Merge pull request #2267 from modelscope/dev_sx2

Shi Xian

2024-12-05 0efc87352ce7d3903dbdedbfa5d01ca5e1cb19e7

 funasr/bin/train_ds.py

@@ -27,7 +27,7 @@
from funasr.train_utils.trainer_ds import Trainer
from funasr.schedulers import scheduler_classes
from funasr.train_utils.initialize import initialize
from funasr.download.download_from_hub import download_model
from funasr.download.download_model_from_hub import download_model
from funasr.models.lora.utils import mark_only_lora_as_trainable
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
@@ -81,7 +81,10 @@
        deepspeed.init_distributed(dist_backend=kwargs.get("backend", "nccl"))
    elif use_ddp or use_fsdp:
        logging.info(f"use_ddp: {use_ddp}, use_fsdp: {use_fsdp}")
        dist.init_process_group(backend=kwargs.get("backend", "nccl"), init_method="env://")
        dist.init_process_group(
            backend=kwargs.get("backend", "nccl"),
            init_method="env://",
        )
        torch.cuda.set_device(local_rank)

    # rank = dist.get_rank()
@@ -131,7 +134,7 @@
        **kwargs.get("train_conf"),
    )

    model = trainer.warp_model(model)
    model = trainer.warp_model(model, **kwargs)

    kwargs["device"] = int(os.environ.get("LOCAL_RANK", 0))
    trainer.device = int(os.environ.get("LOCAL_RANK", 0))