Skip to content

Reset scaling.json files when evaluating RCPs #432

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
merged 1 commit into from
Aug 29, 2025
Merged

Reset scaling.json files when evaluating RCPs #432

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
6 changes: 6 additions & 0 deletions mlperf_logging/rcp_checker/rcp_checker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,6 +439,11 @@ def _set_results_scaling(self, scale_factor, results_dir):
with open(filepath, "w") as scaling_file:
scaling_file.write(json_content)

def _reset_results_scaling(self, results_dir):
filepath = results_dir+'/scaling.json'
if os.path.exists(filepath):
os.remove(filepath)

def _eval_submission_record(self, rcp_record, subm_epochs, results_dir):
'''Compare reference and submission convergence.'''

Expand All @@ -449,6 +454,7 @@ def _eval_submission_record(self, rcp_record, subm_epochs, results_dir):
samples_rejected = 4 if rcp_record["Benchmark"] == 'unet3d' else 1
mean_subm_epochs = np.mean(subm_epochs[samples_rejected:len(subm_epochs)-samples_rejected])
norm_factor = self._find_norm_factor(rcp_record, mean_subm_epochs)
self._reset_results_scaling(results_dir)
if mean_subm_epochs >= (rcp_record["RCP Mean"] / rcp_record["Max Speedup"]):
logging.info(" RCP Record: %s", rcp_record)
logging.info(" Submission mean epochs: %.4f", mean_subm_epochs)
Expand Down