fix ppo trainer save zero3 model

accelerator.get_state_dict(ds_model) should be called at all ranks


Former-commit-id: 3a0f60f0aa072531e4ae5819ec00c8fa42aa0913

src/llamafactory/train/sft/metric.py

@@ -10,12 +10,15 @@ from ...extras.packages import is_jieba_available, is_nltk_available, is_rouge_a
 if TYPE_CHECKING:
     from transformers.tokenization_utils import PreTrainedTokenizer
 
+
 if is_jieba_available():
     import jieba  # type: ignore
 
+
 if is_nltk_available():
     from nltk.translate.bleu_score import SmoothingFunction, sentence_bleu
 
+
 if is_rouge_available():
     from rouge_chinese import Rouge