Skip to content

Remove jax.spmd_mode, its no longer supported #179

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
entrpn merged 1 commit into from
Jun 2, 2025
Merged

Remove jax.spmd_mode, its no longer supported #179

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
39 changes: 19 additions & 20 deletions src/maxdiffusion/train_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,27 +100,26 @@ def write_metrics(writer, local_metrics_file, running_gcs_metrics, metrics, step

def write_metrics_to_tensorboard(writer, metrics, step, config):
"""Writes metrics to tensorboard"""
with jax.spmd_mode("allow_all"):
if jax.process_index() == 0:
for metric_name in metrics.get("scalar", []):
writer.add_scalar(metric_name, np.array(metrics["scalar"][metric_name]), step)
for metric_name in metrics.get("scalars", []):
writer.add_scalars(metric_name, metrics["scalars"][metric_name], step)

full_log = step % config.log_period == 0
if jax.process_index() == 0:
max_logging.log(
"completed step: {}, seconds: {:.3f}, TFLOP/s/device: {:.3f}, loss: {:.3f}".format(
step,
metrics["scalar"]["perf/step_time_seconds"],
metrics["scalar"]["perf/per_device_tflops_per_sec"],
float(metrics["scalar"]["learning/loss"]),
)
)
if jax.process_index() == 0:
for metric_name in metrics.get("scalar", []):
writer.add_scalar(metric_name, np.array(metrics["scalar"][metric_name]), step)
for metric_name in metrics.get("scalars", []):
writer.add_scalars(metric_name, metrics["scalars"][metric_name], step)

full_log = step % config.log_period == 0
if jax.process_index() == 0:
max_logging.log(
"completed step: {}, seconds: {:.3f}, TFLOP/s/device: {:.3f}, loss: {:.3f}".format(
step,
metrics["scalar"]["perf/step_time_seconds"],
metrics["scalar"]["perf/per_device_tflops_per_sec"],
float(metrics["scalar"]["learning/loss"]),
)
)

if full_log and jax.process_index() == 0:
max_logging.log(f"To see full metrics 'tensorboard --logdir={config.tensorboard_dir}'")
writer.flush()
if full_log and jax.process_index() == 0:
max_logging.log(f"To see full metrics 'tensorboard --logdir={config.tensorboard_dir}'")
writer.flush()


def get_params_to_save(params):
Expand Down
Loading