From 87da7393041a9afaa42dc8c4b0fd3bcff624c182 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 23:09:33 +0800
Subject: [PATCH] update
---
funasr/bin/train.py | 20 +++++++++++++++++++-
1 files changed, 19 insertions(+), 1 deletions(-)
diff --git a/funasr/bin/train.py b/funasr/bin/train.py
index f684f3b..38a35c7 100755
--- a/funasr/bin/train.py
+++ b/funasr/bin/train.py
@@ -59,16 +59,19 @@
)
parser.add_argument(
"--dist_world_size",
+ type=int,
default=1,
help="number of nodes for distributed training",
)
parser.add_argument(
"--dist_rank",
+ type=int,
default=None,
help="node rank for distributed training",
)
parser.add_argument(
"--local_rank",
+ type=int,
default=None,
help="local rank for distributed training",
)
@@ -85,6 +88,22 @@
type=int_or_none,
help="The master port for distributed training"
"This value is used when dist_init_method == 'env://'",
+ )
+ parser.add_argument(
+ "--dist_launcher",
+ default=None,
+ type=str_or_none,
+ choices=["slurm", "mpi", None],
+ help="The launcher type for distributed training",
+ )
+ parser.add_argument(
+ "--multiprocessing_distributed",
+ default=True,
+ type=str2bool,
+ help="Use multi-processing distributed training to launch "
+ "N processes per node, which has N GPUs. This is the "
+ "fastest way to use PyTorch for either single node or "
+ "multi node data parallel training",
)
parser.add_argument(
"--unused_parameters",
@@ -449,7 +468,6 @@
args, extra_task_params = parser.parse_known_args()
if extra_task_params:
args = build_args(args, parser, extra_task_params)
- # args = argparse.Namespace(**vars(args), **vars(task_args))
# set random seed
set_all_random_seed(args.seed)
--
Gitblit v1.9.1