Skip to content
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

Jump to bottom

Ray Tune Intermediate Checkpoint Cleaning #1255

Merged
merged 1 commit into from
Aug 13, 2021
Merged

Ray Tune Intermediate Checkpoint Cleaning #1255

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
7 changes: 5 additions & 2 deletions ludwig/hyperopt/execution.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,8 @@ def _has_eval_metric(self, stats):

def get_metric_score(self, train_stats, eval_stats) -> float:
if self._has_metric(train_stats, TEST):
logger.info("Returning metric score from training (test) statistics")
logger.info(
"Returning metric score from training (test) statistics")
return self.get_metric_score_from_train_stats(train_stats, TEST)
elif self._has_eval_metric(eval_stats):
logger.info("Returning metric score from eval statistics. "
Expand All @@ -86,7 +87,8 @@ def get_metric_score(self, train_stats, eval_stats) -> float:
"best validation performance")
return self.get_metric_score_from_eval_stats(eval_stats)
elif self._has_metric(train_stats, VALIDATION):
logger.info("Returning metric score from training (validation) statistics")
logger.info(
"Returning metric score from training (validation) statistics")
return self.get_metric_score_from_train_stats(train_stats, VALIDATION)
elif self._has_metric(train_stats, TRAINING):
logger.info("Returning metric score from training split statistics, "
Expand Down Expand Up @@ -948,6 +950,7 @@ def run_experiment_trial(config, checkpoint_dir=None):
scheduler=self.scheduler,
search_alg=search_alg,
num_samples=self.num_samples,
keep_checkpoints_num=1,
resources_per_trial=resources_per_trial,
time_budget_s=self.time_budget_s,
queue_trials=True,
Expand Down