From 8827e26b8d487f123f8d7d5cbd8d00b81dcefcff Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 23 二月 2024 00:58:18 +0800
Subject: [PATCH] fp16
---
funasr/train_utils/trainer.py | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 5b280bf..3b20596 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -14,6 +14,7 @@
from funasr.train_utils.device_funcs import to_device
from funasr.train_utils.recursive_op import recursive_average
from funasr.train_utils.average_nbest_models import average_checkpoints
+from torch.distributed.fsdp.sharded_grad_scaler import ShardedGradScaler
@contextmanager
def maybe_autocast(enabled):
@@ -84,7 +85,9 @@
self.batch_total = 0
self.use_fp16 = use_fp16
self.disable_gpu_cache = kwargs.get("disable_gpu_cache", True)
- self.scaler = GradScaler(enabled=use_fp16) if use_fp16 else None
+ scaler = GradScaler(enabled=use_fp16) if use_fp16 else None
+ scaler = ShardedGradScaler(enabled=use_fp16) if use_ddp else scaler
+ self.scaler = scaler
try:
--
Gitblit v1.9.1