From 811c516932fd91d17ada8e802a3b2e9ae028be66 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 31 十月 2024 18:39:34 +0800
Subject: [PATCH] docs: 更新教程文档链接
---
funasr/bin/train_ds.py | 11 ++++++++---
1 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.py
index 41ecbe4..5b1eeaa 100644
--- a/funasr/bin/train_ds.py
+++ b/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
@@ -81,8 +81,13 @@
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()
logging.info("Build model, frontend, tokenizer")
device = kwargs.get("device", "cuda")
@@ -144,7 +149,7 @@
dataloader = dataloader_class(**kwargs)
# dataloader_tr, dataloader_val = dataloader_class(**kwargs)
- scaler = GradScaler(enabled=trainer.use_fp16) if trainer.use_fp16 else None
+ scaler = GradScaler(enabled=True) if trainer.use_fp16 or trainer.use_bf16 else None
scaler = ShardedGradScaler(enabled=trainer.use_fp16) if trainer.use_fsdp else scaler
trainer.resume_checkpoint(
--
Gitblit v1.9.1