mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-30 21:19:40 +00:00
fix(train): guard checkpoint saving against save_freq=0 (#4112)
is_saving_step was the only step-frequency check without a `> 0` guard, so save_freq=0 raised ZeroDivisionError from `step % 0` on the first step. Route the decision through a should_save_checkpoint helper that treats a non-positive save_freq as "save only the final checkpoint", matching how log_freq/eval_freq handle non-positive values. Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
This commit is contained in:
committed by
GitHub
parent
bd2a796217
commit
1fe58f2d3a
@@ -30,6 +30,7 @@ from lerobot.common.train_utils import (
|
||||
save_checkpoint,
|
||||
save_training_state,
|
||||
save_training_step,
|
||||
should_save_checkpoint,
|
||||
update_last_checkpoint,
|
||||
)
|
||||
from lerobot.utils.constants import (
|
||||
@@ -50,6 +51,18 @@ def test_get_step_identifier():
|
||||
assert get_step_identifier(456789, 1_000_000) == "0456789"
|
||||
|
||||
|
||||
def test_should_save_checkpoint():
|
||||
# Periodic checkpoints land on multiples of save_freq.
|
||||
assert should_save_checkpoint(10, save_freq=10, total_steps=100) is True
|
||||
assert should_save_checkpoint(5, save_freq=10, total_steps=100) is False
|
||||
# The final step always saves, even when it is not a multiple of save_freq.
|
||||
assert should_save_checkpoint(100, save_freq=30, total_steps=100) is True
|
||||
# save_freq <= 0 disables periodic saving without raising ZeroDivisionError.
|
||||
assert should_save_checkpoint(1, save_freq=0, total_steps=100) is False
|
||||
assert should_save_checkpoint(100, save_freq=0, total_steps=100) is True
|
||||
assert should_save_checkpoint(1, save_freq=-1, total_steps=100) is False
|
||||
|
||||
|
||||
def test_get_step_checkpoint_dir():
|
||||
output_dir = Path("/checkpoints")
|
||||
step_dir = get_step_checkpoint_dir(output_dir, 1000, 5)
|
||||
|
||||
Reference in New Issue
Block a user