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

Update pretraining.py #167

Merged
merged 1 commit into from
Aug 21, 2023
Merged

Update pretraining.py #167

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
2 changes: 1 addition & 1 deletion pretraining.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,7 +457,7 @@ def group_texts(examples):
raise ValueError(f"train files must be same type, e.g. all txt or all jsonl, but got {types}")
data_files["train"] = train_data_files
if data_args.validation_file_dir is not None and os.path.exists(data_args.validation_file_dir):
eval_data_files = glob(f'{data_args.train_file_dir}/**/*.txt', recursive=True) + glob(
eval_data_files = glob(f'{data_args.validation_file_dir}/**/*.txt', recursive=True) + glob(
f'{data_args.train_file_dir}/**/*.json', recursive=True) + glob(
f'{data_args.train_file_dir}/**/*.jsonl', recursive=True)
logger.info(f"eval files: {eval_data_files}")
Expand Down