."
else:
extra_msg = f"Completed in {total_train_time:.2f} seconds, {total_epochs} epochs, {total_optimizer_steps} optimizer steps."
Expand Down
Loading