eu9ene
commented
2 weeks ago Ok, I renamed the existing artifacts with this script:
import os
import subprocess
ls_cmd = 'gsutil ls gs://moz-fx-translations-data--303e-prod-translations-data/models/*/*/evaluation/*/*'
result = subprocess.run(list(ls_cmd.split()), universal_newlines=True, stdout=subprocess.PIPE)
eval_files = result.stdout.split('\n')
for file in eval_files:
if not file.strip():
continue
sep_pos = file.rfind('/')
file_name = file[sep_pos+1:]
if file_name.startswith('mtdata') or file_name.startswith('sacrebleu') or file_name.startswith('flores'):
print(f'Skipping {file_name}, already renamed')
continue
if file_name.startswith('aug'):
dataset_sep_pos = file_name.find('_')
dataset_name = file_name[dataset_sep_pos+1:]
else:
dataset_name = file_name
importer = ""
if dataset_name.startswith('wmt'):
importer = 'sacrebleu'
elif dataset_name.startswith('devtest'):
importer = 'flores'
elif dataset_name.startswith('test'):
importer = 'flores'
elif dataset_name.startswith('Neulab'):
importer = 'mtdata'
else:
raise ValueError(f'Unknown dataset name: {dataset_name}')
new_file_name = f'{importer}_{file_name}'
new_file = file[:sep_pos] + '/' + new_file_name
rename_cmd = f'gsutil mv {file} {new_file}'
print(f'Renaming {file_name} to {new_file_name} with command {rename_cmd}')
subprocess.run(list(rename_cmd.split()))
print('\n')
For example:
shows
For example
aug-mix_wmt19.metricsshould besacrebleu_aug-mix_wmt19.metricslike we have for the old Snakemake experiments. Otherwise we can't upload it to W&B to compare with other experiments. See this comment: https://github.com/mozilla/firefox-translations-training/pull/799#issuecomment-2298932937