Describe the current behavior / 问题描述 (Mandatory / 必填)

facerecognition网络在910B环境训练，出现loss打印异常情况
模型仓地址：https://gitee.com/mindspore/models/tree/master/research/cv/FaceRecognition

Environment / 环境信息 (Mandatory / 必填)

• Hardware Environment(Ascend/GPU/CPU) / 硬件环境:

Please delete the backend not involved / 请删除不涉及的后端:
/device ascend/

• Software Environment / 软件环境 (Mandatory / 必填):
  -- MindSpore version (e.g., 1.7.0.Bxxx) :
  -- Python version (e.g., Python 3.7.5) :
  -- OS platform and distribution (e.g., Linux Ubuntu 16.04):
  -- GCC/Compiler version (if compiled from source):

run：Milan_C13/20231011
mindspore:version/202310/20231012/master_20231012211532_d6223dc8ce70f96682a5d8b6d14aed36712d8f76

• Excute Mode / 执行模式 (Mandatory / 必填)(PyNative/Graph):

Please delete the mode not involved / 请删除不涉及的模式:

/mode graph

Related testcase / 关联用例 (Mandatory / 必填)

用例仓地址：solution_test/cases/02network/00cv/facerecognition/pynative/
用例：
test_ms_usability_benchmark_graph_ascend_facerecognition_time_perf_loss_1p_0001

Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)

1. get code from models
2. cd models/research/cv/FaceRecognition
3. bash run_standalone_train_base.sh DEVICE_ID
   4.验证网络是否训练成功
4. 验证网络loss是否正常

Describe the expected behavior / 预期结果 (Mandatory / 必填)

网络训练成功，loss正常

Related log / screenshot / 日志 / 截图 (Mandatory / 必填)

2023-10-16 10:10:55,584:INFO:epoch[0], iter[10], loss:(Tensor(shape=[], dtype=Float32, value= 46.9084), Tensor(shape=[], dtype=Bool, value= True), Tensor(shape=[], dtype=Float32, value= 64)), cur_lr:0.000082, mean_fps:11.85 imgs/sec
2023-10-16 10:10:58,011:INFO:epoch[0], iter[20], loss:(Tensor(shape=[], dtype=Float32, value= 46.801), Tensor(shape=[], dtype=Bool, value= False), Tensor(shape=[], dtype=Float32, value= 16)), cur_lr:0.000163, mean_fps:893.01 imgs/sec

Special notes for this issue/备注 (Optional / 选填)

走给杨威