From 57e023e5cfa522007e24d87c8e3d82bf7c4a19cd Mon Sep 17 00:00:00 2001
From: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Date: 星期二, 18 二月 2025 15:15:40 +0800
Subject: [PATCH] Merge pull request #2382 from msgk239/dev_clean
---
funasr/bin/train_ds.py | 12 +++++++++---
1 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.py
index 415904e..10a5d08 100644
--- a/funasr/bin/train_ds.py
+++ b/funasr/bin/train_ds.py
@@ -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))
@@ -181,7 +184,10 @@
)
trainer.start_step = 0
- torch.cuda.empty_cache()
+ device = next(model.parameters()).device
+ if device.type == "cuda":
+ with torch.cuda.device(device):
+ torch.cuda.empty_cache()
time_escaped = (time.perf_counter() - time_slice_i) / 3600.0
logging.info(
--
Gitblit v1.9.1