[trainer] update config (#7174)

Former-commit-id: 9f535d0e3c4ee3cd0f1b65218c2eee5d03f43c6f
This commit is contained in:
hoshi-hiyouga
2025-03-05 23:32:54 +08:00
committed by GitHub
parent fd0357a26d
commit 7b985f55db
13 changed files with 49 additions and 7 deletions

View File

@@ -17,6 +17,7 @@ import shutil
from typing import TYPE_CHECKING, Any, Dict, List, Optional
import torch
import torch.distributed as dist
from transformers import PreTrainedModel
from ..data import get_template_and_fix_tokenizer
@@ -76,6 +77,12 @@ def _training_function(config: Dict[str, Any]) -> None:
else:
raise ValueError(f"Unknown task: {finetuning_args.stage}.")
try:
if dist.is_initialized():
dist.destroy_process_group()
except Exception as e:
logger.warning(f"Failed to destroy process group: {e}.")
def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["TrainerCallback"]] = None) -> None:
args = read_args(args)