Skip to content
Closed
Changes from all commits
Commits
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
8 changes: 5 additions & 3 deletions FlagEmbedding/abc/finetune/embedder/AbsDataset.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
from dataclasses import dataclass
from torch.utils.data import Dataset
from transformers import (
PreTrainedTokenizer,
PreTrainedTokenizer,
DataCollatorWithPadding,
TrainerCallback,
TrainerState,
Expand Down Expand Up @@ -63,7 +63,8 @@ def _load_dataset(self, file_path: str):
Returns:
datasets.Dataset: Loaded HF dataset.
"""
if dist.get_rank() == 0:
get_rank_safe = lambda: dist.get_rank() if dist.is_initialized() else 0
if get_rank_safe() == 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:
get_rank_safe = lambda: dist.get_rank() if dist.is_initialized() else 0
if get_rank_safe() == 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