Skip to content

fix bug: safe dist.get_rank() #1532

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
hanhainebula merged 1 commit into from
Sep 23, 2025
Merged

fix bug: safe dist.get_rank() #1532

Show file tree
Hide file tree
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: 4 additions & 2 deletions FlagEmbedding/abc/finetune/embedder/AbsDataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,8 @@ def _load_dataset(self, file_path: str):
Returns:
datasets.Dataset: Loaded HF dataset.
"""
if dist.get_rank() == 0:
safe_rank = dist.get_rank() if dist.is_initialized() else 0
if safe_rank == 0:
logger.info(f'loading data from {file_path} ...')

temp_dataset = datasets.load_dataset('json', data_files=file_path, split='train', cache_dir=self.args.cache_path)
Expand Down Expand Up @@ -342,7 +343,8 @@ def _load_dataset(self, file_path: str):
Returns:
datasets.Dataset: The loaded dataset.
"""
if dist.get_rank() == 0:
safe_rank = dist.get_rank() if dist.is_initialized() else 0
if safe_rank == 0:
logger.info(f'loading data from {file_path} ...')

temp_dataset = datasets.load_dataset('json', data_files=file_path, split='train', cache_dir=self.args.cache_path)
Expand Down
4 changes: 2 additions & 2 deletions FlagEmbedding/abc/finetune/embedder/AbsModeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,8 +54,8 @@ def __init__(
if self.negatives_cross_device:
if not dist.is_initialized():
raise ValueError('Distributed training has not been initialized for representation all gather.')
self.process_rank = dist.get_rank()
self.world_size = dist.get_world_size()
self.process_rank = dist.get_rank() if dist.is_initialized() else 0
self.world_size = dist.get_world_size() if dist.is_initialized() else 1

self.sub_batch_size = sub_batch_size
self.kd_loss_type = kd_loss_type
Expand Down
3 changes: 2 additions & 1 deletion FlagEmbedding/abc/finetune/reranker/AbsDataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,8 @@ def _load_dataset(self, file_path: str):
Returns:
datasets.Dataset: Loaded HF dataset.
"""
if dist.get_rank() == 0:
safe_rank = dist.get_rank() if dist.is_initialized() else 0
if safe_rank == 0:
logger.info(f'loading data from {file_path} ...')

temp_dataset = datasets.load_dataset('json', data_files=file_path, split='train', cache_dir=self.args.cache_path)
Expand Down
Loading