Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 3 additions & 1 deletion recml/core/training/jax_trainer.py
Original file line number Diff line number Diff line change
Expand Up @@ -455,8 +455,10 @@ def checkpoint_manager(self) -> ocp.CheckpointManager:

save_on_steps = set(save_on_steps)

checkpoint_dir = os.path.join(self._model_dir, core.CHECKPOINT_DIR)

return ocp.CheckpointManager(
directory=os.path.join(self._model_dir, core.CHECKPOINT_DIR),
directory=checkpoint_dir,
options=ocp.CheckpointManagerOptions(
should_save_fn=lambda step, _: step in save_on_steps,
max_to_keep=self._max_checkpoints_to_keep,
Expand Down
3 changes: 2 additions & 1 deletion recml/core/training/jax_trainer_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -16,9 +16,11 @@
from collections.abc import Mapping, Sequence
import dataclasses
import os
from unittest import mock

from absl import flags
from absl.testing import absltest
from absl.testing import flagsaver
from absl.testing import parameterized
import clu.metrics as clu_metrics
import flax.linen as nn
Expand Down Expand Up @@ -260,6 +262,5 @@ class State:
self.assertIn("optimizer/learning_rate", metrics)
self.assertEqual(metrics["optimizer/learning_rate"].compute(), 0.1)


if __name__ == "__main__":
absltest.main()
1 change: 1 addition & 0 deletions recml/core/utils/keras_utils_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@

from absl import flags
from absl.testing import absltest
from absl.testing import flagsaver
from absl.testing import parameterized
import jax
import jax.numpy as jnp
Expand Down
Loading