Skip to content
Open
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
4 changes: 4 additions & 0 deletions data_juicer/core/executor/ray_executor_partitioned.py
Original file line number Diff line number Diff line change
Expand Up @@ -156,6 +156,8 @@ def __init__(self, cfg: Optional[Namespace] = None):

self.executor_type = "ray_partitioned"
self.work_dir = self.cfg.work_dir
if self.work_dir and "://" not in self.work_dir:
self.work_dir = os.path.abspath(self.work_dir)
self.job_id = self.cfg.get("job_id", None)

# Initialize temporary directory for Ray operations
Expand All @@ -178,6 +180,8 @@ def __init__(self, cfg: Optional[Namespace] = None):
# Checkpoint configuration and manager initialization
checkpoint_cfg = getattr(self.cfg, "checkpoint", None)
checkpoint_dir = getattr(self.cfg, "checkpoint_dir", os.path.join(self.work_dir, "checkpoints"))
if checkpoint_dir and "://" not in checkpoint_dir:
checkpoint_dir = os.path.abspath(checkpoint_dir)

if checkpoint_cfg:
# Use ConfigAccessor to handle both dict and object configurations
Expand Down
Loading