2023/02/17 12:07:22 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0] CUDA available: True numpy_random_seed: 81210210 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.6.0 MMEngine: 0.5.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/02/17 12:07:22 - mmengine - INFO - Config: preprocess_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]) model = dict( type='Recognizer2D', backbone=dict( type='ResNetTSM', pretrained='torchvision://resnet50', depth=50, norm_eval=False, shift_div=8, num_segments=16), cls_head=dict( type='TSMHead', num_classes=174, in_channels=2048, spatial_type='avg', consensus=dict(type='AvgConsensus', dim=1), dropout_ratio=0.5, init_std=0.001, is_shift=True, average_clips='prob', num_segments=16), data_preprocessor=dict( type='ActionDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]), train_cfg=None, test_cfg=None) default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=20, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=3, save_best='auto', max_keep_ckpts=3), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ] visualizer = dict( type='ActionVisualizer', vis_backends=[ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ]) log_level = 'INFO' load_from = None resume = False dataset_type = 'VideoDataset' data_root = 'data/sthv2/videos' ann_file_train = 'data/sthv2/sthv2_train_list_videos.txt' ann_file_val = 'data/sthv2/sthv2_val_list_videos.txt' file_client_args = dict( io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})) sthv2_flip_label_map = dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 }) train_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='MultiScaleCrop', input_size=224, scales=(1, 0.875, 0.75, 0.66), random_crop=False, max_wh_scale_gap=1, num_fixed_crops=13), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict( type='Flip', flip_ratio=0.5, flip_label_map=dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 })), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] val_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] test_pipeline = [ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16, twice_sample=True, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='TenCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_train_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict( type='MultiScaleCrop', input_size=224, scales=(1, 0.875, 0.75, 0.66), random_crop=False, max_wh_scale_gap=1, num_fixed_crops=13), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict( type='Flip', flip_ratio=0.5, flip_label_map=dict({ 86: 87, 87: 86, 93: 94, 94: 93, 166: 167, 167: 166 })), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ])) val_dataloader = dict( batch_size=16, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_val_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ], test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=8, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='VideoDataset', ann_file='data/sthv2/sthv2_val_list_videos.txt', data_prefix=dict(video='data/sthv2/videos'), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict({ 'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2' })), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True, twice_sample=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='TenCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ], test_mode=True), pipeline=[ dict( type='DecordInit', io_backend='petrel', path_mapping=dict( {'data/sthv2': 's254:s3://openmmlab/datasets/action/sthv2'})), dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16, twice_sample=True, test_mode=True), dict(type='DecordDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='TenCrop', crop_size=224), dict(type='FormatShape', input_format='NCHW'), dict(type='PackActionInputs') ], test_mode=True) val_evaluator = dict(type='AccMetric') test_evaluator = dict(type='AccMetric') train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict(type='LinearLR', start_factor=0.1, by_epoch=True, begin=0, end=5), dict( type='MultiStepLR', begin=0, end=50, by_epoch=True, milestones=[25, 45], gamma=0.1) ] optim_wrapper = dict( constructor='TSMOptimWrapperConstructor', paramwise_cfg=dict(fc_lr5=True), optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0005), clip_grad=dict(max_norm=20, norm_type=2)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = 'work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2023/02/17 12:07:25 - mmengine - INFO - These parameters in pretrained checkpoint are not loaded: {'fc.weight', 'fc.bias'} 2023/02/17 12:07:25 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.conv1.conv.weight - torch.Size([64, 3, 7, 7]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.conv.net.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.0.downsample.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.conv.net.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.1.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.conv.net.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.conv.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer1.2.conv3.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.conv.net.weight - torch.Size([128, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.0.downsample.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.1.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.2.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.conv.net.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.conv.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.conv.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer2.3.conv3.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.conv.net.weight - torch.Size([256, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.conv.weight - torch.Size([1024, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.0.downsample.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.1.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.2.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.3.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.4.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.conv.net.weight - torch.Size([256, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer3.5.conv3.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.conv.net.weight - torch.Size([512, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.conv.weight - torch.Size([2048, 1024, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.0.downsample.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.conv.net.weight - torch.Size([512, 2048, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.1.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.conv.net.weight - torch.Size([512, 2048, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.conv.weight - torch.Size([512, 512, 3, 3]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.bn.weight - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D backbone.layer4.2.conv3.bn.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of Recognizer2D cls_head.fc_cls.weight - torch.Size([174, 2048]): Initialized by user-defined `init_weights` in TSMHead cls_head.fc_cls.bias - torch.Size([174]): Initialized by user-defined `init_weights` in TSMHead 2023/02/17 12:07:27 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb. 2023/02/17 12:08:19 - mmengine - INFO - Epoch(train) [1][ 20/1320] lr: 2.0000e-03 eta: 1 day, 23:08:07 time: 2.5718 data_time: 2.0257 memory: 27031 grad_norm: 2.3701 loss: 5.0730 top1_acc: 0.0000 top5_acc: 0.0625 loss_cls: 5.0730 2023/02/17 12:08:28 - mmengine - INFO - Epoch(train) [1][ 40/1320] lr: 2.0000e-03 eta: 1 day, 3:56:38 time: 0.4785 data_time: 0.0135 memory: 27031 grad_norm: 2.4049 loss: 5.0290 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 5.0290 2023/02/17 12:08:38 - mmengine - INFO - Epoch(train) [1][ 60/1320] lr: 2.0000e-03 eta: 21:33:01 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 2.3866 loss: 4.9963 top1_acc: 0.1875 top5_acc: 0.1875 loss_cls: 4.9963 2023/02/17 12:08:47 - mmengine - INFO - Epoch(train) [1][ 80/1320] lr: 2.0000e-03 eta: 18:20:56 time: 0.4786 data_time: 0.0154 memory: 27031 grad_norm: 2.4992 loss: 4.8305 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.8305 2023/02/17 12:08:57 - mmengine - INFO - Epoch(train) [1][ 100/1320] lr: 2.0000e-03 eta: 16:25:20 time: 0.4773 data_time: 0.0144 memory: 27031 grad_norm: 2.6327 loss: 4.8020 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.8020 2023/02/17 12:09:07 - mmengine - INFO - Epoch(train) [1][ 120/1320] lr: 2.0000e-03 eta: 15:08:11 time: 0.4772 data_time: 0.0139 memory: 27031 grad_norm: 2.6583 loss: 4.7573 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.7573 2023/02/17 12:09:16 - mmengine - INFO - Epoch(train) [1][ 140/1320] lr: 2.0000e-03 eta: 14:13:05 time: 0.4775 data_time: 0.0143 memory: 27031 grad_norm: 2.7799 loss: 4.7763 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 4.7763 2023/02/17 12:09:26 - mmengine - INFO - Epoch(train) [1][ 160/1320] lr: 2.0000e-03 eta: 13:31:46 time: 0.4778 data_time: 0.0148 memory: 27031 grad_norm: 2.8824 loss: 4.7037 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.7037 2023/02/17 12:09:35 - mmengine - INFO - Epoch(train) [1][ 180/1320] lr: 2.0000e-03 eta: 12:59:34 time: 0.4776 data_time: 0.0146 memory: 27031 grad_norm: 2.9521 loss: 4.6401 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.6401 2023/02/17 12:09:45 - mmengine - INFO - Epoch(train) [1][ 200/1320] lr: 2.0000e-03 eta: 12:33:44 time: 0.4772 data_time: 0.0144 memory: 27031 grad_norm: 2.9413 loss: 4.6610 top1_acc: 0.0000 top5_acc: 0.2500 loss_cls: 4.6610 2023/02/17 12:09:54 - mmengine - INFO - Epoch(train) [1][ 220/1320] lr: 2.0000e-03 eta: 12:12:50 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 3.0491 loss: 4.4037 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 4.4037 2023/02/17 12:10:04 - mmengine - INFO - Epoch(train) [1][ 240/1320] lr: 2.0000e-03 eta: 11:55:13 time: 0.4780 data_time: 0.0140 memory: 27031 grad_norm: 3.1929 loss: 4.3779 top1_acc: 0.0000 top5_acc: 0.0625 loss_cls: 4.3779 2023/02/17 12:10:13 - mmengine - INFO - Epoch(train) [1][ 260/1320] lr: 2.0000e-03 eta: 11:40:21 time: 0.4789 data_time: 0.0145 memory: 27031 grad_norm: 3.2554 loss: 4.5858 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 4.5858 2023/02/17 12:10:23 - mmengine - INFO - Epoch(train) [1][ 280/1320] lr: 2.0000e-03 eta: 11:27:31 time: 0.4778 data_time: 0.0146 memory: 27031 grad_norm: 3.3099 loss: 4.4260 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.4260 2023/02/17 12:10:33 - mmengine - INFO - Epoch(train) [1][ 300/1320] lr: 2.0000e-03 eta: 11:16:24 time: 0.4783 data_time: 0.0148 memory: 27031 grad_norm: 3.3482 loss: 4.3744 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 4.3744 2023/02/17 12:10:42 - mmengine - INFO - Epoch(train) [1][ 320/1320] lr: 2.0000e-03 eta: 11:06:47 time: 0.4802 data_time: 0.0138 memory: 27031 grad_norm: 3.4382 loss: 4.5218 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.5218 2023/02/17 12:10:52 - mmengine - INFO - Epoch(train) [1][ 340/1320] lr: 2.0000e-03 eta: 10:58:09 time: 0.4781 data_time: 0.0143 memory: 27031 grad_norm: 3.4903 loss: 4.3752 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 4.3752 2023/02/17 12:11:01 - mmengine - INFO - Epoch(train) [1][ 360/1320] lr: 2.0000e-03 eta: 10:50:34 time: 0.4798 data_time: 0.0157 memory: 27031 grad_norm: 3.5491 loss: 4.3329 top1_acc: 0.0000 top5_acc: 0.0625 loss_cls: 4.3329 2023/02/17 12:11:11 - mmengine - INFO - Epoch(train) [1][ 380/1320] lr: 2.0000e-03 eta: 10:43:39 time: 0.4779 data_time: 0.0146 memory: 27031 grad_norm: 3.5125 loss: 4.1659 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 4.1659 2023/02/17 12:11:20 - mmengine - INFO - Epoch(train) [1][ 400/1320] lr: 2.0000e-03 eta: 10:37:25 time: 0.4781 data_time: 0.0151 memory: 27031 grad_norm: 3.6628 loss: 4.2721 top1_acc: 0.0000 top5_acc: 0.1875 loss_cls: 4.2721 2023/02/17 12:11:30 - mmengine - INFO - Epoch(train) [1][ 420/1320] lr: 2.0000e-03 eta: 10:31:46 time: 0.4783 data_time: 0.0150 memory: 27031 grad_norm: 3.7185 loss: 4.3157 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 4.3157 2023/02/17 12:11:40 - mmengine - INFO - Epoch(train) [1][ 440/1320] lr: 2.0000e-03 eta: 10:26:38 time: 0.4787 data_time: 0.0148 memory: 27031 grad_norm: 3.7815 loss: 4.2219 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 4.2219 2023/02/17 12:11:49 - mmengine - INFO - Epoch(train) [1][ 460/1320] lr: 2.0000e-03 eta: 10:21:54 time: 0.4777 data_time: 0.0144 memory: 27031 grad_norm: 3.7675 loss: 4.2777 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.2777 2023/02/17 12:11:59 - mmengine - INFO - Epoch(train) [1][ 480/1320] lr: 2.0000e-03 eta: 10:17:36 time: 0.4789 data_time: 0.0156 memory: 27031 grad_norm: 3.7871 loss: 4.2967 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 4.2967 2023/02/17 12:12:08 - mmengine - INFO - Epoch(train) [1][ 500/1320] lr: 2.0000e-03 eta: 10:13:35 time: 0.4782 data_time: 0.0149 memory: 27031 grad_norm: 3.8685 loss: 4.1092 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 4.1092 2023/02/17 12:12:18 - mmengine - INFO - Epoch(train) [1][ 520/1320] lr: 2.0000e-03 eta: 10:10:03 time: 0.4822 data_time: 0.0168 memory: 27031 grad_norm: 3.9039 loss: 4.1392 top1_acc: 0.0000 top5_acc: 0.2500 loss_cls: 4.1392 2023/02/17 12:12:28 - mmengine - INFO - Epoch(train) [1][ 540/1320] lr: 2.0000e-03 eta: 10:06:35 time: 0.4780 data_time: 0.0150 memory: 27031 grad_norm: 3.9610 loss: 4.0650 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 4.0650 2023/02/17 12:12:37 - mmengine - INFO - Epoch(train) [1][ 560/1320] lr: 2.0000e-03 eta: 10:03:22 time: 0.4779 data_time: 0.0147 memory: 27031 grad_norm: 3.9962 loss: 4.0747 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 4.0747 2023/02/17 12:12:47 - mmengine - INFO - Epoch(train) [1][ 580/1320] lr: 2.0000e-03 eta: 10:00:23 time: 0.4789 data_time: 0.0153 memory: 27031 grad_norm: 4.1190 loss: 4.0432 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 4.0432 2023/02/17 12:12:56 - mmengine - INFO - Epoch(train) [1][ 600/1320] lr: 2.0000e-03 eta: 9:57:35 time: 0.4785 data_time: 0.0148 memory: 27031 grad_norm: 4.1314 loss: 4.1915 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 4.1915 2023/02/17 12:13:06 - mmengine - INFO - Epoch(train) [1][ 620/1320] lr: 2.0000e-03 eta: 9:54:57 time: 0.4784 data_time: 0.0148 memory: 27031 grad_norm: 4.1186 loss: 4.1454 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 4.1454 2023/02/17 12:13:15 - mmengine - INFO - Epoch(train) [1][ 640/1320] lr: 2.0000e-03 eta: 9:52:30 time: 0.4796 data_time: 0.0131 memory: 27031 grad_norm: 4.2426 loss: 4.0443 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 4.0443 2023/02/17 12:13:25 - mmengine - INFO - Epoch(train) [1][ 660/1320] lr: 2.0000e-03 eta: 9:50:09 time: 0.4782 data_time: 0.0134 memory: 27031 grad_norm: 4.1980 loss: 4.0257 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 4.0257 2023/02/17 12:13:34 - mmengine - INFO - Epoch(train) [1][ 680/1320] lr: 2.0000e-03 eta: 9:47:52 time: 0.4765 data_time: 0.0127 memory: 27031 grad_norm: 4.3372 loss: 3.9166 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.9166 2023/02/17 12:13:44 - mmengine - INFO - Epoch(train) [1][ 700/1320] lr: 2.0000e-03 eta: 9:45:45 time: 0.4775 data_time: 0.0126 memory: 27031 grad_norm: 4.3185 loss: 3.9759 top1_acc: 0.0625 top5_acc: 0.5625 loss_cls: 3.9759 2023/02/17 12:13:54 - mmengine - INFO - Epoch(train) [1][ 720/1320] lr: 2.0000e-03 eta: 9:43:44 time: 0.4773 data_time: 0.0138 memory: 27031 grad_norm: 4.3637 loss: 3.8326 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.8326 2023/02/17 12:14:03 - mmengine - INFO - Epoch(train) [1][ 740/1320] lr: 2.0000e-03 eta: 9:41:54 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 4.4084 loss: 3.9978 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 3.9978 2023/02/17 12:14:13 - mmengine - INFO - Epoch(train) [1][ 760/1320] lr: 2.0000e-03 eta: 9:40:05 time: 0.4780 data_time: 0.0144 memory: 27031 grad_norm: 4.4392 loss: 3.9159 top1_acc: 0.1250 top5_acc: 0.6250 loss_cls: 3.9159 2023/02/17 12:14:22 - mmengine - INFO - Epoch(train) [1][ 780/1320] lr: 2.0000e-03 eta: 9:38:23 time: 0.4785 data_time: 0.0135 memory: 27031 grad_norm: 4.4438 loss: 3.8422 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 3.8422 2023/02/17 12:14:32 - mmengine - INFO - Epoch(train) [1][ 800/1320] lr: 2.0000e-03 eta: 9:36:46 time: 0.4792 data_time: 0.0126 memory: 27031 grad_norm: 4.5846 loss: 3.8520 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 3.8520 2023/02/17 12:14:42 - mmengine - INFO - Epoch(train) [1][ 820/1320] lr: 2.0000e-03 eta: 9:35:16 time: 0.4809 data_time: 0.0140 memory: 27031 grad_norm: 4.6672 loss: 3.8795 top1_acc: 0.3750 top5_acc: 0.4375 loss_cls: 3.8795 2023/02/17 12:14:51 - mmengine - INFO - Epoch(train) [1][ 840/1320] lr: 2.0000e-03 eta: 9:33:47 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.6062 loss: 3.8130 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 3.8130 2023/02/17 12:15:01 - mmengine - INFO - Epoch(train) [1][ 860/1320] lr: 2.0000e-03 eta: 9:32:21 time: 0.4787 data_time: 0.0135 memory: 27031 grad_norm: 4.6077 loss: 3.7752 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 3.7752 2023/02/17 12:15:10 - mmengine - INFO - Epoch(train) [1][ 880/1320] lr: 2.0000e-03 eta: 9:31:01 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.6870 loss: 3.7982 top1_acc: 0.1875 top5_acc: 0.2500 loss_cls: 3.7982 2023/02/17 12:15:20 - mmengine - INFO - Epoch(train) [1][ 900/1320] lr: 2.0000e-03 eta: 9:29:42 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.6213 loss: 3.7868 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 3.7868 2023/02/17 12:15:29 - mmengine - INFO - Epoch(train) [1][ 920/1320] lr: 2.0000e-03 eta: 9:28:27 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.6519 loss: 3.6982 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 3.6982 2023/02/17 12:15:39 - mmengine - INFO - Epoch(train) [1][ 940/1320] lr: 2.0000e-03 eta: 9:27:13 time: 0.4783 data_time: 0.0145 memory: 27031 grad_norm: 4.8392 loss: 3.7227 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.7227 2023/02/17 12:15:49 - mmengine - INFO - Epoch(train) [1][ 960/1320] lr: 2.0000e-03 eta: 9:26:02 time: 0.4786 data_time: 0.0137 memory: 27031 grad_norm: 4.8579 loss: 3.7384 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.7384 2023/02/17 12:15:58 - mmengine - INFO - Epoch(train) [1][ 980/1320] lr: 2.0000e-03 eta: 9:24:58 time: 0.4816 data_time: 0.0171 memory: 27031 grad_norm: 4.8625 loss: 3.7513 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.7513 2023/02/17 12:16:08 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:16:08 - mmengine - INFO - Epoch(train) [1][1000/1320] lr: 2.0000e-03 eta: 9:23:52 time: 0.4785 data_time: 0.0146 memory: 27031 grad_norm: 4.8993 loss: 3.7428 top1_acc: 0.1250 top5_acc: 0.1875 loss_cls: 3.7428 2023/02/17 12:16:17 - mmengine - INFO - Epoch(train) [1][1020/1320] lr: 2.0000e-03 eta: 9:22:50 time: 0.4802 data_time: 0.0137 memory: 27031 grad_norm: 4.8413 loss: 3.6941 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.6941 2023/02/17 12:16:27 - mmengine - INFO - Epoch(train) [1][1040/1320] lr: 2.0000e-03 eta: 9:21:52 time: 0.4814 data_time: 0.0162 memory: 27031 grad_norm: 4.9050 loss: 3.7511 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.7511 2023/02/17 12:16:37 - mmengine - INFO - Epoch(train) [1][1060/1320] lr: 2.0000e-03 eta: 9:20:53 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.9213 loss: 3.7063 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.7063 2023/02/17 12:16:46 - mmengine - INFO - Epoch(train) [1][1080/1320] lr: 2.0000e-03 eta: 9:19:57 time: 0.4798 data_time: 0.0151 memory: 27031 grad_norm: 4.9462 loss: 3.6841 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.6841 2023/02/17 12:16:56 - mmengine - INFO - Epoch(train) [1][1100/1320] lr: 2.0000e-03 eta: 9:19:01 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.9020 loss: 3.7340 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.7340 2023/02/17 12:17:05 - mmengine - INFO - Epoch(train) [1][1120/1320] lr: 2.0000e-03 eta: 9:18:08 time: 0.4797 data_time: 0.0133 memory: 27031 grad_norm: 4.9584 loss: 3.8077 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.8077 2023/02/17 12:17:15 - mmengine - INFO - Epoch(train) [1][1140/1320] lr: 2.0000e-03 eta: 9:17:15 time: 0.4783 data_time: 0.0146 memory: 27031 grad_norm: 5.0302 loss: 3.7053 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 3.7053 2023/02/17 12:17:24 - mmengine - INFO - Epoch(train) [1][1160/1320] lr: 2.0000e-03 eta: 9:16:22 time: 0.4779 data_time: 0.0136 memory: 27031 grad_norm: 5.0907 loss: 3.6536 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.6536 2023/02/17 12:17:34 - mmengine - INFO - Epoch(train) [1][1180/1320] lr: 2.0000e-03 eta: 9:15:31 time: 0.4778 data_time: 0.0145 memory: 27031 grad_norm: 5.1130 loss: 3.5373 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.5373 2023/02/17 12:17:44 - mmengine - INFO - Epoch(train) [1][1200/1320] lr: 2.0000e-03 eta: 9:14:43 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 5.1055 loss: 3.5906 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.5906 2023/02/17 12:17:53 - mmengine - INFO - Epoch(train) [1][1220/1320] lr: 2.0000e-03 eta: 9:13:56 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 5.0711 loss: 3.5884 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.5884 2023/02/17 12:18:03 - mmengine - INFO - Epoch(train) [1][1240/1320] lr: 2.0000e-03 eta: 9:13:14 time: 0.4822 data_time: 0.0149 memory: 27031 grad_norm: 5.1096 loss: 3.5572 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.5572 2023/02/17 12:18:12 - mmengine - INFO - Epoch(train) [1][1260/1320] lr: 2.0000e-03 eta: 9:12:29 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 5.2355 loss: 3.4503 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.4503 2023/02/17 12:18:22 - mmengine - INFO - Epoch(train) [1][1280/1320] lr: 2.0000e-03 eta: 9:11:46 time: 0.4794 data_time: 0.0132 memory: 27031 grad_norm: 5.3587 loss: 3.4109 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.4109 2023/02/17 12:18:32 - mmengine - INFO - Epoch(train) [1][1300/1320] lr: 2.0000e-03 eta: 9:11:04 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 5.2025 loss: 3.7177 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 3.7177 2023/02/17 12:18:41 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:18:41 - mmengine - INFO - Epoch(train) [1][1320/1320] lr: 2.0000e-03 eta: 9:10:17 time: 0.4730 data_time: 0.0151 memory: 27031 grad_norm: 5.3096 loss: 3.5126 top1_acc: 0.0000 top5_acc: 0.3636 loss_cls: 3.5126 2023/02/17 12:19:35 - mmengine - INFO - Epoch(val) [1][ 20/194] eta: 0:07:47 time: 2.6854 data_time: 2.5600 memory: 3265 2023/02/17 12:19:38 - mmengine - INFO - Epoch(val) [1][ 40/194] eta: 0:03:37 time: 0.1347 data_time: 0.0122 memory: 3265 2023/02/17 12:19:44 - mmengine - INFO - Epoch(val) [1][ 60/194] eta: 0:02:20 time: 0.3172 data_time: 0.1949 memory: 3265 2023/02/17 12:19:47 - mmengine - INFO - Epoch(val) [1][ 80/194] eta: 0:01:33 time: 0.1358 data_time: 0.0123 memory: 3265 2023/02/17 12:19:49 - mmengine - INFO - Epoch(val) [1][100/194] eta: 0:01:04 time: 0.1357 data_time: 0.0130 memory: 3265 2023/02/17 12:19:56 - mmengine - INFO - Epoch(val) [1][120/194] eta: 0:00:45 time: 0.3175 data_time: 0.1938 memory: 3265 2023/02/17 12:19:58 - mmengine - INFO - Epoch(val) [1][140/194] eta: 0:00:29 time: 0.1316 data_time: 0.0105 memory: 3265 2023/02/17 12:20:01 - mmengine - INFO - Epoch(val) [1][160/194] eta: 0:00:16 time: 0.1310 data_time: 0.0103 memory: 3265 2023/02/17 12:20:04 - mmengine - INFO - Epoch(val) [1][180/194] eta: 0:00:06 time: 0.1314 data_time: 0.0105 memory: 3265 2023/02/17 12:20:06 - mmengine - INFO - Epoch(val) [1][194/194] acc/top1: 0.1858 acc/top5: 0.4457 acc/mean1: 0.1279 2023/02/17 12:20:07 - mmengine - INFO - The best checkpoint with 0.1858 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2023/02/17 12:20:17 - mmengine - INFO - Epoch(train) [2][ 20/1320] lr: 6.5000e-03 eta: 9:10:18 time: 0.5227 data_time: 0.0513 memory: 27031 grad_norm: 5.7074 loss: 3.6038 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.6038 2023/02/17 12:20:27 - mmengine - INFO - Epoch(train) [2][ 40/1320] lr: 6.5000e-03 eta: 9:09:39 time: 0.4806 data_time: 0.0158 memory: 27031 grad_norm: 5.6761 loss: 3.7666 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.7666 2023/02/17 12:20:37 - mmengine - INFO - Epoch(train) [2][ 60/1320] lr: 6.5000e-03 eta: 9:08:59 time: 0.4779 data_time: 0.0129 memory: 27031 grad_norm: 5.6230 loss: 3.9037 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.9037 2023/02/17 12:20:46 - mmengine - INFO - Epoch(train) [2][ 80/1320] lr: 6.5000e-03 eta: 9:08:22 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 5.4733 loss: 3.8013 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.8013 2023/02/17 12:20:56 - mmengine - INFO - Epoch(train) [2][ 100/1320] lr: 6.5000e-03 eta: 9:07:44 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 5.3971 loss: 3.7344 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.7344 2023/02/17 12:21:05 - mmengine - INFO - Epoch(train) [2][ 120/1320] lr: 6.5000e-03 eta: 9:07:07 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 5.4087 loss: 3.7672 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.7672 2023/02/17 12:21:15 - mmengine - INFO - Epoch(train) [2][ 140/1320] lr: 6.5000e-03 eta: 9:06:32 time: 0.4795 data_time: 0.0149 memory: 27031 grad_norm: 5.4367 loss: 3.7289 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.7289 2023/02/17 12:21:25 - mmengine - INFO - Epoch(train) [2][ 160/1320] lr: 6.5000e-03 eta: 9:05:56 time: 0.4784 data_time: 0.0145 memory: 27031 grad_norm: 5.3878 loss: 3.6248 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.6248 2023/02/17 12:21:34 - mmengine - INFO - Epoch(train) [2][ 180/1320] lr: 6.5000e-03 eta: 9:05:20 time: 0.4782 data_time: 0.0139 memory: 27031 grad_norm: 5.4102 loss: 3.7106 top1_acc: 0.0000 top5_acc: 0.3750 loss_cls: 3.7106 2023/02/17 12:21:44 - mmengine - INFO - Epoch(train) [2][ 200/1320] lr: 6.5000e-03 eta: 9:04:46 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 5.3203 loss: 3.5946 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 3.5946 2023/02/17 12:21:53 - mmengine - INFO - Epoch(train) [2][ 220/1320] lr: 6.5000e-03 eta: 9:04:11 time: 0.4781 data_time: 0.0144 memory: 27031 grad_norm: 5.4133 loss: 3.6907 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.6907 2023/02/17 12:22:03 - mmengine - INFO - Epoch(train) [2][ 240/1320] lr: 6.5000e-03 eta: 9:03:38 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 5.4349 loss: 3.6688 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.6688 2023/02/17 12:22:12 - mmengine - INFO - Epoch(train) [2][ 260/1320] lr: 6.5000e-03 eta: 9:03:06 time: 0.4785 data_time: 0.0148 memory: 27031 grad_norm: 5.5248 loss: 3.5660 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 3.5660 2023/02/17 12:22:22 - mmengine - INFO - Epoch(train) [2][ 280/1320] lr: 6.5000e-03 eta: 9:02:33 time: 0.4776 data_time: 0.0136 memory: 27031 grad_norm: 5.3319 loss: 3.4881 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 3.4881 2023/02/17 12:22:32 - mmengine - INFO - Epoch(train) [2][ 300/1320] lr: 6.5000e-03 eta: 9:02:02 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 5.3961 loss: 3.6221 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.6221 2023/02/17 12:22:41 - mmengine - INFO - Epoch(train) [2][ 320/1320] lr: 6.5000e-03 eta: 9:01:32 time: 0.4792 data_time: 0.0148 memory: 27031 grad_norm: 5.4099 loss: 3.4198 top1_acc: 0.0625 top5_acc: 0.5000 loss_cls: 3.4198 2023/02/17 12:22:51 - mmengine - INFO - Epoch(train) [2][ 340/1320] lr: 6.5000e-03 eta: 9:01:02 time: 0.4790 data_time: 0.0140 memory: 27031 grad_norm: 5.4410 loss: 3.5518 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.5518 2023/02/17 12:23:00 - mmengine - INFO - Epoch(train) [2][ 360/1320] lr: 6.5000e-03 eta: 9:00:33 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 5.4565 loss: 3.4692 top1_acc: 0.0625 top5_acc: 0.5000 loss_cls: 3.4692 2023/02/17 12:23:10 - mmengine - INFO - Epoch(train) [2][ 380/1320] lr: 6.5000e-03 eta: 9:00:03 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 5.3130 loss: 3.2997 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 3.2997 2023/02/17 12:23:19 - mmengine - INFO - Epoch(train) [2][ 400/1320] lr: 6.5000e-03 eta: 8:59:34 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 5.4310 loss: 3.2900 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 3.2900 2023/02/17 12:23:29 - mmengine - INFO - Epoch(train) [2][ 420/1320] lr: 6.5000e-03 eta: 8:59:06 time: 0.4787 data_time: 0.0147 memory: 27031 grad_norm: 5.4530 loss: 3.4529 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.4529 2023/02/17 12:23:39 - mmengine - INFO - Epoch(train) [2][ 440/1320] lr: 6.5000e-03 eta: 8:58:37 time: 0.4779 data_time: 0.0143 memory: 27031 grad_norm: 5.4074 loss: 3.4934 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.4934 2023/02/17 12:23:48 - mmengine - INFO - Epoch(train) [2][ 460/1320] lr: 6.5000e-03 eta: 8:58:10 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 5.5624 loss: 3.1867 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.1867 2023/02/17 12:23:58 - mmengine - INFO - Epoch(train) [2][ 480/1320] lr: 6.5000e-03 eta: 8:57:44 time: 0.4807 data_time: 0.0161 memory: 27031 grad_norm: 5.4780 loss: 3.3095 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.3095 2023/02/17 12:24:07 - mmengine - INFO - Epoch(train) [2][ 500/1320] lr: 6.5000e-03 eta: 8:57:17 time: 0.4785 data_time: 0.0130 memory: 27031 grad_norm: 5.5756 loss: 3.4873 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 3.4873 2023/02/17 12:24:17 - mmengine - INFO - Epoch(train) [2][ 520/1320] lr: 6.5000e-03 eta: 8:56:52 time: 0.4800 data_time: 0.0156 memory: 27031 grad_norm: 5.5434 loss: 3.6019 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.6019 2023/02/17 12:24:27 - mmengine - INFO - Epoch(train) [2][ 540/1320] lr: 6.5000e-03 eta: 8:56:25 time: 0.4780 data_time: 0.0137 memory: 27031 grad_norm: 5.4759 loss: 3.2710 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.2710 2023/02/17 12:24:36 - mmengine - INFO - Epoch(train) [2][ 560/1320] lr: 6.5000e-03 eta: 8:55:59 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 5.3277 loss: 3.4340 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.4340 2023/02/17 12:24:46 - mmengine - INFO - Epoch(train) [2][ 580/1320] lr: 6.5000e-03 eta: 8:55:34 time: 0.4785 data_time: 0.0148 memory: 27031 grad_norm: 5.5844 loss: 3.5513 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 3.5513 2023/02/17 12:24:55 - mmengine - INFO - Epoch(train) [2][ 600/1320] lr: 6.5000e-03 eta: 8:55:08 time: 0.4778 data_time: 0.0139 memory: 27031 grad_norm: 5.4713 loss: 3.3052 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 3.3052 2023/02/17 12:25:05 - mmengine - INFO - Epoch(train) [2][ 620/1320] lr: 6.5000e-03 eta: 8:54:44 time: 0.4797 data_time: 0.0153 memory: 27031 grad_norm: 5.4037 loss: 3.3187 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 3.3187 2023/02/17 12:25:14 - mmengine - INFO - Epoch(train) [2][ 640/1320] lr: 6.5000e-03 eta: 8:54:19 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 5.5265 loss: 3.3921 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.3921 2023/02/17 12:25:24 - mmengine - INFO - Epoch(train) [2][ 660/1320] lr: 6.5000e-03 eta: 8:53:56 time: 0.4791 data_time: 0.0143 memory: 27031 grad_norm: 5.6639 loss: 3.4035 top1_acc: 0.1875 top5_acc: 0.2500 loss_cls: 3.4035 2023/02/17 12:25:34 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:25:34 - mmengine - INFO - Epoch(train) [2][ 680/1320] lr: 6.5000e-03 eta: 8:53:32 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 5.4887 loss: 3.2997 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.2997 2023/02/17 12:25:43 - mmengine - INFO - Epoch(train) [2][ 700/1320] lr: 6.5000e-03 eta: 8:53:09 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 5.4260 loss: 3.2000 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 3.2000 2023/02/17 12:25:53 - mmengine - INFO - Epoch(train) [2][ 720/1320] lr: 6.5000e-03 eta: 8:52:45 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 5.5864 loss: 3.1990 top1_acc: 0.1875 top5_acc: 0.3125 loss_cls: 3.1990 2023/02/17 12:26:02 - mmengine - INFO - Epoch(train) [2][ 740/1320] lr: 6.5000e-03 eta: 8:52:23 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 5.4634 loss: 3.0914 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.0914 2023/02/17 12:26:12 - mmengine - INFO - Epoch(train) [2][ 760/1320] lr: 6.5000e-03 eta: 8:52:00 time: 0.4781 data_time: 0.0148 memory: 27031 grad_norm: 5.5072 loss: 3.1521 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.1521 2023/02/17 12:26:22 - mmengine - INFO - Epoch(train) [2][ 780/1320] lr: 6.5000e-03 eta: 8:51:39 time: 0.4811 data_time: 0.0162 memory: 27031 grad_norm: 5.5683 loss: 3.1226 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 3.1226 2023/02/17 12:26:31 - mmengine - INFO - Epoch(train) [2][ 800/1320] lr: 6.5000e-03 eta: 8:51:16 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 5.5191 loss: 3.2187 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.2187 2023/02/17 12:26:41 - mmengine - INFO - Epoch(train) [2][ 820/1320] lr: 6.5000e-03 eta: 8:50:55 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 5.4704 loss: 3.1700 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 3.1700 2023/02/17 12:26:50 - mmengine - INFO - Epoch(train) [2][ 840/1320] lr: 6.5000e-03 eta: 8:50:33 time: 0.4798 data_time: 0.0153 memory: 27031 grad_norm: 5.5718 loss: 3.2650 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.2650 2023/02/17 12:27:00 - mmengine - INFO - Epoch(train) [2][ 860/1320] lr: 6.5000e-03 eta: 8:50:13 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 5.4768 loss: 3.0124 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 3.0124 2023/02/17 12:27:09 - mmengine - INFO - Epoch(train) [2][ 880/1320] lr: 6.5000e-03 eta: 8:49:52 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 5.6341 loss: 2.8253 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.8253 2023/02/17 12:27:19 - mmengine - INFO - Epoch(train) [2][ 900/1320] lr: 6.5000e-03 eta: 8:49:31 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 5.5244 loss: 3.2388 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.2388 2023/02/17 12:27:29 - mmengine - INFO - Epoch(train) [2][ 920/1320] lr: 6.5000e-03 eta: 8:49:10 time: 0.4780 data_time: 0.0144 memory: 27031 grad_norm: 5.6514 loss: 2.9217 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.9217 2023/02/17 12:27:38 - mmengine - INFO - Epoch(train) [2][ 940/1320] lr: 6.5000e-03 eta: 8:48:50 time: 0.4796 data_time: 0.0149 memory: 27031 grad_norm: 5.3833 loss: 3.0264 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 3.0264 2023/02/17 12:27:48 - mmengine - INFO - Epoch(train) [2][ 960/1320] lr: 6.5000e-03 eta: 8:48:30 time: 0.4800 data_time: 0.0155 memory: 27031 grad_norm: 5.5160 loss: 3.1626 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 3.1626 2023/02/17 12:27:57 - mmengine - INFO - Epoch(train) [2][ 980/1320] lr: 6.5000e-03 eta: 8:48:09 time: 0.4781 data_time: 0.0135 memory: 27031 grad_norm: 5.5290 loss: 3.0166 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.0166 2023/02/17 12:28:07 - mmengine - INFO - Epoch(train) [2][1000/1320] lr: 6.5000e-03 eta: 8:47:49 time: 0.4796 data_time: 0.0148 memory: 27031 grad_norm: 5.7285 loss: 3.2151 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 3.2151 2023/02/17 12:28:17 - mmengine - INFO - Epoch(train) [2][1020/1320] lr: 6.5000e-03 eta: 8:47:30 time: 0.4796 data_time: 0.0157 memory: 27031 grad_norm: 5.5815 loss: 3.0520 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 3.0520 2023/02/17 12:28:26 - mmengine - INFO - Epoch(train) [2][1040/1320] lr: 6.5000e-03 eta: 8:47:10 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 5.5802 loss: 2.9771 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.9771 2023/02/17 12:28:36 - mmengine - INFO - Epoch(train) [2][1060/1320] lr: 6.5000e-03 eta: 8:46:51 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 5.5990 loss: 3.0173 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 3.0173 2023/02/17 12:28:45 - mmengine - INFO - Epoch(train) [2][1080/1320] lr: 6.5000e-03 eta: 8:46:31 time: 0.4786 data_time: 0.0145 memory: 27031 grad_norm: 5.5534 loss: 2.8878 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.8878 2023/02/17 12:28:55 - mmengine - INFO - Epoch(train) [2][1100/1320] lr: 6.5000e-03 eta: 8:46:12 time: 0.4801 data_time: 0.0150 memory: 27031 grad_norm: 5.5788 loss: 3.0022 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 3.0022 2023/02/17 12:29:05 - mmengine - INFO - Epoch(train) [2][1120/1320] lr: 6.5000e-03 eta: 8:45:54 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 5.6750 loss: 3.2064 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.2064 2023/02/17 12:29:14 - mmengine - INFO - Epoch(train) [2][1140/1320] lr: 6.5000e-03 eta: 8:45:34 time: 0.4778 data_time: 0.0145 memory: 27031 grad_norm: 5.6152 loss: 2.9941 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.9941 2023/02/17 12:29:24 - mmengine - INFO - Epoch(train) [2][1160/1320] lr: 6.5000e-03 eta: 8:45:16 time: 0.4798 data_time: 0.0156 memory: 27031 grad_norm: 5.5540 loss: 3.0228 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.0228 2023/02/17 12:29:33 - mmengine - INFO - Epoch(train) [2][1180/1320] lr: 6.5000e-03 eta: 8:44:58 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 5.6270 loss: 2.8775 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.8775 2023/02/17 12:29:43 - mmengine - INFO - Epoch(train) [2][1200/1320] lr: 6.5000e-03 eta: 8:44:40 time: 0.4806 data_time: 0.0155 memory: 27031 grad_norm: 5.7791 loss: 2.9571 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.9571 2023/02/17 12:29:53 - mmengine - INFO - Epoch(train) [2][1220/1320] lr: 6.5000e-03 eta: 8:44:22 time: 0.4798 data_time: 0.0157 memory: 27031 grad_norm: 5.6298 loss: 2.8327 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.8327 2023/02/17 12:30:02 - mmengine - INFO - Epoch(train) [2][1240/1320] lr: 6.5000e-03 eta: 8:44:04 time: 0.4797 data_time: 0.0149 memory: 27031 grad_norm: 5.6820 loss: 3.0552 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.0552 2023/02/17 12:30:12 - mmengine - INFO - Epoch(train) [2][1260/1320] lr: 6.5000e-03 eta: 8:43:47 time: 0.4814 data_time: 0.0159 memory: 27031 grad_norm: 5.5569 loss: 2.9159 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.9159 2023/02/17 12:30:21 - mmengine - INFO - Epoch(train) [2][1280/1320] lr: 6.5000e-03 eta: 8:43:30 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 5.5782 loss: 2.9359 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.9359 2023/02/17 12:30:31 - mmengine - INFO - Epoch(train) [2][1300/1320] lr: 6.5000e-03 eta: 8:43:12 time: 0.4789 data_time: 0.0149 memory: 27031 grad_norm: 5.6103 loss: 2.8161 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.8161 2023/02/17 12:30:40 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:30:40 - mmengine - INFO - Epoch(train) [2][1320/1320] lr: 6.5000e-03 eta: 8:42:51 time: 0.4725 data_time: 0.0166 memory: 27031 grad_norm: 5.7399 loss: 3.0458 top1_acc: 0.2727 top5_acc: 0.4545 loss_cls: 3.0458 2023/02/17 12:30:44 - mmengine - INFO - Epoch(val) [2][ 20/194] eta: 0:00:31 time: 0.1821 data_time: 0.0569 memory: 3265 2023/02/17 12:30:47 - mmengine - INFO - Epoch(val) [2][ 40/194] eta: 0:00:24 time: 0.1348 data_time: 0.0130 memory: 3265 2023/02/17 12:30:49 - mmengine - INFO - Epoch(val) [2][ 60/194] eta: 0:00:20 time: 0.1334 data_time: 0.0117 memory: 3265 2023/02/17 12:30:52 - mmengine - INFO - Epoch(val) [2][ 80/194] eta: 0:00:16 time: 0.1348 data_time: 0.0117 memory: 3265 2023/02/17 12:30:55 - mmengine - INFO - Epoch(val) [2][100/194] eta: 0:00:13 time: 0.1352 data_time: 0.0126 memory: 3265 2023/02/17 12:30:58 - mmengine - INFO - Epoch(val) [2][120/194] eta: 0:00:10 time: 0.1351 data_time: 0.0121 memory: 3265 2023/02/17 12:31:00 - mmengine - INFO - Epoch(val) [2][140/194] eta: 0:00:07 time: 0.1343 data_time: 0.0122 memory: 3265 2023/02/17 12:31:03 - mmengine - INFO - Epoch(val) [2][160/194] eta: 0:00:04 time: 0.1369 data_time: 0.0129 memory: 3265 2023/02/17 12:31:06 - mmengine - INFO - Epoch(val) [2][180/194] eta: 0:00:01 time: 0.1375 data_time: 0.0139 memory: 3265 2023/02/17 12:31:09 - mmengine - INFO - Epoch(val) [2][194/194] acc/top1: 0.3254 acc/top5: 0.6154 acc/mean1: 0.2441 2023/02/17 12:31:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_1.pth is removed 2023/02/17 12:31:10 - mmengine - INFO - The best checkpoint with 0.3254 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2023/02/17 12:31:20 - mmengine - INFO - Epoch(train) [3][ 20/1320] lr: 1.1000e-02 eta: 8:42:54 time: 0.5225 data_time: 0.0535 memory: 27031 grad_norm: 5.7407 loss: 3.1431 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.1431 2023/02/17 12:31:30 - mmengine - INFO - Epoch(train) [3][ 40/1320] lr: 1.1000e-02 eta: 8:42:37 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 5.8025 loss: 3.0717 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.0717 2023/02/17 12:31:40 - mmengine - INFO - Epoch(train) [3][ 60/1320] lr: 1.1000e-02 eta: 8:42:19 time: 0.4781 data_time: 0.0146 memory: 27031 grad_norm: 5.6465 loss: 3.2588 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.2588 2023/02/17 12:31:49 - mmengine - INFO - Epoch(train) [3][ 80/1320] lr: 1.1000e-02 eta: 8:42:02 time: 0.4788 data_time: 0.0144 memory: 27031 grad_norm: 5.6310 loss: 2.8996 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.8996 2023/02/17 12:31:59 - mmengine - INFO - Epoch(train) [3][ 100/1320] lr: 1.1000e-02 eta: 8:41:45 time: 0.4794 data_time: 0.0155 memory: 27031 grad_norm: 5.5080 loss: 3.1405 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 3.1405 2023/02/17 12:32:08 - mmengine - INFO - Epoch(train) [3][ 120/1320] lr: 1.1000e-02 eta: 8:41:29 time: 0.4815 data_time: 0.0157 memory: 27031 grad_norm: 5.5520 loss: 3.1159 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 3.1159 2023/02/17 12:32:18 - mmengine - INFO - Epoch(train) [3][ 140/1320] lr: 1.1000e-02 eta: 8:41:11 time: 0.4785 data_time: 0.0144 memory: 27031 grad_norm: 5.6194 loss: 3.0865 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 3.0865 2023/02/17 12:32:27 - mmengine - INFO - Epoch(train) [3][ 160/1320] lr: 1.1000e-02 eta: 8:40:54 time: 0.4790 data_time: 0.0147 memory: 27031 grad_norm: 5.4907 loss: 2.8304 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.8304 2023/02/17 12:32:37 - mmengine - INFO - Epoch(train) [3][ 180/1320] lr: 1.1000e-02 eta: 8:40:38 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 5.4411 loss: 2.9944 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.9944 2023/02/17 12:32:47 - mmengine - INFO - Epoch(train) [3][ 200/1320] lr: 1.1000e-02 eta: 8:40:22 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 5.4590 loss: 3.0607 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.0607 2023/02/17 12:32:56 - mmengine - INFO - Epoch(train) [3][ 220/1320] lr: 1.1000e-02 eta: 8:40:05 time: 0.4784 data_time: 0.0142 memory: 27031 grad_norm: 5.4650 loss: 3.1562 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.1562 2023/02/17 12:33:06 - mmengine - INFO - Epoch(train) [3][ 240/1320] lr: 1.1000e-02 eta: 8:39:49 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 5.2720 loss: 2.8825 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8825 2023/02/17 12:33:15 - mmengine - INFO - Epoch(train) [3][ 260/1320] lr: 1.1000e-02 eta: 8:39:33 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 5.3157 loss: 2.9149 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.9149 2023/02/17 12:33:25 - mmengine - INFO - Epoch(train) [3][ 280/1320] lr: 1.1000e-02 eta: 8:39:17 time: 0.4805 data_time: 0.0160 memory: 27031 grad_norm: 5.3777 loss: 3.0462 top1_acc: 0.2500 top5_acc: 0.3750 loss_cls: 3.0462 2023/02/17 12:33:35 - mmengine - INFO - Epoch(train) [3][ 300/1320] lr: 1.1000e-02 eta: 8:39:02 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 5.2177 loss: 3.1448 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.1448 2023/02/17 12:33:44 - mmengine - INFO - Epoch(train) [3][ 320/1320] lr: 1.1000e-02 eta: 8:38:46 time: 0.4810 data_time: 0.0167 memory: 27031 grad_norm: 5.4061 loss: 2.7516 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.7516 2023/02/17 12:33:54 - mmengine - INFO - Epoch(train) [3][ 340/1320] lr: 1.1000e-02 eta: 8:38:31 time: 0.4803 data_time: 0.0153 memory: 27031 grad_norm: 5.3663 loss: 3.1741 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.1741 2023/02/17 12:34:04 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:34:04 - mmengine - INFO - Epoch(train) [3][ 360/1320] lr: 1.1000e-02 eta: 8:38:15 time: 0.4811 data_time: 0.0160 memory: 27031 grad_norm: 5.4156 loss: 2.9968 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.9968 2023/02/17 12:34:13 - mmengine - INFO - Epoch(train) [3][ 380/1320] lr: 1.1000e-02 eta: 8:38:00 time: 0.4796 data_time: 0.0149 memory: 27031 grad_norm: 5.1138 loss: 2.6396 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.6396 2023/02/17 12:34:23 - mmengine - INFO - Epoch(train) [3][ 400/1320] lr: 1.1000e-02 eta: 8:37:44 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 5.3330 loss: 2.7963 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.7963 2023/02/17 12:34:32 - mmengine - INFO - Epoch(train) [3][ 420/1320] lr: 1.1000e-02 eta: 8:37:29 time: 0.4810 data_time: 0.0163 memory: 27031 grad_norm: 5.4022 loss: 2.7836 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.7836 2023/02/17 12:34:42 - mmengine - INFO - Epoch(train) [3][ 440/1320] lr: 1.1000e-02 eta: 8:37:14 time: 0.4794 data_time: 0.0159 memory: 27031 grad_norm: 5.1936 loss: 2.8159 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.8159 2023/02/17 12:34:52 - mmengine - INFO - Epoch(train) [3][ 460/1320] lr: 1.1000e-02 eta: 8:36:59 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 5.2893 loss: 3.1100 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 3.1100 2023/02/17 12:35:01 - mmengine - INFO - Epoch(train) [3][ 480/1320] lr: 1.1000e-02 eta: 8:36:43 time: 0.4800 data_time: 0.0151 memory: 27031 grad_norm: 5.0911 loss: 2.9083 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.9083 2023/02/17 12:35:11 - mmengine - INFO - Epoch(train) [3][ 500/1320] lr: 1.1000e-02 eta: 8:36:28 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 5.0512 loss: 2.9139 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.9139 2023/02/17 12:35:20 - mmengine - INFO - Epoch(train) [3][ 520/1320] lr: 1.1000e-02 eta: 8:36:13 time: 0.4800 data_time: 0.0153 memory: 27031 grad_norm: 5.2387 loss: 2.9267 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.9267 2023/02/17 12:35:30 - mmengine - INFO - Epoch(train) [3][ 540/1320] lr: 1.1000e-02 eta: 8:35:58 time: 0.4804 data_time: 0.0158 memory: 27031 grad_norm: 5.2910 loss: 2.9918 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 2.9918 2023/02/17 12:35:40 - mmengine - INFO - Epoch(train) [3][ 560/1320] lr: 1.1000e-02 eta: 8:35:43 time: 0.4798 data_time: 0.0152 memory: 27031 grad_norm: 5.2687 loss: 2.8298 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.8298 2023/02/17 12:35:49 - mmengine - INFO - Epoch(train) [3][ 580/1320] lr: 1.1000e-02 eta: 8:35:29 time: 0.4808 data_time: 0.0160 memory: 27031 grad_norm: 5.2525 loss: 2.9147 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.9147 2023/02/17 12:35:59 - mmengine - INFO - Epoch(train) [3][ 600/1320] lr: 1.1000e-02 eta: 8:35:14 time: 0.4795 data_time: 0.0147 memory: 27031 grad_norm: 5.2743 loss: 2.6962 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.6962 2023/02/17 12:36:08 - mmengine - INFO - Epoch(train) [3][ 620/1320] lr: 1.1000e-02 eta: 8:34:59 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 5.2823 loss: 2.6655 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6655 2023/02/17 12:36:18 - mmengine - INFO - Epoch(train) [3][ 640/1320] lr: 1.1000e-02 eta: 8:34:45 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 5.1136 loss: 2.9378 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.9378 2023/02/17 12:36:28 - mmengine - INFO - Epoch(train) [3][ 660/1320] lr: 1.1000e-02 eta: 8:34:30 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 5.2767 loss: 2.6934 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6934 2023/02/17 12:36:37 - mmengine - INFO - Epoch(train) [3][ 680/1320] lr: 1.1000e-02 eta: 8:34:16 time: 0.4808 data_time: 0.0160 memory: 27031 grad_norm: 5.1416 loss: 2.9450 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.9450 2023/02/17 12:36:47 - mmengine - INFO - Epoch(train) [3][ 700/1320] lr: 1.1000e-02 eta: 8:34:02 time: 0.4802 data_time: 0.0157 memory: 27031 grad_norm: 5.1601 loss: 2.7200 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.7200 2023/02/17 12:36:56 - mmengine - INFO - Epoch(train) [3][ 720/1320] lr: 1.1000e-02 eta: 8:33:47 time: 0.4791 data_time: 0.0152 memory: 27031 grad_norm: 5.3430 loss: 2.6484 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.6484 2023/02/17 12:37:06 - mmengine - INFO - Epoch(train) [3][ 740/1320] lr: 1.1000e-02 eta: 8:33:33 time: 0.4801 data_time: 0.0156 memory: 27031 grad_norm: 5.2031 loss: 2.8836 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.8836 2023/02/17 12:37:16 - mmengine - INFO - Epoch(train) [3][ 760/1320] lr: 1.1000e-02 eta: 8:33:18 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 5.3005 loss: 2.7556 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.7556 2023/02/17 12:37:25 - mmengine - INFO - Epoch(train) [3][ 780/1320] lr: 1.1000e-02 eta: 8:33:04 time: 0.4799 data_time: 0.0162 memory: 27031 grad_norm: 5.0126 loss: 2.8683 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.8683 2023/02/17 12:37:35 - mmengine - INFO - Epoch(train) [3][ 800/1320] lr: 1.1000e-02 eta: 8:32:50 time: 0.4805 data_time: 0.0163 memory: 27031 grad_norm: 5.2749 loss: 2.8393 top1_acc: 0.1250 top5_acc: 0.6875 loss_cls: 2.8393 2023/02/17 12:37:44 - mmengine - INFO - Epoch(train) [3][ 820/1320] lr: 1.1000e-02 eta: 8:32:36 time: 0.4800 data_time: 0.0157 memory: 27031 grad_norm: 5.0270 loss: 2.6099 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.6099 2023/02/17 12:37:54 - mmengine - INFO - Epoch(train) [3][ 840/1320] lr: 1.1000e-02 eta: 8:32:22 time: 0.4802 data_time: 0.0157 memory: 27031 grad_norm: 5.0755 loss: 2.9213 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.9213 2023/02/17 12:38:04 - mmengine - INFO - Epoch(train) [3][ 860/1320] lr: 1.1000e-02 eta: 8:32:08 time: 0.4808 data_time: 0.0165 memory: 27031 grad_norm: 5.1119 loss: 2.7632 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.7632 2023/02/17 12:38:13 - mmengine - INFO - Epoch(train) [3][ 880/1320] lr: 1.1000e-02 eta: 8:31:54 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 5.1201 loss: 2.6912 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6912 2023/02/17 12:38:23 - mmengine - INFO - Epoch(train) [3][ 900/1320] lr: 1.1000e-02 eta: 8:31:40 time: 0.4804 data_time: 0.0167 memory: 27031 grad_norm: 5.2600 loss: 2.7333 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.7333 2023/02/17 12:38:32 - mmengine - INFO - Epoch(train) [3][ 920/1320] lr: 1.1000e-02 eta: 8:31:26 time: 0.4798 data_time: 0.0151 memory: 27031 grad_norm: 5.1414 loss: 2.8742 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.8742 2023/02/17 12:38:42 - mmengine - INFO - Epoch(train) [3][ 940/1320] lr: 1.1000e-02 eta: 8:31:12 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 5.0919 loss: 2.6033 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.6033 2023/02/17 12:38:52 - mmengine - INFO - Epoch(train) [3][ 960/1320] lr: 1.1000e-02 eta: 8:30:59 time: 0.4807 data_time: 0.0164 memory: 27031 grad_norm: 5.2478 loss: 2.7352 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.7352 2023/02/17 12:39:01 - mmengine - INFO - Epoch(train) [3][ 980/1320] lr: 1.1000e-02 eta: 8:30:45 time: 0.4806 data_time: 0.0153 memory: 27031 grad_norm: 5.1247 loss: 2.6113 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.6113 2023/02/17 12:39:11 - mmengine - INFO - Epoch(train) [3][1000/1320] lr: 1.1000e-02 eta: 8:30:32 time: 0.4803 data_time: 0.0153 memory: 27031 grad_norm: 5.0856 loss: 2.7878 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.7878 2023/02/17 12:39:20 - mmengine - INFO - Epoch(train) [3][1020/1320] lr: 1.1000e-02 eta: 8:30:18 time: 0.4812 data_time: 0.0158 memory: 27031 grad_norm: 5.0477 loss: 2.5424 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5424 2023/02/17 12:39:30 - mmengine - INFO - Epoch(train) [3][1040/1320] lr: 1.1000e-02 eta: 8:30:05 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 5.1231 loss: 2.5259 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.5259 2023/02/17 12:39:40 - mmengine - INFO - Epoch(train) [3][1060/1320] lr: 1.1000e-02 eta: 8:29:51 time: 0.4805 data_time: 0.0167 memory: 27031 grad_norm: 5.0864 loss: 2.5763 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.5763 2023/02/17 12:39:49 - mmengine - INFO - Epoch(train) [3][1080/1320] lr: 1.1000e-02 eta: 8:29:38 time: 0.4800 data_time: 0.0158 memory: 27031 grad_norm: 5.1771 loss: 2.6230 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.6230 2023/02/17 12:39:59 - mmengine - INFO - Epoch(train) [3][1100/1320] lr: 1.1000e-02 eta: 8:29:24 time: 0.4794 data_time: 0.0148 memory: 27031 grad_norm: 5.2232 loss: 2.7838 top1_acc: 0.3125 top5_acc: 0.3125 loss_cls: 2.7838 2023/02/17 12:40:08 - mmengine - INFO - Epoch(train) [3][1120/1320] lr: 1.1000e-02 eta: 8:29:11 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.9651 loss: 2.6860 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.6860 2023/02/17 12:40:18 - mmengine - INFO - Epoch(train) [3][1140/1320] lr: 1.1000e-02 eta: 8:28:58 time: 0.4813 data_time: 0.0163 memory: 27031 grad_norm: 5.2190 loss: 2.6711 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.6711 2023/02/17 12:40:28 - mmengine - INFO - Epoch(train) [3][1160/1320] lr: 1.1000e-02 eta: 8:28:45 time: 0.4807 data_time: 0.0160 memory: 27031 grad_norm: 5.0566 loss: 2.5423 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5423 2023/02/17 12:40:37 - mmengine - INFO - Epoch(train) [3][1180/1320] lr: 1.1000e-02 eta: 8:28:31 time: 0.4800 data_time: 0.0157 memory: 27031 grad_norm: 4.9826 loss: 2.5663 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.5663 2023/02/17 12:40:47 - mmengine - INFO - Epoch(train) [3][1200/1320] lr: 1.1000e-02 eta: 8:28:18 time: 0.4801 data_time: 0.0156 memory: 27031 grad_norm: 5.1630 loss: 2.6401 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.6401 2023/02/17 12:40:57 - mmengine - INFO - Epoch(train) [3][1220/1320] lr: 1.1000e-02 eta: 8:28:05 time: 0.4814 data_time: 0.0164 memory: 27031 grad_norm: 5.0917 loss: 2.7468 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.7468 2023/02/17 12:41:06 - mmengine - INFO - Epoch(train) [3][1240/1320] lr: 1.1000e-02 eta: 8:27:52 time: 0.4807 data_time: 0.0154 memory: 27031 grad_norm: 5.1024 loss: 2.7011 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.7011 2023/02/17 12:41:16 - mmengine - INFO - Epoch(train) [3][1260/1320] lr: 1.1000e-02 eta: 8:27:39 time: 0.4805 data_time: 0.0155 memory: 27031 grad_norm: 5.2369 loss: 2.5425 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.5425 2023/02/17 12:41:25 - mmengine - INFO - Epoch(train) [3][1280/1320] lr: 1.1000e-02 eta: 8:27:26 time: 0.4806 data_time: 0.0168 memory: 27031 grad_norm: 4.9065 loss: 2.5516 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.5516 2023/02/17 12:41:35 - mmengine - INFO - Epoch(train) [3][1300/1320] lr: 1.1000e-02 eta: 8:27:13 time: 0.4805 data_time: 0.0154 memory: 27031 grad_norm: 5.0269 loss: 2.8722 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.8722 2023/02/17 12:41:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:41:44 - mmengine - INFO - Epoch(train) [3][1320/1320] lr: 1.1000e-02 eta: 8:26:58 time: 0.4729 data_time: 0.0157 memory: 27031 grad_norm: 5.1131 loss: 2.6116 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 2.6116 2023/02/17 12:41:44 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/02/17 12:41:49 - mmengine - INFO - Epoch(val) [3][ 20/194] eta: 0:00:31 time: 0.1831 data_time: 0.0566 memory: 3265 2023/02/17 12:41:52 - mmengine - INFO - Epoch(val) [3][ 40/194] eta: 0:00:24 time: 0.1344 data_time: 0.0119 memory: 3265 2023/02/17 12:41:55 - mmengine - INFO - Epoch(val) [3][ 60/194] eta: 0:00:20 time: 0.1342 data_time: 0.0117 memory: 3265 2023/02/17 12:41:57 - mmengine - INFO - Epoch(val) [3][ 80/194] eta: 0:00:16 time: 0.1360 data_time: 0.0130 memory: 3265 2023/02/17 12:42:00 - mmengine - INFO - Epoch(val) [3][100/194] eta: 0:00:13 time: 0.1365 data_time: 0.0130 memory: 3265 2023/02/17 12:42:03 - mmengine - INFO - Epoch(val) [3][120/194] eta: 0:00:10 time: 0.1378 data_time: 0.0139 memory: 3265 2023/02/17 12:42:06 - mmengine - INFO - Epoch(val) [3][140/194] eta: 0:00:07 time: 0.1360 data_time: 0.0127 memory: 3265 2023/02/17 12:42:08 - mmengine - INFO - Epoch(val) [3][160/194] eta: 0:00:04 time: 0.1357 data_time: 0.0125 memory: 3265 2023/02/17 12:42:11 - mmengine - INFO - Epoch(val) [3][180/194] eta: 0:00:01 time: 0.1338 data_time: 0.0118 memory: 3265 2023/02/17 12:42:13 - mmengine - INFO - Epoch(val) [3][194/194] acc/top1: 0.3377 acc/top5: 0.6277 acc/mean1: 0.2637 2023/02/17 12:42:13 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_2.pth is removed 2023/02/17 12:42:14 - mmengine - INFO - The best checkpoint with 0.3377 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2023/02/17 12:42:25 - mmengine - INFO - Epoch(train) [4][ 20/1320] lr: 1.5500e-02 eta: 8:26:59 time: 0.5235 data_time: 0.0554 memory: 27031 grad_norm: 5.2617 loss: 2.8853 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.8853 2023/02/17 12:42:34 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:42:34 - mmengine - INFO - Epoch(train) [4][ 40/1320] lr: 1.5500e-02 eta: 8:26:46 time: 0.4795 data_time: 0.0153 memory: 27031 grad_norm: 5.2149 loss: 2.9416 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.9416 2023/02/17 12:42:44 - mmengine - INFO - Epoch(train) [4][ 60/1320] lr: 1.5500e-02 eta: 8:26:33 time: 0.4802 data_time: 0.0166 memory: 27031 grad_norm: 5.1501 loss: 2.7539 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.7539 2023/02/17 12:42:54 - mmengine - INFO - Epoch(train) [4][ 80/1320] lr: 1.5500e-02 eta: 8:26:20 time: 0.4812 data_time: 0.0168 memory: 27031 grad_norm: 5.2106 loss: 2.7609 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.7609 2023/02/17 12:43:03 - mmengine - INFO - Epoch(train) [4][ 100/1320] lr: 1.5500e-02 eta: 8:26:07 time: 0.4802 data_time: 0.0163 memory: 27031 grad_norm: 4.8873 loss: 2.6634 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.6634 2023/02/17 12:43:13 - mmengine - INFO - Epoch(train) [4][ 120/1320] lr: 1.5500e-02 eta: 8:25:54 time: 0.4796 data_time: 0.0160 memory: 27031 grad_norm: 4.9935 loss: 2.9365 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 2.9365 2023/02/17 12:43:22 - mmengine - INFO - Epoch(train) [4][ 140/1320] lr: 1.5500e-02 eta: 8:25:41 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.9756 loss: 2.6282 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.6282 2023/02/17 12:43:32 - mmengine - INFO - Epoch(train) [4][ 160/1320] lr: 1.5500e-02 eta: 8:25:28 time: 0.4805 data_time: 0.0161 memory: 27031 grad_norm: 4.9122 loss: 2.9094 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.9094 2023/02/17 12:43:42 - mmengine - INFO - Epoch(train) [4][ 180/1320] lr: 1.5500e-02 eta: 8:25:15 time: 0.4801 data_time: 0.0156 memory: 27031 grad_norm: 4.8830 loss: 2.6558 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.6558 2023/02/17 12:43:51 - mmengine - INFO - Epoch(train) [4][ 200/1320] lr: 1.5500e-02 eta: 8:25:03 time: 0.4798 data_time: 0.0153 memory: 27031 grad_norm: 4.9406 loss: 2.6250 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.6250 2023/02/17 12:44:01 - mmengine - INFO - Epoch(train) [4][ 220/1320] lr: 1.5500e-02 eta: 8:24:50 time: 0.4800 data_time: 0.0161 memory: 27031 grad_norm: 4.7687 loss: 2.5982 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.5982 2023/02/17 12:44:10 - mmengine - INFO - Epoch(train) [4][ 240/1320] lr: 1.5500e-02 eta: 8:24:37 time: 0.4797 data_time: 0.0158 memory: 27031 grad_norm: 4.9761 loss: 2.5807 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.5807 2023/02/17 12:44:20 - mmengine - INFO - Epoch(train) [4][ 260/1320] lr: 1.5500e-02 eta: 8:24:24 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.9373 loss: 2.6383 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.6383 2023/02/17 12:44:30 - mmengine - INFO - Epoch(train) [4][ 280/1320] lr: 1.5500e-02 eta: 8:24:12 time: 0.4823 data_time: 0.0177 memory: 27031 grad_norm: 4.8782 loss: 2.8473 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.8473 2023/02/17 12:44:39 - mmengine - INFO - Epoch(train) [4][ 300/1320] lr: 1.5500e-02 eta: 8:23:59 time: 0.4790 data_time: 0.0148 memory: 27031 grad_norm: 4.8363 loss: 2.6443 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.6443 2023/02/17 12:44:49 - mmengine - INFO - Epoch(train) [4][ 320/1320] lr: 1.5500e-02 eta: 8:23:47 time: 0.4797 data_time: 0.0160 memory: 27031 grad_norm: 4.9204 loss: 2.8292 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.8292 2023/02/17 12:44:58 - mmengine - INFO - Epoch(train) [4][ 340/1320] lr: 1.5500e-02 eta: 8:23:34 time: 0.4803 data_time: 0.0159 memory: 27031 grad_norm: 4.8038 loss: 2.7624 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.7624 2023/02/17 12:45:08 - mmengine - INFO - Epoch(train) [4][ 360/1320] lr: 1.5500e-02 eta: 8:23:22 time: 0.4820 data_time: 0.0179 memory: 27031 grad_norm: 4.9288 loss: 2.7613 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.7613 2023/02/17 12:45:18 - mmengine - INFO - Epoch(train) [4][ 380/1320] lr: 1.5500e-02 eta: 8:23:09 time: 0.4795 data_time: 0.0164 memory: 27031 grad_norm: 4.7489 loss: 2.7407 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.7407 2023/02/17 12:45:27 - mmengine - INFO - Epoch(train) [4][ 400/1320] lr: 1.5500e-02 eta: 8:22:57 time: 0.4807 data_time: 0.0164 memory: 27031 grad_norm: 4.8447 loss: 2.5744 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5744 2023/02/17 12:45:37 - mmengine - INFO - Epoch(train) [4][ 420/1320] lr: 1.5500e-02 eta: 8:22:45 time: 0.4798 data_time: 0.0152 memory: 27031 grad_norm: 4.8429 loss: 2.7343 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.7343 2023/02/17 12:45:46 - mmengine - INFO - Epoch(train) [4][ 440/1320] lr: 1.5500e-02 eta: 8:22:32 time: 0.4802 data_time: 0.0159 memory: 27031 grad_norm: 4.7590 loss: 2.6267 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.6267 2023/02/17 12:45:56 - mmengine - INFO - Epoch(train) [4][ 460/1320] lr: 1.5500e-02 eta: 8:22:19 time: 0.4792 data_time: 0.0149 memory: 27031 grad_norm: 4.7271 loss: 2.6281 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.6281 2023/02/17 12:46:06 - mmengine - INFO - Epoch(train) [4][ 480/1320] lr: 1.5500e-02 eta: 8:22:07 time: 0.4795 data_time: 0.0150 memory: 27031 grad_norm: 4.8192 loss: 2.7322 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.7322 2023/02/17 12:46:15 - mmengine - INFO - Epoch(train) [4][ 500/1320] lr: 1.5500e-02 eta: 8:21:55 time: 0.4802 data_time: 0.0158 memory: 27031 grad_norm: 4.7780 loss: 2.7192 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.7192 2023/02/17 12:46:25 - mmengine - INFO - Epoch(train) [4][ 520/1320] lr: 1.5500e-02 eta: 8:21:42 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.8236 loss: 2.7624 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.7624 2023/02/17 12:46:34 - mmengine - INFO - Epoch(train) [4][ 540/1320] lr: 1.5500e-02 eta: 8:21:30 time: 0.4809 data_time: 0.0160 memory: 27031 grad_norm: 4.6982 loss: 2.7676 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.7676 2023/02/17 12:46:44 - mmengine - INFO - Epoch(train) [4][ 560/1320] lr: 1.5500e-02 eta: 8:21:17 time: 0.4793 data_time: 0.0153 memory: 27031 grad_norm: 4.6798 loss: 2.6756 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.6756 2023/02/17 12:46:54 - mmengine - INFO - Epoch(train) [4][ 580/1320] lr: 1.5500e-02 eta: 8:21:05 time: 0.4801 data_time: 0.0160 memory: 27031 grad_norm: 4.6778 loss: 2.6460 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.6460 2023/02/17 12:47:03 - mmengine - INFO - Epoch(train) [4][ 600/1320] lr: 1.5500e-02 eta: 8:20:53 time: 0.4820 data_time: 0.0188 memory: 27031 grad_norm: 4.6672 loss: 2.8488 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.8488 2023/02/17 12:47:13 - mmengine - INFO - Epoch(train) [4][ 620/1320] lr: 1.5500e-02 eta: 8:20:41 time: 0.4800 data_time: 0.0159 memory: 27031 grad_norm: 4.6825 loss: 2.7385 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.7385 2023/02/17 12:47:23 - mmengine - INFO - Epoch(train) [4][ 640/1320] lr: 1.5500e-02 eta: 8:20:29 time: 0.4806 data_time: 0.0160 memory: 27031 grad_norm: 4.7723 loss: 2.4753 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.4753 2023/02/17 12:47:32 - mmengine - INFO - Epoch(train) [4][ 660/1320] lr: 1.5500e-02 eta: 8:20:18 time: 0.4825 data_time: 0.0161 memory: 27031 grad_norm: 4.8416 loss: 2.4975 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.4975 2023/02/17 12:47:42 - mmengine - INFO - Epoch(train) [4][ 680/1320] lr: 1.5500e-02 eta: 8:20:05 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.6412 loss: 2.5388 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5388 2023/02/17 12:47:51 - mmengine - INFO - Epoch(train) [4][ 700/1320] lr: 1.5500e-02 eta: 8:19:53 time: 0.4803 data_time: 0.0163 memory: 27031 grad_norm: 4.7909 loss: 2.5280 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.5280 2023/02/17 12:48:01 - mmengine - INFO - Epoch(train) [4][ 720/1320] lr: 1.5500e-02 eta: 8:19:41 time: 0.4802 data_time: 0.0168 memory: 27031 grad_norm: 4.7551 loss: 2.7676 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 2.7676 2023/02/17 12:48:11 - mmengine - INFO - Epoch(train) [4][ 740/1320] lr: 1.5500e-02 eta: 8:19:29 time: 0.4800 data_time: 0.0154 memory: 27031 grad_norm: 4.6609 loss: 2.6873 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.6873 2023/02/17 12:48:20 - mmengine - INFO - Epoch(train) [4][ 760/1320] lr: 1.5500e-02 eta: 8:19:17 time: 0.4796 data_time: 0.0153 memory: 27031 grad_norm: 4.6692 loss: 2.5694 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5694 2023/02/17 12:48:30 - mmengine - INFO - Epoch(train) [4][ 780/1320] lr: 1.5500e-02 eta: 8:19:05 time: 0.4812 data_time: 0.0158 memory: 27031 grad_norm: 4.6380 loss: 2.5430 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5430 2023/02/17 12:48:39 - mmengine - INFO - Epoch(train) [4][ 800/1320] lr: 1.5500e-02 eta: 8:18:53 time: 0.4804 data_time: 0.0162 memory: 27031 grad_norm: 4.7622 loss: 2.7032 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.7032 2023/02/17 12:48:49 - mmengine - INFO - Epoch(train) [4][ 820/1320] lr: 1.5500e-02 eta: 8:18:41 time: 0.4805 data_time: 0.0161 memory: 27031 grad_norm: 4.6009 loss: 2.5738 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.5738 2023/02/17 12:48:59 - mmengine - INFO - Epoch(train) [4][ 840/1320] lr: 1.5500e-02 eta: 8:18:29 time: 0.4794 data_time: 0.0152 memory: 27031 grad_norm: 4.6497 loss: 2.8158 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.8158 2023/02/17 12:49:08 - mmengine - INFO - Epoch(train) [4][ 860/1320] lr: 1.5500e-02 eta: 8:18:18 time: 0.4827 data_time: 0.0176 memory: 27031 grad_norm: 4.6764 loss: 2.6344 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6344 2023/02/17 12:49:18 - mmengine - INFO - Epoch(train) [4][ 880/1320] lr: 1.5500e-02 eta: 8:18:06 time: 0.4812 data_time: 0.0164 memory: 27031 grad_norm: 4.5902 loss: 2.4518 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.4518 2023/02/17 12:49:27 - mmengine - INFO - Epoch(train) [4][ 900/1320] lr: 1.5500e-02 eta: 8:17:54 time: 0.4802 data_time: 0.0162 memory: 27031 grad_norm: 4.7284 loss: 2.8443 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.8443 2023/02/17 12:49:37 - mmengine - INFO - Epoch(train) [4][ 920/1320] lr: 1.5500e-02 eta: 8:17:42 time: 0.4813 data_time: 0.0168 memory: 27031 grad_norm: 4.5618 loss: 2.5170 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5170 2023/02/17 12:49:47 - mmengine - INFO - Epoch(train) [4][ 940/1320] lr: 1.5500e-02 eta: 8:17:30 time: 0.4796 data_time: 0.0153 memory: 27031 grad_norm: 4.6447 loss: 2.4456 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.4456 2023/02/17 12:49:56 - mmengine - INFO - Epoch(train) [4][ 960/1320] lr: 1.5500e-02 eta: 8:17:19 time: 0.4804 data_time: 0.0167 memory: 27031 grad_norm: 4.6262 loss: 2.5098 top1_acc: 0.3750 top5_acc: 0.4375 loss_cls: 2.5098 2023/02/17 12:50:06 - mmengine - INFO - Epoch(train) [4][ 980/1320] lr: 1.5500e-02 eta: 8:17:07 time: 0.4799 data_time: 0.0160 memory: 27031 grad_norm: 4.8062 loss: 2.6046 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.6046 2023/02/17 12:50:15 - mmengine - INFO - Epoch(train) [4][1000/1320] lr: 1.5500e-02 eta: 8:16:55 time: 0.4804 data_time: 0.0156 memory: 27031 grad_norm: 4.6848 loss: 2.4062 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.4062 2023/02/17 12:50:25 - mmengine - INFO - Epoch(train) [4][1020/1320] lr: 1.5500e-02 eta: 8:16:43 time: 0.4810 data_time: 0.0170 memory: 27031 grad_norm: 4.6193 loss: 2.5427 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.5427 2023/02/17 12:50:35 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:50:35 - mmengine - INFO - Epoch(train) [4][1040/1320] lr: 1.5500e-02 eta: 8:16:32 time: 0.4810 data_time: 0.0162 memory: 27031 grad_norm: 4.6024 loss: 2.7163 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.7163 2023/02/17 12:50:44 - mmengine - INFO - Epoch(train) [4][1060/1320] lr: 1.5500e-02 eta: 8:16:20 time: 0.4805 data_time: 0.0168 memory: 27031 grad_norm: 4.6216 loss: 2.6183 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.6183 2023/02/17 12:50:54 - mmengine - INFO - Epoch(train) [4][1080/1320] lr: 1.5500e-02 eta: 8:16:09 time: 0.4813 data_time: 0.0162 memory: 27031 grad_norm: 4.5799 loss: 2.4688 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.4688 2023/02/17 12:51:04 - mmengine - INFO - Epoch(train) [4][1100/1320] lr: 1.5500e-02 eta: 8:15:57 time: 0.4808 data_time: 0.0163 memory: 27031 grad_norm: 4.4085 loss: 2.5823 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.5823 2023/02/17 12:51:13 - mmengine - INFO - Epoch(train) [4][1120/1320] lr: 1.5500e-02 eta: 8:15:45 time: 0.4803 data_time: 0.0156 memory: 27031 grad_norm: 4.7145 loss: 2.5804 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.5804 2023/02/17 12:51:23 - mmengine - INFO - Epoch(train) [4][1140/1320] lr: 1.5500e-02 eta: 8:15:34 time: 0.4808 data_time: 0.0163 memory: 27031 grad_norm: 4.6144 loss: 2.4884 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.4884 2023/02/17 12:51:32 - mmengine - INFO - Epoch(train) [4][1160/1320] lr: 1.5500e-02 eta: 8:15:22 time: 0.4810 data_time: 0.0158 memory: 27031 grad_norm: 4.5063 loss: 2.4845 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.4845 2023/02/17 12:51:42 - mmengine - INFO - Epoch(train) [4][1180/1320] lr: 1.5500e-02 eta: 8:15:11 time: 0.4812 data_time: 0.0172 memory: 27031 grad_norm: 4.6101 loss: 2.3795 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.3795 2023/02/17 12:51:52 - mmengine - INFO - Epoch(train) [4][1200/1320] lr: 1.5500e-02 eta: 8:15:00 time: 0.4827 data_time: 0.0153 memory: 27031 grad_norm: 4.7244 loss: 2.4471 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4471 2023/02/17 12:52:01 - mmengine - INFO - Epoch(train) [4][1220/1320] lr: 1.5500e-02 eta: 8:14:48 time: 0.4811 data_time: 0.0162 memory: 27031 grad_norm: 4.5506 loss: 2.6220 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.6220 2023/02/17 12:52:11 - mmengine - INFO - Epoch(train) [4][1240/1320] lr: 1.5500e-02 eta: 8:14:37 time: 0.4805 data_time: 0.0161 memory: 27031 grad_norm: 4.6165 loss: 2.7186 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.7186 2023/02/17 12:52:21 - mmengine - INFO - Epoch(train) [4][1260/1320] lr: 1.5500e-02 eta: 8:14:25 time: 0.4807 data_time: 0.0164 memory: 27031 grad_norm: 4.7044 loss: 2.5046 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.5046 2023/02/17 12:52:30 - mmengine - INFO - Epoch(train) [4][1280/1320] lr: 1.5500e-02 eta: 8:14:14 time: 0.4804 data_time: 0.0162 memory: 27031 grad_norm: 4.6112 loss: 2.5063 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.5063 2023/02/17 12:52:40 - mmengine - INFO - Epoch(train) [4][1300/1320] lr: 1.5500e-02 eta: 8:14:03 time: 0.4815 data_time: 0.0165 memory: 27031 grad_norm: 4.8026 loss: 2.6883 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.6883 2023/02/17 12:52:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:52:49 - mmengine - INFO - Epoch(train) [4][1320/1320] lr: 1.5500e-02 eta: 8:13:49 time: 0.4729 data_time: 0.0160 memory: 27031 grad_norm: 4.6092 loss: 2.4291 top1_acc: 0.3636 top5_acc: 0.5455 loss_cls: 2.4291 2023/02/17 12:52:53 - mmengine - INFO - Epoch(val) [4][ 20/194] eta: 0:00:31 time: 0.1835 data_time: 0.0564 memory: 3265 2023/02/17 12:52:56 - mmengine - INFO - Epoch(val) [4][ 40/194] eta: 0:00:24 time: 0.1362 data_time: 0.0125 memory: 3265 2023/02/17 12:52:58 - mmengine - INFO - Epoch(val) [4][ 60/194] eta: 0:00:20 time: 0.1359 data_time: 0.0125 memory: 3265 2023/02/17 12:53:01 - mmengine - INFO - Epoch(val) [4][ 80/194] eta: 0:00:16 time: 0.1366 data_time: 0.0127 memory: 3265 2023/02/17 12:53:04 - mmengine - INFO - Epoch(val) [4][100/194] eta: 0:00:13 time: 0.1353 data_time: 0.0126 memory: 3265 2023/02/17 12:53:07 - mmengine - INFO - Epoch(val) [4][120/194] eta: 0:00:10 time: 0.1372 data_time: 0.0135 memory: 3265 2023/02/17 12:53:09 - mmengine - INFO - Epoch(val) [4][140/194] eta: 0:00:07 time: 0.1361 data_time: 0.0127 memory: 3265 2023/02/17 12:53:12 - mmengine - INFO - Epoch(val) [4][160/194] eta: 0:00:04 time: 0.1371 data_time: 0.0135 memory: 3265 2023/02/17 12:53:15 - mmengine - INFO - Epoch(val) [4][180/194] eta: 0:00:01 time: 0.1369 data_time: 0.0130 memory: 3265 2023/02/17 12:53:18 - mmengine - INFO - Epoch(val) [4][194/194] acc/top1: 0.3618 acc/top5: 0.6824 acc/mean1: 0.2971 2023/02/17 12:53:18 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_3.pth is removed 2023/02/17 12:53:19 - mmengine - INFO - The best checkpoint with 0.3618 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2023/02/17 12:53:29 - mmengine - INFO - Epoch(train) [5][ 20/1320] lr: 2.0000e-02 eta: 8:13:48 time: 0.5253 data_time: 0.0527 memory: 27031 grad_norm: 4.5844 loss: 2.4433 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 2.4433 2023/02/17 12:53:39 - mmengine - INFO - Epoch(train) [5][ 40/1320] lr: 2.0000e-02 eta: 8:13:37 time: 0.4813 data_time: 0.0169 memory: 27031 grad_norm: 4.6604 loss: 2.6127 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.6127 2023/02/17 12:53:48 - mmengine - INFO - Epoch(train) [5][ 60/1320] lr: 2.0000e-02 eta: 8:13:25 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.7320 loss: 2.6701 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.6701 2023/02/17 12:53:58 - mmengine - INFO - Epoch(train) [5][ 80/1320] lr: 2.0000e-02 eta: 8:13:14 time: 0.4820 data_time: 0.0183 memory: 27031 grad_norm: 4.4915 loss: 2.8883 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.8883 2023/02/17 12:54:08 - mmengine - INFO - Epoch(train) [5][ 100/1320] lr: 2.0000e-02 eta: 8:13:02 time: 0.4797 data_time: 0.0152 memory: 27031 grad_norm: 4.6467 loss: 2.7363 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.7363 2023/02/17 12:54:17 - mmengine - INFO - Epoch(train) [5][ 120/1320] lr: 2.0000e-02 eta: 8:12:51 time: 0.4809 data_time: 0.0168 memory: 27031 grad_norm: 4.5362 loss: 2.7288 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 2.7288 2023/02/17 12:54:27 - mmengine - INFO - Epoch(train) [5][ 140/1320] lr: 2.0000e-02 eta: 8:12:40 time: 0.4806 data_time: 0.0164 memory: 27031 grad_norm: 4.6308 loss: 2.5455 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.5455 2023/02/17 12:54:37 - mmengine - INFO - Epoch(train) [5][ 160/1320] lr: 2.0000e-02 eta: 8:12:28 time: 0.4807 data_time: 0.0165 memory: 27031 grad_norm: 4.4901 loss: 2.4646 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4646 2023/02/17 12:54:46 - mmengine - INFO - Epoch(train) [5][ 180/1320] lr: 2.0000e-02 eta: 8:12:17 time: 0.4810 data_time: 0.0165 memory: 27031 grad_norm: 4.4423 loss: 2.9446 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 2.9446 2023/02/17 12:54:56 - mmengine - INFO - Epoch(train) [5][ 200/1320] lr: 2.0000e-02 eta: 8:12:05 time: 0.4800 data_time: 0.0158 memory: 27031 grad_norm: 4.4238 loss: 2.6179 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.6179 2023/02/17 12:55:05 - mmengine - INFO - Epoch(train) [5][ 220/1320] lr: 2.0000e-02 eta: 8:11:54 time: 0.4797 data_time: 0.0158 memory: 27031 grad_norm: 4.5440 loss: 2.6453 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.6453 2023/02/17 12:55:15 - mmengine - INFO - Epoch(train) [5][ 240/1320] lr: 2.0000e-02 eta: 8:11:43 time: 0.4807 data_time: 0.0162 memory: 27031 grad_norm: 4.4370 loss: 2.4898 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4898 2023/02/17 12:55:25 - mmengine - INFO - Epoch(train) [5][ 260/1320] lr: 2.0000e-02 eta: 8:11:31 time: 0.4807 data_time: 0.0157 memory: 27031 grad_norm: 4.4062 loss: 2.5732 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.5732 2023/02/17 12:55:34 - mmengine - INFO - Epoch(train) [5][ 280/1320] lr: 2.0000e-02 eta: 8:11:20 time: 0.4805 data_time: 0.0166 memory: 27031 grad_norm: 4.4294 loss: 2.4980 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.4980 2023/02/17 12:55:44 - mmengine - INFO - Epoch(train) [5][ 300/1320] lr: 2.0000e-02 eta: 8:11:09 time: 0.4810 data_time: 0.0160 memory: 27031 grad_norm: 4.5540 loss: 2.6394 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.6394 2023/02/17 12:55:53 - mmengine - INFO - Epoch(train) [5][ 320/1320] lr: 2.0000e-02 eta: 8:10:58 time: 0.4815 data_time: 0.0157 memory: 27031 grad_norm: 4.3661 loss: 2.8551 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.8551 2023/02/17 12:56:03 - mmengine - INFO - Epoch(train) [5][ 340/1320] lr: 2.0000e-02 eta: 8:10:46 time: 0.4809 data_time: 0.0157 memory: 27031 grad_norm: 4.4097 loss: 2.5595 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.5595 2023/02/17 12:56:13 - mmengine - INFO - Epoch(train) [5][ 360/1320] lr: 2.0000e-02 eta: 8:10:35 time: 0.4805 data_time: 0.0160 memory: 27031 grad_norm: 4.3457 loss: 2.3777 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.3777 2023/02/17 12:56:22 - mmengine - INFO - Epoch(train) [5][ 380/1320] lr: 2.0000e-02 eta: 8:10:23 time: 0.4793 data_time: 0.0151 memory: 27031 grad_norm: 4.5180 loss: 2.6580 top1_acc: 0.1875 top5_acc: 0.4375 loss_cls: 2.6580 2023/02/17 12:56:32 - mmengine - INFO - Epoch(train) [5][ 400/1320] lr: 2.0000e-02 eta: 8:10:12 time: 0.4801 data_time: 0.0163 memory: 27031 grad_norm: 4.4403 loss: 2.5398 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.5398 2023/02/17 12:56:41 - mmengine - INFO - Epoch(train) [5][ 420/1320] lr: 2.0000e-02 eta: 8:10:01 time: 0.4795 data_time: 0.0154 memory: 27031 grad_norm: 4.4266 loss: 2.6316 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.6316 2023/02/17 12:56:51 - mmengine - INFO - Epoch(train) [5][ 440/1320] lr: 2.0000e-02 eta: 8:09:50 time: 0.4814 data_time: 0.0167 memory: 27031 grad_norm: 4.3775 loss: 2.5584 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.5584 2023/02/17 12:57:01 - mmengine - INFO - Epoch(train) [5][ 460/1320] lr: 2.0000e-02 eta: 8:09:38 time: 0.4795 data_time: 0.0163 memory: 27031 grad_norm: 4.3855 loss: 2.5910 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.5910 2023/02/17 12:57:10 - mmengine - INFO - Epoch(train) [5][ 480/1320] lr: 2.0000e-02 eta: 8:09:27 time: 0.4800 data_time: 0.0152 memory: 27031 grad_norm: 4.3369 loss: 2.4858 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.4858 2023/02/17 12:57:20 - mmengine - INFO - Epoch(train) [5][ 500/1320] lr: 2.0000e-02 eta: 8:09:16 time: 0.4808 data_time: 0.0159 memory: 27031 grad_norm: 4.5361 loss: 2.4852 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.4852 2023/02/17 12:57:30 - mmengine - INFO - Epoch(train) [5][ 520/1320] lr: 2.0000e-02 eta: 8:09:04 time: 0.4802 data_time: 0.0154 memory: 27031 grad_norm: 4.4090 loss: 2.5616 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.5616 2023/02/17 12:57:39 - mmengine - INFO - Epoch(train) [5][ 540/1320] lr: 2.0000e-02 eta: 8:08:53 time: 0.4802 data_time: 0.0154 memory: 27031 grad_norm: 4.3637 loss: 2.5166 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.5166 2023/02/17 12:57:49 - mmengine - INFO - Epoch(train) [5][ 560/1320] lr: 2.0000e-02 eta: 8:08:42 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 4.3808 loss: 2.3544 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3544 2023/02/17 12:57:58 - mmengine - INFO - Epoch(train) [5][ 580/1320] lr: 2.0000e-02 eta: 8:08:31 time: 0.4808 data_time: 0.0156 memory: 27031 grad_norm: 4.2716 loss: 2.7178 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.7178 2023/02/17 12:58:08 - mmengine - INFO - Epoch(train) [5][ 600/1320] lr: 2.0000e-02 eta: 8:08:20 time: 0.4804 data_time: 0.0153 memory: 27031 grad_norm: 4.4159 loss: 2.5188 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.5188 2023/02/17 12:58:18 - mmengine - INFO - Epoch(train) [5][ 620/1320] lr: 2.0000e-02 eta: 8:08:09 time: 0.4811 data_time: 0.0160 memory: 27031 grad_norm: 4.2864 loss: 2.6300 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.6300 2023/02/17 12:58:27 - mmengine - INFO - Epoch(train) [5][ 640/1320] lr: 2.0000e-02 eta: 8:07:58 time: 0.4810 data_time: 0.0163 memory: 27031 grad_norm: 4.4103 loss: 2.5171 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.5171 2023/02/17 12:58:37 - mmengine - INFO - Epoch(train) [5][ 660/1320] lr: 2.0000e-02 eta: 8:07:47 time: 0.4817 data_time: 0.0163 memory: 27031 grad_norm: 4.3025 loss: 2.4817 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.4817 2023/02/17 12:58:46 - mmengine - INFO - Epoch(train) [5][ 680/1320] lr: 2.0000e-02 eta: 8:07:36 time: 0.4806 data_time: 0.0155 memory: 27031 grad_norm: 4.2701 loss: 2.5558 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.5558 2023/02/17 12:58:56 - mmengine - INFO - Epoch(train) [5][ 700/1320] lr: 2.0000e-02 eta: 8:07:25 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 4.4024 loss: 2.4768 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.4768 2023/02/17 12:59:06 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 12:59:06 - mmengine - INFO - Epoch(train) [5][ 720/1320] lr: 2.0000e-02 eta: 8:07:13 time: 0.4806 data_time: 0.0152 memory: 27031 grad_norm: 4.3313 loss: 2.4557 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.4557 2023/02/17 12:59:15 - mmengine - INFO - Epoch(train) [5][ 740/1320] lr: 2.0000e-02 eta: 8:07:02 time: 0.4806 data_time: 0.0153 memory: 27031 grad_norm: 4.3455 loss: 2.7097 top1_acc: 0.3125 top5_acc: 0.3750 loss_cls: 2.7097 2023/02/17 12:59:25 - mmengine - INFO - Epoch(train) [5][ 760/1320] lr: 2.0000e-02 eta: 8:06:51 time: 0.4815 data_time: 0.0157 memory: 27031 grad_norm: 4.3214 loss: 2.5379 top1_acc: 0.4375 top5_acc: 0.4375 loss_cls: 2.5379 2023/02/17 12:59:35 - mmengine - INFO - Epoch(train) [5][ 780/1320] lr: 2.0000e-02 eta: 8:06:40 time: 0.4807 data_time: 0.0160 memory: 27031 grad_norm: 4.2703 loss: 2.3484 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.3484 2023/02/17 12:59:44 - mmengine - INFO - Epoch(train) [5][ 800/1320] lr: 2.0000e-02 eta: 8:06:29 time: 0.4807 data_time: 0.0157 memory: 27031 grad_norm: 4.1729 loss: 2.8603 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 2.8603 2023/02/17 12:59:54 - mmengine - INFO - Epoch(train) [5][ 820/1320] lr: 2.0000e-02 eta: 8:06:18 time: 0.4809 data_time: 0.0163 memory: 27031 grad_norm: 4.2297 loss: 2.6213 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.6213 2023/02/17 13:00:03 - mmengine - INFO - Epoch(train) [5][ 840/1320] lr: 2.0000e-02 eta: 8:06:07 time: 0.4805 data_time: 0.0156 memory: 27031 grad_norm: 4.3362 loss: 2.5685 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.5685 2023/02/17 13:00:13 - mmengine - INFO - Epoch(train) [5][ 860/1320] lr: 2.0000e-02 eta: 8:05:56 time: 0.4804 data_time: 0.0157 memory: 27031 grad_norm: 4.3156 loss: 2.3506 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.3506 2023/02/17 13:00:23 - mmengine - INFO - Epoch(train) [5][ 880/1320] lr: 2.0000e-02 eta: 8:05:45 time: 0.4797 data_time: 0.0155 memory: 27031 grad_norm: 4.4186 loss: 2.5955 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.5955 2023/02/17 13:00:32 - mmengine - INFO - Epoch(train) [5][ 900/1320] lr: 2.0000e-02 eta: 8:05:34 time: 0.4808 data_time: 0.0159 memory: 27031 grad_norm: 4.3791 loss: 2.5433 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5433 2023/02/17 13:00:42 - mmengine - INFO - Epoch(train) [5][ 920/1320] lr: 2.0000e-02 eta: 8:05:23 time: 0.4804 data_time: 0.0154 memory: 27031 grad_norm: 4.2681 loss: 2.6402 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6402 2023/02/17 13:00:51 - mmengine - INFO - Epoch(train) [5][ 940/1320] lr: 2.0000e-02 eta: 8:05:12 time: 0.4809 data_time: 0.0163 memory: 27031 grad_norm: 4.2067 loss: 2.4977 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.4977 2023/02/17 13:01:01 - mmengine - INFO - Epoch(train) [5][ 960/1320] lr: 2.0000e-02 eta: 8:05:01 time: 0.4801 data_time: 0.0161 memory: 27031 grad_norm: 4.3259 loss: 2.5176 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.5176 2023/02/17 13:01:11 - mmengine - INFO - Epoch(train) [5][ 980/1320] lr: 2.0000e-02 eta: 8:04:51 time: 0.4817 data_time: 0.0158 memory: 27031 grad_norm: 4.3439 loss: 2.2505 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2505 2023/02/17 13:01:20 - mmengine - INFO - Epoch(train) [5][1000/1320] lr: 2.0000e-02 eta: 8:04:40 time: 0.4812 data_time: 0.0157 memory: 27031 grad_norm: 4.3292 loss: 2.5965 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.5965 2023/02/17 13:01:30 - mmengine - INFO - Epoch(train) [5][1020/1320] lr: 2.0000e-02 eta: 8:04:29 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.3093 loss: 2.6604 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.6604 2023/02/17 13:01:39 - mmengine - INFO - Epoch(train) [5][1040/1320] lr: 2.0000e-02 eta: 8:04:18 time: 0.4817 data_time: 0.0164 memory: 27031 grad_norm: 4.1241 loss: 2.5321 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.5321 2023/02/17 13:01:49 - mmengine - INFO - Epoch(train) [5][1060/1320] lr: 2.0000e-02 eta: 8:04:07 time: 0.4800 data_time: 0.0155 memory: 27031 grad_norm: 4.1880 loss: 2.2986 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2986 2023/02/17 13:01:59 - mmengine - INFO - Epoch(train) [5][1080/1320] lr: 2.0000e-02 eta: 8:03:56 time: 0.4800 data_time: 0.0155 memory: 27031 grad_norm: 4.2445 loss: 2.2495 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2495 2023/02/17 13:02:08 - mmengine - INFO - Epoch(train) [5][1100/1320] lr: 2.0000e-02 eta: 8:03:45 time: 0.4814 data_time: 0.0164 memory: 27031 grad_norm: 4.3672 loss: 2.5631 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.5631 2023/02/17 13:02:18 - mmengine - INFO - Epoch(train) [5][1120/1320] lr: 2.0000e-02 eta: 8:03:34 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 4.2652 loss: 2.2967 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.2967 2023/02/17 13:02:28 - mmengine - INFO - Epoch(train) [5][1140/1320] lr: 2.0000e-02 eta: 8:03:23 time: 0.4810 data_time: 0.0165 memory: 27031 grad_norm: 4.2567 loss: 2.5379 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.5379 2023/02/17 13:02:37 - mmengine - INFO - Epoch(train) [5][1160/1320] lr: 2.0000e-02 eta: 8:03:12 time: 0.4805 data_time: 0.0157 memory: 27031 grad_norm: 4.2443 loss: 2.6043 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.6043 2023/02/17 13:02:47 - mmengine - INFO - Epoch(train) [5][1180/1320] lr: 2.0000e-02 eta: 8:03:02 time: 0.4811 data_time: 0.0155 memory: 27031 grad_norm: 4.2151 loss: 2.4966 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.4966 2023/02/17 13:02:56 - mmengine - INFO - Epoch(train) [5][1200/1320] lr: 2.0000e-02 eta: 8:02:51 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 4.2661 loss: 2.5456 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5456 2023/02/17 13:03:06 - mmengine - INFO - Epoch(train) [5][1220/1320] lr: 2.0000e-02 eta: 8:02:40 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.2264 loss: 2.4942 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.4942 2023/02/17 13:03:16 - mmengine - INFO - Epoch(train) [5][1240/1320] lr: 2.0000e-02 eta: 8:02:29 time: 0.4799 data_time: 0.0161 memory: 27031 grad_norm: 4.1442 loss: 2.3511 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.3511 2023/02/17 13:03:25 - mmengine - INFO - Epoch(train) [5][1260/1320] lr: 2.0000e-02 eta: 8:02:18 time: 0.4810 data_time: 0.0161 memory: 27031 grad_norm: 4.1964 loss: 2.2897 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.2897 2023/02/17 13:03:35 - mmengine - INFO - Epoch(train) [5][1280/1320] lr: 2.0000e-02 eta: 8:02:07 time: 0.4791 data_time: 0.0147 memory: 27031 grad_norm: 4.1688 loss: 2.6210 top1_acc: 0.1250 top5_acc: 0.2500 loss_cls: 2.6210 2023/02/17 13:03:44 - mmengine - INFO - Epoch(train) [5][1300/1320] lr: 2.0000e-02 eta: 8:01:56 time: 0.4810 data_time: 0.0154 memory: 27031 grad_norm: 4.2359 loss: 2.4625 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.4625 2023/02/17 13:03:54 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:03:54 - mmengine - INFO - Epoch(train) [5][1320/1320] lr: 2.0000e-02 eta: 8:01:44 time: 0.4742 data_time: 0.0166 memory: 27031 grad_norm: 4.1982 loss: 2.3978 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 2.3978 2023/02/17 13:03:58 - mmengine - INFO - Epoch(val) [5][ 20/194] eta: 0:00:31 time: 0.1830 data_time: 0.0573 memory: 3265 2023/02/17 13:04:00 - mmengine - INFO - Epoch(val) [5][ 40/194] eta: 0:00:24 time: 0.1367 data_time: 0.0131 memory: 3265 2023/02/17 13:04:03 - mmengine - INFO - Epoch(val) [5][ 60/194] eta: 0:00:20 time: 0.1374 data_time: 0.0131 memory: 3265 2023/02/17 13:04:06 - mmengine - INFO - Epoch(val) [5][ 80/194] eta: 0:00:16 time: 0.1372 data_time: 0.0133 memory: 3265 2023/02/17 13:04:09 - mmengine - INFO - Epoch(val) [5][100/194] eta: 0:00:13 time: 0.1364 data_time: 0.0130 memory: 3265 2023/02/17 13:04:11 - mmengine - INFO - Epoch(val) [5][120/194] eta: 0:00:10 time: 0.1362 data_time: 0.0125 memory: 3265 2023/02/17 13:04:14 - mmengine - INFO - Epoch(val) [5][140/194] eta: 0:00:07 time: 0.1366 data_time: 0.0129 memory: 3265 2023/02/17 13:04:17 - mmengine - INFO - Epoch(val) [5][160/194] eta: 0:00:04 time: 0.1393 data_time: 0.0146 memory: 3265 2023/02/17 13:04:20 - mmengine - INFO - Epoch(val) [5][180/194] eta: 0:00:01 time: 0.1366 data_time: 0.0131 memory: 3265 2023/02/17 13:04:22 - mmengine - INFO - Epoch(val) [5][194/194] acc/top1: 0.3555 acc/top5: 0.6577 acc/mean1: 0.2886 2023/02/17 13:04:33 - mmengine - INFO - Epoch(train) [6][ 20/1320] lr: 2.0000e-02 eta: 8:01:42 time: 0.5295 data_time: 0.0558 memory: 27031 grad_norm: 4.2480 loss: 2.3372 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.3372 2023/02/17 13:04:43 - mmengine - INFO - Epoch(train) [6][ 40/1320] lr: 2.0000e-02 eta: 8:01:31 time: 0.4793 data_time: 0.0152 memory: 27031 grad_norm: 4.1620 loss: 2.3670 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.3670 2023/02/17 13:04:52 - mmengine - INFO - Epoch(train) [6][ 60/1320] lr: 2.0000e-02 eta: 8:01:20 time: 0.4789 data_time: 0.0153 memory: 27031 grad_norm: 4.2747 loss: 2.4001 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4001 2023/02/17 13:05:02 - mmengine - INFO - Epoch(train) [6][ 80/1320] lr: 2.0000e-02 eta: 8:01:09 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 4.2418 loss: 2.2541 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2541 2023/02/17 13:05:11 - mmengine - INFO - Epoch(train) [6][ 100/1320] lr: 2.0000e-02 eta: 8:00:58 time: 0.4799 data_time: 0.0158 memory: 27031 grad_norm: 4.1554 loss: 2.3504 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3504 2023/02/17 13:05:21 - mmengine - INFO - Epoch(train) [6][ 120/1320] lr: 2.0000e-02 eta: 8:00:47 time: 0.4794 data_time: 0.0151 memory: 27031 grad_norm: 4.1289 loss: 2.3830 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3830 2023/02/17 13:05:31 - mmengine - INFO - Epoch(train) [6][ 140/1320] lr: 2.0000e-02 eta: 8:00:36 time: 0.4806 data_time: 0.0171 memory: 27031 grad_norm: 4.2231 loss: 2.3852 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3852 2023/02/17 13:05:40 - mmengine - INFO - Epoch(train) [6][ 160/1320] lr: 2.0000e-02 eta: 8:00:25 time: 0.4803 data_time: 0.0152 memory: 27031 grad_norm: 4.3071 loss: 2.2220 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.2220 2023/02/17 13:05:50 - mmengine - INFO - Epoch(train) [6][ 180/1320] lr: 2.0000e-02 eta: 8:00:15 time: 0.4799 data_time: 0.0152 memory: 27031 grad_norm: 4.2890 loss: 2.3776 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3776 2023/02/17 13:06:00 - mmengine - INFO - Epoch(train) [6][ 200/1320] lr: 2.0000e-02 eta: 8:00:04 time: 0.4815 data_time: 0.0153 memory: 27031 grad_norm: 4.2535 loss: 2.4541 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.4541 2023/02/17 13:06:09 - mmengine - INFO - Epoch(train) [6][ 220/1320] lr: 2.0000e-02 eta: 7:59:53 time: 0.4813 data_time: 0.0171 memory: 27031 grad_norm: 4.1496 loss: 2.2992 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2992 2023/02/17 13:06:19 - mmengine - INFO - Epoch(train) [6][ 240/1320] lr: 2.0000e-02 eta: 7:59:42 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2642 loss: 2.4295 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.4295 2023/02/17 13:06:28 - mmengine - INFO - Epoch(train) [6][ 260/1320] lr: 2.0000e-02 eta: 7:59:32 time: 0.4803 data_time: 0.0155 memory: 27031 grad_norm: 4.0791 loss: 2.4609 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.4609 2023/02/17 13:06:38 - mmengine - INFO - Epoch(train) [6][ 280/1320] lr: 2.0000e-02 eta: 7:59:21 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 4.1800 loss: 2.4705 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4705 2023/02/17 13:06:48 - mmengine - INFO - Epoch(train) [6][ 300/1320] lr: 2.0000e-02 eta: 7:59:10 time: 0.4811 data_time: 0.0171 memory: 27031 grad_norm: 4.2388 loss: 2.3601 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3601 2023/02/17 13:06:57 - mmengine - INFO - Epoch(train) [6][ 320/1320] lr: 2.0000e-02 eta: 7:58:59 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.1457 loss: 2.3279 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3279 2023/02/17 13:07:07 - mmengine - INFO - Epoch(train) [6][ 340/1320] lr: 2.0000e-02 eta: 7:58:48 time: 0.4801 data_time: 0.0152 memory: 27031 grad_norm: 4.0603 loss: 2.2920 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.2920 2023/02/17 13:07:16 - mmengine - INFO - Epoch(train) [6][ 360/1320] lr: 2.0000e-02 eta: 7:58:38 time: 0.4817 data_time: 0.0167 memory: 27031 grad_norm: 4.3402 loss: 2.2289 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.2289 2023/02/17 13:07:26 - mmengine - INFO - Epoch(train) [6][ 380/1320] lr: 2.0000e-02 eta: 7:58:27 time: 0.4806 data_time: 0.0155 memory: 27031 grad_norm: 4.3848 loss: 2.3250 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.3250 2023/02/17 13:07:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:07:36 - mmengine - INFO - Epoch(train) [6][ 400/1320] lr: 2.0000e-02 eta: 7:58:16 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 4.2273 loss: 2.2103 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2103 2023/02/17 13:07:45 - mmengine - INFO - Epoch(train) [6][ 420/1320] lr: 2.0000e-02 eta: 7:58:06 time: 0.4806 data_time: 0.0155 memory: 27031 grad_norm: 4.2394 loss: 2.3590 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.3590 2023/02/17 13:07:55 - mmengine - INFO - Epoch(train) [6][ 440/1320] lr: 2.0000e-02 eta: 7:57:55 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.2182 loss: 2.4944 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.4944 2023/02/17 13:08:04 - mmengine - INFO - Epoch(train) [6][ 460/1320] lr: 2.0000e-02 eta: 7:57:44 time: 0.4804 data_time: 0.0160 memory: 27031 grad_norm: 4.2177 loss: 2.3910 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3910 2023/02/17 13:08:14 - mmengine - INFO - Epoch(train) [6][ 480/1320] lr: 2.0000e-02 eta: 7:57:34 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 4.1254 loss: 2.2895 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.2895 2023/02/17 13:08:24 - mmengine - INFO - Epoch(train) [6][ 500/1320] lr: 2.0000e-02 eta: 7:57:23 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 4.3224 loss: 2.5510 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5510 2023/02/17 13:08:33 - mmengine - INFO - Epoch(train) [6][ 520/1320] lr: 2.0000e-02 eta: 7:57:13 time: 0.4823 data_time: 0.0158 memory: 27031 grad_norm: 4.2025 loss: 2.4606 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.4606 2023/02/17 13:08:43 - mmengine - INFO - Epoch(train) [6][ 540/1320] lr: 2.0000e-02 eta: 7:57:02 time: 0.4798 data_time: 0.0152 memory: 27031 grad_norm: 4.1498 loss: 2.4300 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.4300 2023/02/17 13:08:53 - mmengine - INFO - Epoch(train) [6][ 560/1320] lr: 2.0000e-02 eta: 7:56:51 time: 0.4805 data_time: 0.0157 memory: 27031 grad_norm: 4.1467 loss: 2.3188 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.3188 2023/02/17 13:09:02 - mmengine - INFO - Epoch(train) [6][ 580/1320] lr: 2.0000e-02 eta: 7:56:40 time: 0.4811 data_time: 0.0162 memory: 27031 grad_norm: 4.1992 loss: 2.3658 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.3658 2023/02/17 13:09:12 - mmengine - INFO - Epoch(train) [6][ 600/1320] lr: 2.0000e-02 eta: 7:56:30 time: 0.4804 data_time: 0.0156 memory: 27031 grad_norm: 4.2205 loss: 2.5180 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5180 2023/02/17 13:09:21 - mmengine - INFO - Epoch(train) [6][ 620/1320] lr: 2.0000e-02 eta: 7:56:19 time: 0.4811 data_time: 0.0158 memory: 27031 grad_norm: 4.1669 loss: 2.5178 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5178 2023/02/17 13:09:31 - mmengine - INFO - Epoch(train) [6][ 640/1320] lr: 2.0000e-02 eta: 7:56:09 time: 0.4821 data_time: 0.0157 memory: 27031 grad_norm: 4.1798 loss: 2.2283 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2283 2023/02/17 13:09:41 - mmengine - INFO - Epoch(train) [6][ 660/1320] lr: 2.0000e-02 eta: 7:55:58 time: 0.4810 data_time: 0.0150 memory: 27031 grad_norm: 4.3315 loss: 2.4970 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.4970 2023/02/17 13:09:50 - mmengine - INFO - Epoch(train) [6][ 680/1320] lr: 2.0000e-02 eta: 7:55:48 time: 0.4815 data_time: 0.0164 memory: 27031 grad_norm: 4.1870 loss: 2.4946 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.4946 2023/02/17 13:10:00 - mmengine - INFO - Epoch(train) [6][ 700/1320] lr: 2.0000e-02 eta: 7:55:37 time: 0.4802 data_time: 0.0153 memory: 27031 grad_norm: 4.1608 loss: 2.3889 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.3889 2023/02/17 13:10:09 - mmengine - INFO - Epoch(train) [6][ 720/1320] lr: 2.0000e-02 eta: 7:55:26 time: 0.4802 data_time: 0.0154 memory: 27031 grad_norm: 4.2442 loss: 2.3637 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.3637 2023/02/17 13:10:19 - mmengine - INFO - Epoch(train) [6][ 740/1320] lr: 2.0000e-02 eta: 7:55:16 time: 0.4808 data_time: 0.0157 memory: 27031 grad_norm: 4.3031 loss: 2.3198 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3198 2023/02/17 13:10:29 - mmengine - INFO - Epoch(train) [6][ 760/1320] lr: 2.0000e-02 eta: 7:55:05 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 4.2832 loss: 2.5217 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.5217 2023/02/17 13:10:38 - mmengine - INFO - Epoch(train) [6][ 780/1320] lr: 2.0000e-02 eta: 7:54:55 time: 0.4821 data_time: 0.0164 memory: 27031 grad_norm: 4.0860 loss: 2.0444 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0444 2023/02/17 13:10:48 - mmengine - INFO - Epoch(train) [6][ 800/1320] lr: 2.0000e-02 eta: 7:54:44 time: 0.4813 data_time: 0.0161 memory: 27031 grad_norm: 4.3472 loss: 2.2976 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2976 2023/02/17 13:10:58 - mmengine - INFO - Epoch(train) [6][ 820/1320] lr: 2.0000e-02 eta: 7:54:34 time: 0.4807 data_time: 0.0151 memory: 27031 grad_norm: 4.2382 loss: 2.3202 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.3202 2023/02/17 13:11:07 - mmengine - INFO - Epoch(train) [6][ 840/1320] lr: 2.0000e-02 eta: 7:54:24 time: 0.4835 data_time: 0.0177 memory: 27031 grad_norm: 4.2466 loss: 2.1367 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.1367 2023/02/17 13:11:17 - mmengine - INFO - Epoch(train) [6][ 860/1320] lr: 2.0000e-02 eta: 7:54:13 time: 0.4818 data_time: 0.0157 memory: 27031 grad_norm: 4.0872 loss: 2.4124 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.4124 2023/02/17 13:11:26 - mmengine - INFO - Epoch(train) [6][ 880/1320] lr: 2.0000e-02 eta: 7:54:03 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.1452 loss: 2.4594 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.4594 2023/02/17 13:11:36 - mmengine - INFO - Epoch(train) [6][ 900/1320] lr: 2.0000e-02 eta: 7:53:52 time: 0.4794 data_time: 0.0151 memory: 27031 grad_norm: 4.1276 loss: 2.4380 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 2.4380 2023/02/17 13:11:46 - mmengine - INFO - Epoch(train) [6][ 920/1320] lr: 2.0000e-02 eta: 7:53:41 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.1827 loss: 2.3895 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3895 2023/02/17 13:11:55 - mmengine - INFO - Epoch(train) [6][ 940/1320] lr: 2.0000e-02 eta: 7:53:30 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 4.2417 loss: 2.2672 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2672 2023/02/17 13:12:05 - mmengine - INFO - Epoch(train) [6][ 960/1320] lr: 2.0000e-02 eta: 7:53:20 time: 0.4797 data_time: 0.0155 memory: 27031 grad_norm: 3.9640 loss: 2.3218 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.3218 2023/02/17 13:12:14 - mmengine - INFO - Epoch(train) [6][ 980/1320] lr: 2.0000e-02 eta: 7:53:09 time: 0.4797 data_time: 0.0153 memory: 27031 grad_norm: 4.1727 loss: 1.9716 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9716 2023/02/17 13:12:24 - mmengine - INFO - Epoch(train) [6][1000/1320] lr: 2.0000e-02 eta: 7:52:58 time: 0.4803 data_time: 0.0159 memory: 27031 grad_norm: 4.2593 loss: 2.3006 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.3006 2023/02/17 13:12:34 - mmengine - INFO - Epoch(train) [6][1020/1320] lr: 2.0000e-02 eta: 7:52:48 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.1325 loss: 2.2692 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.2692 2023/02/17 13:12:43 - mmengine - INFO - Epoch(train) [6][1040/1320] lr: 2.0000e-02 eta: 7:52:37 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.1772 loss: 2.3081 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3081 2023/02/17 13:12:53 - mmengine - INFO - Epoch(train) [6][1060/1320] lr: 2.0000e-02 eta: 7:52:27 time: 0.4808 data_time: 0.0159 memory: 27031 grad_norm: 4.1854 loss: 2.2396 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2396 2023/02/17 13:13:02 - mmengine - INFO - Epoch(train) [6][1080/1320] lr: 2.0000e-02 eta: 7:52:16 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.1350 loss: 2.3473 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.3473 2023/02/17 13:13:12 - mmengine - INFO - Epoch(train) [6][1100/1320] lr: 2.0000e-02 eta: 7:52:05 time: 0.4797 data_time: 0.0157 memory: 27031 grad_norm: 4.2483 loss: 2.3570 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.3570 2023/02/17 13:13:22 - mmengine - INFO - Epoch(train) [6][1120/1320] lr: 2.0000e-02 eta: 7:51:55 time: 0.4813 data_time: 0.0151 memory: 27031 grad_norm: 4.1815 loss: 2.4363 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.4363 2023/02/17 13:13:31 - mmengine - INFO - Epoch(train) [6][1140/1320] lr: 2.0000e-02 eta: 7:51:44 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.2617 loss: 2.3406 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3406 2023/02/17 13:13:41 - mmengine - INFO - Epoch(train) [6][1160/1320] lr: 2.0000e-02 eta: 7:51:34 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 4.2131 loss: 2.3474 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3474 2023/02/17 13:13:51 - mmengine - INFO - Epoch(train) [6][1180/1320] lr: 2.0000e-02 eta: 7:51:23 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.1444 loss: 2.2729 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.2729 2023/02/17 13:14:00 - mmengine - INFO - Epoch(train) [6][1200/1320] lr: 2.0000e-02 eta: 7:51:12 time: 0.4791 data_time: 0.0148 memory: 27031 grad_norm: 4.1747 loss: 2.3640 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.3640 2023/02/17 13:14:10 - mmengine - INFO - Epoch(train) [6][1220/1320] lr: 2.0000e-02 eta: 7:51:02 time: 0.4812 data_time: 0.0164 memory: 27031 grad_norm: 4.2446 loss: 2.3730 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3730 2023/02/17 13:14:19 - mmengine - INFO - Epoch(train) [6][1240/1320] lr: 2.0000e-02 eta: 7:50:51 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.2527 loss: 2.2177 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2177 2023/02/17 13:14:29 - mmengine - INFO - Epoch(train) [6][1260/1320] lr: 2.0000e-02 eta: 7:50:41 time: 0.4813 data_time: 0.0165 memory: 27031 grad_norm: 4.1526 loss: 2.3230 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3230 2023/02/17 13:14:39 - mmengine - INFO - Epoch(train) [6][1280/1320] lr: 2.0000e-02 eta: 7:50:30 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.1326 loss: 2.4371 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.4371 2023/02/17 13:14:48 - mmengine - INFO - Epoch(train) [6][1300/1320] lr: 2.0000e-02 eta: 7:50:20 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 4.1607 loss: 2.4217 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.4217 2023/02/17 13:14:58 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:14:58 - mmengine - INFO - Epoch(train) [6][1320/1320] lr: 2.0000e-02 eta: 7:50:08 time: 0.4741 data_time: 0.0161 memory: 27031 grad_norm: 4.0942 loss: 2.2534 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 2.2534 2023/02/17 13:14:58 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/02/17 13:15:03 - mmengine - INFO - Epoch(val) [6][ 20/194] eta: 0:00:32 time: 0.1875 data_time: 0.0599 memory: 3265 2023/02/17 13:15:05 - mmengine - INFO - Epoch(val) [6][ 40/194] eta: 0:00:24 time: 0.1359 data_time: 0.0115 memory: 3265 2023/02/17 13:15:08 - mmengine - INFO - Epoch(val) [6][ 60/194] eta: 0:00:20 time: 0.1385 data_time: 0.0142 memory: 3265 2023/02/17 13:15:11 - mmengine - INFO - Epoch(val) [6][ 80/194] eta: 0:00:17 time: 0.1372 data_time: 0.0133 memory: 3265 2023/02/17 13:15:14 - mmengine - INFO - Epoch(val) [6][100/194] eta: 0:00:13 time: 0.1384 data_time: 0.0135 memory: 3265 2023/02/17 13:15:16 - mmengine - INFO - Epoch(val) [6][120/194] eta: 0:00:10 time: 0.1371 data_time: 0.0130 memory: 3265 2023/02/17 13:15:19 - mmengine - INFO - Epoch(val) [6][140/194] eta: 0:00:07 time: 0.1385 data_time: 0.0142 memory: 3265 2023/02/17 13:15:22 - mmengine - INFO - Epoch(val) [6][160/194] eta: 0:00:04 time: 0.1383 data_time: 0.0138 memory: 3265 2023/02/17 13:15:25 - mmengine - INFO - Epoch(val) [6][180/194] eta: 0:00:02 time: 0.1361 data_time: 0.0122 memory: 3265 2023/02/17 13:15:27 - mmengine - INFO - Epoch(val) [6][194/194] acc/top1: 0.3985 acc/top5: 0.6974 acc/mean1: 0.3306 2023/02/17 13:15:27 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_4.pth is removed 2023/02/17 13:15:28 - mmengine - INFO - The best checkpoint with 0.3985 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2023/02/17 13:15:39 - mmengine - INFO - Epoch(train) [7][ 20/1320] lr: 2.0000e-02 eta: 7:50:05 time: 0.5283 data_time: 0.0577 memory: 27031 grad_norm: 4.0201 loss: 2.2012 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2012 2023/02/17 13:15:48 - mmengine - INFO - Epoch(train) [7][ 40/1320] lr: 2.0000e-02 eta: 7:49:54 time: 0.4790 data_time: 0.0143 memory: 27031 grad_norm: 4.2066 loss: 2.3324 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.3324 2023/02/17 13:15:58 - mmengine - INFO - Epoch(train) [7][ 60/1320] lr: 2.0000e-02 eta: 7:49:43 time: 0.4787 data_time: 0.0145 memory: 27031 grad_norm: 4.0915 loss: 2.3131 top1_acc: 0.5625 top5_acc: 0.5625 loss_cls: 2.3131 2023/02/17 13:16:07 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:16:07 - mmengine - INFO - Epoch(train) [7][ 80/1320] lr: 2.0000e-02 eta: 7:49:33 time: 0.4790 data_time: 0.0145 memory: 27031 grad_norm: 4.3241 loss: 2.2767 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2767 2023/02/17 13:16:17 - mmengine - INFO - Epoch(train) [7][ 100/1320] lr: 2.0000e-02 eta: 7:49:22 time: 0.4794 data_time: 0.0156 memory: 27031 grad_norm: 4.1074 loss: 2.2282 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2282 2023/02/17 13:16:27 - mmengine - INFO - Epoch(train) [7][ 120/1320] lr: 2.0000e-02 eta: 7:49:12 time: 0.4803 data_time: 0.0157 memory: 27031 grad_norm: 4.0366 loss: 2.1416 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1416 2023/02/17 13:16:36 - mmengine - INFO - Epoch(train) [7][ 140/1320] lr: 2.0000e-02 eta: 7:49:01 time: 0.4802 data_time: 0.0156 memory: 27031 grad_norm: 4.2341 loss: 2.3676 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 2.3676 2023/02/17 13:16:46 - mmengine - INFO - Epoch(train) [7][ 160/1320] lr: 2.0000e-02 eta: 7:48:51 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 4.1762 loss: 2.0966 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.0966 2023/02/17 13:16:55 - mmengine - INFO - Epoch(train) [7][ 180/1320] lr: 2.0000e-02 eta: 7:48:40 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.2450 loss: 2.3430 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.3430 2023/02/17 13:17:05 - mmengine - INFO - Epoch(train) [7][ 200/1320] lr: 2.0000e-02 eta: 7:48:30 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.1556 loss: 2.0994 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0994 2023/02/17 13:17:15 - mmengine - INFO - Epoch(train) [7][ 220/1320] lr: 2.0000e-02 eta: 7:48:19 time: 0.4799 data_time: 0.0160 memory: 27031 grad_norm: 4.2262 loss: 2.3450 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3450 2023/02/17 13:17:24 - mmengine - INFO - Epoch(train) [7][ 240/1320] lr: 2.0000e-02 eta: 7:48:09 time: 0.4804 data_time: 0.0155 memory: 27031 grad_norm: 4.1942 loss: 2.1920 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1920 2023/02/17 13:17:34 - mmengine - INFO - Epoch(train) [7][ 260/1320] lr: 2.0000e-02 eta: 7:47:58 time: 0.4803 data_time: 0.0156 memory: 27031 grad_norm: 4.1722 loss: 2.1201 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1201 2023/02/17 13:17:43 - mmengine - INFO - Epoch(train) [7][ 280/1320] lr: 2.0000e-02 eta: 7:47:48 time: 0.4802 data_time: 0.0153 memory: 27031 grad_norm: 4.2257 loss: 2.3035 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3035 2023/02/17 13:17:53 - mmengine - INFO - Epoch(train) [7][ 300/1320] lr: 2.0000e-02 eta: 7:47:37 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.2059 loss: 2.5155 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.5155 2023/02/17 13:18:03 - mmengine - INFO - Epoch(train) [7][ 320/1320] lr: 2.0000e-02 eta: 7:47:26 time: 0.4798 data_time: 0.0154 memory: 27031 grad_norm: 4.2580 loss: 2.2860 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2860 2023/02/17 13:18:12 - mmengine - INFO - Epoch(train) [7][ 340/1320] lr: 2.0000e-02 eta: 7:47:16 time: 0.4794 data_time: 0.0134 memory: 27031 grad_norm: 4.2398 loss: 2.3534 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 2.3534 2023/02/17 13:18:22 - mmengine - INFO - Epoch(train) [7][ 360/1320] lr: 2.0000e-02 eta: 7:47:05 time: 0.4794 data_time: 0.0145 memory: 27031 grad_norm: 4.2292 loss: 2.1204 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 2.1204 2023/02/17 13:18:31 - mmengine - INFO - Epoch(train) [7][ 380/1320] lr: 2.0000e-02 eta: 7:46:55 time: 0.4806 data_time: 0.0156 memory: 27031 grad_norm: 4.1043 loss: 2.2122 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.2122 2023/02/17 13:18:41 - mmengine - INFO - Epoch(train) [7][ 400/1320] lr: 2.0000e-02 eta: 7:46:44 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.1743 loss: 2.1439 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.1439 2023/02/17 13:18:51 - mmengine - INFO - Epoch(train) [7][ 420/1320] lr: 2.0000e-02 eta: 7:46:34 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.1397 loss: 2.4379 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.4379 2023/02/17 13:19:00 - mmengine - INFO - Epoch(train) [7][ 440/1320] lr: 2.0000e-02 eta: 7:46:23 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.1917 loss: 2.2320 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2320 2023/02/17 13:19:10 - mmengine - INFO - Epoch(train) [7][ 460/1320] lr: 2.0000e-02 eta: 7:46:13 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 4.1877 loss: 2.3020 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3020 2023/02/17 13:19:19 - mmengine - INFO - Epoch(train) [7][ 480/1320] lr: 2.0000e-02 eta: 7:46:03 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.3525 loss: 2.3516 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.3516 2023/02/17 13:19:29 - mmengine - INFO - Epoch(train) [7][ 500/1320] lr: 2.0000e-02 eta: 7:45:52 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.1785 loss: 2.2896 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2896 2023/02/17 13:19:39 - mmengine - INFO - Epoch(train) [7][ 520/1320] lr: 2.0000e-02 eta: 7:45:42 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.2630 loss: 2.2594 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.2594 2023/02/17 13:19:48 - mmengine - INFO - Epoch(train) [7][ 540/1320] lr: 2.0000e-02 eta: 7:45:31 time: 0.4808 data_time: 0.0157 memory: 27031 grad_norm: 4.1761 loss: 2.2351 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2351 2023/02/17 13:19:58 - mmengine - INFO - Epoch(train) [7][ 560/1320] lr: 2.0000e-02 eta: 7:45:21 time: 0.4792 data_time: 0.0144 memory: 27031 grad_norm: 4.1524 loss: 2.3017 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3017 2023/02/17 13:20:07 - mmengine - INFO - Epoch(train) [7][ 580/1320] lr: 2.0000e-02 eta: 7:45:10 time: 0.4803 data_time: 0.0154 memory: 27031 grad_norm: 4.0605 loss: 2.3242 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3242 2023/02/17 13:20:17 - mmengine - INFO - Epoch(train) [7][ 600/1320] lr: 2.0000e-02 eta: 7:45:00 time: 0.4802 data_time: 0.0155 memory: 27031 grad_norm: 4.2729 loss: 2.1275 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1275 2023/02/17 13:20:27 - mmengine - INFO - Epoch(train) [7][ 620/1320] lr: 2.0000e-02 eta: 7:44:49 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.2379 loss: 2.3194 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3194 2023/02/17 13:20:36 - mmengine - INFO - Epoch(train) [7][ 640/1320] lr: 2.0000e-02 eta: 7:44:39 time: 0.4819 data_time: 0.0168 memory: 27031 grad_norm: 4.1545 loss: 2.0623 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0623 2023/02/17 13:20:46 - mmengine - INFO - Epoch(train) [7][ 660/1320] lr: 2.0000e-02 eta: 7:44:29 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.1045 loss: 2.2577 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 2.2577 2023/02/17 13:20:55 - mmengine - INFO - Epoch(train) [7][ 680/1320] lr: 2.0000e-02 eta: 7:44:18 time: 0.4796 data_time: 0.0153 memory: 27031 grad_norm: 4.0991 loss: 2.2882 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.2882 2023/02/17 13:21:05 - mmengine - INFO - Epoch(train) [7][ 700/1320] lr: 2.0000e-02 eta: 7:44:08 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 4.1911 loss: 2.0979 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0979 2023/02/17 13:21:15 - mmengine - INFO - Epoch(train) [7][ 720/1320] lr: 2.0000e-02 eta: 7:43:57 time: 0.4792 data_time: 0.0149 memory: 27031 grad_norm: 4.1011 loss: 2.3389 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.3389 2023/02/17 13:21:24 - mmengine - INFO - Epoch(train) [7][ 740/1320] lr: 2.0000e-02 eta: 7:43:47 time: 0.4798 data_time: 0.0150 memory: 27031 grad_norm: 4.2478 loss: 2.1632 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1632 2023/02/17 13:21:34 - mmengine - INFO - Epoch(train) [7][ 760/1320] lr: 2.0000e-02 eta: 7:43:37 time: 0.4803 data_time: 0.0154 memory: 27031 grad_norm: 4.2015 loss: 2.2743 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2743 2023/02/17 13:21:43 - mmengine - INFO - Epoch(train) [7][ 780/1320] lr: 2.0000e-02 eta: 7:43:26 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.3234 loss: 2.4131 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.4131 2023/02/17 13:21:53 - mmengine - INFO - Epoch(train) [7][ 800/1320] lr: 2.0000e-02 eta: 7:43:16 time: 0.4794 data_time: 0.0150 memory: 27031 grad_norm: 4.1904 loss: 2.1517 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.1517 2023/02/17 13:22:03 - mmengine - INFO - Epoch(train) [7][ 820/1320] lr: 2.0000e-02 eta: 7:43:05 time: 0.4792 data_time: 0.0148 memory: 27031 grad_norm: 4.1502 loss: 2.2802 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2802 2023/02/17 13:22:12 - mmengine - INFO - Epoch(train) [7][ 840/1320] lr: 2.0000e-02 eta: 7:42:55 time: 0.4800 data_time: 0.0155 memory: 27031 grad_norm: 4.1121 loss: 2.0986 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0986 2023/02/17 13:22:22 - mmengine - INFO - Epoch(train) [7][ 860/1320] lr: 2.0000e-02 eta: 7:42:44 time: 0.4808 data_time: 0.0153 memory: 27031 grad_norm: 4.1704 loss: 2.3831 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3831 2023/02/17 13:22:34 - mmengine - INFO - Epoch(train) [7][ 880/1320] lr: 2.0000e-02 eta: 7:42:49 time: 0.5922 data_time: 0.0152 memory: 27031 grad_norm: 4.2550 loss: 2.1827 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1827 2023/02/17 13:22:43 - mmengine - INFO - Epoch(train) [7][ 900/1320] lr: 2.0000e-02 eta: 7:42:38 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.1231 loss: 2.1696 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1696 2023/02/17 13:22:53 - mmengine - INFO - Epoch(train) [7][ 920/1320] lr: 2.0000e-02 eta: 7:42:28 time: 0.4807 data_time: 0.0157 memory: 27031 grad_norm: 4.2490 loss: 2.2903 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2903 2023/02/17 13:23:02 - mmengine - INFO - Epoch(train) [7][ 940/1320] lr: 2.0000e-02 eta: 7:42:17 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.1076 loss: 2.1602 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.1602 2023/02/17 13:23:12 - mmengine - INFO - Epoch(train) [7][ 960/1320] lr: 2.0000e-02 eta: 7:42:07 time: 0.4799 data_time: 0.0155 memory: 27031 grad_norm: 4.1238 loss: 2.0853 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0853 2023/02/17 13:23:22 - mmengine - INFO - Epoch(train) [7][ 980/1320] lr: 2.0000e-02 eta: 7:41:57 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.4136 loss: 2.1651 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.1651 2023/02/17 13:23:31 - mmengine - INFO - Epoch(train) [7][1000/1320] lr: 2.0000e-02 eta: 7:41:46 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 4.2670 loss: 2.1956 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1956 2023/02/17 13:23:41 - mmengine - INFO - Epoch(train) [7][1020/1320] lr: 2.0000e-02 eta: 7:41:36 time: 0.4805 data_time: 0.0155 memory: 27031 grad_norm: 4.2264 loss: 2.2560 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2560 2023/02/17 13:23:50 - mmengine - INFO - Epoch(train) [7][1040/1320] lr: 2.0000e-02 eta: 7:41:26 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.2095 loss: 2.1581 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1581 2023/02/17 13:24:00 - mmengine - INFO - Epoch(train) [7][1060/1320] lr: 2.0000e-02 eta: 7:41:15 time: 0.4814 data_time: 0.0157 memory: 27031 grad_norm: 4.2150 loss: 2.2364 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.2364 2023/02/17 13:24:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:24:10 - mmengine - INFO - Epoch(train) [7][1080/1320] lr: 2.0000e-02 eta: 7:41:05 time: 0.4810 data_time: 0.0164 memory: 27031 grad_norm: 4.1004 loss: 2.2171 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2171 2023/02/17 13:24:19 - mmengine - INFO - Epoch(train) [7][1100/1320] lr: 2.0000e-02 eta: 7:40:55 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.2337 loss: 2.3799 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 2.3799 2023/02/17 13:24:29 - mmengine - INFO - Epoch(train) [7][1120/1320] lr: 2.0000e-02 eta: 7:40:44 time: 0.4795 data_time: 0.0149 memory: 27031 grad_norm: 4.0901 loss: 2.4687 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4687 2023/02/17 13:24:38 - mmengine - INFO - Epoch(train) [7][1140/1320] lr: 2.0000e-02 eta: 7:40:34 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 4.1040 loss: 2.1281 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1281 2023/02/17 13:24:48 - mmengine - INFO - Epoch(train) [7][1160/1320] lr: 2.0000e-02 eta: 7:40:23 time: 0.4794 data_time: 0.0150 memory: 27031 grad_norm: 4.2374 loss: 2.3025 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.3025 2023/02/17 13:24:58 - mmengine - INFO - Epoch(train) [7][1180/1320] lr: 2.0000e-02 eta: 7:40:13 time: 0.4801 data_time: 0.0152 memory: 27031 grad_norm: 4.1546 loss: 2.0909 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0909 2023/02/17 13:25:07 - mmengine - INFO - Epoch(train) [7][1200/1320] lr: 2.0000e-02 eta: 7:40:03 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.0783 loss: 2.0817 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0817 2023/02/17 13:25:17 - mmengine - INFO - Epoch(train) [7][1220/1320] lr: 2.0000e-02 eta: 7:39:52 time: 0.4801 data_time: 0.0151 memory: 27031 grad_norm: 4.0849 loss: 2.4158 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.4158 2023/02/17 13:25:27 - mmengine - INFO - Epoch(train) [7][1240/1320] lr: 2.0000e-02 eta: 7:39:42 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.1467 loss: 2.2426 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2426 2023/02/17 13:25:36 - mmengine - INFO - Epoch(train) [7][1260/1320] lr: 2.0000e-02 eta: 7:39:32 time: 0.4807 data_time: 0.0161 memory: 27031 grad_norm: 4.1337 loss: 2.2588 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2588 2023/02/17 13:25:46 - mmengine - INFO - Epoch(train) [7][1280/1320] lr: 2.0000e-02 eta: 7:39:22 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.0864 loss: 2.3756 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3756 2023/02/17 13:25:55 - mmengine - INFO - Epoch(train) [7][1300/1320] lr: 2.0000e-02 eta: 7:39:11 time: 0.4801 data_time: 0.0152 memory: 27031 grad_norm: 4.2599 loss: 2.3637 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 2.3637 2023/02/17 13:26:05 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:26:05 - mmengine - INFO - Epoch(train) [7][1320/1320] lr: 2.0000e-02 eta: 7:39:00 time: 0.4727 data_time: 0.0155 memory: 27031 grad_norm: 4.2619 loss: 2.3846 top1_acc: 0.2727 top5_acc: 0.6364 loss_cls: 2.3846 2023/02/17 13:26:08 - mmengine - INFO - Epoch(val) [7][ 20/194] eta: 0:00:32 time: 0.1851 data_time: 0.0576 memory: 3265 2023/02/17 13:26:11 - mmengine - INFO - Epoch(val) [7][ 40/194] eta: 0:00:24 time: 0.1384 data_time: 0.0143 memory: 3265 2023/02/17 13:26:14 - mmengine - INFO - Epoch(val) [7][ 60/194] eta: 0:00:20 time: 0.1377 data_time: 0.0132 memory: 3265 2023/02/17 13:26:17 - mmengine - INFO - Epoch(val) [7][ 80/194] eta: 0:00:17 time: 0.1374 data_time: 0.0131 memory: 3265 2023/02/17 13:26:20 - mmengine - INFO - Epoch(val) [7][100/194] eta: 0:00:13 time: 0.1367 data_time: 0.0128 memory: 3265 2023/02/17 13:26:22 - mmengine - INFO - Epoch(val) [7][120/194] eta: 0:00:10 time: 0.1365 data_time: 0.0131 memory: 3265 2023/02/17 13:26:25 - mmengine - INFO - Epoch(val) [7][140/194] eta: 0:00:07 time: 0.1377 data_time: 0.0130 memory: 3265 2023/02/17 13:26:28 - mmengine - INFO - Epoch(val) [7][160/194] eta: 0:00:04 time: 0.1352 data_time: 0.0126 memory: 3265 2023/02/17 13:26:30 - mmengine - INFO - Epoch(val) [7][180/194] eta: 0:00:01 time: 0.1376 data_time: 0.0132 memory: 3265 2023/02/17 13:26:33 - mmengine - INFO - Epoch(val) [7][194/194] acc/top1: 0.4204 acc/top5: 0.7239 acc/mean1: 0.3421 2023/02/17 13:26:33 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_6.pth is removed 2023/02/17 13:26:35 - mmengine - INFO - The best checkpoint with 0.4204 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2023/02/17 13:26:45 - mmengine - INFO - Epoch(train) [8][ 20/1320] lr: 2.0000e-02 eta: 7:38:55 time: 0.5269 data_time: 0.0541 memory: 27031 grad_norm: 4.1386 loss: 2.1050 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.1050 2023/02/17 13:26:55 - mmengine - INFO - Epoch(train) [8][ 40/1320] lr: 2.0000e-02 eta: 7:38:45 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.1272 loss: 2.3154 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3154 2023/02/17 13:27:04 - mmengine - INFO - Epoch(train) [8][ 60/1320] lr: 2.0000e-02 eta: 7:38:34 time: 0.4794 data_time: 0.0152 memory: 27031 grad_norm: 4.1783 loss: 2.3161 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3161 2023/02/17 13:27:14 - mmengine - INFO - Epoch(train) [8][ 80/1320] lr: 2.0000e-02 eta: 7:38:24 time: 0.4787 data_time: 0.0148 memory: 27031 grad_norm: 4.0736 loss: 1.8840 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8840 2023/02/17 13:27:23 - mmengine - INFO - Epoch(train) [8][ 100/1320] lr: 2.0000e-02 eta: 7:38:14 time: 0.4799 data_time: 0.0155 memory: 27031 grad_norm: 4.2646 loss: 2.3372 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.3372 2023/02/17 13:27:33 - mmengine - INFO - Epoch(train) [8][ 120/1320] lr: 2.0000e-02 eta: 7:38:03 time: 0.4801 data_time: 0.0156 memory: 27031 grad_norm: 4.1043 loss: 2.1097 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1097 2023/02/17 13:27:43 - mmengine - INFO - Epoch(train) [8][ 140/1320] lr: 2.0000e-02 eta: 7:37:53 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.1644 loss: 2.2132 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2132 2023/02/17 13:27:52 - mmengine - INFO - Epoch(train) [8][ 160/1320] lr: 2.0000e-02 eta: 7:37:43 time: 0.4800 data_time: 0.0153 memory: 27031 grad_norm: 4.2426 loss: 2.0759 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0759 2023/02/17 13:28:02 - mmengine - INFO - Epoch(train) [8][ 180/1320] lr: 2.0000e-02 eta: 7:37:32 time: 0.4809 data_time: 0.0155 memory: 27031 grad_norm: 4.3364 loss: 2.2926 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2926 2023/02/17 13:28:11 - mmengine - INFO - Epoch(train) [8][ 200/1320] lr: 2.0000e-02 eta: 7:37:22 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.1681 loss: 2.2674 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.2674 2023/02/17 13:28:21 - mmengine - INFO - Epoch(train) [8][ 220/1320] lr: 2.0000e-02 eta: 7:37:12 time: 0.4804 data_time: 0.0161 memory: 27031 grad_norm: 4.1166 loss: 2.1187 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 2.1187 2023/02/17 13:28:31 - mmengine - INFO - Epoch(train) [8][ 240/1320] lr: 2.0000e-02 eta: 7:37:01 time: 0.4790 data_time: 0.0140 memory: 27031 grad_norm: 4.1372 loss: 2.0801 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0801 2023/02/17 13:28:40 - mmengine - INFO - Epoch(train) [8][ 260/1320] lr: 2.0000e-02 eta: 7:36:51 time: 0.4794 data_time: 0.0150 memory: 27031 grad_norm: 4.2208 loss: 2.0929 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0929 2023/02/17 13:28:50 - mmengine - INFO - Epoch(train) [8][ 280/1320] lr: 2.0000e-02 eta: 7:36:41 time: 0.4797 data_time: 0.0151 memory: 27031 grad_norm: 4.2076 loss: 2.2791 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.2791 2023/02/17 13:28:59 - mmengine - INFO - Epoch(train) [8][ 300/1320] lr: 2.0000e-02 eta: 7:36:30 time: 0.4801 data_time: 0.0154 memory: 27031 grad_norm: 4.2222 loss: 2.1413 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1413 2023/02/17 13:29:09 - mmengine - INFO - Epoch(train) [8][ 320/1320] lr: 2.0000e-02 eta: 7:36:20 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.1056 loss: 2.1285 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.1285 2023/02/17 13:29:19 - mmengine - INFO - Epoch(train) [8][ 340/1320] lr: 2.0000e-02 eta: 7:36:10 time: 0.4805 data_time: 0.0161 memory: 27031 grad_norm: 4.0858 loss: 2.1805 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1805 2023/02/17 13:29:28 - mmengine - INFO - Epoch(train) [8][ 360/1320] lr: 2.0000e-02 eta: 7:35:59 time: 0.4786 data_time: 0.0145 memory: 27031 grad_norm: 4.2387 loss: 2.1655 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.1655 2023/02/17 13:29:38 - mmengine - INFO - Epoch(train) [8][ 380/1320] lr: 2.0000e-02 eta: 7:35:49 time: 0.4811 data_time: 0.0164 memory: 27031 grad_norm: 4.1734 loss: 2.0624 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0624 2023/02/17 13:29:47 - mmengine - INFO - Epoch(train) [8][ 400/1320] lr: 2.0000e-02 eta: 7:35:39 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.1460 loss: 2.2524 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 2.2524 2023/02/17 13:29:57 - mmengine - INFO - Epoch(train) [8][ 420/1320] lr: 2.0000e-02 eta: 7:35:28 time: 0.4789 data_time: 0.0145 memory: 27031 grad_norm: 4.2349 loss: 2.2362 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2362 2023/02/17 13:30:07 - mmengine - INFO - Epoch(train) [8][ 440/1320] lr: 2.0000e-02 eta: 7:35:18 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.0640 loss: 1.9996 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9996 2023/02/17 13:30:16 - mmengine - INFO - Epoch(train) [8][ 460/1320] lr: 2.0000e-02 eta: 7:35:08 time: 0.4797 data_time: 0.0155 memory: 27031 grad_norm: 4.2621 loss: 2.1668 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1668 2023/02/17 13:30:26 - mmengine - INFO - Epoch(train) [8][ 480/1320] lr: 2.0000e-02 eta: 7:34:57 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.1333 loss: 2.1967 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1967 2023/02/17 13:30:35 - mmengine - INFO - Epoch(train) [8][ 500/1320] lr: 2.0000e-02 eta: 7:34:47 time: 0.4790 data_time: 0.0144 memory: 27031 grad_norm: 4.1372 loss: 2.1314 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1314 2023/02/17 13:30:45 - mmengine - INFO - Epoch(train) [8][ 520/1320] lr: 2.0000e-02 eta: 7:34:36 time: 0.4784 data_time: 0.0137 memory: 27031 grad_norm: 4.2064 loss: 2.2286 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2286 2023/02/17 13:30:55 - mmengine - INFO - Epoch(train) [8][ 540/1320] lr: 2.0000e-02 eta: 7:34:26 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.1734 loss: 2.0294 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0294 2023/02/17 13:31:04 - mmengine - INFO - Epoch(train) [8][ 560/1320] lr: 2.0000e-02 eta: 7:34:16 time: 0.4780 data_time: 0.0137 memory: 27031 grad_norm: 4.1798 loss: 2.1832 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.1832 2023/02/17 13:31:14 - mmengine - INFO - Epoch(train) [8][ 580/1320] lr: 2.0000e-02 eta: 7:34:05 time: 0.4781 data_time: 0.0132 memory: 27031 grad_norm: 4.2152 loss: 2.2938 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2938 2023/02/17 13:31:23 - mmengine - INFO - Epoch(train) [8][ 600/1320] lr: 2.0000e-02 eta: 7:33:55 time: 0.4793 data_time: 0.0151 memory: 27031 grad_norm: 4.2562 loss: 2.0733 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0733 2023/02/17 13:31:33 - mmengine - INFO - Epoch(train) [8][ 620/1320] lr: 2.0000e-02 eta: 7:33:44 time: 0.4782 data_time: 0.0137 memory: 27031 grad_norm: 4.1204 loss: 2.1662 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1662 2023/02/17 13:31:42 - mmengine - INFO - Epoch(train) [8][ 640/1320] lr: 2.0000e-02 eta: 7:33:34 time: 0.4787 data_time: 0.0145 memory: 27031 grad_norm: 4.2505 loss: 2.2255 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.2255 2023/02/17 13:31:52 - mmengine - INFO - Epoch(train) [8][ 660/1320] lr: 2.0000e-02 eta: 7:33:24 time: 0.4798 data_time: 0.0151 memory: 27031 grad_norm: 4.2936 loss: 2.1359 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1359 2023/02/17 13:32:02 - mmengine - INFO - Epoch(train) [8][ 680/1320] lr: 2.0000e-02 eta: 7:33:13 time: 0.4779 data_time: 0.0135 memory: 27031 grad_norm: 4.2245 loss: 2.2353 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2353 2023/02/17 13:32:11 - mmengine - INFO - Epoch(train) [8][ 700/1320] lr: 2.0000e-02 eta: 7:33:03 time: 0.4796 data_time: 0.0150 memory: 27031 grad_norm: 4.1620 loss: 2.2569 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.2569 2023/02/17 13:32:21 - mmengine - INFO - Epoch(train) [8][ 720/1320] lr: 2.0000e-02 eta: 7:32:53 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.2148 loss: 2.4133 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.4133 2023/02/17 13:32:30 - mmengine - INFO - Epoch(train) [8][ 740/1320] lr: 2.0000e-02 eta: 7:32:42 time: 0.4778 data_time: 0.0135 memory: 27031 grad_norm: 3.9917 loss: 2.3328 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.3328 2023/02/17 13:32:40 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:32:40 - mmengine - INFO - Epoch(train) [8][ 760/1320] lr: 2.0000e-02 eta: 7:32:32 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 4.2048 loss: 2.2751 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.2751 2023/02/17 13:32:49 - mmengine - INFO - Epoch(train) [8][ 780/1320] lr: 2.0000e-02 eta: 7:32:21 time: 0.4787 data_time: 0.0139 memory: 27031 grad_norm: 4.1741 loss: 1.9967 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9967 2023/02/17 13:32:59 - mmengine - INFO - Epoch(train) [8][ 800/1320] lr: 2.0000e-02 eta: 7:32:11 time: 0.4783 data_time: 0.0136 memory: 27031 grad_norm: 4.2630 loss: 2.2782 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2782 2023/02/17 13:33:09 - mmengine - INFO - Epoch(train) [8][ 820/1320] lr: 2.0000e-02 eta: 7:32:01 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.2400 loss: 2.3648 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.3648 2023/02/17 13:33:18 - mmengine - INFO - Epoch(train) [8][ 840/1320] lr: 2.0000e-02 eta: 7:31:50 time: 0.4788 data_time: 0.0138 memory: 27031 grad_norm: 4.3138 loss: 2.0769 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.0769 2023/02/17 13:33:28 - mmengine - INFO - Epoch(train) [8][ 860/1320] lr: 2.0000e-02 eta: 7:31:40 time: 0.4785 data_time: 0.0144 memory: 27031 grad_norm: 4.1594 loss: 2.2093 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2093 2023/02/17 13:33:37 - mmengine - INFO - Epoch(train) [8][ 880/1320] lr: 2.0000e-02 eta: 7:31:30 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.2272 loss: 2.3227 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3227 2023/02/17 13:33:47 - mmengine - INFO - Epoch(train) [8][ 900/1320] lr: 2.0000e-02 eta: 7:31:19 time: 0.4798 data_time: 0.0133 memory: 27031 grad_norm: 4.1626 loss: 2.1647 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1647 2023/02/17 13:33:57 - mmengine - INFO - Epoch(train) [8][ 920/1320] lr: 2.0000e-02 eta: 7:31:09 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.2082 loss: 2.3865 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.3865 2023/02/17 13:34:06 - mmengine - INFO - Epoch(train) [8][ 940/1320] lr: 2.0000e-02 eta: 7:30:59 time: 0.4812 data_time: 0.0160 memory: 27031 grad_norm: 4.1832 loss: 2.2901 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.2901 2023/02/17 13:34:16 - mmengine - INFO - Epoch(train) [8][ 960/1320] lr: 2.0000e-02 eta: 7:30:49 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1104 loss: 2.2588 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2588 2023/02/17 13:34:25 - mmengine - INFO - Epoch(train) [8][ 980/1320] lr: 2.0000e-02 eta: 7:30:38 time: 0.4790 data_time: 0.0145 memory: 27031 grad_norm: 4.0536 loss: 2.3352 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.3352 2023/02/17 13:34:35 - mmengine - INFO - Epoch(train) [8][1000/1320] lr: 2.0000e-02 eta: 7:30:28 time: 0.4780 data_time: 0.0134 memory: 27031 grad_norm: 4.1731 loss: 1.9978 top1_acc: 0.3750 top5_acc: 1.0000 loss_cls: 1.9978 2023/02/17 13:34:44 - mmengine - INFO - Epoch(train) [8][1020/1320] lr: 2.0000e-02 eta: 7:30:18 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 4.1605 loss: 2.2422 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.2422 2023/02/17 13:34:54 - mmengine - INFO - Epoch(train) [8][1040/1320] lr: 2.0000e-02 eta: 7:30:07 time: 0.4801 data_time: 0.0143 memory: 27031 grad_norm: 4.2676 loss: 2.3019 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3019 2023/02/17 13:35:04 - mmengine - INFO - Epoch(train) [8][1060/1320] lr: 2.0000e-02 eta: 7:29:57 time: 0.4785 data_time: 0.0139 memory: 27031 grad_norm: 4.1705 loss: 2.2445 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.2445 2023/02/17 13:35:13 - mmengine - INFO - Epoch(train) [8][1080/1320] lr: 2.0000e-02 eta: 7:29:47 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.1945 loss: 2.2138 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2138 2023/02/17 13:35:23 - mmengine - INFO - Epoch(train) [8][1100/1320] lr: 2.0000e-02 eta: 7:29:36 time: 0.4785 data_time: 0.0137 memory: 27031 grad_norm: 4.1847 loss: 2.0819 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0819 2023/02/17 13:35:32 - mmengine - INFO - Epoch(train) [8][1120/1320] lr: 2.0000e-02 eta: 7:29:26 time: 0.4796 data_time: 0.0148 memory: 27031 grad_norm: 4.2943 loss: 2.1183 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.1183 2023/02/17 13:35:42 - mmengine - INFO - Epoch(train) [8][1140/1320] lr: 2.0000e-02 eta: 7:29:16 time: 0.4795 data_time: 0.0147 memory: 27031 grad_norm: 4.1361 loss: 2.0851 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0851 2023/02/17 13:35:52 - mmengine - INFO - Epoch(train) [8][1160/1320] lr: 2.0000e-02 eta: 7:29:06 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.2256 loss: 1.9822 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 1.9822 2023/02/17 13:36:01 - mmengine - INFO - Epoch(train) [8][1180/1320] lr: 2.0000e-02 eta: 7:28:55 time: 0.4805 data_time: 0.0156 memory: 27031 grad_norm: 4.1730 loss: 2.1693 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1693 2023/02/17 13:36:11 - mmengine - INFO - Epoch(train) [8][1200/1320] lr: 2.0000e-02 eta: 7:28:45 time: 0.4785 data_time: 0.0144 memory: 27031 grad_norm: 4.1080 loss: 2.1652 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.1652 2023/02/17 13:36:20 - mmengine - INFO - Epoch(train) [8][1220/1320] lr: 2.0000e-02 eta: 7:28:35 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.1388 loss: 2.1341 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1341 2023/02/17 13:36:30 - mmengine - INFO - Epoch(train) [8][1240/1320] lr: 2.0000e-02 eta: 7:28:25 time: 0.4807 data_time: 0.0159 memory: 27031 grad_norm: 4.1865 loss: 2.3781 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.3781 2023/02/17 13:36:40 - mmengine - INFO - Epoch(train) [8][1260/1320] lr: 2.0000e-02 eta: 7:28:14 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.1098 loss: 2.0054 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0054 2023/02/17 13:36:49 - mmengine - INFO - Epoch(train) [8][1280/1320] lr: 2.0000e-02 eta: 7:28:04 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.1428 loss: 2.3159 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.3159 2023/02/17 13:36:59 - mmengine - INFO - Epoch(train) [8][1300/1320] lr: 2.0000e-02 eta: 7:27:54 time: 0.4784 data_time: 0.0141 memory: 27031 grad_norm: 4.1508 loss: 2.2473 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 2.2473 2023/02/17 13:37:08 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:37:08 - mmengine - INFO - Epoch(train) [8][1320/1320] lr: 2.0000e-02 eta: 7:27:43 time: 0.4736 data_time: 0.0164 memory: 27031 grad_norm: 4.1496 loss: 2.1883 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 2.1883 2023/02/17 13:37:12 - mmengine - INFO - Epoch(val) [8][ 20/194] eta: 0:00:32 time: 0.1862 data_time: 0.0612 memory: 3265 2023/02/17 13:37:15 - mmengine - INFO - Epoch(val) [8][ 40/194] eta: 0:00:24 time: 0.1345 data_time: 0.0115 memory: 3265 2023/02/17 13:37:17 - mmengine - INFO - Epoch(val) [8][ 60/194] eta: 0:00:20 time: 0.1393 data_time: 0.0141 memory: 3265 2023/02/17 13:37:20 - mmengine - INFO - Epoch(val) [8][ 80/194] eta: 0:00:17 time: 0.1381 data_time: 0.0136 memory: 3265 2023/02/17 13:37:23 - mmengine - INFO - Epoch(val) [8][100/194] eta: 0:00:13 time: 0.1355 data_time: 0.0119 memory: 3265 2023/02/17 13:37:26 - mmengine - INFO - Epoch(val) [8][120/194] eta: 0:00:10 time: 0.1372 data_time: 0.0133 memory: 3265 2023/02/17 13:37:28 - mmengine - INFO - Epoch(val) [8][140/194] eta: 0:00:07 time: 0.1390 data_time: 0.0136 memory: 3265 2023/02/17 13:37:31 - mmengine - INFO - Epoch(val) [8][160/194] eta: 0:00:04 time: 0.1384 data_time: 0.0137 memory: 3265 2023/02/17 13:37:34 - mmengine - INFO - Epoch(val) [8][180/194] eta: 0:00:02 time: 0.1378 data_time: 0.0133 memory: 3265 2023/02/17 13:37:37 - mmengine - INFO - Epoch(val) [8][194/194] acc/top1: 0.4169 acc/top5: 0.7218 acc/mean1: 0.3379 2023/02/17 13:37:48 - mmengine - INFO - Epoch(train) [9][ 20/1320] lr: 2.0000e-02 eta: 7:27:38 time: 0.5319 data_time: 0.0593 memory: 27031 grad_norm: 4.2610 loss: 2.1842 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1842 2023/02/17 13:37:57 - mmengine - INFO - Epoch(train) [9][ 40/1320] lr: 2.0000e-02 eta: 7:27:28 time: 0.4780 data_time: 0.0142 memory: 27031 grad_norm: 4.0759 loss: 2.1556 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1556 2023/02/17 13:38:07 - mmengine - INFO - Epoch(train) [9][ 60/1320] lr: 2.0000e-02 eta: 7:27:17 time: 0.4776 data_time: 0.0138 memory: 27031 grad_norm: 4.1245 loss: 2.1002 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1002 2023/02/17 13:38:16 - mmengine - INFO - Epoch(train) [9][ 80/1320] lr: 2.0000e-02 eta: 7:27:07 time: 0.4798 data_time: 0.0153 memory: 27031 grad_norm: 4.3148 loss: 2.1547 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1547 2023/02/17 13:38:26 - mmengine - INFO - Epoch(train) [9][ 100/1320] lr: 2.0000e-02 eta: 7:26:57 time: 0.4789 data_time: 0.0146 memory: 27031 grad_norm: 4.2488 loss: 2.1388 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1388 2023/02/17 13:38:35 - mmengine - INFO - Epoch(train) [9][ 120/1320] lr: 2.0000e-02 eta: 7:26:47 time: 0.4784 data_time: 0.0135 memory: 27031 grad_norm: 4.1927 loss: 1.9777 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9777 2023/02/17 13:38:45 - mmengine - INFO - Epoch(train) [9][ 140/1320] lr: 2.0000e-02 eta: 7:26:36 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.0871 loss: 2.0230 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0230 2023/02/17 13:38:55 - mmengine - INFO - Epoch(train) [9][ 160/1320] lr: 2.0000e-02 eta: 7:26:26 time: 0.4779 data_time: 0.0136 memory: 27031 grad_norm: 4.2457 loss: 2.1238 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.1238 2023/02/17 13:39:04 - mmengine - INFO - Epoch(train) [9][ 180/1320] lr: 2.0000e-02 eta: 7:26:16 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.2830 loss: 2.0440 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0440 2023/02/17 13:39:14 - mmengine - INFO - Epoch(train) [9][ 200/1320] lr: 2.0000e-02 eta: 7:26:05 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2656 loss: 2.0908 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0908 2023/02/17 13:39:23 - mmengine - INFO - Epoch(train) [9][ 220/1320] lr: 2.0000e-02 eta: 7:25:55 time: 0.4785 data_time: 0.0137 memory: 27031 grad_norm: 4.3008 loss: 2.3028 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.3028 2023/02/17 13:39:33 - mmengine - INFO - Epoch(train) [9][ 240/1320] lr: 2.0000e-02 eta: 7:25:45 time: 0.4791 data_time: 0.0148 memory: 27031 grad_norm: 4.2370 loss: 2.3053 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3053 2023/02/17 13:39:42 - mmengine - INFO - Epoch(train) [9][ 260/1320] lr: 2.0000e-02 eta: 7:25:35 time: 0.4782 data_time: 0.0141 memory: 27031 grad_norm: 4.2172 loss: 2.3836 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.3836 2023/02/17 13:39:52 - mmengine - INFO - Epoch(train) [9][ 280/1320] lr: 2.0000e-02 eta: 7:25:24 time: 0.4783 data_time: 0.0136 memory: 27031 grad_norm: 4.1328 loss: 2.0620 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0620 2023/02/17 13:40:02 - mmengine - INFO - Epoch(train) [9][ 300/1320] lr: 2.0000e-02 eta: 7:25:14 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.0862 loss: 2.0844 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0844 2023/02/17 13:40:11 - mmengine - INFO - Epoch(train) [9][ 320/1320] lr: 2.0000e-02 eta: 7:25:04 time: 0.4780 data_time: 0.0138 memory: 27031 grad_norm: 4.3408 loss: 2.2306 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2306 2023/02/17 13:40:21 - mmengine - INFO - Epoch(train) [9][ 340/1320] lr: 2.0000e-02 eta: 7:24:53 time: 0.4793 data_time: 0.0148 memory: 27031 grad_norm: 4.1104 loss: 2.1577 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1577 2023/02/17 13:40:30 - mmengine - INFO - Epoch(train) [9][ 360/1320] lr: 2.0000e-02 eta: 7:24:43 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.2589 loss: 2.1205 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1205 2023/02/17 13:40:40 - mmengine - INFO - Epoch(train) [9][ 380/1320] lr: 2.0000e-02 eta: 7:24:33 time: 0.4780 data_time: 0.0138 memory: 27031 grad_norm: 4.2234 loss: 1.9975 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9975 2023/02/17 13:40:49 - mmengine - INFO - Epoch(train) [9][ 400/1320] lr: 2.0000e-02 eta: 7:24:22 time: 0.4782 data_time: 0.0143 memory: 27031 grad_norm: 4.3116 loss: 1.8799 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8799 2023/02/17 13:40:59 - mmengine - INFO - Epoch(train) [9][ 420/1320] lr: 2.0000e-02 eta: 7:24:12 time: 0.4780 data_time: 0.0140 memory: 27031 grad_norm: 4.2785 loss: 2.0960 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0960 2023/02/17 13:41:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:41:09 - mmengine - INFO - Epoch(train) [9][ 440/1320] lr: 2.0000e-02 eta: 7:24:02 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.2061 loss: 1.9856 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9856 2023/02/17 13:41:18 - mmengine - INFO - Epoch(train) [9][ 460/1320] lr: 2.0000e-02 eta: 7:23:52 time: 0.4793 data_time: 0.0147 memory: 27031 grad_norm: 4.1718 loss: 2.1906 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1906 2023/02/17 13:41:28 - mmengine - INFO - Epoch(train) [9][ 480/1320] lr: 2.0000e-02 eta: 7:23:41 time: 0.4784 data_time: 0.0140 memory: 27031 grad_norm: 4.2170 loss: 2.0582 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0582 2023/02/17 13:41:37 - mmengine - INFO - Epoch(train) [9][ 500/1320] lr: 2.0000e-02 eta: 7:23:31 time: 0.4788 data_time: 0.0146 memory: 27031 grad_norm: 4.2219 loss: 2.1117 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1117 2023/02/17 13:41:47 - mmengine - INFO - Epoch(train) [9][ 520/1320] lr: 2.0000e-02 eta: 7:23:21 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2846 loss: 2.2973 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2973 2023/02/17 13:41:56 - mmengine - INFO - Epoch(train) [9][ 540/1320] lr: 2.0000e-02 eta: 7:23:11 time: 0.4783 data_time: 0.0138 memory: 27031 grad_norm: 4.1042 loss: 2.0503 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0503 2023/02/17 13:42:06 - mmengine - INFO - Epoch(train) [9][ 560/1320] lr: 2.0000e-02 eta: 7:23:00 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.2501 loss: 2.3295 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.3295 2023/02/17 13:42:16 - mmengine - INFO - Epoch(train) [9][ 580/1320] lr: 2.0000e-02 eta: 7:22:50 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.2665 loss: 2.2674 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2674 2023/02/17 13:42:25 - mmengine - INFO - Epoch(train) [9][ 600/1320] lr: 2.0000e-02 eta: 7:22:40 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.2185 loss: 2.1895 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.1895 2023/02/17 13:42:35 - mmengine - INFO - Epoch(train) [9][ 620/1320] lr: 2.0000e-02 eta: 7:22:30 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.1016 loss: 2.0282 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0282 2023/02/17 13:42:44 - mmengine - INFO - Epoch(train) [9][ 640/1320] lr: 2.0000e-02 eta: 7:22:20 time: 0.4782 data_time: 0.0140 memory: 27031 grad_norm: 4.1129 loss: 2.1770 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1770 2023/02/17 13:42:54 - mmengine - INFO - Epoch(train) [9][ 660/1320] lr: 2.0000e-02 eta: 7:22:09 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1893 loss: 2.2036 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.2036 2023/02/17 13:43:04 - mmengine - INFO - Epoch(train) [9][ 680/1320] lr: 2.0000e-02 eta: 7:21:59 time: 0.4782 data_time: 0.0139 memory: 27031 grad_norm: 4.1598 loss: 2.0007 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0007 2023/02/17 13:43:13 - mmengine - INFO - Epoch(train) [9][ 700/1320] lr: 2.0000e-02 eta: 7:21:49 time: 0.4782 data_time: 0.0136 memory: 27031 grad_norm: 4.2110 loss: 2.1832 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1832 2023/02/17 13:43:23 - mmengine - INFO - Epoch(train) [9][ 720/1320] lr: 2.0000e-02 eta: 7:21:39 time: 0.4794 data_time: 0.0145 memory: 27031 grad_norm: 4.2323 loss: 2.3123 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3123 2023/02/17 13:43:32 - mmengine - INFO - Epoch(train) [9][ 740/1320] lr: 2.0000e-02 eta: 7:21:28 time: 0.4788 data_time: 0.0133 memory: 27031 grad_norm: 4.2787 loss: 1.9197 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9197 2023/02/17 13:43:42 - mmengine - INFO - Epoch(train) [9][ 760/1320] lr: 2.0000e-02 eta: 7:21:18 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.3171 loss: 2.4125 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.4125 2023/02/17 13:43:51 - mmengine - INFO - Epoch(train) [9][ 780/1320] lr: 2.0000e-02 eta: 7:21:08 time: 0.4793 data_time: 0.0148 memory: 27031 grad_norm: 4.1336 loss: 2.3475 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.3475 2023/02/17 13:44:01 - mmengine - INFO - Epoch(train) [9][ 800/1320] lr: 2.0000e-02 eta: 7:20:58 time: 0.4776 data_time: 0.0135 memory: 27031 grad_norm: 4.0965 loss: 2.2363 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.2363 2023/02/17 13:44:11 - mmengine - INFO - Epoch(train) [9][ 820/1320] lr: 2.0000e-02 eta: 7:20:48 time: 0.4783 data_time: 0.0144 memory: 27031 grad_norm: 4.0189 loss: 2.0807 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0807 2023/02/17 13:44:20 - mmengine - INFO - Epoch(train) [9][ 840/1320] lr: 2.0000e-02 eta: 7:20:37 time: 0.4787 data_time: 0.0146 memory: 27031 grad_norm: 4.1790 loss: 2.1391 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1391 2023/02/17 13:44:30 - mmengine - INFO - Epoch(train) [9][ 860/1320] lr: 2.0000e-02 eta: 7:20:27 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.1880 loss: 2.2874 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.2874 2023/02/17 13:44:39 - mmengine - INFO - Epoch(train) [9][ 880/1320] lr: 2.0000e-02 eta: 7:20:17 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.1772 loss: 2.1937 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.1937 2023/02/17 13:44:49 - mmengine - INFO - Epoch(train) [9][ 900/1320] lr: 2.0000e-02 eta: 7:20:07 time: 0.4794 data_time: 0.0133 memory: 27031 grad_norm: 4.1410 loss: 2.0770 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 2.0770 2023/02/17 13:44:58 - mmengine - INFO - Epoch(train) [9][ 920/1320] lr: 2.0000e-02 eta: 7:19:57 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 4.3162 loss: 2.1261 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1261 2023/02/17 13:45:08 - mmengine - INFO - Epoch(train) [9][ 940/1320] lr: 2.0000e-02 eta: 7:19:47 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.2819 loss: 1.9791 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.9791 2023/02/17 13:45:18 - mmengine - INFO - Epoch(train) [9][ 960/1320] lr: 2.0000e-02 eta: 7:19:37 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.2762 loss: 2.1461 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.1461 2023/02/17 13:45:27 - mmengine - INFO - Epoch(train) [9][ 980/1320] lr: 2.0000e-02 eta: 7:19:26 time: 0.4792 data_time: 0.0145 memory: 27031 grad_norm: 4.1665 loss: 2.0775 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.0775 2023/02/17 13:45:37 - mmengine - INFO - Epoch(train) [9][1000/1320] lr: 2.0000e-02 eta: 7:19:16 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.1199 loss: 1.9942 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9942 2023/02/17 13:45:46 - mmengine - INFO - Epoch(train) [9][1020/1320] lr: 2.0000e-02 eta: 7:19:06 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 4.1978 loss: 2.4248 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4248 2023/02/17 13:45:56 - mmengine - INFO - Epoch(train) [9][1040/1320] lr: 2.0000e-02 eta: 7:18:56 time: 0.4804 data_time: 0.0157 memory: 27031 grad_norm: 4.2030 loss: 2.2789 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2789 2023/02/17 13:46:06 - mmengine - INFO - Epoch(train) [9][1060/1320] lr: 2.0000e-02 eta: 7:18:46 time: 0.4792 data_time: 0.0148 memory: 27031 grad_norm: 4.1881 loss: 2.3059 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3059 2023/02/17 13:46:15 - mmengine - INFO - Epoch(train) [9][1080/1320] lr: 2.0000e-02 eta: 7:18:36 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 4.2096 loss: 1.9832 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9832 2023/02/17 13:46:25 - mmengine - INFO - Epoch(train) [9][1100/1320] lr: 2.0000e-02 eta: 7:18:26 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.3161 loss: 1.9909 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9909 2023/02/17 13:46:34 - mmengine - INFO - Epoch(train) [9][1120/1320] lr: 2.0000e-02 eta: 7:18:15 time: 0.4783 data_time: 0.0139 memory: 27031 grad_norm: 4.1629 loss: 2.2102 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2102 2023/02/17 13:46:44 - mmengine - INFO - Epoch(train) [9][1140/1320] lr: 2.0000e-02 eta: 7:18:05 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.1277 loss: 2.1925 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1925 2023/02/17 13:46:53 - mmengine - INFO - Epoch(train) [9][1160/1320] lr: 2.0000e-02 eta: 7:17:55 time: 0.4786 data_time: 0.0138 memory: 27031 grad_norm: 4.1510 loss: 2.2368 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2368 2023/02/17 13:47:03 - mmengine - INFO - Epoch(train) [9][1180/1320] lr: 2.0000e-02 eta: 7:17:45 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.0941 loss: 2.1829 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1829 2023/02/17 13:47:13 - mmengine - INFO - Epoch(train) [9][1200/1320] lr: 2.0000e-02 eta: 7:17:35 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.1536 loss: 1.9806 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9806 2023/02/17 13:47:22 - mmengine - INFO - Epoch(train) [9][1220/1320] lr: 2.0000e-02 eta: 7:17:25 time: 0.4788 data_time: 0.0135 memory: 27031 grad_norm: 4.1470 loss: 2.1276 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1276 2023/02/17 13:47:32 - mmengine - INFO - Epoch(train) [9][1240/1320] lr: 2.0000e-02 eta: 7:17:14 time: 0.4788 data_time: 0.0144 memory: 27031 grad_norm: 4.2084 loss: 2.0332 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0332 2023/02/17 13:47:41 - mmengine - INFO - Epoch(train) [9][1260/1320] lr: 2.0000e-02 eta: 7:17:04 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.3004 loss: 1.9676 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9676 2023/02/17 13:47:51 - mmengine - INFO - Epoch(train) [9][1280/1320] lr: 2.0000e-02 eta: 7:16:54 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.1139 loss: 2.2416 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2416 2023/02/17 13:48:01 - mmengine - INFO - Epoch(train) [9][1300/1320] lr: 2.0000e-02 eta: 7:16:44 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2388 loss: 2.2194 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2194 2023/02/17 13:48:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:48:10 - mmengine - INFO - Epoch(train) [9][1320/1320] lr: 2.0000e-02 eta: 7:16:34 time: 0.4754 data_time: 0.0164 memory: 27031 grad_norm: 4.1243 loss: 2.0677 top1_acc: 0.7273 top5_acc: 0.8182 loss_cls: 2.0677 2023/02/17 13:48:10 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/02/17 13:48:15 - mmengine - INFO - Epoch(val) [9][ 20/194] eta: 0:00:32 time: 0.1868 data_time: 0.0592 memory: 3265 2023/02/17 13:48:18 - mmengine - INFO - Epoch(val) [9][ 40/194] eta: 0:00:25 time: 0.1403 data_time: 0.0140 memory: 3265 2023/02/17 13:48:21 - mmengine - INFO - Epoch(val) [9][ 60/194] eta: 0:00:20 time: 0.1378 data_time: 0.0136 memory: 3265 2023/02/17 13:48:23 - mmengine - INFO - Epoch(val) [9][ 80/194] eta: 0:00:17 time: 0.1406 data_time: 0.0141 memory: 3265 2023/02/17 13:48:26 - mmengine - INFO - Epoch(val) [9][100/194] eta: 0:00:14 time: 0.1403 data_time: 0.0141 memory: 3265 2023/02/17 13:48:29 - mmengine - INFO - Epoch(val) [9][120/194] eta: 0:00:10 time: 0.1410 data_time: 0.0141 memory: 3265 2023/02/17 13:48:32 - mmengine - INFO - Epoch(val) [9][140/194] eta: 0:00:07 time: 0.1422 data_time: 0.0156 memory: 3265 2023/02/17 13:48:35 - mmengine - INFO - Epoch(val) [9][160/194] eta: 0:00:04 time: 0.1400 data_time: 0.0141 memory: 3265 2023/02/17 13:48:37 - mmengine - INFO - Epoch(val) [9][180/194] eta: 0:00:02 time: 0.1371 data_time: 0.0135 memory: 3265 2023/02/17 13:48:40 - mmengine - INFO - Epoch(val) [9][194/194] acc/top1: 0.4337 acc/top5: 0.7419 acc/mean1: 0.3669 2023/02/17 13:48:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_7.pth is removed 2023/02/17 13:48:41 - mmengine - INFO - The best checkpoint with 0.4337 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2023/02/17 13:48:51 - mmengine - INFO - Epoch(train) [10][ 20/1320] lr: 2.0000e-02 eta: 7:16:28 time: 0.5312 data_time: 0.0599 memory: 27031 grad_norm: 4.0636 loss: 2.0940 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0940 2023/02/17 13:49:01 - mmengine - INFO - Epoch(train) [10][ 40/1320] lr: 2.0000e-02 eta: 7:16:18 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.1363 loss: 2.0451 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0451 2023/02/17 13:49:11 - mmengine - INFO - Epoch(train) [10][ 60/1320] lr: 2.0000e-02 eta: 7:16:08 time: 0.4776 data_time: 0.0136 memory: 27031 grad_norm: 4.3386 loss: 1.9892 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9892 2023/02/17 13:49:20 - mmengine - INFO - Epoch(train) [10][ 80/1320] lr: 2.0000e-02 eta: 7:15:58 time: 0.4780 data_time: 0.0130 memory: 27031 grad_norm: 4.1134 loss: 2.0875 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0875 2023/02/17 13:49:30 - mmengine - INFO - Epoch(train) [10][ 100/1320] lr: 2.0000e-02 eta: 7:15:47 time: 0.4786 data_time: 0.0140 memory: 27031 grad_norm: 4.2535 loss: 2.0321 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0321 2023/02/17 13:49:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:49:39 - mmengine - INFO - Epoch(train) [10][ 120/1320] lr: 2.0000e-02 eta: 7:15:37 time: 0.4779 data_time: 0.0131 memory: 27031 grad_norm: 4.2404 loss: 2.0686 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0686 2023/02/17 13:49:49 - mmengine - INFO - Epoch(train) [10][ 140/1320] lr: 2.0000e-02 eta: 7:15:27 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.1346 loss: 2.2795 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2795 2023/02/17 13:49:58 - mmengine - INFO - Epoch(train) [10][ 160/1320] lr: 2.0000e-02 eta: 7:15:17 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.3217 loss: 2.0991 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0991 2023/02/17 13:50:08 - mmengine - INFO - Epoch(train) [10][ 180/1320] lr: 2.0000e-02 eta: 7:15:07 time: 0.4788 data_time: 0.0138 memory: 27031 grad_norm: 4.1587 loss: 2.3140 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.3140 2023/02/17 13:50:18 - mmengine - INFO - Epoch(train) [10][ 200/1320] lr: 2.0000e-02 eta: 7:14:57 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.2750 loss: 2.3561 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3561 2023/02/17 13:50:27 - mmengine - INFO - Epoch(train) [10][ 220/1320] lr: 2.0000e-02 eta: 7:14:47 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.2775 loss: 2.2017 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.2017 2023/02/17 13:50:37 - mmengine - INFO - Epoch(train) [10][ 240/1320] lr: 2.0000e-02 eta: 7:14:37 time: 0.4783 data_time: 0.0143 memory: 27031 grad_norm: 4.1391 loss: 2.2841 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.2841 2023/02/17 13:50:46 - mmengine - INFO - Epoch(train) [10][ 260/1320] lr: 2.0000e-02 eta: 7:14:27 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2972 loss: 1.9251 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9251 2023/02/17 13:50:56 - mmengine - INFO - Epoch(train) [10][ 280/1320] lr: 2.0000e-02 eta: 7:14:16 time: 0.4781 data_time: 0.0135 memory: 27031 grad_norm: 4.2362 loss: 2.1384 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1384 2023/02/17 13:51:06 - mmengine - INFO - Epoch(train) [10][ 300/1320] lr: 2.0000e-02 eta: 7:14:06 time: 0.4789 data_time: 0.0148 memory: 27031 grad_norm: 4.2245 loss: 2.1068 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1068 2023/02/17 13:51:15 - mmengine - INFO - Epoch(train) [10][ 320/1320] lr: 2.0000e-02 eta: 7:13:56 time: 0.4785 data_time: 0.0139 memory: 27031 grad_norm: 4.1031 loss: 2.0274 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0274 2023/02/17 13:51:25 - mmengine - INFO - Epoch(train) [10][ 340/1320] lr: 2.0000e-02 eta: 7:13:46 time: 0.4803 data_time: 0.0156 memory: 27031 grad_norm: 4.1902 loss: 2.2776 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.2776 2023/02/17 13:51:34 - mmengine - INFO - Epoch(train) [10][ 360/1320] lr: 2.0000e-02 eta: 7:13:36 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.3791 loss: 2.1078 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.1078 2023/02/17 13:51:44 - mmengine - INFO - Epoch(train) [10][ 380/1320] lr: 2.0000e-02 eta: 7:13:26 time: 0.4785 data_time: 0.0138 memory: 27031 grad_norm: 4.3709 loss: 2.1437 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.1437 2023/02/17 13:51:53 - mmengine - INFO - Epoch(train) [10][ 400/1320] lr: 2.0000e-02 eta: 7:13:16 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.1775 loss: 2.0393 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0393 2023/02/17 13:52:03 - mmengine - INFO - Epoch(train) [10][ 420/1320] lr: 2.0000e-02 eta: 7:13:06 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.2362 loss: 2.3137 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3137 2023/02/17 13:52:13 - mmengine - INFO - Epoch(train) [10][ 440/1320] lr: 2.0000e-02 eta: 7:12:55 time: 0.4778 data_time: 0.0135 memory: 27031 grad_norm: 4.2404 loss: 2.2240 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.2240 2023/02/17 13:52:22 - mmengine - INFO - Epoch(train) [10][ 460/1320] lr: 2.0000e-02 eta: 7:12:45 time: 0.4803 data_time: 0.0156 memory: 27031 grad_norm: 4.1478 loss: 2.0640 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0640 2023/02/17 13:52:32 - mmengine - INFO - Epoch(train) [10][ 480/1320] lr: 2.0000e-02 eta: 7:12:35 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 4.1120 loss: 2.0063 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.0063 2023/02/17 13:52:41 - mmengine - INFO - Epoch(train) [10][ 500/1320] lr: 2.0000e-02 eta: 7:12:25 time: 0.4780 data_time: 0.0135 memory: 27031 grad_norm: 4.2158 loss: 1.9355 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9355 2023/02/17 13:52:51 - mmengine - INFO - Epoch(train) [10][ 520/1320] lr: 2.0000e-02 eta: 7:12:15 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.2344 loss: 2.1665 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1665 2023/02/17 13:53:01 - mmengine - INFO - Epoch(train) [10][ 540/1320] lr: 2.0000e-02 eta: 7:12:05 time: 0.4788 data_time: 0.0136 memory: 27031 grad_norm: 4.1889 loss: 2.0416 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0416 2023/02/17 13:53:10 - mmengine - INFO - Epoch(train) [10][ 560/1320] lr: 2.0000e-02 eta: 7:11:55 time: 0.4784 data_time: 0.0142 memory: 27031 grad_norm: 4.1671 loss: 2.0893 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0893 2023/02/17 13:53:20 - mmengine - INFO - Epoch(train) [10][ 580/1320] lr: 2.0000e-02 eta: 7:11:45 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.2361 loss: 2.1810 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1810 2023/02/17 13:53:29 - mmengine - INFO - Epoch(train) [10][ 600/1320] lr: 2.0000e-02 eta: 7:11:35 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.0945 loss: 1.9877 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.9877 2023/02/17 13:53:39 - mmengine - INFO - Epoch(train) [10][ 620/1320] lr: 2.0000e-02 eta: 7:11:25 time: 0.4801 data_time: 0.0158 memory: 27031 grad_norm: 4.1306 loss: 1.9858 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9858 2023/02/17 13:53:48 - mmengine - INFO - Epoch(train) [10][ 640/1320] lr: 2.0000e-02 eta: 7:11:15 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.3791 loss: 2.0885 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.0885 2023/02/17 13:53:58 - mmengine - INFO - Epoch(train) [10][ 660/1320] lr: 2.0000e-02 eta: 7:11:05 time: 0.4785 data_time: 0.0138 memory: 27031 grad_norm: 4.2954 loss: 2.1586 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1586 2023/02/17 13:54:08 - mmengine - INFO - Epoch(train) [10][ 680/1320] lr: 2.0000e-02 eta: 7:10:55 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 4.2617 loss: 2.0519 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0519 2023/02/17 13:54:17 - mmengine - INFO - Epoch(train) [10][ 700/1320] lr: 2.0000e-02 eta: 7:10:44 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.2242 loss: 2.2223 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.2223 2023/02/17 13:54:27 - mmengine - INFO - Epoch(train) [10][ 720/1320] lr: 2.0000e-02 eta: 7:10:34 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.1956 loss: 2.2149 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2149 2023/02/17 13:54:36 - mmengine - INFO - Epoch(train) [10][ 740/1320] lr: 2.0000e-02 eta: 7:10:24 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.1743 loss: 1.9877 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9877 2023/02/17 13:54:46 - mmengine - INFO - Epoch(train) [10][ 760/1320] lr: 2.0000e-02 eta: 7:10:14 time: 0.4782 data_time: 0.0137 memory: 27031 grad_norm: 4.1774 loss: 2.0630 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0630 2023/02/17 13:54:56 - mmengine - INFO - Epoch(train) [10][ 780/1320] lr: 2.0000e-02 eta: 7:10:04 time: 0.4801 data_time: 0.0143 memory: 27031 grad_norm: 4.1761 loss: 2.1373 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1373 2023/02/17 13:55:05 - mmengine - INFO - Epoch(train) [10][ 800/1320] lr: 2.0000e-02 eta: 7:09:54 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 4.0487 loss: 2.2396 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2396 2023/02/17 13:55:15 - mmengine - INFO - Epoch(train) [10][ 820/1320] lr: 2.0000e-02 eta: 7:09:44 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 4.0799 loss: 2.0768 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 2.0768 2023/02/17 13:55:24 - mmengine - INFO - Epoch(train) [10][ 840/1320] lr: 2.0000e-02 eta: 7:09:34 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.2569 loss: 2.1084 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.1084 2023/02/17 13:55:34 - mmengine - INFO - Epoch(train) [10][ 860/1320] lr: 2.0000e-02 eta: 7:09:24 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.1785 loss: 2.1174 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1174 2023/02/17 13:55:44 - mmengine - INFO - Epoch(train) [10][ 880/1320] lr: 2.0000e-02 eta: 7:09:14 time: 0.4786 data_time: 0.0139 memory: 27031 grad_norm: 4.1342 loss: 1.9618 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9618 2023/02/17 13:55:53 - mmengine - INFO - Epoch(train) [10][ 900/1320] lr: 2.0000e-02 eta: 7:09:04 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.2420 loss: 2.2208 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.2208 2023/02/17 13:56:03 - mmengine - INFO - Epoch(train) [10][ 920/1320] lr: 2.0000e-02 eta: 7:08:54 time: 0.4784 data_time: 0.0138 memory: 27031 grad_norm: 4.1839 loss: 2.0964 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0964 2023/02/17 13:56:12 - mmengine - INFO - Epoch(train) [10][ 940/1320] lr: 2.0000e-02 eta: 7:08:44 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.2114 loss: 2.1361 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1361 2023/02/17 13:56:22 - mmengine - INFO - Epoch(train) [10][ 960/1320] lr: 2.0000e-02 eta: 7:08:34 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.2110 loss: 2.0064 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0064 2023/02/17 13:56:31 - mmengine - INFO - Epoch(train) [10][ 980/1320] lr: 2.0000e-02 eta: 7:08:24 time: 0.4789 data_time: 0.0143 memory: 27031 grad_norm: 4.1481 loss: 2.0148 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.0148 2023/02/17 13:56:41 - mmengine - INFO - Epoch(train) [10][1000/1320] lr: 2.0000e-02 eta: 7:08:14 time: 0.4801 data_time: 0.0151 memory: 27031 grad_norm: 4.1321 loss: 2.1046 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.1046 2023/02/17 13:56:51 - mmengine - INFO - Epoch(train) [10][1020/1320] lr: 2.0000e-02 eta: 7:08:04 time: 0.4858 data_time: 0.0209 memory: 27031 grad_norm: 4.2089 loss: 1.9182 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9182 2023/02/17 13:57:00 - mmengine - INFO - Epoch(train) [10][1040/1320] lr: 2.0000e-02 eta: 7:07:54 time: 0.4786 data_time: 0.0142 memory: 27031 grad_norm: 4.3105 loss: 2.0543 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0543 2023/02/17 13:57:10 - mmengine - INFO - Epoch(train) [10][1060/1320] lr: 2.0000e-02 eta: 7:07:44 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.3436 loss: 2.1585 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 2.1585 2023/02/17 13:57:19 - mmengine - INFO - Epoch(train) [10][1080/1320] lr: 2.0000e-02 eta: 7:07:34 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.1869 loss: 2.1179 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1179 2023/02/17 13:57:29 - mmengine - INFO - Epoch(train) [10][1100/1320] lr: 2.0000e-02 eta: 7:07:24 time: 0.4795 data_time: 0.0147 memory: 27031 grad_norm: 4.1250 loss: 2.1962 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1962 2023/02/17 13:57:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:57:39 - mmengine - INFO - Epoch(train) [10][1120/1320] lr: 2.0000e-02 eta: 7:07:14 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.2227 loss: 2.1064 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1064 2023/02/17 13:57:48 - mmengine - INFO - Epoch(train) [10][1140/1320] lr: 2.0000e-02 eta: 7:07:04 time: 0.4808 data_time: 0.0157 memory: 27031 grad_norm: 4.0665 loss: 2.1589 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1589 2023/02/17 13:57:58 - mmengine - INFO - Epoch(train) [10][1160/1320] lr: 2.0000e-02 eta: 7:06:54 time: 0.4790 data_time: 0.0140 memory: 27031 grad_norm: 4.1408 loss: 2.0571 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0571 2023/02/17 13:58:07 - mmengine - INFO - Epoch(train) [10][1180/1320] lr: 2.0000e-02 eta: 7:06:44 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 4.1284 loss: 2.0688 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.0688 2023/02/17 13:58:17 - mmengine - INFO - Epoch(train) [10][1200/1320] lr: 2.0000e-02 eta: 7:06:34 time: 0.4793 data_time: 0.0147 memory: 27031 grad_norm: 4.1271 loss: 1.9512 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9512 2023/02/17 13:58:27 - mmengine - INFO - Epoch(train) [10][1220/1320] lr: 2.0000e-02 eta: 7:06:24 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.1887 loss: 1.8893 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8893 2023/02/17 13:58:36 - mmengine - INFO - Epoch(train) [10][1240/1320] lr: 2.0000e-02 eta: 7:06:14 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 4.2126 loss: 2.0134 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0134 2023/02/17 13:58:46 - mmengine - INFO - Epoch(train) [10][1260/1320] lr: 2.0000e-02 eta: 7:06:04 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.1429 loss: 1.9941 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9941 2023/02/17 13:58:55 - mmengine - INFO - Epoch(train) [10][1280/1320] lr: 2.0000e-02 eta: 7:05:54 time: 0.4795 data_time: 0.0150 memory: 27031 grad_norm: 4.1943 loss: 2.1033 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.1033 2023/02/17 13:59:05 - mmengine - INFO - Epoch(train) [10][1300/1320] lr: 2.0000e-02 eta: 7:05:44 time: 0.4789 data_time: 0.0137 memory: 27031 grad_norm: 4.2340 loss: 2.1424 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1424 2023/02/17 13:59:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 13:59:14 - mmengine - INFO - Epoch(train) [10][1320/1320] lr: 2.0000e-02 eta: 7:05:34 time: 0.4733 data_time: 0.0158 memory: 27031 grad_norm: 4.2212 loss: 2.0810 top1_acc: 0.2727 top5_acc: 0.7273 loss_cls: 2.0810 2023/02/17 13:59:18 - mmengine - INFO - Epoch(val) [10][ 20/194] eta: 0:00:32 time: 0.1853 data_time: 0.0571 memory: 3265 2023/02/17 13:59:21 - mmengine - INFO - Epoch(val) [10][ 40/194] eta: 0:00:24 time: 0.1368 data_time: 0.0125 memory: 3265 2023/02/17 13:59:24 - mmengine - INFO - Epoch(val) [10][ 60/194] eta: 0:00:20 time: 0.1366 data_time: 0.0129 memory: 3265 2023/02/17 13:59:26 - mmengine - INFO - Epoch(val) [10][ 80/194] eta: 0:00:16 time: 0.1372 data_time: 0.0134 memory: 3265 2023/02/17 13:59:29 - mmengine - INFO - Epoch(val) [10][100/194] eta: 0:00:13 time: 0.1371 data_time: 0.0132 memory: 3265 2023/02/17 13:59:32 - mmengine - INFO - Epoch(val) [10][120/194] eta: 0:00:10 time: 0.1376 data_time: 0.0135 memory: 3265 2023/02/17 13:59:35 - mmengine - INFO - Epoch(val) [10][140/194] eta: 0:00:07 time: 0.1375 data_time: 0.0133 memory: 3265 2023/02/17 13:59:37 - mmengine - INFO - Epoch(val) [10][160/194] eta: 0:00:04 time: 0.1378 data_time: 0.0135 memory: 3265 2023/02/17 13:59:40 - mmengine - INFO - Epoch(val) [10][180/194] eta: 0:00:01 time: 0.1368 data_time: 0.0125 memory: 3265 2023/02/17 13:59:43 - mmengine - INFO - Epoch(val) [10][194/194] acc/top1: 0.4358 acc/top5: 0.7307 acc/mean1: 0.3721 2023/02/17 13:59:43 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_9.pth is removed 2023/02/17 13:59:44 - mmengine - INFO - The best checkpoint with 0.4358 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2023/02/17 13:59:55 - mmengine - INFO - Epoch(train) [11][ 20/1320] lr: 2.0000e-02 eta: 7:05:27 time: 0.5264 data_time: 0.0554 memory: 27031 grad_norm: 4.1914 loss: 2.2080 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.2080 2023/02/17 14:00:04 - mmengine - INFO - Epoch(train) [11][ 40/1320] lr: 2.0000e-02 eta: 7:05:17 time: 0.4802 data_time: 0.0157 memory: 27031 grad_norm: 4.0868 loss: 1.9938 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9938 2023/02/17 14:00:14 - mmengine - INFO - Epoch(train) [11][ 60/1320] lr: 2.0000e-02 eta: 7:05:07 time: 0.4793 data_time: 0.0151 memory: 27031 grad_norm: 4.2302 loss: 1.9216 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9216 2023/02/17 14:00:23 - mmengine - INFO - Epoch(train) [11][ 80/1320] lr: 2.0000e-02 eta: 7:04:57 time: 0.4792 data_time: 0.0149 memory: 27031 grad_norm: 4.1419 loss: 2.0442 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0442 2023/02/17 14:00:33 - mmengine - INFO - Epoch(train) [11][ 100/1320] lr: 2.0000e-02 eta: 7:04:47 time: 0.4805 data_time: 0.0155 memory: 27031 grad_norm: 4.1804 loss: 1.8719 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8719 2023/02/17 14:00:43 - mmengine - INFO - Epoch(train) [11][ 120/1320] lr: 2.0000e-02 eta: 7:04:37 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.2292 loss: 2.0799 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0799 2023/02/17 14:00:52 - mmengine - INFO - Epoch(train) [11][ 140/1320] lr: 2.0000e-02 eta: 7:04:27 time: 0.4785 data_time: 0.0132 memory: 27031 grad_norm: 4.2469 loss: 1.9693 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9693 2023/02/17 14:01:02 - mmengine - INFO - Epoch(train) [11][ 160/1320] lr: 2.0000e-02 eta: 7:04:17 time: 0.4791 data_time: 0.0133 memory: 27031 grad_norm: 4.2526 loss: 1.9992 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9992 2023/02/17 14:01:11 - mmengine - INFO - Epoch(train) [11][ 180/1320] lr: 2.0000e-02 eta: 7:04:07 time: 0.4786 data_time: 0.0127 memory: 27031 grad_norm: 4.1133 loss: 2.0356 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 2.0356 2023/02/17 14:01:21 - mmengine - INFO - Epoch(train) [11][ 200/1320] lr: 2.0000e-02 eta: 7:03:57 time: 0.4784 data_time: 0.0138 memory: 27031 grad_norm: 4.1269 loss: 2.1586 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 2.1586 2023/02/17 14:01:31 - mmengine - INFO - Epoch(train) [11][ 220/1320] lr: 2.0000e-02 eta: 7:03:47 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 4.2177 loss: 2.0769 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0769 2023/02/17 14:01:40 - mmengine - INFO - Epoch(train) [11][ 240/1320] lr: 2.0000e-02 eta: 7:03:37 time: 0.4789 data_time: 0.0142 memory: 27031 grad_norm: 4.0811 loss: 1.8849 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8849 2023/02/17 14:01:50 - mmengine - INFO - Epoch(train) [11][ 260/1320] lr: 2.0000e-02 eta: 7:03:27 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 4.2582 loss: 1.8763 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8763 2023/02/17 14:01:59 - mmengine - INFO - Epoch(train) [11][ 280/1320] lr: 2.0000e-02 eta: 7:03:17 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.2344 loss: 2.0437 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0437 2023/02/17 14:02:09 - mmengine - INFO - Epoch(train) [11][ 300/1320] lr: 2.0000e-02 eta: 7:03:07 time: 0.4786 data_time: 0.0134 memory: 27031 grad_norm: 4.1380 loss: 2.0656 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0656 2023/02/17 14:02:18 - mmengine - INFO - Epoch(train) [11][ 320/1320] lr: 2.0000e-02 eta: 7:02:57 time: 0.4791 data_time: 0.0149 memory: 27031 grad_norm: 4.3116 loss: 2.1940 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.1940 2023/02/17 14:02:28 - mmengine - INFO - Epoch(train) [11][ 340/1320] lr: 2.0000e-02 eta: 7:02:47 time: 0.4784 data_time: 0.0136 memory: 27031 grad_norm: 4.2138 loss: 2.1515 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.1515 2023/02/17 14:02:38 - mmengine - INFO - Epoch(train) [11][ 360/1320] lr: 2.0000e-02 eta: 7:02:37 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.1966 loss: 2.0284 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0284 2023/02/17 14:02:47 - mmengine - INFO - Epoch(train) [11][ 380/1320] lr: 2.0000e-02 eta: 7:02:27 time: 0.4789 data_time: 0.0148 memory: 27031 grad_norm: 4.1967 loss: 2.0437 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0437 2023/02/17 14:02:57 - mmengine - INFO - Epoch(train) [11][ 400/1320] lr: 2.0000e-02 eta: 7:02:17 time: 0.4776 data_time: 0.0137 memory: 27031 grad_norm: 4.1630 loss: 1.9220 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9220 2023/02/17 14:03:06 - mmengine - INFO - Epoch(train) [11][ 420/1320] lr: 2.0000e-02 eta: 7:02:07 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.1532 loss: 2.0866 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.0866 2023/02/17 14:03:16 - mmengine - INFO - Epoch(train) [11][ 440/1320] lr: 2.0000e-02 eta: 7:01:57 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.2393 loss: 1.9945 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9945 2023/02/17 14:03:26 - mmengine - INFO - Epoch(train) [11][ 460/1320] lr: 2.0000e-02 eta: 7:01:47 time: 0.4793 data_time: 0.0136 memory: 27031 grad_norm: 4.2782 loss: 1.9571 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9571 2023/02/17 14:03:35 - mmengine - INFO - Epoch(train) [11][ 480/1320] lr: 2.0000e-02 eta: 7:01:37 time: 0.4791 data_time: 0.0146 memory: 27031 grad_norm: 4.2347 loss: 2.1676 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1676 2023/02/17 14:03:45 - mmengine - INFO - Epoch(train) [11][ 500/1320] lr: 2.0000e-02 eta: 7:01:27 time: 0.4799 data_time: 0.0153 memory: 27031 grad_norm: 4.3172 loss: 1.8607 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8607 2023/02/17 14:03:54 - mmengine - INFO - Epoch(train) [11][ 520/1320] lr: 2.0000e-02 eta: 7:01:17 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.1203 loss: 2.0012 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0012 2023/02/17 14:04:04 - mmengine - INFO - Epoch(train) [11][ 540/1320] lr: 2.0000e-02 eta: 7:01:07 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.1851 loss: 1.9675 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9675 2023/02/17 14:04:13 - mmengine - INFO - Epoch(train) [11][ 560/1320] lr: 2.0000e-02 eta: 7:00:57 time: 0.4779 data_time: 0.0139 memory: 27031 grad_norm: 4.3305 loss: 2.0811 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0811 2023/02/17 14:04:23 - mmengine - INFO - Epoch(train) [11][ 580/1320] lr: 2.0000e-02 eta: 7:00:47 time: 0.4796 data_time: 0.0148 memory: 27031 grad_norm: 4.3311 loss: 2.2049 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2049 2023/02/17 14:04:33 - mmengine - INFO - Epoch(train) [11][ 600/1320] lr: 2.0000e-02 eta: 7:00:37 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.1387 loss: 2.1441 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1441 2023/02/17 14:04:42 - mmengine - INFO - Epoch(train) [11][ 620/1320] lr: 2.0000e-02 eta: 7:00:27 time: 0.4781 data_time: 0.0131 memory: 27031 grad_norm: 4.2120 loss: 2.1716 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1716 2023/02/17 14:04:52 - mmengine - INFO - Epoch(train) [11][ 640/1320] lr: 2.0000e-02 eta: 7:00:17 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.1654 loss: 2.3008 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.3008 2023/02/17 14:05:01 - mmengine - INFO - Epoch(train) [11][ 660/1320] lr: 2.0000e-02 eta: 7:00:07 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 4.2224 loss: 2.1119 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.1119 2023/02/17 14:05:11 - mmengine - INFO - Epoch(train) [11][ 680/1320] lr: 2.0000e-02 eta: 6:59:57 time: 0.4795 data_time: 0.0149 memory: 27031 grad_norm: 4.1461 loss: 2.0665 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0665 2023/02/17 14:05:21 - mmengine - INFO - Epoch(train) [11][ 700/1320] lr: 2.0000e-02 eta: 6:59:47 time: 0.4801 data_time: 0.0150 memory: 27031 grad_norm: 4.1789 loss: 1.9701 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 1.9701 2023/02/17 14:05:30 - mmengine - INFO - Epoch(train) [11][ 720/1320] lr: 2.0000e-02 eta: 6:59:37 time: 0.4785 data_time: 0.0142 memory: 27031 grad_norm: 4.2211 loss: 1.8695 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8695 2023/02/17 14:05:40 - mmengine - INFO - Epoch(train) [11][ 740/1320] lr: 2.0000e-02 eta: 6:59:28 time: 0.4893 data_time: 0.0247 memory: 27031 grad_norm: 4.2431 loss: 1.8812 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8812 2023/02/17 14:05:50 - mmengine - INFO - Epoch(train) [11][ 760/1320] lr: 2.0000e-02 eta: 6:59:18 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 4.2196 loss: 1.9709 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.9709 2023/02/17 14:05:59 - mmengine - INFO - Epoch(train) [11][ 780/1320] lr: 2.0000e-02 eta: 6:59:08 time: 0.4788 data_time: 0.0133 memory: 27031 grad_norm: 4.2371 loss: 2.0231 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.0231 2023/02/17 14:06:09 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:06:09 - mmengine - INFO - Epoch(train) [11][ 800/1320] lr: 2.0000e-02 eta: 6:58:58 time: 0.4800 data_time: 0.0152 memory: 27031 grad_norm: 4.3348 loss: 2.1229 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.1229 2023/02/17 14:06:18 - mmengine - INFO - Epoch(train) [11][ 820/1320] lr: 2.0000e-02 eta: 6:58:48 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.2434 loss: 2.1178 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.1178 2023/02/17 14:06:28 - mmengine - INFO - Epoch(train) [11][ 840/1320] lr: 2.0000e-02 eta: 6:58:38 time: 0.4789 data_time: 0.0146 memory: 27031 grad_norm: 4.2980 loss: 2.1377 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.1377 2023/02/17 14:06:38 - mmengine - INFO - Epoch(train) [11][ 860/1320] lr: 2.0000e-02 eta: 6:58:28 time: 0.4796 data_time: 0.0147 memory: 27031 grad_norm: 4.2755 loss: 2.0178 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0178 2023/02/17 14:06:47 - mmengine - INFO - Epoch(train) [11][ 880/1320] lr: 2.0000e-02 eta: 6:58:18 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2155 loss: 1.9890 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.9890 2023/02/17 14:06:57 - mmengine - INFO - Epoch(train) [11][ 900/1320] lr: 2.0000e-02 eta: 6:58:08 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 4.2024 loss: 2.1043 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1043 2023/02/17 14:07:06 - mmengine - INFO - Epoch(train) [11][ 920/1320] lr: 2.0000e-02 eta: 6:57:58 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.1025 loss: 2.1331 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1331 2023/02/17 14:07:16 - mmengine - INFO - Epoch(train) [11][ 940/1320] lr: 2.0000e-02 eta: 6:57:48 time: 0.4795 data_time: 0.0132 memory: 27031 grad_norm: 4.2399 loss: 2.1163 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1163 2023/02/17 14:07:25 - mmengine - INFO - Epoch(train) [11][ 960/1320] lr: 2.0000e-02 eta: 6:57:38 time: 0.4797 data_time: 0.0150 memory: 27031 grad_norm: 4.3264 loss: 2.0738 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0738 2023/02/17 14:07:35 - mmengine - INFO - Epoch(train) [11][ 980/1320] lr: 2.0000e-02 eta: 6:57:28 time: 0.4798 data_time: 0.0135 memory: 27031 grad_norm: 4.2811 loss: 2.1125 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1125 2023/02/17 14:07:45 - mmengine - INFO - Epoch(train) [11][1000/1320] lr: 2.0000e-02 eta: 6:57:18 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.2423 loss: 1.9069 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9069 2023/02/17 14:07:54 - mmengine - INFO - Epoch(train) [11][1020/1320] lr: 2.0000e-02 eta: 6:57:08 time: 0.4798 data_time: 0.0149 memory: 27031 grad_norm: 4.1620 loss: 1.9945 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9945 2023/02/17 14:08:04 - mmengine - INFO - Epoch(train) [11][1040/1320] lr: 2.0000e-02 eta: 6:56:58 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 4.0900 loss: 2.0341 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0341 2023/02/17 14:08:13 - mmengine - INFO - Epoch(train) [11][1060/1320] lr: 2.0000e-02 eta: 6:56:48 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.2225 loss: 2.0283 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0283 2023/02/17 14:08:23 - mmengine - INFO - Epoch(train) [11][1080/1320] lr: 2.0000e-02 eta: 6:56:39 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.0960 loss: 2.0773 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0773 2023/02/17 14:08:33 - mmengine - INFO - Epoch(train) [11][1100/1320] lr: 2.0000e-02 eta: 6:56:29 time: 0.4788 data_time: 0.0139 memory: 27031 grad_norm: 4.2477 loss: 2.1125 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1125 2023/02/17 14:08:42 - mmengine - INFO - Epoch(train) [11][1120/1320] lr: 2.0000e-02 eta: 6:56:19 time: 0.4790 data_time: 0.0146 memory: 27031 grad_norm: 4.1667 loss: 2.0775 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 2.0775 2023/02/17 14:08:52 - mmengine - INFO - Epoch(train) [11][1140/1320] lr: 2.0000e-02 eta: 6:56:09 time: 0.4790 data_time: 0.0139 memory: 27031 grad_norm: 4.2707 loss: 2.1537 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.1537 2023/02/17 14:09:01 - mmengine - INFO - Epoch(train) [11][1160/1320] lr: 2.0000e-02 eta: 6:55:59 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.1478 loss: 1.9964 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9964 2023/02/17 14:09:11 - mmengine - INFO - Epoch(train) [11][1180/1320] lr: 2.0000e-02 eta: 6:55:49 time: 0.4895 data_time: 0.0248 memory: 27031 grad_norm: 4.2103 loss: 2.0014 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0014 2023/02/17 14:09:21 - mmengine - INFO - Epoch(train) [11][1200/1320] lr: 2.0000e-02 eta: 6:55:40 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.3193 loss: 2.0215 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0215 2023/02/17 14:09:30 - mmengine - INFO - Epoch(train) [11][1220/1320] lr: 2.0000e-02 eta: 6:55:30 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.2863 loss: 1.9586 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9586 2023/02/17 14:09:40 - mmengine - INFO - Epoch(train) [11][1240/1320] lr: 2.0000e-02 eta: 6:55:20 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2458 loss: 2.1994 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1994 2023/02/17 14:09:49 - mmengine - INFO - Epoch(train) [11][1260/1320] lr: 2.0000e-02 eta: 6:55:10 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 4.3069 loss: 2.0079 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0079 2023/02/17 14:09:59 - mmengine - INFO - Epoch(train) [11][1280/1320] lr: 2.0000e-02 eta: 6:55:00 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.3054 loss: 2.1262 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1262 2023/02/17 14:10:09 - mmengine - INFO - Epoch(train) [11][1300/1320] lr: 2.0000e-02 eta: 6:54:50 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.2952 loss: 2.0485 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0485 2023/02/17 14:10:18 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:10:18 - mmengine - INFO - Epoch(train) [11][1320/1320] lr: 2.0000e-02 eta: 6:54:39 time: 0.4749 data_time: 0.0159 memory: 27031 grad_norm: 4.1363 loss: 2.0440 top1_acc: 0.2727 top5_acc: 0.6364 loss_cls: 2.0440 2023/02/17 14:10:22 - mmengine - INFO - Epoch(val) [11][ 20/194] eta: 0:00:32 time: 0.1865 data_time: 0.0571 memory: 3265 2023/02/17 14:10:25 - mmengine - INFO - Epoch(val) [11][ 40/194] eta: 0:00:24 time: 0.1370 data_time: 0.0122 memory: 3265 2023/02/17 14:10:27 - mmengine - INFO - Epoch(val) [11][ 60/194] eta: 0:00:20 time: 0.1367 data_time: 0.0132 memory: 3265 2023/02/17 14:10:30 - mmengine - INFO - Epoch(val) [11][ 80/194] eta: 0:00:16 time: 0.1352 data_time: 0.0123 memory: 3265 2023/02/17 14:10:33 - mmengine - INFO - Epoch(val) [11][100/194] eta: 0:00:13 time: 0.1367 data_time: 0.0126 memory: 3265 2023/02/17 14:10:36 - mmengine - INFO - Epoch(val) [11][120/194] eta: 0:00:10 time: 0.1381 data_time: 0.0136 memory: 3265 2023/02/17 14:10:38 - mmengine - INFO - Epoch(val) [11][140/194] eta: 0:00:07 time: 0.1380 data_time: 0.0138 memory: 3265 2023/02/17 14:10:41 - mmengine - INFO - Epoch(val) [11][160/194] eta: 0:00:04 time: 0.1374 data_time: 0.0132 memory: 3265 2023/02/17 14:10:44 - mmengine - INFO - Epoch(val) [11][180/194] eta: 0:00:01 time: 0.1379 data_time: 0.0138 memory: 3265 2023/02/17 14:10:47 - mmengine - INFO - Epoch(val) [11][194/194] acc/top1: 0.4447 acc/top5: 0.7504 acc/mean1: 0.3832 2023/02/17 14:10:47 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_10.pth is removed 2023/02/17 14:10:48 - mmengine - INFO - The best checkpoint with 0.4447 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2023/02/17 14:10:59 - mmengine - INFO - Epoch(train) [12][ 20/1320] lr: 2.0000e-02 eta: 6:54:33 time: 0.5236 data_time: 0.0541 memory: 27031 grad_norm: 4.0920 loss: 2.0495 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0495 2023/02/17 14:11:08 - mmengine - INFO - Epoch(train) [12][ 40/1320] lr: 2.0000e-02 eta: 6:54:23 time: 0.4789 data_time: 0.0145 memory: 27031 grad_norm: 4.3098 loss: 2.0630 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0630 2023/02/17 14:11:18 - mmengine - INFO - Epoch(train) [12][ 60/1320] lr: 2.0000e-02 eta: 6:54:13 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 4.2843 loss: 2.1751 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1751 2023/02/17 14:11:27 - mmengine - INFO - Epoch(train) [12][ 80/1320] lr: 2.0000e-02 eta: 6:54:03 time: 0.4781 data_time: 0.0133 memory: 27031 grad_norm: 4.0754 loss: 1.9736 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9736 2023/02/17 14:11:37 - mmengine - INFO - Epoch(train) [12][ 100/1320] lr: 2.0000e-02 eta: 6:53:53 time: 0.4775 data_time: 0.0136 memory: 27031 grad_norm: 4.2434 loss: 1.9082 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9082 2023/02/17 14:11:46 - mmengine - INFO - Epoch(train) [12][ 120/1320] lr: 2.0000e-02 eta: 6:53:43 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1426 loss: 1.9838 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9838 2023/02/17 14:11:56 - mmengine - INFO - Epoch(train) [12][ 140/1320] lr: 2.0000e-02 eta: 6:53:33 time: 0.4781 data_time: 0.0138 memory: 27031 grad_norm: 4.2051 loss: 2.0297 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0297 2023/02/17 14:12:06 - mmengine - INFO - Epoch(train) [12][ 160/1320] lr: 2.0000e-02 eta: 6:53:23 time: 0.4784 data_time: 0.0145 memory: 27031 grad_norm: 4.3796 loss: 2.3615 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.3615 2023/02/17 14:12:15 - mmengine - INFO - Epoch(train) [12][ 180/1320] lr: 2.0000e-02 eta: 6:53:13 time: 0.4787 data_time: 0.0140 memory: 27031 grad_norm: 4.2294 loss: 2.0065 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0065 2023/02/17 14:12:25 - mmengine - INFO - Epoch(train) [12][ 200/1320] lr: 2.0000e-02 eta: 6:53:03 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.1744 loss: 1.9966 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9966 2023/02/17 14:12:34 - mmengine - INFO - Epoch(train) [12][ 220/1320] lr: 2.0000e-02 eta: 6:52:53 time: 0.4789 data_time: 0.0140 memory: 27031 grad_norm: 4.3048 loss: 2.0708 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0708 2023/02/17 14:12:44 - mmengine - INFO - Epoch(train) [12][ 240/1320] lr: 2.0000e-02 eta: 6:52:43 time: 0.4789 data_time: 0.0151 memory: 27031 grad_norm: 4.3397 loss: 2.0029 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0029 2023/02/17 14:12:54 - mmengine - INFO - Epoch(train) [12][ 260/1320] lr: 2.0000e-02 eta: 6:52:33 time: 0.4786 data_time: 0.0133 memory: 27031 grad_norm: 4.2566 loss: 2.1582 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.1582 2023/02/17 14:13:03 - mmengine - INFO - Epoch(train) [12][ 280/1320] lr: 2.0000e-02 eta: 6:52:23 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.2551 loss: 1.9146 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9146 2023/02/17 14:13:13 - mmengine - INFO - Epoch(train) [12][ 300/1320] lr: 2.0000e-02 eta: 6:52:13 time: 0.4786 data_time: 0.0135 memory: 27031 grad_norm: 4.3018 loss: 2.0324 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 2.0324 2023/02/17 14:13:22 - mmengine - INFO - Epoch(train) [12][ 320/1320] lr: 2.0000e-02 eta: 6:52:03 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 4.3133 loss: 1.9878 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9878 2023/02/17 14:13:32 - mmengine - INFO - Epoch(train) [12][ 340/1320] lr: 2.0000e-02 eta: 6:51:53 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.3016 loss: 2.0199 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0199 2023/02/17 14:13:41 - mmengine - INFO - Epoch(train) [12][ 360/1320] lr: 2.0000e-02 eta: 6:51:43 time: 0.4787 data_time: 0.0142 memory: 27031 grad_norm: 4.1962 loss: 2.0948 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.0948 2023/02/17 14:13:51 - mmengine - INFO - Epoch(train) [12][ 380/1320] lr: 2.0000e-02 eta: 6:51:33 time: 0.4792 data_time: 0.0149 memory: 27031 grad_norm: 4.1558 loss: 2.0492 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0492 2023/02/17 14:14:01 - mmengine - INFO - Epoch(train) [12][ 400/1320] lr: 2.0000e-02 eta: 6:51:23 time: 0.4792 data_time: 0.0148 memory: 27031 grad_norm: 4.2073 loss: 2.2193 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.2193 2023/02/17 14:14:10 - mmengine - INFO - Epoch(train) [12][ 420/1320] lr: 2.0000e-02 eta: 6:51:13 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.1841 loss: 2.0675 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 2.0675 2023/02/17 14:14:20 - mmengine - INFO - Epoch(train) [12][ 440/1320] lr: 2.0000e-02 eta: 6:51:03 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2902 loss: 2.1196 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1196 2023/02/17 14:14:29 - mmengine - INFO - Epoch(train) [12][ 460/1320] lr: 2.0000e-02 eta: 6:50:53 time: 0.4789 data_time: 0.0143 memory: 27031 grad_norm: 4.2259 loss: 2.1558 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.1558 2023/02/17 14:14:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:14:39 - mmengine - INFO - Epoch(train) [12][ 480/1320] lr: 2.0000e-02 eta: 6:50:43 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.2509 loss: 1.9538 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9538 2023/02/17 14:14:49 - mmengine - INFO - Epoch(train) [12][ 500/1320] lr: 2.0000e-02 eta: 6:50:34 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.3012 loss: 1.9839 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9839 2023/02/17 14:14:58 - mmengine - INFO - Epoch(train) [12][ 520/1320] lr: 2.0000e-02 eta: 6:50:24 time: 0.4787 data_time: 0.0144 memory: 27031 grad_norm: 4.3592 loss: 2.1011 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1011 2023/02/17 14:15:08 - mmengine - INFO - Epoch(train) [12][ 540/1320] lr: 2.0000e-02 eta: 6:50:14 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.3641 loss: 2.0953 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0953 2023/02/17 14:15:17 - mmengine - INFO - Epoch(train) [12][ 560/1320] lr: 2.0000e-02 eta: 6:50:04 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.1768 loss: 1.9856 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9856 2023/02/17 14:15:27 - mmengine - INFO - Epoch(train) [12][ 580/1320] lr: 2.0000e-02 eta: 6:49:54 time: 0.4785 data_time: 0.0135 memory: 27031 grad_norm: 4.3161 loss: 1.8815 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8815 2023/02/17 14:15:37 - mmengine - INFO - Epoch(train) [12][ 600/1320] lr: 2.0000e-02 eta: 6:49:44 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 4.1961 loss: 2.0881 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0881 2023/02/17 14:15:47 - mmengine - INFO - Epoch(train) [12][ 620/1320] lr: 2.0000e-02 eta: 6:49:36 time: 0.5102 data_time: 0.0456 memory: 27031 grad_norm: 4.2907 loss: 2.1338 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.1338 2023/02/17 14:15:56 - mmengine - INFO - Epoch(train) [12][ 640/1320] lr: 2.0000e-02 eta: 6:49:26 time: 0.4786 data_time: 0.0143 memory: 27031 grad_norm: 4.2985 loss: 2.0070 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0070 2023/02/17 14:16:06 - mmengine - INFO - Epoch(train) [12][ 660/1320] lr: 2.0000e-02 eta: 6:49:16 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.2506 loss: 2.1295 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 2.1295 2023/02/17 14:16:15 - mmengine - INFO - Epoch(train) [12][ 680/1320] lr: 2.0000e-02 eta: 6:49:06 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.2298 loss: 1.9608 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9608 2023/02/17 14:16:25 - mmengine - INFO - Epoch(train) [12][ 700/1320] lr: 2.0000e-02 eta: 6:48:56 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.1920 loss: 2.0385 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0385 2023/02/17 14:16:35 - mmengine - INFO - Epoch(train) [12][ 720/1320] lr: 2.0000e-02 eta: 6:48:46 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.2268 loss: 1.8011 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8011 2023/02/17 14:16:44 - mmengine - INFO - Epoch(train) [12][ 740/1320] lr: 2.0000e-02 eta: 6:48:36 time: 0.4782 data_time: 0.0134 memory: 27031 grad_norm: 4.3362 loss: 2.0057 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0057 2023/02/17 14:16:54 - mmengine - INFO - Epoch(train) [12][ 760/1320] lr: 2.0000e-02 eta: 6:48:26 time: 0.4796 data_time: 0.0152 memory: 27031 grad_norm: 4.2628 loss: 2.0107 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.0107 2023/02/17 14:17:03 - mmengine - INFO - Epoch(train) [12][ 780/1320] lr: 2.0000e-02 eta: 6:48:17 time: 0.4793 data_time: 0.0150 memory: 27031 grad_norm: 4.3790 loss: 2.1769 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 2.1769 2023/02/17 14:17:13 - mmengine - INFO - Epoch(train) [12][ 800/1320] lr: 2.0000e-02 eta: 6:48:07 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.1276 loss: 2.0573 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.0573 2023/02/17 14:17:23 - mmengine - INFO - Epoch(train) [12][ 820/1320] lr: 2.0000e-02 eta: 6:47:57 time: 0.4788 data_time: 0.0144 memory: 27031 grad_norm: 4.1901 loss: 2.0666 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0666 2023/02/17 14:17:32 - mmengine - INFO - Epoch(train) [12][ 840/1320] lr: 2.0000e-02 eta: 6:47:47 time: 0.4787 data_time: 0.0147 memory: 27031 grad_norm: 4.2802 loss: 2.1230 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1230 2023/02/17 14:17:42 - mmengine - INFO - Epoch(train) [12][ 860/1320] lr: 2.0000e-02 eta: 6:47:39 time: 0.5114 data_time: 0.0467 memory: 27031 grad_norm: 4.2594 loss: 1.8002 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8002 2023/02/17 14:17:52 - mmengine - INFO - Epoch(train) [12][ 880/1320] lr: 2.0000e-02 eta: 6:47:29 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.3528 loss: 2.1280 top1_acc: 0.1250 top5_acc: 0.8125 loss_cls: 2.1280 2023/02/17 14:18:02 - mmengine - INFO - Epoch(train) [12][ 900/1320] lr: 2.0000e-02 eta: 6:47:19 time: 0.4787 data_time: 0.0133 memory: 27031 grad_norm: 4.2406 loss: 2.0472 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0472 2023/02/17 14:18:11 - mmengine - INFO - Epoch(train) [12][ 920/1320] lr: 2.0000e-02 eta: 6:47:09 time: 0.4790 data_time: 0.0145 memory: 27031 grad_norm: 4.2285 loss: 2.1213 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 2.1213 2023/02/17 14:18:21 - mmengine - INFO - Epoch(train) [12][ 940/1320] lr: 2.0000e-02 eta: 6:46:59 time: 0.4789 data_time: 0.0137 memory: 27031 grad_norm: 4.1985 loss: 1.9476 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9476 2023/02/17 14:18:30 - mmengine - INFO - Epoch(train) [12][ 960/1320] lr: 2.0000e-02 eta: 6:46:49 time: 0.4805 data_time: 0.0157 memory: 27031 grad_norm: 4.1804 loss: 2.1265 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1265 2023/02/17 14:18:40 - mmengine - INFO - Epoch(train) [12][ 980/1320] lr: 2.0000e-02 eta: 6:46:39 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.1388 loss: 2.0243 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0243 2023/02/17 14:18:49 - mmengine - INFO - Epoch(train) [12][1000/1320] lr: 2.0000e-02 eta: 6:46:30 time: 0.4796 data_time: 0.0155 memory: 27031 grad_norm: 4.1402 loss: 1.9337 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 1.9337 2023/02/17 14:18:59 - mmengine - INFO - Epoch(train) [12][1020/1320] lr: 2.0000e-02 eta: 6:46:20 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 4.3606 loss: 1.8763 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8763 2023/02/17 14:19:09 - mmengine - INFO - Epoch(train) [12][1040/1320] lr: 2.0000e-02 eta: 6:46:10 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.4144 loss: 1.9756 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9756 2023/02/17 14:19:18 - mmengine - INFO - Epoch(train) [12][1060/1320] lr: 2.0000e-02 eta: 6:46:00 time: 0.4814 data_time: 0.0156 memory: 27031 grad_norm: 4.3175 loss: 2.0136 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.0136 2023/02/17 14:19:28 - mmengine - INFO - Epoch(train) [12][1080/1320] lr: 2.0000e-02 eta: 6:45:50 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.1924 loss: 1.9921 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9921 2023/02/17 14:19:37 - mmengine - INFO - Epoch(train) [12][1100/1320] lr: 2.0000e-02 eta: 6:45:40 time: 0.4788 data_time: 0.0136 memory: 27031 grad_norm: 4.2451 loss: 1.9945 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9945 2023/02/17 14:19:47 - mmengine - INFO - Epoch(train) [12][1120/1320] lr: 2.0000e-02 eta: 6:45:30 time: 0.4793 data_time: 0.0148 memory: 27031 grad_norm: 4.1187 loss: 2.0759 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0759 2023/02/17 14:19:57 - mmengine - INFO - Epoch(train) [12][1140/1320] lr: 2.0000e-02 eta: 6:45:20 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.2885 loss: 2.2019 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.2019 2023/02/17 14:20:06 - mmengine - INFO - Epoch(train) [12][1160/1320] lr: 2.0000e-02 eta: 6:45:11 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.2908 loss: 2.2906 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.2906 2023/02/17 14:20:16 - mmengine - INFO - Epoch(train) [12][1180/1320] lr: 2.0000e-02 eta: 6:45:01 time: 0.4796 data_time: 0.0147 memory: 27031 grad_norm: 4.3016 loss: 1.9721 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 1.9721 2023/02/17 14:20:25 - mmengine - INFO - Epoch(train) [12][1200/1320] lr: 2.0000e-02 eta: 6:44:51 time: 0.4799 data_time: 0.0152 memory: 27031 grad_norm: 4.2392 loss: 2.0754 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0754 2023/02/17 14:20:35 - mmengine - INFO - Epoch(train) [12][1220/1320] lr: 2.0000e-02 eta: 6:44:41 time: 0.4792 data_time: 0.0134 memory: 27031 grad_norm: 4.2125 loss: 2.0385 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0385 2023/02/17 14:20:45 - mmengine - INFO - Epoch(train) [12][1240/1320] lr: 2.0000e-02 eta: 6:44:31 time: 0.4797 data_time: 0.0150 memory: 27031 grad_norm: 4.2278 loss: 1.9594 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9594 2023/02/17 14:20:54 - mmengine - INFO - Epoch(train) [12][1260/1320] lr: 2.0000e-02 eta: 6:44:21 time: 0.4790 data_time: 0.0140 memory: 27031 grad_norm: 4.2246 loss: 2.2128 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.2128 2023/02/17 14:21:04 - mmengine - INFO - Epoch(train) [12][1280/1320] lr: 2.0000e-02 eta: 6:44:11 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2500 loss: 2.0116 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0116 2023/02/17 14:21:13 - mmengine - INFO - Epoch(train) [12][1300/1320] lr: 2.0000e-02 eta: 6:44:01 time: 0.4809 data_time: 0.0159 memory: 27031 grad_norm: 4.1544 loss: 1.9176 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9176 2023/02/17 14:21:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:21:23 - mmengine - INFO - Epoch(train) [12][1320/1320] lr: 2.0000e-02 eta: 6:43:51 time: 0.4723 data_time: 0.0156 memory: 27031 grad_norm: 4.1746 loss: 2.3024 top1_acc: 0.0909 top5_acc: 0.4545 loss_cls: 2.3024 2023/02/17 14:21:23 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/02/17 14:21:28 - mmengine - INFO - Epoch(val) [12][ 20/194] eta: 0:00:33 time: 0.1932 data_time: 0.0623 memory: 3265 2023/02/17 14:21:31 - mmengine - INFO - Epoch(val) [12][ 40/194] eta: 0:00:25 time: 0.1399 data_time: 0.0138 memory: 3265 2023/02/17 14:21:34 - mmengine - INFO - Epoch(val) [12][ 60/194] eta: 0:00:21 time: 0.1411 data_time: 0.0151 memory: 3265 2023/02/17 14:21:36 - mmengine - INFO - Epoch(val) [12][ 80/194] eta: 0:00:17 time: 0.1407 data_time: 0.0144 memory: 3265 2023/02/17 14:21:39 - mmengine - INFO - Epoch(val) [12][100/194] eta: 0:00:14 time: 0.1386 data_time: 0.0135 memory: 3265 2023/02/17 14:21:42 - mmengine - INFO - Epoch(val) [12][120/194] eta: 0:00:11 time: 0.1397 data_time: 0.0146 memory: 3265 2023/02/17 14:21:45 - mmengine - INFO - Epoch(val) [12][140/194] eta: 0:00:07 time: 0.1409 data_time: 0.0151 memory: 3265 2023/02/17 14:21:48 - mmengine - INFO - Epoch(val) [12][160/194] eta: 0:00:04 time: 0.1414 data_time: 0.0149 memory: 3265 2023/02/17 14:21:51 - mmengine - INFO - Epoch(val) [12][180/194] eta: 0:00:02 time: 0.1642 data_time: 0.0137 memory: 3265 2023/02/17 14:21:54 - mmengine - INFO - Epoch(val) [12][194/194] acc/top1: 0.4702 acc/top5: 0.7618 acc/mean1: 0.4077 2023/02/17 14:21:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_11.pth is removed 2023/02/17 14:21:55 - mmengine - INFO - The best checkpoint with 0.4702 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2023/02/17 14:22:05 - mmengine - INFO - Epoch(train) [13][ 20/1320] lr: 2.0000e-02 eta: 6:43:44 time: 0.5289 data_time: 0.0583 memory: 27031 grad_norm: 4.1757 loss: 1.8402 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8402 2023/02/17 14:22:15 - mmengine - INFO - Epoch(train) [13][ 40/1320] lr: 2.0000e-02 eta: 6:43:34 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 4.2239 loss: 2.0752 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0752 2023/02/17 14:22:24 - mmengine - INFO - Epoch(train) [13][ 60/1320] lr: 2.0000e-02 eta: 6:43:25 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.2063 loss: 1.9431 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9431 2023/02/17 14:22:34 - mmengine - INFO - Epoch(train) [13][ 80/1320] lr: 2.0000e-02 eta: 6:43:15 time: 0.4809 data_time: 0.0162 memory: 27031 grad_norm: 4.3101 loss: 1.7693 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7693 2023/02/17 14:22:44 - mmengine - INFO - Epoch(train) [13][ 100/1320] lr: 2.0000e-02 eta: 6:43:05 time: 0.4799 data_time: 0.0151 memory: 27031 grad_norm: 4.3144 loss: 2.1614 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1614 2023/02/17 14:22:53 - mmengine - INFO - Epoch(train) [13][ 120/1320] lr: 2.0000e-02 eta: 6:42:55 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 4.2178 loss: 1.9217 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9217 2023/02/17 14:23:03 - mmengine - INFO - Epoch(train) [13][ 140/1320] lr: 2.0000e-02 eta: 6:42:45 time: 0.4807 data_time: 0.0156 memory: 27031 grad_norm: 4.1733 loss: 2.1162 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.1162 2023/02/17 14:23:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:23:12 - mmengine - INFO - Epoch(train) [13][ 160/1320] lr: 2.0000e-02 eta: 6:42:35 time: 0.4792 data_time: 0.0154 memory: 27031 grad_norm: 4.2641 loss: 1.7984 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7984 2023/02/17 14:23:22 - mmengine - INFO - Epoch(train) [13][ 180/1320] lr: 2.0000e-02 eta: 6:42:26 time: 0.4800 data_time: 0.0157 memory: 27031 grad_norm: 4.3719 loss: 1.8298 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8298 2023/02/17 14:23:32 - mmengine - INFO - Epoch(train) [13][ 200/1320] lr: 2.0000e-02 eta: 6:42:16 time: 0.4822 data_time: 0.0174 memory: 27031 grad_norm: 4.2106 loss: 1.8714 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8714 2023/02/17 14:23:46 - mmengine - INFO - Epoch(train) [13][ 220/1320] lr: 2.0000e-02 eta: 6:42:20 time: 0.7059 data_time: 0.0153 memory: 27031 grad_norm: 4.3887 loss: 2.0475 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0475 2023/02/17 14:23:55 - mmengine - INFO - Epoch(train) [13][ 240/1320] lr: 2.0000e-02 eta: 6:42:10 time: 0.4803 data_time: 0.0155 memory: 27031 grad_norm: 4.1813 loss: 2.0708 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 2.0708 2023/02/17 14:24:05 - mmengine - INFO - Epoch(train) [13][ 260/1320] lr: 2.0000e-02 eta: 6:42:00 time: 0.4801 data_time: 0.0155 memory: 27031 grad_norm: 4.3482 loss: 1.8724 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8724 2023/02/17 14:24:15 - mmengine - INFO - Epoch(train) [13][ 280/1320] lr: 2.0000e-02 eta: 6:41:50 time: 0.4807 data_time: 0.0158 memory: 27031 grad_norm: 4.4208 loss: 1.9940 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9940 2023/02/17 14:24:24 - mmengine - INFO - Epoch(train) [13][ 300/1320] lr: 2.0000e-02 eta: 6:41:41 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 4.2789 loss: 2.1925 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.1925 2023/02/17 14:24:34 - mmengine - INFO - Epoch(train) [13][ 320/1320] lr: 2.0000e-02 eta: 6:41:31 time: 0.4807 data_time: 0.0133 memory: 27031 grad_norm: 4.1802 loss: 2.0172 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0172 2023/02/17 14:24:43 - mmengine - INFO - Epoch(train) [13][ 340/1320] lr: 2.0000e-02 eta: 6:41:21 time: 0.4789 data_time: 0.0140 memory: 27031 grad_norm: 4.2067 loss: 2.0847 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0847 2023/02/17 14:24:53 - mmengine - INFO - Epoch(train) [13][ 360/1320] lr: 2.0000e-02 eta: 6:41:11 time: 0.4794 data_time: 0.0137 memory: 27031 grad_norm: 4.0367 loss: 1.9924 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9924 2023/02/17 14:25:03 - mmengine - INFO - Epoch(train) [13][ 380/1320] lr: 2.0000e-02 eta: 6:41:01 time: 0.4785 data_time: 0.0134 memory: 27031 grad_norm: 4.2367 loss: 1.9100 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9100 2023/02/17 14:25:12 - mmengine - INFO - Epoch(train) [13][ 400/1320] lr: 2.0000e-02 eta: 6:40:51 time: 0.4800 data_time: 0.0139 memory: 27031 grad_norm: 4.2670 loss: 2.1352 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1352 2023/02/17 14:25:22 - mmengine - INFO - Epoch(train) [13][ 420/1320] lr: 2.0000e-02 eta: 6:40:41 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.1474 loss: 2.0000 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0000 2023/02/17 14:25:31 - mmengine - INFO - Epoch(train) [13][ 440/1320] lr: 2.0000e-02 eta: 6:40:31 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.2703 loss: 1.9984 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9984 2023/02/17 14:25:41 - mmengine - INFO - Epoch(train) [13][ 460/1320] lr: 2.0000e-02 eta: 6:40:21 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.2219 loss: 1.9507 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9507 2023/02/17 14:25:51 - mmengine - INFO - Epoch(train) [13][ 480/1320] lr: 2.0000e-02 eta: 6:40:11 time: 0.4797 data_time: 0.0149 memory: 27031 grad_norm: 4.1501 loss: 1.9679 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9679 2023/02/17 14:26:00 - mmengine - INFO - Epoch(train) [13][ 500/1320] lr: 2.0000e-02 eta: 6:40:02 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 4.3312 loss: 2.0425 top1_acc: 0.3750 top5_acc: 1.0000 loss_cls: 2.0425 2023/02/17 14:26:10 - mmengine - INFO - Epoch(train) [13][ 520/1320] lr: 2.0000e-02 eta: 6:39:52 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.2760 loss: 2.0102 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0102 2023/02/17 14:26:19 - mmengine - INFO - Epoch(train) [13][ 540/1320] lr: 2.0000e-02 eta: 6:39:42 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.1789 loss: 2.0738 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0738 2023/02/17 14:26:29 - mmengine - INFO - Epoch(train) [13][ 560/1320] lr: 2.0000e-02 eta: 6:39:32 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.2789 loss: 1.9694 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9694 2023/02/17 14:26:38 - mmengine - INFO - Epoch(train) [13][ 580/1320] lr: 2.0000e-02 eta: 6:39:22 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.3354 loss: 1.7730 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 1.7730 2023/02/17 14:26:48 - mmengine - INFO - Epoch(train) [13][ 600/1320] lr: 2.0000e-02 eta: 6:39:12 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.2367 loss: 1.9140 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9140 2023/02/17 14:26:58 - mmengine - INFO - Epoch(train) [13][ 620/1320] lr: 2.0000e-02 eta: 6:39:02 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.1523 loss: 1.8192 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8192 2023/02/17 14:27:07 - mmengine - INFO - Epoch(train) [13][ 640/1320] lr: 2.0000e-02 eta: 6:38:52 time: 0.4790 data_time: 0.0139 memory: 27031 grad_norm: 4.2738 loss: 2.1713 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1713 2023/02/17 14:27:17 - mmengine - INFO - Epoch(train) [13][ 660/1320] lr: 2.0000e-02 eta: 6:38:42 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.3249 loss: 1.7684 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.7684 2023/02/17 14:27:26 - mmengine - INFO - Epoch(train) [13][ 680/1320] lr: 2.0000e-02 eta: 6:38:32 time: 0.4795 data_time: 0.0148 memory: 27031 grad_norm: 4.3549 loss: 2.0874 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0874 2023/02/17 14:27:36 - mmengine - INFO - Epoch(train) [13][ 700/1320] lr: 2.0000e-02 eta: 6:38:23 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.1865 loss: 2.0421 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0421 2023/02/17 14:27:46 - mmengine - INFO - Epoch(train) [13][ 720/1320] lr: 2.0000e-02 eta: 6:38:13 time: 0.4794 data_time: 0.0148 memory: 27031 grad_norm: 4.2913 loss: 2.1544 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.1544 2023/02/17 14:27:55 - mmengine - INFO - Epoch(train) [13][ 740/1320] lr: 2.0000e-02 eta: 6:38:03 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 4.2084 loss: 2.0970 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0970 2023/02/17 14:28:05 - mmengine - INFO - Epoch(train) [13][ 760/1320] lr: 2.0000e-02 eta: 6:37:53 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.2465 loss: 2.3436 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 2.3436 2023/02/17 14:28:14 - mmengine - INFO - Epoch(train) [13][ 780/1320] lr: 2.0000e-02 eta: 6:37:43 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.2370 loss: 2.1178 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1178 2023/02/17 14:28:24 - mmengine - INFO - Epoch(train) [13][ 800/1320] lr: 2.0000e-02 eta: 6:37:33 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.2806 loss: 2.0331 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0331 2023/02/17 14:28:34 - mmengine - INFO - Epoch(train) [13][ 820/1320] lr: 2.0000e-02 eta: 6:37:23 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 4.2457 loss: 1.9664 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.9664 2023/02/17 14:28:43 - mmengine - INFO - Epoch(train) [13][ 840/1320] lr: 2.0000e-02 eta: 6:37:13 time: 0.4796 data_time: 0.0149 memory: 27031 grad_norm: 4.1610 loss: 1.8577 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.8577 2023/02/17 14:28:53 - mmengine - INFO - Epoch(train) [13][ 860/1320] lr: 2.0000e-02 eta: 6:37:03 time: 0.4783 data_time: 0.0140 memory: 27031 grad_norm: 4.2757 loss: 2.0020 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0020 2023/02/17 14:29:02 - mmengine - INFO - Epoch(train) [13][ 880/1320] lr: 2.0000e-02 eta: 6:36:54 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.2325 loss: 1.8852 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8852 2023/02/17 14:29:12 - mmengine - INFO - Epoch(train) [13][ 900/1320] lr: 2.0000e-02 eta: 6:36:44 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.2175 loss: 1.9243 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 1.9243 2023/02/17 14:29:21 - mmengine - INFO - Epoch(train) [13][ 920/1320] lr: 2.0000e-02 eta: 6:36:34 time: 0.4791 data_time: 0.0146 memory: 27031 grad_norm: 4.2569 loss: 2.0255 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0255 2023/02/17 14:29:31 - mmengine - INFO - Epoch(train) [13][ 940/1320] lr: 2.0000e-02 eta: 6:36:24 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.2217 loss: 1.9252 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9252 2023/02/17 14:29:41 - mmengine - INFO - Epoch(train) [13][ 960/1320] lr: 2.0000e-02 eta: 6:36:14 time: 0.4785 data_time: 0.0137 memory: 27031 grad_norm: 4.2871 loss: 1.9897 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9897 2023/02/17 14:29:50 - mmengine - INFO - Epoch(train) [13][ 980/1320] lr: 2.0000e-02 eta: 6:36:04 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.0595 loss: 1.9655 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9655 2023/02/17 14:30:00 - mmengine - INFO - Epoch(train) [13][1000/1320] lr: 2.0000e-02 eta: 6:35:54 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.3081 loss: 2.0033 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0033 2023/02/17 14:30:09 - mmengine - INFO - Epoch(train) [13][1020/1320] lr: 2.0000e-02 eta: 6:35:44 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.2271 loss: 1.8954 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8954 2023/02/17 14:30:19 - mmengine - INFO - Epoch(train) [13][1040/1320] lr: 2.0000e-02 eta: 6:35:34 time: 0.4798 data_time: 0.0150 memory: 27031 grad_norm: 4.2839 loss: 1.8222 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8222 2023/02/17 14:30:29 - mmengine - INFO - Epoch(train) [13][1060/1320] lr: 2.0000e-02 eta: 6:35:24 time: 0.4783 data_time: 0.0139 memory: 27031 grad_norm: 4.2209 loss: 2.0287 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0287 2023/02/17 14:30:38 - mmengine - INFO - Epoch(train) [13][1080/1320] lr: 2.0000e-02 eta: 6:35:15 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2681 loss: 2.0969 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0969 2023/02/17 14:30:48 - mmengine - INFO - Epoch(train) [13][1100/1320] lr: 2.0000e-02 eta: 6:35:05 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.3299 loss: 1.8396 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8396 2023/02/17 14:30:57 - mmengine - INFO - Epoch(train) [13][1120/1320] lr: 2.0000e-02 eta: 6:34:55 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.1170 loss: 2.1059 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1059 2023/02/17 14:31:07 - mmengine - INFO - Epoch(train) [13][1140/1320] lr: 2.0000e-02 eta: 6:34:45 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.1744 loss: 1.8451 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8451 2023/02/17 14:31:17 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:31:17 - mmengine - INFO - Epoch(train) [13][1160/1320] lr: 2.0000e-02 eta: 6:34:35 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.1756 loss: 2.0173 top1_acc: 0.3750 top5_acc: 0.5000 loss_cls: 2.0173 2023/02/17 14:31:26 - mmengine - INFO - Epoch(train) [13][1180/1320] lr: 2.0000e-02 eta: 6:34:25 time: 0.4781 data_time: 0.0140 memory: 27031 grad_norm: 4.1356 loss: 2.0632 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0632 2023/02/17 14:31:36 - mmengine - INFO - Epoch(train) [13][1200/1320] lr: 2.0000e-02 eta: 6:34:15 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.1813 loss: 2.0178 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0178 2023/02/17 14:31:45 - mmengine - INFO - Epoch(train) [13][1220/1320] lr: 2.0000e-02 eta: 6:34:05 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.1966 loss: 2.0736 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0736 2023/02/17 14:31:55 - mmengine - INFO - Epoch(train) [13][1240/1320] lr: 2.0000e-02 eta: 6:33:55 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.1228 loss: 2.0202 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0202 2023/02/17 14:32:04 - mmengine - INFO - Epoch(train) [13][1260/1320] lr: 2.0000e-02 eta: 6:33:46 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.3464 loss: 1.8672 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8672 2023/02/17 14:32:14 - mmengine - INFO - Epoch(train) [13][1280/1320] lr: 2.0000e-02 eta: 6:33:36 time: 0.4783 data_time: 0.0136 memory: 27031 grad_norm: 4.2026 loss: 2.1571 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.1571 2023/02/17 14:32:24 - mmengine - INFO - Epoch(train) [13][1300/1320] lr: 2.0000e-02 eta: 6:33:26 time: 0.4791 data_time: 0.0149 memory: 27031 grad_norm: 4.2699 loss: 2.0879 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0879 2023/02/17 14:32:33 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:32:33 - mmengine - INFO - Epoch(train) [13][1320/1320] lr: 2.0000e-02 eta: 6:33:16 time: 0.4736 data_time: 0.0160 memory: 27031 grad_norm: 4.3286 loss: 1.9857 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.9857 2023/02/17 14:32:37 - mmengine - INFO - Epoch(val) [13][ 20/194] eta: 0:00:33 time: 0.1899 data_time: 0.0616 memory: 3265 2023/02/17 14:32:40 - mmengine - INFO - Epoch(val) [13][ 40/194] eta: 0:00:25 time: 0.1371 data_time: 0.0127 memory: 3265 2023/02/17 14:32:42 - mmengine - INFO - Epoch(val) [13][ 60/194] eta: 0:00:20 time: 0.1354 data_time: 0.0124 memory: 3265 2023/02/17 14:32:45 - mmengine - INFO - Epoch(val) [13][ 80/194] eta: 0:00:17 time: 0.1367 data_time: 0.0132 memory: 3265 2023/02/17 14:32:48 - mmengine - INFO - Epoch(val) [13][100/194] eta: 0:00:13 time: 0.1367 data_time: 0.0127 memory: 3265 2023/02/17 14:32:51 - mmengine - INFO - Epoch(val) [13][120/194] eta: 0:00:10 time: 0.1375 data_time: 0.0131 memory: 3265 2023/02/17 14:32:53 - mmengine - INFO - Epoch(val) [13][140/194] eta: 0:00:07 time: 0.1388 data_time: 0.0141 memory: 3265 2023/02/17 14:32:56 - mmengine - INFO - Epoch(val) [13][160/194] eta: 0:00:04 time: 0.1369 data_time: 0.0130 memory: 3265 2023/02/17 14:32:59 - mmengine - INFO - Epoch(val) [13][180/194] eta: 0:00:02 time: 0.1371 data_time: 0.0133 memory: 3265 2023/02/17 14:33:02 - mmengine - INFO - Epoch(val) [13][194/194] acc/top1: 0.4774 acc/top5: 0.7764 acc/mean1: 0.4013 2023/02/17 14:33:02 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_12.pth is removed 2023/02/17 14:33:03 - mmengine - INFO - The best checkpoint with 0.4774 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2023/02/17 14:33:13 - mmengine - INFO - Epoch(train) [14][ 20/1320] lr: 2.0000e-02 eta: 6:33:08 time: 0.5236 data_time: 0.0545 memory: 27031 grad_norm: 4.1416 loss: 1.9786 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9786 2023/02/17 14:33:23 - mmengine - INFO - Epoch(train) [14][ 40/1320] lr: 2.0000e-02 eta: 6:32:58 time: 0.4811 data_time: 0.0169 memory: 27031 grad_norm: 4.1822 loss: 1.7248 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7248 2023/02/17 14:33:33 - mmengine - INFO - Epoch(train) [14][ 60/1320] lr: 2.0000e-02 eta: 6:32:49 time: 0.4802 data_time: 0.0156 memory: 27031 grad_norm: 4.3275 loss: 1.9334 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9334 2023/02/17 14:33:42 - mmengine - INFO - Epoch(train) [14][ 80/1320] lr: 2.0000e-02 eta: 6:32:39 time: 0.4793 data_time: 0.0152 memory: 27031 grad_norm: 4.1976 loss: 2.1260 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.1260 2023/02/17 14:33:52 - mmengine - INFO - Epoch(train) [14][ 100/1320] lr: 2.0000e-02 eta: 6:32:29 time: 0.4808 data_time: 0.0161 memory: 27031 grad_norm: 4.1625 loss: 1.8426 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8426 2023/02/17 14:34:01 - mmengine - INFO - Epoch(train) [14][ 120/1320] lr: 2.0000e-02 eta: 6:32:19 time: 0.4807 data_time: 0.0164 memory: 27031 grad_norm: 4.2985 loss: 2.0319 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0319 2023/02/17 14:34:11 - mmengine - INFO - Epoch(train) [14][ 140/1320] lr: 2.0000e-02 eta: 6:32:09 time: 0.4799 data_time: 0.0152 memory: 27031 grad_norm: 4.2506 loss: 1.9763 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9763 2023/02/17 14:34:21 - mmengine - INFO - Epoch(train) [14][ 160/1320] lr: 2.0000e-02 eta: 6:31:59 time: 0.4798 data_time: 0.0151 memory: 27031 grad_norm: 4.2479 loss: 1.9008 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9008 2023/02/17 14:34:30 - mmengine - INFO - Epoch(train) [14][ 180/1320] lr: 2.0000e-02 eta: 6:31:49 time: 0.4777 data_time: 0.0128 memory: 27031 grad_norm: 4.3115 loss: 1.9713 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9713 2023/02/17 14:34:40 - mmengine - INFO - Epoch(train) [14][ 200/1320] lr: 2.0000e-02 eta: 6:31:40 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.3090 loss: 1.7665 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7665 2023/02/17 14:34:49 - mmengine - INFO - Epoch(train) [14][ 220/1320] lr: 2.0000e-02 eta: 6:31:30 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 4.4155 loss: 1.9972 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9972 2023/02/17 14:34:59 - mmengine - INFO - Epoch(train) [14][ 240/1320] lr: 2.0000e-02 eta: 6:31:20 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2440 loss: 2.1623 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.1623 2023/02/17 14:35:08 - mmengine - INFO - Epoch(train) [14][ 260/1320] lr: 2.0000e-02 eta: 6:31:10 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.1802 loss: 1.9808 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9808 2023/02/17 14:35:18 - mmengine - INFO - Epoch(train) [14][ 280/1320] lr: 2.0000e-02 eta: 6:31:00 time: 0.4790 data_time: 0.0138 memory: 27031 grad_norm: 4.2887 loss: 1.9950 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9950 2023/02/17 14:35:28 - mmengine - INFO - Epoch(train) [14][ 300/1320] lr: 2.0000e-02 eta: 6:30:50 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.3442 loss: 1.8778 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.8778 2023/02/17 14:35:37 - mmengine - INFO - Epoch(train) [14][ 320/1320] lr: 2.0000e-02 eta: 6:30:40 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.3596 loss: 1.9941 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9941 2023/02/17 14:35:47 - mmengine - INFO - Epoch(train) [14][ 340/1320] lr: 2.0000e-02 eta: 6:30:30 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.2642 loss: 1.9953 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 1.9953 2023/02/17 14:35:56 - mmengine - INFO - Epoch(train) [14][ 360/1320] lr: 2.0000e-02 eta: 6:30:21 time: 0.4788 data_time: 0.0145 memory: 27031 grad_norm: 4.4139 loss: 2.0239 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.0239 2023/02/17 14:36:06 - mmengine - INFO - Epoch(train) [14][ 380/1320] lr: 2.0000e-02 eta: 6:30:11 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 4.3644 loss: 2.1514 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1514 2023/02/17 14:36:16 - mmengine - INFO - Epoch(train) [14][ 400/1320] lr: 2.0000e-02 eta: 6:30:01 time: 0.4790 data_time: 0.0146 memory: 27031 grad_norm: 4.1521 loss: 1.9922 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9922 2023/02/17 14:36:25 - mmengine - INFO - Epoch(train) [14][ 420/1320] lr: 2.0000e-02 eta: 6:29:51 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.2414 loss: 1.8077 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8077 2023/02/17 14:36:35 - mmengine - INFO - Epoch(train) [14][ 440/1320] lr: 2.0000e-02 eta: 6:29:41 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 4.2704 loss: 2.0891 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0891 2023/02/17 14:36:44 - mmengine - INFO - Epoch(train) [14][ 460/1320] lr: 2.0000e-02 eta: 6:29:31 time: 0.4788 data_time: 0.0147 memory: 27031 grad_norm: 4.0546 loss: 1.9169 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9169 2023/02/17 14:36:54 - mmengine - INFO - Epoch(train) [14][ 480/1320] lr: 2.0000e-02 eta: 6:29:21 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.2096 loss: 2.1454 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1454 2023/02/17 14:37:03 - mmengine - INFO - Epoch(train) [14][ 500/1320] lr: 2.0000e-02 eta: 6:29:11 time: 0.4793 data_time: 0.0130 memory: 27031 grad_norm: 4.3927 loss: 1.8967 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.8967 2023/02/17 14:37:13 - mmengine - INFO - Epoch(train) [14][ 520/1320] lr: 2.0000e-02 eta: 6:29:02 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.3261 loss: 1.7796 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.7796 2023/02/17 14:37:23 - mmengine - INFO - Epoch(train) [14][ 540/1320] lr: 2.0000e-02 eta: 6:28:52 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 4.2677 loss: 1.9111 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9111 2023/02/17 14:37:32 - mmengine - INFO - Epoch(train) [14][ 560/1320] lr: 2.0000e-02 eta: 6:28:42 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.3108 loss: 1.8014 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8014 2023/02/17 14:37:42 - mmengine - INFO - Epoch(train) [14][ 580/1320] lr: 2.0000e-02 eta: 6:28:32 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.2597 loss: 2.0662 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0662 2023/02/17 14:37:51 - mmengine - INFO - Epoch(train) [14][ 600/1320] lr: 2.0000e-02 eta: 6:28:22 time: 0.4792 data_time: 0.0144 memory: 27031 grad_norm: 4.2479 loss: 2.1596 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.1596 2023/02/17 14:38:01 - mmengine - INFO - Epoch(train) [14][ 620/1320] lr: 2.0000e-02 eta: 6:28:12 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2433 loss: 2.0059 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0059 2023/02/17 14:38:11 - mmengine - INFO - Epoch(train) [14][ 640/1320] lr: 2.0000e-02 eta: 6:28:03 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 4.1935 loss: 1.9372 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9372 2023/02/17 14:38:20 - mmengine - INFO - Epoch(train) [14][ 660/1320] lr: 2.0000e-02 eta: 6:27:53 time: 0.4796 data_time: 0.0136 memory: 27031 grad_norm: 4.2238 loss: 2.1491 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1491 2023/02/17 14:38:30 - mmengine - INFO - Epoch(train) [14][ 680/1320] lr: 2.0000e-02 eta: 6:27:43 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.1398 loss: 1.8864 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8864 2023/02/17 14:38:39 - mmengine - INFO - Epoch(train) [14][ 700/1320] lr: 2.0000e-02 eta: 6:27:33 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 4.3805 loss: 2.0647 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.0647 2023/02/17 14:38:49 - mmengine - INFO - Epoch(train) [14][ 720/1320] lr: 2.0000e-02 eta: 6:27:23 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.3276 loss: 2.0969 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.0969 2023/02/17 14:38:59 - mmengine - INFO - Epoch(train) [14][ 740/1320] lr: 2.0000e-02 eta: 6:27:13 time: 0.4800 data_time: 0.0152 memory: 27031 grad_norm: 4.1060 loss: 1.9985 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9985 2023/02/17 14:39:08 - mmengine - INFO - Epoch(train) [14][ 760/1320] lr: 2.0000e-02 eta: 6:27:03 time: 0.4782 data_time: 0.0140 memory: 27031 grad_norm: 4.2418 loss: 2.0892 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0892 2023/02/17 14:39:18 - mmengine - INFO - Epoch(train) [14][ 780/1320] lr: 2.0000e-02 eta: 6:26:54 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.1186 loss: 1.9040 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9040 2023/02/17 14:39:27 - mmengine - INFO - Epoch(train) [14][ 800/1320] lr: 2.0000e-02 eta: 6:26:44 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.1662 loss: 1.9702 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9702 2023/02/17 14:39:37 - mmengine - INFO - Epoch(train) [14][ 820/1320] lr: 2.0000e-02 eta: 6:26:34 time: 0.4788 data_time: 0.0138 memory: 27031 grad_norm: 4.2595 loss: 1.8641 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.8641 2023/02/17 14:39:47 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:39:47 - mmengine - INFO - Epoch(train) [14][ 840/1320] lr: 2.0000e-02 eta: 6:26:24 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.2234 loss: 2.1280 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1280 2023/02/17 14:39:56 - mmengine - INFO - Epoch(train) [14][ 860/1320] lr: 2.0000e-02 eta: 6:26:14 time: 0.4784 data_time: 0.0137 memory: 27031 grad_norm: 4.2923 loss: 2.0981 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0981 2023/02/17 14:40:06 - mmengine - INFO - Epoch(train) [14][ 880/1320] lr: 2.0000e-02 eta: 6:26:04 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.2838 loss: 1.9397 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9397 2023/02/17 14:40:15 - mmengine - INFO - Epoch(train) [14][ 900/1320] lr: 2.0000e-02 eta: 6:25:54 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 4.1527 loss: 1.8995 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8995 2023/02/17 14:40:25 - mmengine - INFO - Epoch(train) [14][ 920/1320] lr: 2.0000e-02 eta: 6:25:45 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.2322 loss: 2.0001 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 2.0001 2023/02/17 14:40:34 - mmengine - INFO - Epoch(train) [14][ 940/1320] lr: 2.0000e-02 eta: 6:25:35 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.2267 loss: 1.9935 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 1.9935 2023/02/17 14:40:44 - mmengine - INFO - Epoch(train) [14][ 960/1320] lr: 2.0000e-02 eta: 6:25:25 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.0583 loss: 1.9823 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9823 2023/02/17 14:40:54 - mmengine - INFO - Epoch(train) [14][ 980/1320] lr: 2.0000e-02 eta: 6:25:15 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.2915 loss: 1.8595 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8595 2023/02/17 14:41:03 - mmengine - INFO - Epoch(train) [14][1000/1320] lr: 2.0000e-02 eta: 6:25:05 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.3232 loss: 1.7727 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.7727 2023/02/17 14:41:13 - mmengine - INFO - Epoch(train) [14][1020/1320] lr: 2.0000e-02 eta: 6:24:55 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.2437 loss: 2.0027 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.0027 2023/02/17 14:41:22 - mmengine - INFO - Epoch(train) [14][1040/1320] lr: 2.0000e-02 eta: 6:24:46 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.1536 loss: 2.0794 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0794 2023/02/17 14:41:32 - mmengine - INFO - Epoch(train) [14][1060/1320] lr: 2.0000e-02 eta: 6:24:36 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.3050 loss: 2.0481 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0481 2023/02/17 14:41:42 - mmengine - INFO - Epoch(train) [14][1080/1320] lr: 2.0000e-02 eta: 6:24:26 time: 0.4799 data_time: 0.0138 memory: 27031 grad_norm: 4.1855 loss: 1.8441 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8441 2023/02/17 14:41:51 - mmengine - INFO - Epoch(train) [14][1100/1320] lr: 2.0000e-02 eta: 6:24:16 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 4.2953 loss: 2.1547 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1547 2023/02/17 14:42:01 - mmengine - INFO - Epoch(train) [14][1120/1320] lr: 2.0000e-02 eta: 6:24:06 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.3370 loss: 1.9936 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9936 2023/02/17 14:42:10 - mmengine - INFO - Epoch(train) [14][1140/1320] lr: 2.0000e-02 eta: 6:23:56 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.1623 loss: 2.0207 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0207 2023/02/17 14:42:20 - mmengine - INFO - Epoch(train) [14][1160/1320] lr: 2.0000e-02 eta: 6:23:47 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.3062 loss: 2.1035 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1035 2023/02/17 14:42:30 - mmengine - INFO - Epoch(train) [14][1180/1320] lr: 2.0000e-02 eta: 6:23:37 time: 0.4790 data_time: 0.0145 memory: 27031 grad_norm: 4.2752 loss: 1.8995 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8995 2023/02/17 14:42:39 - mmengine - INFO - Epoch(train) [14][1200/1320] lr: 2.0000e-02 eta: 6:23:27 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.2907 loss: 2.1440 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1440 2023/02/17 14:42:49 - mmengine - INFO - Epoch(train) [14][1220/1320] lr: 2.0000e-02 eta: 6:23:17 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.2613 loss: 2.1053 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1053 2023/02/17 14:42:58 - mmengine - INFO - Epoch(train) [14][1240/1320] lr: 2.0000e-02 eta: 6:23:07 time: 0.4805 data_time: 0.0154 memory: 27031 grad_norm: 4.1803 loss: 1.8683 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8683 2023/02/17 14:43:08 - mmengine - INFO - Epoch(train) [14][1260/1320] lr: 2.0000e-02 eta: 6:22:58 time: 0.4814 data_time: 0.0167 memory: 27031 grad_norm: 4.2617 loss: 2.0560 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0560 2023/02/17 14:43:18 - mmengine - INFO - Epoch(train) [14][1280/1320] lr: 2.0000e-02 eta: 6:22:48 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 4.3691 loss: 2.1099 top1_acc: 0.3125 top5_acc: 0.3750 loss_cls: 2.1099 2023/02/17 14:43:27 - mmengine - INFO - Epoch(train) [14][1300/1320] lr: 2.0000e-02 eta: 6:22:38 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 4.2871 loss: 1.9238 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9238 2023/02/17 14:43:37 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:43:37 - mmengine - INFO - Epoch(train) [14][1320/1320] lr: 2.0000e-02 eta: 6:22:28 time: 0.4737 data_time: 0.0159 memory: 27031 grad_norm: 4.3642 loss: 2.0307 top1_acc: 0.3636 top5_acc: 0.4545 loss_cls: 2.0307 2023/02/17 14:43:40 - mmengine - INFO - Epoch(val) [14][ 20/194] eta: 0:00:32 time: 0.1886 data_time: 0.0601 memory: 3265 2023/02/17 14:43:43 - mmengine - INFO - Epoch(val) [14][ 40/194] eta: 0:00:25 time: 0.1385 data_time: 0.0134 memory: 3265 2023/02/17 14:43:46 - mmengine - INFO - Epoch(val) [14][ 60/194] eta: 0:00:20 time: 0.1367 data_time: 0.0128 memory: 3265 2023/02/17 14:43:49 - mmengine - INFO - Epoch(val) [14][ 80/194] eta: 0:00:17 time: 0.1384 data_time: 0.0140 memory: 3265 2023/02/17 14:43:52 - mmengine - INFO - Epoch(val) [14][100/194] eta: 0:00:13 time: 0.1376 data_time: 0.0132 memory: 3265 2023/02/17 14:43:54 - mmengine - INFO - Epoch(val) [14][120/194] eta: 0:00:10 time: 0.1376 data_time: 0.0134 memory: 3265 2023/02/17 14:43:57 - mmengine - INFO - Epoch(val) [14][140/194] eta: 0:00:07 time: 0.1389 data_time: 0.0139 memory: 3265 2023/02/17 14:44:00 - mmengine - INFO - Epoch(val) [14][160/194] eta: 0:00:04 time: 0.1372 data_time: 0.0134 memory: 3265 2023/02/17 14:44:03 - mmengine - INFO - Epoch(val) [14][180/194] eta: 0:00:02 time: 0.1391 data_time: 0.0141 memory: 3265 2023/02/17 14:44:05 - mmengine - INFO - Epoch(val) [14][194/194] acc/top1: 0.4585 acc/top5: 0.7580 acc/mean1: 0.3884 2023/02/17 14:44:16 - mmengine - INFO - Epoch(train) [15][ 20/1320] lr: 2.0000e-02 eta: 6:22:21 time: 0.5375 data_time: 0.0658 memory: 27031 grad_norm: 4.2050 loss: 1.8442 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8442 2023/02/17 14:44:26 - mmengine - INFO - Epoch(train) [15][ 40/1320] lr: 2.0000e-02 eta: 6:22:11 time: 0.4791 data_time: 0.0146 memory: 27031 grad_norm: 4.1478 loss: 2.2380 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.2380 2023/02/17 14:44:35 - mmengine - INFO - Epoch(train) [15][ 60/1320] lr: 2.0000e-02 eta: 6:22:01 time: 0.4792 data_time: 0.0138 memory: 27031 grad_norm: 4.1091 loss: 1.9590 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9590 2023/02/17 14:44:45 - mmengine - INFO - Epoch(train) [15][ 80/1320] lr: 2.0000e-02 eta: 6:21:51 time: 0.4783 data_time: 0.0141 memory: 27031 grad_norm: 4.2906 loss: 1.8322 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8322 2023/02/17 14:44:54 - mmengine - INFO - Epoch(train) [15][ 100/1320] lr: 2.0000e-02 eta: 6:21:41 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.2978 loss: 1.9563 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9563 2023/02/17 14:45:04 - mmengine - INFO - Epoch(train) [15][ 120/1320] lr: 2.0000e-02 eta: 6:21:32 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 4.2873 loss: 1.8590 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8590 2023/02/17 14:45:13 - mmengine - INFO - Epoch(train) [15][ 140/1320] lr: 2.0000e-02 eta: 6:21:22 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.3633 loss: 2.0193 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.0193 2023/02/17 14:45:23 - mmengine - INFO - Epoch(train) [15][ 160/1320] lr: 2.0000e-02 eta: 6:21:12 time: 0.4789 data_time: 0.0145 memory: 27031 grad_norm: 4.2296 loss: 2.2854 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2854 2023/02/17 14:45:33 - mmengine - INFO - Epoch(train) [15][ 180/1320] lr: 2.0000e-02 eta: 6:21:02 time: 0.4782 data_time: 0.0141 memory: 27031 grad_norm: 4.1758 loss: 2.0567 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0567 2023/02/17 14:45:42 - mmengine - INFO - Epoch(train) [15][ 200/1320] lr: 2.0000e-02 eta: 6:20:52 time: 0.4786 data_time: 0.0138 memory: 27031 grad_norm: 4.1171 loss: 2.0788 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0788 2023/02/17 14:45:52 - mmengine - INFO - Epoch(train) [15][ 220/1320] lr: 2.0000e-02 eta: 6:20:42 time: 0.4791 data_time: 0.0143 memory: 27031 grad_norm: 4.2222 loss: 1.8554 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8554 2023/02/17 14:46:01 - mmengine - INFO - Epoch(train) [15][ 240/1320] lr: 2.0000e-02 eta: 6:20:32 time: 0.4801 data_time: 0.0154 memory: 27031 grad_norm: 4.1682 loss: 1.9856 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 1.9856 2023/02/17 14:46:11 - mmengine - INFO - Epoch(train) [15][ 260/1320] lr: 2.0000e-02 eta: 6:20:23 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.2353 loss: 1.9340 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9340 2023/02/17 14:46:21 - mmengine - INFO - Epoch(train) [15][ 280/1320] lr: 2.0000e-02 eta: 6:20:13 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.2854 loss: 1.9829 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9829 2023/02/17 14:46:30 - mmengine - INFO - Epoch(train) [15][ 300/1320] lr: 2.0000e-02 eta: 6:20:03 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.3064 loss: 1.7945 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7945 2023/02/17 14:46:40 - mmengine - INFO - Epoch(train) [15][ 320/1320] lr: 2.0000e-02 eta: 6:19:53 time: 0.4798 data_time: 0.0152 memory: 27031 grad_norm: 4.2146 loss: 1.7983 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.7983 2023/02/17 14:46:49 - mmengine - INFO - Epoch(train) [15][ 340/1320] lr: 2.0000e-02 eta: 6:19:43 time: 0.4788 data_time: 0.0139 memory: 27031 grad_norm: 4.2263 loss: 1.7981 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7981 2023/02/17 14:46:59 - mmengine - INFO - Epoch(train) [15][ 360/1320] lr: 2.0000e-02 eta: 6:19:33 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.2303 loss: 2.0658 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.0658 2023/02/17 14:47:08 - mmengine - INFO - Epoch(train) [15][ 380/1320] lr: 2.0000e-02 eta: 6:19:24 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.2166 loss: 1.9643 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9643 2023/02/17 14:47:18 - mmengine - INFO - Epoch(train) [15][ 400/1320] lr: 2.0000e-02 eta: 6:19:14 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.3149 loss: 1.8919 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8919 2023/02/17 14:47:28 - mmengine - INFO - Epoch(train) [15][ 420/1320] lr: 2.0000e-02 eta: 6:19:04 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.2886 loss: 2.0897 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0897 2023/02/17 14:47:37 - mmengine - INFO - Epoch(train) [15][ 440/1320] lr: 2.0000e-02 eta: 6:18:54 time: 0.4796 data_time: 0.0149 memory: 27031 grad_norm: 4.2435 loss: 1.9751 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9751 2023/02/17 14:47:47 - mmengine - INFO - Epoch(train) [15][ 460/1320] lr: 2.0000e-02 eta: 6:18:44 time: 0.4795 data_time: 0.0133 memory: 27031 grad_norm: 4.2009 loss: 1.7210 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.7210 2023/02/17 14:47:56 - mmengine - INFO - Epoch(train) [15][ 480/1320] lr: 2.0000e-02 eta: 6:18:35 time: 0.4804 data_time: 0.0156 memory: 27031 grad_norm: 4.2045 loss: 1.9261 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.9261 2023/02/17 14:48:06 - mmengine - INFO - Epoch(train) [15][ 500/1320] lr: 2.0000e-02 eta: 6:18:25 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.1825 loss: 1.7873 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7873 2023/02/17 14:48:16 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:48:16 - mmengine - INFO - Epoch(train) [15][ 520/1320] lr: 2.0000e-02 eta: 6:18:15 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.2707 loss: 1.8345 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8345 2023/02/17 14:48:25 - mmengine - INFO - Epoch(train) [15][ 540/1320] lr: 2.0000e-02 eta: 6:18:05 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.2461 loss: 1.9627 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9627 2023/02/17 14:48:35 - mmengine - INFO - Epoch(train) [15][ 560/1320] lr: 2.0000e-02 eta: 6:17:55 time: 0.4782 data_time: 0.0136 memory: 27031 grad_norm: 4.2249 loss: 1.8695 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8695 2023/02/17 14:48:44 - mmengine - INFO - Epoch(train) [15][ 580/1320] lr: 2.0000e-02 eta: 6:17:45 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2771 loss: 2.1307 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 2.1307 2023/02/17 14:48:54 - mmengine - INFO - Epoch(train) [15][ 600/1320] lr: 2.0000e-02 eta: 6:17:36 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.2447 loss: 2.0082 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0082 2023/02/17 14:49:04 - mmengine - INFO - Epoch(train) [15][ 620/1320] lr: 2.0000e-02 eta: 6:17:26 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.2027 loss: 1.7984 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.7984 2023/02/17 14:49:13 - mmengine - INFO - Epoch(train) [15][ 640/1320] lr: 2.0000e-02 eta: 6:17:16 time: 0.4791 data_time: 0.0146 memory: 27031 grad_norm: 4.3263 loss: 2.0380 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 2.0380 2023/02/17 14:49:23 - mmengine - INFO - Epoch(train) [15][ 660/1320] lr: 2.0000e-02 eta: 6:17:06 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.3901 loss: 1.9501 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9501 2023/02/17 14:49:32 - mmengine - INFO - Epoch(train) [15][ 680/1320] lr: 2.0000e-02 eta: 6:16:56 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 4.3956 loss: 1.9748 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9748 2023/02/17 14:49:42 - mmengine - INFO - Epoch(train) [15][ 700/1320] lr: 2.0000e-02 eta: 6:16:46 time: 0.4792 data_time: 0.0144 memory: 27031 grad_norm: 4.2411 loss: 2.0744 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 2.0744 2023/02/17 14:49:52 - mmengine - INFO - Epoch(train) [15][ 720/1320] lr: 2.0000e-02 eta: 6:16:37 time: 0.4792 data_time: 0.0134 memory: 27031 grad_norm: 4.2347 loss: 1.9285 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9285 2023/02/17 14:50:01 - mmengine - INFO - Epoch(train) [15][ 740/1320] lr: 2.0000e-02 eta: 6:16:27 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.2079 loss: 1.9070 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9070 2023/02/17 14:50:11 - mmengine - INFO - Epoch(train) [15][ 760/1320] lr: 2.0000e-02 eta: 6:16:17 time: 0.4790 data_time: 0.0144 memory: 27031 grad_norm: 4.3406 loss: 1.9518 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9518 2023/02/17 14:50:20 - mmengine - INFO - Epoch(train) [15][ 780/1320] lr: 2.0000e-02 eta: 6:16:07 time: 0.4786 data_time: 0.0140 memory: 27031 grad_norm: 4.2239 loss: 1.9021 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9021 2023/02/17 14:50:30 - mmengine - INFO - Epoch(train) [15][ 800/1320] lr: 2.0000e-02 eta: 6:15:57 time: 0.4800 data_time: 0.0151 memory: 27031 grad_norm: 4.2358 loss: 2.1431 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.1431 2023/02/17 14:50:39 - mmengine - INFO - Epoch(train) [15][ 820/1320] lr: 2.0000e-02 eta: 6:15:47 time: 0.4788 data_time: 0.0138 memory: 27031 grad_norm: 4.0896 loss: 1.9761 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9761 2023/02/17 14:50:49 - mmengine - INFO - Epoch(train) [15][ 840/1320] lr: 2.0000e-02 eta: 6:15:38 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2473 loss: 1.9591 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9591 2023/02/17 14:50:59 - mmengine - INFO - Epoch(train) [15][ 860/1320] lr: 2.0000e-02 eta: 6:15:28 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2162 loss: 2.0178 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0178 2023/02/17 14:51:08 - mmengine - INFO - Epoch(train) [15][ 880/1320] lr: 2.0000e-02 eta: 6:15:18 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 4.3256 loss: 2.0526 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0526 2023/02/17 14:51:18 - mmengine - INFO - Epoch(train) [15][ 900/1320] lr: 2.0000e-02 eta: 6:15:08 time: 0.4802 data_time: 0.0149 memory: 27031 grad_norm: 4.2225 loss: 1.8869 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8869 2023/02/17 14:51:27 - mmengine - INFO - Epoch(train) [15][ 920/1320] lr: 2.0000e-02 eta: 6:14:58 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.3330 loss: 2.0344 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0344 2023/02/17 14:51:37 - mmengine - INFO - Epoch(train) [15][ 940/1320] lr: 2.0000e-02 eta: 6:14:49 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 4.3235 loss: 2.1255 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.1255 2023/02/17 14:51:47 - mmengine - INFO - Epoch(train) [15][ 960/1320] lr: 2.0000e-02 eta: 6:14:39 time: 0.4799 data_time: 0.0153 memory: 27031 grad_norm: 4.1683 loss: 2.1148 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.1148 2023/02/17 14:51:56 - mmengine - INFO - Epoch(train) [15][ 980/1320] lr: 2.0000e-02 eta: 6:14:29 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.2229 loss: 1.8757 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8757 2023/02/17 14:52:06 - mmengine - INFO - Epoch(train) [15][1000/1320] lr: 2.0000e-02 eta: 6:14:19 time: 0.4800 data_time: 0.0136 memory: 27031 grad_norm: 4.3439 loss: 1.9500 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9500 2023/02/17 14:52:15 - mmengine - INFO - Epoch(train) [15][1020/1320] lr: 2.0000e-02 eta: 6:14:09 time: 0.4811 data_time: 0.0160 memory: 27031 grad_norm: 4.2760 loss: 1.9026 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9026 2023/02/17 14:52:25 - mmengine - INFO - Epoch(train) [15][1040/1320] lr: 2.0000e-02 eta: 6:14:00 time: 0.4788 data_time: 0.0130 memory: 27031 grad_norm: 4.3259 loss: 1.8359 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8359 2023/02/17 14:52:35 - mmengine - INFO - Epoch(train) [15][1060/1320] lr: 2.0000e-02 eta: 6:13:50 time: 0.4797 data_time: 0.0149 memory: 27031 grad_norm: 4.1963 loss: 1.9629 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9629 2023/02/17 14:52:44 - mmengine - INFO - Epoch(train) [15][1080/1320] lr: 2.0000e-02 eta: 6:13:40 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.3191 loss: 2.0271 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.0271 2023/02/17 14:52:54 - mmengine - INFO - Epoch(train) [15][1100/1320] lr: 2.0000e-02 eta: 6:13:30 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 4.3078 loss: 2.0136 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.0136 2023/02/17 14:53:03 - mmengine - INFO - Epoch(train) [15][1120/1320] lr: 2.0000e-02 eta: 6:13:20 time: 0.4803 data_time: 0.0151 memory: 27031 grad_norm: 4.2144 loss: 1.8110 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.8110 2023/02/17 14:53:13 - mmengine - INFO - Epoch(train) [15][1140/1320] lr: 2.0000e-02 eta: 6:13:11 time: 0.4794 data_time: 0.0148 memory: 27031 grad_norm: 4.3995 loss: 1.8796 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8796 2023/02/17 14:53:23 - mmengine - INFO - Epoch(train) [15][1160/1320] lr: 2.0000e-02 eta: 6:13:01 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 4.2351 loss: 1.8717 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8717 2023/02/17 14:53:32 - mmengine - INFO - Epoch(train) [15][1180/1320] lr: 2.0000e-02 eta: 6:12:51 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.1910 loss: 1.9440 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9440 2023/02/17 14:53:42 - mmengine - INFO - Epoch(train) [15][1200/1320] lr: 2.0000e-02 eta: 6:12:41 time: 0.4783 data_time: 0.0134 memory: 27031 grad_norm: 4.3033 loss: 1.8491 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8491 2023/02/17 14:53:51 - mmengine - INFO - Epoch(train) [15][1220/1320] lr: 2.0000e-02 eta: 6:12:31 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 4.3115 loss: 1.8815 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8815 2023/02/17 14:54:01 - mmengine - INFO - Epoch(train) [15][1240/1320] lr: 2.0000e-02 eta: 6:12:22 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2105 loss: 1.6806 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.6806 2023/02/17 14:54:11 - mmengine - INFO - Epoch(train) [15][1260/1320] lr: 2.0000e-02 eta: 6:12:12 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.2529 loss: 1.9570 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9570 2023/02/17 14:54:20 - mmengine - INFO - Epoch(train) [15][1280/1320] lr: 2.0000e-02 eta: 6:12:02 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.3440 loss: 1.8553 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8553 2023/02/17 14:54:30 - mmengine - INFO - Epoch(train) [15][1300/1320] lr: 2.0000e-02 eta: 6:11:52 time: 0.4796 data_time: 0.0152 memory: 27031 grad_norm: 4.4148 loss: 1.8468 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8468 2023/02/17 14:54:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:54:39 - mmengine - INFO - Epoch(train) [15][1320/1320] lr: 2.0000e-02 eta: 6:11:42 time: 0.4740 data_time: 0.0153 memory: 27031 grad_norm: 4.3697 loss: 1.9810 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 1.9810 2023/02/17 14:54:39 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/02/17 14:54:44 - mmengine - INFO - Epoch(val) [15][ 20/194] eta: 0:00:31 time: 0.1837 data_time: 0.0569 memory: 3265 2023/02/17 14:54:47 - mmengine - INFO - Epoch(val) [15][ 40/194] eta: 0:00:24 time: 0.1377 data_time: 0.0128 memory: 3265 2023/02/17 14:54:50 - mmengine - INFO - Epoch(val) [15][ 60/194] eta: 0:00:20 time: 0.1375 data_time: 0.0133 memory: 3265 2023/02/17 14:54:52 - mmengine - INFO - Epoch(val) [15][ 80/194] eta: 0:00:17 time: 0.1386 data_time: 0.0138 memory: 3265 2023/02/17 14:54:55 - mmengine - INFO - Epoch(val) [15][100/194] eta: 0:00:13 time: 0.1388 data_time: 0.0141 memory: 3265 2023/02/17 14:54:58 - mmengine - INFO - Epoch(val) [15][120/194] eta: 0:00:10 time: 0.1386 data_time: 0.0135 memory: 3265 2023/02/17 14:55:01 - mmengine - INFO - Epoch(val) [15][140/194] eta: 0:00:07 time: 0.1387 data_time: 0.0140 memory: 3265 2023/02/17 14:55:04 - mmengine - INFO - Epoch(val) [15][160/194] eta: 0:00:04 time: 0.1412 data_time: 0.0143 memory: 3265 2023/02/17 14:55:06 - mmengine - INFO - Epoch(val) [15][180/194] eta: 0:00:02 time: 0.1349 data_time: 0.0123 memory: 3265 2023/02/17 14:55:09 - mmengine - INFO - Epoch(val) [15][194/194] acc/top1: 0.4593 acc/top5: 0.7585 acc/mean1: 0.3928 2023/02/17 14:55:20 - mmengine - INFO - Epoch(train) [16][ 20/1320] lr: 2.0000e-02 eta: 6:11:35 time: 0.5339 data_time: 0.0587 memory: 27031 grad_norm: 4.2414 loss: 1.9757 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9757 2023/02/17 14:55:29 - mmengine - INFO - Epoch(train) [16][ 40/1320] lr: 2.0000e-02 eta: 6:11:25 time: 0.4785 data_time: 0.0139 memory: 27031 grad_norm: 4.1770 loss: 1.7416 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.7416 2023/02/17 14:55:39 - mmengine - INFO - Epoch(train) [16][ 60/1320] lr: 2.0000e-02 eta: 6:11:15 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.3237 loss: 1.7894 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.7894 2023/02/17 14:55:48 - mmengine - INFO - Epoch(train) [16][ 80/1320] lr: 2.0000e-02 eta: 6:11:05 time: 0.4800 data_time: 0.0156 memory: 27031 grad_norm: 4.2244 loss: 1.9573 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9573 2023/02/17 14:55:58 - mmengine - INFO - Epoch(train) [16][ 100/1320] lr: 2.0000e-02 eta: 6:10:55 time: 0.4785 data_time: 0.0137 memory: 27031 grad_norm: 4.3900 loss: 1.7013 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.7013 2023/02/17 14:56:07 - mmengine - INFO - Epoch(train) [16][ 120/1320] lr: 2.0000e-02 eta: 6:10:46 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.2225 loss: 1.9071 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9071 2023/02/17 14:56:17 - mmengine - INFO - Epoch(train) [16][ 140/1320] lr: 2.0000e-02 eta: 6:10:36 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.3116 loss: 1.9832 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9832 2023/02/17 14:56:27 - mmengine - INFO - Epoch(train) [16][ 160/1320] lr: 2.0000e-02 eta: 6:10:26 time: 0.4785 data_time: 0.0141 memory: 27031 grad_norm: 4.3733 loss: 1.9035 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9035 2023/02/17 14:56:36 - mmengine - INFO - Epoch(train) [16][ 180/1320] lr: 2.0000e-02 eta: 6:10:16 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.3169 loss: 2.0857 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0857 2023/02/17 14:56:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 14:56:46 - mmengine - INFO - Epoch(train) [16][ 200/1320] lr: 2.0000e-02 eta: 6:10:06 time: 0.4794 data_time: 0.0138 memory: 27031 grad_norm: 4.2420 loss: 2.0051 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0051 2023/02/17 14:56:55 - mmengine - INFO - Epoch(train) [16][ 220/1320] lr: 2.0000e-02 eta: 6:09:57 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.2222 loss: 2.0401 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.0401 2023/02/17 14:57:05 - mmengine - INFO - Epoch(train) [16][ 240/1320] lr: 2.0000e-02 eta: 6:09:47 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.2408 loss: 1.7926 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7926 2023/02/17 14:57:15 - mmengine - INFO - Epoch(train) [16][ 260/1320] lr: 2.0000e-02 eta: 6:09:37 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.3218 loss: 1.8360 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8360 2023/02/17 14:57:24 - mmengine - INFO - Epoch(train) [16][ 280/1320] lr: 2.0000e-02 eta: 6:09:27 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.2346 loss: 2.0192 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0192 2023/02/17 14:57:34 - mmengine - INFO - Epoch(train) [16][ 300/1320] lr: 2.0000e-02 eta: 6:09:17 time: 0.4791 data_time: 0.0139 memory: 27031 grad_norm: 4.1760 loss: 1.8460 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8460 2023/02/17 14:57:43 - mmengine - INFO - Epoch(train) [16][ 320/1320] lr: 2.0000e-02 eta: 6:09:07 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.3178 loss: 1.8915 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8915 2023/02/17 14:57:53 - mmengine - INFO - Epoch(train) [16][ 340/1320] lr: 2.0000e-02 eta: 6:08:58 time: 0.4797 data_time: 0.0150 memory: 27031 grad_norm: 4.3537 loss: 2.1236 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1236 2023/02/17 14:58:03 - mmengine - INFO - Epoch(train) [16][ 360/1320] lr: 2.0000e-02 eta: 6:08:48 time: 0.4791 data_time: 0.0135 memory: 27031 grad_norm: 4.2896 loss: 1.9549 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9549 2023/02/17 14:58:12 - mmengine - INFO - Epoch(train) [16][ 380/1320] lr: 2.0000e-02 eta: 6:08:38 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.2518 loss: 1.8365 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8365 2023/02/17 14:58:22 - mmengine - INFO - Epoch(train) [16][ 400/1320] lr: 2.0000e-02 eta: 6:08:28 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.1898 loss: 1.8848 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.8848 2023/02/17 14:58:31 - mmengine - INFO - Epoch(train) [16][ 420/1320] lr: 2.0000e-02 eta: 6:08:18 time: 0.4783 data_time: 0.0135 memory: 27031 grad_norm: 4.1992 loss: 1.8891 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8891 2023/02/17 14:58:41 - mmengine - INFO - Epoch(train) [16][ 440/1320] lr: 2.0000e-02 eta: 6:08:09 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 4.3396 loss: 1.8736 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8736 2023/02/17 14:58:50 - mmengine - INFO - Epoch(train) [16][ 460/1320] lr: 2.0000e-02 eta: 6:07:59 time: 0.4790 data_time: 0.0143 memory: 27031 grad_norm: 4.2672 loss: 1.9795 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9795 2023/02/17 14:59:00 - mmengine - INFO - Epoch(train) [16][ 480/1320] lr: 2.0000e-02 eta: 6:07:49 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 4.2647 loss: 1.9066 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9066 2023/02/17 14:59:10 - mmengine - INFO - Epoch(train) [16][ 500/1320] lr: 2.0000e-02 eta: 6:07:39 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.3154 loss: 1.8098 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8098 2023/02/17 14:59:19 - mmengine - INFO - Epoch(train) [16][ 520/1320] lr: 2.0000e-02 eta: 6:07:29 time: 0.4793 data_time: 0.0136 memory: 27031 grad_norm: 4.2657 loss: 1.7584 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.7584 2023/02/17 14:59:29 - mmengine - INFO - Epoch(train) [16][ 540/1320] lr: 2.0000e-02 eta: 6:07:20 time: 0.4795 data_time: 0.0147 memory: 27031 grad_norm: 4.2139 loss: 2.1216 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 2.1216 2023/02/17 14:59:38 - mmengine - INFO - Epoch(train) [16][ 560/1320] lr: 2.0000e-02 eta: 6:07:10 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.3047 loss: 1.9683 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9683 2023/02/17 14:59:48 - mmengine - INFO - Epoch(train) [16][ 580/1320] lr: 2.0000e-02 eta: 6:07:00 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.2804 loss: 1.8586 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 1.8586 2023/02/17 14:59:58 - mmengine - INFO - Epoch(train) [16][ 600/1320] lr: 2.0000e-02 eta: 6:06:50 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 4.2820 loss: 2.0637 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0637 2023/02/17 15:00:07 - mmengine - INFO - Epoch(train) [16][ 620/1320] lr: 2.0000e-02 eta: 6:06:41 time: 0.4786 data_time: 0.0141 memory: 27031 grad_norm: 4.1883 loss: 1.9081 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9081 2023/02/17 15:00:17 - mmengine - INFO - Epoch(train) [16][ 640/1320] lr: 2.0000e-02 eta: 6:06:31 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.3721 loss: 1.6657 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.6657 2023/02/17 15:00:26 - mmengine - INFO - Epoch(train) [16][ 660/1320] lr: 2.0000e-02 eta: 6:06:21 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.3861 loss: 1.8869 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8869 2023/02/17 15:00:36 - mmengine - INFO - Epoch(train) [16][ 680/1320] lr: 2.0000e-02 eta: 6:06:11 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2735 loss: 1.9384 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9384 2023/02/17 15:00:46 - mmengine - INFO - Epoch(train) [16][ 700/1320] lr: 2.0000e-02 eta: 6:06:01 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2605 loss: 1.8828 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8828 2023/02/17 15:00:55 - mmengine - INFO - Epoch(train) [16][ 720/1320] lr: 2.0000e-02 eta: 6:05:52 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.2486 loss: 1.9589 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9589 2023/02/17 15:01:05 - mmengine - INFO - Epoch(train) [16][ 740/1320] lr: 2.0000e-02 eta: 6:05:42 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.2178 loss: 1.7734 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.7734 2023/02/17 15:01:14 - mmengine - INFO - Epoch(train) [16][ 760/1320] lr: 2.0000e-02 eta: 6:05:32 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.2486 loss: 1.8071 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8071 2023/02/17 15:01:24 - mmengine - INFO - Epoch(train) [16][ 780/1320] lr: 2.0000e-02 eta: 6:05:22 time: 0.4788 data_time: 0.0134 memory: 27031 grad_norm: 4.2292 loss: 1.9701 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9701 2023/02/17 15:01:34 - mmengine - INFO - Epoch(train) [16][ 800/1320] lr: 2.0000e-02 eta: 6:05:12 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.1946 loss: 1.8275 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8275 2023/02/17 15:01:43 - mmengine - INFO - Epoch(train) [16][ 820/1320] lr: 2.0000e-02 eta: 6:05:03 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.3389 loss: 1.9288 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9288 2023/02/17 15:01:53 - mmengine - INFO - Epoch(train) [16][ 840/1320] lr: 2.0000e-02 eta: 6:04:53 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.3541 loss: 2.0158 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0158 2023/02/17 15:02:02 - mmengine - INFO - Epoch(train) [16][ 860/1320] lr: 2.0000e-02 eta: 6:04:43 time: 0.4799 data_time: 0.0141 memory: 27031 grad_norm: 4.2989 loss: 2.0008 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0008 2023/02/17 15:02:12 - mmengine - INFO - Epoch(train) [16][ 880/1320] lr: 2.0000e-02 eta: 6:04:33 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 4.3673 loss: 2.1035 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.1035 2023/02/17 15:02:22 - mmengine - INFO - Epoch(train) [16][ 900/1320] lr: 2.0000e-02 eta: 6:04:23 time: 0.4785 data_time: 0.0137 memory: 27031 grad_norm: 4.2328 loss: 1.9889 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9889 2023/02/17 15:02:31 - mmengine - INFO - Epoch(train) [16][ 920/1320] lr: 2.0000e-02 eta: 6:04:14 time: 0.4801 data_time: 0.0150 memory: 27031 grad_norm: 4.2136 loss: 1.8045 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8045 2023/02/17 15:02:41 - mmengine - INFO - Epoch(train) [16][ 940/1320] lr: 2.0000e-02 eta: 6:04:04 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.2550 loss: 1.9359 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9359 2023/02/17 15:02:50 - mmengine - INFO - Epoch(train) [16][ 960/1320] lr: 2.0000e-02 eta: 6:03:54 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.2448 loss: 2.0393 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0393 2023/02/17 15:03:00 - mmengine - INFO - Epoch(train) [16][ 980/1320] lr: 2.0000e-02 eta: 6:03:44 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.1951 loss: 2.1068 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1068 2023/02/17 15:03:09 - mmengine - INFO - Epoch(train) [16][1000/1320] lr: 2.0000e-02 eta: 6:03:35 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.3057 loss: 1.8864 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8864 2023/02/17 15:03:19 - mmengine - INFO - Epoch(train) [16][1020/1320] lr: 2.0000e-02 eta: 6:03:25 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.2378 loss: 1.8991 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8991 2023/02/17 15:03:29 - mmengine - INFO - Epoch(train) [16][1040/1320] lr: 2.0000e-02 eta: 6:03:15 time: 0.4811 data_time: 0.0161 memory: 27031 grad_norm: 4.3052 loss: 2.0272 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0272 2023/02/17 15:03:38 - mmengine - INFO - Epoch(train) [16][1060/1320] lr: 2.0000e-02 eta: 6:03:05 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.3958 loss: 2.0405 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0405 2023/02/17 15:03:48 - mmengine - INFO - Epoch(train) [16][1080/1320] lr: 2.0000e-02 eta: 6:02:56 time: 0.4810 data_time: 0.0154 memory: 27031 grad_norm: 4.1777 loss: 1.7268 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.7268 2023/02/17 15:03:58 - mmengine - INFO - Epoch(train) [16][1100/1320] lr: 2.0000e-02 eta: 6:02:46 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.2478 loss: 1.9170 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9170 2023/02/17 15:04:07 - mmengine - INFO - Epoch(train) [16][1120/1320] lr: 2.0000e-02 eta: 6:02:36 time: 0.4797 data_time: 0.0150 memory: 27031 grad_norm: 4.3157 loss: 1.9179 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9179 2023/02/17 15:04:17 - mmengine - INFO - Epoch(train) [16][1140/1320] lr: 2.0000e-02 eta: 6:02:26 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.3284 loss: 2.0156 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0156 2023/02/17 15:04:26 - mmengine - INFO - Epoch(train) [16][1160/1320] lr: 2.0000e-02 eta: 6:02:16 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.1583 loss: 1.9159 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9159 2023/02/17 15:04:36 - mmengine - INFO - Epoch(train) [16][1180/1320] lr: 2.0000e-02 eta: 6:02:07 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.2690 loss: 1.8815 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8815 2023/02/17 15:04:45 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:04:45 - mmengine - INFO - Epoch(train) [16][1200/1320] lr: 2.0000e-02 eta: 6:01:57 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.2900 loss: 1.8907 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8907 2023/02/17 15:04:55 - mmengine - INFO - Epoch(train) [16][1220/1320] lr: 2.0000e-02 eta: 6:01:47 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.2736 loss: 1.8990 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8990 2023/02/17 15:05:05 - mmengine - INFO - Epoch(train) [16][1240/1320] lr: 2.0000e-02 eta: 6:01:37 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 4.3815 loss: 1.8914 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8914 2023/02/17 15:05:14 - mmengine - INFO - Epoch(train) [16][1260/1320] lr: 2.0000e-02 eta: 6:01:27 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 4.2511 loss: 1.8958 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8958 2023/02/17 15:05:24 - mmengine - INFO - Epoch(train) [16][1280/1320] lr: 2.0000e-02 eta: 6:01:18 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.1486 loss: 1.6822 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.6822 2023/02/17 15:05:33 - mmengine - INFO - Epoch(train) [16][1300/1320] lr: 2.0000e-02 eta: 6:01:08 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.2352 loss: 1.9434 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9434 2023/02/17 15:05:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:05:43 - mmengine - INFO - Epoch(train) [16][1320/1320] lr: 2.0000e-02 eta: 6:00:58 time: 0.4735 data_time: 0.0153 memory: 27031 grad_norm: 4.3869 loss: 2.1330 top1_acc: 0.9091 top5_acc: 0.9091 loss_cls: 2.1330 2023/02/17 15:05:47 - mmengine - INFO - Epoch(val) [16][ 20/194] eta: 0:00:33 time: 0.1927 data_time: 0.0669 memory: 3265 2023/02/17 15:05:50 - mmengine - INFO - Epoch(val) [16][ 40/194] eta: 0:00:25 time: 0.1382 data_time: 0.0137 memory: 3265 2023/02/17 15:05:52 - mmengine - INFO - Epoch(val) [16][ 60/194] eta: 0:00:21 time: 0.1407 data_time: 0.0158 memory: 3265 2023/02/17 15:05:55 - mmengine - INFO - Epoch(val) [16][ 80/194] eta: 0:00:17 time: 0.1367 data_time: 0.0130 memory: 3265 2023/02/17 15:05:58 - mmengine - INFO - Epoch(val) [16][100/194] eta: 0:00:14 time: 0.1376 data_time: 0.0140 memory: 3265 2023/02/17 15:06:01 - mmengine - INFO - Epoch(val) [16][120/194] eta: 0:00:10 time: 0.1379 data_time: 0.0135 memory: 3265 2023/02/17 15:06:03 - mmengine - INFO - Epoch(val) [16][140/194] eta: 0:00:07 time: 0.1366 data_time: 0.0128 memory: 3265 2023/02/17 15:06:06 - mmengine - INFO - Epoch(val) [16][160/194] eta: 0:00:04 time: 0.1374 data_time: 0.0134 memory: 3265 2023/02/17 15:06:09 - mmengine - INFO - Epoch(val) [16][180/194] eta: 0:00:02 time: 0.1357 data_time: 0.0126 memory: 3265 2023/02/17 15:06:12 - mmengine - INFO - Epoch(val) [16][194/194] acc/top1: 0.4646 acc/top5: 0.7592 acc/mean1: 0.3946 2023/02/17 15:06:22 - mmengine - INFO - Epoch(train) [17][ 20/1320] lr: 2.0000e-02 eta: 6:00:50 time: 0.5344 data_time: 0.0606 memory: 27031 grad_norm: 4.1845 loss: 1.8830 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8830 2023/02/17 15:06:32 - mmengine - INFO - Epoch(train) [17][ 40/1320] lr: 2.0000e-02 eta: 6:00:41 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.2089 loss: 1.6270 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.6270 2023/02/17 15:06:42 - mmengine - INFO - Epoch(train) [17][ 60/1320] lr: 2.0000e-02 eta: 6:00:31 time: 0.4774 data_time: 0.0138 memory: 27031 grad_norm: 4.2849 loss: 1.8495 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8495 2023/02/17 15:06:51 - mmengine - INFO - Epoch(train) [17][ 80/1320] lr: 2.0000e-02 eta: 6:00:21 time: 0.4789 data_time: 0.0145 memory: 27031 grad_norm: 4.3322 loss: 1.9177 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9177 2023/02/17 15:07:01 - mmengine - INFO - Epoch(train) [17][ 100/1320] lr: 2.0000e-02 eta: 6:00:11 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.3604 loss: 1.9963 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9963 2023/02/17 15:07:10 - mmengine - INFO - Epoch(train) [17][ 120/1320] lr: 2.0000e-02 eta: 6:00:01 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2423 loss: 1.9093 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9093 2023/02/17 15:07:20 - mmengine - INFO - Epoch(train) [17][ 140/1320] lr: 2.0000e-02 eta: 5:59:52 time: 0.4805 data_time: 0.0152 memory: 27031 grad_norm: 4.3479 loss: 2.0037 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0037 2023/02/17 15:07:29 - mmengine - INFO - Epoch(train) [17][ 160/1320] lr: 2.0000e-02 eta: 5:59:42 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.3161 loss: 2.0334 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 2.0334 2023/02/17 15:07:39 - mmengine - INFO - Epoch(train) [17][ 180/1320] lr: 2.0000e-02 eta: 5:59:32 time: 0.4796 data_time: 0.0139 memory: 27031 grad_norm: 4.2893 loss: 1.8868 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8868 2023/02/17 15:07:49 - mmengine - INFO - Epoch(train) [17][ 200/1320] lr: 2.0000e-02 eta: 5:59:22 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2102 loss: 1.7262 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.7262 2023/02/17 15:07:58 - mmengine - INFO - Epoch(train) [17][ 220/1320] lr: 2.0000e-02 eta: 5:59:13 time: 0.4790 data_time: 0.0136 memory: 27031 grad_norm: 4.2958 loss: 2.0502 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0502 2023/02/17 15:08:08 - mmengine - INFO - Epoch(train) [17][ 240/1320] lr: 2.0000e-02 eta: 5:59:03 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2216 loss: 1.7207 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7207 2023/02/17 15:08:17 - mmengine - INFO - Epoch(train) [17][ 260/1320] lr: 2.0000e-02 eta: 5:58:53 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.2843 loss: 2.0424 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 2.0424 2023/02/17 15:08:27 - mmengine - INFO - Epoch(train) [17][ 280/1320] lr: 2.0000e-02 eta: 5:58:43 time: 0.4803 data_time: 0.0155 memory: 27031 grad_norm: 4.4023 loss: 1.9912 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9912 2023/02/17 15:08:37 - mmengine - INFO - Epoch(train) [17][ 300/1320] lr: 2.0000e-02 eta: 5:58:33 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.4025 loss: 1.7435 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.7435 2023/02/17 15:08:46 - mmengine - INFO - Epoch(train) [17][ 320/1320] lr: 2.0000e-02 eta: 5:58:24 time: 0.4787 data_time: 0.0131 memory: 27031 grad_norm: 4.2675 loss: 1.8466 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8466 2023/02/17 15:08:56 - mmengine - INFO - Epoch(train) [17][ 340/1320] lr: 2.0000e-02 eta: 5:58:14 time: 0.4795 data_time: 0.0148 memory: 27031 grad_norm: 4.3296 loss: 1.9289 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9289 2023/02/17 15:09:05 - mmengine - INFO - Epoch(train) [17][ 360/1320] lr: 2.0000e-02 eta: 5:58:04 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2384 loss: 1.7753 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.7753 2023/02/17 15:09:15 - mmengine - INFO - Epoch(train) [17][ 380/1320] lr: 2.0000e-02 eta: 5:57:54 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.3353 loss: 1.8508 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.8508 2023/02/17 15:09:25 - mmengine - INFO - Epoch(train) [17][ 400/1320] lr: 2.0000e-02 eta: 5:57:45 time: 0.4801 data_time: 0.0153 memory: 27031 grad_norm: 4.1756 loss: 1.8368 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8368 2023/02/17 15:09:34 - mmengine - INFO - Epoch(train) [17][ 420/1320] lr: 2.0000e-02 eta: 5:57:35 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.1769 loss: 1.9849 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9849 2023/02/17 15:09:44 - mmengine - INFO - Epoch(train) [17][ 440/1320] lr: 2.0000e-02 eta: 5:57:25 time: 0.4787 data_time: 0.0136 memory: 27031 grad_norm: 4.3097 loss: 1.6620 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.6620 2023/02/17 15:09:53 - mmengine - INFO - Epoch(train) [17][ 460/1320] lr: 2.0000e-02 eta: 5:57:15 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.1987 loss: 1.9994 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 1.9994 2023/02/17 15:10:03 - mmengine - INFO - Epoch(train) [17][ 480/1320] lr: 2.0000e-02 eta: 5:57:05 time: 0.4794 data_time: 0.0145 memory: 27031 grad_norm: 4.4008 loss: 1.7217 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7217 2023/02/17 15:10:12 - mmengine - INFO - Epoch(train) [17][ 500/1320] lr: 2.0000e-02 eta: 5:56:56 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2789 loss: 2.0848 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.0848 2023/02/17 15:10:22 - mmengine - INFO - Epoch(train) [17][ 520/1320] lr: 2.0000e-02 eta: 5:56:46 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.3847 loss: 1.9811 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9811 2023/02/17 15:10:32 - mmengine - INFO - Epoch(train) [17][ 540/1320] lr: 2.0000e-02 eta: 5:56:36 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.2919 loss: 1.8857 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8857 2023/02/17 15:10:41 - mmengine - INFO - Epoch(train) [17][ 560/1320] lr: 2.0000e-02 eta: 5:56:26 time: 0.4791 data_time: 0.0148 memory: 27031 grad_norm: 4.2998 loss: 1.7839 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.7839 2023/02/17 15:10:51 - mmengine - INFO - Epoch(train) [17][ 580/1320] lr: 2.0000e-02 eta: 5:56:16 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.3352 loss: 1.8108 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8108 2023/02/17 15:11:00 - mmengine - INFO - Epoch(train) [17][ 600/1320] lr: 2.0000e-02 eta: 5:56:07 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 4.3286 loss: 1.7635 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.7635 2023/02/17 15:11:10 - mmengine - INFO - Epoch(train) [17][ 620/1320] lr: 2.0000e-02 eta: 5:55:57 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.3394 loss: 1.9629 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.9629 2023/02/17 15:11:20 - mmengine - INFO - Epoch(train) [17][ 640/1320] lr: 2.0000e-02 eta: 5:55:47 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.3433 loss: 1.9257 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9257 2023/02/17 15:11:29 - mmengine - INFO - Epoch(train) [17][ 660/1320] lr: 2.0000e-02 eta: 5:55:37 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.2975 loss: 2.0303 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0303 2023/02/17 15:11:39 - mmengine - INFO - Epoch(train) [17][ 680/1320] lr: 2.0000e-02 eta: 5:55:27 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.1874 loss: 1.8475 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8475 2023/02/17 15:11:48 - mmengine - INFO - Epoch(train) [17][ 700/1320] lr: 2.0000e-02 eta: 5:55:18 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.1869 loss: 1.8921 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8921 2023/02/17 15:11:58 - mmengine - INFO - Epoch(train) [17][ 720/1320] lr: 2.0000e-02 eta: 5:55:08 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 4.3355 loss: 2.2330 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.2330 2023/02/17 15:12:08 - mmengine - INFO - Epoch(train) [17][ 740/1320] lr: 2.0000e-02 eta: 5:54:58 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 4.2513 loss: 1.8780 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8780 2023/02/17 15:12:17 - mmengine - INFO - Epoch(train) [17][ 760/1320] lr: 2.0000e-02 eta: 5:54:48 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.1818 loss: 1.8237 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8237 2023/02/17 15:12:27 - mmengine - INFO - Epoch(train) [17][ 780/1320] lr: 2.0000e-02 eta: 5:54:39 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 4.1981 loss: 1.9567 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.9567 2023/02/17 15:12:36 - mmengine - INFO - Epoch(train) [17][ 800/1320] lr: 2.0000e-02 eta: 5:54:29 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.4199 loss: 1.9341 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9341 2023/02/17 15:12:46 - mmengine - INFO - Epoch(train) [17][ 820/1320] lr: 2.0000e-02 eta: 5:54:19 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.2263 loss: 1.7690 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7690 2023/02/17 15:12:56 - mmengine - INFO - Epoch(train) [17][ 840/1320] lr: 2.0000e-02 eta: 5:54:09 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.3301 loss: 1.8748 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.8748 2023/02/17 15:13:05 - mmengine - INFO - Epoch(train) [17][ 860/1320] lr: 2.0000e-02 eta: 5:54:00 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.3193 loss: 1.8963 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8963 2023/02/17 15:13:15 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:13:15 - mmengine - INFO - Epoch(train) [17][ 880/1320] lr: 2.0000e-02 eta: 5:53:50 time: 0.4802 data_time: 0.0152 memory: 27031 grad_norm: 4.2351 loss: 1.9805 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9805 2023/02/17 15:13:24 - mmengine - INFO - Epoch(train) [17][ 900/1320] lr: 2.0000e-02 eta: 5:53:40 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1587 loss: 1.9983 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.9983 2023/02/17 15:13:34 - mmengine - INFO - Epoch(train) [17][ 920/1320] lr: 2.0000e-02 eta: 5:53:30 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2711 loss: 1.8877 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8877 2023/02/17 15:13:43 - mmengine - INFO - Epoch(train) [17][ 940/1320] lr: 2.0000e-02 eta: 5:53:20 time: 0.4797 data_time: 0.0149 memory: 27031 grad_norm: 4.3364 loss: 2.1159 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.1159 2023/02/17 15:13:53 - mmengine - INFO - Epoch(train) [17][ 960/1320] lr: 2.0000e-02 eta: 5:53:11 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 4.0817 loss: 1.8451 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.8451 2023/02/17 15:14:03 - mmengine - INFO - Epoch(train) [17][ 980/1320] lr: 2.0000e-02 eta: 5:53:01 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 4.2622 loss: 1.8872 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8872 2023/02/17 15:14:12 - mmengine - INFO - Epoch(train) [17][1000/1320] lr: 2.0000e-02 eta: 5:52:51 time: 0.4792 data_time: 0.0145 memory: 27031 grad_norm: 4.3243 loss: 1.9192 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9192 2023/02/17 15:14:22 - mmengine - INFO - Epoch(train) [17][1020/1320] lr: 2.0000e-02 eta: 5:52:41 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 4.2475 loss: 1.9657 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9657 2023/02/17 15:14:31 - mmengine - INFO - Epoch(train) [17][1040/1320] lr: 2.0000e-02 eta: 5:52:32 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 4.3737 loss: 1.7782 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7782 2023/02/17 15:14:41 - mmengine - INFO - Epoch(train) [17][1060/1320] lr: 2.0000e-02 eta: 5:52:22 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2808 loss: 2.0598 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0598 2023/02/17 15:14:51 - mmengine - INFO - Epoch(train) [17][1080/1320] lr: 2.0000e-02 eta: 5:52:12 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 4.2608 loss: 1.8193 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8193 2023/02/17 15:15:00 - mmengine - INFO - Epoch(train) [17][1100/1320] lr: 2.0000e-02 eta: 5:52:02 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 4.4434 loss: 1.9011 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9011 2023/02/17 15:15:10 - mmengine - INFO - Epoch(train) [17][1120/1320] lr: 2.0000e-02 eta: 5:51:53 time: 0.4790 data_time: 0.0138 memory: 27031 grad_norm: 4.2676 loss: 1.9679 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 1.9679 2023/02/17 15:15:19 - mmengine - INFO - Epoch(train) [17][1140/1320] lr: 2.0000e-02 eta: 5:51:43 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.2594 loss: 1.8982 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8982 2023/02/17 15:15:29 - mmengine - INFO - Epoch(train) [17][1160/1320] lr: 2.0000e-02 eta: 5:51:33 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 4.3073 loss: 1.8421 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8421 2023/02/17 15:15:39 - mmengine - INFO - Epoch(train) [17][1180/1320] lr: 2.0000e-02 eta: 5:51:23 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.3133 loss: 1.8119 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8119 2023/02/17 15:15:48 - mmengine - INFO - Epoch(train) [17][1200/1320] lr: 2.0000e-02 eta: 5:51:14 time: 0.4811 data_time: 0.0153 memory: 27031 grad_norm: 4.1732 loss: 2.0450 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.0450 2023/02/17 15:15:58 - mmengine - INFO - Epoch(train) [17][1220/1320] lr: 2.0000e-02 eta: 5:51:04 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.2631 loss: 1.8425 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8425 2023/02/17 15:16:07 - mmengine - INFO - Epoch(train) [17][1240/1320] lr: 2.0000e-02 eta: 5:50:54 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.3899 loss: 1.8326 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8326 2023/02/17 15:16:17 - mmengine - INFO - Epoch(train) [17][1260/1320] lr: 2.0000e-02 eta: 5:50:44 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.2917 loss: 1.8963 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.8963 2023/02/17 15:16:27 - mmengine - INFO - Epoch(train) [17][1280/1320] lr: 2.0000e-02 eta: 5:50:35 time: 0.4787 data_time: 0.0142 memory: 27031 grad_norm: 4.3391 loss: 1.8508 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8508 2023/02/17 15:16:36 - mmengine - INFO - Epoch(train) [17][1300/1320] lr: 2.0000e-02 eta: 5:50:25 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 4.3294 loss: 1.9235 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9235 2023/02/17 15:16:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:16:46 - mmengine - INFO - Epoch(train) [17][1320/1320] lr: 2.0000e-02 eta: 5:50:15 time: 0.4733 data_time: 0.0153 memory: 27031 grad_norm: 4.1280 loss: 1.9413 top1_acc: 0.5455 top5_acc: 0.6364 loss_cls: 1.9413 2023/02/17 15:16:49 - mmengine - INFO - Epoch(val) [17][ 20/194] eta: 0:00:32 time: 0.1843 data_time: 0.0591 memory: 3265 2023/02/17 15:16:52 - mmengine - INFO - Epoch(val) [17][ 40/194] eta: 0:00:24 time: 0.1368 data_time: 0.0137 memory: 3265 2023/02/17 15:16:55 - mmengine - INFO - Epoch(val) [17][ 60/194] eta: 0:00:20 time: 0.1368 data_time: 0.0131 memory: 3265 2023/02/17 15:16:58 - mmengine - INFO - Epoch(val) [17][ 80/194] eta: 0:00:16 time: 0.1381 data_time: 0.0138 memory: 3265 2023/02/17 15:17:00 - mmengine - INFO - Epoch(val) [17][100/194] eta: 0:00:13 time: 0.1390 data_time: 0.0143 memory: 3265 2023/02/17 15:17:03 - mmengine - INFO - Epoch(val) [17][120/194] eta: 0:00:10 time: 0.1369 data_time: 0.0130 memory: 3265 2023/02/17 15:17:06 - mmengine - INFO - Epoch(val) [17][140/194] eta: 0:00:07 time: 0.1373 data_time: 0.0132 memory: 3265 2023/02/17 15:17:09 - mmengine - INFO - Epoch(val) [17][160/194] eta: 0:00:04 time: 0.1374 data_time: 0.0129 memory: 3265 2023/02/17 15:17:11 - mmengine - INFO - Epoch(val) [17][180/194] eta: 0:00:01 time: 0.1387 data_time: 0.0138 memory: 3265 2023/02/17 15:17:14 - mmengine - INFO - Epoch(val) [17][194/194] acc/top1: 0.4732 acc/top5: 0.7649 acc/mean1: 0.4033 2023/02/17 15:17:25 - mmengine - INFO - Epoch(train) [18][ 20/1320] lr: 2.0000e-02 eta: 5:50:07 time: 0.5332 data_time: 0.0571 memory: 27031 grad_norm: 4.2288 loss: 1.6441 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.6441 2023/02/17 15:17:35 - mmengine - INFO - Epoch(train) [18][ 40/1320] lr: 2.0000e-02 eta: 5:49:57 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.3768 loss: 1.9986 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9986 2023/02/17 15:17:44 - mmengine - INFO - Epoch(train) [18][ 60/1320] lr: 2.0000e-02 eta: 5:49:48 time: 0.4782 data_time: 0.0134 memory: 27031 grad_norm: 4.3647 loss: 1.7066 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7066 2023/02/17 15:17:54 - mmengine - INFO - Epoch(train) [18][ 80/1320] lr: 2.0000e-02 eta: 5:49:38 time: 0.4789 data_time: 0.0134 memory: 27031 grad_norm: 4.4015 loss: 1.7004 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7004 2023/02/17 15:18:03 - mmengine - INFO - Epoch(train) [18][ 100/1320] lr: 2.0000e-02 eta: 5:49:28 time: 0.4801 data_time: 0.0157 memory: 27031 grad_norm: 4.3496 loss: 1.9561 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9561 2023/02/17 15:18:13 - mmengine - INFO - Epoch(train) [18][ 120/1320] lr: 2.0000e-02 eta: 5:49:18 time: 0.4788 data_time: 0.0131 memory: 27031 grad_norm: 4.2539 loss: 2.0075 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0075 2023/02/17 15:18:23 - mmengine - INFO - Epoch(train) [18][ 140/1320] lr: 2.0000e-02 eta: 5:49:09 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.2937 loss: 1.9540 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9540 2023/02/17 15:18:32 - mmengine - INFO - Epoch(train) [18][ 160/1320] lr: 2.0000e-02 eta: 5:48:59 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.2447 loss: 1.9894 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9894 2023/02/17 15:18:42 - mmengine - INFO - Epoch(train) [18][ 180/1320] lr: 2.0000e-02 eta: 5:48:49 time: 0.4784 data_time: 0.0140 memory: 27031 grad_norm: 4.2946 loss: 1.7604 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7604 2023/02/17 15:18:51 - mmengine - INFO - Epoch(train) [18][ 200/1320] lr: 2.0000e-02 eta: 5:48:39 time: 0.4802 data_time: 0.0149 memory: 27031 grad_norm: 4.3183 loss: 1.8552 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8552 2023/02/17 15:19:01 - mmengine - INFO - Epoch(train) [18][ 220/1320] lr: 2.0000e-02 eta: 5:48:29 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.3378 loss: 1.8888 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8888 2023/02/17 15:19:11 - mmengine - INFO - Epoch(train) [18][ 240/1320] lr: 2.0000e-02 eta: 5:48:20 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 4.3629 loss: 2.0380 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0380 2023/02/17 15:19:20 - mmengine - INFO - Epoch(train) [18][ 260/1320] lr: 2.0000e-02 eta: 5:48:10 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 4.2018 loss: 1.8709 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8709 2023/02/17 15:19:30 - mmengine - INFO - Epoch(train) [18][ 280/1320] lr: 2.0000e-02 eta: 5:48:00 time: 0.4779 data_time: 0.0136 memory: 27031 grad_norm: 4.3340 loss: 1.9090 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9090 2023/02/17 15:19:39 - mmengine - INFO - Epoch(train) [18][ 300/1320] lr: 2.0000e-02 eta: 5:47:50 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.1945 loss: 1.9330 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9330 2023/02/17 15:19:49 - mmengine - INFO - Epoch(train) [18][ 320/1320] lr: 2.0000e-02 eta: 5:47:41 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.3291 loss: 1.7390 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.7390 2023/02/17 15:19:59 - mmengine - INFO - Epoch(train) [18][ 340/1320] lr: 2.0000e-02 eta: 5:47:31 time: 0.4783 data_time: 0.0140 memory: 27031 grad_norm: 4.1619 loss: 1.8791 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8791 2023/02/17 15:20:08 - mmengine - INFO - Epoch(train) [18][ 360/1320] lr: 2.0000e-02 eta: 5:47:21 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.2581 loss: 1.9150 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.9150 2023/02/17 15:20:18 - mmengine - INFO - Epoch(train) [18][ 380/1320] lr: 2.0000e-02 eta: 5:47:11 time: 0.4795 data_time: 0.0141 memory: 27031 grad_norm: 4.2020 loss: 1.9272 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9272 2023/02/17 15:20:27 - mmengine - INFO - Epoch(train) [18][ 400/1320] lr: 2.0000e-02 eta: 5:47:02 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3175 loss: 1.8874 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8874 2023/02/17 15:20:37 - mmengine - INFO - Epoch(train) [18][ 420/1320] lr: 2.0000e-02 eta: 5:46:52 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 4.2841 loss: 1.9303 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9303 2023/02/17 15:20:46 - mmengine - INFO - Epoch(train) [18][ 440/1320] lr: 2.0000e-02 eta: 5:46:42 time: 0.4789 data_time: 0.0136 memory: 27031 grad_norm: 4.2228 loss: 1.9562 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9562 2023/02/17 15:20:56 - mmengine - INFO - Epoch(train) [18][ 460/1320] lr: 2.0000e-02 eta: 5:46:32 time: 0.4806 data_time: 0.0150 memory: 27031 grad_norm: 4.3237 loss: 1.8163 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8163 2023/02/17 15:21:06 - mmengine - INFO - Epoch(train) [18][ 480/1320] lr: 2.0000e-02 eta: 5:46:23 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.2159 loss: 1.9708 top1_acc: 0.2500 top5_acc: 0.8125 loss_cls: 1.9708 2023/02/17 15:21:15 - mmengine - INFO - Epoch(train) [18][ 500/1320] lr: 2.0000e-02 eta: 5:46:13 time: 0.4784 data_time: 0.0134 memory: 27031 grad_norm: 4.3648 loss: 1.8940 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.8940 2023/02/17 15:21:25 - mmengine - INFO - Epoch(train) [18][ 520/1320] lr: 2.0000e-02 eta: 5:46:03 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 4.3401 loss: 2.1954 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 2.1954 2023/02/17 15:21:34 - mmengine - INFO - Epoch(train) [18][ 540/1320] lr: 2.0000e-02 eta: 5:45:53 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.2666 loss: 1.9680 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9680 2023/02/17 15:21:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:21:44 - mmengine - INFO - Epoch(train) [18][ 560/1320] lr: 2.0000e-02 eta: 5:45:44 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.4594 loss: 1.8387 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8387 2023/02/17 15:21:54 - mmengine - INFO - Epoch(train) [18][ 580/1320] lr: 2.0000e-02 eta: 5:45:34 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.3921 loss: 1.9002 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.9002 2023/02/17 15:22:03 - mmengine - INFO - Epoch(train) [18][ 600/1320] lr: 2.0000e-02 eta: 5:45:24 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.3773 loss: 2.0466 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.0466 2023/02/17 15:22:13 - mmengine - INFO - Epoch(train) [18][ 620/1320] lr: 2.0000e-02 eta: 5:45:14 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.3367 loss: 2.0448 top1_acc: 0.1875 top5_acc: 0.8125 loss_cls: 2.0448 2023/02/17 15:22:22 - mmengine - INFO - Epoch(train) [18][ 640/1320] lr: 2.0000e-02 eta: 5:45:04 time: 0.4796 data_time: 0.0148 memory: 27031 grad_norm: 4.3445 loss: 1.9622 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 1.9622 2023/02/17 15:22:32 - mmengine - INFO - Epoch(train) [18][ 660/1320] lr: 2.0000e-02 eta: 5:44:55 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 4.2659 loss: 1.9918 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9918 2023/02/17 15:22:42 - mmengine - INFO - Epoch(train) [18][ 680/1320] lr: 2.0000e-02 eta: 5:44:45 time: 0.4810 data_time: 0.0161 memory: 27031 grad_norm: 4.2581 loss: 1.9547 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9547 2023/02/17 15:22:51 - mmengine - INFO - Epoch(train) [18][ 700/1320] lr: 2.0000e-02 eta: 5:44:35 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 4.3756 loss: 2.1356 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.1356 2023/02/17 15:23:01 - mmengine - INFO - Epoch(train) [18][ 720/1320] lr: 2.0000e-02 eta: 5:44:26 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.2000 loss: 1.8943 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8943 2023/02/17 15:23:10 - mmengine - INFO - Epoch(train) [18][ 740/1320] lr: 2.0000e-02 eta: 5:44:16 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.4328 loss: 1.8262 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8262 2023/02/17 15:23:20 - mmengine - INFO - Epoch(train) [18][ 760/1320] lr: 2.0000e-02 eta: 5:44:06 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.2195 loss: 1.9059 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9059 2023/02/17 15:23:30 - mmengine - INFO - Epoch(train) [18][ 780/1320] lr: 2.0000e-02 eta: 5:43:56 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2441 loss: 2.2092 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.2092 2023/02/17 15:23:39 - mmengine - INFO - Epoch(train) [18][ 800/1320] lr: 2.0000e-02 eta: 5:43:47 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.2763 loss: 1.8827 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 1.8827 2023/02/17 15:23:49 - mmengine - INFO - Epoch(train) [18][ 820/1320] lr: 2.0000e-02 eta: 5:43:37 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.3741 loss: 1.9581 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.9581 2023/02/17 15:23:58 - mmengine - INFO - Epoch(train) [18][ 840/1320] lr: 2.0000e-02 eta: 5:43:27 time: 0.4806 data_time: 0.0155 memory: 27031 grad_norm: 4.3349 loss: 2.0804 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0804 2023/02/17 15:24:08 - mmengine - INFO - Epoch(train) [18][ 860/1320] lr: 2.0000e-02 eta: 5:43:17 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 4.2181 loss: 1.8736 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.8736 2023/02/17 15:24:18 - mmengine - INFO - Epoch(train) [18][ 880/1320] lr: 2.0000e-02 eta: 5:43:08 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.3230 loss: 1.8595 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.8595 2023/02/17 15:24:55 - mmengine - INFO - Epoch(train) [18][ 900/1320] lr: 2.0000e-02 eta: 5:43:49 time: 1.8843 data_time: 0.0145 memory: 27031 grad_norm: 4.2538 loss: 1.9623 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.9623 2023/02/17 15:25:05 - mmengine - INFO - Epoch(train) [18][ 920/1320] lr: 2.0000e-02 eta: 5:43:39 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 4.3884 loss: 1.9627 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9627 2023/02/17 15:25:14 - mmengine - INFO - Epoch(train) [18][ 940/1320] lr: 2.0000e-02 eta: 5:43:30 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.2928 loss: 1.9337 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.9337 2023/02/17 15:25:24 - mmengine - INFO - Epoch(train) [18][ 960/1320] lr: 2.0000e-02 eta: 5:43:20 time: 0.4806 data_time: 0.0152 memory: 27031 grad_norm: 4.3125 loss: 1.8727 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.8727 2023/02/17 15:25:34 - mmengine - INFO - Epoch(train) [18][ 980/1320] lr: 2.0000e-02 eta: 5:43:10 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 4.4177 loss: 1.9060 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9060 2023/02/17 15:25:43 - mmengine - INFO - Epoch(train) [18][1000/1320] lr: 2.0000e-02 eta: 5:43:00 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.2929 loss: 1.9770 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9770 2023/02/17 15:25:53 - mmengine - INFO - Epoch(train) [18][1020/1320] lr: 2.0000e-02 eta: 5:42:50 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.2778 loss: 1.9727 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9727 2023/02/17 15:26:02 - mmengine - INFO - Epoch(train) [18][1040/1320] lr: 2.0000e-02 eta: 5:42:40 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.1798 loss: 1.9018 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9018 2023/02/17 15:26:12 - mmengine - INFO - Epoch(train) [18][1060/1320] lr: 2.0000e-02 eta: 5:42:31 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.3156 loss: 1.7660 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.7660 2023/02/17 15:26:22 - mmengine - INFO - Epoch(train) [18][1080/1320] lr: 2.0000e-02 eta: 5:42:21 time: 0.4810 data_time: 0.0151 memory: 27031 grad_norm: 4.4248 loss: 1.7958 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.7958 2023/02/17 15:26:31 - mmengine - INFO - Epoch(train) [18][1100/1320] lr: 2.0000e-02 eta: 5:42:11 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.3125 loss: 1.8787 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8787 2023/02/17 15:26:41 - mmengine - INFO - Epoch(train) [18][1120/1320] lr: 2.0000e-02 eta: 5:42:01 time: 0.4795 data_time: 0.0141 memory: 27031 grad_norm: 4.2698 loss: 1.8734 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8734 2023/02/17 15:26:50 - mmengine - INFO - Epoch(train) [18][1140/1320] lr: 2.0000e-02 eta: 5:41:51 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2546 loss: 1.8655 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8655 2023/02/17 15:27:00 - mmengine - INFO - Epoch(train) [18][1160/1320] lr: 2.0000e-02 eta: 5:41:42 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 4.2609 loss: 1.8178 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8178 2023/02/17 15:27:10 - mmengine - INFO - Epoch(train) [18][1180/1320] lr: 2.0000e-02 eta: 5:41:32 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2374 loss: 1.9931 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9931 2023/02/17 15:27:19 - mmengine - INFO - Epoch(train) [18][1200/1320] lr: 2.0000e-02 eta: 5:41:22 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 4.2689 loss: 1.7992 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7992 2023/02/17 15:27:29 - mmengine - INFO - Epoch(train) [18][1220/1320] lr: 2.0000e-02 eta: 5:41:12 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.2375 loss: 1.9182 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 1.9182 2023/02/17 15:27:38 - mmengine - INFO - Epoch(train) [18][1240/1320] lr: 2.0000e-02 eta: 5:41:02 time: 0.4788 data_time: 0.0135 memory: 27031 grad_norm: 4.2429 loss: 1.8736 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8736 2023/02/17 15:27:48 - mmengine - INFO - Epoch(train) [18][1260/1320] lr: 2.0000e-02 eta: 5:40:53 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.2414 loss: 1.8872 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8872 2023/02/17 15:27:58 - mmengine - INFO - Epoch(train) [18][1280/1320] lr: 2.0000e-02 eta: 5:40:43 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.2573 loss: 1.9532 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9532 2023/02/17 15:28:07 - mmengine - INFO - Epoch(train) [18][1300/1320] lr: 2.0000e-02 eta: 5:40:33 time: 0.4794 data_time: 0.0138 memory: 27031 grad_norm: 4.1355 loss: 1.7429 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.7429 2023/02/17 15:28:17 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:28:17 - mmengine - INFO - Epoch(train) [18][1320/1320] lr: 2.0000e-02 eta: 5:40:23 time: 0.4728 data_time: 0.0152 memory: 27031 grad_norm: 4.3362 loss: 1.7753 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 1.7753 2023/02/17 15:28:17 - mmengine - INFO - Saving checkpoint at 18 epochs 2023/02/17 15:28:22 - mmengine - INFO - Epoch(val) [18][ 20/194] eta: 0:00:32 time: 0.1866 data_time: 0.0578 memory: 3265 2023/02/17 15:28:24 - mmengine - INFO - Epoch(val) [18][ 40/194] eta: 0:00:25 time: 0.1383 data_time: 0.0145 memory: 3265 2023/02/17 15:28:27 - mmengine - INFO - Epoch(val) [18][ 60/194] eta: 0:00:20 time: 0.1363 data_time: 0.0128 memory: 3265 2023/02/17 15:28:30 - mmengine - INFO - Epoch(val) [18][ 80/194] eta: 0:00:17 time: 0.1364 data_time: 0.0123 memory: 3265 2023/02/17 15:28:33 - mmengine - INFO - Epoch(val) [18][100/194] eta: 0:00:13 time: 0.1381 data_time: 0.0138 memory: 3265 2023/02/17 15:28:35 - mmengine - INFO - Epoch(val) [18][120/194] eta: 0:00:10 time: 0.1365 data_time: 0.0131 memory: 3265 2023/02/17 15:28:38 - mmengine - INFO - Epoch(val) [18][140/194] eta: 0:00:07 time: 0.1378 data_time: 0.0133 memory: 3265 2023/02/17 15:28:41 - mmengine - INFO - Epoch(val) [18][160/194] eta: 0:00:04 time: 0.1373 data_time: 0.0131 memory: 3265 2023/02/17 15:28:44 - mmengine - INFO - Epoch(val) [18][180/194] eta: 0:00:01 time: 0.1364 data_time: 0.0122 memory: 3265 2023/02/17 15:28:46 - mmengine - INFO - Epoch(val) [18][194/194] acc/top1: 0.4695 acc/top5: 0.7710 acc/mean1: 0.4156 2023/02/17 15:28:57 - mmengine - INFO - Epoch(train) [19][ 20/1320] lr: 2.0000e-02 eta: 5:40:15 time: 0.5337 data_time: 0.0567 memory: 27031 grad_norm: 4.2119 loss: 2.0350 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0350 2023/02/17 15:29:06 - mmengine - INFO - Epoch(train) [19][ 40/1320] lr: 2.0000e-02 eta: 5:40:05 time: 0.4783 data_time: 0.0135 memory: 27031 grad_norm: 4.1228 loss: 1.7365 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7365 2023/02/17 15:29:16 - mmengine - INFO - Epoch(train) [19][ 60/1320] lr: 2.0000e-02 eta: 5:39:55 time: 0.4796 data_time: 0.0139 memory: 27031 grad_norm: 4.3473 loss: 1.8222 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8222 2023/02/17 15:29:26 - mmengine - INFO - Epoch(train) [19][ 80/1320] lr: 2.0000e-02 eta: 5:39:46 time: 0.4784 data_time: 0.0143 memory: 27031 grad_norm: 4.2312 loss: 1.9358 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.9358 2023/02/17 15:29:35 - mmengine - INFO - Epoch(train) [19][ 100/1320] lr: 2.0000e-02 eta: 5:39:36 time: 0.4786 data_time: 0.0143 memory: 27031 grad_norm: 4.3093 loss: 1.9077 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9077 2023/02/17 15:29:45 - mmengine - INFO - Epoch(train) [19][ 120/1320] lr: 2.0000e-02 eta: 5:39:26 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.3006 loss: 1.9313 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.9313 2023/02/17 15:29:55 - mmengine - INFO - Epoch(train) [19][ 140/1320] lr: 2.0000e-02 eta: 5:39:17 time: 0.5111 data_time: 0.0460 memory: 27031 grad_norm: 4.3243 loss: 1.9107 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9107 2023/02/17 15:30:04 - mmengine - INFO - Epoch(train) [19][ 160/1320] lr: 2.0000e-02 eta: 5:39:07 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.2985 loss: 1.6519 top1_acc: 0.2500 top5_acc: 0.6875 loss_cls: 1.6519 2023/02/17 15:30:14 - mmengine - INFO - Epoch(train) [19][ 180/1320] lr: 2.0000e-02 eta: 5:38:58 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.4089 loss: 1.7210 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7210 2023/02/17 15:30:24 - mmengine - INFO - Epoch(train) [19][ 200/1320] lr: 2.0000e-02 eta: 5:38:48 time: 0.4784 data_time: 0.0137 memory: 27031 grad_norm: 4.3478 loss: 1.8113 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8113 2023/02/17 15:30:33 - mmengine - INFO - Epoch(train) [19][ 220/1320] lr: 2.0000e-02 eta: 5:38:38 time: 0.4792 data_time: 0.0145 memory: 27031 grad_norm: 4.3762 loss: 1.7433 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7433 2023/02/17 15:30:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:30:43 - mmengine - INFO - Epoch(train) [19][ 240/1320] lr: 2.0000e-02 eta: 5:38:28 time: 0.4783 data_time: 0.0135 memory: 27031 grad_norm: 4.1586 loss: 1.7029 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7029 2023/02/17 15:30:52 - mmengine - INFO - Epoch(train) [19][ 260/1320] lr: 2.0000e-02 eta: 5:38:18 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2517 loss: 1.9778 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9778 2023/02/17 15:31:02 - mmengine - INFO - Epoch(train) [19][ 280/1320] lr: 2.0000e-02 eta: 5:38:08 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.3382 loss: 2.0780 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0780 2023/02/17 15:31:12 - mmengine - INFO - Epoch(train) [19][ 300/1320] lr: 2.0000e-02 eta: 5:37:59 time: 0.4788 data_time: 0.0134 memory: 27031 grad_norm: 4.2633 loss: 1.7450 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7450 2023/02/17 15:31:21 - mmengine - INFO - Epoch(train) [19][ 320/1320] lr: 2.0000e-02 eta: 5:37:49 time: 0.4815 data_time: 0.0147 memory: 27031 grad_norm: 4.2877 loss: 1.7233 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7233 2023/02/17 15:31:31 - mmengine - INFO - Epoch(train) [19][ 340/1320] lr: 2.0000e-02 eta: 5:37:39 time: 0.4789 data_time: 0.0140 memory: 27031 grad_norm: 4.2136 loss: 1.8416 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8416 2023/02/17 15:31:40 - mmengine - INFO - Epoch(train) [19][ 360/1320] lr: 2.0000e-02 eta: 5:37:29 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.3051 loss: 1.6343 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.6343 2023/02/17 15:31:50 - mmengine - INFO - Epoch(train) [19][ 380/1320] lr: 2.0000e-02 eta: 5:37:19 time: 0.4799 data_time: 0.0151 memory: 27031 grad_norm: 4.2748 loss: 1.9613 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.9613 2023/02/17 15:32:00 - mmengine - INFO - Epoch(train) [19][ 400/1320] lr: 2.0000e-02 eta: 5:37:10 time: 0.4787 data_time: 0.0143 memory: 27031 grad_norm: 4.2986 loss: 1.6868 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.6868 2023/02/17 15:32:09 - mmengine - INFO - Epoch(train) [19][ 420/1320] lr: 2.0000e-02 eta: 5:37:00 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.3466 loss: 2.0039 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0039 2023/02/17 15:32:19 - mmengine - INFO - Epoch(train) [19][ 440/1320] lr: 2.0000e-02 eta: 5:36:50 time: 0.4794 data_time: 0.0150 memory: 27031 grad_norm: 4.3313 loss: 1.7880 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.7880 2023/02/17 15:32:28 - mmengine - INFO - Epoch(train) [19][ 460/1320] lr: 2.0000e-02 eta: 5:36:40 time: 0.4791 data_time: 0.0136 memory: 27031 grad_norm: 4.3107 loss: 2.0573 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.0573 2023/02/17 15:32:38 - mmengine - INFO - Epoch(train) [19][ 480/1320] lr: 2.0000e-02 eta: 5:36:30 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.3081 loss: 1.9178 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.9178 2023/02/17 15:32:47 - mmengine - INFO - Epoch(train) [19][ 500/1320] lr: 2.0000e-02 eta: 5:36:20 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.2058 loss: 1.7913 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7913 2023/02/17 15:32:57 - mmengine - INFO - Epoch(train) [19][ 520/1320] lr: 2.0000e-02 eta: 5:36:11 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 4.2865 loss: 1.8002 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.8002 2023/02/17 15:33:07 - mmengine - INFO - Epoch(train) [19][ 540/1320] lr: 2.0000e-02 eta: 5:36:01 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.2890 loss: 1.8547 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8547 2023/02/17 15:33:16 - mmengine - INFO - Epoch(train) [19][ 560/1320] lr: 2.0000e-02 eta: 5:35:51 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 4.3247 loss: 1.7490 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.7490 2023/02/17 15:33:26 - mmengine - INFO - Epoch(train) [19][ 580/1320] lr: 2.0000e-02 eta: 5:35:41 time: 0.4799 data_time: 0.0151 memory: 27031 grad_norm: 4.3205 loss: 1.7232 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7232 2023/02/17 15:33:35 - mmengine - INFO - Epoch(train) [19][ 600/1320] lr: 2.0000e-02 eta: 5:35:32 time: 0.4800 data_time: 0.0139 memory: 27031 grad_norm: 4.3039 loss: 1.7863 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7863 2023/02/17 15:33:45 - mmengine - INFO - Epoch(train) [19][ 620/1320] lr: 2.0000e-02 eta: 5:35:22 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.3491 loss: 1.8739 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8739 2023/02/17 15:33:55 - mmengine - INFO - Epoch(train) [19][ 640/1320] lr: 2.0000e-02 eta: 5:35:12 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.3697 loss: 1.9500 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9500 2023/02/17 15:34:04 - mmengine - INFO - Epoch(train) [19][ 660/1320] lr: 2.0000e-02 eta: 5:35:02 time: 0.4799 data_time: 0.0152 memory: 27031 grad_norm: 4.2458 loss: 1.8552 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8552 2023/02/17 15:34:14 - mmengine - INFO - Epoch(train) [19][ 680/1320] lr: 2.0000e-02 eta: 5:34:52 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.3573 loss: 1.8402 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8402 2023/02/17 15:34:23 - mmengine - INFO - Epoch(train) [19][ 700/1320] lr: 2.0000e-02 eta: 5:34:42 time: 0.4796 data_time: 0.0147 memory: 27031 grad_norm: 4.4047 loss: 1.7926 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7926 2023/02/17 15:34:33 - mmengine - INFO - Epoch(train) [19][ 720/1320] lr: 2.0000e-02 eta: 5:34:33 time: 0.4799 data_time: 0.0137 memory: 27031 grad_norm: 4.4887 loss: 2.0167 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.0167 2023/02/17 15:34:43 - mmengine - INFO - Epoch(train) [19][ 740/1320] lr: 2.0000e-02 eta: 5:34:23 time: 0.4791 data_time: 0.0143 memory: 27031 grad_norm: 4.2719 loss: 1.8094 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8094 2023/02/17 15:34:52 - mmengine - INFO - Epoch(train) [19][ 760/1320] lr: 2.0000e-02 eta: 5:34:13 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.3233 loss: 1.8744 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8744 2023/02/17 15:35:02 - mmengine - INFO - Epoch(train) [19][ 780/1320] lr: 2.0000e-02 eta: 5:34:03 time: 0.4789 data_time: 0.0138 memory: 27031 grad_norm: 4.3104 loss: 1.8779 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8779 2023/02/17 15:35:11 - mmengine - INFO - Epoch(train) [19][ 800/1320] lr: 2.0000e-02 eta: 5:33:53 time: 0.4790 data_time: 0.0138 memory: 27031 grad_norm: 4.2330 loss: 1.8481 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8481 2023/02/17 15:35:21 - mmengine - INFO - Epoch(train) [19][ 820/1320] lr: 2.0000e-02 eta: 5:33:44 time: 0.4791 data_time: 0.0145 memory: 27031 grad_norm: 4.3157 loss: 1.7918 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7918 2023/02/17 15:35:31 - mmengine - INFO - Epoch(train) [19][ 840/1320] lr: 2.0000e-02 eta: 5:33:34 time: 0.4803 data_time: 0.0155 memory: 27031 grad_norm: 4.3674 loss: 1.8808 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8808 2023/02/17 15:35:40 - mmengine - INFO - Epoch(train) [19][ 860/1320] lr: 2.0000e-02 eta: 5:33:24 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.1831 loss: 1.8306 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8306 2023/02/17 15:35:50 - mmengine - INFO - Epoch(train) [19][ 880/1320] lr: 2.0000e-02 eta: 5:33:14 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 4.2684 loss: 1.8190 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8190 2023/02/17 15:35:59 - mmengine - INFO - Epoch(train) [19][ 900/1320] lr: 2.0000e-02 eta: 5:33:04 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.4792 loss: 1.9166 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9166 2023/02/17 15:36:09 - mmengine - INFO - Epoch(train) [19][ 920/1320] lr: 2.0000e-02 eta: 5:32:55 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.3736 loss: 1.6892 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6892 2023/02/17 15:36:19 - mmengine - INFO - Epoch(train) [19][ 940/1320] lr: 2.0000e-02 eta: 5:32:45 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.3496 loss: 2.0912 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0912 2023/02/17 15:36:28 - mmengine - INFO - Epoch(train) [19][ 960/1320] lr: 2.0000e-02 eta: 5:32:35 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.3250 loss: 1.8924 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8924 2023/02/17 15:36:38 - mmengine - INFO - Epoch(train) [19][ 980/1320] lr: 2.0000e-02 eta: 5:32:25 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.1702 loss: 1.7870 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7870 2023/02/17 15:36:47 - mmengine - INFO - Epoch(train) [19][1000/1320] lr: 2.0000e-02 eta: 5:32:16 time: 0.4799 data_time: 0.0141 memory: 27031 grad_norm: 4.4435 loss: 1.7028 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.7028 2023/02/17 15:36:57 - mmengine - INFO - Epoch(train) [19][1020/1320] lr: 2.0000e-02 eta: 5:32:06 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.3880 loss: 2.0365 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0365 2023/02/17 15:37:07 - mmengine - INFO - Epoch(train) [19][1040/1320] lr: 2.0000e-02 eta: 5:31:56 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.2293 loss: 1.8509 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8509 2023/02/17 15:37:16 - mmengine - INFO - Epoch(train) [19][1060/1320] lr: 2.0000e-02 eta: 5:31:46 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 4.2469 loss: 2.1227 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1227 2023/02/17 15:37:26 - mmengine - INFO - Epoch(train) [19][1080/1320] lr: 2.0000e-02 eta: 5:31:36 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.3272 loss: 1.9798 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9798 2023/02/17 15:37:35 - mmengine - INFO - Epoch(train) [19][1100/1320] lr: 2.0000e-02 eta: 5:31:27 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.2591 loss: 1.9090 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.9090 2023/02/17 15:37:45 - mmengine - INFO - Epoch(train) [19][1120/1320] lr: 2.0000e-02 eta: 5:31:17 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 4.3117 loss: 1.8608 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8608 2023/02/17 15:37:55 - mmengine - INFO - Epoch(train) [19][1140/1320] lr: 2.0000e-02 eta: 5:31:07 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.2306 loss: 1.9820 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.9820 2023/02/17 15:38:04 - mmengine - INFO - Epoch(train) [19][1160/1320] lr: 2.0000e-02 eta: 5:30:57 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.2491 loss: 2.0126 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.0126 2023/02/17 15:38:14 - mmengine - INFO - Epoch(train) [19][1180/1320] lr: 2.0000e-02 eta: 5:30:47 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.2567 loss: 2.0311 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0311 2023/02/17 15:38:23 - mmengine - INFO - Epoch(train) [19][1200/1320] lr: 2.0000e-02 eta: 5:30:38 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.2525 loss: 2.0551 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 2.0551 2023/02/17 15:38:33 - mmengine - INFO - Epoch(train) [19][1220/1320] lr: 2.0000e-02 eta: 5:30:28 time: 0.4809 data_time: 0.0156 memory: 27031 grad_norm: 4.2747 loss: 1.8525 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8525 2023/02/17 15:38:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:38:43 - mmengine - INFO - Epoch(train) [19][1240/1320] lr: 2.0000e-02 eta: 5:30:18 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.2478 loss: 1.8228 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8228 2023/02/17 15:38:52 - mmengine - INFO - Epoch(train) [19][1260/1320] lr: 2.0000e-02 eta: 5:30:08 time: 0.4804 data_time: 0.0138 memory: 27031 grad_norm: 4.3439 loss: 1.9642 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9642 2023/02/17 15:39:02 - mmengine - INFO - Epoch(train) [19][1280/1320] lr: 2.0000e-02 eta: 5:29:59 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.3957 loss: 1.9632 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9632 2023/02/17 15:39:11 - mmengine - INFO - Epoch(train) [19][1300/1320] lr: 2.0000e-02 eta: 5:29:49 time: 0.4789 data_time: 0.0139 memory: 27031 grad_norm: 4.3155 loss: 1.9327 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.9327 2023/02/17 15:39:21 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:39:21 - mmengine - INFO - Epoch(train) [19][1320/1320] lr: 2.0000e-02 eta: 5:29:39 time: 0.4733 data_time: 0.0149 memory: 27031 grad_norm: 4.2921 loss: 1.9809 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.9809 2023/02/17 15:39:25 - mmengine - INFO - Epoch(val) [19][ 20/194] eta: 0:00:33 time: 0.1907 data_time: 0.0620 memory: 3265 2023/02/17 15:39:27 - mmengine - INFO - Epoch(val) [19][ 40/194] eta: 0:00:25 time: 0.1370 data_time: 0.0124 memory: 3265 2023/02/17 15:39:30 - mmengine - INFO - Epoch(val) [19][ 60/194] eta: 0:00:20 time: 0.1383 data_time: 0.0135 memory: 3265 2023/02/17 15:39:33 - mmengine - INFO - Epoch(val) [19][ 80/194] eta: 0:00:17 time: 0.1367 data_time: 0.0132 memory: 3265 2023/02/17 15:39:36 - mmengine - INFO - Epoch(val) [19][100/194] eta: 0:00:13 time: 0.1390 data_time: 0.0138 memory: 3265 2023/02/17 15:39:38 - mmengine - INFO - Epoch(val) [19][120/194] eta: 0:00:10 time: 0.1371 data_time: 0.0135 memory: 3265 2023/02/17 15:39:41 - mmengine - INFO - Epoch(val) [19][140/194] eta: 0:00:07 time: 0.1368 data_time: 0.0131 memory: 3265 2023/02/17 15:39:44 - mmengine - INFO - Epoch(val) [19][160/194] eta: 0:00:04 time: 0.1381 data_time: 0.0134 memory: 3265 2023/02/17 15:39:47 - mmengine - INFO - Epoch(val) [19][180/194] eta: 0:00:02 time: 0.1381 data_time: 0.0139 memory: 3265 2023/02/17 15:39:49 - mmengine - INFO - Epoch(val) [19][194/194] acc/top1: 0.4671 acc/top5: 0.7630 acc/mean1: 0.4047 2023/02/17 15:40:00 - mmengine - INFO - Epoch(train) [20][ 20/1320] lr: 2.0000e-02 eta: 5:29:31 time: 0.5349 data_time: 0.0606 memory: 27031 grad_norm: 4.2715 loss: 1.6790 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.6790 2023/02/17 15:40:10 - mmengine - INFO - Epoch(train) [20][ 40/1320] lr: 2.0000e-02 eta: 5:29:21 time: 0.4791 data_time: 0.0135 memory: 27031 grad_norm: 4.3912 loss: 1.9568 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9568 2023/02/17 15:40:19 - mmengine - INFO - Epoch(train) [20][ 60/1320] lr: 2.0000e-02 eta: 5:29:11 time: 0.4791 data_time: 0.0146 memory: 27031 grad_norm: 4.1881 loss: 1.7776 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.7776 2023/02/17 15:40:29 - mmengine - INFO - Epoch(train) [20][ 80/1320] lr: 2.0000e-02 eta: 5:29:01 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 4.0666 loss: 1.7618 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7618 2023/02/17 15:40:39 - mmengine - INFO - Epoch(train) [20][ 100/1320] lr: 2.0000e-02 eta: 5:28:52 time: 0.4791 data_time: 0.0150 memory: 27031 grad_norm: 4.3352 loss: 1.6535 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.6535 2023/02/17 15:40:48 - mmengine - INFO - Epoch(train) [20][ 120/1320] lr: 2.0000e-02 eta: 5:28:42 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.3360 loss: 1.9528 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9528 2023/02/17 15:40:58 - mmengine - INFO - Epoch(train) [20][ 140/1320] lr: 2.0000e-02 eta: 5:28:32 time: 0.4789 data_time: 0.0135 memory: 27031 grad_norm: 4.4059 loss: 1.7965 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.7965 2023/02/17 15:41:07 - mmengine - INFO - Epoch(train) [20][ 160/1320] lr: 2.0000e-02 eta: 5:28:22 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.1176 loss: 1.4927 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.4927 2023/02/17 15:41:17 - mmengine - INFO - Epoch(train) [20][ 180/1320] lr: 2.0000e-02 eta: 5:28:12 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.2888 loss: 1.8408 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8408 2023/02/17 15:41:26 - mmengine - INFO - Epoch(train) [20][ 200/1320] lr: 2.0000e-02 eta: 5:28:03 time: 0.4790 data_time: 0.0138 memory: 27031 grad_norm: 4.4075 loss: 2.0375 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0375 2023/02/17 15:41:36 - mmengine - INFO - Epoch(train) [20][ 220/1320] lr: 2.0000e-02 eta: 5:27:53 time: 0.4789 data_time: 0.0144 memory: 27031 grad_norm: 4.2995 loss: 1.9174 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9174 2023/02/17 15:41:46 - mmengine - INFO - Epoch(train) [20][ 240/1320] lr: 2.0000e-02 eta: 5:27:43 time: 0.4787 data_time: 0.0141 memory: 27031 grad_norm: 4.3037 loss: 1.8101 top1_acc: 0.6875 top5_acc: 0.6875 loss_cls: 1.8101 2023/02/17 15:41:55 - mmengine - INFO - Epoch(train) [20][ 260/1320] lr: 2.0000e-02 eta: 5:27:33 time: 0.4788 data_time: 0.0136 memory: 27031 grad_norm: 4.2867 loss: 1.9025 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 1.9025 2023/02/17 15:42:05 - mmengine - INFO - Epoch(train) [20][ 280/1320] lr: 2.0000e-02 eta: 5:27:23 time: 0.4821 data_time: 0.0159 memory: 27031 grad_norm: 4.2951 loss: 1.9078 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9078 2023/02/17 15:42:14 - mmengine - INFO - Epoch(train) [20][ 300/1320] lr: 2.0000e-02 eta: 5:27:14 time: 0.4792 data_time: 0.0144 memory: 27031 grad_norm: 4.2952 loss: 1.8888 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8888 2023/02/17 15:42:24 - mmengine - INFO - Epoch(train) [20][ 320/1320] lr: 2.0000e-02 eta: 5:27:04 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.3974 loss: 1.7862 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.7862 2023/02/17 15:42:34 - mmengine - INFO - Epoch(train) [20][ 340/1320] lr: 2.0000e-02 eta: 5:26:54 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.2802 loss: 1.8134 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8134 2023/02/17 15:42:43 - mmengine - INFO - Epoch(train) [20][ 360/1320] lr: 2.0000e-02 eta: 5:26:44 time: 0.4788 data_time: 0.0137 memory: 27031 grad_norm: 4.2547 loss: 1.7981 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 1.7981 2023/02/17 15:42:53 - mmengine - INFO - Epoch(train) [20][ 380/1320] lr: 2.0000e-02 eta: 5:26:34 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.2399 loss: 1.8717 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8717 2023/02/17 15:43:02 - mmengine - INFO - Epoch(train) [20][ 400/1320] lr: 2.0000e-02 eta: 5:26:25 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.4214 loss: 1.8737 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8737 2023/02/17 15:43:12 - mmengine - INFO - Epoch(train) [20][ 420/1320] lr: 2.0000e-02 eta: 5:26:15 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.3896 loss: 1.9274 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9274 2023/02/17 15:43:22 - mmengine - INFO - Epoch(train) [20][ 440/1320] lr: 2.0000e-02 eta: 5:26:05 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 4.3793 loss: 1.7886 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 1.7886 2023/02/17 15:43:31 - mmengine - INFO - Epoch(train) [20][ 460/1320] lr: 2.0000e-02 eta: 5:25:55 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.4164 loss: 1.8251 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8251 2023/02/17 15:43:41 - mmengine - INFO - Epoch(train) [20][ 480/1320] lr: 2.0000e-02 eta: 5:25:46 time: 0.4787 data_time: 0.0140 memory: 27031 grad_norm: 4.2707 loss: 1.6412 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.6412 2023/02/17 15:43:50 - mmengine - INFO - Epoch(train) [20][ 500/1320] lr: 2.0000e-02 eta: 5:25:36 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.4348 loss: 1.8500 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.8500 2023/02/17 15:44:00 - mmengine - INFO - Epoch(train) [20][ 520/1320] lr: 2.0000e-02 eta: 5:25:26 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.3989 loss: 1.8526 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8526 2023/02/17 15:44:10 - mmengine - INFO - Epoch(train) [20][ 540/1320] lr: 2.0000e-02 eta: 5:25:16 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.3458 loss: 1.8367 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 1.8367 2023/02/17 15:44:19 - mmengine - INFO - Epoch(train) [20][ 560/1320] lr: 2.0000e-02 eta: 5:25:06 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.4416 loss: 1.8753 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.8753 2023/02/17 15:44:29 - mmengine - INFO - Epoch(train) [20][ 580/1320] lr: 2.0000e-02 eta: 5:24:57 time: 0.4790 data_time: 0.0133 memory: 27031 grad_norm: 4.3532 loss: 1.9605 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9605 2023/02/17 15:44:38 - mmengine - INFO - Epoch(train) [20][ 600/1320] lr: 2.0000e-02 eta: 5:24:47 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.2388 loss: 2.0607 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0607 2023/02/17 15:44:48 - mmengine - INFO - Epoch(train) [20][ 620/1320] lr: 2.0000e-02 eta: 5:24:37 time: 0.4798 data_time: 0.0149 memory: 27031 grad_norm: 4.3916 loss: 1.8685 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8685 2023/02/17 15:44:58 - mmengine - INFO - Epoch(train) [20][ 640/1320] lr: 2.0000e-02 eta: 5:24:27 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.3377 loss: 1.9251 top1_acc: 0.2500 top5_acc: 0.8750 loss_cls: 1.9251 2023/02/17 15:45:07 - mmengine - INFO - Epoch(train) [20][ 660/1320] lr: 2.0000e-02 eta: 5:24:18 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.2835 loss: 1.9524 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 1.9524 2023/02/17 15:45:17 - mmengine - INFO - Epoch(train) [20][ 680/1320] lr: 2.0000e-02 eta: 5:24:08 time: 0.4801 data_time: 0.0152 memory: 27031 grad_norm: 4.3198 loss: 1.9313 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9313 2023/02/17 15:45:26 - mmengine - INFO - Epoch(train) [20][ 700/1320] lr: 2.0000e-02 eta: 5:23:58 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 4.3343 loss: 1.7250 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.7250 2023/02/17 15:45:36 - mmengine - INFO - Epoch(train) [20][ 720/1320] lr: 2.0000e-02 eta: 5:23:48 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.0976 loss: 1.7497 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7497 2023/02/17 15:45:46 - mmengine - INFO - Epoch(train) [20][ 740/1320] lr: 2.0000e-02 eta: 5:23:38 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 4.2809 loss: 2.0950 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.0950 2023/02/17 15:45:55 - mmengine - INFO - Epoch(train) [20][ 760/1320] lr: 2.0000e-02 eta: 5:23:29 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.2337 loss: 1.8126 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 1.8126 2023/02/17 15:46:05 - mmengine - INFO - Epoch(train) [20][ 780/1320] lr: 2.0000e-02 eta: 5:23:19 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 4.3286 loss: 2.1387 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1387 2023/02/17 15:46:14 - mmengine - INFO - Epoch(train) [20][ 800/1320] lr: 2.0000e-02 eta: 5:23:09 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.2873 loss: 1.8759 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8759 2023/02/17 15:46:24 - mmengine - INFO - Epoch(train) [20][ 820/1320] lr: 2.0000e-02 eta: 5:22:59 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 4.2673 loss: 1.8680 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8680 2023/02/17 15:46:34 - mmengine - INFO - Epoch(train) [20][ 840/1320] lr: 2.0000e-02 eta: 5:22:50 time: 0.4799 data_time: 0.0153 memory: 27031 grad_norm: 4.3474 loss: 1.8709 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8709 2023/02/17 15:46:43 - mmengine - INFO - Epoch(train) [20][ 860/1320] lr: 2.0000e-02 eta: 5:22:40 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.1755 loss: 1.8959 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8959 2023/02/17 15:46:53 - mmengine - INFO - Epoch(train) [20][ 880/1320] lr: 2.0000e-02 eta: 5:22:30 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.1645 loss: 1.7156 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7156 2023/02/17 15:47:02 - mmengine - INFO - Epoch(train) [20][ 900/1320] lr: 2.0000e-02 eta: 5:22:20 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.2259 loss: 1.7901 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7901 2023/02/17 15:47:12 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:47:12 - mmengine - INFO - Epoch(train) [20][ 920/1320] lr: 2.0000e-02 eta: 5:22:10 time: 0.4792 data_time: 0.0144 memory: 27031 grad_norm: 4.2872 loss: 1.7331 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7331 2023/02/17 15:47:22 - mmengine - INFO - Epoch(train) [20][ 940/1320] lr: 2.0000e-02 eta: 5:22:01 time: 0.4806 data_time: 0.0138 memory: 27031 grad_norm: 4.3091 loss: 1.9974 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9974 2023/02/17 15:47:31 - mmengine - INFO - Epoch(train) [20][ 960/1320] lr: 2.0000e-02 eta: 5:21:51 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.3774 loss: 1.8782 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8782 2023/02/17 15:47:41 - mmengine - INFO - Epoch(train) [20][ 980/1320] lr: 2.0000e-02 eta: 5:21:41 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 4.4053 loss: 1.8663 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8663 2023/02/17 15:47:50 - mmengine - INFO - Epoch(train) [20][1000/1320] lr: 2.0000e-02 eta: 5:21:31 time: 0.4789 data_time: 0.0137 memory: 27031 grad_norm: 4.2512 loss: 1.8934 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8934 2023/02/17 15:48:00 - mmengine - INFO - Epoch(train) [20][1020/1320] lr: 2.0000e-02 eta: 5:21:22 time: 0.4803 data_time: 0.0148 memory: 27031 grad_norm: 4.3029 loss: 1.8662 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.8662 2023/02/17 15:48:10 - mmengine - INFO - Epoch(train) [20][1040/1320] lr: 2.0000e-02 eta: 5:21:12 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.3265 loss: 2.0377 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0377 2023/02/17 15:48:19 - mmengine - INFO - Epoch(train) [20][1060/1320] lr: 2.0000e-02 eta: 5:21:02 time: 0.4799 data_time: 0.0141 memory: 27031 grad_norm: 4.3353 loss: 1.9754 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9754 2023/02/17 15:48:29 - mmengine - INFO - Epoch(train) [20][1080/1320] lr: 2.0000e-02 eta: 5:20:52 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 4.3168 loss: 1.7861 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7861 2023/02/17 15:48:38 - mmengine - INFO - Epoch(train) [20][1100/1320] lr: 2.0000e-02 eta: 5:20:43 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.3422 loss: 1.9496 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9496 2023/02/17 15:48:48 - mmengine - INFO - Epoch(train) [20][1120/1320] lr: 2.0000e-02 eta: 5:20:33 time: 0.4795 data_time: 0.0148 memory: 27031 grad_norm: 4.2842 loss: 1.9568 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9568 2023/02/17 15:48:57 - mmengine - INFO - Epoch(train) [20][1140/1320] lr: 2.0000e-02 eta: 5:20:23 time: 0.4797 data_time: 0.0150 memory: 27031 grad_norm: 4.1786 loss: 1.9930 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9930 2023/02/17 15:49:07 - mmengine - INFO - Epoch(train) [20][1160/1320] lr: 2.0000e-02 eta: 5:20:13 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.3041 loss: 1.7935 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.7935 2023/02/17 15:49:17 - mmengine - INFO - Epoch(train) [20][1180/1320] lr: 2.0000e-02 eta: 5:20:03 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.2653 loss: 1.7747 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.7747 2023/02/17 15:49:26 - mmengine - INFO - Epoch(train) [20][1200/1320] lr: 2.0000e-02 eta: 5:19:54 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.3633 loss: 2.0452 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0452 2023/02/17 15:49:36 - mmengine - INFO - Epoch(train) [20][1220/1320] lr: 2.0000e-02 eta: 5:19:44 time: 0.4782 data_time: 0.0134 memory: 27031 grad_norm: 4.3036 loss: 1.9833 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9833 2023/02/17 15:49:45 - mmengine - INFO - Epoch(train) [20][1240/1320] lr: 2.0000e-02 eta: 5:19:34 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.4046 loss: 1.9083 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9083 2023/02/17 15:49:55 - mmengine - INFO - Epoch(train) [20][1260/1320] lr: 2.0000e-02 eta: 5:19:24 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.2721 loss: 1.9386 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9386 2023/02/17 15:50:05 - mmengine - INFO - Epoch(train) [20][1280/1320] lr: 2.0000e-02 eta: 5:19:15 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 4.1285 loss: 1.7380 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7380 2023/02/17 15:50:14 - mmengine - INFO - Epoch(train) [20][1300/1320] lr: 2.0000e-02 eta: 5:19:05 time: 0.4799 data_time: 0.0152 memory: 27031 grad_norm: 4.3422 loss: 1.8837 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.8837 2023/02/17 15:50:24 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:50:24 - mmengine - INFO - Epoch(train) [20][1320/1320] lr: 2.0000e-02 eta: 5:18:55 time: 0.4739 data_time: 0.0154 memory: 27031 grad_norm: 4.3037 loss: 1.7136 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 1.7136 2023/02/17 15:50:27 - mmengine - INFO - Epoch(val) [20][ 20/194] eta: 0:00:31 time: 0.1813 data_time: 0.0562 memory: 3265 2023/02/17 15:50:30 - mmengine - INFO - Epoch(val) [20][ 40/194] eta: 0:00:24 time: 0.1365 data_time: 0.0128 memory: 3265 2023/02/17 15:50:33 - mmengine - INFO - Epoch(val) [20][ 60/194] eta: 0:00:20 time: 0.1387 data_time: 0.0140 memory: 3265 2023/02/17 15:50:36 - mmengine - INFO - Epoch(val) [20][ 80/194] eta: 0:00:16 time: 0.1385 data_time: 0.0139 memory: 3265 2023/02/17 15:50:38 - mmengine - INFO - Epoch(val) [20][100/194] eta: 0:00:13 time: 0.1378 data_time: 0.0133 memory: 3265 2023/02/17 15:50:41 - mmengine - INFO - Epoch(val) [20][120/194] eta: 0:00:10 time: 0.1377 data_time: 0.0131 memory: 3265 2023/02/17 15:50:44 - mmengine - INFO - Epoch(val) [20][140/194] eta: 0:00:07 time: 0.1396 data_time: 0.0130 memory: 3265 2023/02/17 15:50:47 - mmengine - INFO - Epoch(val) [20][160/194] eta: 0:00:04 time: 0.1399 data_time: 0.0144 memory: 3265 2023/02/17 15:50:50 - mmengine - INFO - Epoch(val) [20][180/194] eta: 0:00:02 time: 0.1408 data_time: 0.0141 memory: 3265 2023/02/17 15:50:52 - mmengine - INFO - Epoch(val) [20][194/194] acc/top1: 0.4792 acc/top5: 0.7725 acc/mean1: 0.4136 2023/02/17 15:50:52 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_13.pth is removed 2023/02/17 15:50:53 - mmengine - INFO - The best checkpoint with 0.4792 acc/top1 at 20 epoch is saved to best_acc/top1_epoch_20.pth. 2023/02/17 15:51:04 - mmengine - INFO - Epoch(train) [21][ 20/1320] lr: 2.0000e-02 eta: 5:18:46 time: 0.5254 data_time: 0.0554 memory: 27031 grad_norm: 4.2475 loss: 1.8984 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8984 2023/02/17 15:51:13 - mmengine - INFO - Epoch(train) [21][ 40/1320] lr: 2.0000e-02 eta: 5:18:37 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 4.3784 loss: 1.8684 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8684 2023/02/17 15:51:23 - mmengine - INFO - Epoch(train) [21][ 60/1320] lr: 2.0000e-02 eta: 5:18:27 time: 0.4800 data_time: 0.0151 memory: 27031 grad_norm: 4.1813 loss: 1.6371 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.6371 2023/02/17 15:51:33 - mmengine - INFO - Epoch(train) [21][ 80/1320] lr: 2.0000e-02 eta: 5:18:17 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3803 loss: 1.4452 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.4452 2023/02/17 15:51:42 - mmengine - INFO - Epoch(train) [21][ 100/1320] lr: 2.0000e-02 eta: 5:18:07 time: 0.4782 data_time: 0.0128 memory: 27031 grad_norm: 4.3341 loss: 1.6987 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.6987 2023/02/17 15:51:52 - mmengine - INFO - Epoch(train) [21][ 120/1320] lr: 2.0000e-02 eta: 5:17:58 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.3667 loss: 1.7647 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7647 2023/02/17 15:52:01 - mmengine - INFO - Epoch(train) [21][ 140/1320] lr: 2.0000e-02 eta: 5:17:48 time: 0.4811 data_time: 0.0154 memory: 27031 grad_norm: 4.4075 loss: 1.9353 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9353 2023/02/17 15:52:11 - mmengine - INFO - Epoch(train) [21][ 160/1320] lr: 2.0000e-02 eta: 5:17:38 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.2627 loss: 1.8052 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8052 2023/02/17 15:52:21 - mmengine - INFO - Epoch(train) [21][ 180/1320] lr: 2.0000e-02 eta: 5:17:28 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.2313 loss: 1.8330 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.8330 2023/02/17 15:52:30 - mmengine - INFO - Epoch(train) [21][ 200/1320] lr: 2.0000e-02 eta: 5:17:19 time: 0.4802 data_time: 0.0136 memory: 27031 grad_norm: 4.3087 loss: 1.6866 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.6866 2023/02/17 15:52:40 - mmengine - INFO - Epoch(train) [21][ 220/1320] lr: 2.0000e-02 eta: 5:17:09 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.3482 loss: 2.0941 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 2.0941 2023/02/17 15:52:49 - mmengine - INFO - Epoch(train) [21][ 240/1320] lr: 2.0000e-02 eta: 5:16:59 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.4045 loss: 1.8160 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8160 2023/02/17 15:52:59 - mmengine - INFO - Epoch(train) [21][ 260/1320] lr: 2.0000e-02 eta: 5:16:49 time: 0.4810 data_time: 0.0152 memory: 27031 grad_norm: 4.2815 loss: 1.8530 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8530 2023/02/17 15:53:09 - mmengine - INFO - Epoch(train) [21][ 280/1320] lr: 2.0000e-02 eta: 5:16:40 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 4.3471 loss: 1.8227 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8227 2023/02/17 15:53:18 - mmengine - INFO - Epoch(train) [21][ 300/1320] lr: 2.0000e-02 eta: 5:16:30 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.3758 loss: 1.8536 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8536 2023/02/17 15:53:28 - mmengine - INFO - Epoch(train) [21][ 320/1320] lr: 2.0000e-02 eta: 5:16:20 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 4.4549 loss: 1.8461 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8461 2023/02/17 15:53:37 - mmengine - INFO - Epoch(train) [21][ 340/1320] lr: 2.0000e-02 eta: 5:16:10 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.5088 loss: 2.0557 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0557 2023/02/17 15:53:47 - mmengine - INFO - Epoch(train) [21][ 360/1320] lr: 2.0000e-02 eta: 5:16:00 time: 0.4811 data_time: 0.0153 memory: 27031 grad_norm: 4.3212 loss: 1.8901 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8901 2023/02/17 15:53:57 - mmengine - INFO - Epoch(train) [21][ 380/1320] lr: 2.0000e-02 eta: 5:15:51 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3653 loss: 1.8182 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8182 2023/02/17 15:54:06 - mmengine - INFO - Epoch(train) [21][ 400/1320] lr: 2.0000e-02 eta: 5:15:41 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.4752 loss: 1.6632 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6632 2023/02/17 15:54:16 - mmengine - INFO - Epoch(train) [21][ 420/1320] lr: 2.0000e-02 eta: 5:15:31 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 4.3521 loss: 1.7636 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.7636 2023/02/17 15:54:25 - mmengine - INFO - Epoch(train) [21][ 440/1320] lr: 2.0000e-02 eta: 5:15:21 time: 0.4793 data_time: 0.0136 memory: 27031 grad_norm: 4.2532 loss: 2.0014 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0014 2023/02/17 15:54:35 - mmengine - INFO - Epoch(train) [21][ 460/1320] lr: 2.0000e-02 eta: 5:15:12 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2443 loss: 1.6761 top1_acc: 0.3125 top5_acc: 0.9375 loss_cls: 1.6761 2023/02/17 15:54:45 - mmengine - INFO - Epoch(train) [21][ 480/1320] lr: 2.0000e-02 eta: 5:15:02 time: 0.4786 data_time: 0.0137 memory: 27031 grad_norm: 4.4468 loss: 1.7166 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.7166 2023/02/17 15:54:54 - mmengine - INFO - Epoch(train) [21][ 500/1320] lr: 2.0000e-02 eta: 5:14:52 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 4.2448 loss: 1.7776 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7776 2023/02/17 15:55:04 - mmengine - INFO - Epoch(train) [21][ 520/1320] lr: 2.0000e-02 eta: 5:14:42 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.4126 loss: 1.9114 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9114 2023/02/17 15:55:13 - mmengine - INFO - Epoch(train) [21][ 540/1320] lr: 2.0000e-02 eta: 5:14:33 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.3722 loss: 1.7595 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 1.7595 2023/02/17 15:55:23 - mmengine - INFO - Epoch(train) [21][ 560/1320] lr: 2.0000e-02 eta: 5:14:23 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.3409 loss: 1.8779 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8779 2023/02/17 15:55:33 - mmengine - INFO - Epoch(train) [21][ 580/1320] lr: 2.0000e-02 eta: 5:14:13 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.3929 loss: 1.9465 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.9465 2023/02/17 15:55:42 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 15:55:42 - mmengine - INFO - Epoch(train) [21][ 600/1320] lr: 2.0000e-02 eta: 5:14:03 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.3236 loss: 1.8929 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.8929 2023/02/17 15:55:52 - mmengine - INFO - Epoch(train) [21][ 620/1320] lr: 2.0000e-02 eta: 5:13:54 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.3675 loss: 1.9222 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.9222 2023/02/17 15:56:01 - mmengine - INFO - Epoch(train) [21][ 640/1320] lr: 2.0000e-02 eta: 5:13:44 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.3941 loss: 1.8416 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8416 2023/02/17 15:56:11 - mmengine - INFO - Epoch(train) [21][ 660/1320] lr: 2.0000e-02 eta: 5:13:34 time: 0.4806 data_time: 0.0158 memory: 27031 grad_norm: 4.2139 loss: 1.8993 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8993 2023/02/17 15:56:21 - mmengine - INFO - Epoch(train) [21][ 680/1320] lr: 2.0000e-02 eta: 5:13:24 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 4.3272 loss: 1.9486 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9486 2023/02/17 15:56:30 - mmengine - INFO - Epoch(train) [21][ 700/1320] lr: 2.0000e-02 eta: 5:13:15 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 4.3161 loss: 1.9721 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9721 2023/02/17 15:56:40 - mmengine - INFO - Epoch(train) [21][ 720/1320] lr: 2.0000e-02 eta: 5:13:05 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 4.3907 loss: 2.0480 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0480 2023/02/17 15:56:49 - mmengine - INFO - Epoch(train) [21][ 740/1320] lr: 2.0000e-02 eta: 5:12:55 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.3556 loss: 1.7131 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7131 2023/02/17 15:56:59 - mmengine - INFO - Epoch(train) [21][ 760/1320] lr: 2.0000e-02 eta: 5:12:45 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 4.4216 loss: 1.8521 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8521 2023/02/17 15:57:09 - mmengine - INFO - Epoch(train) [21][ 780/1320] lr: 2.0000e-02 eta: 5:12:36 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 4.4161 loss: 1.8113 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8113 2023/02/17 15:57:18 - mmengine - INFO - Epoch(train) [21][ 800/1320] lr: 2.0000e-02 eta: 5:12:26 time: 0.4803 data_time: 0.0148 memory: 27031 grad_norm: 4.2015 loss: 1.7623 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7623 2023/02/17 15:57:28 - mmengine - INFO - Epoch(train) [21][ 820/1320] lr: 2.0000e-02 eta: 5:12:16 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.3708 loss: 1.9060 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9060 2023/02/17 15:57:38 - mmengine - INFO - Epoch(train) [21][ 840/1320] lr: 2.0000e-02 eta: 5:12:06 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.2030 loss: 1.7940 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7940 2023/02/17 15:57:47 - mmengine - INFO - Epoch(train) [21][ 860/1320] lr: 2.0000e-02 eta: 5:11:57 time: 0.4789 data_time: 0.0134 memory: 27031 grad_norm: 4.2209 loss: 1.9115 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.9115 2023/02/17 15:57:57 - mmengine - INFO - Epoch(train) [21][ 880/1320] lr: 2.0000e-02 eta: 5:11:47 time: 0.4801 data_time: 0.0153 memory: 27031 grad_norm: 4.2886 loss: 1.8905 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8905 2023/02/17 15:58:06 - mmengine - INFO - Epoch(train) [21][ 900/1320] lr: 2.0000e-02 eta: 5:11:37 time: 0.4797 data_time: 0.0137 memory: 27031 grad_norm: 4.2751 loss: 1.6849 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.6849 2023/02/17 15:58:16 - mmengine - INFO - Epoch(train) [21][ 920/1320] lr: 2.0000e-02 eta: 5:11:27 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 4.3876 loss: 1.9498 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9498 2023/02/17 15:58:26 - mmengine - INFO - Epoch(train) [21][ 940/1320] lr: 2.0000e-02 eta: 5:11:18 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 4.5173 loss: 1.9112 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9112 2023/02/17 15:58:35 - mmengine - INFO - Epoch(train) [21][ 960/1320] lr: 2.0000e-02 eta: 5:11:08 time: 0.4793 data_time: 0.0147 memory: 27031 grad_norm: 4.2737 loss: 1.9028 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.9028 2023/02/17 15:58:45 - mmengine - INFO - Epoch(train) [21][ 980/1320] lr: 2.0000e-02 eta: 5:10:58 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.3749 loss: 1.8896 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8896 2023/02/17 15:58:54 - mmengine - INFO - Epoch(train) [21][1000/1320] lr: 2.0000e-02 eta: 5:10:48 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.3494 loss: 1.8981 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8981 2023/02/17 15:59:04 - mmengine - INFO - Epoch(train) [21][1020/1320] lr: 2.0000e-02 eta: 5:10:39 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.2289 loss: 1.8217 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8217 2023/02/17 15:59:14 - mmengine - INFO - Epoch(train) [21][1040/1320] lr: 2.0000e-02 eta: 5:10:29 time: 0.4821 data_time: 0.0171 memory: 27031 grad_norm: 4.3518 loss: 2.1033 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 2.1033 2023/02/17 15:59:23 - mmengine - INFO - Epoch(train) [21][1060/1320] lr: 2.0000e-02 eta: 5:10:19 time: 0.4796 data_time: 0.0135 memory: 27031 grad_norm: 4.4102 loss: 2.1168 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1168 2023/02/17 15:59:33 - mmengine - INFO - Epoch(train) [21][1080/1320] lr: 2.0000e-02 eta: 5:10:09 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.0863 loss: 1.7982 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.7982 2023/02/17 15:59:42 - mmengine - INFO - Epoch(train) [21][1100/1320] lr: 2.0000e-02 eta: 5:10:00 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.3139 loss: 1.7678 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7678 2023/02/17 15:59:52 - mmengine - INFO - Epoch(train) [21][1120/1320] lr: 2.0000e-02 eta: 5:09:50 time: 0.4792 data_time: 0.0147 memory: 27031 grad_norm: 4.2306 loss: 1.9601 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 1.9601 2023/02/17 16:00:02 - mmengine - INFO - Epoch(train) [21][1140/1320] lr: 2.0000e-02 eta: 5:09:40 time: 0.4816 data_time: 0.0157 memory: 27031 grad_norm: 4.4079 loss: 1.8567 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8567 2023/02/17 16:00:11 - mmengine - INFO - Epoch(train) [21][1160/1320] lr: 2.0000e-02 eta: 5:09:30 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.3526 loss: 1.9418 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9418 2023/02/17 16:00:21 - mmengine - INFO - Epoch(train) [21][1180/1320] lr: 2.0000e-02 eta: 5:09:21 time: 0.4797 data_time: 0.0136 memory: 27031 grad_norm: 4.2343 loss: 1.9847 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9847 2023/02/17 16:00:30 - mmengine - INFO - Epoch(train) [21][1200/1320] lr: 2.0000e-02 eta: 5:09:11 time: 0.4795 data_time: 0.0147 memory: 27031 grad_norm: 4.3413 loss: 1.7486 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7486 2023/02/17 16:00:40 - mmengine - INFO - Epoch(train) [21][1220/1320] lr: 2.0000e-02 eta: 5:09:01 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 4.3549 loss: 1.8815 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8815 2023/02/17 16:00:50 - mmengine - INFO - Epoch(train) [21][1240/1320] lr: 2.0000e-02 eta: 5:08:51 time: 0.4795 data_time: 0.0153 memory: 27031 grad_norm: 4.1268 loss: 1.6750 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.6750 2023/02/17 16:00:59 - mmengine - INFO - Epoch(train) [21][1260/1320] lr: 2.0000e-02 eta: 5:08:42 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.2950 loss: 2.0409 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.0409 2023/02/17 16:01:09 - mmengine - INFO - Epoch(train) [21][1280/1320] lr: 2.0000e-02 eta: 5:08:32 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.4601 loss: 1.9384 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9384 2023/02/17 16:01:18 - mmengine - INFO - Epoch(train) [21][1300/1320] lr: 2.0000e-02 eta: 5:08:22 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.4064 loss: 1.8665 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8665 2023/02/17 16:01:28 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:01:28 - mmengine - INFO - Epoch(train) [21][1320/1320] lr: 2.0000e-02 eta: 5:08:12 time: 0.4742 data_time: 0.0162 memory: 27031 grad_norm: 4.2424 loss: 1.8379 top1_acc: 0.4545 top5_acc: 0.6364 loss_cls: 1.8379 2023/02/17 16:01:28 - mmengine - INFO - Saving checkpoint at 21 epochs 2023/02/17 16:01:33 - mmengine - INFO - Epoch(val) [21][ 20/194] eta: 0:00:33 time: 0.1923 data_time: 0.0647 memory: 3265 2023/02/17 16:01:35 - mmengine - INFO - Epoch(val) [21][ 40/194] eta: 0:00:25 time: 0.1363 data_time: 0.0120 memory: 3265 2023/02/17 16:01:38 - mmengine - INFO - Epoch(val) [21][ 60/194] eta: 0:00:20 time: 0.1375 data_time: 0.0133 memory: 3265 2023/02/17 16:01:41 - mmengine - INFO - Epoch(val) [21][ 80/194] eta: 0:00:17 time: 0.1370 data_time: 0.0128 memory: 3265 2023/02/17 16:01:44 - mmengine - INFO - Epoch(val) [21][100/194] eta: 0:00:13 time: 0.1373 data_time: 0.0133 memory: 3265 2023/02/17 16:01:46 - mmengine - INFO - Epoch(val) [21][120/194] eta: 0:00:10 time: 0.1392 data_time: 0.0138 memory: 3265 2023/02/17 16:01:49 - mmengine - INFO - Epoch(val) [21][140/194] eta: 0:00:07 time: 0.1391 data_time: 0.0142 memory: 3265 2023/02/17 16:01:52 - mmengine - INFO - Epoch(val) [21][160/194] eta: 0:00:04 time: 0.1393 data_time: 0.0144 memory: 3265 2023/02/17 16:01:55 - mmengine - INFO - Epoch(val) [21][180/194] eta: 0:00:02 time: 0.1372 data_time: 0.0126 memory: 3265 2023/02/17 16:01:57 - mmengine - INFO - Epoch(val) [21][194/194] acc/top1: 0.4861 acc/top5: 0.7751 acc/mean1: 0.4206 2023/02/17 16:01:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_20.pth is removed 2023/02/17 16:01:58 - mmengine - INFO - The best checkpoint with 0.4861 acc/top1 at 21 epoch is saved to best_acc/top1_epoch_21.pth. 2023/02/17 16:02:09 - mmengine - INFO - Epoch(train) [22][ 20/1320] lr: 2.0000e-02 eta: 5:08:04 time: 0.5223 data_time: 0.0521 memory: 27031 grad_norm: 4.2382 loss: 1.8769 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8769 2023/02/17 16:02:18 - mmengine - INFO - Epoch(train) [22][ 40/1320] lr: 2.0000e-02 eta: 5:07:54 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.2412 loss: 1.7049 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7049 2023/02/17 16:02:28 - mmengine - INFO - Epoch(train) [22][ 60/1320] lr: 2.0000e-02 eta: 5:07:44 time: 0.4781 data_time: 0.0131 memory: 27031 grad_norm: 4.3293 loss: 1.9126 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9126 2023/02/17 16:02:38 - mmengine - INFO - Epoch(train) [22][ 80/1320] lr: 2.0000e-02 eta: 5:07:34 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.3272 loss: 1.7905 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7905 2023/02/17 16:02:47 - mmengine - INFO - Epoch(train) [22][ 100/1320] lr: 2.0000e-02 eta: 5:07:24 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 4.2934 loss: 1.8628 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8628 2023/02/17 16:02:57 - mmengine - INFO - Epoch(train) [22][ 120/1320] lr: 2.0000e-02 eta: 5:07:15 time: 0.4795 data_time: 0.0139 memory: 27031 grad_norm: 4.3410 loss: 1.8875 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8875 2023/02/17 16:03:06 - mmengine - INFO - Epoch(train) [22][ 140/1320] lr: 2.0000e-02 eta: 5:07:05 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.3852 loss: 1.8747 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8747 2023/02/17 16:03:16 - mmengine - INFO - Epoch(train) [22][ 160/1320] lr: 2.0000e-02 eta: 5:06:55 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.3457 loss: 1.8807 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.8807 2023/02/17 16:03:26 - mmengine - INFO - Epoch(train) [22][ 180/1320] lr: 2.0000e-02 eta: 5:06:45 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.2033 loss: 1.9604 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9604 2023/02/17 16:03:35 - mmengine - INFO - Epoch(train) [22][ 200/1320] lr: 2.0000e-02 eta: 5:06:36 time: 0.4809 data_time: 0.0153 memory: 27031 grad_norm: 4.3743 loss: 1.9523 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9523 2023/02/17 16:03:45 - mmengine - INFO - Epoch(train) [22][ 220/1320] lr: 2.0000e-02 eta: 5:06:26 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.3486 loss: 1.8543 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8543 2023/02/17 16:03:54 - mmengine - INFO - Epoch(train) [22][ 240/1320] lr: 2.0000e-02 eta: 5:06:16 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 4.2734 loss: 1.4934 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.4934 2023/02/17 16:04:04 - mmengine - INFO - Epoch(train) [22][ 260/1320] lr: 2.0000e-02 eta: 5:06:06 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.3431 loss: 1.8173 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8173 2023/02/17 16:04:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:04:14 - mmengine - INFO - Epoch(train) [22][ 280/1320] lr: 2.0000e-02 eta: 5:05:57 time: 0.4837 data_time: 0.0173 memory: 27031 grad_norm: 4.2763 loss: 1.8578 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8578 2023/02/17 16:04:23 - mmengine - INFO - Epoch(train) [22][ 300/1320] lr: 2.0000e-02 eta: 5:05:47 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.2118 loss: 1.8366 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.8366 2023/02/17 16:04:33 - mmengine - INFO - Epoch(train) [22][ 320/1320] lr: 2.0000e-02 eta: 5:05:37 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.1967 loss: 1.7446 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7446 2023/02/17 16:04:42 - mmengine - INFO - Epoch(train) [22][ 340/1320] lr: 2.0000e-02 eta: 5:05:27 time: 0.4787 data_time: 0.0138 memory: 27031 grad_norm: 4.4264 loss: 1.9024 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.9024 2023/02/17 16:04:52 - mmengine - INFO - Epoch(train) [22][ 360/1320] lr: 2.0000e-02 eta: 5:05:18 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.5011 loss: 1.8455 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.8455 2023/02/17 16:05:02 - mmengine - INFO - Epoch(train) [22][ 380/1320] lr: 2.0000e-02 eta: 5:05:08 time: 0.4788 data_time: 0.0136 memory: 27031 grad_norm: 4.3965 loss: 1.9113 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9113 2023/02/17 16:05:11 - mmengine - INFO - Epoch(train) [22][ 400/1320] lr: 2.0000e-02 eta: 5:04:58 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.1638 loss: 1.8008 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8008 2023/02/17 16:05:21 - mmengine - INFO - Epoch(train) [22][ 420/1320] lr: 2.0000e-02 eta: 5:04:48 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 4.2830 loss: 1.5894 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5894 2023/02/17 16:05:30 - mmengine - INFO - Epoch(train) [22][ 440/1320] lr: 2.0000e-02 eta: 5:04:39 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.4560 loss: 1.8841 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8841 2023/02/17 16:05:40 - mmengine - INFO - Epoch(train) [22][ 460/1320] lr: 2.0000e-02 eta: 5:04:29 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.3934 loss: 1.9644 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9644 2023/02/17 16:05:50 - mmengine - INFO - Epoch(train) [22][ 480/1320] lr: 2.0000e-02 eta: 5:04:19 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.4217 loss: 1.8643 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8643 2023/02/17 16:05:59 - mmengine - INFO - Epoch(train) [22][ 500/1320] lr: 2.0000e-02 eta: 5:04:09 time: 0.4788 data_time: 0.0136 memory: 27031 grad_norm: 4.1728 loss: 1.7246 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7246 2023/02/17 16:06:09 - mmengine - INFO - Epoch(train) [22][ 520/1320] lr: 2.0000e-02 eta: 5:04:00 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.2648 loss: 1.7322 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.7322 2023/02/17 16:06:18 - mmengine - INFO - Epoch(train) [22][ 540/1320] lr: 2.0000e-02 eta: 5:03:50 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 4.2233 loss: 1.9844 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9844 2023/02/17 16:06:28 - mmengine - INFO - Epoch(train) [22][ 560/1320] lr: 2.0000e-02 eta: 5:03:40 time: 0.4802 data_time: 0.0152 memory: 27031 grad_norm: 4.3478 loss: 1.7295 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.7295 2023/02/17 16:06:38 - mmengine - INFO - Epoch(train) [22][ 580/1320] lr: 2.0000e-02 eta: 5:03:30 time: 0.4810 data_time: 0.0149 memory: 27031 grad_norm: 4.3282 loss: 1.8182 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.8182 2023/02/17 16:06:47 - mmengine - INFO - Epoch(train) [22][ 600/1320] lr: 2.0000e-02 eta: 5:03:21 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.3258 loss: 1.9039 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9039 2023/02/17 16:06:57 - mmengine - INFO - Epoch(train) [22][ 620/1320] lr: 2.0000e-02 eta: 5:03:11 time: 0.4798 data_time: 0.0150 memory: 27031 grad_norm: 4.2452 loss: 1.9126 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9126 2023/02/17 16:07:06 - mmengine - INFO - Epoch(train) [22][ 640/1320] lr: 2.0000e-02 eta: 5:03:01 time: 0.4798 data_time: 0.0149 memory: 27031 grad_norm: 4.3833 loss: 1.9884 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9884 2023/02/17 16:07:16 - mmengine - INFO - Epoch(train) [22][ 660/1320] lr: 2.0000e-02 eta: 5:02:51 time: 0.4785 data_time: 0.0132 memory: 27031 grad_norm: 4.4093 loss: 1.9369 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9369 2023/02/17 16:07:26 - mmengine - INFO - Epoch(train) [22][ 680/1320] lr: 2.0000e-02 eta: 5:02:42 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 4.2586 loss: 1.8736 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8736 2023/02/17 16:07:35 - mmengine - INFO - Epoch(train) [22][ 700/1320] lr: 2.0000e-02 eta: 5:02:32 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 4.4035 loss: 1.7059 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7059 2023/02/17 16:07:45 - mmengine - INFO - Epoch(train) [22][ 720/1320] lr: 2.0000e-02 eta: 5:02:22 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.2595 loss: 1.7030 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7030 2023/02/17 16:07:54 - mmengine - INFO - Epoch(train) [22][ 740/1320] lr: 2.0000e-02 eta: 5:02:13 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.3538 loss: 1.9308 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9308 2023/02/17 16:08:04 - mmengine - INFO - Epoch(train) [22][ 760/1320] lr: 2.0000e-02 eta: 5:02:03 time: 0.4785 data_time: 0.0134 memory: 27031 grad_norm: 4.3769 loss: 1.8859 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8859 2023/02/17 16:08:14 - mmengine - INFO - Epoch(train) [22][ 780/1320] lr: 2.0000e-02 eta: 5:01:53 time: 0.4811 data_time: 0.0162 memory: 27031 grad_norm: 4.3152 loss: 1.9624 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.9624 2023/02/17 16:08:23 - mmengine - INFO - Epoch(train) [22][ 800/1320] lr: 2.0000e-02 eta: 5:01:43 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.3000 loss: 1.7698 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7698 2023/02/17 16:08:33 - mmengine - INFO - Epoch(train) [22][ 820/1320] lr: 2.0000e-02 eta: 5:01:34 time: 0.4792 data_time: 0.0138 memory: 27031 grad_norm: 4.5047 loss: 1.8930 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8930 2023/02/17 16:08:42 - mmengine - INFO - Epoch(train) [22][ 840/1320] lr: 2.0000e-02 eta: 5:01:24 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 4.2838 loss: 2.0531 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0531 2023/02/17 16:08:52 - mmengine - INFO - Epoch(train) [22][ 860/1320] lr: 2.0000e-02 eta: 5:01:14 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 4.1815 loss: 1.8269 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8269 2023/02/17 16:09:02 - mmengine - INFO - Epoch(train) [22][ 880/1320] lr: 2.0000e-02 eta: 5:01:04 time: 0.4790 data_time: 0.0145 memory: 27031 grad_norm: 4.2925 loss: 1.8686 top1_acc: 0.4375 top5_acc: 0.5625 loss_cls: 1.8686 2023/02/17 16:09:11 - mmengine - INFO - Epoch(train) [22][ 900/1320] lr: 2.0000e-02 eta: 5:00:55 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.3555 loss: 1.9146 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9146 2023/02/17 16:09:21 - mmengine - INFO - Epoch(train) [22][ 920/1320] lr: 2.0000e-02 eta: 5:00:45 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.2298 loss: 1.7579 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7579 2023/02/17 16:09:30 - mmengine - INFO - Epoch(train) [22][ 940/1320] lr: 2.0000e-02 eta: 5:00:35 time: 0.4795 data_time: 0.0150 memory: 27031 grad_norm: 4.3332 loss: 1.9298 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9298 2023/02/17 16:09:40 - mmengine - INFO - Epoch(train) [22][ 960/1320] lr: 2.0000e-02 eta: 5:00:25 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.2728 loss: 1.7862 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7862 2023/02/17 16:09:50 - mmengine - INFO - Epoch(train) [22][ 980/1320] lr: 2.0000e-02 eta: 5:00:15 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.2675 loss: 1.7885 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7885 2023/02/17 16:09:59 - mmengine - INFO - Epoch(train) [22][1000/1320] lr: 2.0000e-02 eta: 5:00:06 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.2889 loss: 1.7953 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7953 2023/02/17 16:10:09 - mmengine - INFO - Epoch(train) [22][1020/1320] lr: 2.0000e-02 eta: 4:59:56 time: 0.4803 data_time: 0.0137 memory: 27031 grad_norm: 4.4628 loss: 1.8846 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8846 2023/02/17 16:10:18 - mmengine - INFO - Epoch(train) [22][1040/1320] lr: 2.0000e-02 eta: 4:59:46 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 4.3565 loss: 1.7920 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.7920 2023/02/17 16:10:28 - mmengine - INFO - Epoch(train) [22][1060/1320] lr: 2.0000e-02 eta: 4:59:37 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.2416 loss: 1.8932 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.8932 2023/02/17 16:10:38 - mmengine - INFO - Epoch(train) [22][1080/1320] lr: 2.0000e-02 eta: 4:59:27 time: 0.4791 data_time: 0.0139 memory: 27031 grad_norm: 4.2871 loss: 1.6737 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.6737 2023/02/17 16:10:47 - mmengine - INFO - Epoch(train) [22][1100/1320] lr: 2.0000e-02 eta: 4:59:17 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.2932 loss: 1.8245 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8245 2023/02/17 16:10:57 - mmengine - INFO - Epoch(train) [22][1120/1320] lr: 2.0000e-02 eta: 4:59:07 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.3221 loss: 1.9538 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9538 2023/02/17 16:11:06 - mmengine - INFO - Epoch(train) [22][1140/1320] lr: 2.0000e-02 eta: 4:58:58 time: 0.4788 data_time: 0.0135 memory: 27031 grad_norm: 4.3672 loss: 1.6544 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.6544 2023/02/17 16:11:16 - mmengine - INFO - Epoch(train) [22][1160/1320] lr: 2.0000e-02 eta: 4:58:48 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 4.2957 loss: 1.8942 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8942 2023/02/17 16:11:26 - mmengine - INFO - Epoch(train) [22][1180/1320] lr: 2.0000e-02 eta: 4:58:38 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.2686 loss: 1.9706 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9706 2023/02/17 16:11:35 - mmengine - INFO - Epoch(train) [22][1200/1320] lr: 2.0000e-02 eta: 4:58:28 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.3514 loss: 1.7660 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.7660 2023/02/17 16:11:45 - mmengine - INFO - Epoch(train) [22][1220/1320] lr: 2.0000e-02 eta: 4:58:19 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.3470 loss: 1.9268 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9268 2023/02/17 16:11:54 - mmengine - INFO - Epoch(train) [22][1240/1320] lr: 2.0000e-02 eta: 4:58:09 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.3203 loss: 1.9725 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9725 2023/02/17 16:12:04 - mmengine - INFO - Epoch(train) [22][1260/1320] lr: 2.0000e-02 eta: 4:57:59 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 4.3425 loss: 1.9622 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.9622 2023/02/17 16:12:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:12:14 - mmengine - INFO - Epoch(train) [22][1280/1320] lr: 2.0000e-02 eta: 4:57:49 time: 0.4797 data_time: 0.0148 memory: 27031 grad_norm: 4.2702 loss: 1.8164 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.8164 2023/02/17 16:12:23 - mmengine - INFO - Epoch(train) [22][1300/1320] lr: 2.0000e-02 eta: 4:57:40 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.4100 loss: 1.9211 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9211 2023/02/17 16:12:33 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:12:33 - mmengine - INFO - Epoch(train) [22][1320/1320] lr: 2.0000e-02 eta: 4:57:30 time: 0.4738 data_time: 0.0158 memory: 27031 grad_norm: 4.2149 loss: 1.9885 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.9885 2023/02/17 16:12:36 - mmengine - INFO - Epoch(val) [22][ 20/194] eta: 0:00:31 time: 0.1817 data_time: 0.0563 memory: 3265 2023/02/17 16:12:39 - mmengine - INFO - Epoch(val) [22][ 40/194] eta: 0:00:24 time: 0.1395 data_time: 0.0147 memory: 3265 2023/02/17 16:12:42 - mmengine - INFO - Epoch(val) [22][ 60/194] eta: 0:00:20 time: 0.1375 data_time: 0.0130 memory: 3265 2023/02/17 16:12:45 - mmengine - INFO - Epoch(val) [22][ 80/194] eta: 0:00:17 time: 0.1398 data_time: 0.0143 memory: 3265 2023/02/17 16:12:47 - mmengine - INFO - Epoch(val) [22][100/194] eta: 0:00:13 time: 0.1378 data_time: 0.0134 memory: 3265 2023/02/17 16:12:50 - mmengine - INFO - Epoch(val) [22][120/194] eta: 0:00:10 time: 0.1384 data_time: 0.0136 memory: 3265 2023/02/17 16:12:53 - mmengine - INFO - Epoch(val) [22][140/194] eta: 0:00:07 time: 0.1381 data_time: 0.0133 memory: 3265 2023/02/17 16:12:56 - mmengine - INFO - Epoch(val) [22][160/194] eta: 0:00:04 time: 0.1384 data_time: 0.0138 memory: 3265 2023/02/17 16:12:58 - mmengine - INFO - Epoch(val) [22][180/194] eta: 0:00:02 time: 0.1394 data_time: 0.0142 memory: 3265 2023/02/17 16:13:01 - mmengine - INFO - Epoch(val) [22][194/194] acc/top1: 0.4854 acc/top5: 0.7737 acc/mean1: 0.4111 2023/02/17 16:13:12 - mmengine - INFO - Epoch(train) [23][ 20/1320] lr: 2.0000e-02 eta: 4:57:21 time: 0.5353 data_time: 0.0581 memory: 27031 grad_norm: 4.3201 loss: 1.9240 top1_acc: 0.4375 top5_acc: 1.0000 loss_cls: 1.9240 2023/02/17 16:13:22 - mmengine - INFO - Epoch(train) [23][ 40/1320] lr: 2.0000e-02 eta: 4:57:12 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.1139 loss: 1.6662 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.6662 2023/02/17 16:13:31 - mmengine - INFO - Epoch(train) [23][ 60/1320] lr: 2.0000e-02 eta: 4:57:02 time: 0.4787 data_time: 0.0142 memory: 27031 grad_norm: 4.2034 loss: 1.5378 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.5378 2023/02/17 16:13:41 - mmengine - INFO - Epoch(train) [23][ 80/1320] lr: 2.0000e-02 eta: 4:56:52 time: 0.4804 data_time: 0.0152 memory: 27031 grad_norm: 4.3574 loss: 1.8872 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8872 2023/02/17 16:13:50 - mmengine - INFO - Epoch(train) [23][ 100/1320] lr: 2.0000e-02 eta: 4:56:42 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.2286 loss: 1.7249 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7249 2023/02/17 16:14:00 - mmengine - INFO - Epoch(train) [23][ 120/1320] lr: 2.0000e-02 eta: 4:56:33 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.5137 loss: 1.7309 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.7309 2023/02/17 16:14:10 - mmengine - INFO - Epoch(train) [23][ 140/1320] lr: 2.0000e-02 eta: 4:56:23 time: 0.4786 data_time: 0.0136 memory: 27031 grad_norm: 4.3203 loss: 1.8279 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8279 2023/02/17 16:14:19 - mmengine - INFO - Epoch(train) [23][ 160/1320] lr: 2.0000e-02 eta: 4:56:13 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.3645 loss: 1.7967 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7967 2023/02/17 16:14:29 - mmengine - INFO - Epoch(train) [23][ 180/1320] lr: 2.0000e-02 eta: 4:56:03 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.4573 loss: 2.0202 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0202 2023/02/17 16:14:38 - mmengine - INFO - Epoch(train) [23][ 200/1320] lr: 2.0000e-02 eta: 4:55:54 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.4383 loss: 1.7870 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7870 2023/02/17 16:14:48 - mmengine - INFO - Epoch(train) [23][ 220/1320] lr: 2.0000e-02 eta: 4:55:44 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.2056 loss: 1.7052 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.7052 2023/02/17 16:14:57 - mmengine - INFO - Epoch(train) [23][ 240/1320] lr: 2.0000e-02 eta: 4:55:34 time: 0.4790 data_time: 0.0132 memory: 27031 grad_norm: 4.1718 loss: 1.7929 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7929 2023/02/17 16:15:07 - mmengine - INFO - Epoch(train) [23][ 260/1320] lr: 2.0000e-02 eta: 4:55:24 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.2451 loss: 1.9610 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9610 2023/02/17 16:15:17 - mmengine - INFO - Epoch(train) [23][ 280/1320] lr: 2.0000e-02 eta: 4:55:15 time: 0.4802 data_time: 0.0156 memory: 27031 grad_norm: 4.4108 loss: 1.6464 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.6464 2023/02/17 16:15:26 - mmengine - INFO - Epoch(train) [23][ 300/1320] lr: 2.0000e-02 eta: 4:55:05 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 4.3841 loss: 1.7862 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.7862 2023/02/17 16:15:36 - mmengine - INFO - Epoch(train) [23][ 320/1320] lr: 2.0000e-02 eta: 4:54:55 time: 0.4794 data_time: 0.0149 memory: 27031 grad_norm: 4.3753 loss: 1.7876 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.7876 2023/02/17 16:15:45 - mmengine - INFO - Epoch(train) [23][ 340/1320] lr: 2.0000e-02 eta: 4:54:45 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.2740 loss: 1.8435 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.8435 2023/02/17 16:15:55 - mmengine - INFO - Epoch(train) [23][ 360/1320] lr: 2.0000e-02 eta: 4:54:36 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.4753 loss: 1.8048 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8048 2023/02/17 16:16:05 - mmengine - INFO - Epoch(train) [23][ 380/1320] lr: 2.0000e-02 eta: 4:54:26 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.4330 loss: 1.9636 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9636 2023/02/17 16:16:14 - mmengine - INFO - Epoch(train) [23][ 400/1320] lr: 2.0000e-02 eta: 4:54:16 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.2302 loss: 1.6977 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.6977 2023/02/17 16:16:24 - mmengine - INFO - Epoch(train) [23][ 420/1320] lr: 2.0000e-02 eta: 4:54:07 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 4.1601 loss: 1.6706 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6706 2023/02/17 16:16:33 - mmengine - INFO - Epoch(train) [23][ 440/1320] lr: 2.0000e-02 eta: 4:53:57 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.3120 loss: 1.8757 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8757 2023/02/17 16:16:43 - mmengine - INFO - Epoch(train) [23][ 460/1320] lr: 2.0000e-02 eta: 4:53:47 time: 0.4784 data_time: 0.0134 memory: 27031 grad_norm: 4.3072 loss: 1.8616 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8616 2023/02/17 16:16:53 - mmengine - INFO - Epoch(train) [23][ 480/1320] lr: 2.0000e-02 eta: 4:53:37 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.2813 loss: 1.7870 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7870 2023/02/17 16:17:02 - mmengine - INFO - Epoch(train) [23][ 500/1320] lr: 2.0000e-02 eta: 4:53:28 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.2386 loss: 1.7339 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.7339 2023/02/17 16:17:12 - mmengine - INFO - Epoch(train) [23][ 520/1320] lr: 2.0000e-02 eta: 4:53:18 time: 0.4785 data_time: 0.0135 memory: 27031 grad_norm: 4.4022 loss: 1.5827 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.5827 2023/02/17 16:17:21 - mmengine - INFO - Epoch(train) [23][ 540/1320] lr: 2.0000e-02 eta: 4:53:08 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.3859 loss: 1.8330 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8330 2023/02/17 16:17:31 - mmengine - INFO - Epoch(train) [23][ 560/1320] lr: 2.0000e-02 eta: 4:52:58 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.3838 loss: 1.8221 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8221 2023/02/17 16:17:41 - mmengine - INFO - Epoch(train) [23][ 580/1320] lr: 2.0000e-02 eta: 4:52:49 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.4059 loss: 1.8856 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8856 2023/02/17 16:17:50 - mmengine - INFO - Epoch(train) [23][ 600/1320] lr: 2.0000e-02 eta: 4:52:39 time: 0.4810 data_time: 0.0151 memory: 27031 grad_norm: 4.2445 loss: 1.6809 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6809 2023/02/17 16:18:00 - mmengine - INFO - Epoch(train) [23][ 620/1320] lr: 2.0000e-02 eta: 4:52:29 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.3240 loss: 1.7675 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.7675 2023/02/17 16:18:09 - mmengine - INFO - Epoch(train) [23][ 640/1320] lr: 2.0000e-02 eta: 4:52:19 time: 0.4807 data_time: 0.0151 memory: 27031 grad_norm: 4.5327 loss: 1.7549 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7549 2023/02/17 16:18:19 - mmengine - INFO - Epoch(train) [23][ 660/1320] lr: 2.0000e-02 eta: 4:52:10 time: 0.4795 data_time: 0.0141 memory: 27031 grad_norm: 4.3952 loss: 1.6180 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6180 2023/02/17 16:18:29 - mmengine - INFO - Epoch(train) [23][ 680/1320] lr: 2.0000e-02 eta: 4:52:00 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.2045 loss: 1.7961 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.7961 2023/02/17 16:18:38 - mmengine - INFO - Epoch(train) [23][ 700/1320] lr: 2.0000e-02 eta: 4:51:50 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.5382 loss: 1.7904 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.7904 2023/02/17 16:18:48 - mmengine - INFO - Epoch(train) [23][ 720/1320] lr: 2.0000e-02 eta: 4:51:40 time: 0.4787 data_time: 0.0135 memory: 27031 grad_norm: 4.2161 loss: 1.7443 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.7443 2023/02/17 16:18:57 - mmengine - INFO - Epoch(train) [23][ 740/1320] lr: 2.0000e-02 eta: 4:51:31 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.3631 loss: 1.8139 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8139 2023/02/17 16:19:07 - mmengine - INFO - Epoch(train) [23][ 760/1320] lr: 2.0000e-02 eta: 4:51:21 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.2784 loss: 1.7734 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.7734 2023/02/17 16:19:17 - mmengine - INFO - Epoch(train) [23][ 780/1320] lr: 2.0000e-02 eta: 4:51:11 time: 0.4791 data_time: 0.0136 memory: 27031 grad_norm: 4.3797 loss: 1.8506 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 1.8506 2023/02/17 16:19:26 - mmengine - INFO - Epoch(train) [23][ 800/1320] lr: 2.0000e-02 eta: 4:51:02 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.4300 loss: 1.8033 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8033 2023/02/17 16:19:36 - mmengine - INFO - Epoch(train) [23][ 820/1320] lr: 2.0000e-02 eta: 4:50:52 time: 0.4791 data_time: 0.0139 memory: 27031 grad_norm: 4.2839 loss: 1.9207 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.9207 2023/02/17 16:19:45 - mmengine - INFO - Epoch(train) [23][ 840/1320] lr: 2.0000e-02 eta: 4:50:42 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.3195 loss: 2.0782 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 2.0782 2023/02/17 16:19:55 - mmengine - INFO - Epoch(train) [23][ 860/1320] lr: 2.0000e-02 eta: 4:50:32 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.2664 loss: 2.0596 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0596 2023/02/17 16:20:05 - mmengine - INFO - Epoch(train) [23][ 880/1320] lr: 2.0000e-02 eta: 4:50:23 time: 0.4790 data_time: 0.0139 memory: 27031 grad_norm: 4.3888 loss: 1.6821 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.6821 2023/02/17 16:20:14 - mmengine - INFO - Epoch(train) [23][ 900/1320] lr: 2.0000e-02 eta: 4:50:13 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.4260 loss: 1.8183 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8183 2023/02/17 16:20:24 - mmengine - INFO - Epoch(train) [23][ 920/1320] lr: 2.0000e-02 eta: 4:50:03 time: 0.4801 data_time: 0.0143 memory: 27031 grad_norm: 4.3400 loss: 1.8794 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8794 2023/02/17 16:20:33 - mmengine - INFO - Epoch(train) [23][ 940/1320] lr: 2.0000e-02 eta: 4:49:53 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.1916 loss: 1.8020 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.8020 2023/02/17 16:20:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:20:43 - mmengine - INFO - Epoch(train) [23][ 960/1320] lr: 2.0000e-02 eta: 4:49:44 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.2412 loss: 1.9117 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9117 2023/02/17 16:20:53 - mmengine - INFO - Epoch(train) [23][ 980/1320] lr: 2.0000e-02 eta: 4:49:34 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.2816 loss: 1.8795 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8795 2023/02/17 16:21:02 - mmengine - INFO - Epoch(train) [23][1000/1320] lr: 2.0000e-02 eta: 4:49:24 time: 0.4789 data_time: 0.0140 memory: 27031 grad_norm: 4.2468 loss: 1.8083 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8083 2023/02/17 16:21:12 - mmengine - INFO - Epoch(train) [23][1020/1320] lr: 2.0000e-02 eta: 4:49:14 time: 0.4796 data_time: 0.0147 memory: 27031 grad_norm: 4.3695 loss: 1.7664 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7664 2023/02/17 16:21:21 - mmengine - INFO - Epoch(train) [23][1040/1320] lr: 2.0000e-02 eta: 4:49:05 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.4476 loss: 1.8463 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8463 2023/02/17 16:21:31 - mmengine - INFO - Epoch(train) [23][1060/1320] lr: 2.0000e-02 eta: 4:48:55 time: 0.4798 data_time: 0.0150 memory: 27031 grad_norm: 4.2222 loss: 1.8547 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8547 2023/02/17 16:21:40 - mmengine - INFO - Epoch(train) [23][1080/1320] lr: 2.0000e-02 eta: 4:48:45 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 4.2478 loss: 1.7943 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7943 2023/02/17 16:21:50 - mmengine - INFO - Epoch(train) [23][1100/1320] lr: 2.0000e-02 eta: 4:48:35 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.3079 loss: 1.7466 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.7466 2023/02/17 16:22:00 - mmengine - INFO - Epoch(train) [23][1120/1320] lr: 2.0000e-02 eta: 4:48:26 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.4096 loss: 1.8917 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8917 2023/02/17 16:22:09 - mmengine - INFO - Epoch(train) [23][1140/1320] lr: 2.0000e-02 eta: 4:48:16 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.3469 loss: 1.7888 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.7888 2023/02/17 16:22:19 - mmengine - INFO - Epoch(train) [23][1160/1320] lr: 2.0000e-02 eta: 4:48:06 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.3921 loss: 1.8746 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8746 2023/02/17 16:22:28 - mmengine - INFO - Epoch(train) [23][1180/1320] lr: 2.0000e-02 eta: 4:47:57 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.3118 loss: 1.8418 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8418 2023/02/17 16:22:38 - mmengine - INFO - Epoch(train) [23][1200/1320] lr: 2.0000e-02 eta: 4:47:47 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 4.2461 loss: 1.6184 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.6184 2023/02/17 16:22:48 - mmengine - INFO - Epoch(train) [23][1220/1320] lr: 2.0000e-02 eta: 4:47:37 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 4.3711 loss: 1.8163 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8163 2023/02/17 16:22:57 - mmengine - INFO - Epoch(train) [23][1240/1320] lr: 2.0000e-02 eta: 4:47:27 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.2996 loss: 1.8193 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8193 2023/02/17 16:23:07 - mmengine - INFO - Epoch(train) [23][1260/1320] lr: 2.0000e-02 eta: 4:47:18 time: 0.4797 data_time: 0.0135 memory: 27031 grad_norm: 4.2847 loss: 1.9332 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.9332 2023/02/17 16:23:17 - mmengine - INFO - Epoch(train) [23][1280/1320] lr: 2.0000e-02 eta: 4:47:08 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.4640 loss: 1.8888 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8888 2023/02/17 16:23:26 - mmengine - INFO - Epoch(train) [23][1300/1320] lr: 2.0000e-02 eta: 4:46:58 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.3778 loss: 1.8000 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8000 2023/02/17 16:23:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:23:36 - mmengine - INFO - Epoch(train) [23][1320/1320] lr: 2.0000e-02 eta: 4:46:48 time: 0.4730 data_time: 0.0151 memory: 27031 grad_norm: 4.3741 loss: 1.7973 top1_acc: 0.8182 top5_acc: 1.0000 loss_cls: 1.7973 2023/02/17 16:23:39 - mmengine - INFO - Epoch(val) [23][ 20/194] eta: 0:00:33 time: 0.1937 data_time: 0.0672 memory: 3265 2023/02/17 16:23:42 - mmengine - INFO - Epoch(val) [23][ 40/194] eta: 0:00:25 time: 0.1387 data_time: 0.0150 memory: 3265 2023/02/17 16:23:45 - mmengine - INFO - Epoch(val) [23][ 60/194] eta: 0:00:21 time: 0.1389 data_time: 0.0138 memory: 3265 2023/02/17 16:23:48 - mmengine - INFO - Epoch(val) [23][ 80/194] eta: 0:00:17 time: 0.1395 data_time: 0.0140 memory: 3265 2023/02/17 16:23:51 - mmengine - INFO - Epoch(val) [23][100/194] eta: 0:00:14 time: 0.1374 data_time: 0.0131 memory: 3265 2023/02/17 16:23:53 - mmengine - INFO - Epoch(val) [23][120/194] eta: 0:00:10 time: 0.1384 data_time: 0.0132 memory: 3265 2023/02/17 16:23:56 - mmengine - INFO - Epoch(val) [23][140/194] eta: 0:00:07 time: 0.1383 data_time: 0.0135 memory: 3265 2023/02/17 16:23:59 - mmengine - INFO - Epoch(val) [23][160/194] eta: 0:00:04 time: 0.1386 data_time: 0.0131 memory: 3265 2023/02/17 16:24:02 - mmengine - INFO - Epoch(val) [23][180/194] eta: 0:00:02 time: 0.1385 data_time: 0.0138 memory: 3265 2023/02/17 16:24:04 - mmengine - INFO - Epoch(val) [23][194/194] acc/top1: 0.4827 acc/top5: 0.7790 acc/mean1: 0.4181 2023/02/17 16:24:15 - mmengine - INFO - Epoch(train) [24][ 20/1320] lr: 2.0000e-02 eta: 4:46:40 time: 0.5357 data_time: 0.0578 memory: 27031 grad_norm: 4.3135 loss: 1.7179 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7179 2023/02/17 16:24:25 - mmengine - INFO - Epoch(train) [24][ 40/1320] lr: 2.0000e-02 eta: 4:46:30 time: 0.4797 data_time: 0.0137 memory: 27031 grad_norm: 4.3711 loss: 1.6847 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.6847 2023/02/17 16:24:34 - mmengine - INFO - Epoch(train) [24][ 60/1320] lr: 2.0000e-02 eta: 4:46:20 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.3416 loss: 1.6654 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6654 2023/02/17 16:24:44 - mmengine - INFO - Epoch(train) [24][ 80/1320] lr: 2.0000e-02 eta: 4:46:11 time: 0.4798 data_time: 0.0149 memory: 27031 grad_norm: 4.2564 loss: 1.8246 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8246 2023/02/17 16:24:53 - mmengine - INFO - Epoch(train) [24][ 100/1320] lr: 2.0000e-02 eta: 4:46:01 time: 0.4794 data_time: 0.0145 memory: 27031 grad_norm: 4.3597 loss: 1.6720 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.6720 2023/02/17 16:25:03 - mmengine - INFO - Epoch(train) [24][ 120/1320] lr: 2.0000e-02 eta: 4:45:51 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.5008 loss: 1.7889 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7889 2023/02/17 16:25:13 - mmengine - INFO - Epoch(train) [24][ 140/1320] lr: 2.0000e-02 eta: 4:45:41 time: 0.4787 data_time: 0.0142 memory: 27031 grad_norm: 4.4821 loss: 1.7262 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.7262 2023/02/17 16:25:22 - mmengine - INFO - Epoch(train) [24][ 160/1320] lr: 2.0000e-02 eta: 4:45:32 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.2320 loss: 1.8060 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8060 2023/02/17 16:25:32 - mmengine - INFO - Epoch(train) [24][ 180/1320] lr: 2.0000e-02 eta: 4:45:22 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 4.3887 loss: 1.7919 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7919 2023/02/17 16:25:41 - mmengine - INFO - Epoch(train) [24][ 200/1320] lr: 2.0000e-02 eta: 4:45:12 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.3186 loss: 1.8073 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.8073 2023/02/17 16:25:51 - mmengine - INFO - Epoch(train) [24][ 220/1320] lr: 2.0000e-02 eta: 4:45:03 time: 0.4812 data_time: 0.0165 memory: 27031 grad_norm: 4.3680 loss: 1.8320 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8320 2023/02/17 16:26:01 - mmengine - INFO - Epoch(train) [24][ 240/1320] lr: 2.0000e-02 eta: 4:44:53 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.2763 loss: 1.8389 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8389 2023/02/17 16:26:10 - mmengine - INFO - Epoch(train) [24][ 260/1320] lr: 2.0000e-02 eta: 4:44:43 time: 0.4784 data_time: 0.0137 memory: 27031 grad_norm: 4.4002 loss: 1.7284 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7284 2023/02/17 16:26:20 - mmengine - INFO - Epoch(train) [24][ 280/1320] lr: 2.0000e-02 eta: 4:44:33 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.3603 loss: 1.7286 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.7286 2023/02/17 16:26:29 - mmengine - INFO - Epoch(train) [24][ 300/1320] lr: 2.0000e-02 eta: 4:44:24 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.2002 loss: 1.7909 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7909 2023/02/17 16:26:39 - mmengine - INFO - Epoch(train) [24][ 320/1320] lr: 2.0000e-02 eta: 4:44:14 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 4.5053 loss: 1.7478 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7478 2023/02/17 16:26:49 - mmengine - INFO - Epoch(train) [24][ 340/1320] lr: 2.0000e-02 eta: 4:44:04 time: 0.4810 data_time: 0.0159 memory: 27031 grad_norm: 4.2689 loss: 1.8481 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8481 2023/02/17 16:26:58 - mmengine - INFO - Epoch(train) [24][ 360/1320] lr: 2.0000e-02 eta: 4:43:54 time: 0.4788 data_time: 0.0133 memory: 27031 grad_norm: 4.3560 loss: 1.7819 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.7819 2023/02/17 16:27:08 - mmengine - INFO - Epoch(train) [24][ 380/1320] lr: 2.0000e-02 eta: 4:43:45 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.2696 loss: 1.9919 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.9919 2023/02/17 16:27:17 - mmengine - INFO - Epoch(train) [24][ 400/1320] lr: 2.0000e-02 eta: 4:43:35 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.3620 loss: 1.4879 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4879 2023/02/17 16:27:27 - mmengine - INFO - Epoch(train) [24][ 420/1320] lr: 2.0000e-02 eta: 4:43:25 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.3281 loss: 1.8423 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8423 2023/02/17 16:27:37 - mmengine - INFO - Epoch(train) [24][ 440/1320] lr: 2.0000e-02 eta: 4:43:16 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 4.2287 loss: 1.7322 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7322 2023/02/17 16:27:46 - mmengine - INFO - Epoch(train) [24][ 460/1320] lr: 2.0000e-02 eta: 4:43:06 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.4643 loss: 1.7050 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.7050 2023/02/17 16:27:56 - mmengine - INFO - Epoch(train) [24][ 480/1320] lr: 2.0000e-02 eta: 4:42:56 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.4311 loss: 1.8379 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8379 2023/02/17 16:28:05 - mmengine - INFO - Epoch(train) [24][ 500/1320] lr: 2.0000e-02 eta: 4:42:46 time: 0.4809 data_time: 0.0146 memory: 27031 grad_norm: 4.3343 loss: 1.6621 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.6621 2023/02/17 16:28:15 - mmengine - INFO - Epoch(train) [24][ 520/1320] lr: 2.0000e-02 eta: 4:42:37 time: 0.4788 data_time: 0.0138 memory: 27031 grad_norm: 4.3536 loss: 1.5914 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5914 2023/02/17 16:28:25 - mmengine - INFO - Epoch(train) [24][ 540/1320] lr: 2.0000e-02 eta: 4:42:27 time: 0.4805 data_time: 0.0148 memory: 27031 grad_norm: 4.3994 loss: 1.8466 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8466 2023/02/17 16:28:34 - mmengine - INFO - Epoch(train) [24][ 560/1320] lr: 2.0000e-02 eta: 4:42:17 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.2736 loss: 1.8065 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8065 2023/02/17 16:28:44 - mmengine - INFO - Epoch(train) [24][ 580/1320] lr: 2.0000e-02 eta: 4:42:07 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.3026 loss: 1.9534 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9534 2023/02/17 16:28:53 - mmengine - INFO - Epoch(train) [24][ 600/1320] lr: 2.0000e-02 eta: 4:41:58 time: 0.4805 data_time: 0.0159 memory: 27031 grad_norm: 4.3819 loss: 1.7944 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7944 2023/02/17 16:29:03 - mmengine - INFO - Epoch(train) [24][ 620/1320] lr: 2.0000e-02 eta: 4:41:48 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.3541 loss: 1.8537 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8537 2023/02/17 16:29:13 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:29:13 - mmengine - INFO - Epoch(train) [24][ 640/1320] lr: 2.0000e-02 eta: 4:41:38 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.2610 loss: 1.8370 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.8370 2023/02/17 16:29:22 - mmengine - INFO - Epoch(train) [24][ 660/1320] lr: 2.0000e-02 eta: 4:41:29 time: 0.4802 data_time: 0.0149 memory: 27031 grad_norm: 4.3774 loss: 1.7050 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.7050 2023/02/17 16:29:32 - mmengine - INFO - Epoch(train) [24][ 680/1320] lr: 2.0000e-02 eta: 4:41:19 time: 0.4791 data_time: 0.0144 memory: 27031 grad_norm: 4.4183 loss: 1.9108 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9108 2023/02/17 16:29:41 - mmengine - INFO - Epoch(train) [24][ 700/1320] lr: 2.0000e-02 eta: 4:41:09 time: 0.4799 data_time: 0.0150 memory: 27031 grad_norm: 4.3217 loss: 1.6790 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.6790 2023/02/17 16:29:51 - mmengine - INFO - Epoch(train) [24][ 720/1320] lr: 2.0000e-02 eta: 4:40:59 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.4294 loss: 1.7257 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.7257 2023/02/17 16:30:01 - mmengine - INFO - Epoch(train) [24][ 740/1320] lr: 2.0000e-02 eta: 4:40:50 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3323 loss: 1.7824 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7824 2023/02/17 16:30:10 - mmengine - INFO - Epoch(train) [24][ 760/1320] lr: 2.0000e-02 eta: 4:40:40 time: 0.4809 data_time: 0.0152 memory: 27031 grad_norm: 4.4684 loss: 1.8110 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8110 2023/02/17 16:30:20 - mmengine - INFO - Epoch(train) [24][ 780/1320] lr: 2.0000e-02 eta: 4:40:30 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.3720 loss: 1.9528 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 1.9528 2023/02/17 16:30:29 - mmengine - INFO - Epoch(train) [24][ 800/1320] lr: 2.0000e-02 eta: 4:40:21 time: 0.4793 data_time: 0.0145 memory: 27031 grad_norm: 4.3571 loss: 1.8923 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.8923 2023/02/17 16:30:39 - mmengine - INFO - Epoch(train) [24][ 820/1320] lr: 2.0000e-02 eta: 4:40:11 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 4.3829 loss: 1.9965 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9965 2023/02/17 16:30:49 - mmengine - INFO - Epoch(train) [24][ 840/1320] lr: 2.0000e-02 eta: 4:40:01 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.2438 loss: 1.8533 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8533 2023/02/17 16:30:58 - mmengine - INFO - Epoch(train) [24][ 860/1320] lr: 2.0000e-02 eta: 4:39:51 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 4.3530 loss: 1.9105 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9105 2023/02/17 16:31:08 - mmengine - INFO - Epoch(train) [24][ 880/1320] lr: 2.0000e-02 eta: 4:39:42 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.4451 loss: 1.8461 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.8461 2023/02/17 16:31:17 - mmengine - INFO - Epoch(train) [24][ 900/1320] lr: 2.0000e-02 eta: 4:39:32 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.4098 loss: 1.9945 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9945 2023/02/17 16:31:27 - mmengine - INFO - Epoch(train) [24][ 920/1320] lr: 2.0000e-02 eta: 4:39:22 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.3045 loss: 1.9244 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9244 2023/02/17 16:31:37 - mmengine - INFO - Epoch(train) [24][ 940/1320] lr: 2.0000e-02 eta: 4:39:12 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 4.3784 loss: 1.9711 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9711 2023/02/17 16:31:46 - mmengine - INFO - Epoch(train) [24][ 960/1320] lr: 2.0000e-02 eta: 4:39:03 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3105 loss: 1.9707 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.9707 2023/02/17 16:31:56 - mmengine - INFO - Epoch(train) [24][ 980/1320] lr: 2.0000e-02 eta: 4:38:53 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.1865 loss: 1.8087 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8087 2023/02/17 16:32:05 - mmengine - INFO - Epoch(train) [24][1000/1320] lr: 2.0000e-02 eta: 4:38:43 time: 0.4789 data_time: 0.0141 memory: 27031 grad_norm: 4.2548 loss: 1.6469 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6469 2023/02/17 16:32:15 - mmengine - INFO - Epoch(train) [24][1020/1320] lr: 2.0000e-02 eta: 4:38:34 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 4.4468 loss: 1.8048 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.8048 2023/02/17 16:32:25 - mmengine - INFO - Epoch(train) [24][1040/1320] lr: 2.0000e-02 eta: 4:38:24 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 4.2280 loss: 1.8088 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8088 2023/02/17 16:32:34 - mmengine - INFO - Epoch(train) [24][1060/1320] lr: 2.0000e-02 eta: 4:38:14 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 4.3645 loss: 1.9568 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9568 2023/02/17 16:32:44 - mmengine - INFO - Epoch(train) [24][1080/1320] lr: 2.0000e-02 eta: 4:38:04 time: 0.4810 data_time: 0.0157 memory: 27031 grad_norm: 4.3393 loss: 1.7145 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.7145 2023/02/17 16:32:53 - mmengine - INFO - Epoch(train) [24][1100/1320] lr: 2.0000e-02 eta: 4:37:55 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.4059 loss: 1.6980 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.6980 2023/02/17 16:33:03 - mmengine - INFO - Epoch(train) [24][1120/1320] lr: 2.0000e-02 eta: 4:37:45 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.2442 loss: 1.8274 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8274 2023/02/17 16:33:13 - mmengine - INFO - Epoch(train) [24][1140/1320] lr: 2.0000e-02 eta: 4:37:35 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.3124 loss: 1.6896 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.6896 2023/02/17 16:33:22 - mmengine - INFO - Epoch(train) [24][1160/1320] lr: 2.0000e-02 eta: 4:37:26 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 4.2682 loss: 1.8621 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.8621 2023/02/17 16:33:32 - mmengine - INFO - Epoch(train) [24][1180/1320] lr: 2.0000e-02 eta: 4:37:16 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 4.2347 loss: 2.0420 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0420 2023/02/17 16:33:41 - mmengine - INFO - Epoch(train) [24][1200/1320] lr: 2.0000e-02 eta: 4:37:06 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.3364 loss: 1.8029 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8029 2023/02/17 16:33:51 - mmengine - INFO - Epoch(train) [24][1220/1320] lr: 2.0000e-02 eta: 4:36:56 time: 0.4795 data_time: 0.0136 memory: 27031 grad_norm: 4.1747 loss: 1.8387 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8387 2023/02/17 16:34:01 - mmengine - INFO - Epoch(train) [24][1240/1320] lr: 2.0000e-02 eta: 4:36:47 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.3419 loss: 1.6988 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6988 2023/02/17 16:34:10 - mmengine - INFO - Epoch(train) [24][1260/1320] lr: 2.0000e-02 eta: 4:36:37 time: 0.4796 data_time: 0.0136 memory: 27031 grad_norm: 4.3287 loss: 1.8852 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.8852 2023/02/17 16:34:20 - mmengine - INFO - Epoch(train) [24][1280/1320] lr: 2.0000e-02 eta: 4:36:27 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 4.3205 loss: 1.8652 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.8652 2023/02/17 16:34:29 - mmengine - INFO - Epoch(train) [24][1300/1320] lr: 2.0000e-02 eta: 4:36:18 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 4.2771 loss: 1.7863 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7863 2023/02/17 16:34:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:34:39 - mmengine - INFO - Epoch(train) [24][1320/1320] lr: 2.0000e-02 eta: 4:36:08 time: 0.4746 data_time: 0.0151 memory: 27031 grad_norm: 4.4412 loss: 1.8729 top1_acc: 0.3636 top5_acc: 0.7273 loss_cls: 1.8729 2023/02/17 16:34:39 - mmengine - INFO - Saving checkpoint at 24 epochs 2023/02/17 16:34:44 - mmengine - INFO - Epoch(val) [24][ 20/194] eta: 0:00:32 time: 0.1877 data_time: 0.0612 memory: 3265 2023/02/17 16:34:47 - mmengine - INFO - Epoch(val) [24][ 40/194] eta: 0:00:25 time: 0.1389 data_time: 0.0137 memory: 3265 2023/02/17 16:34:49 - mmengine - INFO - Epoch(val) [24][ 60/194] eta: 0:00:20 time: 0.1378 data_time: 0.0133 memory: 3265 2023/02/17 16:34:52 - mmengine - INFO - Epoch(val) [24][ 80/194] eta: 0:00:17 time: 0.1405 data_time: 0.0142 memory: 3265 2023/02/17 16:34:55 - mmengine - INFO - Epoch(val) [24][100/194] eta: 0:00:13 time: 0.1374 data_time: 0.0132 memory: 3265 2023/02/17 16:34:58 - mmengine - INFO - Epoch(val) [24][120/194] eta: 0:00:10 time: 0.1397 data_time: 0.0148 memory: 3265 2023/02/17 16:35:01 - mmengine - INFO - Epoch(val) [24][140/194] eta: 0:00:07 time: 0.1386 data_time: 0.0140 memory: 3265 2023/02/17 16:35:03 - mmengine - INFO - Epoch(val) [24][160/194] eta: 0:00:04 time: 0.1399 data_time: 0.0151 memory: 3265 2023/02/17 16:35:06 - mmengine - INFO - Epoch(val) [24][180/194] eta: 0:00:02 time: 0.1346 data_time: 0.0119 memory: 3265 2023/02/17 16:35:09 - mmengine - INFO - Epoch(val) [24][194/194] acc/top1: 0.4967 acc/top5: 0.7850 acc/mean1: 0.4246 2023/02/17 16:35:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_21.pth is removed 2023/02/17 16:35:10 - mmengine - INFO - The best checkpoint with 0.4967 acc/top1 at 24 epoch is saved to best_acc/top1_epoch_24.pth. 2023/02/17 16:35:20 - mmengine - INFO - Epoch(train) [25][ 20/1320] lr: 2.0000e-02 eta: 4:35:59 time: 0.5319 data_time: 0.0593 memory: 27031 grad_norm: 4.2371 loss: 1.7861 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.7861 2023/02/17 16:35:30 - mmengine - INFO - Epoch(train) [25][ 40/1320] lr: 2.0000e-02 eta: 4:35:49 time: 0.4792 data_time: 0.0146 memory: 27031 grad_norm: 4.3631 loss: 1.5036 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.5036 2023/02/17 16:35:39 - mmengine - INFO - Epoch(train) [25][ 60/1320] lr: 2.0000e-02 eta: 4:35:40 time: 0.4791 data_time: 0.0142 memory: 27031 grad_norm: 4.2240 loss: 1.9007 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.9007 2023/02/17 16:35:49 - mmengine - INFO - Epoch(train) [25][ 80/1320] lr: 2.0000e-02 eta: 4:35:30 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.3157 loss: 1.8167 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8167 2023/02/17 16:35:58 - mmengine - INFO - Epoch(train) [25][ 100/1320] lr: 2.0000e-02 eta: 4:35:20 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.3616 loss: 1.6905 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.6905 2023/02/17 16:36:08 - mmengine - INFO - Epoch(train) [25][ 120/1320] lr: 2.0000e-02 eta: 4:35:10 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.3278 loss: 1.8250 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8250 2023/02/17 16:36:18 - mmengine - INFO - Epoch(train) [25][ 140/1320] lr: 2.0000e-02 eta: 4:35:01 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 4.3898 loss: 1.7503 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.7503 2023/02/17 16:36:27 - mmengine - INFO - Epoch(train) [25][ 160/1320] lr: 2.0000e-02 eta: 4:34:51 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 4.4624 loss: 1.6692 top1_acc: 0.5625 top5_acc: 0.5625 loss_cls: 1.6692 2023/02/17 16:36:37 - mmengine - INFO - Epoch(train) [25][ 180/1320] lr: 2.0000e-02 eta: 4:34:41 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.4193 loss: 1.7080 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.7080 2023/02/17 16:36:46 - mmengine - INFO - Epoch(train) [25][ 200/1320] lr: 2.0000e-02 eta: 4:34:32 time: 0.4799 data_time: 0.0149 memory: 27031 grad_norm: 4.3372 loss: 1.8019 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8019 2023/02/17 16:36:56 - mmengine - INFO - Epoch(train) [25][ 220/1320] lr: 2.0000e-02 eta: 4:34:22 time: 0.4797 data_time: 0.0152 memory: 27031 grad_norm: 4.3306 loss: 1.5719 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.5719 2023/02/17 16:37:06 - mmengine - INFO - Epoch(train) [25][ 240/1320] lr: 2.0000e-02 eta: 4:34:12 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.3887 loss: 1.7327 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.7327 2023/02/17 16:37:15 - mmengine - INFO - Epoch(train) [25][ 260/1320] lr: 2.0000e-02 eta: 4:34:02 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.3628 loss: 1.9663 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9663 2023/02/17 16:37:25 - mmengine - INFO - Epoch(train) [25][ 280/1320] lr: 2.0000e-02 eta: 4:33:53 time: 0.4788 data_time: 0.0142 memory: 27031 grad_norm: 4.3221 loss: 2.0524 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0524 2023/02/17 16:37:34 - mmengine - INFO - Epoch(train) [25][ 300/1320] lr: 2.0000e-02 eta: 4:33:43 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.2615 loss: 1.8431 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8431 2023/02/17 16:37:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:37:44 - mmengine - INFO - Epoch(train) [25][ 320/1320] lr: 2.0000e-02 eta: 4:33:33 time: 0.4794 data_time: 0.0137 memory: 27031 grad_norm: 4.3164 loss: 1.8118 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.8118 2023/02/17 16:37:54 - mmengine - INFO - Epoch(train) [25][ 340/1320] lr: 2.0000e-02 eta: 4:33:24 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 4.3275 loss: 1.9069 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.9069 2023/02/17 16:38:03 - mmengine - INFO - Epoch(train) [25][ 360/1320] lr: 2.0000e-02 eta: 4:33:14 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 4.3355 loss: 1.6965 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.6965 2023/02/17 16:38:13 - mmengine - INFO - Epoch(train) [25][ 380/1320] lr: 2.0000e-02 eta: 4:33:04 time: 0.4790 data_time: 0.0142 memory: 27031 grad_norm: 4.4750 loss: 1.9137 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.9137 2023/02/17 16:38:23 - mmengine - INFO - Epoch(train) [25][ 400/1320] lr: 2.0000e-02 eta: 4:32:55 time: 0.4902 data_time: 0.0251 memory: 27031 grad_norm: 4.2988 loss: 1.6235 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.6235 2023/02/17 16:38:32 - mmengine - INFO - Epoch(train) [25][ 420/1320] lr: 2.0000e-02 eta: 4:32:45 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.4592 loss: 1.7775 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.7775 2023/02/17 16:38:42 - mmengine - INFO - Epoch(train) [25][ 440/1320] lr: 2.0000e-02 eta: 4:32:35 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.4557 loss: 1.8216 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.8216 2023/02/17 16:38:51 - mmengine - INFO - Epoch(train) [25][ 460/1320] lr: 2.0000e-02 eta: 4:32:25 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.3087 loss: 1.9090 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9090 2023/02/17 16:39:01 - mmengine - INFO - Epoch(train) [25][ 480/1320] lr: 2.0000e-02 eta: 4:32:16 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 4.2944 loss: 1.6869 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.6869 2023/02/17 16:39:11 - mmengine - INFO - Epoch(train) [25][ 500/1320] lr: 2.0000e-02 eta: 4:32:06 time: 0.4804 data_time: 0.0151 memory: 27031 grad_norm: 4.4100 loss: 1.8276 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.8276 2023/02/17 16:39:20 - mmengine - INFO - Epoch(train) [25][ 520/1320] lr: 2.0000e-02 eta: 4:31:56 time: 0.4804 data_time: 0.0153 memory: 27031 grad_norm: 4.2950 loss: 1.7496 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.7496 2023/02/17 16:39:30 - mmengine - INFO - Epoch(train) [25][ 540/1320] lr: 2.0000e-02 eta: 4:31:47 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 4.4985 loss: 1.8221 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.8221 2023/02/17 16:39:39 - mmengine - INFO - Epoch(train) [25][ 560/1320] lr: 2.0000e-02 eta: 4:31:37 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.4482 loss: 1.9433 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9433 2023/02/17 16:39:49 - mmengine - INFO - Epoch(train) [25][ 580/1320] lr: 2.0000e-02 eta: 4:31:27 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.4341 loss: 1.6403 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6403 2023/02/17 16:39:59 - mmengine - INFO - Epoch(train) [25][ 600/1320] lr: 2.0000e-02 eta: 4:31:17 time: 0.4796 data_time: 0.0147 memory: 27031 grad_norm: 4.4974 loss: 1.9111 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9111 2023/02/17 16:40:08 - mmengine - INFO - Epoch(train) [25][ 620/1320] lr: 2.0000e-02 eta: 4:31:08 time: 0.4804 data_time: 0.0151 memory: 27031 grad_norm: 4.4415 loss: 1.7870 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7870 2023/02/17 16:40:18 - mmengine - INFO - Epoch(train) [25][ 640/1320] lr: 2.0000e-02 eta: 4:30:58 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.3030 loss: 1.8642 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.8642 2023/02/17 16:40:27 - mmengine - INFO - Epoch(train) [25][ 660/1320] lr: 2.0000e-02 eta: 4:30:48 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 4.3636 loss: 1.7463 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.7463 2023/02/17 16:40:37 - mmengine - INFO - Epoch(train) [25][ 680/1320] lr: 2.0000e-02 eta: 4:30:39 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 4.4115 loss: 1.7679 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7679 2023/02/17 16:40:47 - mmengine - INFO - Epoch(train) [25][ 700/1320] lr: 2.0000e-02 eta: 4:30:29 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.4011 loss: 1.8181 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8181 2023/02/17 16:40:56 - mmengine - INFO - Epoch(train) [25][ 720/1320] lr: 2.0000e-02 eta: 4:30:19 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 4.2883 loss: 1.8421 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8421 2023/02/17 16:41:06 - mmengine - INFO - Epoch(train) [25][ 740/1320] lr: 2.0000e-02 eta: 4:30:09 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 4.4153 loss: 1.9160 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.9160 2023/02/17 16:41:15 - mmengine - INFO - Epoch(train) [25][ 760/1320] lr: 2.0000e-02 eta: 4:30:00 time: 0.4795 data_time: 0.0137 memory: 27031 grad_norm: 4.2724 loss: 1.7198 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7198 2023/02/17 16:41:25 - mmengine - INFO - Epoch(train) [25][ 780/1320] lr: 2.0000e-02 eta: 4:29:50 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.3453 loss: 1.8684 top1_acc: 0.3125 top5_acc: 0.4375 loss_cls: 1.8684 2023/02/17 16:41:35 - mmengine - INFO - Epoch(train) [25][ 800/1320] lr: 2.0000e-02 eta: 4:29:40 time: 0.4788 data_time: 0.0135 memory: 27031 grad_norm: 4.2782 loss: 1.7816 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 1.7816 2023/02/17 16:41:44 - mmengine - INFO - Epoch(train) [25][ 820/1320] lr: 2.0000e-02 eta: 4:29:31 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.1783 loss: 1.6432 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.6432 2023/02/17 16:41:54 - mmengine - INFO - Epoch(train) [25][ 840/1320] lr: 2.0000e-02 eta: 4:29:21 time: 0.4825 data_time: 0.0169 memory: 27031 grad_norm: 4.3507 loss: 1.7256 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7256 2023/02/17 16:42:03 - mmengine - INFO - Epoch(train) [25][ 860/1320] lr: 2.0000e-02 eta: 4:29:11 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.3195 loss: 1.8282 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.8282 2023/02/17 16:42:13 - mmengine - INFO - Epoch(train) [25][ 880/1320] lr: 2.0000e-02 eta: 4:29:02 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.4497 loss: 1.8868 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.8868 2023/02/17 16:42:23 - mmengine - INFO - Epoch(train) [25][ 900/1320] lr: 2.0000e-02 eta: 4:28:52 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.2542 loss: 1.7032 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7032 2023/02/17 16:42:32 - mmengine - INFO - Epoch(train) [25][ 920/1320] lr: 2.0000e-02 eta: 4:28:42 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 4.4635 loss: 1.6763 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.6763 2023/02/17 16:42:42 - mmengine - INFO - Epoch(train) [25][ 940/1320] lr: 2.0000e-02 eta: 4:28:32 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.3708 loss: 1.8428 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8428 2023/02/17 16:42:52 - mmengine - INFO - Epoch(train) [25][ 960/1320] lr: 2.0000e-02 eta: 4:28:23 time: 0.4794 data_time: 0.0137 memory: 27031 grad_norm: 4.4755 loss: 1.9548 top1_acc: 0.2500 top5_acc: 0.8750 loss_cls: 1.9548 2023/02/17 16:43:01 - mmengine - INFO - Epoch(train) [25][ 980/1320] lr: 2.0000e-02 eta: 4:28:13 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.1642 loss: 1.8593 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.8593 2023/02/17 16:43:11 - mmengine - INFO - Epoch(train) [25][1000/1320] lr: 2.0000e-02 eta: 4:28:03 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2330 loss: 1.7806 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.7806 2023/02/17 16:43:20 - mmengine - INFO - Epoch(train) [25][1020/1320] lr: 2.0000e-02 eta: 4:27:54 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.3471 loss: 2.0803 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.0803 2023/02/17 16:43:30 - mmengine - INFO - Epoch(train) [25][1040/1320] lr: 2.0000e-02 eta: 4:27:44 time: 0.4828 data_time: 0.0175 memory: 27031 grad_norm: 4.4048 loss: 2.0086 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.0086 2023/02/17 16:43:40 - mmengine - INFO - Epoch(train) [25][1060/1320] lr: 2.0000e-02 eta: 4:27:34 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 4.3459 loss: 1.6359 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.6359 2023/02/17 16:43:49 - mmengine - INFO - Epoch(train) [25][1080/1320] lr: 2.0000e-02 eta: 4:27:24 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 4.3271 loss: 1.7509 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.7509 2023/02/17 16:43:59 - mmengine - INFO - Epoch(train) [25][1100/1320] lr: 2.0000e-02 eta: 4:27:15 time: 0.4803 data_time: 0.0152 memory: 27031 grad_norm: 4.3768 loss: 1.8212 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 1.8212 2023/02/17 16:44:08 - mmengine - INFO - Epoch(train) [25][1120/1320] lr: 2.0000e-02 eta: 4:27:05 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.2923 loss: 1.8360 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.8360 2023/02/17 16:44:18 - mmengine - INFO - Epoch(train) [25][1140/1320] lr: 2.0000e-02 eta: 4:26:55 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 4.4248 loss: 1.7377 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.7377 2023/02/17 16:44:28 - mmengine - INFO - Epoch(train) [25][1160/1320] lr: 2.0000e-02 eta: 4:26:46 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.3796 loss: 1.9126 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.9126 2023/02/17 16:44:37 - mmengine - INFO - Epoch(train) [25][1180/1320] lr: 2.0000e-02 eta: 4:26:36 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.3857 loss: 1.9538 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.9538 2023/02/17 16:44:47 - mmengine - INFO - Epoch(train) [25][1200/1320] lr: 2.0000e-02 eta: 4:26:26 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.3733 loss: 1.7669 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.7669 2023/02/17 16:44:56 - mmengine - INFO - Epoch(train) [25][1220/1320] lr: 2.0000e-02 eta: 4:26:17 time: 0.4802 data_time: 0.0149 memory: 27031 grad_norm: 4.4058 loss: 1.8752 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8752 2023/02/17 16:45:06 - mmengine - INFO - Epoch(train) [25][1240/1320] lr: 2.0000e-02 eta: 4:26:07 time: 0.4799 data_time: 0.0139 memory: 27031 grad_norm: 4.4220 loss: 1.8622 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.8622 2023/02/17 16:45:16 - mmengine - INFO - Epoch(train) [25][1260/1320] lr: 2.0000e-02 eta: 4:25:57 time: 0.4800 data_time: 0.0150 memory: 27031 grad_norm: 4.2211 loss: 1.8757 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8757 2023/02/17 16:45:25 - mmengine - INFO - Epoch(train) [25][1280/1320] lr: 2.0000e-02 eta: 4:25:47 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.2821 loss: 1.6981 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.6981 2023/02/17 16:45:35 - mmengine - INFO - Epoch(train) [25][1300/1320] lr: 2.0000e-02 eta: 4:25:38 time: 0.4821 data_time: 0.0168 memory: 27031 grad_norm: 4.3432 loss: 1.7417 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.7417 2023/02/17 16:45:44 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:45:44 - mmengine - INFO - Epoch(train) [25][1320/1320] lr: 2.0000e-02 eta: 4:25:28 time: 0.4736 data_time: 0.0156 memory: 27031 grad_norm: 4.3777 loss: 1.9093 top1_acc: 0.8182 top5_acc: 0.9091 loss_cls: 1.9093 2023/02/17 16:45:48 - mmengine - INFO - Epoch(val) [25][ 20/194] eta: 0:00:32 time: 0.1888 data_time: 0.0615 memory: 3265 2023/02/17 16:45:51 - mmengine - INFO - Epoch(val) [25][ 40/194] eta: 0:00:25 time: 0.1374 data_time: 0.0126 memory: 3265 2023/02/17 16:45:54 - mmengine - INFO - Epoch(val) [25][ 60/194] eta: 0:00:20 time: 0.1369 data_time: 0.0128 memory: 3265 2023/02/17 16:45:56 - mmengine - INFO - Epoch(val) [25][ 80/194] eta: 0:00:17 time: 0.1386 data_time: 0.0140 memory: 3265 2023/02/17 16:45:59 - mmengine - INFO - Epoch(val) [25][100/194] eta: 0:00:13 time: 0.1388 data_time: 0.0136 memory: 3265 2023/02/17 16:46:02 - mmengine - INFO - Epoch(val) [25][120/194] eta: 0:00:10 time: 0.1391 data_time: 0.0143 memory: 3265 2023/02/17 16:46:05 - mmengine - INFO - Epoch(val) [25][140/194] eta: 0:00:07 time: 0.1391 data_time: 0.0139 memory: 3265 2023/02/17 16:46:07 - mmengine - INFO - Epoch(val) [25][160/194] eta: 0:00:04 time: 0.1372 data_time: 0.0132 memory: 3265 2023/02/17 16:46:10 - mmengine - INFO - Epoch(val) [25][180/194] eta: 0:00:02 time: 0.1373 data_time: 0.0131 memory: 3265 2023/02/17 16:46:13 - mmengine - INFO - Epoch(val) [25][194/194] acc/top1: 0.4848 acc/top5: 0.7782 acc/mean1: 0.4142 2023/02/17 16:46:24 - mmengine - INFO - Epoch(train) [26][ 20/1320] lr: 2.0000e-03 eta: 4:25:19 time: 0.5375 data_time: 0.0626 memory: 27031 grad_norm: 4.1188 loss: 1.7180 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.7180 2023/02/17 16:46:33 - mmengine - INFO - Epoch(train) [26][ 40/1320] lr: 2.0000e-03 eta: 4:25:10 time: 0.4803 data_time: 0.0141 memory: 27031 grad_norm: 3.9292 loss: 1.6331 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.6331 2023/02/17 16:46:43 - mmengine - INFO - Epoch(train) [26][ 60/1320] lr: 2.0000e-03 eta: 4:25:00 time: 0.4781 data_time: 0.0130 memory: 27031 grad_norm: 3.8218 loss: 1.5358 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.5358 2023/02/17 16:46:52 - mmengine - INFO - Epoch(train) [26][ 80/1320] lr: 2.0000e-03 eta: 4:24:50 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 3.9199 loss: 1.5113 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5113 2023/02/17 16:47:02 - mmengine - INFO - Epoch(train) [26][ 100/1320] lr: 2.0000e-03 eta: 4:24:40 time: 0.4787 data_time: 0.0135 memory: 27031 grad_norm: 3.9453 loss: 1.4221 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4221 2023/02/17 16:47:12 - mmengine - INFO - Epoch(train) [26][ 120/1320] lr: 2.0000e-03 eta: 4:24:31 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 3.8539 loss: 1.5844 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5844 2023/02/17 16:47:21 - mmengine - INFO - Epoch(train) [26][ 140/1320] lr: 2.0000e-03 eta: 4:24:21 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 3.8179 loss: 1.3080 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3080 2023/02/17 16:47:31 - mmengine - INFO - Epoch(train) [26][ 160/1320] lr: 2.0000e-03 eta: 4:24:11 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 3.9061 loss: 1.5212 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5212 2023/02/17 16:47:40 - mmengine - INFO - Epoch(train) [26][ 180/1320] lr: 2.0000e-03 eta: 4:24:02 time: 0.4787 data_time: 0.0140 memory: 27031 grad_norm: 3.9117 loss: 1.3916 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.3916 2023/02/17 16:47:50 - mmengine - INFO - Epoch(train) [26][ 200/1320] lr: 2.0000e-03 eta: 4:23:52 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 3.9100 loss: 1.4765 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4765 2023/02/17 16:48:00 - mmengine - INFO - Epoch(train) [26][ 220/1320] lr: 2.0000e-03 eta: 4:23:42 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 4.0123 loss: 1.5149 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5149 2023/02/17 16:48:09 - mmengine - INFO - Epoch(train) [26][ 240/1320] lr: 2.0000e-03 eta: 4:23:32 time: 0.4786 data_time: 0.0139 memory: 27031 grad_norm: 3.8857 loss: 1.5130 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.5130 2023/02/17 16:48:19 - mmengine - INFO - Epoch(train) [26][ 260/1320] lr: 2.0000e-03 eta: 4:23:23 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 3.8473 loss: 1.2984 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.2984 2023/02/17 16:48:28 - mmengine - INFO - Epoch(train) [26][ 280/1320] lr: 2.0000e-03 eta: 4:23:13 time: 0.4807 data_time: 0.0150 memory: 27031 grad_norm: 3.9056 loss: 1.4611 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4611 2023/02/17 16:48:38 - mmengine - INFO - Epoch(train) [26][ 300/1320] lr: 2.0000e-03 eta: 4:23:03 time: 0.4800 data_time: 0.0153 memory: 27031 grad_norm: 4.0223 loss: 1.4564 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4564 2023/02/17 16:48:48 - mmengine - INFO - Epoch(train) [26][ 320/1320] lr: 2.0000e-03 eta: 4:22:54 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 3.8876 loss: 1.4600 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.4600 2023/02/17 16:48:57 - mmengine - INFO - Epoch(train) [26][ 340/1320] lr: 2.0000e-03 eta: 4:22:44 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 3.8643 loss: 1.4444 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4444 2023/02/17 16:49:07 - mmengine - INFO - Epoch(train) [26][ 360/1320] lr: 2.0000e-03 eta: 4:22:34 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.0468 loss: 1.3340 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.3340 2023/02/17 16:49:16 - mmengine - INFO - Epoch(train) [26][ 380/1320] lr: 2.0000e-03 eta: 4:22:24 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 4.0150 loss: 1.4840 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4840 2023/02/17 16:49:26 - mmengine - INFO - Epoch(train) [26][ 400/1320] lr: 2.0000e-03 eta: 4:22:15 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 3.9135 loss: 1.3871 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.3871 2023/02/17 16:49:36 - mmengine - INFO - Epoch(train) [26][ 420/1320] lr: 2.0000e-03 eta: 4:22:05 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 3.9172 loss: 1.4895 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4895 2023/02/17 16:49:45 - mmengine - INFO - Epoch(train) [26][ 440/1320] lr: 2.0000e-03 eta: 4:21:55 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 3.9716 loss: 1.2447 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.2447 2023/02/17 16:49:55 - mmengine - INFO - Epoch(train) [26][ 460/1320] lr: 2.0000e-03 eta: 4:21:46 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 4.0307 loss: 1.5817 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.5817 2023/02/17 16:50:04 - mmengine - INFO - Epoch(train) [26][ 480/1320] lr: 2.0000e-03 eta: 4:21:36 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.0669 loss: 1.4171 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4171 2023/02/17 16:50:14 - mmengine - INFO - Epoch(train) [26][ 500/1320] lr: 2.0000e-03 eta: 4:21:26 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 3.9622 loss: 1.4138 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4138 2023/02/17 16:50:24 - mmengine - INFO - Epoch(train) [26][ 520/1320] lr: 2.0000e-03 eta: 4:21:17 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 3.8675 loss: 1.3781 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3781 2023/02/17 16:50:33 - mmengine - INFO - Epoch(train) [26][ 540/1320] lr: 2.0000e-03 eta: 4:21:07 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 3.9786 loss: 1.3666 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3666 2023/02/17 16:50:43 - mmengine - INFO - Epoch(train) [26][ 560/1320] lr: 2.0000e-03 eta: 4:20:57 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.0495 loss: 1.3784 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3784 2023/02/17 16:50:52 - mmengine - INFO - Epoch(train) [26][ 580/1320] lr: 2.0000e-03 eta: 4:20:47 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.0000 loss: 1.2839 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2839 2023/02/17 16:51:02 - mmengine - INFO - Epoch(train) [26][ 600/1320] lr: 2.0000e-03 eta: 4:20:38 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.1398 loss: 1.4320 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.4320 2023/02/17 16:51:12 - mmengine - INFO - Epoch(train) [26][ 620/1320] lr: 2.0000e-03 eta: 4:20:28 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.0487 loss: 1.4085 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.4085 2023/02/17 16:51:21 - mmengine - INFO - Epoch(train) [26][ 640/1320] lr: 2.0000e-03 eta: 4:20:18 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 3.9270 loss: 1.4453 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4453 2023/02/17 16:51:31 - mmengine - INFO - Epoch(train) [26][ 660/1320] lr: 2.0000e-03 eta: 4:20:09 time: 0.4790 data_time: 0.0141 memory: 27031 grad_norm: 4.1967 loss: 1.4749 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4749 2023/02/17 16:51:40 - mmengine - INFO - Epoch(train) [26][ 680/1320] lr: 2.0000e-03 eta: 4:19:59 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 3.9934 loss: 1.3882 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3882 2023/02/17 16:51:50 - mmengine - INFO - Epoch(train) [26][ 700/1320] lr: 2.0000e-03 eta: 4:19:49 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1298 loss: 1.4109 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.4109 2023/02/17 16:52:00 - mmengine - INFO - Epoch(train) [26][ 720/1320] lr: 2.0000e-03 eta: 4:19:39 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 3.9496 loss: 1.1620 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1620 2023/02/17 16:52:09 - mmengine - INFO - Epoch(train) [26][ 740/1320] lr: 2.0000e-03 eta: 4:19:30 time: 0.4815 data_time: 0.0159 memory: 27031 grad_norm: 4.0941 loss: 1.3239 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.3239 2023/02/17 16:52:19 - mmengine - INFO - Epoch(train) [26][ 760/1320] lr: 2.0000e-03 eta: 4:19:20 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 4.1226 loss: 1.3820 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3820 2023/02/17 16:52:28 - mmengine - INFO - Epoch(train) [26][ 780/1320] lr: 2.0000e-03 eta: 4:19:10 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 3.9126 loss: 1.3301 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.3301 2023/02/17 16:52:38 - mmengine - INFO - Epoch(train) [26][ 800/1320] lr: 2.0000e-03 eta: 4:19:01 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.0871 loss: 1.2595 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2595 2023/02/17 16:52:48 - mmengine - INFO - Epoch(train) [26][ 820/1320] lr: 2.0000e-03 eta: 4:18:51 time: 0.4790 data_time: 0.0143 memory: 27031 grad_norm: 4.0633 loss: 1.2743 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2743 2023/02/17 16:52:57 - mmengine - INFO - Epoch(train) [26][ 840/1320] lr: 2.0000e-03 eta: 4:18:41 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.0960 loss: 1.2510 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2510 2023/02/17 16:53:07 - mmengine - INFO - Epoch(train) [26][ 860/1320] lr: 2.0000e-03 eta: 4:18:32 time: 0.4794 data_time: 0.0144 memory: 27031 grad_norm: 4.0640 loss: 1.3163 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3163 2023/02/17 16:53:16 - mmengine - INFO - Epoch(train) [26][ 880/1320] lr: 2.0000e-03 eta: 4:18:22 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.1643 loss: 1.2795 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.2795 2023/02/17 16:53:26 - mmengine - INFO - Epoch(train) [26][ 900/1320] lr: 2.0000e-03 eta: 4:18:12 time: 0.4801 data_time: 0.0151 memory: 27031 grad_norm: 4.1038 loss: 1.3564 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.3564 2023/02/17 16:53:36 - mmengine - INFO - Epoch(train) [26][ 920/1320] lr: 2.0000e-03 eta: 4:18:02 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.1755 loss: 1.2387 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2387 2023/02/17 16:53:45 - mmengine - INFO - Epoch(train) [26][ 940/1320] lr: 2.0000e-03 eta: 4:17:53 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.0692 loss: 1.3737 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.3737 2023/02/17 16:53:55 - mmengine - INFO - Epoch(train) [26][ 960/1320] lr: 2.0000e-03 eta: 4:17:43 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 3.9960 loss: 1.2228 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2228 2023/02/17 16:54:04 - mmengine - INFO - Epoch(train) [26][ 980/1320] lr: 2.0000e-03 eta: 4:17:33 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.1311 loss: 1.2784 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2784 2023/02/17 16:54:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:54:14 - mmengine - INFO - Epoch(train) [26][1000/1320] lr: 2.0000e-03 eta: 4:17:24 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.1394 loss: 1.1991 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1991 2023/02/17 16:54:24 - mmengine - INFO - Epoch(train) [26][1020/1320] lr: 2.0000e-03 eta: 4:17:14 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.1069 loss: 1.4073 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4073 2023/02/17 16:54:33 - mmengine - INFO - Epoch(train) [26][1040/1320] lr: 2.0000e-03 eta: 4:17:04 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.0713 loss: 1.2281 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2281 2023/02/17 16:54:43 - mmengine - INFO - Epoch(train) [26][1060/1320] lr: 2.0000e-03 eta: 4:16:54 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.1134 loss: 1.2489 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2489 2023/02/17 16:54:52 - mmengine - INFO - Epoch(train) [26][1080/1320] lr: 2.0000e-03 eta: 4:16:45 time: 0.4790 data_time: 0.0136 memory: 27031 grad_norm: 4.1682 loss: 1.3047 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3047 2023/02/17 16:55:02 - mmengine - INFO - Epoch(train) [26][1100/1320] lr: 2.0000e-03 eta: 4:16:35 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 4.0743 loss: 1.4053 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4053 2023/02/17 16:55:12 - mmengine - INFO - Epoch(train) [26][1120/1320] lr: 2.0000e-03 eta: 4:16:25 time: 0.4788 data_time: 0.0141 memory: 27031 grad_norm: 4.0578 loss: 1.2869 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2869 2023/02/17 16:55:21 - mmengine - INFO - Epoch(train) [26][1140/1320] lr: 2.0000e-03 eta: 4:16:16 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 4.1009 loss: 1.3947 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3947 2023/02/17 16:55:31 - mmengine - INFO - Epoch(train) [26][1160/1320] lr: 2.0000e-03 eta: 4:16:06 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 4.2325 loss: 1.2247 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2247 2023/02/17 16:55:40 - mmengine - INFO - Epoch(train) [26][1180/1320] lr: 2.0000e-03 eta: 4:15:56 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 4.0099 loss: 1.1683 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1683 2023/02/17 16:55:50 - mmengine - INFO - Epoch(train) [26][1200/1320] lr: 2.0000e-03 eta: 4:15:47 time: 0.4811 data_time: 0.0148 memory: 27031 grad_norm: 4.0391 loss: 1.1985 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1985 2023/02/17 16:56:00 - mmengine - INFO - Epoch(train) [26][1220/1320] lr: 2.0000e-03 eta: 4:15:37 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 3.9659 loss: 1.1992 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1992 2023/02/17 16:56:09 - mmengine - INFO - Epoch(train) [26][1240/1320] lr: 2.0000e-03 eta: 4:15:27 time: 0.4823 data_time: 0.0165 memory: 27031 grad_norm: 4.0684 loss: 1.3242 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3242 2023/02/17 16:56:19 - mmengine - INFO - Epoch(train) [26][1260/1320] lr: 2.0000e-03 eta: 4:15:18 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 4.0765 loss: 1.2220 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2220 2023/02/17 16:56:29 - mmengine - INFO - Epoch(train) [26][1280/1320] lr: 2.0000e-03 eta: 4:15:08 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.1554 loss: 1.3238 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3238 2023/02/17 16:56:38 - mmengine - INFO - Epoch(train) [26][1300/1320] lr: 2.0000e-03 eta: 4:14:58 time: 0.4811 data_time: 0.0157 memory: 27031 grad_norm: 4.0985 loss: 1.1785 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1785 2023/02/17 16:56:48 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 16:56:48 - mmengine - INFO - Epoch(train) [26][1320/1320] lr: 2.0000e-03 eta: 4:14:48 time: 0.4746 data_time: 0.0163 memory: 27031 grad_norm: 4.1559 loss: 1.2829 top1_acc: 0.5455 top5_acc: 0.8182 loss_cls: 1.2829 2023/02/17 16:56:51 - mmengine - INFO - Epoch(val) [26][ 20/194] eta: 0:00:31 time: 0.1806 data_time: 0.0561 memory: 3265 2023/02/17 16:56:54 - mmengine - INFO - Epoch(val) [26][ 40/194] eta: 0:00:24 time: 0.1364 data_time: 0.0129 memory: 3265 2023/02/17 16:56:57 - mmengine - INFO - Epoch(val) [26][ 60/194] eta: 0:00:20 time: 0.1372 data_time: 0.0129 memory: 3265 2023/02/17 16:57:00 - mmengine - INFO - Epoch(val) [26][ 80/194] eta: 0:00:16 time: 0.1378 data_time: 0.0133 memory: 3265 2023/02/17 16:57:02 - mmengine - INFO - Epoch(val) [26][100/194] eta: 0:00:13 time: 0.1388 data_time: 0.0139 memory: 3265 2023/02/17 16:57:05 - mmengine - INFO - Epoch(val) [26][120/194] eta: 0:00:10 time: 0.1368 data_time: 0.0129 memory: 3265 2023/02/17 16:57:08 - mmengine - INFO - Epoch(val) [26][140/194] eta: 0:00:07 time: 0.1399 data_time: 0.0143 memory: 3265 2023/02/17 16:57:11 - mmengine - INFO - Epoch(val) [26][160/194] eta: 0:00:04 time: 0.1373 data_time: 0.0134 memory: 3265 2023/02/17 16:57:13 - mmengine - INFO - Epoch(val) [26][180/194] eta: 0:00:01 time: 0.1398 data_time: 0.0149 memory: 3265 2023/02/17 16:57:16 - mmengine - INFO - Epoch(val) [26][194/194] acc/top1: 0.5964 acc/top5: 0.8562 acc/mean1: 0.5302 2023/02/17 16:57:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_24.pth is removed 2023/02/17 16:57:17 - mmengine - INFO - The best checkpoint with 0.5964 acc/top1 at 26 epoch is saved to best_acc/top1_epoch_26.pth. 2023/02/17 16:57:28 - mmengine - INFO - Epoch(train) [27][ 20/1320] lr: 2.0000e-03 eta: 4:14:40 time: 0.5334 data_time: 0.0596 memory: 27031 grad_norm: 4.0340 loss: 1.4102 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.4102 2023/02/17 16:57:38 - mmengine - INFO - Epoch(train) [27][ 40/1320] lr: 2.0000e-03 eta: 4:14:30 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.0959 loss: 1.3161 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3161 2023/02/17 16:57:47 - mmengine - INFO - Epoch(train) [27][ 60/1320] lr: 2.0000e-03 eta: 4:14:20 time: 0.4797 data_time: 0.0136 memory: 27031 grad_norm: 4.0376 loss: 1.1867 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1867 2023/02/17 16:57:57 - mmengine - INFO - Epoch(train) [27][ 80/1320] lr: 2.0000e-03 eta: 4:14:10 time: 0.4794 data_time: 0.0135 memory: 27031 grad_norm: 4.1072 loss: 1.2100 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2100 2023/02/17 16:58:06 - mmengine - INFO - Epoch(train) [27][ 100/1320] lr: 2.0000e-03 eta: 4:14:01 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.0281 loss: 1.3808 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3808 2023/02/17 16:58:16 - mmengine - INFO - Epoch(train) [27][ 120/1320] lr: 2.0000e-03 eta: 4:13:51 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.0463 loss: 1.3334 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3334 2023/02/17 16:58:26 - mmengine - INFO - Epoch(train) [27][ 140/1320] lr: 2.0000e-03 eta: 4:13:41 time: 0.4790 data_time: 0.0135 memory: 27031 grad_norm: 4.1194 loss: 1.2566 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2566 2023/02/17 16:58:35 - mmengine - INFO - Epoch(train) [27][ 160/1320] lr: 2.0000e-03 eta: 4:13:32 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 4.0946 loss: 1.1647 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1647 2023/02/17 16:58:45 - mmengine - INFO - Epoch(train) [27][ 180/1320] lr: 2.0000e-03 eta: 4:13:22 time: 0.4786 data_time: 0.0135 memory: 27031 grad_norm: 4.2320 loss: 1.4716 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.4716 2023/02/17 16:58:54 - mmengine - INFO - Epoch(train) [27][ 200/1320] lr: 2.0000e-03 eta: 4:13:12 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 3.9798 loss: 1.2296 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2296 2023/02/17 16:59:04 - mmengine - INFO - Epoch(train) [27][ 220/1320] lr: 2.0000e-03 eta: 4:13:03 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.0656 loss: 1.2551 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2551 2023/02/17 16:59:14 - mmengine - INFO - Epoch(train) [27][ 240/1320] lr: 2.0000e-03 eta: 4:12:53 time: 0.4793 data_time: 0.0140 memory: 27031 grad_norm: 4.0324 loss: 1.2787 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.2787 2023/02/17 16:59:23 - mmengine - INFO - Epoch(train) [27][ 260/1320] lr: 2.0000e-03 eta: 4:12:43 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.1393 loss: 1.3303 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3303 2023/02/17 16:59:33 - mmengine - INFO - Epoch(train) [27][ 280/1320] lr: 2.0000e-03 eta: 4:12:33 time: 0.4795 data_time: 0.0149 memory: 27031 grad_norm: 4.1111 loss: 1.3114 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 1.3114 2023/02/17 16:59:42 - mmengine - INFO - Epoch(train) [27][ 300/1320] lr: 2.0000e-03 eta: 4:12:24 time: 0.4789 data_time: 0.0143 memory: 27031 grad_norm: 4.2299 loss: 1.3483 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3483 2023/02/17 16:59:52 - mmengine - INFO - Epoch(train) [27][ 320/1320] lr: 2.0000e-03 eta: 4:12:14 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.0933 loss: 1.2904 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.2904 2023/02/17 17:00:01 - mmengine - INFO - Epoch(train) [27][ 340/1320] lr: 2.0000e-03 eta: 4:12:04 time: 0.4793 data_time: 0.0142 memory: 27031 grad_norm: 4.1451 loss: 1.3168 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3168 2023/02/17 17:00:11 - mmengine - INFO - Epoch(train) [27][ 360/1320] lr: 2.0000e-03 eta: 4:11:55 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.1103 loss: 1.2677 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2677 2023/02/17 17:00:21 - mmengine - INFO - Epoch(train) [27][ 380/1320] lr: 2.0000e-03 eta: 4:11:45 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 4.1655 loss: 1.4507 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.4507 2023/02/17 17:00:31 - mmengine - INFO - Epoch(train) [27][ 400/1320] lr: 2.0000e-03 eta: 4:11:36 time: 0.5318 data_time: 0.0662 memory: 27031 grad_norm: 4.1689 loss: 1.2926 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2926 2023/02/17 17:00:41 - mmengine - INFO - Epoch(train) [27][ 420/1320] lr: 2.0000e-03 eta: 4:11:26 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.2372 loss: 1.2314 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2314 2023/02/17 17:00:51 - mmengine - INFO - Epoch(train) [27][ 440/1320] lr: 2.0000e-03 eta: 4:11:17 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 4.1516 loss: 1.2616 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.2616 2023/02/17 17:01:00 - mmengine - INFO - Epoch(train) [27][ 460/1320] lr: 2.0000e-03 eta: 4:11:07 time: 0.4790 data_time: 0.0139 memory: 27031 grad_norm: 4.1714 loss: 1.1689 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1689 2023/02/17 17:01:10 - mmengine - INFO - Epoch(train) [27][ 480/1320] lr: 2.0000e-03 eta: 4:10:57 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.0840 loss: 1.0295 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0295 2023/02/17 17:01:19 - mmengine - INFO - Epoch(train) [27][ 500/1320] lr: 2.0000e-03 eta: 4:10:48 time: 0.4796 data_time: 0.0149 memory: 27031 grad_norm: 4.1602 loss: 1.2404 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2404 2023/02/17 17:01:29 - mmengine - INFO - Epoch(train) [27][ 520/1320] lr: 2.0000e-03 eta: 4:10:38 time: 0.4795 data_time: 0.0140 memory: 27031 grad_norm: 4.2262 loss: 1.1235 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1235 2023/02/17 17:01:39 - mmengine - INFO - Epoch(train) [27][ 540/1320] lr: 2.0000e-03 eta: 4:10:28 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 4.2421 loss: 1.2777 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2777 2023/02/17 17:01:48 - mmengine - INFO - Epoch(train) [27][ 560/1320] lr: 2.0000e-03 eta: 4:10:18 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 4.2003 loss: 1.2651 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2651 2023/02/17 17:01:58 - mmengine - INFO - Epoch(train) [27][ 580/1320] lr: 2.0000e-03 eta: 4:10:09 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 4.1737 loss: 1.2674 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2674 2023/02/17 17:02:07 - mmengine - INFO - Epoch(train) [27][ 600/1320] lr: 2.0000e-03 eta: 4:09:59 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.1497 loss: 1.4240 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4240 2023/02/17 17:02:17 - mmengine - INFO - Epoch(train) [27][ 620/1320] lr: 2.0000e-03 eta: 4:09:49 time: 0.4791 data_time: 0.0149 memory: 27031 grad_norm: 4.1584 loss: 1.1667 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 1.1667 2023/02/17 17:02:27 - mmengine - INFO - Epoch(train) [27][ 640/1320] lr: 2.0000e-03 eta: 4:09:40 time: 0.4811 data_time: 0.0156 memory: 27031 grad_norm: 4.1801 loss: 1.2745 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2745 2023/02/17 17:02:36 - mmengine - INFO - Epoch(train) [27][ 660/1320] lr: 2.0000e-03 eta: 4:09:30 time: 0.4800 data_time: 0.0149 memory: 27031 grad_norm: 4.2421 loss: 1.3291 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3291 2023/02/17 17:02:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:02:46 - mmengine - INFO - Epoch(train) [27][ 680/1320] lr: 2.0000e-03 eta: 4:09:20 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 4.2876 loss: 1.2496 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.2496 2023/02/17 17:02:55 - mmengine - INFO - Epoch(train) [27][ 700/1320] lr: 2.0000e-03 eta: 4:09:11 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.0986 loss: 1.1713 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1713 2023/02/17 17:03:05 - mmengine - INFO - Epoch(train) [27][ 720/1320] lr: 2.0000e-03 eta: 4:09:01 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 4.2804 loss: 1.1080 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1080 2023/02/17 17:03:15 - mmengine - INFO - Epoch(train) [27][ 740/1320] lr: 2.0000e-03 eta: 4:08:51 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.2556 loss: 1.0934 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.0934 2023/02/17 17:03:24 - mmengine - INFO - Epoch(train) [27][ 760/1320] lr: 2.0000e-03 eta: 4:08:42 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 4.1503 loss: 1.1048 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1048 2023/02/17 17:03:34 - mmengine - INFO - Epoch(train) [27][ 780/1320] lr: 2.0000e-03 eta: 4:08:32 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 4.1695 loss: 1.0507 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0507 2023/02/17 17:03:43 - mmengine - INFO - Epoch(train) [27][ 800/1320] lr: 2.0000e-03 eta: 4:08:22 time: 0.4799 data_time: 0.0141 memory: 27031 grad_norm: 4.2589 loss: 1.3130 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.3130 2023/02/17 17:03:53 - mmengine - INFO - Epoch(train) [27][ 820/1320] lr: 2.0000e-03 eta: 4:08:12 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.1668 loss: 1.3319 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3319 2023/02/17 17:04:03 - mmengine - INFO - Epoch(train) [27][ 840/1320] lr: 2.0000e-03 eta: 4:08:03 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 4.2383 loss: 1.2145 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2145 2023/02/17 17:04:12 - mmengine - INFO - Epoch(train) [27][ 860/1320] lr: 2.0000e-03 eta: 4:07:53 time: 0.4804 data_time: 0.0152 memory: 27031 grad_norm: 4.2747 loss: 1.3116 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3116 2023/02/17 17:04:22 - mmengine - INFO - Epoch(train) [27][ 880/1320] lr: 2.0000e-03 eta: 4:07:43 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 4.1766 loss: 1.0905 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0905 2023/02/17 17:04:31 - mmengine - INFO - Epoch(train) [27][ 900/1320] lr: 2.0000e-03 eta: 4:07:34 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.1817 loss: 1.2640 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2640 2023/02/17 17:04:41 - mmengine - INFO - Epoch(train) [27][ 920/1320] lr: 2.0000e-03 eta: 4:07:24 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.1909 loss: 1.3230 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3230 2023/02/17 17:04:51 - mmengine - INFO - Epoch(train) [27][ 940/1320] lr: 2.0000e-03 eta: 4:07:14 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 4.3056 loss: 1.5127 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.5127 2023/02/17 17:05:00 - mmengine - INFO - Epoch(train) [27][ 960/1320] lr: 2.0000e-03 eta: 4:07:05 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 4.2427 loss: 1.1977 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1977 2023/02/17 17:05:10 - mmengine - INFO - Epoch(train) [27][ 980/1320] lr: 2.0000e-03 eta: 4:06:55 time: 0.4816 data_time: 0.0161 memory: 27031 grad_norm: 4.2974 loss: 1.3679 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3679 2023/02/17 17:05:19 - mmengine - INFO - Epoch(train) [27][1000/1320] lr: 2.0000e-03 eta: 4:06:45 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.1912 loss: 1.3517 top1_acc: 0.5000 top5_acc: 0.5625 loss_cls: 1.3517 2023/02/17 17:05:29 - mmengine - INFO - Epoch(train) [27][1020/1320] lr: 2.0000e-03 eta: 4:06:35 time: 0.4803 data_time: 0.0151 memory: 27031 grad_norm: 4.2138 loss: 1.2148 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2148 2023/02/17 17:05:39 - mmengine - INFO - Epoch(train) [27][1040/1320] lr: 2.0000e-03 eta: 4:06:26 time: 0.4795 data_time: 0.0133 memory: 27031 grad_norm: 4.1061 loss: 1.2392 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2392 2023/02/17 17:05:48 - mmengine - INFO - Epoch(train) [27][1060/1320] lr: 2.0000e-03 eta: 4:06:16 time: 0.4807 data_time: 0.0150 memory: 27031 grad_norm: 4.3108 loss: 1.1916 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1916 2023/02/17 17:05:58 - mmengine - INFO - Epoch(train) [27][1080/1320] lr: 2.0000e-03 eta: 4:06:06 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.3034 loss: 1.3510 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.3510 2023/02/17 17:06:07 - mmengine - INFO - Epoch(train) [27][1100/1320] lr: 2.0000e-03 eta: 4:05:57 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2906 loss: 1.1074 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1074 2023/02/17 17:06:17 - mmengine - INFO - Epoch(train) [27][1120/1320] lr: 2.0000e-03 eta: 4:05:47 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.3246 loss: 1.2423 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.2423 2023/02/17 17:06:27 - mmengine - INFO - Epoch(train) [27][1140/1320] lr: 2.0000e-03 eta: 4:05:37 time: 0.4802 data_time: 0.0156 memory: 27031 grad_norm: 4.2036 loss: 1.1861 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1861 2023/02/17 17:06:36 - mmengine - INFO - Epoch(train) [27][1160/1320] lr: 2.0000e-03 eta: 4:05:28 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.2489 loss: 1.2953 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2953 2023/02/17 17:06:46 - mmengine - INFO - Epoch(train) [27][1180/1320] lr: 2.0000e-03 eta: 4:05:18 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 4.2037 loss: 1.1271 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1271 2023/02/17 17:06:56 - mmengine - INFO - Epoch(train) [27][1200/1320] lr: 2.0000e-03 eta: 4:05:08 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 4.2940 loss: 1.2309 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2309 2023/02/17 17:07:05 - mmengine - INFO - Epoch(train) [27][1220/1320] lr: 2.0000e-03 eta: 4:04:59 time: 0.4801 data_time: 0.0150 memory: 27031 grad_norm: 4.3173 loss: 1.2154 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2154 2023/02/17 17:07:15 - mmengine - INFO - Epoch(train) [27][1240/1320] lr: 2.0000e-03 eta: 4:04:49 time: 0.4801 data_time: 0.0137 memory: 27031 grad_norm: 4.2659 loss: 1.3198 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3198 2023/02/17 17:07:24 - mmengine - INFO - Epoch(train) [27][1260/1320] lr: 2.0000e-03 eta: 4:04:39 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.1882 loss: 1.1795 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1795 2023/02/17 17:07:34 - mmengine - INFO - Epoch(train) [27][1280/1320] lr: 2.0000e-03 eta: 4:04:29 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 4.1778 loss: 1.1314 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.1314 2023/02/17 17:07:44 - mmengine - INFO - Epoch(train) [27][1300/1320] lr: 2.0000e-03 eta: 4:04:20 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.3014 loss: 1.3499 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3499 2023/02/17 17:07:53 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:07:53 - mmengine - INFO - Epoch(train) [27][1320/1320] lr: 2.0000e-03 eta: 4:04:10 time: 0.4747 data_time: 0.0148 memory: 27031 grad_norm: 4.2185 loss: 1.2014 top1_acc: 0.6364 top5_acc: 1.0000 loss_cls: 1.2014 2023/02/17 17:07:53 - mmengine - INFO - Saving checkpoint at 27 epochs 2023/02/17 17:07:58 - mmengine - INFO - Epoch(val) [27][ 20/194] eta: 0:00:33 time: 0.1925 data_time: 0.0608 memory: 3265 2023/02/17 17:08:01 - mmengine - INFO - Epoch(val) [27][ 40/194] eta: 0:00:25 time: 0.1390 data_time: 0.0133 memory: 3265 2023/02/17 17:08:04 - mmengine - INFO - Epoch(val) [27][ 60/194] eta: 0:00:21 time: 0.1411 data_time: 0.0144 memory: 3265 2023/02/17 17:08:07 - mmengine - INFO - Epoch(val) [27][ 80/194] eta: 0:00:17 time: 0.1389 data_time: 0.0136 memory: 3265 2023/02/17 17:08:09 - mmengine - INFO - Epoch(val) [27][100/194] eta: 0:00:14 time: 0.1388 data_time: 0.0139 memory: 3265 2023/02/17 17:08:12 - mmengine - INFO - Epoch(val) [27][120/194] eta: 0:00:10 time: 0.1348 data_time: 0.0122 memory: 3265 2023/02/17 17:08:15 - mmengine - INFO - Epoch(val) [27][140/194] eta: 0:00:07 time: 0.1374 data_time: 0.0129 memory: 3265 2023/02/17 17:08:18 - mmengine - INFO - Epoch(val) [27][160/194] eta: 0:00:04 time: 0.1383 data_time: 0.0137 memory: 3265 2023/02/17 17:08:20 - mmengine - INFO - Epoch(val) [27][180/194] eta: 0:00:02 time: 0.1356 data_time: 0.0123 memory: 3265 2023/02/17 17:08:23 - mmengine - INFO - Epoch(val) [27][194/194] acc/top1: 0.5995 acc/top5: 0.8612 acc/mean1: 0.5374 2023/02/17 17:08:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_26.pth is removed 2023/02/17 17:08:24 - mmengine - INFO - The best checkpoint with 0.5995 acc/top1 at 27 epoch is saved to best_acc/top1_epoch_27.pth. 2023/02/17 17:08:35 - mmengine - INFO - Epoch(train) [28][ 20/1320] lr: 2.0000e-03 eta: 4:04:01 time: 0.5253 data_time: 0.0519 memory: 27031 grad_norm: 4.1451 loss: 1.2535 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2535 2023/02/17 17:08:44 - mmengine - INFO - Epoch(train) [28][ 40/1320] lr: 2.0000e-03 eta: 4:03:51 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 4.1254 loss: 1.0772 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0772 2023/02/17 17:08:54 - mmengine - INFO - Epoch(train) [28][ 60/1320] lr: 2.0000e-03 eta: 4:03:42 time: 0.4795 data_time: 0.0136 memory: 27031 grad_norm: 4.1671 loss: 1.0950 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0950 2023/02/17 17:09:03 - mmengine - INFO - Epoch(train) [28][ 80/1320] lr: 2.0000e-03 eta: 4:03:32 time: 0.4793 data_time: 0.0146 memory: 27031 grad_norm: 4.2738 loss: 1.0773 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0773 2023/02/17 17:09:13 - mmengine - INFO - Epoch(train) [28][ 100/1320] lr: 2.0000e-03 eta: 4:03:22 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.1493 loss: 1.2016 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2016 2023/02/17 17:09:23 - mmengine - INFO - Epoch(train) [28][ 120/1320] lr: 2.0000e-03 eta: 4:03:13 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 4.2048 loss: 1.3490 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.3490 2023/02/17 17:09:32 - mmengine - INFO - Epoch(train) [28][ 140/1320] lr: 2.0000e-03 eta: 4:03:03 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.2345 loss: 1.1598 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1598 2023/02/17 17:09:42 - mmengine - INFO - Epoch(train) [28][ 160/1320] lr: 2.0000e-03 eta: 4:02:53 time: 0.4790 data_time: 0.0139 memory: 27031 grad_norm: 4.2352 loss: 1.3032 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3032 2023/02/17 17:09:51 - mmengine - INFO - Epoch(train) [28][ 180/1320] lr: 2.0000e-03 eta: 4:02:43 time: 0.4806 data_time: 0.0152 memory: 27031 grad_norm: 4.2491 loss: 1.2225 top1_acc: 0.6250 top5_acc: 0.6250 loss_cls: 1.2225 2023/02/17 17:10:01 - mmengine - INFO - Epoch(train) [28][ 200/1320] lr: 2.0000e-03 eta: 4:02:34 time: 0.4792 data_time: 0.0142 memory: 27031 grad_norm: 4.2523 loss: 1.3026 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3026 2023/02/17 17:10:11 - mmengine - INFO - Epoch(train) [28][ 220/1320] lr: 2.0000e-03 eta: 4:02:24 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 4.2240 loss: 1.0045 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0045 2023/02/17 17:10:20 - mmengine - INFO - Epoch(train) [28][ 240/1320] lr: 2.0000e-03 eta: 4:02:14 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 4.3618 loss: 1.2085 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2085 2023/02/17 17:10:30 - mmengine - INFO - Epoch(train) [28][ 260/1320] lr: 2.0000e-03 eta: 4:02:05 time: 0.4791 data_time: 0.0142 memory: 27031 grad_norm: 4.3207 loss: 1.1142 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1142 2023/02/17 17:10:39 - mmengine - INFO - Epoch(train) [28][ 280/1320] lr: 2.0000e-03 eta: 4:01:55 time: 0.4804 data_time: 0.0152 memory: 27031 grad_norm: 4.3074 loss: 1.1943 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1943 2023/02/17 17:10:49 - mmengine - INFO - Epoch(train) [28][ 300/1320] lr: 2.0000e-03 eta: 4:01:45 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 4.2234 loss: 1.3560 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3560 2023/02/17 17:10:59 - mmengine - INFO - Epoch(train) [28][ 320/1320] lr: 2.0000e-03 eta: 4:01:36 time: 0.4792 data_time: 0.0143 memory: 27031 grad_norm: 4.2198 loss: 1.2447 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.2447 2023/02/17 17:11:08 - mmengine - INFO - Epoch(train) [28][ 340/1320] lr: 2.0000e-03 eta: 4:01:26 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.2273 loss: 1.1159 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1159 2023/02/17 17:11:18 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:11:18 - mmengine - INFO - Epoch(train) [28][ 360/1320] lr: 2.0000e-03 eta: 4:01:16 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.1584 loss: 1.2297 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2297 2023/02/17 17:11:27 - mmengine - INFO - Epoch(train) [28][ 380/1320] lr: 2.0000e-03 eta: 4:01:07 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 4.2354 loss: 1.1876 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1876 2023/02/17 17:11:37 - mmengine - INFO - Epoch(train) [28][ 400/1320] lr: 2.0000e-03 eta: 4:00:57 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 4.2955 loss: 1.2370 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2370 2023/02/17 17:11:47 - mmengine - INFO - Epoch(train) [28][ 420/1320] lr: 2.0000e-03 eta: 4:00:47 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.2191 loss: 1.1747 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1747 2023/02/17 17:11:56 - mmengine - INFO - Epoch(train) [28][ 440/1320] lr: 2.0000e-03 eta: 4:00:37 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.2706 loss: 1.2400 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2400 2023/02/17 17:12:06 - mmengine - INFO - Epoch(train) [28][ 460/1320] lr: 2.0000e-03 eta: 4:00:28 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 4.3380 loss: 1.3084 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3084 2023/02/17 17:12:15 - mmengine - INFO - Epoch(train) [28][ 480/1320] lr: 2.0000e-03 eta: 4:00:18 time: 0.4798 data_time: 0.0148 memory: 27031 grad_norm: 4.2504 loss: 1.1422 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1422 2023/02/17 17:12:25 - mmengine - INFO - Epoch(train) [28][ 500/1320] lr: 2.0000e-03 eta: 4:00:08 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.1564 loss: 1.1504 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1504 2023/02/17 17:12:35 - mmengine - INFO - Epoch(train) [28][ 520/1320] lr: 2.0000e-03 eta: 3:59:59 time: 0.4794 data_time: 0.0135 memory: 27031 grad_norm: 4.2246 loss: 1.1696 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1696 2023/02/17 17:12:44 - mmengine - INFO - Epoch(train) [28][ 540/1320] lr: 2.0000e-03 eta: 3:59:49 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.2747 loss: 1.3275 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.3275 2023/02/17 17:12:54 - mmengine - INFO - Epoch(train) [28][ 560/1320] lr: 2.0000e-03 eta: 3:59:39 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 4.2460 loss: 1.3399 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3399 2023/02/17 17:13:03 - mmengine - INFO - Epoch(train) [28][ 580/1320] lr: 2.0000e-03 eta: 3:59:30 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.2038 loss: 1.2596 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2596 2023/02/17 17:13:13 - mmengine - INFO - Epoch(train) [28][ 600/1320] lr: 2.0000e-03 eta: 3:59:20 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 4.2896 loss: 1.2764 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2764 2023/02/17 17:13:23 - mmengine - INFO - Epoch(train) [28][ 620/1320] lr: 2.0000e-03 eta: 3:59:10 time: 0.4793 data_time: 0.0144 memory: 27031 grad_norm: 4.3059 loss: 1.2782 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2782 2023/02/17 17:13:32 - mmengine - INFO - Epoch(train) [28][ 640/1320] lr: 2.0000e-03 eta: 3:59:00 time: 0.4810 data_time: 0.0149 memory: 27031 grad_norm: 4.2427 loss: 1.2535 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2535 2023/02/17 17:13:42 - mmengine - INFO - Epoch(train) [28][ 660/1320] lr: 2.0000e-03 eta: 3:58:51 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 4.4390 loss: 1.2931 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2931 2023/02/17 17:13:51 - mmengine - INFO - Epoch(train) [28][ 680/1320] lr: 2.0000e-03 eta: 3:58:41 time: 0.4790 data_time: 0.0143 memory: 27031 grad_norm: 4.3595 loss: 1.2159 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2159 2023/02/17 17:14:01 - mmengine - INFO - Epoch(train) [28][ 700/1320] lr: 2.0000e-03 eta: 3:58:31 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 4.4606 loss: 1.2754 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2754 2023/02/17 17:14:11 - mmengine - INFO - Epoch(train) [28][ 720/1320] lr: 2.0000e-03 eta: 3:58:22 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 4.2462 loss: 1.1596 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1596 2023/02/17 17:14:20 - mmengine - INFO - Epoch(train) [28][ 740/1320] lr: 2.0000e-03 eta: 3:58:12 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.3859 loss: 1.0945 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0945 2023/02/17 17:14:30 - mmengine - INFO - Epoch(train) [28][ 760/1320] lr: 2.0000e-03 eta: 3:58:02 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 4.4075 loss: 1.1984 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1984 2023/02/17 17:14:39 - mmengine - INFO - Epoch(train) [28][ 780/1320] lr: 2.0000e-03 eta: 3:57:53 time: 0.4804 data_time: 0.0141 memory: 27031 grad_norm: 4.3102 loss: 1.2090 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2090 2023/02/17 17:14:49 - mmengine - INFO - Epoch(train) [28][ 800/1320] lr: 2.0000e-03 eta: 3:57:43 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.2830 loss: 1.2271 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2271 2023/02/17 17:14:59 - mmengine - INFO - Epoch(train) [28][ 820/1320] lr: 2.0000e-03 eta: 3:57:33 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.2184 loss: 1.1662 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1662 2023/02/17 17:15:08 - mmengine - INFO - Epoch(train) [28][ 840/1320] lr: 2.0000e-03 eta: 3:57:24 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.3442 loss: 1.2110 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2110 2023/02/17 17:15:18 - mmengine - INFO - Epoch(train) [28][ 860/1320] lr: 2.0000e-03 eta: 3:57:14 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.3212 loss: 1.3061 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3061 2023/02/17 17:15:27 - mmengine - INFO - Epoch(train) [28][ 880/1320] lr: 2.0000e-03 eta: 3:57:04 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.4455 loss: 1.2229 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2229 2023/02/17 17:15:37 - mmengine - INFO - Epoch(train) [28][ 900/1320] lr: 2.0000e-03 eta: 3:56:54 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 4.4242 loss: 1.3362 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3362 2023/02/17 17:15:47 - mmengine - INFO - Epoch(train) [28][ 920/1320] lr: 2.0000e-03 eta: 3:56:45 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 4.5057 loss: 1.1288 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1288 2023/02/17 17:15:56 - mmengine - INFO - Epoch(train) [28][ 940/1320] lr: 2.0000e-03 eta: 3:56:35 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.3866 loss: 1.2220 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2220 2023/02/17 17:16:06 - mmengine - INFO - Epoch(train) [28][ 960/1320] lr: 2.0000e-03 eta: 3:56:25 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.2975 loss: 1.0794 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0794 2023/02/17 17:16:16 - mmengine - INFO - Epoch(train) [28][ 980/1320] lr: 2.0000e-03 eta: 3:56:16 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 4.4430 loss: 1.2141 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2141 2023/02/17 17:16:25 - mmengine - INFO - Epoch(train) [28][1000/1320] lr: 2.0000e-03 eta: 3:56:06 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.3291 loss: 1.1610 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1610 2023/02/17 17:16:35 - mmengine - INFO - Epoch(train) [28][1020/1320] lr: 2.0000e-03 eta: 3:55:56 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 4.2636 loss: 1.3343 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3343 2023/02/17 17:16:44 - mmengine - INFO - Epoch(train) [28][1040/1320] lr: 2.0000e-03 eta: 3:55:47 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.3696 loss: 1.1901 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1901 2023/02/17 17:16:54 - mmengine - INFO - Epoch(train) [28][1060/1320] lr: 2.0000e-03 eta: 3:55:37 time: 0.4799 data_time: 0.0139 memory: 27031 grad_norm: 4.3759 loss: 1.2656 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2656 2023/02/17 17:17:04 - mmengine - INFO - Epoch(train) [28][1080/1320] lr: 2.0000e-03 eta: 3:55:27 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.4755 loss: 1.3214 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.3214 2023/02/17 17:17:13 - mmengine - INFO - Epoch(train) [28][1100/1320] lr: 2.0000e-03 eta: 3:55:18 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 4.4357 loss: 1.2222 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2222 2023/02/17 17:17:23 - mmengine - INFO - Epoch(train) [28][1120/1320] lr: 2.0000e-03 eta: 3:55:08 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.2625 loss: 1.1482 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1482 2023/02/17 17:17:32 - mmengine - INFO - Epoch(train) [28][1140/1320] lr: 2.0000e-03 eta: 3:54:58 time: 0.4813 data_time: 0.0147 memory: 27031 grad_norm: 4.3041 loss: 1.2348 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.2348 2023/02/17 17:17:42 - mmengine - INFO - Epoch(train) [28][1160/1320] lr: 2.0000e-03 eta: 3:54:49 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 4.3174 loss: 1.1852 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1852 2023/02/17 17:17:52 - mmengine - INFO - Epoch(train) [28][1180/1320] lr: 2.0000e-03 eta: 3:54:39 time: 0.4820 data_time: 0.0159 memory: 27031 grad_norm: 4.4256 loss: 1.1908 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1908 2023/02/17 17:18:01 - mmengine - INFO - Epoch(train) [28][1200/1320] lr: 2.0000e-03 eta: 3:54:29 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 4.2759 loss: 1.1807 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1807 2023/02/17 17:18:11 - mmengine - INFO - Epoch(train) [28][1220/1320] lr: 2.0000e-03 eta: 3:54:19 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 4.2872 loss: 1.2629 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.2629 2023/02/17 17:18:20 - mmengine - INFO - Epoch(train) [28][1240/1320] lr: 2.0000e-03 eta: 3:54:10 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.4481 loss: 1.1152 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1152 2023/02/17 17:18:30 - mmengine - INFO - Epoch(train) [28][1260/1320] lr: 2.0000e-03 eta: 3:54:00 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.3123 loss: 1.1518 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1518 2023/02/17 17:18:40 - mmengine - INFO - Epoch(train) [28][1280/1320] lr: 2.0000e-03 eta: 3:53:50 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.3543 loss: 1.0578 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0578 2023/02/17 17:18:49 - mmengine - INFO - Epoch(train) [28][1300/1320] lr: 2.0000e-03 eta: 3:53:41 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 4.3742 loss: 1.2543 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2543 2023/02/17 17:18:59 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:18:59 - mmengine - INFO - Epoch(train) [28][1320/1320] lr: 2.0000e-03 eta: 3:53:31 time: 0.4734 data_time: 0.0146 memory: 27031 grad_norm: 4.3563 loss: 1.1420 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 1.1420 2023/02/17 17:19:02 - mmengine - INFO - Epoch(val) [28][ 20/194] eta: 0:00:32 time: 0.1846 data_time: 0.0573 memory: 3265 2023/02/17 17:19:05 - mmengine - INFO - Epoch(val) [28][ 40/194] eta: 0:00:24 time: 0.1380 data_time: 0.0123 memory: 3265 2023/02/17 17:19:08 - mmengine - INFO - Epoch(val) [28][ 60/194] eta: 0:00:20 time: 0.1399 data_time: 0.0145 memory: 3265 2023/02/17 17:19:11 - mmengine - INFO - Epoch(val) [28][ 80/194] eta: 0:00:17 time: 0.1382 data_time: 0.0136 memory: 3265 2023/02/17 17:19:13 - mmengine - INFO - Epoch(val) [28][100/194] eta: 0:00:13 time: 0.1377 data_time: 0.0134 memory: 3265 2023/02/17 17:19:16 - mmengine - INFO - Epoch(val) [28][120/194] eta: 0:00:10 time: 0.1373 data_time: 0.0133 memory: 3265 2023/02/17 17:19:19 - mmengine - INFO - Epoch(val) [28][140/194] eta: 0:00:07 time: 0.1393 data_time: 0.0139 memory: 3265 2023/02/17 17:19:22 - mmengine - INFO - Epoch(val) [28][160/194] eta: 0:00:04 time: 0.1371 data_time: 0.0128 memory: 3265 2023/02/17 17:19:24 - mmengine - INFO - Epoch(val) [28][180/194] eta: 0:00:02 time: 0.1363 data_time: 0.0128 memory: 3265 2023/02/17 17:19:27 - mmengine - INFO - Epoch(val) [28][194/194] acc/top1: 0.6057 acc/top5: 0.8641 acc/mean1: 0.5408 2023/02/17 17:19:27 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_27.pth is removed 2023/02/17 17:19:28 - mmengine - INFO - The best checkpoint with 0.6057 acc/top1 at 28 epoch is saved to best_acc/top1_epoch_28.pth. 2023/02/17 17:19:39 - mmengine - INFO - Epoch(train) [29][ 20/1320] lr: 2.0000e-03 eta: 3:53:22 time: 0.5295 data_time: 0.0574 memory: 27031 grad_norm: 4.3845 loss: 1.1418 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1418 2023/02/17 17:19:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:19:49 - mmengine - INFO - Epoch(train) [29][ 40/1320] lr: 2.0000e-03 eta: 3:53:12 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 4.4331 loss: 1.3910 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3910 2023/02/17 17:19:58 - mmengine - INFO - Epoch(train) [29][ 60/1320] lr: 2.0000e-03 eta: 3:53:03 time: 0.4788 data_time: 0.0132 memory: 27031 grad_norm: 4.3973 loss: 1.0559 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0559 2023/02/17 17:20:08 - mmengine - INFO - Epoch(train) [29][ 80/1320] lr: 2.0000e-03 eta: 3:52:53 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.3805 loss: 1.2028 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2028 2023/02/17 17:20:17 - mmengine - INFO - Epoch(train) [29][ 100/1320] lr: 2.0000e-03 eta: 3:52:43 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 4.4197 loss: 1.2531 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2531 2023/02/17 17:20:27 - mmengine - INFO - Epoch(train) [29][ 120/1320] lr: 2.0000e-03 eta: 3:52:34 time: 0.4804 data_time: 0.0151 memory: 27031 grad_norm: 4.3292 loss: 1.0886 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0886 2023/02/17 17:20:37 - mmengine - INFO - Epoch(train) [29][ 140/1320] lr: 2.0000e-03 eta: 3:52:24 time: 0.4823 data_time: 0.0167 memory: 27031 grad_norm: 4.5006 loss: 1.1838 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.1838 2023/02/17 17:20:46 - mmengine - INFO - Epoch(train) [29][ 160/1320] lr: 2.0000e-03 eta: 3:52:14 time: 0.4788 data_time: 0.0143 memory: 27031 grad_norm: 4.4590 loss: 1.2348 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2348 2023/02/17 17:20:56 - mmengine - INFO - Epoch(train) [29][ 180/1320] lr: 2.0000e-03 eta: 3:52:05 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.4231 loss: 1.1701 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1701 2023/02/17 17:21:05 - mmengine - INFO - Epoch(train) [29][ 200/1320] lr: 2.0000e-03 eta: 3:51:55 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.4353 loss: 1.1477 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1477 2023/02/17 17:21:15 - mmengine - INFO - Epoch(train) [29][ 220/1320] lr: 2.0000e-03 eta: 3:51:45 time: 0.4793 data_time: 0.0140 memory: 27031 grad_norm: 4.4593 loss: 1.0968 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0968 2023/02/17 17:21:25 - mmengine - INFO - Epoch(train) [29][ 240/1320] lr: 2.0000e-03 eta: 3:51:35 time: 0.4805 data_time: 0.0152 memory: 27031 grad_norm: 4.3668 loss: 1.1453 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.1453 2023/02/17 17:21:34 - mmengine - INFO - Epoch(train) [29][ 260/1320] lr: 2.0000e-03 eta: 3:51:26 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 4.4224 loss: 1.1746 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1746 2023/02/17 17:21:44 - mmengine - INFO - Epoch(train) [29][ 280/1320] lr: 2.0000e-03 eta: 3:51:16 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 4.3943 loss: 1.2253 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2253 2023/02/17 17:21:53 - mmengine - INFO - Epoch(train) [29][ 300/1320] lr: 2.0000e-03 eta: 3:51:06 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 4.5442 loss: 1.3373 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3373 2023/02/17 17:22:03 - mmengine - INFO - Epoch(train) [29][ 320/1320] lr: 2.0000e-03 eta: 3:50:57 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.5506 loss: 1.3361 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3361 2023/02/17 17:22:13 - mmengine - INFO - Epoch(train) [29][ 340/1320] lr: 2.0000e-03 eta: 3:50:47 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 4.4511 loss: 1.2297 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2297 2023/02/17 17:22:22 - mmengine - INFO - Epoch(train) [29][ 360/1320] lr: 2.0000e-03 eta: 3:50:37 time: 0.4808 data_time: 0.0154 memory: 27031 grad_norm: 4.4351 loss: 1.2276 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2276 2023/02/17 17:22:32 - mmengine - INFO - Epoch(train) [29][ 380/1320] lr: 2.0000e-03 eta: 3:50:28 time: 0.4795 data_time: 0.0137 memory: 27031 grad_norm: 4.5519 loss: 1.1855 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1855 2023/02/17 17:22:41 - mmengine - INFO - Epoch(train) [29][ 400/1320] lr: 2.0000e-03 eta: 3:50:18 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.5762 loss: 1.1201 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1201 2023/02/17 17:22:51 - mmengine - INFO - Epoch(train) [29][ 420/1320] lr: 2.0000e-03 eta: 3:50:08 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.4581 loss: 1.1140 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1140 2023/02/17 17:23:01 - mmengine - INFO - Epoch(train) [29][ 440/1320] lr: 2.0000e-03 eta: 3:49:59 time: 0.4798 data_time: 0.0150 memory: 27031 grad_norm: 4.4774 loss: 1.2438 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2438 2023/02/17 17:23:10 - mmengine - INFO - Epoch(train) [29][ 460/1320] lr: 2.0000e-03 eta: 3:49:49 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.2900 loss: 1.1732 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1732 2023/02/17 17:23:20 - mmengine - INFO - Epoch(train) [29][ 480/1320] lr: 2.0000e-03 eta: 3:49:39 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 4.4524 loss: 1.2785 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2785 2023/02/17 17:23:29 - mmengine - INFO - Epoch(train) [29][ 500/1320] lr: 2.0000e-03 eta: 3:49:30 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.4082 loss: 1.2641 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2641 2023/02/17 17:23:39 - mmengine - INFO - Epoch(train) [29][ 520/1320] lr: 2.0000e-03 eta: 3:49:20 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 4.4616 loss: 1.0973 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0973 2023/02/17 17:23:49 - mmengine - INFO - Epoch(train) [29][ 540/1320] lr: 2.0000e-03 eta: 3:49:10 time: 0.4795 data_time: 0.0132 memory: 27031 grad_norm: 4.4111 loss: 1.1288 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1288 2023/02/17 17:23:58 - mmengine - INFO - Epoch(train) [29][ 560/1320] lr: 2.0000e-03 eta: 3:49:00 time: 0.4804 data_time: 0.0154 memory: 27031 grad_norm: 4.2719 loss: 1.1907 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1907 2023/02/17 17:24:08 - mmengine - INFO - Epoch(train) [29][ 580/1320] lr: 2.0000e-03 eta: 3:48:51 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 4.5072 loss: 1.1854 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1854 2023/02/17 17:24:17 - mmengine - INFO - Epoch(train) [29][ 600/1320] lr: 2.0000e-03 eta: 3:48:41 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 4.4841 loss: 1.1845 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1845 2023/02/17 17:24:27 - mmengine - INFO - Epoch(train) [29][ 620/1320] lr: 2.0000e-03 eta: 3:48:31 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 4.2882 loss: 1.1678 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1678 2023/02/17 17:24:37 - mmengine - INFO - Epoch(train) [29][ 640/1320] lr: 2.0000e-03 eta: 3:48:22 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 4.4190 loss: 1.1753 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1753 2023/02/17 17:24:46 - mmengine - INFO - Epoch(train) [29][ 660/1320] lr: 2.0000e-03 eta: 3:48:12 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.3807 loss: 1.2302 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2302 2023/02/17 17:24:56 - mmengine - INFO - Epoch(train) [29][ 680/1320] lr: 2.0000e-03 eta: 3:48:02 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 4.4654 loss: 1.2836 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2836 2023/02/17 17:25:05 - mmengine - INFO - Epoch(train) [29][ 700/1320] lr: 2.0000e-03 eta: 3:47:53 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.3007 loss: 1.2547 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2547 2023/02/17 17:25:15 - mmengine - INFO - Epoch(train) [29][ 720/1320] lr: 2.0000e-03 eta: 3:47:43 time: 0.4811 data_time: 0.0150 memory: 27031 grad_norm: 4.4134 loss: 1.1771 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1771 2023/02/17 17:25:25 - mmengine - INFO - Epoch(train) [29][ 740/1320] lr: 2.0000e-03 eta: 3:47:33 time: 0.4799 data_time: 0.0139 memory: 27031 grad_norm: 4.4777 loss: 1.3385 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 1.3385 2023/02/17 17:25:34 - mmengine - INFO - Epoch(train) [29][ 760/1320] lr: 2.0000e-03 eta: 3:47:24 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 4.5657 loss: 1.0363 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0363 2023/02/17 17:25:44 - mmengine - INFO - Epoch(train) [29][ 780/1320] lr: 2.0000e-03 eta: 3:47:14 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.5770 loss: 1.1979 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1979 2023/02/17 17:25:53 - mmengine - INFO - Epoch(train) [29][ 800/1320] lr: 2.0000e-03 eta: 3:47:04 time: 0.4786 data_time: 0.0139 memory: 27031 grad_norm: 4.5174 loss: 1.2024 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2024 2023/02/17 17:26:03 - mmengine - INFO - Epoch(train) [29][ 820/1320] lr: 2.0000e-03 eta: 3:46:55 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.5616 loss: 1.3307 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3307 2023/02/17 17:26:13 - mmengine - INFO - Epoch(train) [29][ 840/1320] lr: 2.0000e-03 eta: 3:46:45 time: 0.4810 data_time: 0.0153 memory: 27031 grad_norm: 4.4965 loss: 1.2156 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2156 2023/02/17 17:26:22 - mmengine - INFO - Epoch(train) [29][ 860/1320] lr: 2.0000e-03 eta: 3:46:35 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.4703 loss: 1.1737 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1737 2023/02/17 17:26:32 - mmengine - INFO - Epoch(train) [29][ 880/1320] lr: 2.0000e-03 eta: 3:46:26 time: 0.4813 data_time: 0.0150 memory: 27031 grad_norm: 4.5596 loss: 1.2903 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2903 2023/02/17 17:26:42 - mmengine - INFO - Epoch(train) [29][ 900/1320] lr: 2.0000e-03 eta: 3:46:16 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 4.4924 loss: 1.2071 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2071 2023/02/17 17:26:51 - mmengine - INFO - Epoch(train) [29][ 920/1320] lr: 2.0000e-03 eta: 3:46:06 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.3610 loss: 1.1927 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1927 2023/02/17 17:27:01 - mmengine - INFO - Epoch(train) [29][ 940/1320] lr: 2.0000e-03 eta: 3:45:56 time: 0.4796 data_time: 0.0146 memory: 27031 grad_norm: 4.5128 loss: 1.2397 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2397 2023/02/17 17:27:10 - mmengine - INFO - Epoch(train) [29][ 960/1320] lr: 2.0000e-03 eta: 3:45:47 time: 0.4792 data_time: 0.0139 memory: 27031 grad_norm: 4.5211 loss: 1.0624 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0624 2023/02/17 17:27:20 - mmengine - INFO - Epoch(train) [29][ 980/1320] lr: 2.0000e-03 eta: 3:45:37 time: 0.4812 data_time: 0.0158 memory: 27031 grad_norm: 4.4541 loss: 1.2423 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2423 2023/02/17 17:27:30 - mmengine - INFO - Epoch(train) [29][1000/1320] lr: 2.0000e-03 eta: 3:45:27 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.4945 loss: 1.2063 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.2063 2023/02/17 17:27:39 - mmengine - INFO - Epoch(train) [29][1020/1320] lr: 2.0000e-03 eta: 3:45:18 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.5524 loss: 1.2274 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2274 2023/02/17 17:27:49 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:27:49 - mmengine - INFO - Epoch(train) [29][1040/1320] lr: 2.0000e-03 eta: 3:45:08 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 4.5435 loss: 1.2442 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2442 2023/02/17 17:27:58 - mmengine - INFO - Epoch(train) [29][1060/1320] lr: 2.0000e-03 eta: 3:44:58 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.4581 loss: 1.2484 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.2484 2023/02/17 17:28:08 - mmengine - INFO - Epoch(train) [29][1080/1320] lr: 2.0000e-03 eta: 3:44:49 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.4255 loss: 1.1840 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1840 2023/02/17 17:28:18 - mmengine - INFO - Epoch(train) [29][1100/1320] lr: 2.0000e-03 eta: 3:44:39 time: 0.4807 data_time: 0.0141 memory: 27031 grad_norm: 4.4864 loss: 1.1228 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1228 2023/02/17 17:28:27 - mmengine - INFO - Epoch(train) [29][1120/1320] lr: 2.0000e-03 eta: 3:44:29 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 4.4873 loss: 1.0804 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0804 2023/02/17 17:28:37 - mmengine - INFO - Epoch(train) [29][1140/1320] lr: 2.0000e-03 eta: 3:44:20 time: 0.4802 data_time: 0.0152 memory: 27031 grad_norm: 4.5851 loss: 0.9356 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9356 2023/02/17 17:28:46 - mmengine - INFO - Epoch(train) [29][1160/1320] lr: 2.0000e-03 eta: 3:44:10 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 4.3932 loss: 1.2645 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2645 2023/02/17 17:28:56 - mmengine - INFO - Epoch(train) [29][1180/1320] lr: 2.0000e-03 eta: 3:44:00 time: 0.4808 data_time: 0.0155 memory: 27031 grad_norm: 4.4574 loss: 1.2023 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2023 2023/02/17 17:29:06 - mmengine - INFO - Epoch(train) [29][1200/1320] lr: 2.0000e-03 eta: 3:43:51 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 4.6928 loss: 1.2764 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2764 2023/02/17 17:29:15 - mmengine - INFO - Epoch(train) [29][1220/1320] lr: 2.0000e-03 eta: 3:43:41 time: 0.4789 data_time: 0.0137 memory: 27031 grad_norm: 4.5974 loss: 1.1365 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1365 2023/02/17 17:29:25 - mmengine - INFO - Epoch(train) [29][1240/1320] lr: 2.0000e-03 eta: 3:43:31 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 4.6602 loss: 1.1511 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1511 2023/02/17 17:29:34 - mmengine - INFO - Epoch(train) [29][1260/1320] lr: 2.0000e-03 eta: 3:43:22 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.5701 loss: 1.2234 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2234 2023/02/17 17:29:44 - mmengine - INFO - Epoch(train) [29][1280/1320] lr: 2.0000e-03 eta: 3:43:12 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 4.5683 loss: 1.1955 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1955 2023/02/17 17:29:54 - mmengine - INFO - Epoch(train) [29][1300/1320] lr: 2.0000e-03 eta: 3:43:02 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 4.4167 loss: 1.0530 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0530 2023/02/17 17:30:03 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:30:03 - mmengine - INFO - Epoch(train) [29][1320/1320] lr: 2.0000e-03 eta: 3:42:52 time: 0.4730 data_time: 0.0151 memory: 27031 grad_norm: 4.5707 loss: 1.2162 top1_acc: 0.3636 top5_acc: 0.9091 loss_cls: 1.2162 2023/02/17 17:30:07 - mmengine - INFO - Epoch(val) [29][ 20/194] eta: 0:00:32 time: 0.1856 data_time: 0.0610 memory: 3265 2023/02/17 17:30:10 - mmengine - INFO - Epoch(val) [29][ 40/194] eta: 0:00:24 time: 0.1388 data_time: 0.0149 memory: 3265 2023/02/17 17:30:12 - mmengine - INFO - Epoch(val) [29][ 60/194] eta: 0:00:20 time: 0.1390 data_time: 0.0139 memory: 3265 2023/02/17 17:30:15 - mmengine - INFO - Epoch(val) [29][ 80/194] eta: 0:00:17 time: 0.1363 data_time: 0.0128 memory: 3265 2023/02/17 17:30:18 - mmengine - INFO - Epoch(val) [29][100/194] eta: 0:00:13 time: 0.1391 data_time: 0.0144 memory: 3265 2023/02/17 17:30:21 - mmengine - INFO - Epoch(val) [29][120/194] eta: 0:00:10 time: 0.1366 data_time: 0.0127 memory: 3265 2023/02/17 17:30:23 - mmengine - INFO - Epoch(val) [29][140/194] eta: 0:00:07 time: 0.1404 data_time: 0.0148 memory: 3265 2023/02/17 17:30:26 - mmengine - INFO - Epoch(val) [29][160/194] eta: 0:00:04 time: 0.1387 data_time: 0.0136 memory: 3265 2023/02/17 17:30:29 - mmengine - INFO - Epoch(val) [29][180/194] eta: 0:00:02 time: 0.1404 data_time: 0.0136 memory: 3265 2023/02/17 17:30:32 - mmengine - INFO - Epoch(val) [29][194/194] acc/top1: 0.6096 acc/top5: 0.8669 acc/mean1: 0.5454 2023/02/17 17:30:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_28.pth is removed 2023/02/17 17:30:33 - mmengine - INFO - The best checkpoint with 0.6096 acc/top1 at 29 epoch is saved to best_acc/top1_epoch_29.pth. 2023/02/17 17:30:43 - mmengine - INFO - Epoch(train) [30][ 20/1320] lr: 2.0000e-03 eta: 3:42:43 time: 0.5309 data_time: 0.0580 memory: 27031 grad_norm: 4.4613 loss: 1.1687 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1687 2023/02/17 17:30:53 - mmengine - INFO - Epoch(train) [30][ 40/1320] lr: 2.0000e-03 eta: 3:42:34 time: 0.4796 data_time: 0.0150 memory: 27031 grad_norm: 4.6898 loss: 1.2188 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2188 2023/02/17 17:31:03 - mmengine - INFO - Epoch(train) [30][ 60/1320] lr: 2.0000e-03 eta: 3:42:24 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.5165 loss: 1.1173 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1173 2023/02/17 17:31:12 - mmengine - INFO - Epoch(train) [30][ 80/1320] lr: 2.0000e-03 eta: 3:42:14 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.4629 loss: 1.1366 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1366 2023/02/17 17:31:22 - mmengine - INFO - Epoch(train) [30][ 100/1320] lr: 2.0000e-03 eta: 3:42:05 time: 0.4810 data_time: 0.0147 memory: 27031 grad_norm: 4.6665 loss: 1.1477 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1477 2023/02/17 17:31:31 - mmengine - INFO - Epoch(train) [30][ 120/1320] lr: 2.0000e-03 eta: 3:41:55 time: 0.4786 data_time: 0.0131 memory: 27031 grad_norm: 4.4916 loss: 1.1527 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1527 2023/02/17 17:31:41 - mmengine - INFO - Epoch(train) [30][ 140/1320] lr: 2.0000e-03 eta: 3:41:45 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.5719 loss: 1.1242 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1242 2023/02/17 17:31:51 - mmengine - INFO - Epoch(train) [30][ 160/1320] lr: 2.0000e-03 eta: 3:41:36 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 4.4398 loss: 1.0577 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0577 2023/02/17 17:32:00 - mmengine - INFO - Epoch(train) [30][ 180/1320] lr: 2.0000e-03 eta: 3:41:26 time: 0.4783 data_time: 0.0137 memory: 27031 grad_norm: 4.5015 loss: 1.1921 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1921 2023/02/17 17:32:10 - mmengine - INFO - Epoch(train) [30][ 200/1320] lr: 2.0000e-03 eta: 3:41:16 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.6446 loss: 1.3246 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3246 2023/02/17 17:32:19 - mmengine - INFO - Epoch(train) [30][ 220/1320] lr: 2.0000e-03 eta: 3:41:07 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.5486 loss: 1.2418 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2418 2023/02/17 17:32:29 - mmengine - INFO - Epoch(train) [30][ 240/1320] lr: 2.0000e-03 eta: 3:40:57 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.4290 loss: 1.0343 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.0343 2023/02/17 17:32:39 - mmengine - INFO - Epoch(train) [30][ 260/1320] lr: 2.0000e-03 eta: 3:40:47 time: 0.4804 data_time: 0.0152 memory: 27031 grad_norm: 4.4204 loss: 0.9855 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9855 2023/02/17 17:32:48 - mmengine - INFO - Epoch(train) [30][ 280/1320] lr: 2.0000e-03 eta: 3:40:38 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 4.5527 loss: 1.0764 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0764 2023/02/17 17:32:58 - mmengine - INFO - Epoch(train) [30][ 300/1320] lr: 2.0000e-03 eta: 3:40:28 time: 0.4798 data_time: 0.0149 memory: 27031 grad_norm: 4.4923 loss: 1.2472 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2472 2023/02/17 17:33:07 - mmengine - INFO - Epoch(train) [30][ 320/1320] lr: 2.0000e-03 eta: 3:40:18 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 4.5888 loss: 1.0996 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0996 2023/02/17 17:33:17 - mmengine - INFO - Epoch(train) [30][ 340/1320] lr: 2.0000e-03 eta: 3:40:08 time: 0.4798 data_time: 0.0140 memory: 27031 grad_norm: 4.6974 loss: 1.0244 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0244 2023/02/17 17:33:27 - mmengine - INFO - Epoch(train) [30][ 360/1320] lr: 2.0000e-03 eta: 3:39:59 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.6921 loss: 1.0832 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0832 2023/02/17 17:33:36 - mmengine - INFO - Epoch(train) [30][ 380/1320] lr: 2.0000e-03 eta: 3:39:49 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 4.6066 loss: 1.1193 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1193 2023/02/17 17:33:46 - mmengine - INFO - Epoch(train) [30][ 400/1320] lr: 2.0000e-03 eta: 3:39:39 time: 0.4792 data_time: 0.0141 memory: 27031 grad_norm: 4.5241 loss: 1.1393 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1393 2023/02/17 17:33:55 - mmengine - INFO - Epoch(train) [30][ 420/1320] lr: 2.0000e-03 eta: 3:39:30 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.5492 loss: 1.1009 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1009 2023/02/17 17:34:05 - mmengine - INFO - Epoch(train) [30][ 440/1320] lr: 2.0000e-03 eta: 3:39:20 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 4.5988 loss: 1.1594 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1594 2023/02/17 17:34:15 - mmengine - INFO - Epoch(train) [30][ 460/1320] lr: 2.0000e-03 eta: 3:39:10 time: 0.4809 data_time: 0.0151 memory: 27031 grad_norm: 4.4999 loss: 1.0716 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0716 2023/02/17 17:34:24 - mmengine - INFO - Epoch(train) [30][ 480/1320] lr: 2.0000e-03 eta: 3:39:01 time: 0.4816 data_time: 0.0159 memory: 27031 grad_norm: 4.5821 loss: 1.1863 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1863 2023/02/17 17:34:34 - mmengine - INFO - Epoch(train) [30][ 500/1320] lr: 2.0000e-03 eta: 3:38:51 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 4.6542 loss: 1.2968 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2968 2023/02/17 17:34:44 - mmengine - INFO - Epoch(train) [30][ 520/1320] lr: 2.0000e-03 eta: 3:38:41 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.5593 loss: 0.9920 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9920 2023/02/17 17:34:53 - mmengine - INFO - Epoch(train) [30][ 540/1320] lr: 2.0000e-03 eta: 3:38:32 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.4985 loss: 0.9762 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9762 2023/02/17 17:35:03 - mmengine - INFO - Epoch(train) [30][ 560/1320] lr: 2.0000e-03 eta: 3:38:22 time: 0.4806 data_time: 0.0151 memory: 27031 grad_norm: 4.5308 loss: 1.2285 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2285 2023/02/17 17:35:12 - mmengine - INFO - Epoch(train) [30][ 580/1320] lr: 2.0000e-03 eta: 3:38:12 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.6320 loss: 1.1828 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1828 2023/02/17 17:35:22 - mmengine - INFO - Epoch(train) [30][ 600/1320] lr: 2.0000e-03 eta: 3:38:03 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 4.5862 loss: 1.1370 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1370 2023/02/17 17:35:32 - mmengine - INFO - Epoch(train) [30][ 620/1320] lr: 2.0000e-03 eta: 3:37:53 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 4.5791 loss: 1.1595 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1595 2023/02/17 17:35:41 - mmengine - INFO - Epoch(train) [30][ 640/1320] lr: 2.0000e-03 eta: 3:37:43 time: 0.4803 data_time: 0.0141 memory: 27031 grad_norm: 4.5941 loss: 1.2073 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2073 2023/02/17 17:35:51 - mmengine - INFO - Epoch(train) [30][ 660/1320] lr: 2.0000e-03 eta: 3:37:34 time: 0.4790 data_time: 0.0138 memory: 27031 grad_norm: 4.6908 loss: 1.2601 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2601 2023/02/17 17:36:00 - mmengine - INFO - Epoch(train) [30][ 680/1320] lr: 2.0000e-03 eta: 3:37:24 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 4.6772 loss: 1.0444 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0444 2023/02/17 17:36:10 - mmengine - INFO - Epoch(train) [30][ 700/1320] lr: 2.0000e-03 eta: 3:37:14 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 4.6396 loss: 1.0699 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 1.0699 2023/02/17 17:36:20 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:36:20 - mmengine - INFO - Epoch(train) [30][ 720/1320] lr: 2.0000e-03 eta: 3:37:05 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 4.6999 loss: 1.2156 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2156 2023/02/17 17:36:29 - mmengine - INFO - Epoch(train) [30][ 740/1320] lr: 2.0000e-03 eta: 3:36:55 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.5502 loss: 1.1594 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.1594 2023/02/17 17:36:39 - mmengine - INFO - Epoch(train) [30][ 760/1320] lr: 2.0000e-03 eta: 3:36:45 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 4.5902 loss: 1.2401 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2401 2023/02/17 17:36:48 - mmengine - INFO - Epoch(train) [30][ 780/1320] lr: 2.0000e-03 eta: 3:36:36 time: 0.4806 data_time: 0.0140 memory: 27031 grad_norm: 4.7145 loss: 1.0652 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0652 2023/02/17 17:36:58 - mmengine - INFO - Epoch(train) [30][ 800/1320] lr: 2.0000e-03 eta: 3:36:26 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.6547 loss: 1.2834 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2834 2023/02/17 17:37:08 - mmengine - INFO - Epoch(train) [30][ 820/1320] lr: 2.0000e-03 eta: 3:36:16 time: 0.4802 data_time: 0.0138 memory: 27031 grad_norm: 4.7466 loss: 1.2440 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.2440 2023/02/17 17:37:17 - mmengine - INFO - Epoch(train) [30][ 840/1320] lr: 2.0000e-03 eta: 3:36:06 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.6113 loss: 1.1990 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1990 2023/02/17 17:37:27 - mmengine - INFO - Epoch(train) [30][ 860/1320] lr: 2.0000e-03 eta: 3:35:57 time: 0.4791 data_time: 0.0135 memory: 27031 grad_norm: 4.6214 loss: 1.1612 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1612 2023/02/17 17:37:36 - mmengine - INFO - Epoch(train) [30][ 880/1320] lr: 2.0000e-03 eta: 3:35:47 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.6537 loss: 1.0651 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0651 2023/02/17 17:37:46 - mmengine - INFO - Epoch(train) [30][ 900/1320] lr: 2.0000e-03 eta: 3:35:37 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 4.7212 loss: 1.0782 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0782 2023/02/17 17:37:56 - mmengine - INFO - Epoch(train) [30][ 920/1320] lr: 2.0000e-03 eta: 3:35:28 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 4.5958 loss: 1.2590 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2590 2023/02/17 17:38:05 - mmengine - INFO - Epoch(train) [30][ 940/1320] lr: 2.0000e-03 eta: 3:35:18 time: 0.4813 data_time: 0.0152 memory: 27031 grad_norm: 4.7096 loss: 1.1854 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1854 2023/02/17 17:38:15 - mmengine - INFO - Epoch(train) [30][ 960/1320] lr: 2.0000e-03 eta: 3:35:08 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.5713 loss: 1.0719 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.0719 2023/02/17 17:38:24 - mmengine - INFO - Epoch(train) [30][ 980/1320] lr: 2.0000e-03 eta: 3:34:59 time: 0.4826 data_time: 0.0168 memory: 27031 grad_norm: 4.6862 loss: 1.1627 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1627 2023/02/17 17:38:34 - mmengine - INFO - Epoch(train) [30][1000/1320] lr: 2.0000e-03 eta: 3:34:49 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 4.6116 loss: 1.1360 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1360 2023/02/17 17:38:44 - mmengine - INFO - Epoch(train) [30][1020/1320] lr: 2.0000e-03 eta: 3:34:39 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.6764 loss: 1.0755 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0755 2023/02/17 17:38:53 - mmengine - INFO - Epoch(train) [30][1040/1320] lr: 2.0000e-03 eta: 3:34:30 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.5843 loss: 1.1519 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.1519 2023/02/17 17:39:03 - mmengine - INFO - Epoch(train) [30][1060/1320] lr: 2.0000e-03 eta: 3:34:20 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 4.5285 loss: 1.0369 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0369 2023/02/17 17:39:13 - mmengine - INFO - Epoch(train) [30][1080/1320] lr: 2.0000e-03 eta: 3:34:10 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.6760 loss: 1.0946 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0946 2023/02/17 17:39:22 - mmengine - INFO - Epoch(train) [30][1100/1320] lr: 2.0000e-03 eta: 3:34:01 time: 0.4807 data_time: 0.0150 memory: 27031 grad_norm: 4.6945 loss: 1.2292 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2292 2023/02/17 17:39:32 - mmengine - INFO - Epoch(train) [30][1120/1320] lr: 2.0000e-03 eta: 3:33:51 time: 0.4825 data_time: 0.0171 memory: 27031 grad_norm: 4.6837 loss: 1.2403 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2403 2023/02/17 17:39:41 - mmengine - INFO - Epoch(train) [30][1140/1320] lr: 2.0000e-03 eta: 3:33:41 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 4.6937 loss: 1.2857 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2857 2023/02/17 17:39:51 - mmengine - INFO - Epoch(train) [30][1160/1320] lr: 2.0000e-03 eta: 3:33:32 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 4.7215 loss: 1.0705 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0705 2023/02/17 17:40:01 - mmengine - INFO - Epoch(train) [30][1180/1320] lr: 2.0000e-03 eta: 3:33:22 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.6144 loss: 1.0408 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0408 2023/02/17 17:40:10 - mmengine - INFO - Epoch(train) [30][1200/1320] lr: 2.0000e-03 eta: 3:33:12 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.6068 loss: 1.1020 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1020 2023/02/17 17:40:20 - mmengine - INFO - Epoch(train) [30][1220/1320] lr: 2.0000e-03 eta: 3:33:03 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 4.5714 loss: 1.1558 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1558 2023/02/17 17:40:29 - mmengine - INFO - Epoch(train) [30][1240/1320] lr: 2.0000e-03 eta: 3:32:53 time: 0.4822 data_time: 0.0165 memory: 27031 grad_norm: 4.6420 loss: 1.1914 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1914 2023/02/17 17:40:39 - mmengine - INFO - Epoch(train) [30][1260/1320] lr: 2.0000e-03 eta: 3:32:43 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 4.5872 loss: 1.1207 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1207 2023/02/17 17:40:49 - mmengine - INFO - Epoch(train) [30][1280/1320] lr: 2.0000e-03 eta: 3:32:34 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 4.6818 loss: 1.2682 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.2682 2023/02/17 17:40:58 - mmengine - INFO - Epoch(train) [30][1300/1320] lr: 2.0000e-03 eta: 3:32:24 time: 0.4795 data_time: 0.0136 memory: 27031 grad_norm: 4.6584 loss: 1.1576 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.1576 2023/02/17 17:41:08 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:41:08 - mmengine - INFO - Epoch(train) [30][1320/1320] lr: 2.0000e-03 eta: 3:32:14 time: 0.4754 data_time: 0.0159 memory: 27031 grad_norm: 4.7357 loss: 1.2580 top1_acc: 0.5455 top5_acc: 0.8182 loss_cls: 1.2580 2023/02/17 17:41:08 - mmengine - INFO - Saving checkpoint at 30 epochs 2023/02/17 17:41:13 - mmengine - INFO - Epoch(val) [30][ 20/194] eta: 0:00:32 time: 0.1840 data_time: 0.0572 memory: 3265 2023/02/17 17:41:16 - mmengine - INFO - Epoch(val) [30][ 40/194] eta: 0:00:24 time: 0.1387 data_time: 0.0141 memory: 3265 2023/02/17 17:41:18 - mmengine - INFO - Epoch(val) [30][ 60/194] eta: 0:00:20 time: 0.1397 data_time: 0.0143 memory: 3265 2023/02/17 17:41:21 - mmengine - INFO - Epoch(val) [30][ 80/194] eta: 0:00:17 time: 0.1377 data_time: 0.0133 memory: 3265 2023/02/17 17:41:24 - mmengine - INFO - Epoch(val) [30][100/194] eta: 0:00:13 time: 0.1366 data_time: 0.0126 memory: 3265 2023/02/17 17:41:27 - mmengine - INFO - Epoch(val) [30][120/194] eta: 0:00:10 time: 0.1390 data_time: 0.0138 memory: 3265 2023/02/17 17:41:29 - mmengine - INFO - Epoch(val) [30][140/194] eta: 0:00:07 time: 0.1375 data_time: 0.0134 memory: 3265 2023/02/17 17:41:32 - mmengine - INFO - Epoch(val) [30][160/194] eta: 0:00:04 time: 0.1387 data_time: 0.0139 memory: 3265 2023/02/17 17:41:35 - mmengine - INFO - Epoch(val) [30][180/194] eta: 0:00:02 time: 0.1362 data_time: 0.0123 memory: 3265 2023/02/17 17:41:38 - mmengine - INFO - Epoch(val) [30][194/194] acc/top1: 0.6134 acc/top5: 0.8699 acc/mean1: 0.5460 2023/02/17 17:41:38 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_29.pth is removed 2023/02/17 17:41:39 - mmengine - INFO - The best checkpoint with 0.6134 acc/top1 at 30 epoch is saved to best_acc/top1_epoch_30.pth. 2023/02/17 17:41:49 - mmengine - INFO - Epoch(train) [31][ 20/1320] lr: 2.0000e-03 eta: 3:32:05 time: 0.5290 data_time: 0.0570 memory: 27031 grad_norm: 4.5797 loss: 1.0146 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0146 2023/02/17 17:41:59 - mmengine - INFO - Epoch(train) [31][ 40/1320] lr: 2.0000e-03 eta: 3:31:56 time: 0.4804 data_time: 0.0152 memory: 27031 grad_norm: 4.5199 loss: 0.9876 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9876 2023/02/17 17:42:08 - mmengine - INFO - Epoch(train) [31][ 60/1320] lr: 2.0000e-03 eta: 3:31:46 time: 0.4808 data_time: 0.0154 memory: 27031 grad_norm: 4.5920 loss: 1.1478 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1478 2023/02/17 17:42:18 - mmengine - INFO - Epoch(train) [31][ 80/1320] lr: 2.0000e-03 eta: 3:31:36 time: 0.4804 data_time: 0.0153 memory: 27031 grad_norm: 4.6103 loss: 1.1439 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1439 2023/02/17 17:42:28 - mmengine - INFO - Epoch(train) [31][ 100/1320] lr: 2.0000e-03 eta: 3:31:27 time: 0.4819 data_time: 0.0159 memory: 27031 grad_norm: 4.5280 loss: 1.2830 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2830 2023/02/17 17:42:37 - mmengine - INFO - Epoch(train) [31][ 120/1320] lr: 2.0000e-03 eta: 3:31:17 time: 0.4813 data_time: 0.0162 memory: 27031 grad_norm: 4.6206 loss: 1.0979 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0979 2023/02/17 17:42:47 - mmengine - INFO - Epoch(train) [31][ 140/1320] lr: 2.0000e-03 eta: 3:31:07 time: 0.4810 data_time: 0.0153 memory: 27031 grad_norm: 4.6120 loss: 1.0045 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0045 2023/02/17 17:42:57 - mmengine - INFO - Epoch(train) [31][ 160/1320] lr: 2.0000e-03 eta: 3:30:58 time: 0.4814 data_time: 0.0163 memory: 27031 grad_norm: 4.5558 loss: 0.9673 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9673 2023/02/17 17:43:06 - mmengine - INFO - Epoch(train) [31][ 180/1320] lr: 2.0000e-03 eta: 3:30:48 time: 0.4818 data_time: 0.0157 memory: 27031 grad_norm: 4.5382 loss: 1.1071 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1071 2023/02/17 17:43:16 - mmengine - INFO - Epoch(train) [31][ 200/1320] lr: 2.0000e-03 eta: 3:30:38 time: 0.4814 data_time: 0.0158 memory: 27031 grad_norm: 4.8906 loss: 1.0878 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0878 2023/02/17 17:43:25 - mmengine - INFO - Epoch(train) [31][ 220/1320] lr: 2.0000e-03 eta: 3:30:29 time: 0.4818 data_time: 0.0160 memory: 27031 grad_norm: 4.6990 loss: 1.2794 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2794 2023/02/17 17:43:35 - mmengine - INFO - Epoch(train) [31][ 240/1320] lr: 2.0000e-03 eta: 3:30:19 time: 0.4813 data_time: 0.0160 memory: 27031 grad_norm: 4.7143 loss: 1.1882 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1882 2023/02/17 17:43:45 - mmengine - INFO - Epoch(train) [31][ 260/1320] lr: 2.0000e-03 eta: 3:30:09 time: 0.4815 data_time: 0.0161 memory: 27031 grad_norm: 4.6237 loss: 1.1407 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1407 2023/02/17 17:43:54 - mmengine - INFO - Epoch(train) [31][ 280/1320] lr: 2.0000e-03 eta: 3:30:00 time: 0.4811 data_time: 0.0158 memory: 27031 grad_norm: 4.7169 loss: 1.2288 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2288 2023/02/17 17:44:04 - mmengine - INFO - Epoch(train) [31][ 300/1320] lr: 2.0000e-03 eta: 3:29:50 time: 0.4812 data_time: 0.0154 memory: 27031 grad_norm: 4.7506 loss: 1.2594 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2594 2023/02/17 17:44:14 - mmengine - INFO - Epoch(train) [31][ 320/1320] lr: 2.0000e-03 eta: 3:29:40 time: 0.4811 data_time: 0.0160 memory: 27031 grad_norm: 4.6096 loss: 0.9709 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9709 2023/02/17 17:44:23 - mmengine - INFO - Epoch(train) [31][ 340/1320] lr: 2.0000e-03 eta: 3:29:31 time: 0.4827 data_time: 0.0173 memory: 27031 grad_norm: 4.6921 loss: 1.1049 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1049 2023/02/17 17:44:33 - mmengine - INFO - Epoch(train) [31][ 360/1320] lr: 2.0000e-03 eta: 3:29:21 time: 0.4821 data_time: 0.0160 memory: 27031 grad_norm: 4.7148 loss: 1.0373 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0373 2023/02/17 17:44:43 - mmengine - INFO - Epoch(train) [31][ 380/1320] lr: 2.0000e-03 eta: 3:29:11 time: 0.4814 data_time: 0.0156 memory: 27031 grad_norm: 4.7070 loss: 1.0426 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0426 2023/02/17 17:44:52 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:44:52 - mmengine - INFO - Epoch(train) [31][ 400/1320] lr: 2.0000e-03 eta: 3:29:02 time: 0.4821 data_time: 0.0159 memory: 27031 grad_norm: 4.8442 loss: 1.1581 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1581 2023/02/17 17:45:02 - mmengine - INFO - Epoch(train) [31][ 420/1320] lr: 2.0000e-03 eta: 3:28:52 time: 0.4821 data_time: 0.0167 memory: 27031 grad_norm: 4.6081 loss: 1.1177 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1177 2023/02/17 17:45:11 - mmengine - INFO - Epoch(train) [31][ 440/1320] lr: 2.0000e-03 eta: 3:28:42 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 4.7646 loss: 1.1507 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1507 2023/02/17 17:45:21 - mmengine - INFO - Epoch(train) [31][ 460/1320] lr: 2.0000e-03 eta: 3:28:33 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 4.7492 loss: 1.1509 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1509 2023/02/17 17:45:31 - mmengine - INFO - Epoch(train) [31][ 480/1320] lr: 2.0000e-03 eta: 3:28:23 time: 0.4795 data_time: 0.0136 memory: 27031 grad_norm: 4.8324 loss: 0.9904 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9904 2023/02/17 17:45:40 - mmengine - INFO - Epoch(train) [31][ 500/1320] lr: 2.0000e-03 eta: 3:28:13 time: 0.4794 data_time: 0.0127 memory: 27031 grad_norm: 4.9016 loss: 1.1231 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1231 2023/02/17 17:45:50 - mmengine - INFO - Epoch(train) [31][ 520/1320] lr: 2.0000e-03 eta: 3:28:04 time: 0.4800 data_time: 0.0138 memory: 27031 grad_norm: 4.7727 loss: 1.0769 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0769 2023/02/17 17:45:59 - mmengine - INFO - Epoch(train) [31][ 540/1320] lr: 2.0000e-03 eta: 3:27:54 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 4.7386 loss: 1.2158 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2158 2023/02/17 17:46:09 - mmengine - INFO - Epoch(train) [31][ 560/1320] lr: 2.0000e-03 eta: 3:27:44 time: 0.4792 data_time: 0.0135 memory: 27031 grad_norm: 4.7332 loss: 1.2148 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2148 2023/02/17 17:46:19 - mmengine - INFO - Epoch(train) [31][ 580/1320] lr: 2.0000e-03 eta: 3:27:35 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 4.8468 loss: 1.0251 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0251 2023/02/17 17:46:28 - mmengine - INFO - Epoch(train) [31][ 600/1320] lr: 2.0000e-03 eta: 3:27:25 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 4.7746 loss: 1.0351 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 1.0351 2023/02/17 17:46:38 - mmengine - INFO - Epoch(train) [31][ 620/1320] lr: 2.0000e-03 eta: 3:27:15 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.7960 loss: 1.1947 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1947 2023/02/17 17:46:47 - mmengine - INFO - Epoch(train) [31][ 640/1320] lr: 2.0000e-03 eta: 3:27:06 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 4.7224 loss: 1.0870 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0870 2023/02/17 17:46:57 - mmengine - INFO - Epoch(train) [31][ 660/1320] lr: 2.0000e-03 eta: 3:26:56 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 4.6909 loss: 0.9851 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.9851 2023/02/17 17:47:07 - mmengine - INFO - Epoch(train) [31][ 680/1320] lr: 2.0000e-03 eta: 3:26:46 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 4.6690 loss: 1.1768 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1768 2023/02/17 17:47:16 - mmengine - INFO - Epoch(train) [31][ 700/1320] lr: 2.0000e-03 eta: 3:26:36 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 4.7663 loss: 1.0711 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0711 2023/02/17 17:47:26 - mmengine - INFO - Epoch(train) [31][ 720/1320] lr: 2.0000e-03 eta: 3:26:27 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 4.9832 loss: 1.2284 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2284 2023/02/17 17:47:35 - mmengine - INFO - Epoch(train) [31][ 740/1320] lr: 2.0000e-03 eta: 3:26:17 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.8018 loss: 1.1524 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1524 2023/02/17 17:47:45 - mmengine - INFO - Epoch(train) [31][ 760/1320] lr: 2.0000e-03 eta: 3:26:07 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.9260 loss: 1.2402 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2402 2023/02/17 17:47:55 - mmengine - INFO - Epoch(train) [31][ 780/1320] lr: 2.0000e-03 eta: 3:25:58 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 4.7941 loss: 1.0554 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0554 2023/02/17 17:48:04 - mmengine - INFO - Epoch(train) [31][ 800/1320] lr: 2.0000e-03 eta: 3:25:48 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 4.9326 loss: 1.1826 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1826 2023/02/17 17:48:14 - mmengine - INFO - Epoch(train) [31][ 820/1320] lr: 2.0000e-03 eta: 3:25:38 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.8978 loss: 1.1294 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1294 2023/02/17 17:48:23 - mmengine - INFO - Epoch(train) [31][ 840/1320] lr: 2.0000e-03 eta: 3:25:29 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 4.7256 loss: 1.0635 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0635 2023/02/17 17:48:33 - mmengine - INFO - Epoch(train) [31][ 860/1320] lr: 2.0000e-03 eta: 3:25:19 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 4.8820 loss: 1.0662 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0662 2023/02/17 17:48:43 - mmengine - INFO - Epoch(train) [31][ 880/1320] lr: 2.0000e-03 eta: 3:25:09 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.8919 loss: 1.2013 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2013 2023/02/17 17:48:52 - mmengine - INFO - Epoch(train) [31][ 900/1320] lr: 2.0000e-03 eta: 3:25:00 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 4.6497 loss: 0.9577 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9577 2023/02/17 17:49:02 - mmengine - INFO - Epoch(train) [31][ 920/1320] lr: 2.0000e-03 eta: 3:24:50 time: 0.4808 data_time: 0.0141 memory: 27031 grad_norm: 4.9041 loss: 1.0528 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0528 2023/02/17 17:49:12 - mmengine - INFO - Epoch(train) [31][ 940/1320] lr: 2.0000e-03 eta: 3:24:40 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 4.6358 loss: 1.1916 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1916 2023/02/17 17:49:21 - mmengine - INFO - Epoch(train) [31][ 960/1320] lr: 2.0000e-03 eta: 3:24:31 time: 0.4811 data_time: 0.0150 memory: 27031 grad_norm: 4.7968 loss: 1.2008 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.2008 2023/02/17 17:49:31 - mmengine - INFO - Epoch(train) [31][ 980/1320] lr: 2.0000e-03 eta: 3:24:21 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.7477 loss: 1.0852 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0852 2023/02/17 17:49:40 - mmengine - INFO - Epoch(train) [31][1000/1320] lr: 2.0000e-03 eta: 3:24:11 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 4.7828 loss: 1.1142 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.1142 2023/02/17 17:49:50 - mmengine - INFO - Epoch(train) [31][1020/1320] lr: 2.0000e-03 eta: 3:24:02 time: 0.4816 data_time: 0.0160 memory: 27031 grad_norm: 4.8755 loss: 0.9861 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9861 2023/02/17 17:50:00 - mmengine - INFO - Epoch(train) [31][1040/1320] lr: 2.0000e-03 eta: 3:23:52 time: 0.4792 data_time: 0.0136 memory: 27031 grad_norm: 4.8180 loss: 1.1573 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1573 2023/02/17 17:50:09 - mmengine - INFO - Epoch(train) [31][1060/1320] lr: 2.0000e-03 eta: 3:23:42 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 4.8227 loss: 1.1853 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1853 2023/02/17 17:50:19 - mmengine - INFO - Epoch(train) [31][1080/1320] lr: 2.0000e-03 eta: 3:23:33 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 4.9143 loss: 1.2179 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.2179 2023/02/17 17:50:28 - mmengine - INFO - Epoch(train) [31][1100/1320] lr: 2.0000e-03 eta: 3:23:23 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 4.8190 loss: 1.0064 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0064 2023/02/17 17:50:38 - mmengine - INFO - Epoch(train) [31][1120/1320] lr: 2.0000e-03 eta: 3:23:13 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 4.9103 loss: 1.1607 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1607 2023/02/17 17:50:48 - mmengine - INFO - Epoch(train) [31][1140/1320] lr: 2.0000e-03 eta: 3:23:04 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 4.9023 loss: 1.1089 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1089 2023/02/17 17:50:57 - mmengine - INFO - Epoch(train) [31][1160/1320] lr: 2.0000e-03 eta: 3:22:54 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.8604 loss: 1.0432 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0432 2023/02/17 17:51:07 - mmengine - INFO - Epoch(train) [31][1180/1320] lr: 2.0000e-03 eta: 3:22:44 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 4.8831 loss: 1.1234 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1234 2023/02/17 17:51:16 - mmengine - INFO - Epoch(train) [31][1200/1320] lr: 2.0000e-03 eta: 3:22:35 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 4.9192 loss: 1.1635 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1635 2023/02/17 17:51:26 - mmengine - INFO - Epoch(train) [31][1220/1320] lr: 2.0000e-03 eta: 3:22:25 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.7844 loss: 1.0564 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0564 2023/02/17 17:51:36 - mmengine - INFO - Epoch(train) [31][1240/1320] lr: 2.0000e-03 eta: 3:22:15 time: 0.4815 data_time: 0.0166 memory: 27031 grad_norm: 4.9609 loss: 0.9690 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9690 2023/02/17 17:51:45 - mmengine - INFO - Epoch(train) [31][1260/1320] lr: 2.0000e-03 eta: 3:22:06 time: 0.4794 data_time: 0.0138 memory: 27031 grad_norm: 4.8052 loss: 1.2150 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2150 2023/02/17 17:51:55 - mmengine - INFO - Epoch(train) [31][1280/1320] lr: 2.0000e-03 eta: 3:21:56 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 4.8009 loss: 1.0880 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0880 2023/02/17 17:52:04 - mmengine - INFO - Epoch(train) [31][1300/1320] lr: 2.0000e-03 eta: 3:21:46 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 4.7859 loss: 1.0290 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0290 2023/02/17 17:52:14 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:52:14 - mmengine - INFO - Epoch(train) [31][1320/1320] lr: 2.0000e-03 eta: 3:21:37 time: 0.4741 data_time: 0.0154 memory: 27031 grad_norm: 4.9932 loss: 1.2472 top1_acc: 0.6364 top5_acc: 0.8182 loss_cls: 1.2472 2023/02/17 17:52:18 - mmengine - INFO - Epoch(val) [31][ 20/194] eta: 0:00:32 time: 0.1844 data_time: 0.0584 memory: 3265 2023/02/17 17:52:20 - mmengine - INFO - Epoch(val) [31][ 40/194] eta: 0:00:24 time: 0.1375 data_time: 0.0130 memory: 3265 2023/02/17 17:52:23 - mmengine - INFO - Epoch(val) [31][ 60/194] eta: 0:00:20 time: 0.1377 data_time: 0.0134 memory: 3265 2023/02/17 17:52:26 - mmengine - INFO - Epoch(val) [31][ 80/194] eta: 0:00:16 time: 0.1369 data_time: 0.0133 memory: 3265 2023/02/17 17:52:29 - mmengine - INFO - Epoch(val) [31][100/194] eta: 0:00:13 time: 0.1377 data_time: 0.0134 memory: 3265 2023/02/17 17:52:31 - mmengine - INFO - Epoch(val) [31][120/194] eta: 0:00:10 time: 0.1381 data_time: 0.0133 memory: 3265 2023/02/17 17:52:34 - mmengine - INFO - Epoch(val) [31][140/194] eta: 0:00:07 time: 0.1362 data_time: 0.0127 memory: 3265 2023/02/17 17:52:37 - mmengine - INFO - Epoch(val) [31][160/194] eta: 0:00:04 time: 0.1375 data_time: 0.0131 memory: 3265 2023/02/17 17:52:40 - mmengine - INFO - Epoch(val) [31][180/194] eta: 0:00:01 time: 0.1359 data_time: 0.0127 memory: 3265 2023/02/17 17:52:43 - mmengine - INFO - Epoch(val) [31][194/194] acc/top1: 0.6167 acc/top5: 0.8702 acc/mean1: 0.5511 2023/02/17 17:52:43 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_30.pth is removed 2023/02/17 17:52:44 - mmengine - INFO - The best checkpoint with 0.6167 acc/top1 at 31 epoch is saved to best_acc/top1_epoch_31.pth. 2023/02/17 17:52:54 - mmengine - INFO - Epoch(train) [32][ 20/1320] lr: 2.0000e-03 eta: 3:21:27 time: 0.5245 data_time: 0.0543 memory: 27031 grad_norm: 4.8035 loss: 1.2836 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2836 2023/02/17 17:53:04 - mmengine - INFO - Epoch(train) [32][ 40/1320] lr: 2.0000e-03 eta: 3:21:18 time: 0.4821 data_time: 0.0144 memory: 27031 grad_norm: 4.8438 loss: 1.1784 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1784 2023/02/17 17:53:14 - mmengine - INFO - Epoch(train) [32][ 60/1320] lr: 2.0000e-03 eta: 3:21:08 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 4.7485 loss: 1.2458 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.2458 2023/02/17 17:53:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 17:53:23 - mmengine - INFO - Epoch(train) [32][ 80/1320] lr: 2.0000e-03 eta: 3:20:58 time: 0.4817 data_time: 0.0146 memory: 27031 grad_norm: 4.8869 loss: 1.0655 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0655 2023/02/17 17:53:33 - mmengine - INFO - Epoch(train) [32][ 100/1320] lr: 2.0000e-03 eta: 3:20:49 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 4.7395 loss: 1.0433 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.0433 2023/02/17 17:53:43 - mmengine - INFO - Epoch(train) [32][ 120/1320] lr: 2.0000e-03 eta: 3:20:39 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.7324 loss: 1.1159 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1159 2023/02/17 17:53:52 - mmengine - INFO - Epoch(train) [32][ 140/1320] lr: 2.0000e-03 eta: 3:20:29 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 4.8157 loss: 1.1474 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1474 2023/02/17 17:54:02 - mmengine - INFO - Epoch(train) [32][ 160/1320] lr: 2.0000e-03 eta: 3:20:20 time: 0.4819 data_time: 0.0159 memory: 27031 grad_norm: 4.7585 loss: 1.0164 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0164 2023/02/17 17:54:11 - mmengine - INFO - Epoch(train) [32][ 180/1320] lr: 2.0000e-03 eta: 3:20:10 time: 0.4803 data_time: 0.0148 memory: 27031 grad_norm: 4.9118 loss: 1.0504 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0504 2023/02/17 17:54:21 - mmengine - INFO - Epoch(train) [32][ 200/1320] lr: 2.0000e-03 eta: 3:20:00 time: 0.4791 data_time: 0.0129 memory: 27031 grad_norm: 4.8041 loss: 1.0998 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0998 2023/02/17 17:54:31 - mmengine - INFO - Epoch(train) [32][ 220/1320] lr: 2.0000e-03 eta: 3:19:51 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.8138 loss: 1.1284 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1284 2023/02/17 17:54:40 - mmengine - INFO - Epoch(train) [32][ 240/1320] lr: 2.0000e-03 eta: 3:19:41 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 4.8644 loss: 1.1415 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1415 2023/02/17 17:54:50 - mmengine - INFO - Epoch(train) [32][ 260/1320] lr: 2.0000e-03 eta: 3:19:31 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 4.9007 loss: 1.1477 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1477 2023/02/17 17:54:59 - mmengine - INFO - Epoch(train) [32][ 280/1320] lr: 2.0000e-03 eta: 3:19:22 time: 0.4817 data_time: 0.0157 memory: 27031 grad_norm: 4.8545 loss: 1.2699 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2699 2023/02/17 17:55:09 - mmengine - INFO - Epoch(train) [32][ 300/1320] lr: 2.0000e-03 eta: 3:19:12 time: 0.4793 data_time: 0.0140 memory: 27031 grad_norm: 4.9250 loss: 0.9504 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9504 2023/02/17 17:55:19 - mmengine - INFO - Epoch(train) [32][ 320/1320] lr: 2.0000e-03 eta: 3:19:02 time: 0.4791 data_time: 0.0141 memory: 27031 grad_norm: 4.9439 loss: 1.1662 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1662 2023/02/17 17:55:28 - mmengine - INFO - Epoch(train) [32][ 340/1320] lr: 2.0000e-03 eta: 3:18:53 time: 0.4796 data_time: 0.0148 memory: 27031 grad_norm: 4.9459 loss: 1.0866 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0866 2023/02/17 17:55:38 - mmengine - INFO - Epoch(train) [32][ 360/1320] lr: 2.0000e-03 eta: 3:18:43 time: 0.4789 data_time: 0.0133 memory: 27031 grad_norm: 4.8989 loss: 1.1125 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1125 2023/02/17 17:55:47 - mmengine - INFO - Epoch(train) [32][ 380/1320] lr: 2.0000e-03 eta: 3:18:33 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 4.8642 loss: 1.2007 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2007 2023/02/17 17:55:57 - mmengine - INFO - Epoch(train) [32][ 400/1320] lr: 2.0000e-03 eta: 3:18:24 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.8931 loss: 1.2015 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2015 2023/02/17 17:56:07 - mmengine - INFO - Epoch(train) [32][ 420/1320] lr: 2.0000e-03 eta: 3:18:14 time: 0.4795 data_time: 0.0141 memory: 27031 grad_norm: 4.8640 loss: 1.2353 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2353 2023/02/17 17:56:16 - mmengine - INFO - Epoch(train) [32][ 440/1320] lr: 2.0000e-03 eta: 3:18:04 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 4.9286 loss: 1.0377 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0377 2023/02/17 17:56:26 - mmengine - INFO - Epoch(train) [32][ 460/1320] lr: 2.0000e-03 eta: 3:17:55 time: 0.4795 data_time: 0.0146 memory: 27031 grad_norm: 4.8924 loss: 0.9828 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9828 2023/02/17 17:56:35 - mmengine - INFO - Epoch(train) [32][ 480/1320] lr: 2.0000e-03 eta: 3:17:45 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 4.9305 loss: 1.2391 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2391 2023/02/17 17:56:45 - mmengine - INFO - Epoch(train) [32][ 500/1320] lr: 2.0000e-03 eta: 3:17:35 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 4.8952 loss: 1.1725 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1725 2023/02/17 17:56:55 - mmengine - INFO - Epoch(train) [32][ 520/1320] lr: 2.0000e-03 eta: 3:17:26 time: 0.4795 data_time: 0.0134 memory: 27031 grad_norm: 4.8973 loss: 1.2471 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2471 2023/02/17 17:57:04 - mmengine - INFO - Epoch(train) [32][ 540/1320] lr: 2.0000e-03 eta: 3:17:16 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 4.8229 loss: 1.0770 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0770 2023/02/17 17:57:14 - mmengine - INFO - Epoch(train) [32][ 560/1320] lr: 2.0000e-03 eta: 3:17:06 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 4.9549 loss: 1.1369 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1369 2023/02/17 17:57:23 - mmengine - INFO - Epoch(train) [32][ 580/1320] lr: 2.0000e-03 eta: 3:16:57 time: 0.4791 data_time: 0.0142 memory: 27031 grad_norm: 4.9138 loss: 1.1002 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1002 2023/02/17 17:57:33 - mmengine - INFO - Epoch(train) [32][ 600/1320] lr: 2.0000e-03 eta: 3:16:47 time: 0.4800 data_time: 0.0151 memory: 27031 grad_norm: 4.8228 loss: 1.1096 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 1.1096 2023/02/17 17:57:43 - mmengine - INFO - Epoch(train) [32][ 620/1320] lr: 2.0000e-03 eta: 3:16:37 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 4.8088 loss: 1.0590 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0590 2023/02/17 17:57:52 - mmengine - INFO - Epoch(train) [32][ 640/1320] lr: 2.0000e-03 eta: 3:16:28 time: 0.4801 data_time: 0.0148 memory: 27031 grad_norm: 4.7500 loss: 1.0359 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0359 2023/02/17 17:58:02 - mmengine - INFO - Epoch(train) [32][ 660/1320] lr: 2.0000e-03 eta: 3:16:18 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 4.9430 loss: 1.1524 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1524 2023/02/17 17:58:11 - mmengine - INFO - Epoch(train) [32][ 680/1320] lr: 2.0000e-03 eta: 3:16:08 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 4.8756 loss: 1.0799 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0799 2023/02/17 17:58:21 - mmengine - INFO - Epoch(train) [32][ 700/1320] lr: 2.0000e-03 eta: 3:15:59 time: 0.4798 data_time: 0.0147 memory: 27031 grad_norm: 4.9774 loss: 1.0317 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0317 2023/02/17 17:58:31 - mmengine - INFO - Epoch(train) [32][ 720/1320] lr: 2.0000e-03 eta: 3:15:49 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 5.0355 loss: 1.0835 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0835 2023/02/17 17:58:40 - mmengine - INFO - Epoch(train) [32][ 740/1320] lr: 2.0000e-03 eta: 3:15:39 time: 0.4799 data_time: 0.0136 memory: 27031 grad_norm: 5.1147 loss: 1.2367 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2367 2023/02/17 17:58:50 - mmengine - INFO - Epoch(train) [32][ 760/1320] lr: 2.0000e-03 eta: 3:15:29 time: 0.4800 data_time: 0.0148 memory: 27031 grad_norm: 4.8302 loss: 1.0184 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0184 2023/02/17 17:58:59 - mmengine - INFO - Epoch(train) [32][ 780/1320] lr: 2.0000e-03 eta: 3:15:20 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 4.8644 loss: 1.0023 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0023 2023/02/17 17:59:09 - mmengine - INFO - Epoch(train) [32][ 800/1320] lr: 2.0000e-03 eta: 3:15:10 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 4.9372 loss: 0.9244 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9244 2023/02/17 17:59:19 - mmengine - INFO - Epoch(train) [32][ 820/1320] lr: 2.0000e-03 eta: 3:15:00 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 4.8992 loss: 1.0050 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0050 2023/02/17 17:59:28 - mmengine - INFO - Epoch(train) [32][ 840/1320] lr: 2.0000e-03 eta: 3:14:51 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 5.0943 loss: 1.1710 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.1710 2023/02/17 17:59:38 - mmengine - INFO - Epoch(train) [32][ 860/1320] lr: 2.0000e-03 eta: 3:14:41 time: 0.4812 data_time: 0.0143 memory: 27031 grad_norm: 4.7996 loss: 0.9903 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9903 2023/02/17 17:59:48 - mmengine - INFO - Epoch(train) [32][ 880/1320] lr: 2.0000e-03 eta: 3:14:31 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 4.9684 loss: 1.1225 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1225 2023/02/17 17:59:57 - mmengine - INFO - Epoch(train) [32][ 900/1320] lr: 2.0000e-03 eta: 3:14:22 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 5.0182 loss: 1.1854 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1854 2023/02/17 18:00:07 - mmengine - INFO - Epoch(train) [32][ 920/1320] lr: 2.0000e-03 eta: 3:14:12 time: 0.4815 data_time: 0.0159 memory: 27031 grad_norm: 4.9233 loss: 1.0116 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0116 2023/02/17 18:00:16 - mmengine - INFO - Epoch(train) [32][ 940/1320] lr: 2.0000e-03 eta: 3:14:02 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 5.0200 loss: 1.0884 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0884 2023/02/17 18:00:26 - mmengine - INFO - Epoch(train) [32][ 960/1320] lr: 2.0000e-03 eta: 3:13:53 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 5.0303 loss: 1.0209 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.0209 2023/02/17 18:00:36 - mmengine - INFO - Epoch(train) [32][ 980/1320] lr: 2.0000e-03 eta: 3:13:43 time: 0.4800 data_time: 0.0151 memory: 27031 grad_norm: 5.0685 loss: 0.9912 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9912 2023/02/17 18:00:45 - mmengine - INFO - Epoch(train) [32][1000/1320] lr: 2.0000e-03 eta: 3:13:33 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 5.1090 loss: 1.0449 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0449 2023/02/17 18:00:55 - mmengine - INFO - Epoch(train) [32][1020/1320] lr: 2.0000e-03 eta: 3:13:24 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 5.0338 loss: 1.0681 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.0681 2023/02/17 18:01:04 - mmengine - INFO - Epoch(train) [32][1040/1320] lr: 2.0000e-03 eta: 3:13:14 time: 0.4816 data_time: 0.0161 memory: 27031 grad_norm: 4.9548 loss: 1.1839 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1839 2023/02/17 18:01:14 - mmengine - INFO - Epoch(train) [32][1060/1320] lr: 2.0000e-03 eta: 3:13:04 time: 0.4794 data_time: 0.0138 memory: 27031 grad_norm: 4.9700 loss: 1.2139 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2139 2023/02/17 18:01:24 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:01:24 - mmengine - INFO - Epoch(train) [32][1080/1320] lr: 2.0000e-03 eta: 3:12:55 time: 0.4812 data_time: 0.0152 memory: 27031 grad_norm: 4.8804 loss: 0.9829 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9829 2023/02/17 18:01:33 - mmengine - INFO - Epoch(train) [32][1100/1320] lr: 2.0000e-03 eta: 3:12:45 time: 0.4807 data_time: 0.0142 memory: 27031 grad_norm: 4.8949 loss: 1.0923 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0923 2023/02/17 18:01:43 - mmengine - INFO - Epoch(train) [32][1120/1320] lr: 2.0000e-03 eta: 3:12:35 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 4.9644 loss: 1.2100 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2100 2023/02/17 18:01:53 - mmengine - INFO - Epoch(train) [32][1140/1320] lr: 2.0000e-03 eta: 3:12:26 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 5.0014 loss: 0.9671 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9671 2023/02/17 18:02:02 - mmengine - INFO - Epoch(train) [32][1160/1320] lr: 2.0000e-03 eta: 3:12:16 time: 0.4808 data_time: 0.0145 memory: 27031 grad_norm: 5.0611 loss: 1.1068 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1068 2023/02/17 18:02:12 - mmengine - INFO - Epoch(train) [32][1180/1320] lr: 2.0000e-03 eta: 3:12:06 time: 0.4811 data_time: 0.0158 memory: 27031 grad_norm: 5.0484 loss: 1.1373 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1373 2023/02/17 18:02:21 - mmengine - INFO - Epoch(train) [32][1200/1320] lr: 2.0000e-03 eta: 3:11:57 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 4.9060 loss: 1.2347 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.2347 2023/02/17 18:02:31 - mmengine - INFO - Epoch(train) [32][1220/1320] lr: 2.0000e-03 eta: 3:11:47 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 5.2034 loss: 1.2120 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2120 2023/02/17 18:02:41 - mmengine - INFO - Epoch(train) [32][1240/1320] lr: 2.0000e-03 eta: 3:11:37 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 4.9611 loss: 1.2177 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2177 2023/02/17 18:02:50 - mmengine - INFO - Epoch(train) [32][1260/1320] lr: 2.0000e-03 eta: 3:11:28 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 5.0532 loss: 1.0993 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0993 2023/02/17 18:03:00 - mmengine - INFO - Epoch(train) [32][1280/1320] lr: 2.0000e-03 eta: 3:11:18 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 5.1907 loss: 1.1688 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1688 2023/02/17 18:03:09 - mmengine - INFO - Epoch(train) [32][1300/1320] lr: 2.0000e-03 eta: 3:11:08 time: 0.4816 data_time: 0.0149 memory: 27031 grad_norm: 5.1016 loss: 1.2630 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2630 2023/02/17 18:03:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:03:19 - mmengine - INFO - Epoch(train) [32][1320/1320] lr: 2.0000e-03 eta: 3:10:59 time: 0.4750 data_time: 0.0158 memory: 27031 grad_norm: 5.0753 loss: 1.0234 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 1.0234 2023/02/17 18:03:23 - mmengine - INFO - Epoch(val) [32][ 20/194] eta: 0:00:32 time: 0.1887 data_time: 0.0642 memory: 3265 2023/02/17 18:03:25 - mmengine - INFO - Epoch(val) [32][ 40/194] eta: 0:00:25 time: 0.1385 data_time: 0.0140 memory: 3265 2023/02/17 18:03:28 - mmengine - INFO - Epoch(val) [32][ 60/194] eta: 0:00:20 time: 0.1387 data_time: 0.0137 memory: 3265 2023/02/17 18:03:31 - mmengine - INFO - Epoch(val) [32][ 80/194] eta: 0:00:17 time: 0.1370 data_time: 0.0128 memory: 3265 2023/02/17 18:03:34 - mmengine - INFO - Epoch(val) [32][100/194] eta: 0:00:13 time: 0.1394 data_time: 0.0140 memory: 3265 2023/02/17 18:03:37 - mmengine - INFO - Epoch(val) [32][120/194] eta: 0:00:10 time: 0.1395 data_time: 0.0144 memory: 3265 2023/02/17 18:03:39 - mmengine - INFO - Epoch(val) [32][140/194] eta: 0:00:07 time: 0.1381 data_time: 0.0139 memory: 3265 2023/02/17 18:03:42 - mmengine - INFO - Epoch(val) [32][160/194] eta: 0:00:04 time: 0.1397 data_time: 0.0152 memory: 3265 2023/02/17 18:03:45 - mmengine - INFO - Epoch(val) [32][180/194] eta: 0:00:02 time: 0.1385 data_time: 0.0133 memory: 3265 2023/02/17 18:03:48 - mmengine - INFO - Epoch(val) [32][194/194] acc/top1: 0.6110 acc/top5: 0.8687 acc/mean1: 0.5506 2023/02/17 18:03:58 - mmengine - INFO - Epoch(train) [33][ 20/1320] lr: 2.0000e-03 eta: 3:10:50 time: 0.5374 data_time: 0.0574 memory: 27031 grad_norm: 4.8764 loss: 1.1322 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1322 2023/02/17 18:04:08 - mmengine - INFO - Epoch(train) [33][ 40/1320] lr: 2.0000e-03 eta: 3:10:40 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 4.9301 loss: 1.0384 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0384 2023/02/17 18:04:18 - mmengine - INFO - Epoch(train) [33][ 60/1320] lr: 2.0000e-03 eta: 3:10:30 time: 0.4797 data_time: 0.0147 memory: 27031 grad_norm: 4.9016 loss: 1.0883 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0883 2023/02/17 18:04:27 - mmengine - INFO - Epoch(train) [33][ 80/1320] lr: 2.0000e-03 eta: 3:10:21 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 4.9435 loss: 0.9783 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9783 2023/02/17 18:04:37 - mmengine - INFO - Epoch(train) [33][ 100/1320] lr: 2.0000e-03 eta: 3:10:11 time: 0.4794 data_time: 0.0147 memory: 27031 grad_norm: 5.0245 loss: 1.1894 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1894 2023/02/17 18:04:46 - mmengine - INFO - Epoch(train) [33][ 120/1320] lr: 2.0000e-03 eta: 3:10:01 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 4.9198 loss: 1.1858 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1858 2023/02/17 18:04:56 - mmengine - INFO - Epoch(train) [33][ 140/1320] lr: 2.0000e-03 eta: 3:09:52 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 5.0315 loss: 1.0784 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0784 2023/02/17 18:05:06 - mmengine - INFO - Epoch(train) [33][ 160/1320] lr: 2.0000e-03 eta: 3:09:42 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 4.8838 loss: 1.0285 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0285 2023/02/17 18:05:15 - mmengine - INFO - Epoch(train) [33][ 180/1320] lr: 2.0000e-03 eta: 3:09:32 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 4.9356 loss: 1.1078 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1078 2023/02/17 18:05:25 - mmengine - INFO - Epoch(train) [33][ 200/1320] lr: 2.0000e-03 eta: 3:09:23 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 5.0122 loss: 1.2065 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.2065 2023/02/17 18:05:34 - mmengine - INFO - Epoch(train) [33][ 220/1320] lr: 2.0000e-03 eta: 3:09:13 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 4.8715 loss: 1.0435 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0435 2023/02/17 18:05:44 - mmengine - INFO - Epoch(train) [33][ 240/1320] lr: 2.0000e-03 eta: 3:09:03 time: 0.4796 data_time: 0.0145 memory: 27031 grad_norm: 5.0247 loss: 0.9740 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9740 2023/02/17 18:05:54 - mmengine - INFO - Epoch(train) [33][ 260/1320] lr: 2.0000e-03 eta: 3:08:54 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 5.1617 loss: 1.0503 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0503 2023/02/17 18:06:03 - mmengine - INFO - Epoch(train) [33][ 280/1320] lr: 2.0000e-03 eta: 3:08:44 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 5.0341 loss: 1.0359 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0359 2023/02/17 18:06:13 - mmengine - INFO - Epoch(train) [33][ 300/1320] lr: 2.0000e-03 eta: 3:08:34 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 4.9205 loss: 0.9436 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9436 2023/02/17 18:06:22 - mmengine - INFO - Epoch(train) [33][ 320/1320] lr: 2.0000e-03 eta: 3:08:25 time: 0.4792 data_time: 0.0136 memory: 27031 grad_norm: 4.9654 loss: 1.1123 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1123 2023/02/17 18:06:32 - mmengine - INFO - Epoch(train) [33][ 340/1320] lr: 2.0000e-03 eta: 3:08:15 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 5.0055 loss: 1.1044 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1044 2023/02/17 18:06:42 - mmengine - INFO - Epoch(train) [33][ 360/1320] lr: 2.0000e-03 eta: 3:08:05 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 4.9501 loss: 0.9664 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9664 2023/02/17 18:06:51 - mmengine - INFO - Epoch(train) [33][ 380/1320] lr: 2.0000e-03 eta: 3:07:56 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 5.0441 loss: 1.1290 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1290 2023/02/17 18:07:01 - mmengine - INFO - Epoch(train) [33][ 400/1320] lr: 2.0000e-03 eta: 3:07:46 time: 0.4809 data_time: 0.0151 memory: 27031 grad_norm: 5.1401 loss: 1.1492 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1492 2023/02/17 18:07:10 - mmengine - INFO - Epoch(train) [33][ 420/1320] lr: 2.0000e-03 eta: 3:07:36 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 4.9510 loss: 1.0178 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0178 2023/02/17 18:07:20 - mmengine - INFO - Epoch(train) [33][ 440/1320] lr: 2.0000e-03 eta: 3:07:27 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.0164 loss: 0.8732 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8732 2023/02/17 18:07:30 - mmengine - INFO - Epoch(train) [33][ 460/1320] lr: 2.0000e-03 eta: 3:07:17 time: 0.4800 data_time: 0.0145 memory: 27031 grad_norm: 5.0471 loss: 1.2089 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2089 2023/02/17 18:07:39 - mmengine - INFO - Epoch(train) [33][ 480/1320] lr: 2.0000e-03 eta: 3:07:07 time: 0.4799 data_time: 0.0136 memory: 27031 grad_norm: 5.0786 loss: 1.0503 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0503 2023/02/17 18:07:49 - mmengine - INFO - Epoch(train) [33][ 500/1320] lr: 2.0000e-03 eta: 3:06:58 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 5.1582 loss: 1.0505 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 1.0505 2023/02/17 18:07:59 - mmengine - INFO - Epoch(train) [33][ 520/1320] lr: 2.0000e-03 eta: 3:06:48 time: 0.4795 data_time: 0.0144 memory: 27031 grad_norm: 5.1626 loss: 1.1097 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1097 2023/02/17 18:08:08 - mmengine - INFO - Epoch(train) [33][ 540/1320] lr: 2.0000e-03 eta: 3:06:38 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 5.1339 loss: 0.9670 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9670 2023/02/17 18:08:18 - mmengine - INFO - Epoch(train) [33][ 560/1320] lr: 2.0000e-03 eta: 3:06:29 time: 0.4813 data_time: 0.0154 memory: 27031 grad_norm: 5.1433 loss: 1.0907 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.0907 2023/02/17 18:08:27 - mmengine - INFO - Epoch(train) [33][ 580/1320] lr: 2.0000e-03 eta: 3:06:19 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 5.2473 loss: 1.1511 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1511 2023/02/17 18:08:37 - mmengine - INFO - Epoch(train) [33][ 600/1320] lr: 2.0000e-03 eta: 3:06:09 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 5.0165 loss: 0.9928 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9928 2023/02/17 18:08:47 - mmengine - INFO - Epoch(train) [33][ 620/1320] lr: 2.0000e-03 eta: 3:06:00 time: 0.4800 data_time: 0.0147 memory: 27031 grad_norm: 5.0795 loss: 1.0363 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0363 2023/02/17 18:08:56 - mmengine - INFO - Epoch(train) [33][ 640/1320] lr: 2.0000e-03 eta: 3:05:50 time: 0.4810 data_time: 0.0152 memory: 27031 grad_norm: 5.2711 loss: 1.2805 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2805 2023/02/17 18:09:06 - mmengine - INFO - Epoch(train) [33][ 660/1320] lr: 2.0000e-03 eta: 3:05:40 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 4.9980 loss: 1.0554 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0554 2023/02/17 18:09:15 - mmengine - INFO - Epoch(train) [33][ 680/1320] lr: 2.0000e-03 eta: 3:05:31 time: 0.4810 data_time: 0.0150 memory: 27031 grad_norm: 4.9052 loss: 0.9636 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9636 2023/02/17 18:09:25 - mmengine - INFO - Epoch(train) [33][ 700/1320] lr: 2.0000e-03 eta: 3:05:21 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 5.0611 loss: 0.8769 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8769 2023/02/17 18:09:35 - mmengine - INFO - Epoch(train) [33][ 720/1320] lr: 2.0000e-03 eta: 3:05:11 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 5.2426 loss: 1.2042 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2042 2023/02/17 18:09:44 - mmengine - INFO - Epoch(train) [33][ 740/1320] lr: 2.0000e-03 eta: 3:05:02 time: 0.4796 data_time: 0.0142 memory: 27031 grad_norm: 5.1663 loss: 1.2359 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2359 2023/02/17 18:09:54 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:09:54 - mmengine - INFO - Epoch(train) [33][ 760/1320] lr: 2.0000e-03 eta: 3:04:52 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 5.2146 loss: 1.1567 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1567 2023/02/17 18:10:03 - mmengine - INFO - Epoch(train) [33][ 780/1320] lr: 2.0000e-03 eta: 3:04:42 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 5.0643 loss: 1.0417 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0417 2023/02/17 18:10:13 - mmengine - INFO - Epoch(train) [33][ 800/1320] lr: 2.0000e-03 eta: 3:04:33 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 5.1288 loss: 1.0888 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0888 2023/02/17 18:10:23 - mmengine - INFO - Epoch(train) [33][ 820/1320] lr: 2.0000e-03 eta: 3:04:23 time: 0.4812 data_time: 0.0159 memory: 27031 grad_norm: 5.2272 loss: 1.1259 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1259 2023/02/17 18:10:32 - mmengine - INFO - Epoch(train) [33][ 840/1320] lr: 2.0000e-03 eta: 3:04:13 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 5.1412 loss: 1.0659 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0659 2023/02/17 18:10:42 - mmengine - INFO - Epoch(train) [33][ 860/1320] lr: 2.0000e-03 eta: 3:04:04 time: 0.4799 data_time: 0.0139 memory: 27031 grad_norm: 5.1595 loss: 1.1063 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1063 2023/02/17 18:10:52 - mmengine - INFO - Epoch(train) [33][ 880/1320] lr: 2.0000e-03 eta: 3:03:54 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 5.2490 loss: 1.1027 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1027 2023/02/17 18:11:01 - mmengine - INFO - Epoch(train) [33][ 900/1320] lr: 2.0000e-03 eta: 3:03:44 time: 0.4818 data_time: 0.0162 memory: 27031 grad_norm: 5.0896 loss: 1.0692 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0692 2023/02/17 18:11:11 - mmengine - INFO - Epoch(train) [33][ 920/1320] lr: 2.0000e-03 eta: 3:03:35 time: 0.4805 data_time: 0.0148 memory: 27031 grad_norm: 5.0041 loss: 0.9686 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9686 2023/02/17 18:11:20 - mmengine - INFO - Epoch(train) [33][ 940/1320] lr: 2.0000e-03 eta: 3:03:25 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 5.0760 loss: 1.0464 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0464 2023/02/17 18:11:30 - mmengine - INFO - Epoch(train) [33][ 960/1320] lr: 2.0000e-03 eta: 3:03:15 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 5.0985 loss: 1.1887 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1887 2023/02/17 18:11:40 - mmengine - INFO - Epoch(train) [33][ 980/1320] lr: 2.0000e-03 eta: 3:03:06 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 5.0920 loss: 1.0413 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0413 2023/02/17 18:11:49 - mmengine - INFO - Epoch(train) [33][1000/1320] lr: 2.0000e-03 eta: 3:02:56 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 5.0456 loss: 1.0003 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0003 2023/02/17 18:11:59 - mmengine - INFO - Epoch(train) [33][1020/1320] lr: 2.0000e-03 eta: 3:02:46 time: 0.4791 data_time: 0.0140 memory: 27031 grad_norm: 5.0353 loss: 0.9227 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9227 2023/02/17 18:12:08 - mmengine - INFO - Epoch(train) [33][1040/1320] lr: 2.0000e-03 eta: 3:02:37 time: 0.4806 data_time: 0.0150 memory: 27031 grad_norm: 5.0946 loss: 1.0277 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0277 2023/02/17 18:12:18 - mmengine - INFO - Epoch(train) [33][1060/1320] lr: 2.0000e-03 eta: 3:02:27 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 4.9755 loss: 0.9959 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9959 2023/02/17 18:12:28 - mmengine - INFO - Epoch(train) [33][1080/1320] lr: 2.0000e-03 eta: 3:02:17 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.1929 loss: 1.1627 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1627 2023/02/17 18:12:37 - mmengine - INFO - Epoch(train) [33][1100/1320] lr: 2.0000e-03 eta: 3:02:08 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 5.1645 loss: 1.0921 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0921 2023/02/17 18:12:47 - mmengine - INFO - Epoch(train) [33][1120/1320] lr: 2.0000e-03 eta: 3:01:58 time: 0.4796 data_time: 0.0136 memory: 27031 grad_norm: 5.1674 loss: 1.0569 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0569 2023/02/17 18:12:57 - mmengine - INFO - Epoch(train) [33][1140/1320] lr: 2.0000e-03 eta: 3:01:48 time: 0.4806 data_time: 0.0151 memory: 27031 grad_norm: 5.3021 loss: 0.9547 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9547 2023/02/17 18:13:06 - mmengine - INFO - Epoch(train) [33][1160/1320] lr: 2.0000e-03 eta: 3:01:39 time: 0.4807 data_time: 0.0140 memory: 27031 grad_norm: 5.0290 loss: 1.0796 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0796 2023/02/17 18:13:16 - mmengine - INFO - Epoch(train) [33][1180/1320] lr: 2.0000e-03 eta: 3:01:29 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 5.3411 loss: 1.0722 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0722 2023/02/17 18:13:25 - mmengine - INFO - Epoch(train) [33][1200/1320] lr: 2.0000e-03 eta: 3:01:19 time: 0.4807 data_time: 0.0154 memory: 27031 grad_norm: 5.1451 loss: 1.1412 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1412 2023/02/17 18:13:35 - mmengine - INFO - Epoch(train) [33][1220/1320] lr: 2.0000e-03 eta: 3:01:10 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 5.3040 loss: 1.2810 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.2810 2023/02/17 18:13:45 - mmengine - INFO - Epoch(train) [33][1240/1320] lr: 2.0000e-03 eta: 3:01:00 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 5.0479 loss: 1.1568 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1568 2023/02/17 18:13:54 - mmengine - INFO - Epoch(train) [33][1260/1320] lr: 2.0000e-03 eta: 3:00:50 time: 0.4803 data_time: 0.0150 memory: 27031 grad_norm: 5.0380 loss: 1.0906 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0906 2023/02/17 18:14:04 - mmengine - INFO - Epoch(train) [33][1280/1320] lr: 2.0000e-03 eta: 3:00:41 time: 0.4804 data_time: 0.0138 memory: 27031 grad_norm: 5.1407 loss: 1.2047 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2047 2023/02/17 18:14:13 - mmengine - INFO - Epoch(train) [33][1300/1320] lr: 2.0000e-03 eta: 3:00:31 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 5.2914 loss: 1.0862 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0862 2023/02/17 18:14:23 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:14:23 - mmengine - INFO - Epoch(train) [33][1320/1320] lr: 2.0000e-03 eta: 3:00:21 time: 0.4752 data_time: 0.0164 memory: 27031 grad_norm: 5.2689 loss: 1.0568 top1_acc: 0.5455 top5_acc: 0.9091 loss_cls: 1.0568 2023/02/17 18:14:23 - mmengine - INFO - Saving checkpoint at 33 epochs 2023/02/17 18:14:28 - mmengine - INFO - Epoch(val) [33][ 20/194] eta: 0:00:32 time: 0.1886 data_time: 0.0605 memory: 3265 2023/02/17 18:14:31 - mmengine - INFO - Epoch(val) [33][ 40/194] eta: 0:00:25 time: 0.1378 data_time: 0.0126 memory: 3265 2023/02/17 18:14:33 - mmengine - INFO - Epoch(val) [33][ 60/194] eta: 0:00:20 time: 0.1382 data_time: 0.0134 memory: 3265 2023/02/17 18:14:36 - mmengine - INFO - Epoch(val) [33][ 80/194] eta: 0:00:17 time: 0.1368 data_time: 0.0128 memory: 3265 2023/02/17 18:14:39 - mmengine - INFO - Epoch(val) [33][100/194] eta: 0:00:13 time: 0.1366 data_time: 0.0128 memory: 3265 2023/02/17 18:14:42 - mmengine - INFO - Epoch(val) [33][120/194] eta: 0:00:10 time: 0.1386 data_time: 0.0138 memory: 3265 2023/02/17 18:14:44 - mmengine - INFO - Epoch(val) [33][140/194] eta: 0:00:07 time: 0.1393 data_time: 0.0138 memory: 3265 2023/02/17 18:14:47 - mmengine - INFO - Epoch(val) [33][160/194] eta: 0:00:04 time: 0.1384 data_time: 0.0137 memory: 3265 2023/02/17 18:14:50 - mmengine - INFO - Epoch(val) [33][180/194] eta: 0:00:02 time: 0.1363 data_time: 0.0129 memory: 3265 2023/02/17 18:14:52 - mmengine - INFO - Epoch(val) [33][194/194] acc/top1: 0.6131 acc/top5: 0.8699 acc/mean1: 0.5542 2023/02/17 18:15:03 - mmengine - INFO - Epoch(train) [34][ 20/1320] lr: 2.0000e-03 eta: 3:00:12 time: 0.5355 data_time: 0.0606 memory: 27031 grad_norm: 5.0943 loss: 1.2446 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2446 2023/02/17 18:15:13 - mmengine - INFO - Epoch(train) [34][ 40/1320] lr: 2.0000e-03 eta: 3:00:03 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 5.1111 loss: 1.2171 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2171 2023/02/17 18:15:22 - mmengine - INFO - Epoch(train) [34][ 60/1320] lr: 2.0000e-03 eta: 2:59:53 time: 0.4800 data_time: 0.0130 memory: 27031 grad_norm: 5.2443 loss: 1.0059 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0059 2023/02/17 18:15:32 - mmengine - INFO - Epoch(train) [34][ 80/1320] lr: 2.0000e-03 eta: 2:59:43 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 5.2198 loss: 1.0143 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0143 2023/02/17 18:15:42 - mmengine - INFO - Epoch(train) [34][ 100/1320] lr: 2.0000e-03 eta: 2:59:34 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 5.1471 loss: 0.9670 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9670 2023/02/17 18:15:51 - mmengine - INFO - Epoch(train) [34][ 120/1320] lr: 2.0000e-03 eta: 2:59:24 time: 0.4810 data_time: 0.0147 memory: 27031 grad_norm: 5.0995 loss: 1.1535 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1535 2023/02/17 18:16:01 - mmengine - INFO - Epoch(train) [34][ 140/1320] lr: 2.0000e-03 eta: 2:59:14 time: 0.4800 data_time: 0.0140 memory: 27031 grad_norm: 5.2219 loss: 0.9437 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9437 2023/02/17 18:16:10 - mmengine - INFO - Epoch(train) [34][ 160/1320] lr: 2.0000e-03 eta: 2:59:05 time: 0.4802 data_time: 0.0151 memory: 27031 grad_norm: 5.1344 loss: 1.0509 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0509 2023/02/17 18:16:20 - mmengine - INFO - Epoch(train) [34][ 180/1320] lr: 2.0000e-03 eta: 2:58:55 time: 0.4804 data_time: 0.0150 memory: 27031 grad_norm: 5.1283 loss: 1.0074 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0074 2023/02/17 18:16:30 - mmengine - INFO - Epoch(train) [34][ 200/1320] lr: 2.0000e-03 eta: 2:58:45 time: 0.4806 data_time: 0.0159 memory: 27031 grad_norm: 5.2276 loss: 1.1150 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1150 2023/02/17 18:16:39 - mmengine - INFO - Epoch(train) [34][ 220/1320] lr: 2.0000e-03 eta: 2:58:36 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 4.9382 loss: 1.1072 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1072 2023/02/17 18:16:49 - mmengine - INFO - Epoch(train) [34][ 240/1320] lr: 2.0000e-03 eta: 2:58:26 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 5.3246 loss: 1.0747 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0747 2023/02/17 18:16:58 - mmengine - INFO - Epoch(train) [34][ 260/1320] lr: 2.0000e-03 eta: 2:58:16 time: 0.4794 data_time: 0.0146 memory: 27031 grad_norm: 5.0547 loss: 1.0633 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.0633 2023/02/17 18:17:08 - mmengine - INFO - Epoch(train) [34][ 280/1320] lr: 2.0000e-03 eta: 2:58:07 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 5.1911 loss: 1.2103 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2103 2023/02/17 18:17:18 - mmengine - INFO - Epoch(train) [34][ 300/1320] lr: 2.0000e-03 eta: 2:57:57 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 4.9425 loss: 1.0561 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0561 2023/02/17 18:17:27 - mmengine - INFO - Epoch(train) [34][ 320/1320] lr: 2.0000e-03 eta: 2:57:47 time: 0.4805 data_time: 0.0148 memory: 27031 grad_norm: 5.0379 loss: 0.9318 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9318 2023/02/17 18:17:37 - mmengine - INFO - Epoch(train) [34][ 340/1320] lr: 2.0000e-03 eta: 2:57:38 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 5.1113 loss: 0.9603 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9603 2023/02/17 18:17:46 - mmengine - INFO - Epoch(train) [34][ 360/1320] lr: 2.0000e-03 eta: 2:57:28 time: 0.4806 data_time: 0.0144 memory: 27031 grad_norm: 5.1737 loss: 1.0138 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0138 2023/02/17 18:17:56 - mmengine - INFO - Epoch(train) [34][ 380/1320] lr: 2.0000e-03 eta: 2:57:18 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 5.1519 loss: 1.1246 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.1246 2023/02/17 18:18:06 - mmengine - INFO - Epoch(train) [34][ 400/1320] lr: 2.0000e-03 eta: 2:57:09 time: 0.4813 data_time: 0.0150 memory: 27031 grad_norm: 5.1924 loss: 1.1724 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.1724 2023/02/17 18:18:15 - mmengine - INFO - Epoch(train) [34][ 420/1320] lr: 2.0000e-03 eta: 2:56:59 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 5.3392 loss: 0.9093 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9093 2023/02/17 18:18:25 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:18:25 - mmengine - INFO - Epoch(train) [34][ 440/1320] lr: 2.0000e-03 eta: 2:56:49 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 5.4236 loss: 1.2023 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2023 2023/02/17 18:18:35 - mmengine - INFO - Epoch(train) [34][ 460/1320] lr: 2.0000e-03 eta: 2:56:40 time: 0.4811 data_time: 0.0153 memory: 27031 grad_norm: 5.2186 loss: 1.0304 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0304 2023/02/17 18:18:44 - mmengine - INFO - Epoch(train) [34][ 480/1320] lr: 2.0000e-03 eta: 2:56:30 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 5.2267 loss: 1.3274 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.3274 2023/02/17 18:18:54 - mmengine - INFO - Epoch(train) [34][ 500/1320] lr: 2.0000e-03 eta: 2:56:20 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 5.3148 loss: 1.0813 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0813 2023/02/17 18:19:03 - mmengine - INFO - Epoch(train) [34][ 520/1320] lr: 2.0000e-03 eta: 2:56:11 time: 0.4809 data_time: 0.0149 memory: 27031 grad_norm: 5.2147 loss: 0.9901 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9901 2023/02/17 18:19:13 - mmengine - INFO - Epoch(train) [34][ 540/1320] lr: 2.0000e-03 eta: 2:56:01 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 5.0820 loss: 0.9792 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9792 2023/02/17 18:19:23 - mmengine - INFO - Epoch(train) [34][ 560/1320] lr: 2.0000e-03 eta: 2:55:51 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 5.2230 loss: 1.0294 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0294 2023/02/17 18:19:32 - mmengine - INFO - Epoch(train) [34][ 580/1320] lr: 2.0000e-03 eta: 2:55:42 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 5.2404 loss: 1.1472 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1472 2023/02/17 18:19:42 - mmengine - INFO - Epoch(train) [34][ 600/1320] lr: 2.0000e-03 eta: 2:55:32 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 5.2058 loss: 0.9628 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9628 2023/02/17 18:19:51 - mmengine - INFO - Epoch(train) [34][ 620/1320] lr: 2.0000e-03 eta: 2:55:22 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 5.3648 loss: 1.0721 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0721 2023/02/17 18:20:01 - mmengine - INFO - Epoch(train) [34][ 640/1320] lr: 2.0000e-03 eta: 2:55:13 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 5.3770 loss: 1.2058 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2058 2023/02/17 18:20:11 - mmengine - INFO - Epoch(train) [34][ 660/1320] lr: 2.0000e-03 eta: 2:55:03 time: 0.4793 data_time: 0.0143 memory: 27031 grad_norm: 5.3918 loss: 0.9642 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9642 2023/02/17 18:20:20 - mmengine - INFO - Epoch(train) [34][ 680/1320] lr: 2.0000e-03 eta: 2:54:53 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 5.2491 loss: 1.1830 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1830 2023/02/17 18:20:30 - mmengine - INFO - Epoch(train) [34][ 700/1320] lr: 2.0000e-03 eta: 2:54:44 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 5.1869 loss: 1.0805 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0805 2023/02/17 18:20:39 - mmengine - INFO - Epoch(train) [34][ 720/1320] lr: 2.0000e-03 eta: 2:54:34 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 5.2309 loss: 1.0709 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0709 2023/02/17 18:20:49 - mmengine - INFO - Epoch(train) [34][ 740/1320] lr: 2.0000e-03 eta: 2:54:24 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 5.2203 loss: 1.0099 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0099 2023/02/17 18:20:59 - mmengine - INFO - Epoch(train) [34][ 760/1320] lr: 2.0000e-03 eta: 2:54:15 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 5.3206 loss: 1.1047 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1047 2023/02/17 18:21:08 - mmengine - INFO - Epoch(train) [34][ 780/1320] lr: 2.0000e-03 eta: 2:54:05 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 5.3341 loss: 0.9562 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9562 2023/02/17 18:21:18 - mmengine - INFO - Epoch(train) [34][ 800/1320] lr: 2.0000e-03 eta: 2:53:55 time: 0.4810 data_time: 0.0154 memory: 27031 grad_norm: 5.2166 loss: 1.1189 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1189 2023/02/17 18:21:28 - mmengine - INFO - Epoch(train) [34][ 820/1320] lr: 2.0000e-03 eta: 2:53:46 time: 0.4798 data_time: 0.0144 memory: 27031 grad_norm: 5.2465 loss: 1.0981 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0981 2023/02/17 18:21:37 - mmengine - INFO - Epoch(train) [34][ 840/1320] lr: 2.0000e-03 eta: 2:53:36 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 5.3133 loss: 1.0972 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0972 2023/02/17 18:21:47 - mmengine - INFO - Epoch(train) [34][ 860/1320] lr: 2.0000e-03 eta: 2:53:26 time: 0.4799 data_time: 0.0140 memory: 27031 grad_norm: 5.2165 loss: 0.9670 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9670 2023/02/17 18:21:56 - mmengine - INFO - Epoch(train) [34][ 880/1320] lr: 2.0000e-03 eta: 2:53:17 time: 0.4798 data_time: 0.0146 memory: 27031 grad_norm: 5.2608 loss: 0.9607 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9607 2023/02/17 18:22:06 - mmengine - INFO - Epoch(train) [34][ 900/1320] lr: 2.0000e-03 eta: 2:53:07 time: 0.4812 data_time: 0.0151 memory: 27031 grad_norm: 5.4633 loss: 1.0292 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0292 2023/02/17 18:22:16 - mmengine - INFO - Epoch(train) [34][ 920/1320] lr: 2.0000e-03 eta: 2:52:57 time: 0.4813 data_time: 0.0141 memory: 27031 grad_norm: 5.4709 loss: 1.1222 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1222 2023/02/17 18:22:25 - mmengine - INFO - Epoch(train) [34][ 940/1320] lr: 2.0000e-03 eta: 2:52:48 time: 0.4812 data_time: 0.0152 memory: 27031 grad_norm: 5.3938 loss: 1.1958 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1958 2023/02/17 18:22:35 - mmengine - INFO - Epoch(train) [34][ 960/1320] lr: 2.0000e-03 eta: 2:52:38 time: 0.4811 data_time: 0.0152 memory: 27031 grad_norm: 5.2931 loss: 0.9519 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.9519 2023/02/17 18:22:44 - mmengine - INFO - Epoch(train) [34][ 980/1320] lr: 2.0000e-03 eta: 2:52:28 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.3886 loss: 1.0985 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0985 2023/02/17 18:22:54 - mmengine - INFO - Epoch(train) [34][1000/1320] lr: 2.0000e-03 eta: 2:52:19 time: 0.4815 data_time: 0.0147 memory: 27031 grad_norm: 5.3224 loss: 1.1508 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1508 2023/02/17 18:23:04 - mmengine - INFO - Epoch(train) [34][1020/1320] lr: 2.0000e-03 eta: 2:52:09 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 5.1790 loss: 0.9117 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9117 2023/02/17 18:23:13 - mmengine - INFO - Epoch(train) [34][1040/1320] lr: 2.0000e-03 eta: 2:51:59 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 5.4098 loss: 0.9815 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9815 2023/02/17 18:23:23 - mmengine - INFO - Epoch(train) [34][1060/1320] lr: 2.0000e-03 eta: 2:51:50 time: 0.4809 data_time: 0.0152 memory: 27031 grad_norm: 5.3090 loss: 0.9358 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9358 2023/02/17 18:23:33 - mmengine - INFO - Epoch(train) [34][1080/1320] lr: 2.0000e-03 eta: 2:51:40 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 5.5443 loss: 1.1101 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1101 2023/02/17 18:23:42 - mmengine - INFO - Epoch(train) [34][1100/1320] lr: 2.0000e-03 eta: 2:51:30 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 5.3224 loss: 1.0369 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0369 2023/02/17 18:23:52 - mmengine - INFO - Epoch(train) [34][1120/1320] lr: 2.0000e-03 eta: 2:51:21 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 5.3417 loss: 1.2292 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2292 2023/02/17 18:24:01 - mmengine - INFO - Epoch(train) [34][1140/1320] lr: 2.0000e-03 eta: 2:51:11 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 5.2554 loss: 1.0337 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0337 2023/02/17 18:24:11 - mmengine - INFO - Epoch(train) [34][1160/1320] lr: 2.0000e-03 eta: 2:51:01 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 5.3024 loss: 1.1632 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1632 2023/02/17 18:24:21 - mmengine - INFO - Epoch(train) [34][1180/1320] lr: 2.0000e-03 eta: 2:50:52 time: 0.4826 data_time: 0.0169 memory: 27031 grad_norm: 5.4934 loss: 1.2213 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.2213 2023/02/17 18:24:30 - mmengine - INFO - Epoch(train) [34][1200/1320] lr: 2.0000e-03 eta: 2:50:42 time: 0.4795 data_time: 0.0141 memory: 27031 grad_norm: 5.3384 loss: 1.1312 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1312 2023/02/17 18:24:40 - mmengine - INFO - Epoch(train) [34][1220/1320] lr: 2.0000e-03 eta: 2:50:32 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 5.3725 loss: 1.1538 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.1538 2023/02/17 18:24:49 - mmengine - INFO - Epoch(train) [34][1240/1320] lr: 2.0000e-03 eta: 2:50:23 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 5.3858 loss: 1.0688 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0688 2023/02/17 18:24:59 - mmengine - INFO - Epoch(train) [34][1260/1320] lr: 2.0000e-03 eta: 2:50:13 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 5.2606 loss: 1.1286 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1286 2023/02/17 18:25:09 - mmengine - INFO - Epoch(train) [34][1280/1320] lr: 2.0000e-03 eta: 2:50:03 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 5.2611 loss: 1.0176 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0176 2023/02/17 18:25:18 - mmengine - INFO - Epoch(train) [34][1300/1320] lr: 2.0000e-03 eta: 2:49:54 time: 0.4810 data_time: 0.0141 memory: 27031 grad_norm: 5.2621 loss: 1.1554 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.1554 2023/02/17 18:25:28 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:25:28 - mmengine - INFO - Epoch(train) [34][1320/1320] lr: 2.0000e-03 eta: 2:49:44 time: 0.4757 data_time: 0.0164 memory: 27031 grad_norm: 5.3963 loss: 1.0899 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 1.0899 2023/02/17 18:25:32 - mmengine - INFO - Epoch(val) [34][ 20/194] eta: 0:00:33 time: 0.1919 data_time: 0.0635 memory: 3265 2023/02/17 18:25:34 - mmengine - INFO - Epoch(val) [34][ 40/194] eta: 0:00:25 time: 0.1394 data_time: 0.0141 memory: 3265 2023/02/17 18:25:37 - mmengine - INFO - Epoch(val) [34][ 60/194] eta: 0:00:20 time: 0.1379 data_time: 0.0138 memory: 3265 2023/02/17 18:25:40 - mmengine - INFO - Epoch(val) [34][ 80/194] eta: 0:00:17 time: 0.1358 data_time: 0.0124 memory: 3265 2023/02/17 18:25:43 - mmengine - INFO - Epoch(val) [34][100/194] eta: 0:00:13 time: 0.1372 data_time: 0.0131 memory: 3265 2023/02/17 18:25:45 - mmengine - INFO - Epoch(val) [34][120/194] eta: 0:00:10 time: 0.1374 data_time: 0.0131 memory: 3265 2023/02/17 18:25:48 - mmengine - INFO - Epoch(val) [34][140/194] eta: 0:00:07 time: 0.1396 data_time: 0.0147 memory: 3265 2023/02/17 18:25:51 - mmengine - INFO - Epoch(val) [34][160/194] eta: 0:00:04 time: 0.1396 data_time: 0.0144 memory: 3265 2023/02/17 18:25:54 - mmengine - INFO - Epoch(val) [34][180/194] eta: 0:00:02 time: 0.1368 data_time: 0.0132 memory: 3265 2023/02/17 18:25:57 - mmengine - INFO - Epoch(val) [34][194/194] acc/top1: 0.6142 acc/top5: 0.8705 acc/mean1: 0.5523 2023/02/17 18:26:07 - mmengine - INFO - Epoch(train) [35][ 20/1320] lr: 2.0000e-03 eta: 2:49:35 time: 0.5395 data_time: 0.0597 memory: 27031 grad_norm: 5.1881 loss: 1.1421 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1421 2023/02/17 18:26:17 - mmengine - INFO - Epoch(train) [35][ 40/1320] lr: 2.0000e-03 eta: 2:49:25 time: 0.4807 data_time: 0.0153 memory: 27031 grad_norm: 5.4614 loss: 0.9907 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9907 2023/02/17 18:26:27 - mmengine - INFO - Epoch(train) [35][ 60/1320] lr: 2.0000e-03 eta: 2:49:16 time: 0.4809 data_time: 0.0160 memory: 27031 grad_norm: 5.2322 loss: 1.0223 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0223 2023/02/17 18:26:36 - mmengine - INFO - Epoch(train) [35][ 80/1320] lr: 2.0000e-03 eta: 2:49:06 time: 0.4811 data_time: 0.0150 memory: 27031 grad_norm: 5.1729 loss: 0.8403 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8403 2023/02/17 18:26:46 - mmengine - INFO - Epoch(train) [35][ 100/1320] lr: 2.0000e-03 eta: 2:48:56 time: 0.4808 data_time: 0.0156 memory: 27031 grad_norm: 5.2422 loss: 1.0570 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0570 2023/02/17 18:26:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:26:56 - mmengine - INFO - Epoch(train) [35][ 120/1320] lr: 2.0000e-03 eta: 2:48:47 time: 0.4800 data_time: 0.0138 memory: 27031 grad_norm: 5.2902 loss: 0.9897 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9897 2023/02/17 18:27:05 - mmengine - INFO - Epoch(train) [35][ 140/1320] lr: 2.0000e-03 eta: 2:48:37 time: 0.4793 data_time: 0.0129 memory: 27031 grad_norm: 5.1623 loss: 1.0694 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0694 2023/02/17 18:27:15 - mmengine - INFO - Epoch(train) [35][ 160/1320] lr: 2.0000e-03 eta: 2:48:27 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 5.4409 loss: 1.1402 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1402 2023/02/17 18:27:24 - mmengine - INFO - Epoch(train) [35][ 180/1320] lr: 2.0000e-03 eta: 2:48:18 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 5.2447 loss: 1.1132 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1132 2023/02/17 18:27:34 - mmengine - INFO - Epoch(train) [35][ 200/1320] lr: 2.0000e-03 eta: 2:48:08 time: 0.4799 data_time: 0.0146 memory: 27031 grad_norm: 5.2963 loss: 1.0408 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0408 2023/02/17 18:27:44 - mmengine - INFO - Epoch(train) [35][ 220/1320] lr: 2.0000e-03 eta: 2:47:58 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 5.4427 loss: 1.3007 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.3007 2023/02/17 18:27:53 - mmengine - INFO - Epoch(train) [35][ 240/1320] lr: 2.0000e-03 eta: 2:47:49 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 5.4169 loss: 1.1246 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1246 2023/02/17 18:28:03 - mmengine - INFO - Epoch(train) [35][ 260/1320] lr: 2.0000e-03 eta: 2:47:39 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 5.2893 loss: 0.9245 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9245 2023/02/17 18:28:12 - mmengine - INFO - Epoch(train) [35][ 280/1320] lr: 2.0000e-03 eta: 2:47:29 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 5.3849 loss: 1.0147 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0147 2023/02/17 18:28:22 - mmengine - INFO - Epoch(train) [35][ 300/1320] lr: 2.0000e-03 eta: 2:47:20 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 5.3748 loss: 1.1296 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1296 2023/02/17 18:28:32 - mmengine - INFO - Epoch(train) [35][ 320/1320] lr: 2.0000e-03 eta: 2:47:10 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 5.4169 loss: 0.9528 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9528 2023/02/17 18:28:41 - mmengine - INFO - Epoch(train) [35][ 340/1320] lr: 2.0000e-03 eta: 2:47:00 time: 0.4821 data_time: 0.0169 memory: 27031 grad_norm: 5.3423 loss: 1.0419 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0419 2023/02/17 18:28:51 - mmengine - INFO - Epoch(train) [35][ 360/1320] lr: 2.0000e-03 eta: 2:46:51 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 5.4292 loss: 1.1245 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1245 2023/02/17 18:29:00 - mmengine - INFO - Epoch(train) [35][ 380/1320] lr: 2.0000e-03 eta: 2:46:41 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 5.4051 loss: 1.1146 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.1146 2023/02/17 18:29:10 - mmengine - INFO - Epoch(train) [35][ 400/1320] lr: 2.0000e-03 eta: 2:46:31 time: 0.4818 data_time: 0.0148 memory: 27031 grad_norm: 5.2945 loss: 1.0100 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0100 2023/02/17 18:29:20 - mmengine - INFO - Epoch(train) [35][ 420/1320] lr: 2.0000e-03 eta: 2:46:22 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 5.4803 loss: 0.9791 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9791 2023/02/17 18:29:29 - mmengine - INFO - Epoch(train) [35][ 440/1320] lr: 2.0000e-03 eta: 2:46:12 time: 0.4797 data_time: 0.0137 memory: 27031 grad_norm: 5.4008 loss: 1.1138 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1138 2023/02/17 18:29:39 - mmengine - INFO - Epoch(train) [35][ 460/1320] lr: 2.0000e-03 eta: 2:46:02 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 5.3720 loss: 1.1056 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1056 2023/02/17 18:29:48 - mmengine - INFO - Epoch(train) [35][ 480/1320] lr: 2.0000e-03 eta: 2:45:53 time: 0.4807 data_time: 0.0142 memory: 27031 grad_norm: 5.3615 loss: 0.8759 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.8759 2023/02/17 18:29:58 - mmengine - INFO - Epoch(train) [35][ 500/1320] lr: 2.0000e-03 eta: 2:45:43 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 5.5798 loss: 1.0142 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0142 2023/02/17 18:30:08 - mmengine - INFO - Epoch(train) [35][ 520/1320] lr: 2.0000e-03 eta: 2:45:33 time: 0.4797 data_time: 0.0145 memory: 27031 grad_norm: 5.3527 loss: 1.1300 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1300 2023/02/17 18:30:17 - mmengine - INFO - Epoch(train) [35][ 540/1320] lr: 2.0000e-03 eta: 2:45:24 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 5.5482 loss: 1.1777 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1777 2023/02/17 18:30:27 - mmengine - INFO - Epoch(train) [35][ 560/1320] lr: 2.0000e-03 eta: 2:45:14 time: 0.4788 data_time: 0.0140 memory: 27031 grad_norm: 5.2822 loss: 1.1293 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1293 2023/02/17 18:30:36 - mmengine - INFO - Epoch(train) [35][ 580/1320] lr: 2.0000e-03 eta: 2:45:04 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 5.4608 loss: 1.2229 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.2229 2023/02/17 18:30:46 - mmengine - INFO - Epoch(train) [35][ 600/1320] lr: 2.0000e-03 eta: 2:44:55 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 5.3805 loss: 1.2907 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.2907 2023/02/17 18:30:56 - mmengine - INFO - Epoch(train) [35][ 620/1320] lr: 2.0000e-03 eta: 2:44:45 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 5.3926 loss: 1.1683 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.1683 2023/02/17 18:31:05 - mmengine - INFO - Epoch(train) [35][ 640/1320] lr: 2.0000e-03 eta: 2:44:35 time: 0.4808 data_time: 0.0153 memory: 27031 grad_norm: 5.2820 loss: 0.9639 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9639 2023/02/17 18:31:15 - mmengine - INFO - Epoch(train) [35][ 660/1320] lr: 2.0000e-03 eta: 2:44:26 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 5.4793 loss: 1.0668 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0668 2023/02/17 18:31:25 - mmengine - INFO - Epoch(train) [35][ 680/1320] lr: 2.0000e-03 eta: 2:44:16 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 5.3984 loss: 0.9857 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9857 2023/02/17 18:31:34 - mmengine - INFO - Epoch(train) [35][ 700/1320] lr: 2.0000e-03 eta: 2:44:06 time: 0.4822 data_time: 0.0164 memory: 27031 grad_norm: 5.4933 loss: 1.0551 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0551 2023/02/17 18:31:44 - mmengine - INFO - Epoch(train) [35][ 720/1320] lr: 2.0000e-03 eta: 2:43:57 time: 0.4793 data_time: 0.0135 memory: 27031 grad_norm: 5.4360 loss: 1.1484 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1484 2023/02/17 18:31:53 - mmengine - INFO - Epoch(train) [35][ 740/1320] lr: 2.0000e-03 eta: 2:43:47 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 5.5141 loss: 1.0446 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0446 2023/02/17 18:32:03 - mmengine - INFO - Epoch(train) [35][ 760/1320] lr: 2.0000e-03 eta: 2:43:37 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 5.5477 loss: 1.1188 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1188 2023/02/17 18:32:13 - mmengine - INFO - Epoch(train) [35][ 780/1320] lr: 2.0000e-03 eta: 2:43:28 time: 0.4793 data_time: 0.0135 memory: 27031 grad_norm: 5.2946 loss: 0.9468 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9468 2023/02/17 18:32:22 - mmengine - INFO - Epoch(train) [35][ 800/1320] lr: 2.0000e-03 eta: 2:43:18 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 5.4054 loss: 0.9591 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9591 2023/02/17 18:32:32 - mmengine - INFO - Epoch(train) [35][ 820/1320] lr: 2.0000e-03 eta: 2:43:08 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 5.3703 loss: 1.1522 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1522 2023/02/17 18:32:41 - mmengine - INFO - Epoch(train) [35][ 840/1320] lr: 2.0000e-03 eta: 2:42:59 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 5.4067 loss: 1.0922 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0922 2023/02/17 18:32:51 - mmengine - INFO - Epoch(train) [35][ 860/1320] lr: 2.0000e-03 eta: 2:42:49 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 5.3436 loss: 1.0037 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0037 2023/02/17 18:33:01 - mmengine - INFO - Epoch(train) [35][ 880/1320] lr: 2.0000e-03 eta: 2:42:39 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 5.6025 loss: 1.0872 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0872 2023/02/17 18:33:10 - mmengine - INFO - Epoch(train) [35][ 900/1320] lr: 2.0000e-03 eta: 2:42:30 time: 0.4809 data_time: 0.0146 memory: 27031 grad_norm: 5.6156 loss: 1.0329 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0329 2023/02/17 18:33:20 - mmengine - INFO - Epoch(train) [35][ 920/1320] lr: 2.0000e-03 eta: 2:42:20 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 5.4207 loss: 1.0050 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0050 2023/02/17 18:33:29 - mmengine - INFO - Epoch(train) [35][ 940/1320] lr: 2.0000e-03 eta: 2:42:10 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 5.3437 loss: 0.9843 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9843 2023/02/17 18:33:39 - mmengine - INFO - Epoch(train) [35][ 960/1320] lr: 2.0000e-03 eta: 2:42:01 time: 0.4814 data_time: 0.0147 memory: 27031 grad_norm: 5.4789 loss: 1.0099 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0099 2023/02/17 18:33:49 - mmengine - INFO - Epoch(train) [35][ 980/1320] lr: 2.0000e-03 eta: 2:41:51 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 5.6265 loss: 1.2252 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2252 2023/02/17 18:33:58 - mmengine - INFO - Epoch(train) [35][1000/1320] lr: 2.0000e-03 eta: 2:41:41 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 5.5768 loss: 1.0065 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0065 2023/02/17 18:34:08 - mmengine - INFO - Epoch(train) [35][1020/1320] lr: 2.0000e-03 eta: 2:41:32 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 5.3812 loss: 1.0307 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.0307 2023/02/17 18:34:18 - mmengine - INFO - Epoch(train) [35][1040/1320] lr: 2.0000e-03 eta: 2:41:22 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 5.4522 loss: 1.0651 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0651 2023/02/17 18:34:27 - mmengine - INFO - Epoch(train) [35][1060/1320] lr: 2.0000e-03 eta: 2:41:12 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 5.3917 loss: 1.0025 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0025 2023/02/17 18:34:37 - mmengine - INFO - Epoch(train) [35][1080/1320] lr: 2.0000e-03 eta: 2:41:03 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 5.4693 loss: 0.9502 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9502 2023/02/17 18:34:46 - mmengine - INFO - Epoch(train) [35][1100/1320] lr: 2.0000e-03 eta: 2:40:53 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 5.5283 loss: 1.1382 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1382 2023/02/17 18:34:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:34:56 - mmengine - INFO - Epoch(train) [35][1120/1320] lr: 2.0000e-03 eta: 2:40:44 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 5.7219 loss: 1.1037 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1037 2023/02/17 18:35:06 - mmengine - INFO - Epoch(train) [35][1140/1320] lr: 2.0000e-03 eta: 2:40:34 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 5.3378 loss: 0.9383 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9383 2023/02/17 18:35:15 - mmengine - INFO - Epoch(train) [35][1160/1320] lr: 2.0000e-03 eta: 2:40:24 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 5.4553 loss: 1.0390 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0390 2023/02/17 18:35:25 - mmengine - INFO - Epoch(train) [35][1180/1320] lr: 2.0000e-03 eta: 2:40:15 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 5.4300 loss: 0.9649 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9649 2023/02/17 18:35:34 - mmengine - INFO - Epoch(train) [35][1200/1320] lr: 2.0000e-03 eta: 2:40:05 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 5.4726 loss: 0.9298 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9298 2023/02/17 18:35:44 - mmengine - INFO - Epoch(train) [35][1220/1320] lr: 2.0000e-03 eta: 2:39:55 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 5.6016 loss: 1.1193 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1193 2023/02/17 18:35:54 - mmengine - INFO - Epoch(train) [35][1240/1320] lr: 2.0000e-03 eta: 2:39:46 time: 0.4819 data_time: 0.0147 memory: 27031 grad_norm: 5.3913 loss: 1.0677 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0677 2023/02/17 18:36:03 - mmengine - INFO - Epoch(train) [35][1260/1320] lr: 2.0000e-03 eta: 2:39:36 time: 0.4801 data_time: 0.0135 memory: 27031 grad_norm: 5.4373 loss: 0.9963 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9963 2023/02/17 18:36:13 - mmengine - INFO - Epoch(train) [35][1280/1320] lr: 2.0000e-03 eta: 2:39:26 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 5.5426 loss: 0.9368 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9368 2023/02/17 18:36:22 - mmengine - INFO - Epoch(train) [35][1300/1320] lr: 2.0000e-03 eta: 2:39:17 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 5.5372 loss: 1.1627 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1627 2023/02/17 18:36:32 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:36:32 - mmengine - INFO - Epoch(train) [35][1320/1320] lr: 2.0000e-03 eta: 2:39:07 time: 0.4748 data_time: 0.0146 memory: 27031 grad_norm: 5.5048 loss: 0.9993 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 0.9993 2023/02/17 18:36:36 - mmengine - INFO - Epoch(val) [35][ 20/194] eta: 0:00:32 time: 0.1879 data_time: 0.0604 memory: 3265 2023/02/17 18:36:38 - mmengine - INFO - Epoch(val) [35][ 40/194] eta: 0:00:24 time: 0.1365 data_time: 0.0120 memory: 3265 2023/02/17 18:36:41 - mmengine - INFO - Epoch(val) [35][ 60/194] eta: 0:00:20 time: 0.1390 data_time: 0.0140 memory: 3265 2023/02/17 18:36:44 - mmengine - INFO - Epoch(val) [35][ 80/194] eta: 0:00:17 time: 0.1377 data_time: 0.0134 memory: 3265 2023/02/17 18:36:47 - mmengine - INFO - Epoch(val) [35][100/194] eta: 0:00:13 time: 0.1383 data_time: 0.0140 memory: 3265 2023/02/17 18:36:50 - mmengine - INFO - Epoch(val) [35][120/194] eta: 0:00:10 time: 0.1381 data_time: 0.0139 memory: 3265 2023/02/17 18:36:52 - mmengine - INFO - Epoch(val) [35][140/194] eta: 0:00:07 time: 0.1378 data_time: 0.0128 memory: 3265 2023/02/17 18:36:55 - mmengine - INFO - Epoch(val) [35][160/194] eta: 0:00:04 time: 0.1374 data_time: 0.0133 memory: 3265 2023/02/17 18:36:58 - mmengine - INFO - Epoch(val) [35][180/194] eta: 0:00:02 time: 0.1379 data_time: 0.0137 memory: 3265 2023/02/17 18:37:01 - mmengine - INFO - Epoch(val) [35][194/194] acc/top1: 0.6072 acc/top5: 0.8698 acc/mean1: 0.5481 2023/02/17 18:37:11 - mmengine - INFO - Epoch(train) [36][ 20/1320] lr: 2.0000e-03 eta: 2:38:58 time: 0.5371 data_time: 0.0612 memory: 27031 grad_norm: 5.3720 loss: 1.0813 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0813 2023/02/17 18:37:21 - mmengine - INFO - Epoch(train) [36][ 40/1320] lr: 2.0000e-03 eta: 2:38:48 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 5.3551 loss: 1.0909 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0909 2023/02/17 18:37:31 - mmengine - INFO - Epoch(train) [36][ 60/1320] lr: 2.0000e-03 eta: 2:38:38 time: 0.4806 data_time: 0.0139 memory: 27031 grad_norm: 5.3850 loss: 0.9801 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 0.9801 2023/02/17 18:37:40 - mmengine - INFO - Epoch(train) [36][ 80/1320] lr: 2.0000e-03 eta: 2:38:29 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 5.4746 loss: 1.0462 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0462 2023/02/17 18:37:50 - mmengine - INFO - Epoch(train) [36][ 100/1320] lr: 2.0000e-03 eta: 2:38:19 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 5.4901 loss: 1.1088 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1088 2023/02/17 18:37:59 - mmengine - INFO - Epoch(train) [36][ 120/1320] lr: 2.0000e-03 eta: 2:38:09 time: 0.4807 data_time: 0.0154 memory: 27031 grad_norm: 5.6962 loss: 0.9919 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9919 2023/02/17 18:38:09 - mmengine - INFO - Epoch(train) [36][ 140/1320] lr: 2.0000e-03 eta: 2:38:00 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 5.4979 loss: 1.2092 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.2092 2023/02/17 18:38:19 - mmengine - INFO - Epoch(train) [36][ 160/1320] lr: 2.0000e-03 eta: 2:37:50 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 5.4110 loss: 1.0117 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0117 2023/02/17 18:38:28 - mmengine - INFO - Epoch(train) [36][ 180/1320] lr: 2.0000e-03 eta: 2:37:40 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 5.5060 loss: 1.0637 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.0637 2023/02/17 18:38:38 - mmengine - INFO - Epoch(train) [36][ 200/1320] lr: 2.0000e-03 eta: 2:37:31 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 5.4561 loss: 0.8876 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8876 2023/02/17 18:38:48 - mmengine - INFO - Epoch(train) [36][ 220/1320] lr: 2.0000e-03 eta: 2:37:21 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 5.6183 loss: 1.0330 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.0330 2023/02/17 18:38:57 - mmengine - INFO - Epoch(train) [36][ 240/1320] lr: 2.0000e-03 eta: 2:37:11 time: 0.4800 data_time: 0.0146 memory: 27031 grad_norm: 5.4525 loss: 0.9861 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9861 2023/02/17 18:39:07 - mmengine - INFO - Epoch(train) [36][ 260/1320] lr: 2.0000e-03 eta: 2:37:02 time: 0.4796 data_time: 0.0137 memory: 27031 grad_norm: 5.4375 loss: 1.1516 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.1516 2023/02/17 18:39:16 - mmengine - INFO - Epoch(train) [36][ 280/1320] lr: 2.0000e-03 eta: 2:36:52 time: 0.4812 data_time: 0.0153 memory: 27031 grad_norm: 5.4695 loss: 1.0511 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0511 2023/02/17 18:39:26 - mmengine - INFO - Epoch(train) [36][ 300/1320] lr: 2.0000e-03 eta: 2:36:42 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 5.5974 loss: 1.0718 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.0718 2023/02/17 18:39:36 - mmengine - INFO - Epoch(train) [36][ 320/1320] lr: 2.0000e-03 eta: 2:36:33 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 5.4731 loss: 1.0437 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0437 2023/02/17 18:39:45 - mmengine - INFO - Epoch(train) [36][ 340/1320] lr: 2.0000e-03 eta: 2:36:23 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 5.4291 loss: 0.9545 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9545 2023/02/17 18:39:55 - mmengine - INFO - Epoch(train) [36][ 360/1320] lr: 2.0000e-03 eta: 2:36:13 time: 0.4812 data_time: 0.0156 memory: 27031 grad_norm: 5.4478 loss: 1.0567 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0567 2023/02/17 18:40:04 - mmengine - INFO - Epoch(train) [36][ 380/1320] lr: 2.0000e-03 eta: 2:36:04 time: 0.4803 data_time: 0.0143 memory: 27031 grad_norm: 5.5560 loss: 0.9195 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9195 2023/02/17 18:40:14 - mmengine - INFO - Epoch(train) [36][ 400/1320] lr: 2.0000e-03 eta: 2:35:54 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 5.7290 loss: 1.0648 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 1.0648 2023/02/17 18:40:24 - mmengine - INFO - Epoch(train) [36][ 420/1320] lr: 2.0000e-03 eta: 2:35:44 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 5.5428 loss: 1.0072 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0072 2023/02/17 18:40:33 - mmengine - INFO - Epoch(train) [36][ 440/1320] lr: 2.0000e-03 eta: 2:35:35 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 5.4764 loss: 0.9241 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9241 2023/02/17 18:40:43 - mmengine - INFO - Epoch(train) [36][ 460/1320] lr: 2.0000e-03 eta: 2:35:25 time: 0.4794 data_time: 0.0143 memory: 27031 grad_norm: 5.4840 loss: 0.9497 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9497 2023/02/17 18:40:52 - mmengine - INFO - Epoch(train) [36][ 480/1320] lr: 2.0000e-03 eta: 2:35:16 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 5.6217 loss: 1.0793 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0793 2023/02/17 18:41:02 - mmengine - INFO - Epoch(train) [36][ 500/1320] lr: 2.0000e-03 eta: 2:35:06 time: 0.4797 data_time: 0.0146 memory: 27031 grad_norm: 5.6702 loss: 1.0219 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0219 2023/02/17 18:41:12 - mmengine - INFO - Epoch(train) [36][ 520/1320] lr: 2.0000e-03 eta: 2:34:56 time: 0.4809 data_time: 0.0152 memory: 27031 grad_norm: 5.4802 loss: 1.1493 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1493 2023/02/17 18:41:21 - mmengine - INFO - Epoch(train) [36][ 540/1320] lr: 2.0000e-03 eta: 2:34:47 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 5.6475 loss: 1.0620 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0620 2023/02/17 18:41:31 - mmengine - INFO - Epoch(train) [36][ 560/1320] lr: 2.0000e-03 eta: 2:34:37 time: 0.4799 data_time: 0.0148 memory: 27031 grad_norm: 5.6410 loss: 1.1474 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1474 2023/02/17 18:41:40 - mmengine - INFO - Epoch(train) [36][ 580/1320] lr: 2.0000e-03 eta: 2:34:27 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 5.4709 loss: 0.9858 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9858 2023/02/17 18:41:50 - mmengine - INFO - Epoch(train) [36][ 600/1320] lr: 2.0000e-03 eta: 2:34:18 time: 0.4812 data_time: 0.0152 memory: 27031 grad_norm: 5.7197 loss: 1.0417 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0417 2023/02/17 18:42:00 - mmengine - INFO - Epoch(train) [36][ 620/1320] lr: 2.0000e-03 eta: 2:34:08 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 5.6868 loss: 1.0530 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0530 2023/02/17 18:42:09 - mmengine - INFO - Epoch(train) [36][ 640/1320] lr: 2.0000e-03 eta: 2:33:58 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 5.6997 loss: 1.2923 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.2923 2023/02/17 18:42:19 - mmengine - INFO - Epoch(train) [36][ 660/1320] lr: 2.0000e-03 eta: 2:33:49 time: 0.4811 data_time: 0.0153 memory: 27031 grad_norm: 5.5759 loss: 0.9124 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9124 2023/02/17 18:42:29 - mmengine - INFO - Epoch(train) [36][ 680/1320] lr: 2.0000e-03 eta: 2:33:39 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 5.4885 loss: 1.0228 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0228 2023/02/17 18:42:38 - mmengine - INFO - Epoch(train) [36][ 700/1320] lr: 2.0000e-03 eta: 2:33:29 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 5.5535 loss: 0.9505 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9505 2023/02/17 18:42:48 - mmengine - INFO - Epoch(train) [36][ 720/1320] lr: 2.0000e-03 eta: 2:33:20 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 5.4957 loss: 0.9803 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9803 2023/02/17 18:42:57 - mmengine - INFO - Epoch(train) [36][ 740/1320] lr: 2.0000e-03 eta: 2:33:10 time: 0.4795 data_time: 0.0143 memory: 27031 grad_norm: 5.5245 loss: 1.0529 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0529 2023/02/17 18:43:07 - mmengine - INFO - Epoch(train) [36][ 760/1320] lr: 2.0000e-03 eta: 2:33:00 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 5.5270 loss: 1.0252 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.0252 2023/02/17 18:43:17 - mmengine - INFO - Epoch(train) [36][ 780/1320] lr: 2.0000e-03 eta: 2:32:51 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 5.6652 loss: 0.9554 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9554 2023/02/17 18:43:26 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:43:26 - mmengine - INFO - Epoch(train) [36][ 800/1320] lr: 2.0000e-03 eta: 2:32:41 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 5.6753 loss: 0.9653 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9653 2023/02/17 18:43:36 - mmengine - INFO - Epoch(train) [36][ 820/1320] lr: 2.0000e-03 eta: 2:32:31 time: 0.4813 data_time: 0.0147 memory: 27031 grad_norm: 5.4490 loss: 0.9266 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9266 2023/02/17 18:43:45 - mmengine - INFO - Epoch(train) [36][ 840/1320] lr: 2.0000e-03 eta: 2:32:22 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 5.4554 loss: 0.9931 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9931 2023/02/17 18:43:55 - mmengine - INFO - Epoch(train) [36][ 860/1320] lr: 2.0000e-03 eta: 2:32:12 time: 0.4817 data_time: 0.0158 memory: 27031 grad_norm: 5.5565 loss: 1.1129 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.1129 2023/02/17 18:44:05 - mmengine - INFO - Epoch(train) [36][ 880/1320] lr: 2.0000e-03 eta: 2:32:02 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 5.5916 loss: 1.0865 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0865 2023/02/17 18:44:14 - mmengine - INFO - Epoch(train) [36][ 900/1320] lr: 2.0000e-03 eta: 2:31:53 time: 0.4790 data_time: 0.0133 memory: 27031 grad_norm: 5.7209 loss: 1.1170 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1170 2023/02/17 18:44:24 - mmengine - INFO - Epoch(train) [36][ 920/1320] lr: 2.0000e-03 eta: 2:31:43 time: 0.4809 data_time: 0.0146 memory: 27031 grad_norm: 5.7749 loss: 1.2486 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.2486 2023/02/17 18:44:34 - mmengine - INFO - Epoch(train) [36][ 940/1320] lr: 2.0000e-03 eta: 2:31:33 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 5.6274 loss: 1.0701 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0701 2023/02/17 18:44:43 - mmengine - INFO - Epoch(train) [36][ 960/1320] lr: 2.0000e-03 eta: 2:31:24 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 5.5675 loss: 0.9543 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9543 2023/02/17 18:44:53 - mmengine - INFO - Epoch(train) [36][ 980/1320] lr: 2.0000e-03 eta: 2:31:14 time: 0.4811 data_time: 0.0147 memory: 27031 grad_norm: 5.7052 loss: 1.1465 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1465 2023/02/17 18:45:02 - mmengine - INFO - Epoch(train) [36][1000/1320] lr: 2.0000e-03 eta: 2:31:04 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 5.7010 loss: 1.0168 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0168 2023/02/17 18:45:12 - mmengine - INFO - Epoch(train) [36][1020/1320] lr: 2.0000e-03 eta: 2:30:55 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 5.5516 loss: 1.0237 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0237 2023/02/17 18:45:22 - mmengine - INFO - Epoch(train) [36][1040/1320] lr: 2.0000e-03 eta: 2:30:45 time: 0.4818 data_time: 0.0146 memory: 27031 grad_norm: 5.6161 loss: 1.0502 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0502 2023/02/17 18:45:31 - mmengine - INFO - Epoch(train) [36][1060/1320] lr: 2.0000e-03 eta: 2:30:35 time: 0.4811 data_time: 0.0137 memory: 27031 grad_norm: 5.5456 loss: 1.0499 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0499 2023/02/17 18:45:41 - mmengine - INFO - Epoch(train) [36][1080/1320] lr: 2.0000e-03 eta: 2:30:26 time: 0.4814 data_time: 0.0147 memory: 27031 grad_norm: 5.4515 loss: 0.8045 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8045 2023/02/17 18:45:50 - mmengine - INFO - Epoch(train) [36][1100/1320] lr: 2.0000e-03 eta: 2:30:16 time: 0.4808 data_time: 0.0140 memory: 27031 grad_norm: 5.7163 loss: 1.0934 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0934 2023/02/17 18:46:00 - mmengine - INFO - Epoch(train) [36][1120/1320] lr: 2.0000e-03 eta: 2:30:06 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 5.4567 loss: 0.9430 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9430 2023/02/17 18:46:10 - mmengine - INFO - Epoch(train) [36][1140/1320] lr: 2.0000e-03 eta: 2:29:57 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 5.4926 loss: 0.9885 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9885 2023/02/17 18:46:19 - mmengine - INFO - Epoch(train) [36][1160/1320] lr: 2.0000e-03 eta: 2:29:47 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 5.8009 loss: 0.9427 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9427 2023/02/17 18:46:29 - mmengine - INFO - Epoch(train) [36][1180/1320] lr: 2.0000e-03 eta: 2:29:38 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 5.4184 loss: 0.9927 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9927 2023/02/17 18:46:39 - mmengine - INFO - Epoch(train) [36][1200/1320] lr: 2.0000e-03 eta: 2:29:28 time: 0.4814 data_time: 0.0153 memory: 27031 grad_norm: 5.6187 loss: 1.1080 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1080 2023/02/17 18:46:48 - mmengine - INFO - Epoch(train) [36][1220/1320] lr: 2.0000e-03 eta: 2:29:18 time: 0.4798 data_time: 0.0138 memory: 27031 grad_norm: 5.6478 loss: 1.0269 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0269 2023/02/17 18:46:58 - mmengine - INFO - Epoch(train) [36][1240/1320] lr: 2.0000e-03 eta: 2:29:09 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 5.7197 loss: 1.0464 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0464 2023/02/17 18:47:07 - mmengine - INFO - Epoch(train) [36][1260/1320] lr: 2.0000e-03 eta: 2:28:59 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 5.5292 loss: 1.1250 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1250 2023/02/17 18:47:17 - mmengine - INFO - Epoch(train) [36][1280/1320] lr: 2.0000e-03 eta: 2:28:49 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 5.7269 loss: 1.2584 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2584 2023/02/17 18:47:27 - mmengine - INFO - Epoch(train) [36][1300/1320] lr: 2.0000e-03 eta: 2:28:40 time: 0.4806 data_time: 0.0150 memory: 27031 grad_norm: 5.6714 loss: 1.1626 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1626 2023/02/17 18:47:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:47:36 - mmengine - INFO - Epoch(train) [36][1320/1320] lr: 2.0000e-03 eta: 2:28:30 time: 0.4738 data_time: 0.0148 memory: 27031 grad_norm: 5.7998 loss: 1.1648 top1_acc: 0.4545 top5_acc: 0.8182 loss_cls: 1.1648 2023/02/17 18:47:36 - mmengine - INFO - Saving checkpoint at 36 epochs 2023/02/17 18:47:41 - mmengine - INFO - Epoch(val) [36][ 20/194] eta: 0:00:33 time: 0.1945 data_time: 0.0657 memory: 3265 2023/02/17 18:47:44 - mmengine - INFO - Epoch(val) [36][ 40/194] eta: 0:00:25 time: 0.1397 data_time: 0.0130 memory: 3265 2023/02/17 18:47:47 - mmengine - INFO - Epoch(val) [36][ 60/194] eta: 0:00:21 time: 0.1421 data_time: 0.0152 memory: 3265 2023/02/17 18:47:50 - mmengine - INFO - Epoch(val) [36][ 80/194] eta: 0:00:17 time: 0.1412 data_time: 0.0144 memory: 3265 2023/02/17 18:47:53 - mmengine - INFO - Epoch(val) [36][100/194] eta: 0:00:14 time: 0.1397 data_time: 0.0140 memory: 3265 2023/02/17 18:47:55 - mmengine - INFO - Epoch(val) [36][120/194] eta: 0:00:11 time: 0.1405 data_time: 0.0144 memory: 3265 2023/02/17 18:47:58 - mmengine - INFO - Epoch(val) [36][140/194] eta: 0:00:08 time: 0.1410 data_time: 0.0146 memory: 3265 2023/02/17 18:48:01 - mmengine - INFO - Epoch(val) [36][160/194] eta: 0:00:05 time: 0.1413 data_time: 0.0149 memory: 3265 2023/02/17 18:48:04 - mmengine - INFO - Epoch(val) [36][180/194] eta: 0:00:02 time: 0.1349 data_time: 0.0121 memory: 3265 2023/02/17 18:48:06 - mmengine - INFO - Epoch(val) [36][194/194] acc/top1: 0.6107 acc/top5: 0.8728 acc/mean1: 0.5501 2023/02/17 18:48:17 - mmengine - INFO - Epoch(train) [37][ 20/1320] lr: 2.0000e-03 eta: 2:28:21 time: 0.5358 data_time: 0.0577 memory: 27031 grad_norm: 5.6213 loss: 0.9450 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9450 2023/02/17 18:48:27 - mmengine - INFO - Epoch(train) [37][ 40/1320] lr: 2.0000e-03 eta: 2:28:11 time: 0.4814 data_time: 0.0157 memory: 27031 grad_norm: 5.6311 loss: 0.8531 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8531 2023/02/17 18:48:36 - mmengine - INFO - Epoch(train) [37][ 60/1320] lr: 2.0000e-03 eta: 2:28:01 time: 0.4812 data_time: 0.0154 memory: 27031 grad_norm: 5.3908 loss: 0.8487 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8487 2023/02/17 18:48:46 - mmengine - INFO - Epoch(train) [37][ 80/1320] lr: 2.0000e-03 eta: 2:27:52 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 5.7147 loss: 1.0434 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0434 2023/02/17 18:48:56 - mmengine - INFO - Epoch(train) [37][ 100/1320] lr: 2.0000e-03 eta: 2:27:42 time: 0.4794 data_time: 0.0138 memory: 27031 grad_norm: 5.7074 loss: 1.1045 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.1045 2023/02/17 18:49:05 - mmengine - INFO - Epoch(train) [37][ 120/1320] lr: 2.0000e-03 eta: 2:27:32 time: 0.4803 data_time: 0.0138 memory: 27031 grad_norm: 5.7574 loss: 0.9404 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9404 2023/02/17 18:49:15 - mmengine - INFO - Epoch(train) [37][ 140/1320] lr: 2.0000e-03 eta: 2:27:23 time: 0.4793 data_time: 0.0127 memory: 27031 grad_norm: 5.4857 loss: 1.0183 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0183 2023/02/17 18:49:24 - mmengine - INFO - Epoch(train) [37][ 160/1320] lr: 2.0000e-03 eta: 2:27:13 time: 0.4806 data_time: 0.0138 memory: 27031 grad_norm: 5.6935 loss: 1.0866 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0866 2023/02/17 18:49:34 - mmengine - INFO - Epoch(train) [37][ 180/1320] lr: 2.0000e-03 eta: 2:27:03 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 5.6829 loss: 0.9977 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 0.9977 2023/02/17 18:49:44 - mmengine - INFO - Epoch(train) [37][ 200/1320] lr: 2.0000e-03 eta: 2:26:54 time: 0.4803 data_time: 0.0143 memory: 27031 grad_norm: 5.7175 loss: 1.1380 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.1380 2023/02/17 18:49:53 - mmengine - INFO - Epoch(train) [37][ 220/1320] lr: 2.0000e-03 eta: 2:26:44 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 5.5570 loss: 0.8537 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8537 2023/02/17 18:50:03 - mmengine - INFO - Epoch(train) [37][ 240/1320] lr: 2.0000e-03 eta: 2:26:34 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 5.9235 loss: 0.9322 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9322 2023/02/17 18:50:12 - mmengine - INFO - Epoch(train) [37][ 260/1320] lr: 2.0000e-03 eta: 2:26:25 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 5.7550 loss: 1.0381 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0381 2023/02/17 18:50:22 - mmengine - INFO - Epoch(train) [37][ 280/1320] lr: 2.0000e-03 eta: 2:26:15 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 5.9533 loss: 1.1622 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1622 2023/02/17 18:50:32 - mmengine - INFO - Epoch(train) [37][ 300/1320] lr: 2.0000e-03 eta: 2:26:05 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 5.7217 loss: 1.0997 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0997 2023/02/17 18:50:41 - mmengine - INFO - Epoch(train) [37][ 320/1320] lr: 2.0000e-03 eta: 2:25:56 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 5.6494 loss: 1.0098 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0098 2023/02/17 18:50:51 - mmengine - INFO - Epoch(train) [37][ 340/1320] lr: 2.0000e-03 eta: 2:25:46 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 5.7109 loss: 1.0860 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0860 2023/02/17 18:51:00 - mmengine - INFO - Epoch(train) [37][ 360/1320] lr: 2.0000e-03 eta: 2:25:36 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 5.7730 loss: 1.0603 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0603 2023/02/17 18:51:10 - mmengine - INFO - Epoch(train) [37][ 380/1320] lr: 2.0000e-03 eta: 2:25:27 time: 0.4794 data_time: 0.0142 memory: 27031 grad_norm: 5.6075 loss: 1.0773 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0773 2023/02/17 18:51:20 - mmengine - INFO - Epoch(train) [37][ 400/1320] lr: 2.0000e-03 eta: 2:25:17 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 5.7944 loss: 1.1839 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1839 2023/02/17 18:51:29 - mmengine - INFO - Epoch(train) [37][ 420/1320] lr: 2.0000e-03 eta: 2:25:07 time: 0.4804 data_time: 0.0136 memory: 27031 grad_norm: 5.7320 loss: 0.9897 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9897 2023/02/17 18:51:39 - mmengine - INFO - Epoch(train) [37][ 440/1320] lr: 2.0000e-03 eta: 2:24:58 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 5.7130 loss: 1.0854 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0854 2023/02/17 18:51:49 - mmengine - INFO - Epoch(train) [37][ 460/1320] lr: 2.0000e-03 eta: 2:24:48 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 5.7132 loss: 1.1208 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.1208 2023/02/17 18:51:58 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:51:58 - mmengine - INFO - Epoch(train) [37][ 480/1320] lr: 2.0000e-03 eta: 2:24:39 time: 0.4794 data_time: 0.0141 memory: 27031 grad_norm: 5.6172 loss: 1.2163 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2163 2023/02/17 18:52:08 - mmengine - INFO - Epoch(train) [37][ 500/1320] lr: 2.0000e-03 eta: 2:24:29 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 5.7464 loss: 0.9171 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9171 2023/02/17 18:52:17 - mmengine - INFO - Epoch(train) [37][ 520/1320] lr: 2.0000e-03 eta: 2:24:19 time: 0.4811 data_time: 0.0150 memory: 27031 grad_norm: 5.7531 loss: 1.1574 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1574 2023/02/17 18:52:27 - mmengine - INFO - Epoch(train) [37][ 540/1320] lr: 2.0000e-03 eta: 2:24:10 time: 0.4795 data_time: 0.0137 memory: 27031 grad_norm: 5.7797 loss: 1.0992 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.0992 2023/02/17 18:52:37 - mmengine - INFO - Epoch(train) [37][ 560/1320] lr: 2.0000e-03 eta: 2:24:00 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 5.7913 loss: 0.9847 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9847 2023/02/17 18:52:46 - mmengine - INFO - Epoch(train) [37][ 580/1320] lr: 2.0000e-03 eta: 2:23:50 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 5.7436 loss: 0.8624 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8624 2023/02/17 18:52:56 - mmengine - INFO - Epoch(train) [37][ 600/1320] lr: 2.0000e-03 eta: 2:23:41 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 5.6230 loss: 0.9939 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9939 2023/02/17 18:53:05 - mmengine - INFO - Epoch(train) [37][ 620/1320] lr: 2.0000e-03 eta: 2:23:31 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 5.7861 loss: 1.0949 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0949 2023/02/17 18:53:15 - mmengine - INFO - Epoch(train) [37][ 640/1320] lr: 2.0000e-03 eta: 2:23:21 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 5.8187 loss: 1.0882 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0882 2023/02/17 18:53:25 - mmengine - INFO - Epoch(train) [37][ 660/1320] lr: 2.0000e-03 eta: 2:23:12 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 5.7758 loss: 1.0062 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0062 2023/02/17 18:53:34 - mmengine - INFO - Epoch(train) [37][ 680/1320] lr: 2.0000e-03 eta: 2:23:02 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.6198 loss: 1.1256 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1256 2023/02/17 18:53:44 - mmengine - INFO - Epoch(train) [37][ 700/1320] lr: 2.0000e-03 eta: 2:22:52 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 5.7668 loss: 1.1619 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1619 2023/02/17 18:53:53 - mmengine - INFO - Epoch(train) [37][ 720/1320] lr: 2.0000e-03 eta: 2:22:43 time: 0.4815 data_time: 0.0149 memory: 27031 grad_norm: 5.5400 loss: 0.9735 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.9735 2023/02/17 18:54:03 - mmengine - INFO - Epoch(train) [37][ 740/1320] lr: 2.0000e-03 eta: 2:22:33 time: 0.4806 data_time: 0.0140 memory: 27031 grad_norm: 5.6609 loss: 1.0685 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0685 2023/02/17 18:54:13 - mmengine - INFO - Epoch(train) [37][ 760/1320] lr: 2.0000e-03 eta: 2:22:23 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 5.8130 loss: 0.9410 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9410 2023/02/17 18:54:22 - mmengine - INFO - Epoch(train) [37][ 780/1320] lr: 2.0000e-03 eta: 2:22:14 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 5.7678 loss: 0.8542 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8542 2023/02/17 18:54:32 - mmengine - INFO - Epoch(train) [37][ 800/1320] lr: 2.0000e-03 eta: 2:22:04 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 5.7984 loss: 0.8352 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8352 2023/02/17 18:54:42 - mmengine - INFO - Epoch(train) [37][ 820/1320] lr: 2.0000e-03 eta: 2:21:54 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.5994 loss: 1.0590 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0590 2023/02/17 18:54:51 - mmengine - INFO - Epoch(train) [37][ 840/1320] lr: 2.0000e-03 eta: 2:21:45 time: 0.4812 data_time: 0.0157 memory: 27031 grad_norm: 5.7843 loss: 1.1309 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1309 2023/02/17 18:55:01 - mmengine - INFO - Epoch(train) [37][ 860/1320] lr: 2.0000e-03 eta: 2:21:35 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 5.7909 loss: 0.9886 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9886 2023/02/17 18:55:10 - mmengine - INFO - Epoch(train) [37][ 880/1320] lr: 2.0000e-03 eta: 2:21:25 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 5.9294 loss: 1.0576 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0576 2023/02/17 18:55:20 - mmengine - INFO - Epoch(train) [37][ 900/1320] lr: 2.0000e-03 eta: 2:21:16 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 5.6748 loss: 1.0803 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 1.0803 2023/02/17 18:55:30 - mmengine - INFO - Epoch(train) [37][ 920/1320] lr: 2.0000e-03 eta: 2:21:06 time: 0.4809 data_time: 0.0146 memory: 27031 grad_norm: 5.8863 loss: 1.1748 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1748 2023/02/17 18:55:39 - mmengine - INFO - Epoch(train) [37][ 940/1320] lr: 2.0000e-03 eta: 2:20:56 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 5.8087 loss: 0.9990 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9990 2023/02/17 18:55:49 - mmengine - INFO - Epoch(train) [37][ 960/1320] lr: 2.0000e-03 eta: 2:20:47 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 5.7734 loss: 0.8616 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8616 2023/02/17 18:55:58 - mmengine - INFO - Epoch(train) [37][ 980/1320] lr: 2.0000e-03 eta: 2:20:37 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 5.7732 loss: 1.0832 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0832 2023/02/17 18:56:08 - mmengine - INFO - Epoch(train) [37][1000/1320] lr: 2.0000e-03 eta: 2:20:27 time: 0.4799 data_time: 0.0143 memory: 27031 grad_norm: 5.8287 loss: 1.0173 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0173 2023/02/17 18:56:18 - mmengine - INFO - Epoch(train) [37][1020/1320] lr: 2.0000e-03 eta: 2:20:18 time: 0.4798 data_time: 0.0140 memory: 27031 grad_norm: 5.9449 loss: 1.0380 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0380 2023/02/17 18:56:27 - mmengine - INFO - Epoch(train) [37][1040/1320] lr: 2.0000e-03 eta: 2:20:08 time: 0.4810 data_time: 0.0155 memory: 27031 grad_norm: 5.7228 loss: 1.1485 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1485 2023/02/17 18:56:37 - mmengine - INFO - Epoch(train) [37][1060/1320] lr: 2.0000e-03 eta: 2:19:58 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 5.8228 loss: 1.1406 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1406 2023/02/17 18:56:47 - mmengine - INFO - Epoch(train) [37][1080/1320] lr: 2.0000e-03 eta: 2:19:49 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 5.7861 loss: 1.1034 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.1034 2023/02/17 18:56:56 - mmengine - INFO - Epoch(train) [37][1100/1320] lr: 2.0000e-03 eta: 2:19:39 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 5.5766 loss: 0.8463 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8463 2023/02/17 18:57:06 - mmengine - INFO - Epoch(train) [37][1120/1320] lr: 2.0000e-03 eta: 2:19:30 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 5.8047 loss: 0.9972 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9972 2023/02/17 18:57:15 - mmengine - INFO - Epoch(train) [37][1140/1320] lr: 2.0000e-03 eta: 2:19:20 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 5.7611 loss: 0.9264 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9264 2023/02/17 18:57:25 - mmengine - INFO - Epoch(train) [37][1160/1320] lr: 2.0000e-03 eta: 2:19:10 time: 0.4813 data_time: 0.0152 memory: 27031 grad_norm: 5.7155 loss: 1.1045 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1045 2023/02/17 18:57:35 - mmengine - INFO - Epoch(train) [37][1180/1320] lr: 2.0000e-03 eta: 2:19:01 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 5.7001 loss: 1.0671 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0671 2023/02/17 18:57:44 - mmengine - INFO - Epoch(train) [37][1200/1320] lr: 2.0000e-03 eta: 2:18:51 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 5.9383 loss: 1.1869 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1869 2023/02/17 18:57:54 - mmengine - INFO - Epoch(train) [37][1220/1320] lr: 2.0000e-03 eta: 2:18:41 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 5.8595 loss: 0.9731 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9731 2023/02/17 18:58:03 - mmengine - INFO - Epoch(train) [37][1240/1320] lr: 2.0000e-03 eta: 2:18:32 time: 0.4799 data_time: 0.0145 memory: 27031 grad_norm: 5.6651 loss: 0.9850 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9850 2023/02/17 18:58:13 - mmengine - INFO - Epoch(train) [37][1260/1320] lr: 2.0000e-03 eta: 2:18:22 time: 0.4806 data_time: 0.0151 memory: 27031 grad_norm: 5.8102 loss: 0.9332 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9332 2023/02/17 18:58:23 - mmengine - INFO - Epoch(train) [37][1280/1320] lr: 2.0000e-03 eta: 2:18:12 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 5.7116 loss: 1.1355 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1355 2023/02/17 18:58:32 - mmengine - INFO - Epoch(train) [37][1300/1320] lr: 2.0000e-03 eta: 2:18:03 time: 0.4808 data_time: 0.0152 memory: 27031 grad_norm: 5.9638 loss: 1.2068 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.2068 2023/02/17 18:58:42 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 18:58:42 - mmengine - INFO - Epoch(train) [37][1320/1320] lr: 2.0000e-03 eta: 2:17:53 time: 0.4762 data_time: 0.0170 memory: 27031 grad_norm: 5.9088 loss: 1.1182 top1_acc: 0.4545 top5_acc: 0.7273 loss_cls: 1.1182 2023/02/17 18:58:46 - mmengine - INFO - Epoch(val) [37][ 20/194] eta: 0:00:33 time: 0.1917 data_time: 0.0623 memory: 3265 2023/02/17 18:58:48 - mmengine - INFO - Epoch(val) [37][ 40/194] eta: 0:00:25 time: 0.1403 data_time: 0.0138 memory: 3265 2023/02/17 18:58:51 - mmengine - INFO - Epoch(val) [37][ 60/194] eta: 0:00:21 time: 0.1401 data_time: 0.0144 memory: 3265 2023/02/17 18:58:54 - mmengine - INFO - Epoch(val) [37][ 80/194] eta: 0:00:17 time: 0.1395 data_time: 0.0140 memory: 3265 2023/02/17 18:58:57 - mmengine - INFO - Epoch(val) [37][100/194] eta: 0:00:14 time: 0.1390 data_time: 0.0137 memory: 3265 2023/02/17 18:59:00 - mmengine - INFO - Epoch(val) [37][120/194] eta: 0:00:10 time: 0.1407 data_time: 0.0147 memory: 3265 2023/02/17 18:59:02 - mmengine - INFO - Epoch(val) [37][140/194] eta: 0:00:07 time: 0.1401 data_time: 0.0136 memory: 3265 2023/02/17 18:59:05 - mmengine - INFO - Epoch(val) [37][160/194] eta: 0:00:04 time: 0.1410 data_time: 0.0146 memory: 3265 2023/02/17 18:59:08 - mmengine - INFO - Epoch(val) [37][180/194] eta: 0:00:02 time: 0.1396 data_time: 0.0142 memory: 3265 2023/02/17 18:59:11 - mmengine - INFO - Epoch(val) [37][194/194] acc/top1: 0.6142 acc/top5: 0.8710 acc/mean1: 0.5517 2023/02/17 18:59:22 - mmengine - INFO - Epoch(train) [38][ 20/1320] lr: 2.0000e-03 eta: 2:17:44 time: 0.5422 data_time: 0.0652 memory: 27031 grad_norm: 5.6996 loss: 1.1420 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1420 2023/02/17 18:59:31 - mmengine - INFO - Epoch(train) [38][ 40/1320] lr: 2.0000e-03 eta: 2:17:34 time: 0.4852 data_time: 0.0180 memory: 27031 grad_norm: 5.7396 loss: 1.0321 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0321 2023/02/17 18:59:41 - mmengine - INFO - Epoch(train) [38][ 60/1320] lr: 2.0000e-03 eta: 2:17:24 time: 0.4827 data_time: 0.0164 memory: 27031 grad_norm: 5.6954 loss: 0.9946 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9946 2023/02/17 18:59:51 - mmengine - INFO - Epoch(train) [38][ 80/1320] lr: 2.0000e-03 eta: 2:17:15 time: 0.4810 data_time: 0.0158 memory: 27031 grad_norm: 5.8871 loss: 0.9874 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9874 2023/02/17 19:00:00 - mmengine - INFO - Epoch(train) [38][ 100/1320] lr: 2.0000e-03 eta: 2:17:05 time: 0.4807 data_time: 0.0154 memory: 27031 grad_norm: 5.7074 loss: 1.0630 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0630 2023/02/17 19:00:10 - mmengine - INFO - Epoch(train) [38][ 120/1320] lr: 2.0000e-03 eta: 2:16:56 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 5.7536 loss: 1.0992 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0992 2023/02/17 19:00:19 - mmengine - INFO - Epoch(train) [38][ 140/1320] lr: 2.0000e-03 eta: 2:16:46 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 5.7082 loss: 0.9998 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9998 2023/02/17 19:00:29 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:00:29 - mmengine - INFO - Epoch(train) [38][ 160/1320] lr: 2.0000e-03 eta: 2:16:36 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 5.8068 loss: 1.0062 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0062 2023/02/17 19:00:39 - mmengine - INFO - Epoch(train) [38][ 180/1320] lr: 2.0000e-03 eta: 2:16:27 time: 0.4801 data_time: 0.0129 memory: 27031 grad_norm: 5.7864 loss: 0.9673 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9673 2023/02/17 19:00:48 - mmengine - INFO - Epoch(train) [38][ 200/1320] lr: 2.0000e-03 eta: 2:16:17 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 5.7862 loss: 1.1137 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1137 2023/02/17 19:00:58 - mmengine - INFO - Epoch(train) [38][ 220/1320] lr: 2.0000e-03 eta: 2:16:07 time: 0.4793 data_time: 0.0139 memory: 27031 grad_norm: 5.8462 loss: 0.8507 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8507 2023/02/17 19:01:07 - mmengine - INFO - Epoch(train) [38][ 240/1320] lr: 2.0000e-03 eta: 2:15:58 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 5.7713 loss: 0.9484 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9484 2023/02/17 19:01:17 - mmengine - INFO - Epoch(train) [38][ 260/1320] lr: 2.0000e-03 eta: 2:15:48 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 5.9018 loss: 1.0720 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0720 2023/02/17 19:01:27 - mmengine - INFO - Epoch(train) [38][ 280/1320] lr: 2.0000e-03 eta: 2:15:38 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 5.7036 loss: 1.0618 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.0618 2023/02/17 19:01:36 - mmengine - INFO - Epoch(train) [38][ 300/1320] lr: 2.0000e-03 eta: 2:15:29 time: 0.4814 data_time: 0.0156 memory: 27031 grad_norm: 5.8687 loss: 0.9393 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9393 2023/02/17 19:01:46 - mmengine - INFO - Epoch(train) [38][ 320/1320] lr: 2.0000e-03 eta: 2:15:19 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 5.7577 loss: 0.9995 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9995 2023/02/17 19:01:55 - mmengine - INFO - Epoch(train) [38][ 340/1320] lr: 2.0000e-03 eta: 2:15:09 time: 0.4802 data_time: 0.0138 memory: 27031 grad_norm: 5.8070 loss: 0.9206 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9206 2023/02/17 19:02:05 - mmengine - INFO - Epoch(train) [38][ 360/1320] lr: 2.0000e-03 eta: 2:15:00 time: 0.4815 data_time: 0.0153 memory: 27031 grad_norm: 5.9776 loss: 0.9580 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9580 2023/02/17 19:02:15 - mmengine - INFO - Epoch(train) [38][ 380/1320] lr: 2.0000e-03 eta: 2:14:50 time: 0.4801 data_time: 0.0138 memory: 27031 grad_norm: 5.9756 loss: 1.0212 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0212 2023/02/17 19:02:24 - mmengine - INFO - Epoch(train) [38][ 400/1320] lr: 2.0000e-03 eta: 2:14:40 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 6.0059 loss: 1.0698 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0698 2023/02/17 19:02:34 - mmengine - INFO - Epoch(train) [38][ 420/1320] lr: 2.0000e-03 eta: 2:14:31 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 5.8683 loss: 1.0216 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0216 2023/02/17 19:02:43 - mmengine - INFO - Epoch(train) [38][ 440/1320] lr: 2.0000e-03 eta: 2:14:21 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 5.9365 loss: 1.0317 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.0317 2023/02/17 19:02:53 - mmengine - INFO - Epoch(train) [38][ 460/1320] lr: 2.0000e-03 eta: 2:14:11 time: 0.4815 data_time: 0.0148 memory: 27031 grad_norm: 5.9665 loss: 1.0064 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0064 2023/02/17 19:03:03 - mmengine - INFO - Epoch(train) [38][ 480/1320] lr: 2.0000e-03 eta: 2:14:02 time: 0.4801 data_time: 0.0149 memory: 27031 grad_norm: 5.8442 loss: 0.9515 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9515 2023/02/17 19:03:12 - mmengine - INFO - Epoch(train) [38][ 500/1320] lr: 2.0000e-03 eta: 2:13:52 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 5.9152 loss: 1.0605 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0605 2023/02/17 19:03:22 - mmengine - INFO - Epoch(train) [38][ 520/1320] lr: 2.0000e-03 eta: 2:13:42 time: 0.4812 data_time: 0.0145 memory: 27031 grad_norm: 5.9415 loss: 0.9855 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9855 2023/02/17 19:03:32 - mmengine - INFO - Epoch(train) [38][ 540/1320] lr: 2.0000e-03 eta: 2:13:33 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 5.9564 loss: 1.0010 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0010 2023/02/17 19:03:41 - mmengine - INFO - Epoch(train) [38][ 560/1320] lr: 2.0000e-03 eta: 2:13:23 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 5.8589 loss: 0.9121 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9121 2023/02/17 19:03:51 - mmengine - INFO - Epoch(train) [38][ 580/1320] lr: 2.0000e-03 eta: 2:13:13 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 5.7619 loss: 0.9170 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9170 2023/02/17 19:04:00 - mmengine - INFO - Epoch(train) [38][ 600/1320] lr: 2.0000e-03 eta: 2:13:04 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 6.0104 loss: 1.1527 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1527 2023/02/17 19:04:10 - mmengine - INFO - Epoch(train) [38][ 620/1320] lr: 2.0000e-03 eta: 2:12:54 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 5.8896 loss: 0.7815 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7815 2023/02/17 19:04:20 - mmengine - INFO - Epoch(train) [38][ 640/1320] lr: 2.0000e-03 eta: 2:12:44 time: 0.4812 data_time: 0.0144 memory: 27031 grad_norm: 6.1075 loss: 1.0031 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0031 2023/02/17 19:04:29 - mmengine - INFO - Epoch(train) [38][ 660/1320] lr: 2.0000e-03 eta: 2:12:35 time: 0.4800 data_time: 0.0133 memory: 27031 grad_norm: 6.0207 loss: 0.9359 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9359 2023/02/17 19:04:39 - mmengine - INFO - Epoch(train) [38][ 680/1320] lr: 2.0000e-03 eta: 2:12:25 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 6.0528 loss: 1.0636 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0636 2023/02/17 19:04:48 - mmengine - INFO - Epoch(train) [38][ 700/1320] lr: 2.0000e-03 eta: 2:12:16 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 6.1948 loss: 0.9925 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9925 2023/02/17 19:04:58 - mmengine - INFO - Epoch(train) [38][ 720/1320] lr: 2.0000e-03 eta: 2:12:06 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 6.0866 loss: 0.9669 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9669 2023/02/17 19:05:08 - mmengine - INFO - Epoch(train) [38][ 740/1320] lr: 2.0000e-03 eta: 2:11:56 time: 0.4807 data_time: 0.0154 memory: 27031 grad_norm: 5.9586 loss: 1.0992 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0992 2023/02/17 19:05:17 - mmengine - INFO - Epoch(train) [38][ 760/1320] lr: 2.0000e-03 eta: 2:11:47 time: 0.4806 data_time: 0.0149 memory: 27031 grad_norm: 5.8044 loss: 0.8664 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8664 2023/02/17 19:05:27 - mmengine - INFO - Epoch(train) [38][ 780/1320] lr: 2.0000e-03 eta: 2:11:37 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.0383 loss: 0.8815 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8815 2023/02/17 19:05:37 - mmengine - INFO - Epoch(train) [38][ 800/1320] lr: 2.0000e-03 eta: 2:11:27 time: 0.4808 data_time: 0.0143 memory: 27031 grad_norm: 6.0440 loss: 1.1416 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1416 2023/02/17 19:05:46 - mmengine - INFO - Epoch(train) [38][ 820/1320] lr: 2.0000e-03 eta: 2:11:18 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.0534 loss: 1.1084 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1084 2023/02/17 19:05:56 - mmengine - INFO - Epoch(train) [38][ 840/1320] lr: 2.0000e-03 eta: 2:11:08 time: 0.4813 data_time: 0.0149 memory: 27031 grad_norm: 5.8498 loss: 1.0546 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0546 2023/02/17 19:06:05 - mmengine - INFO - Epoch(train) [38][ 860/1320] lr: 2.0000e-03 eta: 2:10:58 time: 0.4804 data_time: 0.0137 memory: 27031 grad_norm: 6.0333 loss: 0.9243 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9243 2023/02/17 19:06:15 - mmengine - INFO - Epoch(train) [38][ 880/1320] lr: 2.0000e-03 eta: 2:10:49 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 5.9504 loss: 1.0138 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0138 2023/02/17 19:06:25 - mmengine - INFO - Epoch(train) [38][ 900/1320] lr: 2.0000e-03 eta: 2:10:39 time: 0.4808 data_time: 0.0151 memory: 27031 grad_norm: 6.0103 loss: 0.9662 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9662 2023/02/17 19:06:34 - mmengine - INFO - Epoch(train) [38][ 920/1320] lr: 2.0000e-03 eta: 2:10:29 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 5.9053 loss: 1.0528 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0528 2023/02/17 19:06:44 - mmengine - INFO - Epoch(train) [38][ 940/1320] lr: 2.0000e-03 eta: 2:10:20 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 5.9868 loss: 0.9422 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9422 2023/02/17 19:06:53 - mmengine - INFO - Epoch(train) [38][ 960/1320] lr: 2.0000e-03 eta: 2:10:10 time: 0.4815 data_time: 0.0151 memory: 27031 grad_norm: 5.8612 loss: 0.9444 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9444 2023/02/17 19:07:03 - mmengine - INFO - Epoch(train) [38][ 980/1320] lr: 2.0000e-03 eta: 2:10:00 time: 0.4800 data_time: 0.0139 memory: 27031 grad_norm: 5.9867 loss: 0.9171 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9171 2023/02/17 19:07:13 - mmengine - INFO - Epoch(train) [38][1000/1320] lr: 2.0000e-03 eta: 2:09:51 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 6.0498 loss: 1.0514 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0514 2023/02/17 19:07:22 - mmengine - INFO - Epoch(train) [38][1020/1320] lr: 2.0000e-03 eta: 2:09:41 time: 0.4816 data_time: 0.0151 memory: 27031 grad_norm: 6.0036 loss: 1.0739 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0739 2023/02/17 19:07:32 - mmengine - INFO - Epoch(train) [38][1040/1320] lr: 2.0000e-03 eta: 2:09:31 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 6.0318 loss: 1.0070 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0070 2023/02/17 19:07:42 - mmengine - INFO - Epoch(train) [38][1060/1320] lr: 2.0000e-03 eta: 2:09:22 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 5.9803 loss: 1.0616 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0616 2023/02/17 19:07:51 - mmengine - INFO - Epoch(train) [38][1080/1320] lr: 2.0000e-03 eta: 2:09:12 time: 0.4814 data_time: 0.0146 memory: 27031 grad_norm: 5.9200 loss: 1.0315 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0315 2023/02/17 19:08:01 - mmengine - INFO - Epoch(train) [38][1100/1320] lr: 2.0000e-03 eta: 2:09:02 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.0778 loss: 1.0440 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.0440 2023/02/17 19:08:10 - mmengine - INFO - Epoch(train) [38][1120/1320] lr: 2.0000e-03 eta: 2:08:53 time: 0.4810 data_time: 0.0150 memory: 27031 grad_norm: 5.9921 loss: 1.0241 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0241 2023/02/17 19:08:20 - mmengine - INFO - Epoch(train) [38][1140/1320] lr: 2.0000e-03 eta: 2:08:43 time: 0.4815 data_time: 0.0154 memory: 27031 grad_norm: 5.8312 loss: 1.0059 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0059 2023/02/17 19:08:30 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:08:30 - mmengine - INFO - Epoch(train) [38][1160/1320] lr: 2.0000e-03 eta: 2:08:34 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 5.9292 loss: 1.1003 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 1.1003 2023/02/17 19:08:39 - mmengine - INFO - Epoch(train) [38][1180/1320] lr: 2.0000e-03 eta: 2:08:24 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 5.9722 loss: 1.0284 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0284 2023/02/17 19:08:49 - mmengine - INFO - Epoch(train) [38][1200/1320] lr: 2.0000e-03 eta: 2:08:14 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 5.9143 loss: 1.2372 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2372 2023/02/17 19:08:58 - mmengine - INFO - Epoch(train) [38][1220/1320] lr: 2.0000e-03 eta: 2:08:05 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 6.0266 loss: 1.1345 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.1345 2023/02/17 19:09:08 - mmengine - INFO - Epoch(train) [38][1240/1320] lr: 2.0000e-03 eta: 2:07:55 time: 0.4810 data_time: 0.0141 memory: 27031 grad_norm: 6.0241 loss: 0.9430 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9430 2023/02/17 19:09:18 - mmengine - INFO - Epoch(train) [38][1260/1320] lr: 2.0000e-03 eta: 2:07:45 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 5.9590 loss: 1.0474 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.0474 2023/02/17 19:09:27 - mmengine - INFO - Epoch(train) [38][1280/1320] lr: 2.0000e-03 eta: 2:07:36 time: 0.4812 data_time: 0.0142 memory: 27031 grad_norm: 5.9269 loss: 0.9371 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9371 2023/02/17 19:09:37 - mmengine - INFO - Epoch(train) [38][1300/1320] lr: 2.0000e-03 eta: 2:07:26 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 6.0914 loss: 0.9719 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9719 2023/02/17 19:09:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:09:46 - mmengine - INFO - Epoch(train) [38][1320/1320] lr: 2.0000e-03 eta: 2:07:16 time: 0.4747 data_time: 0.0164 memory: 27031 grad_norm: 6.1161 loss: 1.0664 top1_acc: 0.5455 top5_acc: 0.6364 loss_cls: 1.0664 2023/02/17 19:09:50 - mmengine - INFO - Epoch(val) [38][ 20/194] eta: 0:00:33 time: 0.1952 data_time: 0.0657 memory: 3265 2023/02/17 19:09:53 - mmengine - INFO - Epoch(val) [38][ 40/194] eta: 0:00:25 time: 0.1383 data_time: 0.0136 memory: 3265 2023/02/17 19:09:56 - mmengine - INFO - Epoch(val) [38][ 60/194] eta: 0:00:21 time: 0.1379 data_time: 0.0140 memory: 3265 2023/02/17 19:09:59 - mmengine - INFO - Epoch(val) [38][ 80/194] eta: 0:00:17 time: 0.1358 data_time: 0.0122 memory: 3265 2023/02/17 19:10:01 - mmengine - INFO - Epoch(val) [38][100/194] eta: 0:00:14 time: 0.1379 data_time: 0.0146 memory: 3265 2023/02/17 19:10:04 - mmengine - INFO - Epoch(val) [38][120/194] eta: 0:00:10 time: 0.1366 data_time: 0.0128 memory: 3265 2023/02/17 19:10:07 - mmengine - INFO - Epoch(val) [38][140/194] eta: 0:00:07 time: 0.1392 data_time: 0.0136 memory: 3265 2023/02/17 19:10:10 - mmengine - INFO - Epoch(val) [38][160/194] eta: 0:00:04 time: 0.1370 data_time: 0.0133 memory: 3265 2023/02/17 19:10:12 - mmengine - INFO - Epoch(val) [38][180/194] eta: 0:00:02 time: 0.1373 data_time: 0.0130 memory: 3265 2023/02/17 19:10:15 - mmengine - INFO - Epoch(val) [38][194/194] acc/top1: 0.6084 acc/top5: 0.8704 acc/mean1: 0.5471 2023/02/17 19:10:26 - mmengine - INFO - Epoch(train) [39][ 20/1320] lr: 2.0000e-03 eta: 2:07:07 time: 0.5349 data_time: 0.0618 memory: 27031 grad_norm: 5.9770 loss: 0.9832 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9832 2023/02/17 19:10:36 - mmengine - INFO - Epoch(train) [39][ 40/1320] lr: 2.0000e-03 eta: 2:06:57 time: 0.4809 data_time: 0.0139 memory: 27031 grad_norm: 5.8629 loss: 1.0149 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0149 2023/02/17 19:10:45 - mmengine - INFO - Epoch(train) [39][ 60/1320] lr: 2.0000e-03 eta: 2:06:48 time: 0.4789 data_time: 0.0135 memory: 27031 grad_norm: 5.7547 loss: 0.9732 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9732 2023/02/17 19:10:55 - mmengine - INFO - Epoch(train) [39][ 80/1320] lr: 2.0000e-03 eta: 2:06:38 time: 0.4797 data_time: 0.0135 memory: 27031 grad_norm: 5.8233 loss: 0.9880 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9880 2023/02/17 19:11:04 - mmengine - INFO - Epoch(train) [39][ 100/1320] lr: 2.0000e-03 eta: 2:06:28 time: 0.4796 data_time: 0.0143 memory: 27031 grad_norm: 5.9215 loss: 0.9999 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9999 2023/02/17 19:11:14 - mmengine - INFO - Epoch(train) [39][ 120/1320] lr: 2.0000e-03 eta: 2:06:19 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 6.0342 loss: 1.1053 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1053 2023/02/17 19:11:23 - mmengine - INFO - Epoch(train) [39][ 140/1320] lr: 2.0000e-03 eta: 2:06:09 time: 0.4791 data_time: 0.0137 memory: 27031 grad_norm: 5.7908 loss: 1.0025 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0025 2023/02/17 19:11:33 - mmengine - INFO - Epoch(train) [39][ 160/1320] lr: 2.0000e-03 eta: 2:05:59 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 6.0192 loss: 0.8959 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8959 2023/02/17 19:11:43 - mmengine - INFO - Epoch(train) [39][ 180/1320] lr: 2.0000e-03 eta: 2:05:50 time: 0.4785 data_time: 0.0136 memory: 27031 grad_norm: 6.1021 loss: 1.0569 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.0569 2023/02/17 19:11:52 - mmengine - INFO - Epoch(train) [39][ 200/1320] lr: 2.0000e-03 eta: 2:05:40 time: 0.4823 data_time: 0.0163 memory: 27031 grad_norm: 5.9145 loss: 0.9759 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9759 2023/02/17 19:12:02 - mmengine - INFO - Epoch(train) [39][ 220/1320] lr: 2.0000e-03 eta: 2:05:30 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 6.0537 loss: 0.9622 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 0.9622 2023/02/17 19:12:12 - mmengine - INFO - Epoch(train) [39][ 240/1320] lr: 2.0000e-03 eta: 2:05:21 time: 0.4802 data_time: 0.0138 memory: 27031 grad_norm: 6.0467 loss: 0.9463 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9463 2023/02/17 19:12:21 - mmengine - INFO - Epoch(train) [39][ 260/1320] lr: 2.0000e-03 eta: 2:05:11 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 5.8702 loss: 1.0716 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0716 2023/02/17 19:12:31 - mmengine - INFO - Epoch(train) [39][ 280/1320] lr: 2.0000e-03 eta: 2:05:01 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 5.9107 loss: 1.2130 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2130 2023/02/17 19:12:40 - mmengine - INFO - Epoch(train) [39][ 300/1320] lr: 2.0000e-03 eta: 2:04:52 time: 0.4801 data_time: 0.0143 memory: 27031 grad_norm: 6.1388 loss: 1.0978 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0978 2023/02/17 19:12:50 - mmengine - INFO - Epoch(train) [39][ 320/1320] lr: 2.0000e-03 eta: 2:04:42 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 6.0084 loss: 0.9225 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.9225 2023/02/17 19:13:00 - mmengine - INFO - Epoch(train) [39][ 340/1320] lr: 2.0000e-03 eta: 2:04:32 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 5.9863 loss: 1.0251 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0251 2023/02/17 19:13:09 - mmengine - INFO - Epoch(train) [39][ 360/1320] lr: 2.0000e-03 eta: 2:04:23 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 5.9313 loss: 0.9528 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9528 2023/02/17 19:13:19 - mmengine - INFO - Epoch(train) [39][ 380/1320] lr: 2.0000e-03 eta: 2:04:13 time: 0.4815 data_time: 0.0145 memory: 27031 grad_norm: 6.0892 loss: 1.0054 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0054 2023/02/17 19:13:28 - mmengine - INFO - Epoch(train) [39][ 400/1320] lr: 2.0000e-03 eta: 2:04:04 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.3120 loss: 1.1226 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1226 2023/02/17 19:13:38 - mmengine - INFO - Epoch(train) [39][ 420/1320] lr: 2.0000e-03 eta: 2:03:54 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 6.0064 loss: 1.1169 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1169 2023/02/17 19:13:48 - mmengine - INFO - Epoch(train) [39][ 440/1320] lr: 2.0000e-03 eta: 2:03:44 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 6.0133 loss: 0.9474 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9474 2023/02/17 19:13:57 - mmengine - INFO - Epoch(train) [39][ 460/1320] lr: 2.0000e-03 eta: 2:03:35 time: 0.4815 data_time: 0.0155 memory: 27031 grad_norm: 5.9023 loss: 0.8897 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8897 2023/02/17 19:14:07 - mmengine - INFO - Epoch(train) [39][ 480/1320] lr: 2.0000e-03 eta: 2:03:25 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 6.1436 loss: 1.1127 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1127 2023/02/17 19:14:16 - mmengine - INFO - Epoch(train) [39][ 500/1320] lr: 2.0000e-03 eta: 2:03:15 time: 0.4796 data_time: 0.0138 memory: 27031 grad_norm: 6.1190 loss: 0.9860 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9860 2023/02/17 19:14:26 - mmengine - INFO - Epoch(train) [39][ 520/1320] lr: 2.0000e-03 eta: 2:03:06 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 5.9868 loss: 0.9053 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9053 2023/02/17 19:14:36 - mmengine - INFO - Epoch(train) [39][ 540/1320] lr: 2.0000e-03 eta: 2:02:56 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 6.0844 loss: 1.0154 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0154 2023/02/17 19:14:45 - mmengine - INFO - Epoch(train) [39][ 560/1320] lr: 2.0000e-03 eta: 2:02:46 time: 0.4806 data_time: 0.0139 memory: 27031 grad_norm: 6.0248 loss: 1.0193 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0193 2023/02/17 19:14:55 - mmengine - INFO - Epoch(train) [39][ 580/1320] lr: 2.0000e-03 eta: 2:02:37 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 5.9816 loss: 0.9787 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9787 2023/02/17 19:15:05 - mmengine - INFO - Epoch(train) [39][ 600/1320] lr: 2.0000e-03 eta: 2:02:27 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 5.9538 loss: 0.9607 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9607 2023/02/17 19:15:14 - mmengine - INFO - Epoch(train) [39][ 620/1320] lr: 2.0000e-03 eta: 2:02:17 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 5.9717 loss: 0.9659 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9659 2023/02/17 19:15:24 - mmengine - INFO - Epoch(train) [39][ 640/1320] lr: 2.0000e-03 eta: 2:02:08 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.2606 loss: 0.9347 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9347 2023/02/17 19:15:33 - mmengine - INFO - Epoch(train) [39][ 660/1320] lr: 2.0000e-03 eta: 2:01:58 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.2058 loss: 1.0283 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0283 2023/02/17 19:15:43 - mmengine - INFO - Epoch(train) [39][ 680/1320] lr: 2.0000e-03 eta: 2:01:48 time: 0.4794 data_time: 0.0140 memory: 27031 grad_norm: 6.2274 loss: 1.1424 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1424 2023/02/17 19:15:53 - mmengine - INFO - Epoch(train) [39][ 700/1320] lr: 2.0000e-03 eta: 2:01:39 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.1689 loss: 0.8518 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8518 2023/02/17 19:16:02 - mmengine - INFO - Epoch(train) [39][ 720/1320] lr: 2.0000e-03 eta: 2:01:29 time: 0.4793 data_time: 0.0131 memory: 27031 grad_norm: 5.9959 loss: 0.9374 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9374 2023/02/17 19:16:12 - mmengine - INFO - Epoch(train) [39][ 740/1320] lr: 2.0000e-03 eta: 2:01:19 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 6.0858 loss: 1.0311 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0311 2023/02/17 19:16:21 - mmengine - INFO - Epoch(train) [39][ 760/1320] lr: 2.0000e-03 eta: 2:01:10 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 6.0130 loss: 1.0293 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0293 2023/02/17 19:16:31 - mmengine - INFO - Epoch(train) [39][ 780/1320] lr: 2.0000e-03 eta: 2:01:00 time: 0.4804 data_time: 0.0139 memory: 27031 grad_norm: 6.0804 loss: 0.9349 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9349 2023/02/17 19:16:41 - mmengine - INFO - Epoch(train) [39][ 800/1320] lr: 2.0000e-03 eta: 2:00:50 time: 0.4806 data_time: 0.0151 memory: 27031 grad_norm: 6.3572 loss: 1.0838 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0838 2023/02/17 19:16:50 - mmengine - INFO - Epoch(train) [39][ 820/1320] lr: 2.0000e-03 eta: 2:00:41 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 6.2180 loss: 0.9712 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9712 2023/02/17 19:17:00 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:17:00 - mmengine - INFO - Epoch(train) [39][ 840/1320] lr: 2.0000e-03 eta: 2:00:31 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.0576 loss: 1.1188 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.1188 2023/02/17 19:17:10 - mmengine - INFO - Epoch(train) [39][ 860/1320] lr: 2.0000e-03 eta: 2:00:21 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 6.1118 loss: 1.0223 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0223 2023/02/17 19:17:19 - mmengine - INFO - Epoch(train) [39][ 880/1320] lr: 2.0000e-03 eta: 2:00:12 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 6.0835 loss: 0.9764 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9764 2023/02/17 19:17:29 - mmengine - INFO - Epoch(train) [39][ 900/1320] lr: 2.0000e-03 eta: 2:00:02 time: 0.4800 data_time: 0.0139 memory: 27031 grad_norm: 6.2468 loss: 0.9230 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9230 2023/02/17 19:17:38 - mmengine - INFO - Epoch(train) [39][ 920/1320] lr: 2.0000e-03 eta: 1:59:53 time: 0.4823 data_time: 0.0151 memory: 27031 grad_norm: 6.2889 loss: 0.9597 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9597 2023/02/17 19:17:48 - mmengine - INFO - Epoch(train) [39][ 940/1320] lr: 2.0000e-03 eta: 1:59:43 time: 0.4802 data_time: 0.0138 memory: 27031 grad_norm: 6.2560 loss: 0.9319 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9319 2023/02/17 19:17:58 - mmengine - INFO - Epoch(train) [39][ 960/1320] lr: 2.0000e-03 eta: 1:59:33 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 6.2593 loss: 1.0760 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0760 2023/02/17 19:18:07 - mmengine - INFO - Epoch(train) [39][ 980/1320] lr: 2.0000e-03 eta: 1:59:24 time: 0.4813 data_time: 0.0140 memory: 27031 grad_norm: 6.2824 loss: 1.0218 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0218 2023/02/17 19:18:17 - mmengine - INFO - Epoch(train) [39][1000/1320] lr: 2.0000e-03 eta: 1:59:14 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.1900 loss: 1.0472 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0472 2023/02/17 19:18:26 - mmengine - INFO - Epoch(train) [39][1020/1320] lr: 2.0000e-03 eta: 1:59:04 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 6.2525 loss: 1.0536 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0536 2023/02/17 19:18:36 - mmengine - INFO - Epoch(train) [39][1040/1320] lr: 2.0000e-03 eta: 1:58:55 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 6.0648 loss: 0.8747 top1_acc: 0.6875 top5_acc: 0.7500 loss_cls: 0.8747 2023/02/17 19:18:46 - mmengine - INFO - Epoch(train) [39][1060/1320] lr: 2.0000e-03 eta: 1:58:45 time: 0.4796 data_time: 0.0144 memory: 27031 grad_norm: 6.3117 loss: 0.9960 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9960 2023/02/17 19:18:55 - mmengine - INFO - Epoch(train) [39][1080/1320] lr: 2.0000e-03 eta: 1:58:35 time: 0.4808 data_time: 0.0143 memory: 27031 grad_norm: 6.2006 loss: 0.8727 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8727 2023/02/17 19:19:05 - mmengine - INFO - Epoch(train) [39][1100/1320] lr: 2.0000e-03 eta: 1:58:26 time: 0.4826 data_time: 0.0161 memory: 27031 grad_norm: 6.0420 loss: 1.0287 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0287 2023/02/17 19:19:15 - mmengine - INFO - Epoch(train) [39][1120/1320] lr: 2.0000e-03 eta: 1:58:16 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 6.2620 loss: 0.9889 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9889 2023/02/17 19:19:24 - mmengine - INFO - Epoch(train) [39][1140/1320] lr: 2.0000e-03 eta: 1:58:06 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 6.1602 loss: 1.0394 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0394 2023/02/17 19:19:34 - mmengine - INFO - Epoch(train) [39][1160/1320] lr: 2.0000e-03 eta: 1:57:57 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 6.1484 loss: 1.0284 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0284 2023/02/17 19:19:43 - mmengine - INFO - Epoch(train) [39][1180/1320] lr: 2.0000e-03 eta: 1:57:47 time: 0.4813 data_time: 0.0154 memory: 27031 grad_norm: 6.2939 loss: 1.0306 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0306 2023/02/17 19:19:53 - mmengine - INFO - Epoch(train) [39][1200/1320] lr: 2.0000e-03 eta: 1:57:37 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 6.1619 loss: 0.9915 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9915 2023/02/17 19:20:03 - mmengine - INFO - Epoch(train) [39][1220/1320] lr: 2.0000e-03 eta: 1:57:28 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 6.1373 loss: 1.0186 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0186 2023/02/17 19:20:12 - mmengine - INFO - Epoch(train) [39][1240/1320] lr: 2.0000e-03 eta: 1:57:18 time: 0.4805 data_time: 0.0148 memory: 27031 grad_norm: 6.3051 loss: 0.8320 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8320 2023/02/17 19:20:22 - mmengine - INFO - Epoch(train) [39][1260/1320] lr: 2.0000e-03 eta: 1:57:08 time: 0.4809 data_time: 0.0141 memory: 27031 grad_norm: 6.1989 loss: 1.1066 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1066 2023/02/17 19:20:31 - mmengine - INFO - Epoch(train) [39][1280/1320] lr: 2.0000e-03 eta: 1:56:59 time: 0.4802 data_time: 0.0147 memory: 27031 grad_norm: 6.2038 loss: 0.9478 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9478 2023/02/17 19:20:41 - mmengine - INFO - Epoch(train) [39][1300/1320] lr: 2.0000e-03 eta: 1:56:49 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 6.0964 loss: 0.9759 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9759 2023/02/17 19:20:51 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:20:51 - mmengine - INFO - Epoch(train) [39][1320/1320] lr: 2.0000e-03 eta: 1:56:40 time: 0.4740 data_time: 0.0154 memory: 27031 grad_norm: 6.2558 loss: 1.0591 top1_acc: 0.8182 top5_acc: 0.8182 loss_cls: 1.0591 2023/02/17 19:20:51 - mmengine - INFO - Saving checkpoint at 39 epochs 2023/02/17 19:20:56 - mmengine - INFO - Epoch(val) [39][ 20/194] eta: 0:00:33 time: 0.1909 data_time: 0.0632 memory: 3265 2023/02/17 19:20:58 - mmengine - INFO - Epoch(val) [39][ 40/194] eta: 0:00:25 time: 0.1388 data_time: 0.0145 memory: 3265 2023/02/17 19:21:01 - mmengine - INFO - Epoch(val) [39][ 60/194] eta: 0:00:20 time: 0.1386 data_time: 0.0134 memory: 3265 2023/02/17 19:21:04 - mmengine - INFO - Epoch(val) [39][ 80/194] eta: 0:00:17 time: 0.1393 data_time: 0.0142 memory: 3265 2023/02/17 19:21:07 - mmengine - INFO - Epoch(val) [39][100/194] eta: 0:00:14 time: 0.1387 data_time: 0.0141 memory: 3265 2023/02/17 19:21:10 - mmengine - INFO - Epoch(val) [39][120/194] eta: 0:00:10 time: 0.1380 data_time: 0.0134 memory: 3265 2023/02/17 19:21:12 - mmengine - INFO - Epoch(val) [39][140/194] eta: 0:00:07 time: 0.1377 data_time: 0.0135 memory: 3265 2023/02/17 19:21:15 - mmengine - INFO - Epoch(val) [39][160/194] eta: 0:00:04 time: 0.1388 data_time: 0.0144 memory: 3265 2023/02/17 19:21:18 - mmengine - INFO - Epoch(val) [39][180/194] eta: 0:00:02 time: 0.1364 data_time: 0.0129 memory: 3265 2023/02/17 19:21:20 - mmengine - INFO - Epoch(val) [39][194/194] acc/top1: 0.6158 acc/top5: 0.8740 acc/mean1: 0.5553 2023/02/17 19:21:31 - mmengine - INFO - Epoch(train) [40][ 20/1320] lr: 2.0000e-03 eta: 1:56:30 time: 0.5349 data_time: 0.0589 memory: 27031 grad_norm: 6.2346 loss: 1.2328 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.2328 2023/02/17 19:21:41 - mmengine - INFO - Epoch(train) [40][ 40/1320] lr: 2.0000e-03 eta: 1:56:21 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 6.1284 loss: 0.9335 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9335 2023/02/17 19:21:50 - mmengine - INFO - Epoch(train) [40][ 60/1320] lr: 2.0000e-03 eta: 1:56:11 time: 0.4797 data_time: 0.0143 memory: 27031 grad_norm: 6.2437 loss: 0.9254 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9254 2023/02/17 19:22:00 - mmengine - INFO - Epoch(train) [40][ 80/1320] lr: 2.0000e-03 eta: 1:56:01 time: 0.4821 data_time: 0.0170 memory: 27031 grad_norm: 6.0269 loss: 1.2038 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2038 2023/02/17 19:22:10 - mmengine - INFO - Epoch(train) [40][ 100/1320] lr: 2.0000e-03 eta: 1:55:52 time: 0.4808 data_time: 0.0136 memory: 27031 grad_norm: 6.0256 loss: 0.9513 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9513 2023/02/17 19:22:19 - mmengine - INFO - Epoch(train) [40][ 120/1320] lr: 2.0000e-03 eta: 1:55:42 time: 0.4818 data_time: 0.0150 memory: 27031 grad_norm: 6.1768 loss: 1.0623 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0623 2023/02/17 19:22:29 - mmengine - INFO - Epoch(train) [40][ 140/1320] lr: 2.0000e-03 eta: 1:55:32 time: 0.4801 data_time: 0.0136 memory: 27031 grad_norm: 6.2578 loss: 0.9717 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9717 2023/02/17 19:22:38 - mmengine - INFO - Epoch(train) [40][ 160/1320] lr: 2.0000e-03 eta: 1:55:23 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 5.9595 loss: 0.8934 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8934 2023/02/17 19:22:48 - mmengine - INFO - Epoch(train) [40][ 180/1320] lr: 2.0000e-03 eta: 1:55:13 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 6.1594 loss: 1.0020 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0020 2023/02/17 19:22:58 - mmengine - INFO - Epoch(train) [40][ 200/1320] lr: 2.0000e-03 eta: 1:55:03 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 6.1976 loss: 0.8986 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.8986 2023/02/17 19:23:07 - mmengine - INFO - Epoch(train) [40][ 220/1320] lr: 2.0000e-03 eta: 1:54:54 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 5.9806 loss: 0.9002 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9002 2023/02/17 19:23:17 - mmengine - INFO - Epoch(train) [40][ 240/1320] lr: 2.0000e-03 eta: 1:54:44 time: 0.4819 data_time: 0.0152 memory: 27031 grad_norm: 6.0605 loss: 0.7883 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7883 2023/02/17 19:23:26 - mmengine - INFO - Epoch(train) [40][ 260/1320] lr: 2.0000e-03 eta: 1:54:34 time: 0.4782 data_time: 0.0128 memory: 27031 grad_norm: 6.2183 loss: 1.0984 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0984 2023/02/17 19:23:36 - mmengine - INFO - Epoch(train) [40][ 280/1320] lr: 2.0000e-03 eta: 1:54:25 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 6.2538 loss: 0.8566 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8566 2023/02/17 19:23:46 - mmengine - INFO - Epoch(train) [40][ 300/1320] lr: 2.0000e-03 eta: 1:54:15 time: 0.4805 data_time: 0.0138 memory: 27031 grad_norm: 6.2599 loss: 1.0295 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0295 2023/02/17 19:23:55 - mmengine - INFO - Epoch(train) [40][ 320/1320] lr: 2.0000e-03 eta: 1:54:05 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 6.1938 loss: 1.0827 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0827 2023/02/17 19:24:05 - mmengine - INFO - Epoch(train) [40][ 340/1320] lr: 2.0000e-03 eta: 1:53:56 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 6.1442 loss: 1.0933 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0933 2023/02/17 19:24:15 - mmengine - INFO - Epoch(train) [40][ 360/1320] lr: 2.0000e-03 eta: 1:53:46 time: 0.4797 data_time: 0.0137 memory: 27031 grad_norm: 6.3159 loss: 1.0168 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0168 2023/02/17 19:24:24 - mmengine - INFO - Epoch(train) [40][ 380/1320] lr: 2.0000e-03 eta: 1:53:36 time: 0.4811 data_time: 0.0152 memory: 27031 grad_norm: 6.3694 loss: 0.9595 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9595 2023/02/17 19:24:34 - mmengine - INFO - Epoch(train) [40][ 400/1320] lr: 2.0000e-03 eta: 1:53:27 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 6.1249 loss: 0.9410 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9410 2023/02/17 19:24:43 - mmengine - INFO - Epoch(train) [40][ 420/1320] lr: 2.0000e-03 eta: 1:53:17 time: 0.4803 data_time: 0.0136 memory: 27031 grad_norm: 6.1885 loss: 0.9540 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9540 2023/02/17 19:24:53 - mmengine - INFO - Epoch(train) [40][ 440/1320] lr: 2.0000e-03 eta: 1:53:07 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 6.2649 loss: 1.0322 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0322 2023/02/17 19:25:03 - mmengine - INFO - Epoch(train) [40][ 460/1320] lr: 2.0000e-03 eta: 1:52:58 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 6.2511 loss: 1.2631 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2631 2023/02/17 19:25:12 - mmengine - INFO - Epoch(train) [40][ 480/1320] lr: 2.0000e-03 eta: 1:52:48 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 6.1482 loss: 0.8682 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.8682 2023/02/17 19:25:22 - mmengine - INFO - Epoch(train) [40][ 500/1320] lr: 2.0000e-03 eta: 1:52:39 time: 0.4816 data_time: 0.0157 memory: 27031 grad_norm: 6.2920 loss: 1.1645 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.1645 2023/02/17 19:25:31 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:25:31 - mmengine - INFO - Epoch(train) [40][ 520/1320] lr: 2.0000e-03 eta: 1:52:29 time: 0.4806 data_time: 0.0141 memory: 27031 grad_norm: 6.3079 loss: 1.1027 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.1027 2023/02/17 19:25:41 - mmengine - INFO - Epoch(train) [40][ 540/1320] lr: 2.0000e-03 eta: 1:52:19 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 6.3506 loss: 1.0726 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0726 2023/02/17 19:25:51 - mmengine - INFO - Epoch(train) [40][ 560/1320] lr: 2.0000e-03 eta: 1:52:10 time: 0.4806 data_time: 0.0140 memory: 27031 grad_norm: 6.2715 loss: 1.0467 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0467 2023/02/17 19:26:00 - mmengine - INFO - Epoch(train) [40][ 580/1320] lr: 2.0000e-03 eta: 1:52:00 time: 0.4798 data_time: 0.0140 memory: 27031 grad_norm: 6.3557 loss: 1.0237 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0237 2023/02/17 19:26:10 - mmengine - INFO - Epoch(train) [40][ 600/1320] lr: 2.0000e-03 eta: 1:51:50 time: 0.4825 data_time: 0.0166 memory: 27031 grad_norm: 6.1017 loss: 1.0250 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0250 2023/02/17 19:26:20 - mmengine - INFO - Epoch(train) [40][ 620/1320] lr: 2.0000e-03 eta: 1:51:41 time: 0.4803 data_time: 0.0137 memory: 27031 grad_norm: 6.1944 loss: 0.9395 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9395 2023/02/17 19:26:29 - mmengine - INFO - Epoch(train) [40][ 640/1320] lr: 2.0000e-03 eta: 1:51:31 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 6.1838 loss: 1.0332 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0332 2023/02/17 19:26:39 - mmengine - INFO - Epoch(train) [40][ 660/1320] lr: 2.0000e-03 eta: 1:51:21 time: 0.4802 data_time: 0.0149 memory: 27031 grad_norm: 6.1627 loss: 0.9402 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9402 2023/02/17 19:26:48 - mmengine - INFO - Epoch(train) [40][ 680/1320] lr: 2.0000e-03 eta: 1:51:12 time: 0.4799 data_time: 0.0138 memory: 27031 grad_norm: 6.3758 loss: 1.1130 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 1.1130 2023/02/17 19:26:58 - mmengine - INFO - Epoch(train) [40][ 700/1320] lr: 2.0000e-03 eta: 1:51:02 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 6.0995 loss: 0.9825 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9825 2023/02/17 19:27:08 - mmengine - INFO - Epoch(train) [40][ 720/1320] lr: 2.0000e-03 eta: 1:50:52 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 6.2211 loss: 0.9280 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9280 2023/02/17 19:27:17 - mmengine - INFO - Epoch(train) [40][ 740/1320] lr: 2.0000e-03 eta: 1:50:43 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 6.0758 loss: 0.9262 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9262 2023/02/17 19:27:27 - mmengine - INFO - Epoch(train) [40][ 760/1320] lr: 2.0000e-03 eta: 1:50:33 time: 0.4804 data_time: 0.0141 memory: 27031 grad_norm: 6.2554 loss: 0.9265 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9265 2023/02/17 19:27:36 - mmengine - INFO - Epoch(train) [40][ 780/1320] lr: 2.0000e-03 eta: 1:50:23 time: 0.4802 data_time: 0.0143 memory: 27031 grad_norm: 6.2932 loss: 0.9713 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9713 2023/02/17 19:27:46 - mmengine - INFO - Epoch(train) [40][ 800/1320] lr: 2.0000e-03 eta: 1:50:14 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.2823 loss: 1.0385 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0385 2023/02/17 19:27:56 - mmengine - INFO - Epoch(train) [40][ 820/1320] lr: 2.0000e-03 eta: 1:50:04 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 6.3117 loss: 0.8496 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8496 2023/02/17 19:28:05 - mmengine - INFO - Epoch(train) [40][ 840/1320] lr: 2.0000e-03 eta: 1:49:54 time: 0.4803 data_time: 0.0136 memory: 27031 grad_norm: 6.2120 loss: 1.0253 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0253 2023/02/17 19:28:15 - mmengine - INFO - Epoch(train) [40][ 860/1320] lr: 2.0000e-03 eta: 1:49:45 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 6.1974 loss: 0.9141 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9141 2023/02/17 19:28:25 - mmengine - INFO - Epoch(train) [40][ 880/1320] lr: 2.0000e-03 eta: 1:49:35 time: 0.4816 data_time: 0.0153 memory: 27031 grad_norm: 6.1717 loss: 0.8395 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8395 2023/02/17 19:28:34 - mmengine - INFO - Epoch(train) [40][ 900/1320] lr: 2.0000e-03 eta: 1:49:26 time: 0.4801 data_time: 0.0138 memory: 27031 grad_norm: 6.2046 loss: 0.9289 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9289 2023/02/17 19:28:44 - mmengine - INFO - Epoch(train) [40][ 920/1320] lr: 2.0000e-03 eta: 1:49:16 time: 0.4814 data_time: 0.0154 memory: 27031 grad_norm: 6.2296 loss: 1.0578 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0578 2023/02/17 19:28:53 - mmengine - INFO - Epoch(train) [40][ 940/1320] lr: 2.0000e-03 eta: 1:49:06 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.2627 loss: 0.8256 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8256 2023/02/17 19:29:03 - mmengine - INFO - Epoch(train) [40][ 960/1320] lr: 2.0000e-03 eta: 1:48:57 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.2676 loss: 0.8741 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8741 2023/02/17 19:29:13 - mmengine - INFO - Epoch(train) [40][ 980/1320] lr: 2.0000e-03 eta: 1:48:47 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.2822 loss: 1.0246 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0246 2023/02/17 19:29:22 - mmengine - INFO - Epoch(train) [40][1000/1320] lr: 2.0000e-03 eta: 1:48:37 time: 0.4803 data_time: 0.0137 memory: 27031 grad_norm: 6.4366 loss: 1.0316 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0316 2023/02/17 19:29:32 - mmengine - INFO - Epoch(train) [40][1020/1320] lr: 2.0000e-03 eta: 1:48:28 time: 0.4824 data_time: 0.0157 memory: 27031 grad_norm: 6.1863 loss: 0.9438 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9438 2023/02/17 19:29:41 - mmengine - INFO - Epoch(train) [40][1040/1320] lr: 2.0000e-03 eta: 1:48:18 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 6.4089 loss: 1.0558 top1_acc: 0.6250 top5_acc: 0.6875 loss_cls: 1.0558 2023/02/17 19:29:51 - mmengine - INFO - Epoch(train) [40][1060/1320] lr: 2.0000e-03 eta: 1:48:08 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 6.2469 loss: 0.9809 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9809 2023/02/17 19:30:01 - mmengine - INFO - Epoch(train) [40][1080/1320] lr: 2.0000e-03 eta: 1:47:59 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 6.3943 loss: 0.8555 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8555 2023/02/17 19:30:10 - mmengine - INFO - Epoch(train) [40][1100/1320] lr: 2.0000e-03 eta: 1:47:49 time: 0.4805 data_time: 0.0145 memory: 27031 grad_norm: 6.4155 loss: 0.9652 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9652 2023/02/17 19:30:20 - mmengine - INFO - Epoch(train) [40][1120/1320] lr: 2.0000e-03 eta: 1:47:39 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 6.4475 loss: 0.8091 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8091 2023/02/17 19:30:30 - mmengine - INFO - Epoch(train) [40][1140/1320] lr: 2.0000e-03 eta: 1:47:30 time: 0.4806 data_time: 0.0150 memory: 27031 grad_norm: 6.3283 loss: 0.7269 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.7269 2023/02/17 19:30:39 - mmengine - INFO - Epoch(train) [40][1160/1320] lr: 2.0000e-03 eta: 1:47:20 time: 0.4791 data_time: 0.0138 memory: 27031 grad_norm: 6.3762 loss: 1.0767 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0767 2023/02/17 19:30:49 - mmengine - INFO - Epoch(train) [40][1180/1320] lr: 2.0000e-03 eta: 1:47:10 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 6.1637 loss: 1.0273 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0273 2023/02/17 19:30:58 - mmengine - INFO - Epoch(train) [40][1200/1320] lr: 2.0000e-03 eta: 1:47:01 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 6.2396 loss: 1.0220 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0220 2023/02/17 19:31:08 - mmengine - INFO - Epoch(train) [40][1220/1320] lr: 2.0000e-03 eta: 1:46:51 time: 0.4808 data_time: 0.0139 memory: 27031 grad_norm: 6.4954 loss: 1.0795 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.0795 2023/02/17 19:31:18 - mmengine - INFO - Epoch(train) [40][1240/1320] lr: 2.0000e-03 eta: 1:46:41 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 6.4918 loss: 1.1792 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1792 2023/02/17 19:31:27 - mmengine - INFO - Epoch(train) [40][1260/1320] lr: 2.0000e-03 eta: 1:46:32 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.2501 loss: 1.1199 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1199 2023/02/17 19:31:37 - mmengine - INFO - Epoch(train) [40][1280/1320] lr: 2.0000e-03 eta: 1:46:22 time: 0.4812 data_time: 0.0154 memory: 27031 grad_norm: 6.0686 loss: 0.8927 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8927 2023/02/17 19:31:46 - mmengine - INFO - Epoch(train) [40][1300/1320] lr: 2.0000e-03 eta: 1:46:13 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 6.2498 loss: 0.9526 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9526 2023/02/17 19:31:56 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:31:56 - mmengine - INFO - Epoch(train) [40][1320/1320] lr: 2.0000e-03 eta: 1:46:03 time: 0.4742 data_time: 0.0152 memory: 27031 grad_norm: 6.3691 loss: 0.8982 top1_acc: 0.7273 top5_acc: 0.9091 loss_cls: 0.8982 2023/02/17 19:32:00 - mmengine - INFO - Epoch(val) [40][ 20/194] eta: 0:00:31 time: 0.1810 data_time: 0.0556 memory: 3265 2023/02/17 19:32:02 - mmengine - INFO - Epoch(val) [40][ 40/194] eta: 0:00:24 time: 0.1393 data_time: 0.0146 memory: 3265 2023/02/17 19:32:05 - mmengine - INFO - Epoch(val) [40][ 60/194] eta: 0:00:20 time: 0.1381 data_time: 0.0137 memory: 3265 2023/02/17 19:32:08 - mmengine - INFO - Epoch(val) [40][ 80/194] eta: 0:00:16 time: 0.1379 data_time: 0.0139 memory: 3265 2023/02/17 19:32:11 - mmengine - INFO - Epoch(val) [40][100/194] eta: 0:00:13 time: 0.1363 data_time: 0.0128 memory: 3265 2023/02/17 19:32:13 - mmengine - INFO - Epoch(val) [40][120/194] eta: 0:00:10 time: 0.1371 data_time: 0.0130 memory: 3265 2023/02/17 19:32:16 - mmengine - INFO - Epoch(val) [40][140/194] eta: 0:00:07 time: 0.1387 data_time: 0.0140 memory: 3265 2023/02/17 19:32:19 - mmengine - INFO - Epoch(val) [40][160/194] eta: 0:00:04 time: 0.1386 data_time: 0.0140 memory: 3265 2023/02/17 19:32:22 - mmengine - INFO - Epoch(val) [40][180/194] eta: 0:00:01 time: 0.1387 data_time: 0.0134 memory: 3265 2023/02/17 19:32:25 - mmengine - INFO - Epoch(val) [40][194/194] acc/top1: 0.6069 acc/top5: 0.8670 acc/mean1: 0.5488 2023/02/17 19:32:35 - mmengine - INFO - Epoch(train) [41][ 20/1320] lr: 2.0000e-03 eta: 1:45:53 time: 0.5355 data_time: 0.0590 memory: 27031 grad_norm: 6.3967 loss: 0.9494 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9494 2023/02/17 19:32:45 - mmengine - INFO - Epoch(train) [41][ 40/1320] lr: 2.0000e-03 eta: 1:45:44 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 6.2607 loss: 0.9707 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9707 2023/02/17 19:32:55 - mmengine - INFO - Epoch(train) [41][ 60/1320] lr: 2.0000e-03 eta: 1:45:34 time: 0.4792 data_time: 0.0138 memory: 27031 grad_norm: 6.0513 loss: 0.9293 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9293 2023/02/17 19:33:04 - mmengine - INFO - Epoch(train) [41][ 80/1320] lr: 2.0000e-03 eta: 1:45:25 time: 0.4826 data_time: 0.0159 memory: 27031 grad_norm: 6.2805 loss: 1.0681 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0681 2023/02/17 19:33:14 - mmengine - INFO - Epoch(train) [41][ 100/1320] lr: 2.0000e-03 eta: 1:45:15 time: 0.4803 data_time: 0.0143 memory: 27031 grad_norm: 6.3271 loss: 0.9681 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9681 2023/02/17 19:33:23 - mmengine - INFO - Epoch(train) [41][ 120/1320] lr: 2.0000e-03 eta: 1:45:05 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 6.2392 loss: 0.9584 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 0.9584 2023/02/17 19:33:33 - mmengine - INFO - Epoch(train) [41][ 140/1320] lr: 2.0000e-03 eta: 1:44:56 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 6.2260 loss: 1.0297 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0297 2023/02/17 19:33:43 - mmengine - INFO - Epoch(train) [41][ 160/1320] lr: 2.0000e-03 eta: 1:44:46 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 6.3553 loss: 0.9431 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9431 2023/02/17 19:33:52 - mmengine - INFO - Epoch(train) [41][ 180/1320] lr: 2.0000e-03 eta: 1:44:36 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.2205 loss: 0.9199 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9199 2023/02/17 19:34:02 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:34:02 - mmengine - INFO - Epoch(train) [41][ 200/1320] lr: 2.0000e-03 eta: 1:44:27 time: 0.4814 data_time: 0.0145 memory: 27031 grad_norm: 6.1105 loss: 0.9605 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9605 2023/02/17 19:34:12 - mmengine - INFO - Epoch(train) [41][ 220/1320] lr: 2.0000e-03 eta: 1:44:17 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 6.3188 loss: 0.8212 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.8212 2023/02/17 19:34:21 - mmengine - INFO - Epoch(train) [41][ 240/1320] lr: 2.0000e-03 eta: 1:44:07 time: 0.4805 data_time: 0.0152 memory: 27031 grad_norm: 5.9914 loss: 0.9407 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9407 2023/02/17 19:34:31 - mmengine - INFO - Epoch(train) [41][ 260/1320] lr: 2.0000e-03 eta: 1:43:58 time: 0.4808 data_time: 0.0141 memory: 27031 grad_norm: 6.4442 loss: 0.9578 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9578 2023/02/17 19:34:40 - mmengine - INFO - Epoch(train) [41][ 280/1320] lr: 2.0000e-03 eta: 1:43:48 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 6.3703 loss: 0.9211 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9211 2023/02/17 19:34:50 - mmengine - INFO - Epoch(train) [41][ 300/1320] lr: 2.0000e-03 eta: 1:43:38 time: 0.4813 data_time: 0.0149 memory: 27031 grad_norm: 6.6312 loss: 0.9964 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9964 2023/02/17 19:35:00 - mmengine - INFO - Epoch(train) [41][ 320/1320] lr: 2.0000e-03 eta: 1:43:29 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 6.4371 loss: 0.9031 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.9031 2023/02/17 19:35:09 - mmengine - INFO - Epoch(train) [41][ 340/1320] lr: 2.0000e-03 eta: 1:43:19 time: 0.4814 data_time: 0.0152 memory: 27031 grad_norm: 6.2321 loss: 0.9166 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9166 2023/02/17 19:35:19 - mmengine - INFO - Epoch(train) [41][ 360/1320] lr: 2.0000e-03 eta: 1:43:09 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 6.5272 loss: 1.0984 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0984 2023/02/17 19:35:28 - mmengine - INFO - Epoch(train) [41][ 380/1320] lr: 2.0000e-03 eta: 1:43:00 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 6.2225 loss: 0.9431 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9431 2023/02/17 19:35:38 - mmengine - INFO - Epoch(train) [41][ 400/1320] lr: 2.0000e-03 eta: 1:42:50 time: 0.4813 data_time: 0.0153 memory: 27031 grad_norm: 6.5263 loss: 1.0928 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0928 2023/02/17 19:35:48 - mmengine - INFO - Epoch(train) [41][ 420/1320] lr: 2.0000e-03 eta: 1:42:41 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.4219 loss: 0.9902 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9902 2023/02/17 19:35:57 - mmengine - INFO - Epoch(train) [41][ 440/1320] lr: 2.0000e-03 eta: 1:42:31 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 6.2255 loss: 0.8633 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8633 2023/02/17 19:36:07 - mmengine - INFO - Epoch(train) [41][ 460/1320] lr: 2.0000e-03 eta: 1:42:21 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 6.3410 loss: 0.7840 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.7840 2023/02/17 19:36:17 - mmengine - INFO - Epoch(train) [41][ 480/1320] lr: 2.0000e-03 eta: 1:42:12 time: 0.4800 data_time: 0.0141 memory: 27031 grad_norm: 6.5005 loss: 0.9694 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9694 2023/02/17 19:36:26 - mmengine - INFO - Epoch(train) [41][ 500/1320] lr: 2.0000e-03 eta: 1:42:02 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 6.3302 loss: 0.9401 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9401 2023/02/17 19:36:36 - mmengine - INFO - Epoch(train) [41][ 520/1320] lr: 2.0000e-03 eta: 1:41:52 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.1790 loss: 1.0024 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0024 2023/02/17 19:36:45 - mmengine - INFO - Epoch(train) [41][ 540/1320] lr: 2.0000e-03 eta: 1:41:43 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 6.4271 loss: 1.0785 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0785 2023/02/17 19:36:55 - mmengine - INFO - Epoch(train) [41][ 560/1320] lr: 2.0000e-03 eta: 1:41:33 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 6.2201 loss: 0.9002 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9002 2023/02/17 19:37:05 - mmengine - INFO - Epoch(train) [41][ 580/1320] lr: 2.0000e-03 eta: 1:41:23 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 6.7259 loss: 0.9363 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9363 2023/02/17 19:37:14 - mmengine - INFO - Epoch(train) [41][ 600/1320] lr: 2.0000e-03 eta: 1:41:14 time: 0.4800 data_time: 0.0136 memory: 27031 grad_norm: 6.4912 loss: 1.0417 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0417 2023/02/17 19:37:24 - mmengine - INFO - Epoch(train) [41][ 620/1320] lr: 2.0000e-03 eta: 1:41:04 time: 0.4812 data_time: 0.0151 memory: 27031 grad_norm: 6.5858 loss: 1.0807 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0807 2023/02/17 19:37:33 - mmengine - INFO - Epoch(train) [41][ 640/1320] lr: 2.0000e-03 eta: 1:40:54 time: 0.4809 data_time: 0.0133 memory: 27031 grad_norm: 6.3839 loss: 0.9872 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9872 2023/02/17 19:37:43 - mmengine - INFO - Epoch(train) [41][ 660/1320] lr: 2.0000e-03 eta: 1:40:45 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 6.3471 loss: 0.8800 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8800 2023/02/17 19:37:53 - mmengine - INFO - Epoch(train) [41][ 680/1320] lr: 2.0000e-03 eta: 1:40:35 time: 0.4811 data_time: 0.0141 memory: 27031 grad_norm: 6.2669 loss: 0.9254 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9254 2023/02/17 19:38:02 - mmengine - INFO - Epoch(train) [41][ 700/1320] lr: 2.0000e-03 eta: 1:40:25 time: 0.4810 data_time: 0.0140 memory: 27031 grad_norm: 6.3995 loss: 0.9907 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9907 2023/02/17 19:38:12 - mmengine - INFO - Epoch(train) [41][ 720/1320] lr: 2.0000e-03 eta: 1:40:16 time: 0.4810 data_time: 0.0142 memory: 27031 grad_norm: 6.5639 loss: 0.9934 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9934 2023/02/17 19:38:22 - mmengine - INFO - Epoch(train) [41][ 740/1320] lr: 2.0000e-03 eta: 1:40:06 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 6.4703 loss: 0.9915 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.9915 2023/02/17 19:38:31 - mmengine - INFO - Epoch(train) [41][ 760/1320] lr: 2.0000e-03 eta: 1:39:56 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.6474 loss: 0.9225 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9225 2023/02/17 19:38:41 - mmengine - INFO - Epoch(train) [41][ 780/1320] lr: 2.0000e-03 eta: 1:39:47 time: 0.4806 data_time: 0.0150 memory: 27031 grad_norm: 6.4097 loss: 0.8272 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8272 2023/02/17 19:38:50 - mmengine - INFO - Epoch(train) [41][ 800/1320] lr: 2.0000e-03 eta: 1:39:37 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 6.5467 loss: 1.0375 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0375 2023/02/17 19:39:00 - mmengine - INFO - Epoch(train) [41][ 820/1320] lr: 2.0000e-03 eta: 1:39:28 time: 0.4804 data_time: 0.0148 memory: 27031 grad_norm: 6.5354 loss: 0.9308 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9308 2023/02/17 19:39:10 - mmengine - INFO - Epoch(train) [41][ 840/1320] lr: 2.0000e-03 eta: 1:39:18 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 6.4288 loss: 0.9308 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9308 2023/02/17 19:39:19 - mmengine - INFO - Epoch(train) [41][ 860/1320] lr: 2.0000e-03 eta: 1:39:08 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.5485 loss: 0.9686 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9686 2023/02/17 19:39:29 - mmengine - INFO - Epoch(train) [41][ 880/1320] lr: 2.0000e-03 eta: 1:38:59 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.6114 loss: 1.0264 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0264 2023/02/17 19:39:38 - mmengine - INFO - Epoch(train) [41][ 900/1320] lr: 2.0000e-03 eta: 1:38:49 time: 0.4804 data_time: 0.0141 memory: 27031 grad_norm: 6.4374 loss: 0.9996 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9996 2023/02/17 19:39:48 - mmengine - INFO - Epoch(train) [41][ 920/1320] lr: 2.0000e-03 eta: 1:38:39 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 6.3669 loss: 0.8235 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8235 2023/02/17 19:39:58 - mmengine - INFO - Epoch(train) [41][ 940/1320] lr: 2.0000e-03 eta: 1:38:30 time: 0.4803 data_time: 0.0149 memory: 27031 grad_norm: 6.4827 loss: 1.0468 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0468 2023/02/17 19:40:07 - mmengine - INFO - Epoch(train) [41][ 960/1320] lr: 2.0000e-03 eta: 1:38:20 time: 0.4795 data_time: 0.0137 memory: 27031 grad_norm: 6.6273 loss: 0.9412 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9412 2023/02/17 19:40:17 - mmengine - INFO - Epoch(train) [41][ 980/1320] lr: 2.0000e-03 eta: 1:38:10 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 6.6233 loss: 1.1047 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.1047 2023/02/17 19:40:27 - mmengine - INFO - Epoch(train) [41][1000/1320] lr: 2.0000e-03 eta: 1:38:01 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 6.6936 loss: 0.9187 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9187 2023/02/17 19:40:36 - mmengine - INFO - Epoch(train) [41][1020/1320] lr: 2.0000e-03 eta: 1:37:51 time: 0.4816 data_time: 0.0158 memory: 27031 grad_norm: 6.6331 loss: 1.1645 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.1645 2023/02/17 19:40:46 - mmengine - INFO - Epoch(train) [41][1040/1320] lr: 2.0000e-03 eta: 1:37:41 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 6.5651 loss: 0.9198 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9198 2023/02/17 19:40:55 - mmengine - INFO - Epoch(train) [41][1060/1320] lr: 2.0000e-03 eta: 1:37:32 time: 0.4798 data_time: 0.0140 memory: 27031 grad_norm: 6.6175 loss: 1.0188 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0188 2023/02/17 19:41:05 - mmengine - INFO - Epoch(train) [41][1080/1320] lr: 2.0000e-03 eta: 1:37:22 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.5095 loss: 1.1657 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.1657 2023/02/17 19:41:15 - mmengine - INFO - Epoch(train) [41][1100/1320] lr: 2.0000e-03 eta: 1:37:12 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 6.3620 loss: 1.0058 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0058 2023/02/17 19:41:24 - mmengine - INFO - Epoch(train) [41][1120/1320] lr: 2.0000e-03 eta: 1:37:03 time: 0.4803 data_time: 0.0141 memory: 27031 grad_norm: 6.6608 loss: 0.9987 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9987 2023/02/17 19:41:34 - mmengine - INFO - Epoch(train) [41][1140/1320] lr: 2.0000e-03 eta: 1:36:53 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 6.4528 loss: 1.1189 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1189 2023/02/17 19:41:44 - mmengine - INFO - Epoch(train) [41][1160/1320] lr: 2.0000e-03 eta: 1:36:44 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 6.2169 loss: 0.8997 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8997 2023/02/17 19:41:53 - mmengine - INFO - Epoch(train) [41][1180/1320] lr: 2.0000e-03 eta: 1:36:34 time: 0.4811 data_time: 0.0145 memory: 27031 grad_norm: 6.3904 loss: 0.9075 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9075 2023/02/17 19:42:03 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:42:03 - mmengine - INFO - Epoch(train) [41][1200/1320] lr: 2.0000e-03 eta: 1:36:24 time: 0.4814 data_time: 0.0148 memory: 27031 grad_norm: 6.5333 loss: 0.9497 top1_acc: 0.6875 top5_acc: 0.6875 loss_cls: 0.9497 2023/02/17 19:42:12 - mmengine - INFO - Epoch(train) [41][1220/1320] lr: 2.0000e-03 eta: 1:36:15 time: 0.4802 data_time: 0.0145 memory: 27031 grad_norm: 6.4414 loss: 0.9538 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9538 2023/02/17 19:42:22 - mmengine - INFO - Epoch(train) [41][1240/1320] lr: 2.0000e-03 eta: 1:36:05 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 6.4822 loss: 1.1449 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1449 2023/02/17 19:42:32 - mmengine - INFO - Epoch(train) [41][1260/1320] lr: 2.0000e-03 eta: 1:35:55 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.3283 loss: 0.9626 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9626 2023/02/17 19:42:41 - mmengine - INFO - Epoch(train) [41][1280/1320] lr: 2.0000e-03 eta: 1:35:46 time: 0.4800 data_time: 0.0136 memory: 27031 grad_norm: 6.5934 loss: 1.1345 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1345 2023/02/17 19:42:51 - mmengine - INFO - Epoch(train) [41][1300/1320] lr: 2.0000e-03 eta: 1:35:36 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 6.4938 loss: 1.0055 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.0055 2023/02/17 19:43:00 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:43:00 - mmengine - INFO - Epoch(train) [41][1320/1320] lr: 2.0000e-03 eta: 1:35:26 time: 0.4748 data_time: 0.0152 memory: 27031 grad_norm: 6.5294 loss: 0.9179 top1_acc: 0.9091 top5_acc: 0.9091 loss_cls: 0.9179 2023/02/17 19:43:04 - mmengine - INFO - Epoch(val) [41][ 20/194] eta: 0:00:33 time: 0.1912 data_time: 0.0651 memory: 3265 2023/02/17 19:43:07 - mmengine - INFO - Epoch(val) [41][ 40/194] eta: 0:00:25 time: 0.1382 data_time: 0.0135 memory: 3265 2023/02/17 19:43:10 - mmengine - INFO - Epoch(val) [41][ 60/194] eta: 0:00:21 time: 0.1411 data_time: 0.0153 memory: 3265 2023/02/17 19:43:13 - mmengine - INFO - Epoch(val) [41][ 80/194] eta: 0:00:17 time: 0.1380 data_time: 0.0135 memory: 3265 2023/02/17 19:43:15 - mmengine - INFO - Epoch(val) [41][100/194] eta: 0:00:14 time: 0.1406 data_time: 0.0148 memory: 3265 2023/02/17 19:43:18 - mmengine - INFO - Epoch(val) [41][120/194] eta: 0:00:10 time: 0.1400 data_time: 0.0147 memory: 3265 2023/02/17 19:43:21 - mmengine - INFO - Epoch(val) [41][140/194] eta: 0:00:07 time: 0.1395 data_time: 0.0144 memory: 3265 2023/02/17 19:43:24 - mmengine - INFO - Epoch(val) [41][160/194] eta: 0:00:04 time: 0.1369 data_time: 0.0132 memory: 3265 2023/02/17 19:43:27 - mmengine - INFO - Epoch(val) [41][180/194] eta: 0:00:02 time: 0.1409 data_time: 0.0139 memory: 3265 2023/02/17 19:43:29 - mmengine - INFO - Epoch(val) [41][194/194] acc/top1: 0.6060 acc/top5: 0.8686 acc/mean1: 0.5451 2023/02/17 19:43:40 - mmengine - INFO - Epoch(train) [42][ 20/1320] lr: 2.0000e-03 eta: 1:35:17 time: 0.5329 data_time: 0.0583 memory: 27031 grad_norm: 6.2851 loss: 0.9742 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9742 2023/02/17 19:43:49 - mmengine - INFO - Epoch(train) [42][ 40/1320] lr: 2.0000e-03 eta: 1:35:07 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 6.4029 loss: 1.0639 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0639 2023/02/17 19:43:59 - mmengine - INFO - Epoch(train) [42][ 60/1320] lr: 2.0000e-03 eta: 1:34:58 time: 0.4807 data_time: 0.0151 memory: 27031 grad_norm: 6.4820 loss: 0.9593 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 0.9593 2023/02/17 19:44:09 - mmengine - INFO - Epoch(train) [42][ 80/1320] lr: 2.0000e-03 eta: 1:34:48 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.3513 loss: 0.8344 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8344 2023/02/17 19:44:18 - mmengine - INFO - Epoch(train) [42][ 100/1320] lr: 2.0000e-03 eta: 1:34:38 time: 0.4809 data_time: 0.0151 memory: 27031 grad_norm: 6.6167 loss: 0.9723 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9723 2023/02/17 19:44:28 - mmengine - INFO - Epoch(train) [42][ 120/1320] lr: 2.0000e-03 eta: 1:34:29 time: 0.4789 data_time: 0.0132 memory: 27031 grad_norm: 6.4383 loss: 0.9165 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9165 2023/02/17 19:44:37 - mmengine - INFO - Epoch(train) [42][ 140/1320] lr: 2.0000e-03 eta: 1:34:19 time: 0.4817 data_time: 0.0147 memory: 27031 grad_norm: 6.4274 loss: 0.8727 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8727 2023/02/17 19:44:47 - mmengine - INFO - Epoch(train) [42][ 160/1320] lr: 2.0000e-03 eta: 1:34:09 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 6.3172 loss: 0.7533 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7533 2023/02/17 19:44:57 - mmengine - INFO - Epoch(train) [42][ 180/1320] lr: 2.0000e-03 eta: 1:34:00 time: 0.4795 data_time: 0.0145 memory: 27031 grad_norm: 6.2982 loss: 0.8346 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8346 2023/02/17 19:45:06 - mmengine - INFO - Epoch(train) [42][ 200/1320] lr: 2.0000e-03 eta: 1:33:50 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 6.3780 loss: 0.8533 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8533 2023/02/17 19:45:16 - mmengine - INFO - Epoch(train) [42][ 220/1320] lr: 2.0000e-03 eta: 1:33:40 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.3899 loss: 1.0278 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0278 2023/02/17 19:45:26 - mmengine - INFO - Epoch(train) [42][ 240/1320] lr: 2.0000e-03 eta: 1:33:31 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 6.6203 loss: 1.0019 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0019 2023/02/17 19:45:35 - mmengine - INFO - Epoch(train) [42][ 260/1320] lr: 2.0000e-03 eta: 1:33:21 time: 0.4813 data_time: 0.0144 memory: 27031 grad_norm: 6.2332 loss: 0.9252 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9252 2023/02/17 19:45:45 - mmengine - INFO - Epoch(train) [42][ 280/1320] lr: 2.0000e-03 eta: 1:33:11 time: 0.4801 data_time: 0.0138 memory: 27031 grad_norm: 6.4829 loss: 1.0049 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0049 2023/02/17 19:45:54 - mmengine - INFO - Epoch(train) [42][ 300/1320] lr: 2.0000e-03 eta: 1:33:02 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 6.3145 loss: 0.8569 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8569 2023/02/17 19:46:04 - mmengine - INFO - Epoch(train) [42][ 320/1320] lr: 2.0000e-03 eta: 1:32:52 time: 0.4817 data_time: 0.0162 memory: 27031 grad_norm: 6.4146 loss: 0.9490 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9490 2023/02/17 19:46:14 - mmengine - INFO - Epoch(train) [42][ 340/1320] lr: 2.0000e-03 eta: 1:32:43 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 6.3421 loss: 0.8525 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8525 2023/02/17 19:46:23 - mmengine - INFO - Epoch(train) [42][ 360/1320] lr: 2.0000e-03 eta: 1:32:33 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 6.4633 loss: 1.0127 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0127 2023/02/17 19:46:33 - mmengine - INFO - Epoch(train) [42][ 380/1320] lr: 2.0000e-03 eta: 1:32:23 time: 0.4804 data_time: 0.0138 memory: 27031 grad_norm: 6.7155 loss: 0.9306 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9306 2023/02/17 19:46:42 - mmengine - INFO - Epoch(train) [42][ 400/1320] lr: 2.0000e-03 eta: 1:32:14 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 6.4806 loss: 1.0071 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0071 2023/02/17 19:46:52 - mmengine - INFO - Epoch(train) [42][ 420/1320] lr: 2.0000e-03 eta: 1:32:04 time: 0.4811 data_time: 0.0147 memory: 27031 grad_norm: 6.6284 loss: 0.9009 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.9009 2023/02/17 19:47:02 - mmengine - INFO - Epoch(train) [42][ 440/1320] lr: 2.0000e-03 eta: 1:31:54 time: 0.4793 data_time: 0.0138 memory: 27031 grad_norm: 6.6688 loss: 1.0288 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0288 2023/02/17 19:47:11 - mmengine - INFO - Epoch(train) [42][ 460/1320] lr: 2.0000e-03 eta: 1:31:45 time: 0.4809 data_time: 0.0149 memory: 27031 grad_norm: 6.5069 loss: 0.9180 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9180 2023/02/17 19:47:21 - mmengine - INFO - Epoch(train) [42][ 480/1320] lr: 2.0000e-03 eta: 1:31:35 time: 0.4806 data_time: 0.0144 memory: 27031 grad_norm: 6.5964 loss: 1.0390 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0390 2023/02/17 19:47:31 - mmengine - INFO - Epoch(train) [42][ 500/1320] lr: 2.0000e-03 eta: 1:31:25 time: 0.4797 data_time: 0.0142 memory: 27031 grad_norm: 6.6096 loss: 0.9477 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9477 2023/02/17 19:47:40 - mmengine - INFO - Epoch(train) [42][ 520/1320] lr: 2.0000e-03 eta: 1:31:16 time: 0.4814 data_time: 0.0146 memory: 27031 grad_norm: 6.5971 loss: 1.0220 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 1.0220 2023/02/17 19:47:50 - mmengine - INFO - Epoch(train) [42][ 540/1320] lr: 2.0000e-03 eta: 1:31:06 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 6.4277 loss: 1.0305 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 1.0305 2023/02/17 19:47:59 - mmengine - INFO - Epoch(train) [42][ 560/1320] lr: 2.0000e-03 eta: 1:30:56 time: 0.4805 data_time: 0.0138 memory: 27031 grad_norm: 6.5667 loss: 1.0076 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0076 2023/02/17 19:48:09 - mmengine - INFO - Epoch(train) [42][ 580/1320] lr: 2.0000e-03 eta: 1:30:47 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 6.4590 loss: 1.0299 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0299 2023/02/17 19:48:19 - mmengine - INFO - Epoch(train) [42][ 600/1320] lr: 2.0000e-03 eta: 1:30:37 time: 0.4794 data_time: 0.0134 memory: 27031 grad_norm: 6.3303 loss: 0.8441 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8441 2023/02/17 19:48:28 - mmengine - INFO - Epoch(train) [42][ 620/1320] lr: 2.0000e-03 eta: 1:30:27 time: 0.4816 data_time: 0.0149 memory: 27031 grad_norm: 6.5713 loss: 1.1537 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1537 2023/02/17 19:48:38 - mmengine - INFO - Epoch(train) [42][ 640/1320] lr: 2.0000e-03 eta: 1:30:18 time: 0.4811 data_time: 0.0145 memory: 27031 grad_norm: 6.5170 loss: 0.9434 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9434 2023/02/17 19:48:47 - mmengine - INFO - Epoch(train) [42][ 660/1320] lr: 2.0000e-03 eta: 1:30:08 time: 0.4791 data_time: 0.0135 memory: 27031 grad_norm: 6.6787 loss: 0.9758 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9758 2023/02/17 19:48:57 - mmengine - INFO - Epoch(train) [42][ 680/1320] lr: 2.0000e-03 eta: 1:29:59 time: 0.4798 data_time: 0.0143 memory: 27031 grad_norm: 6.3546 loss: 0.8220 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8220 2023/02/17 19:49:07 - mmengine - INFO - Epoch(train) [42][ 700/1320] lr: 2.0000e-03 eta: 1:29:49 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 6.7418 loss: 0.9720 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9720 2023/02/17 19:49:16 - mmengine - INFO - Epoch(train) [42][ 720/1320] lr: 2.0000e-03 eta: 1:29:39 time: 0.4795 data_time: 0.0136 memory: 27031 grad_norm: 6.7468 loss: 0.8630 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8630 2023/02/17 19:49:26 - mmengine - INFO - Epoch(train) [42][ 740/1320] lr: 2.0000e-03 eta: 1:29:30 time: 0.4818 data_time: 0.0155 memory: 27031 grad_norm: 6.5833 loss: 0.9625 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9625 2023/02/17 19:49:35 - mmengine - INFO - Epoch(train) [42][ 760/1320] lr: 2.0000e-03 eta: 1:29:20 time: 0.4798 data_time: 0.0140 memory: 27031 grad_norm: 6.6108 loss: 0.9358 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9358 2023/02/17 19:49:45 - mmengine - INFO - Epoch(train) [42][ 780/1320] lr: 2.0000e-03 eta: 1:29:10 time: 0.4810 data_time: 0.0152 memory: 27031 grad_norm: 6.7344 loss: 0.9583 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9583 2023/02/17 19:49:55 - mmengine - INFO - Epoch(train) [42][ 800/1320] lr: 2.0000e-03 eta: 1:29:01 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 6.7368 loss: 1.0262 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0262 2023/02/17 19:50:04 - mmengine - INFO - Epoch(train) [42][ 820/1320] lr: 2.0000e-03 eta: 1:28:51 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.4691 loss: 1.0199 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0199 2023/02/17 19:50:14 - mmengine - INFO - Epoch(train) [42][ 840/1320] lr: 2.0000e-03 eta: 1:28:41 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 6.6139 loss: 0.7543 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7543 2023/02/17 19:50:24 - mmengine - INFO - Epoch(train) [42][ 860/1320] lr: 2.0000e-03 eta: 1:28:32 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 6.5556 loss: 1.0350 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0350 2023/02/17 19:50:33 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:50:33 - mmengine - INFO - Epoch(train) [42][ 880/1320] lr: 2.0000e-03 eta: 1:28:22 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 6.6817 loss: 0.8952 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8952 2023/02/17 19:50:43 - mmengine - INFO - Epoch(train) [42][ 900/1320] lr: 2.0000e-03 eta: 1:28:12 time: 0.4797 data_time: 0.0144 memory: 27031 grad_norm: 6.7021 loss: 1.0002 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0002 2023/02/17 19:50:52 - mmengine - INFO - Epoch(train) [42][ 920/1320] lr: 2.0000e-03 eta: 1:28:03 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 6.4734 loss: 0.8132 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8132 2023/02/17 19:51:02 - mmengine - INFO - Epoch(train) [42][ 940/1320] lr: 2.0000e-03 eta: 1:27:53 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 6.5504 loss: 0.8212 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8212 2023/02/17 19:51:12 - mmengine - INFO - Epoch(train) [42][ 960/1320] lr: 2.0000e-03 eta: 1:27:43 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.4691 loss: 0.9300 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9300 2023/02/17 19:51:21 - mmengine - INFO - Epoch(train) [42][ 980/1320] lr: 2.0000e-03 eta: 1:27:34 time: 0.4806 data_time: 0.0137 memory: 27031 grad_norm: 6.6336 loss: 1.0361 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0361 2023/02/17 19:51:31 - mmengine - INFO - Epoch(train) [42][1000/1320] lr: 2.0000e-03 eta: 1:27:24 time: 0.4815 data_time: 0.0148 memory: 27031 grad_norm: 6.6778 loss: 1.0528 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0528 2023/02/17 19:51:41 - mmengine - INFO - Epoch(train) [42][1020/1320] lr: 2.0000e-03 eta: 1:27:15 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 6.5917 loss: 0.9527 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9527 2023/02/17 19:51:50 - mmengine - INFO - Epoch(train) [42][1040/1320] lr: 2.0000e-03 eta: 1:27:05 time: 0.4818 data_time: 0.0146 memory: 27031 grad_norm: 6.7196 loss: 0.9607 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9607 2023/02/17 19:52:00 - mmengine - INFO - Epoch(train) [42][1060/1320] lr: 2.0000e-03 eta: 1:26:55 time: 0.4809 data_time: 0.0149 memory: 27031 grad_norm: 6.5685 loss: 0.9463 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9463 2023/02/17 19:52:09 - mmengine - INFO - Epoch(train) [42][1080/1320] lr: 2.0000e-03 eta: 1:26:46 time: 0.4799 data_time: 0.0138 memory: 27031 grad_norm: 6.7472 loss: 0.9199 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9199 2023/02/17 19:52:19 - mmengine - INFO - Epoch(train) [42][1100/1320] lr: 2.0000e-03 eta: 1:26:36 time: 0.4818 data_time: 0.0151 memory: 27031 grad_norm: 6.8146 loss: 0.8027 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8027 2023/02/17 19:52:29 - mmengine - INFO - Epoch(train) [42][1120/1320] lr: 2.0000e-03 eta: 1:26:26 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.7144 loss: 1.1710 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1710 2023/02/17 19:52:38 - mmengine - INFO - Epoch(train) [42][1140/1320] lr: 2.0000e-03 eta: 1:26:17 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 6.7792 loss: 1.1031 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1031 2023/02/17 19:52:48 - mmengine - INFO - Epoch(train) [42][1160/1320] lr: 2.0000e-03 eta: 1:26:07 time: 0.4813 data_time: 0.0147 memory: 27031 grad_norm: 6.6966 loss: 0.9855 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9855 2023/02/17 19:52:58 - mmengine - INFO - Epoch(train) [42][1180/1320] lr: 2.0000e-03 eta: 1:25:57 time: 0.4807 data_time: 0.0138 memory: 27031 grad_norm: 6.8348 loss: 1.0244 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0244 2023/02/17 19:53:07 - mmengine - INFO - Epoch(train) [42][1200/1320] lr: 2.0000e-03 eta: 1:25:48 time: 0.4820 data_time: 0.0150 memory: 27031 grad_norm: 6.7668 loss: 1.0389 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0389 2023/02/17 19:53:17 - mmengine - INFO - Epoch(train) [42][1220/1320] lr: 2.0000e-03 eta: 1:25:38 time: 0.4816 data_time: 0.0151 memory: 27031 grad_norm: 6.6983 loss: 0.9666 top1_acc: 0.3125 top5_acc: 0.8750 loss_cls: 0.9666 2023/02/17 19:53:26 - mmengine - INFO - Epoch(train) [42][1240/1320] lr: 2.0000e-03 eta: 1:25:28 time: 0.4801 data_time: 0.0146 memory: 27031 grad_norm: 6.6970 loss: 0.8330 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8330 2023/02/17 19:53:36 - mmengine - INFO - Epoch(train) [42][1260/1320] lr: 2.0000e-03 eta: 1:25:19 time: 0.4811 data_time: 0.0143 memory: 27031 grad_norm: 6.6370 loss: 0.9890 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9890 2023/02/17 19:53:46 - mmengine - INFO - Epoch(train) [42][1280/1320] lr: 2.0000e-03 eta: 1:25:09 time: 0.4813 data_time: 0.0151 memory: 27031 grad_norm: 6.6746 loss: 0.9136 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9136 2023/02/17 19:53:55 - mmengine - INFO - Epoch(train) [42][1300/1320] lr: 2.0000e-03 eta: 1:25:00 time: 0.4800 data_time: 0.0138 memory: 27031 grad_norm: 6.5678 loss: 0.8462 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8462 2023/02/17 19:54:05 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:54:05 - mmengine - INFO - Epoch(train) [42][1320/1320] lr: 2.0000e-03 eta: 1:24:50 time: 0.4742 data_time: 0.0153 memory: 27031 grad_norm: 6.6522 loss: 0.9086 top1_acc: 0.9091 top5_acc: 1.0000 loss_cls: 0.9086 2023/02/17 19:54:05 - mmengine - INFO - Saving checkpoint at 42 epochs 2023/02/17 19:54:10 - mmengine - INFO - Epoch(val) [42][ 20/194] eta: 0:00:31 time: 0.1832 data_time: 0.0571 memory: 3265 2023/02/17 19:54:12 - mmengine - INFO - Epoch(val) [42][ 40/194] eta: 0:00:24 time: 0.1375 data_time: 0.0126 memory: 3265 2023/02/17 19:54:15 - mmengine - INFO - Epoch(val) [42][ 60/194] eta: 0:00:20 time: 0.1395 data_time: 0.0141 memory: 3265 2023/02/17 19:54:18 - mmengine - INFO - Epoch(val) [42][ 80/194] eta: 0:00:17 time: 0.1398 data_time: 0.0142 memory: 3265 2023/02/17 19:54:21 - mmengine - INFO - Epoch(val) [42][100/194] eta: 0:00:13 time: 0.1384 data_time: 0.0139 memory: 3265 2023/02/17 19:54:24 - mmengine - INFO - Epoch(val) [42][120/194] eta: 0:00:10 time: 0.1388 data_time: 0.0140 memory: 3265 2023/02/17 19:54:26 - mmengine - INFO - Epoch(val) [42][140/194] eta: 0:00:07 time: 0.1416 data_time: 0.0155 memory: 3265 2023/02/17 19:54:29 - mmengine - INFO - Epoch(val) [42][160/194] eta: 0:00:04 time: 0.1388 data_time: 0.0142 memory: 3265 2023/02/17 19:54:32 - mmengine - INFO - Epoch(val) [42][180/194] eta: 0:00:02 time: 0.1360 data_time: 0.0130 memory: 3265 2023/02/17 19:54:34 - mmengine - INFO - Epoch(val) [42][194/194] acc/top1: 0.6092 acc/top5: 0.8692 acc/mean1: 0.5494 2023/02/17 19:54:45 - mmengine - INFO - Epoch(train) [43][ 20/1320] lr: 2.0000e-03 eta: 1:24:40 time: 0.5431 data_time: 0.0633 memory: 27031 grad_norm: 6.6425 loss: 0.8182 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8182 2023/02/17 19:54:55 - mmengine - INFO - Epoch(train) [43][ 40/1320] lr: 2.0000e-03 eta: 1:24:31 time: 0.4810 data_time: 0.0154 memory: 27031 grad_norm: 6.4846 loss: 0.9353 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9353 2023/02/17 19:55:05 - mmengine - INFO - Epoch(train) [43][ 60/1320] lr: 2.0000e-03 eta: 1:24:21 time: 0.4816 data_time: 0.0158 memory: 27031 grad_norm: 6.5578 loss: 0.9336 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9336 2023/02/17 19:55:14 - mmengine - INFO - Epoch(train) [43][ 80/1320] lr: 2.0000e-03 eta: 1:24:12 time: 0.4814 data_time: 0.0151 memory: 27031 grad_norm: 6.5964 loss: 0.8375 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8375 2023/02/17 19:55:24 - mmengine - INFO - Epoch(train) [43][ 100/1320] lr: 2.0000e-03 eta: 1:24:02 time: 0.4809 data_time: 0.0139 memory: 27031 grad_norm: 6.7681 loss: 1.0383 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0383 2023/02/17 19:55:33 - mmengine - INFO - Epoch(train) [43][ 120/1320] lr: 2.0000e-03 eta: 1:23:52 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 6.6193 loss: 0.8943 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8943 2023/02/17 19:55:43 - mmengine - INFO - Epoch(train) [43][ 140/1320] lr: 2.0000e-03 eta: 1:23:43 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 6.7253 loss: 0.9593 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9593 2023/02/17 19:55:53 - mmengine - INFO - Epoch(train) [43][ 160/1320] lr: 2.0000e-03 eta: 1:23:33 time: 0.4817 data_time: 0.0149 memory: 27031 grad_norm: 6.5985 loss: 0.8898 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8898 2023/02/17 19:56:02 - mmengine - INFO - Epoch(train) [43][ 180/1320] lr: 2.0000e-03 eta: 1:23:23 time: 0.4807 data_time: 0.0140 memory: 27031 grad_norm: 6.4371 loss: 0.7640 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7640 2023/02/17 19:56:12 - mmengine - INFO - Epoch(train) [43][ 200/1320] lr: 2.0000e-03 eta: 1:23:14 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 6.6266 loss: 0.8805 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8805 2023/02/17 19:56:22 - mmengine - INFO - Epoch(train) [43][ 220/1320] lr: 2.0000e-03 eta: 1:23:04 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.8000 loss: 0.8989 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8989 2023/02/17 19:56:31 - mmengine - INFO - Epoch(train) [43][ 240/1320] lr: 2.0000e-03 eta: 1:22:54 time: 0.4792 data_time: 0.0140 memory: 27031 grad_norm: 6.8140 loss: 0.8093 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8093 2023/02/17 19:56:41 - mmengine - INFO - Epoch(train) [43][ 260/1320] lr: 2.0000e-03 eta: 1:22:45 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 6.8502 loss: 0.8874 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8874 2023/02/17 19:56:50 - mmengine - INFO - Epoch(train) [43][ 280/1320] lr: 2.0000e-03 eta: 1:22:35 time: 0.4813 data_time: 0.0152 memory: 27031 grad_norm: 6.6983 loss: 0.8642 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8642 2023/02/17 19:57:00 - mmengine - INFO - Epoch(train) [43][ 300/1320] lr: 2.0000e-03 eta: 1:22:25 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.6143 loss: 0.8054 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8054 2023/02/17 19:57:10 - mmengine - INFO - Epoch(train) [43][ 320/1320] lr: 2.0000e-03 eta: 1:22:16 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 6.6172 loss: 0.8969 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8969 2023/02/17 19:57:19 - mmengine - INFO - Epoch(train) [43][ 340/1320] lr: 2.0000e-03 eta: 1:22:06 time: 0.4811 data_time: 0.0148 memory: 27031 grad_norm: 6.5949 loss: 0.9401 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9401 2023/02/17 19:57:29 - mmengine - INFO - Epoch(train) [43][ 360/1320] lr: 2.0000e-03 eta: 1:21:56 time: 0.4801 data_time: 0.0143 memory: 27031 grad_norm: 6.7355 loss: 0.9795 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9795 2023/02/17 19:57:38 - mmengine - INFO - Epoch(train) [43][ 380/1320] lr: 2.0000e-03 eta: 1:21:47 time: 0.4810 data_time: 0.0151 memory: 27031 grad_norm: 6.6711 loss: 0.8829 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8829 2023/02/17 19:57:48 - mmengine - INFO - Epoch(train) [43][ 400/1320] lr: 2.0000e-03 eta: 1:21:37 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 6.5884 loss: 0.9140 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.9140 2023/02/17 19:57:58 - mmengine - INFO - Epoch(train) [43][ 420/1320] lr: 2.0000e-03 eta: 1:21:28 time: 0.4803 data_time: 0.0144 memory: 27031 grad_norm: 6.6799 loss: 0.9562 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9562 2023/02/17 19:58:07 - mmengine - INFO - Epoch(train) [43][ 440/1320] lr: 2.0000e-03 eta: 1:21:18 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 6.7327 loss: 0.8140 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8140 2023/02/17 19:58:17 - mmengine - INFO - Epoch(train) [43][ 460/1320] lr: 2.0000e-03 eta: 1:21:08 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.7377 loss: 0.9229 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9229 2023/02/17 19:58:27 - mmengine - INFO - Epoch(train) [43][ 480/1320] lr: 2.0000e-03 eta: 1:20:59 time: 0.4814 data_time: 0.0144 memory: 27031 grad_norm: 6.8508 loss: 0.9450 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9450 2023/02/17 19:58:36 - mmengine - INFO - Epoch(train) [43][ 500/1320] lr: 2.0000e-03 eta: 1:20:49 time: 0.4816 data_time: 0.0139 memory: 27031 grad_norm: 6.8332 loss: 0.9339 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9339 2023/02/17 19:58:46 - mmengine - INFO - Epoch(train) [43][ 520/1320] lr: 2.0000e-03 eta: 1:20:39 time: 0.4803 data_time: 0.0141 memory: 27031 grad_norm: 6.6416 loss: 0.9416 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9416 2023/02/17 19:58:55 - mmengine - INFO - Epoch(train) [43][ 540/1320] lr: 2.0000e-03 eta: 1:20:30 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.9099 loss: 0.8330 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.8330 2023/02/17 19:59:05 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 19:59:05 - mmengine - INFO - Epoch(train) [43][ 560/1320] lr: 2.0000e-03 eta: 1:20:20 time: 0.4798 data_time: 0.0138 memory: 27031 grad_norm: 6.5385 loss: 0.9661 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9661 2023/02/17 19:59:15 - mmengine - INFO - Epoch(train) [43][ 580/1320] lr: 2.0000e-03 eta: 1:20:10 time: 0.4806 data_time: 0.0144 memory: 27031 grad_norm: 6.7763 loss: 0.9806 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9806 2023/02/17 19:59:24 - mmengine - INFO - Epoch(train) [43][ 600/1320] lr: 2.0000e-03 eta: 1:20:01 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 6.9263 loss: 1.0365 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0365 2023/02/17 19:59:34 - mmengine - INFO - Epoch(train) [43][ 620/1320] lr: 2.0000e-03 eta: 1:19:51 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.9893 loss: 0.8919 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 0.8919 2023/02/17 19:59:43 - mmengine - INFO - Epoch(train) [43][ 640/1320] lr: 2.0000e-03 eta: 1:19:41 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 6.8401 loss: 1.0052 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0052 2023/02/17 19:59:53 - mmengine - INFO - Epoch(train) [43][ 660/1320] lr: 2.0000e-03 eta: 1:19:32 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.5249 loss: 0.8721 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8721 2023/02/17 20:00:03 - mmengine - INFO - Epoch(train) [43][ 680/1320] lr: 2.0000e-03 eta: 1:19:22 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 6.7018 loss: 0.9706 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9706 2023/02/17 20:00:12 - mmengine - INFO - Epoch(train) [43][ 700/1320] lr: 2.0000e-03 eta: 1:19:12 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 6.8455 loss: 1.0470 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0470 2023/02/17 20:00:22 - mmengine - INFO - Epoch(train) [43][ 720/1320] lr: 2.0000e-03 eta: 1:19:03 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 6.6400 loss: 0.7696 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7696 2023/02/17 20:00:32 - mmengine - INFO - Epoch(train) [43][ 740/1320] lr: 2.0000e-03 eta: 1:18:53 time: 0.4811 data_time: 0.0151 memory: 27031 grad_norm: 6.7918 loss: 1.0781 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0781 2023/02/17 20:00:41 - mmengine - INFO - Epoch(train) [43][ 760/1320] lr: 2.0000e-03 eta: 1:18:44 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 6.7717 loss: 0.9760 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9760 2023/02/17 20:00:51 - mmengine - INFO - Epoch(train) [43][ 780/1320] lr: 2.0000e-03 eta: 1:18:34 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.5850 loss: 0.8439 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8439 2023/02/17 20:01:00 - mmengine - INFO - Epoch(train) [43][ 800/1320] lr: 2.0000e-03 eta: 1:18:24 time: 0.4812 data_time: 0.0148 memory: 27031 grad_norm: 6.5243 loss: 0.9790 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9790 2023/02/17 20:01:10 - mmengine - INFO - Epoch(train) [43][ 820/1320] lr: 2.0000e-03 eta: 1:18:15 time: 0.4809 data_time: 0.0146 memory: 27031 grad_norm: 6.7568 loss: 1.0081 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0081 2023/02/17 20:01:20 - mmengine - INFO - Epoch(train) [43][ 840/1320] lr: 2.0000e-03 eta: 1:18:05 time: 0.4804 data_time: 0.0142 memory: 27031 grad_norm: 6.6915 loss: 0.7205 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7205 2023/02/17 20:01:29 - mmengine - INFO - Epoch(train) [43][ 860/1320] lr: 2.0000e-03 eta: 1:17:55 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 6.7577 loss: 0.7990 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7990 2023/02/17 20:01:39 - mmengine - INFO - Epoch(train) [43][ 880/1320] lr: 2.0000e-03 eta: 1:17:46 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 6.6339 loss: 0.9307 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9307 2023/02/17 20:01:48 - mmengine - INFO - Epoch(train) [43][ 900/1320] lr: 2.0000e-03 eta: 1:17:36 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 6.9207 loss: 1.0158 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0158 2023/02/17 20:01:58 - mmengine - INFO - Epoch(train) [43][ 920/1320] lr: 2.0000e-03 eta: 1:17:26 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 6.8947 loss: 1.0428 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0428 2023/02/17 20:02:08 - mmengine - INFO - Epoch(train) [43][ 940/1320] lr: 2.0000e-03 eta: 1:17:17 time: 0.4800 data_time: 0.0136 memory: 27031 grad_norm: 7.0240 loss: 0.9230 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9230 2023/02/17 20:02:17 - mmengine - INFO - Epoch(train) [43][ 960/1320] lr: 2.0000e-03 eta: 1:17:07 time: 0.4820 data_time: 0.0159 memory: 27031 grad_norm: 6.7973 loss: 0.8703 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8703 2023/02/17 20:02:27 - mmengine - INFO - Epoch(train) [43][ 980/1320] lr: 2.0000e-03 eta: 1:16:57 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 6.7508 loss: 0.9805 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9805 2023/02/17 20:02:37 - mmengine - INFO - Epoch(train) [43][1000/1320] lr: 2.0000e-03 eta: 1:16:48 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.6368 loss: 0.9518 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9518 2023/02/17 20:02:46 - mmengine - INFO - Epoch(train) [43][1020/1320] lr: 2.0000e-03 eta: 1:16:38 time: 0.4812 data_time: 0.0145 memory: 27031 grad_norm: 6.8896 loss: 0.9953 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9953 2023/02/17 20:02:56 - mmengine - INFO - Epoch(train) [43][1040/1320] lr: 2.0000e-03 eta: 1:16:28 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.8573 loss: 1.0094 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.0094 2023/02/17 20:03:05 - mmengine - INFO - Epoch(train) [43][1060/1320] lr: 2.0000e-03 eta: 1:16:19 time: 0.4811 data_time: 0.0147 memory: 27031 grad_norm: 6.8323 loss: 0.9267 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9267 2023/02/17 20:03:15 - mmengine - INFO - Epoch(train) [43][1080/1320] lr: 2.0000e-03 eta: 1:16:09 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 6.9362 loss: 0.9706 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9706 2023/02/17 20:03:25 - mmengine - INFO - Epoch(train) [43][1100/1320] lr: 2.0000e-03 eta: 1:16:00 time: 0.4802 data_time: 0.0136 memory: 27031 grad_norm: 6.8755 loss: 0.9965 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9965 2023/02/17 20:03:34 - mmengine - INFO - Epoch(train) [43][1120/1320] lr: 2.0000e-03 eta: 1:15:50 time: 0.4814 data_time: 0.0149 memory: 27031 grad_norm: 6.6826 loss: 0.9175 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9175 2023/02/17 20:03:44 - mmengine - INFO - Epoch(train) [43][1140/1320] lr: 2.0000e-03 eta: 1:15:40 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 6.6636 loss: 0.8665 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8665 2023/02/17 20:03:53 - mmengine - INFO - Epoch(train) [43][1160/1320] lr: 2.0000e-03 eta: 1:15:31 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.6271 loss: 0.9298 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9298 2023/02/17 20:04:03 - mmengine - INFO - Epoch(train) [43][1180/1320] lr: 2.0000e-03 eta: 1:15:21 time: 0.4811 data_time: 0.0149 memory: 27031 grad_norm: 6.9966 loss: 0.9876 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9876 2023/02/17 20:04:13 - mmengine - INFO - Epoch(train) [43][1200/1320] lr: 2.0000e-03 eta: 1:15:11 time: 0.4794 data_time: 0.0139 memory: 27031 grad_norm: 6.9349 loss: 0.8229 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8229 2023/02/17 20:04:22 - mmengine - INFO - Epoch(train) [43][1220/1320] lr: 2.0000e-03 eta: 1:15:02 time: 0.4816 data_time: 0.0146 memory: 27031 grad_norm: 6.6528 loss: 0.9821 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9821 2023/02/17 20:04:32 - mmengine - INFO - Epoch(train) [43][1240/1320] lr: 2.0000e-03 eta: 1:14:52 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 6.8272 loss: 0.8296 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8296 2023/02/17 20:04:42 - mmengine - INFO - Epoch(train) [43][1260/1320] lr: 2.0000e-03 eta: 1:14:42 time: 0.4797 data_time: 0.0136 memory: 27031 grad_norm: 6.6868 loss: 0.9892 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9892 2023/02/17 20:04:51 - mmengine - INFO - Epoch(train) [43][1280/1320] lr: 2.0000e-03 eta: 1:14:33 time: 0.4821 data_time: 0.0146 memory: 27031 grad_norm: 6.8369 loss: 1.0341 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0341 2023/02/17 20:05:01 - mmengine - INFO - Epoch(train) [43][1300/1320] lr: 2.0000e-03 eta: 1:14:23 time: 0.4807 data_time: 0.0136 memory: 27031 grad_norm: 6.9443 loss: 0.9500 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.9500 2023/02/17 20:05:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:05:10 - mmengine - INFO - Epoch(train) [43][1320/1320] lr: 2.0000e-03 eta: 1:14:13 time: 0.4746 data_time: 0.0148 memory: 27031 grad_norm: 7.2464 loss: 1.0470 top1_acc: 0.7273 top5_acc: 1.0000 loss_cls: 1.0470 2023/02/17 20:05:14 - mmengine - INFO - Epoch(val) [43][ 20/194] eta: 0:00:33 time: 0.1952 data_time: 0.0650 memory: 3265 2023/02/17 20:05:17 - mmengine - INFO - Epoch(val) [43][ 40/194] eta: 0:00:25 time: 0.1396 data_time: 0.0137 memory: 3265 2023/02/17 20:05:20 - mmengine - INFO - Epoch(val) [43][ 60/194] eta: 0:00:21 time: 0.1377 data_time: 0.0138 memory: 3265 2023/02/17 20:05:23 - mmengine - INFO - Epoch(val) [43][ 80/194] eta: 0:00:17 time: 0.1369 data_time: 0.0132 memory: 3265 2023/02/17 20:05:25 - mmengine - INFO - Epoch(val) [43][100/194] eta: 0:00:14 time: 0.1387 data_time: 0.0135 memory: 3265 2023/02/17 20:05:28 - mmengine - INFO - Epoch(val) [43][120/194] eta: 0:00:10 time: 0.1394 data_time: 0.0140 memory: 3265 2023/02/17 20:05:31 - mmengine - INFO - Epoch(val) [43][140/194] eta: 0:00:07 time: 0.1388 data_time: 0.0139 memory: 3265 2023/02/17 20:05:34 - mmengine - INFO - Epoch(val) [43][160/194] eta: 0:00:04 time: 0.1387 data_time: 0.0140 memory: 3265 2023/02/17 20:05:36 - mmengine - INFO - Epoch(val) [43][180/194] eta: 0:00:02 time: 0.1385 data_time: 0.0134 memory: 3265 2023/02/17 20:05:39 - mmengine - INFO - Epoch(val) [43][194/194] acc/top1: 0.6026 acc/top5: 0.8658 acc/mean1: 0.5450 2023/02/17 20:05:50 - mmengine - INFO - Epoch(train) [44][ 20/1320] lr: 2.0000e-03 eta: 1:14:04 time: 0.5379 data_time: 0.0603 memory: 27031 grad_norm: 6.9352 loss: 1.0411 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0411 2023/02/17 20:05:59 - mmengine - INFO - Epoch(train) [44][ 40/1320] lr: 2.0000e-03 eta: 1:13:54 time: 0.4810 data_time: 0.0153 memory: 27031 grad_norm: 6.4974 loss: 0.8866 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8866 2023/02/17 20:06:09 - mmengine - INFO - Epoch(train) [44][ 60/1320] lr: 2.0000e-03 eta: 1:13:45 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 6.6893 loss: 1.0042 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 1.0042 2023/02/17 20:06:19 - mmengine - INFO - Epoch(train) [44][ 80/1320] lr: 2.0000e-03 eta: 1:13:35 time: 0.4808 data_time: 0.0141 memory: 27031 grad_norm: 6.5137 loss: 0.9645 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9645 2023/02/17 20:06:28 - mmengine - INFO - Epoch(train) [44][ 100/1320] lr: 2.0000e-03 eta: 1:13:25 time: 0.4800 data_time: 0.0131 memory: 27031 grad_norm: 6.6718 loss: 0.9280 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9280 2023/02/17 20:06:38 - mmengine - INFO - Epoch(train) [44][ 120/1320] lr: 2.0000e-03 eta: 1:13:16 time: 0.4812 data_time: 0.0152 memory: 27031 grad_norm: 6.7725 loss: 0.7546 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7546 2023/02/17 20:06:47 - mmengine - INFO - Epoch(train) [44][ 140/1320] lr: 2.0000e-03 eta: 1:13:06 time: 0.4803 data_time: 0.0142 memory: 27031 grad_norm: 6.8953 loss: 0.9581 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9581 2023/02/17 20:06:57 - mmengine - INFO - Epoch(train) [44][ 160/1320] lr: 2.0000e-03 eta: 1:12:56 time: 0.4798 data_time: 0.0145 memory: 27031 grad_norm: 6.6212 loss: 0.8872 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8872 2023/02/17 20:07:07 - mmengine - INFO - Epoch(train) [44][ 180/1320] lr: 2.0000e-03 eta: 1:12:47 time: 0.4812 data_time: 0.0145 memory: 27031 grad_norm: 6.8309 loss: 0.8822 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8822 2023/02/17 20:07:16 - mmengine - INFO - Epoch(train) [44][ 200/1320] lr: 2.0000e-03 eta: 1:12:37 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 6.6969 loss: 0.8691 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8691 2023/02/17 20:07:26 - mmengine - INFO - Epoch(train) [44][ 220/1320] lr: 2.0000e-03 eta: 1:12:28 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 7.0397 loss: 1.0182 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0182 2023/02/17 20:07:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:07:36 - mmengine - INFO - Epoch(train) [44][ 240/1320] lr: 2.0000e-03 eta: 1:12:18 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 6.9813 loss: 0.9363 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9363 2023/02/17 20:07:45 - mmengine - INFO - Epoch(train) [44][ 260/1320] lr: 2.0000e-03 eta: 1:12:08 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 6.8336 loss: 0.9820 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9820 2023/02/17 20:07:55 - mmengine - INFO - Epoch(train) [44][ 280/1320] lr: 2.0000e-03 eta: 1:11:59 time: 0.4820 data_time: 0.0146 memory: 27031 grad_norm: 6.7594 loss: 0.8677 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8677 2023/02/17 20:08:04 - mmengine - INFO - Epoch(train) [44][ 300/1320] lr: 2.0000e-03 eta: 1:11:49 time: 0.4809 data_time: 0.0138 memory: 27031 grad_norm: 6.9244 loss: 0.9217 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9217 2023/02/17 20:08:14 - mmengine - INFO - Epoch(train) [44][ 320/1320] lr: 2.0000e-03 eta: 1:11:39 time: 0.4809 data_time: 0.0155 memory: 27031 grad_norm: 6.5899 loss: 0.8442 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8442 2023/02/17 20:08:24 - mmengine - INFO - Epoch(train) [44][ 340/1320] lr: 2.0000e-03 eta: 1:11:30 time: 0.4815 data_time: 0.0143 memory: 27031 grad_norm: 6.8994 loss: 1.0317 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0317 2023/02/17 20:08:33 - mmengine - INFO - Epoch(train) [44][ 360/1320] lr: 2.0000e-03 eta: 1:11:20 time: 0.4808 data_time: 0.0140 memory: 27031 grad_norm: 7.0378 loss: 0.9015 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9015 2023/02/17 20:08:43 - mmengine - INFO - Epoch(train) [44][ 380/1320] lr: 2.0000e-03 eta: 1:11:10 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 7.0599 loss: 0.8855 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8855 2023/02/17 20:08:53 - mmengine - INFO - Epoch(train) [44][ 400/1320] lr: 2.0000e-03 eta: 1:11:01 time: 0.4823 data_time: 0.0151 memory: 27031 grad_norm: 6.6291 loss: 0.9347 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9347 2023/02/17 20:09:02 - mmengine - INFO - Epoch(train) [44][ 420/1320] lr: 2.0000e-03 eta: 1:10:51 time: 0.4809 data_time: 0.0141 memory: 27031 grad_norm: 6.7952 loss: 0.9639 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9639 2023/02/17 20:09:12 - mmengine - INFO - Epoch(train) [44][ 440/1320] lr: 2.0000e-03 eta: 1:10:41 time: 0.4810 data_time: 0.0152 memory: 27031 grad_norm: 6.7255 loss: 0.9168 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9168 2023/02/17 20:09:21 - mmengine - INFO - Epoch(train) [44][ 460/1320] lr: 2.0000e-03 eta: 1:10:32 time: 0.4805 data_time: 0.0143 memory: 27031 grad_norm: 6.9699 loss: 0.9641 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9641 2023/02/17 20:09:31 - mmengine - INFO - Epoch(train) [44][ 480/1320] lr: 2.0000e-03 eta: 1:10:22 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 6.8569 loss: 0.9150 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9150 2023/02/17 20:09:41 - mmengine - INFO - Epoch(train) [44][ 500/1320] lr: 2.0000e-03 eta: 1:10:13 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 6.9215 loss: 0.9333 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9333 2023/02/17 20:09:50 - mmengine - INFO - Epoch(train) [44][ 520/1320] lr: 2.0000e-03 eta: 1:10:03 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 6.7692 loss: 0.7833 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7833 2023/02/17 20:10:00 - mmengine - INFO - Epoch(train) [44][ 540/1320] lr: 2.0000e-03 eta: 1:09:53 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 6.9484 loss: 1.0280 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.0280 2023/02/17 20:10:09 - mmengine - INFO - Epoch(train) [44][ 560/1320] lr: 2.0000e-03 eta: 1:09:44 time: 0.4802 data_time: 0.0141 memory: 27031 grad_norm: 6.8685 loss: 1.0389 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0389 2023/02/17 20:10:19 - mmengine - INFO - Epoch(train) [44][ 580/1320] lr: 2.0000e-03 eta: 1:09:34 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 6.9630 loss: 0.8517 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8517 2023/02/17 20:10:29 - mmengine - INFO - Epoch(train) [44][ 600/1320] lr: 2.0000e-03 eta: 1:09:24 time: 0.4803 data_time: 0.0148 memory: 27031 grad_norm: 7.0551 loss: 0.9536 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9536 2023/02/17 20:10:38 - mmengine - INFO - Epoch(train) [44][ 620/1320] lr: 2.0000e-03 eta: 1:09:15 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 6.8252 loss: 0.9801 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9801 2023/02/17 20:10:48 - mmengine - INFO - Epoch(train) [44][ 640/1320] lr: 2.0000e-03 eta: 1:09:05 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 7.1116 loss: 0.7575 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.7575 2023/02/17 20:10:58 - mmengine - INFO - Epoch(train) [44][ 660/1320] lr: 2.0000e-03 eta: 1:08:55 time: 0.4814 data_time: 0.0146 memory: 27031 grad_norm: 6.9577 loss: 0.9725 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9725 2023/02/17 20:11:07 - mmengine - INFO - Epoch(train) [44][ 680/1320] lr: 2.0000e-03 eta: 1:08:46 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 6.9384 loss: 0.9586 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9586 2023/02/17 20:11:17 - mmengine - INFO - Epoch(train) [44][ 700/1320] lr: 2.0000e-03 eta: 1:08:36 time: 0.4820 data_time: 0.0160 memory: 27031 grad_norm: 6.8702 loss: 0.8741 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8741 2023/02/17 20:11:26 - mmengine - INFO - Epoch(train) [44][ 720/1320] lr: 2.0000e-03 eta: 1:08:26 time: 0.4811 data_time: 0.0147 memory: 27031 grad_norm: 6.7485 loss: 0.8424 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8424 2023/02/17 20:11:36 - mmengine - INFO - Epoch(train) [44][ 740/1320] lr: 2.0000e-03 eta: 1:08:17 time: 0.4805 data_time: 0.0135 memory: 27031 grad_norm: 7.0828 loss: 0.7715 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7715 2023/02/17 20:11:46 - mmengine - INFO - Epoch(train) [44][ 760/1320] lr: 2.0000e-03 eta: 1:08:07 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 7.0133 loss: 0.9682 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 0.9682 2023/02/17 20:11:55 - mmengine - INFO - Epoch(train) [44][ 780/1320] lr: 2.0000e-03 eta: 1:07:57 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 6.9678 loss: 0.9625 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9625 2023/02/17 20:12:05 - mmengine - INFO - Epoch(train) [44][ 800/1320] lr: 2.0000e-03 eta: 1:07:48 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.8026 loss: 0.8135 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8135 2023/02/17 20:12:14 - mmengine - INFO - Epoch(train) [44][ 820/1320] lr: 2.0000e-03 eta: 1:07:38 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 6.7403 loss: 0.9332 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9332 2023/02/17 20:12:24 - mmengine - INFO - Epoch(train) [44][ 840/1320] lr: 2.0000e-03 eta: 1:07:29 time: 0.4809 data_time: 0.0141 memory: 27031 grad_norm: 7.1218 loss: 1.0782 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.0782 2023/02/17 20:12:34 - mmengine - INFO - Epoch(train) [44][ 860/1320] lr: 2.0000e-03 eta: 1:07:19 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 6.9763 loss: 1.0254 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.0254 2023/02/17 20:12:43 - mmengine - INFO - Epoch(train) [44][ 880/1320] lr: 2.0000e-03 eta: 1:07:09 time: 0.4821 data_time: 0.0163 memory: 27031 grad_norm: 6.9670 loss: 0.8674 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8674 2023/02/17 20:12:53 - mmengine - INFO - Epoch(train) [44][ 900/1320] lr: 2.0000e-03 eta: 1:07:00 time: 0.4801 data_time: 0.0137 memory: 27031 grad_norm: 6.8265 loss: 0.9529 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9529 2023/02/17 20:13:03 - mmengine - INFO - Epoch(train) [44][ 920/1320] lr: 2.0000e-03 eta: 1:06:50 time: 0.4826 data_time: 0.0160 memory: 27031 grad_norm: 6.9439 loss: 0.9258 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9258 2023/02/17 20:13:12 - mmengine - INFO - Epoch(train) [44][ 940/1320] lr: 2.0000e-03 eta: 1:06:40 time: 0.4800 data_time: 0.0137 memory: 27031 grad_norm: 7.0769 loss: 1.0246 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.0246 2023/02/17 20:13:22 - mmengine - INFO - Epoch(train) [44][ 960/1320] lr: 2.0000e-03 eta: 1:06:31 time: 0.4832 data_time: 0.0167 memory: 27031 grad_norm: 7.1363 loss: 0.8963 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8963 2023/02/17 20:13:32 - mmengine - INFO - Epoch(train) [44][ 980/1320] lr: 2.0000e-03 eta: 1:06:21 time: 0.4811 data_time: 0.0141 memory: 27031 grad_norm: 6.8276 loss: 0.9280 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9280 2023/02/17 20:13:41 - mmengine - INFO - Epoch(train) [44][1000/1320] lr: 2.0000e-03 eta: 1:06:11 time: 0.4807 data_time: 0.0142 memory: 27031 grad_norm: 6.7173 loss: 0.8214 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8214 2023/02/17 20:13:51 - mmengine - INFO - Epoch(train) [44][1020/1320] lr: 2.0000e-03 eta: 1:06:02 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 6.9477 loss: 0.8956 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8956 2023/02/17 20:14:00 - mmengine - INFO - Epoch(train) [44][1040/1320] lr: 2.0000e-03 eta: 1:05:52 time: 0.4812 data_time: 0.0144 memory: 27031 grad_norm: 7.1869 loss: 1.0087 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0087 2023/02/17 20:14:10 - mmengine - INFO - Epoch(train) [44][1060/1320] lr: 2.0000e-03 eta: 1:05:42 time: 0.4807 data_time: 0.0138 memory: 27031 grad_norm: 6.9483 loss: 0.8446 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8446 2023/02/17 20:14:20 - mmengine - INFO - Epoch(train) [44][1080/1320] lr: 2.0000e-03 eta: 1:05:33 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 6.9226 loss: 1.0113 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0113 2023/02/17 20:14:29 - mmengine - INFO - Epoch(train) [44][1100/1320] lr: 2.0000e-03 eta: 1:05:23 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 7.0296 loss: 0.9654 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9654 2023/02/17 20:14:39 - mmengine - INFO - Epoch(train) [44][1120/1320] lr: 2.0000e-03 eta: 1:05:14 time: 0.4811 data_time: 0.0145 memory: 27031 grad_norm: 6.7705 loss: 0.9287 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9287 2023/02/17 20:14:49 - mmengine - INFO - Epoch(train) [44][1140/1320] lr: 2.0000e-03 eta: 1:05:04 time: 0.4813 data_time: 0.0143 memory: 27031 grad_norm: 6.9406 loss: 0.8776 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8776 2023/02/17 20:14:58 - mmengine - INFO - Epoch(train) [44][1160/1320] lr: 2.0000e-03 eta: 1:04:54 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 6.7312 loss: 0.9781 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.9781 2023/02/17 20:15:08 - mmengine - INFO - Epoch(train) [44][1180/1320] lr: 2.0000e-03 eta: 1:04:45 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 7.0906 loss: 0.9311 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9311 2023/02/17 20:15:17 - mmengine - INFO - Epoch(train) [44][1200/1320] lr: 2.0000e-03 eta: 1:04:35 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 7.0312 loss: 0.8639 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8639 2023/02/17 20:15:27 - mmengine - INFO - Epoch(train) [44][1220/1320] lr: 2.0000e-03 eta: 1:04:25 time: 0.4797 data_time: 0.0139 memory: 27031 grad_norm: 6.9249 loss: 0.8308 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8308 2023/02/17 20:15:37 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:15:37 - mmengine - INFO - Epoch(train) [44][1240/1320] lr: 2.0000e-03 eta: 1:04:16 time: 0.4813 data_time: 0.0147 memory: 27031 grad_norm: 6.9731 loss: 0.8210 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8210 2023/02/17 20:15:46 - mmengine - INFO - Epoch(train) [44][1260/1320] lr: 2.0000e-03 eta: 1:04:06 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 7.0468 loss: 0.7922 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7922 2023/02/17 20:15:56 - mmengine - INFO - Epoch(train) [44][1280/1320] lr: 2.0000e-03 eta: 1:03:56 time: 0.4814 data_time: 0.0153 memory: 27031 grad_norm: 6.9640 loss: 0.8894 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8894 2023/02/17 20:16:06 - mmengine - INFO - Epoch(train) [44][1300/1320] lr: 2.0000e-03 eta: 1:03:47 time: 0.4810 data_time: 0.0141 memory: 27031 grad_norm: 7.1049 loss: 0.9414 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9414 2023/02/17 20:16:15 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:16:15 - mmengine - INFO - Epoch(train) [44][1320/1320] lr: 2.0000e-03 eta: 1:03:37 time: 0.4749 data_time: 0.0152 memory: 27031 grad_norm: 6.9824 loss: 0.8606 top1_acc: 0.9091 top5_acc: 0.9091 loss_cls: 0.8606 2023/02/17 20:16:19 - mmengine - INFO - Epoch(val) [44][ 20/194] eta: 0:00:32 time: 0.1868 data_time: 0.0593 memory: 3265 2023/02/17 20:16:22 - mmengine - INFO - Epoch(val) [44][ 40/194] eta: 0:00:24 time: 0.1364 data_time: 0.0131 memory: 3265 2023/02/17 20:16:24 - mmengine - INFO - Epoch(val) [44][ 60/194] eta: 0:00:20 time: 0.1379 data_time: 0.0134 memory: 3265 2023/02/17 20:16:27 - mmengine - INFO - Epoch(val) [44][ 80/194] eta: 0:00:17 time: 0.1379 data_time: 0.0137 memory: 3265 2023/02/17 20:16:30 - mmengine - INFO - Epoch(val) [44][100/194] eta: 0:00:13 time: 0.1386 data_time: 0.0140 memory: 3265 2023/02/17 20:16:33 - mmengine - INFO - Epoch(val) [44][120/194] eta: 0:00:10 time: 0.1374 data_time: 0.0136 memory: 3265 2023/02/17 20:16:35 - mmengine - INFO - Epoch(val) [44][140/194] eta: 0:00:07 time: 0.1383 data_time: 0.0139 memory: 3265 2023/02/17 20:16:38 - mmengine - INFO - Epoch(val) [44][160/194] eta: 0:00:04 time: 0.1391 data_time: 0.0143 memory: 3265 2023/02/17 20:16:41 - mmengine - INFO - Epoch(val) [44][180/194] eta: 0:00:02 time: 0.1378 data_time: 0.0134 memory: 3265 2023/02/17 20:16:44 - mmengine - INFO - Epoch(val) [44][194/194] acc/top1: 0.6028 acc/top5: 0.8651 acc/mean1: 0.5415 2023/02/17 20:16:54 - mmengine - INFO - Epoch(train) [45][ 20/1320] lr: 2.0000e-03 eta: 1:03:28 time: 0.5331 data_time: 0.0602 memory: 27031 grad_norm: 6.8198 loss: 0.9689 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9689 2023/02/17 20:17:04 - mmengine - INFO - Epoch(train) [45][ 40/1320] lr: 2.0000e-03 eta: 1:03:18 time: 0.4808 data_time: 0.0141 memory: 27031 grad_norm: 6.9933 loss: 0.9618 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9618 2023/02/17 20:17:14 - mmengine - INFO - Epoch(train) [45][ 60/1320] lr: 2.0000e-03 eta: 1:03:08 time: 0.4787 data_time: 0.0129 memory: 27031 grad_norm: 6.9259 loss: 0.9387 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9387 2023/02/17 20:17:23 - mmengine - INFO - Epoch(train) [45][ 80/1320] lr: 2.0000e-03 eta: 1:02:59 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 7.0446 loss: 1.1299 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1299 2023/02/17 20:17:33 - mmengine - INFO - Epoch(train) [45][ 100/1320] lr: 2.0000e-03 eta: 1:02:49 time: 0.4807 data_time: 0.0150 memory: 27031 grad_norm: 6.7660 loss: 0.8927 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8927 2023/02/17 20:17:42 - mmengine - INFO - Epoch(train) [45][ 120/1320] lr: 2.0000e-03 eta: 1:02:39 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 7.1506 loss: 0.9630 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9630 2023/02/17 20:17:52 - mmengine - INFO - Epoch(train) [45][ 140/1320] lr: 2.0000e-03 eta: 1:02:30 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 6.9909 loss: 0.8092 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8092 2023/02/17 20:18:02 - mmengine - INFO - Epoch(train) [45][ 160/1320] lr: 2.0000e-03 eta: 1:02:20 time: 0.4803 data_time: 0.0138 memory: 27031 grad_norm: 7.0891 loss: 0.8671 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8671 2023/02/17 20:18:11 - mmengine - INFO - Epoch(train) [45][ 180/1320] lr: 2.0000e-03 eta: 1:02:10 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 6.8874 loss: 0.9896 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9896 2023/02/17 20:18:21 - mmengine - INFO - Epoch(train) [45][ 200/1320] lr: 2.0000e-03 eta: 1:02:01 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 7.0549 loss: 0.8553 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8553 2023/02/17 20:18:31 - mmengine - INFO - Epoch(train) [45][ 220/1320] lr: 2.0000e-03 eta: 1:01:51 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.8418 loss: 0.8728 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8728 2023/02/17 20:18:40 - mmengine - INFO - Epoch(train) [45][ 240/1320] lr: 2.0000e-03 eta: 1:01:41 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 6.6978 loss: 0.8246 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8246 2023/02/17 20:18:50 - mmengine - INFO - Epoch(train) [45][ 260/1320] lr: 2.0000e-03 eta: 1:01:32 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 6.9361 loss: 0.8709 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8709 2023/02/17 20:18:59 - mmengine - INFO - Epoch(train) [45][ 280/1320] lr: 2.0000e-03 eta: 1:01:22 time: 0.4802 data_time: 0.0137 memory: 27031 grad_norm: 7.0061 loss: 0.9350 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9350 2023/02/17 20:19:09 - mmengine - INFO - Epoch(train) [45][ 300/1320] lr: 2.0000e-03 eta: 1:01:13 time: 0.4815 data_time: 0.0145 memory: 27031 grad_norm: 6.7659 loss: 0.9929 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9929 2023/02/17 20:19:19 - mmengine - INFO - Epoch(train) [45][ 320/1320] lr: 2.0000e-03 eta: 1:01:03 time: 0.4803 data_time: 0.0143 memory: 27031 grad_norm: 6.8527 loss: 0.8444 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8444 2023/02/17 20:19:28 - mmengine - INFO - Epoch(train) [45][ 340/1320] lr: 2.0000e-03 eta: 1:00:53 time: 0.4806 data_time: 0.0147 memory: 27031 grad_norm: 7.1543 loss: 0.8610 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8610 2023/02/17 20:19:38 - mmengine - INFO - Epoch(train) [45][ 360/1320] lr: 2.0000e-03 eta: 1:00:44 time: 0.4804 data_time: 0.0141 memory: 27031 grad_norm: 6.9252 loss: 0.9024 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9024 2023/02/17 20:19:47 - mmengine - INFO - Epoch(train) [45][ 380/1320] lr: 2.0000e-03 eta: 1:00:34 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.8752 loss: 0.9284 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9284 2023/02/17 20:19:57 - mmengine - INFO - Epoch(train) [45][ 400/1320] lr: 2.0000e-03 eta: 1:00:24 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.9715 loss: 0.9906 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9906 2023/02/17 20:20:07 - mmengine - INFO - Epoch(train) [45][ 420/1320] lr: 2.0000e-03 eta: 1:00:15 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 7.0134 loss: 0.8122 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8122 2023/02/17 20:20:16 - mmengine - INFO - Epoch(train) [45][ 440/1320] lr: 2.0000e-03 eta: 1:00:05 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 7.0002 loss: 0.8221 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8221 2023/02/17 20:20:26 - mmengine - INFO - Epoch(train) [45][ 460/1320] lr: 2.0000e-03 eta: 0:59:55 time: 0.4804 data_time: 0.0149 memory: 27031 grad_norm: 6.9951 loss: 0.9980 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9980 2023/02/17 20:20:36 - mmengine - INFO - Epoch(train) [45][ 480/1320] lr: 2.0000e-03 eta: 0:59:46 time: 0.4803 data_time: 0.0140 memory: 27031 grad_norm: 7.1469 loss: 0.9565 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9565 2023/02/17 20:20:45 - mmengine - INFO - Epoch(train) [45][ 500/1320] lr: 2.0000e-03 eta: 0:59:36 time: 0.4805 data_time: 0.0149 memory: 27031 grad_norm: 6.8780 loss: 0.9181 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9181 2023/02/17 20:20:55 - mmengine - INFO - Epoch(train) [45][ 520/1320] lr: 2.0000e-03 eta: 0:59:26 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 6.9660 loss: 0.9068 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9068 2023/02/17 20:21:04 - mmengine - INFO - Epoch(train) [45][ 540/1320] lr: 2.0000e-03 eta: 0:59:17 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 7.0254 loss: 0.9352 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9352 2023/02/17 20:21:14 - mmengine - INFO - Epoch(train) [45][ 560/1320] lr: 2.0000e-03 eta: 0:59:07 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 7.3457 loss: 0.9325 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9325 2023/02/17 20:21:24 - mmengine - INFO - Epoch(train) [45][ 580/1320] lr: 2.0000e-03 eta: 0:58:58 time: 0.4834 data_time: 0.0163 memory: 27031 grad_norm: 7.1416 loss: 0.9528 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9528 2023/02/17 20:21:33 - mmengine - INFO - Epoch(train) [45][ 600/1320] lr: 2.0000e-03 eta: 0:58:48 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 7.0715 loss: 1.0198 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0198 2023/02/17 20:21:43 - mmengine - INFO - Epoch(train) [45][ 620/1320] lr: 2.0000e-03 eta: 0:58:38 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.9603 loss: 0.8515 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8515 2023/02/17 20:21:52 - mmengine - INFO - Epoch(train) [45][ 640/1320] lr: 2.0000e-03 eta: 0:58:29 time: 0.4797 data_time: 0.0140 memory: 27031 grad_norm: 7.0853 loss: 0.9288 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9288 2023/02/17 20:22:02 - mmengine - INFO - Epoch(train) [45][ 660/1320] lr: 2.0000e-03 eta: 0:58:19 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 7.2494 loss: 0.9208 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9208 2023/02/17 20:22:12 - mmengine - INFO - Epoch(train) [45][ 680/1320] lr: 2.0000e-03 eta: 0:58:09 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 7.1964 loss: 0.9935 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9935 2023/02/17 20:22:21 - mmengine - INFO - Epoch(train) [45][ 700/1320] lr: 2.0000e-03 eta: 0:58:00 time: 0.4796 data_time: 0.0137 memory: 27031 grad_norm: 7.1438 loss: 0.9816 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.9816 2023/02/17 20:22:31 - mmengine - INFO - Epoch(train) [45][ 720/1320] lr: 2.0000e-03 eta: 0:57:50 time: 0.4813 data_time: 0.0147 memory: 27031 grad_norm: 7.1562 loss: 0.9124 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.9124 2023/02/17 20:22:41 - mmengine - INFO - Epoch(train) [45][ 740/1320] lr: 2.0000e-03 eta: 0:57:40 time: 0.4805 data_time: 0.0147 memory: 27031 grad_norm: 7.1319 loss: 0.8986 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8986 2023/02/17 20:22:50 - mmengine - INFO - Epoch(train) [45][ 760/1320] lr: 2.0000e-03 eta: 0:57:31 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 7.1516 loss: 0.7521 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7521 2023/02/17 20:23:00 - mmengine - INFO - Epoch(train) [45][ 780/1320] lr: 2.0000e-03 eta: 0:57:21 time: 0.4802 data_time: 0.0146 memory: 27031 grad_norm: 7.3738 loss: 1.0260 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.0260 2023/02/17 20:23:09 - mmengine - INFO - Epoch(train) [45][ 800/1320] lr: 2.0000e-03 eta: 0:57:11 time: 0.4814 data_time: 0.0138 memory: 27031 grad_norm: 7.2043 loss: 0.9897 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9897 2023/02/17 20:23:19 - mmengine - INFO - Epoch(train) [45][ 820/1320] lr: 2.0000e-03 eta: 0:57:02 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 7.1877 loss: 1.0189 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.0189 2023/02/17 20:23:29 - mmengine - INFO - Epoch(train) [45][ 840/1320] lr: 2.0000e-03 eta: 0:56:52 time: 0.4802 data_time: 0.0148 memory: 27031 grad_norm: 6.9683 loss: 0.9927 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9927 2023/02/17 20:23:38 - mmengine - INFO - Epoch(train) [45][ 860/1320] lr: 2.0000e-03 eta: 0:56:43 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 7.1715 loss: 0.9927 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9927 2023/02/17 20:23:48 - mmengine - INFO - Epoch(train) [45][ 880/1320] lr: 2.0000e-03 eta: 0:56:33 time: 0.4814 data_time: 0.0150 memory: 27031 grad_norm: 7.0808 loss: 0.9570 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9570 2023/02/17 20:23:58 - mmengine - INFO - Epoch(train) [45][ 900/1320] lr: 2.0000e-03 eta: 0:56:23 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 7.1207 loss: 0.9484 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9484 2023/02/17 20:24:07 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:24:07 - mmengine - INFO - Epoch(train) [45][ 920/1320] lr: 2.0000e-03 eta: 0:56:14 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 7.1766 loss: 1.0489 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.0489 2023/02/17 20:24:17 - mmengine - INFO - Epoch(train) [45][ 940/1320] lr: 2.0000e-03 eta: 0:56:04 time: 0.4817 data_time: 0.0149 memory: 27031 grad_norm: 6.9142 loss: 1.0339 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0339 2023/02/17 20:24:26 - mmengine - INFO - Epoch(train) [45][ 960/1320] lr: 2.0000e-03 eta: 0:55:54 time: 0.4793 data_time: 0.0141 memory: 27031 grad_norm: 6.8370 loss: 0.9455 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9455 2023/02/17 20:24:36 - mmengine - INFO - Epoch(train) [45][ 980/1320] lr: 2.0000e-03 eta: 0:55:45 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 7.2015 loss: 1.1608 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.1608 2023/02/17 20:24:46 - mmengine - INFO - Epoch(train) [45][1000/1320] lr: 2.0000e-03 eta: 0:55:35 time: 0.4807 data_time: 0.0144 memory: 27031 grad_norm: 7.3016 loss: 0.9170 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9170 2023/02/17 20:24:55 - mmengine - INFO - Epoch(train) [45][1020/1320] lr: 2.0000e-03 eta: 0:55:25 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 7.1261 loss: 0.8606 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8606 2023/02/17 20:25:05 - mmengine - INFO - Epoch(train) [45][1040/1320] lr: 2.0000e-03 eta: 0:55:16 time: 0.4816 data_time: 0.0153 memory: 27031 grad_norm: 6.8796 loss: 0.8966 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8966 2023/02/17 20:25:14 - mmengine - INFO - Epoch(train) [45][1060/1320] lr: 2.0000e-03 eta: 0:55:06 time: 0.4802 data_time: 0.0139 memory: 27031 grad_norm: 7.0419 loss: 0.9548 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9548 2023/02/17 20:25:24 - mmengine - INFO - Epoch(train) [45][1080/1320] lr: 2.0000e-03 eta: 0:54:56 time: 0.4813 data_time: 0.0149 memory: 27031 grad_norm: 7.1812 loss: 1.0051 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.0051 2023/02/17 20:25:34 - mmengine - INFO - Epoch(train) [45][1100/1320] lr: 2.0000e-03 eta: 0:54:47 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 7.2102 loss: 1.0346 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.0346 2023/02/17 20:25:43 - mmengine - INFO - Epoch(train) [45][1120/1320] lr: 2.0000e-03 eta: 0:54:37 time: 0.4807 data_time: 0.0139 memory: 27031 grad_norm: 7.0889 loss: 1.0033 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0033 2023/02/17 20:25:53 - mmengine - INFO - Epoch(train) [45][1140/1320] lr: 2.0000e-03 eta: 0:54:28 time: 0.4813 data_time: 0.0145 memory: 27031 grad_norm: 7.1834 loss: 1.0284 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 1.0284 2023/02/17 20:26:03 - mmengine - INFO - Epoch(train) [45][1160/1320] lr: 2.0000e-03 eta: 0:54:18 time: 0.4817 data_time: 0.0155 memory: 27031 grad_norm: 7.0711 loss: 1.1507 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1507 2023/02/17 20:26:12 - mmengine - INFO - Epoch(train) [45][1180/1320] lr: 2.0000e-03 eta: 0:54:08 time: 0.4805 data_time: 0.0137 memory: 27031 grad_norm: 7.3192 loss: 0.8781 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8781 2023/02/17 20:26:22 - mmengine - INFO - Epoch(train) [45][1200/1320] lr: 2.0000e-03 eta: 0:53:59 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 7.1513 loss: 0.9882 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9882 2023/02/17 20:26:31 - mmengine - INFO - Epoch(train) [45][1220/1320] lr: 2.0000e-03 eta: 0:53:49 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 7.2628 loss: 0.9374 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9374 2023/02/17 20:26:41 - mmengine - INFO - Epoch(train) [45][1240/1320] lr: 2.0000e-03 eta: 0:53:39 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 7.1474 loss: 1.1236 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1236 2023/02/17 20:26:51 - mmengine - INFO - Epoch(train) [45][1260/1320] lr: 2.0000e-03 eta: 0:53:30 time: 0.4821 data_time: 0.0154 memory: 27031 grad_norm: 6.8435 loss: 0.9285 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9285 2023/02/17 20:27:00 - mmengine - INFO - Epoch(train) [45][1280/1320] lr: 2.0000e-03 eta: 0:53:20 time: 0.4802 data_time: 0.0142 memory: 27031 grad_norm: 6.9130 loss: 0.8318 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8318 2023/02/17 20:27:10 - mmengine - INFO - Epoch(train) [45][1300/1320] lr: 2.0000e-03 eta: 0:53:10 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 7.1235 loss: 0.9317 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9317 2023/02/17 20:27:19 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:27:19 - mmengine - INFO - Epoch(train) [45][1320/1320] lr: 2.0000e-03 eta: 0:53:01 time: 0.4744 data_time: 0.0148 memory: 27031 grad_norm: 7.4542 loss: 0.9010 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 0.9010 2023/02/17 20:27:19 - mmengine - INFO - Saving checkpoint at 45 epochs 2023/02/17 20:27:24 - mmengine - INFO - Epoch(val) [45][ 20/194] eta: 0:00:32 time: 0.1852 data_time: 0.0591 memory: 3265 2023/02/17 20:27:27 - mmengine - INFO - Epoch(val) [45][ 40/194] eta: 0:00:24 time: 0.1389 data_time: 0.0142 memory: 3265 2023/02/17 20:27:30 - mmengine - INFO - Epoch(val) [45][ 60/194] eta: 0:00:20 time: 0.1386 data_time: 0.0141 memory: 3265 2023/02/17 20:27:33 - mmengine - INFO - Epoch(val) [45][ 80/194] eta: 0:00:17 time: 0.1377 data_time: 0.0132 memory: 3265 2023/02/17 20:27:35 - mmengine - INFO - Epoch(val) [45][100/194] eta: 0:00:13 time: 0.1388 data_time: 0.0142 memory: 3265 2023/02/17 20:27:38 - mmengine - INFO - Epoch(val) [45][120/194] eta: 0:00:10 time: 0.1376 data_time: 0.0137 memory: 3265 2023/02/17 20:27:41 - mmengine - INFO - Epoch(val) [45][140/194] eta: 0:00:07 time: 0.1387 data_time: 0.0142 memory: 3265 2023/02/17 20:27:44 - mmengine - INFO - Epoch(val) [45][160/194] eta: 0:00:04 time: 0.1382 data_time: 0.0136 memory: 3265 2023/02/17 20:27:47 - mmengine - INFO - Epoch(val) [45][180/194] eta: 0:00:02 time: 0.1384 data_time: 0.0143 memory: 3265 2023/02/17 20:27:49 - mmengine - INFO - Epoch(val) [45][194/194] acc/top1: 0.6024 acc/top5: 0.8662 acc/mean1: 0.5426 2023/02/17 20:28:00 - mmengine - INFO - Epoch(train) [46][ 20/1320] lr: 2.0000e-04 eta: 0:52:51 time: 0.5430 data_time: 0.0617 memory: 27031 grad_norm: 7.1301 loss: 0.9683 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9683 2023/02/17 20:28:10 - mmengine - INFO - Epoch(train) [46][ 40/1320] lr: 2.0000e-04 eta: 0:52:42 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 6.9507 loss: 0.8526 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8526 2023/02/17 20:28:19 - mmengine - INFO - Epoch(train) [46][ 60/1320] lr: 2.0000e-04 eta: 0:52:32 time: 0.4819 data_time: 0.0161 memory: 27031 grad_norm: 6.8886 loss: 0.8118 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8118 2023/02/17 20:28:29 - mmengine - INFO - Epoch(train) [46][ 80/1320] lr: 2.0000e-04 eta: 0:52:22 time: 0.4799 data_time: 0.0142 memory: 27031 grad_norm: 6.7951 loss: 0.8870 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8870 2023/02/17 20:28:38 - mmengine - INFO - Epoch(train) [46][ 100/1320] lr: 2.0000e-04 eta: 0:52:13 time: 0.4817 data_time: 0.0152 memory: 27031 grad_norm: 6.8876 loss: 0.7852 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7852 2023/02/17 20:28:48 - mmengine - INFO - Epoch(train) [46][ 120/1320] lr: 2.0000e-04 eta: 0:52:03 time: 0.4806 data_time: 0.0139 memory: 27031 grad_norm: 7.0168 loss: 1.0534 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0534 2023/02/17 20:28:58 - mmengine - INFO - Epoch(train) [46][ 140/1320] lr: 2.0000e-04 eta: 0:51:53 time: 0.4801 data_time: 0.0147 memory: 27031 grad_norm: 6.7148 loss: 0.9351 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9351 2023/02/17 20:29:07 - mmengine - INFO - Epoch(train) [46][ 160/1320] lr: 2.0000e-04 eta: 0:51:44 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 6.6831 loss: 0.7678 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7678 2023/02/17 20:29:17 - mmengine - INFO - Epoch(train) [46][ 180/1320] lr: 2.0000e-04 eta: 0:51:34 time: 0.4806 data_time: 0.0140 memory: 27031 grad_norm: 6.6477 loss: 0.7953 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7953 2023/02/17 20:29:27 - mmengine - INFO - Epoch(train) [46][ 200/1320] lr: 2.0000e-04 eta: 0:51:24 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 6.7409 loss: 0.7505 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7505 2023/02/17 20:29:36 - mmengine - INFO - Epoch(train) [46][ 220/1320] lr: 2.0000e-04 eta: 0:51:15 time: 0.4796 data_time: 0.0141 memory: 27031 grad_norm: 6.7471 loss: 0.8140 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8140 2023/02/17 20:29:46 - mmengine - INFO - Epoch(train) [46][ 240/1320] lr: 2.0000e-04 eta: 0:51:05 time: 0.4804 data_time: 0.0146 memory: 27031 grad_norm: 6.7387 loss: 0.8966 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.8966 2023/02/17 20:29:55 - mmengine - INFO - Epoch(train) [46][ 260/1320] lr: 2.0000e-04 eta: 0:50:56 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.8172 loss: 0.8145 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8145 2023/02/17 20:30:05 - mmengine - INFO - Epoch(train) [46][ 280/1320] lr: 2.0000e-04 eta: 0:50:46 time: 0.4797 data_time: 0.0141 memory: 27031 grad_norm: 6.9541 loss: 0.8858 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8858 2023/02/17 20:30:15 - mmengine - INFO - Epoch(train) [46][ 300/1320] lr: 2.0000e-04 eta: 0:50:36 time: 0.4799 data_time: 0.0147 memory: 27031 grad_norm: 6.8701 loss: 0.8306 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8306 2023/02/17 20:30:24 - mmengine - INFO - Epoch(train) [46][ 320/1320] lr: 2.0000e-04 eta: 0:50:27 time: 0.4820 data_time: 0.0164 memory: 27031 grad_norm: 6.8307 loss: 0.9283 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9283 2023/02/17 20:30:34 - mmengine - INFO - Epoch(train) [46][ 340/1320] lr: 2.0000e-04 eta: 0:50:17 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 6.7931 loss: 0.8552 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8552 2023/02/17 20:30:43 - mmengine - INFO - Epoch(train) [46][ 360/1320] lr: 2.0000e-04 eta: 0:50:07 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 6.5232 loss: 0.7595 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7595 2023/02/17 20:30:53 - mmengine - INFO - Epoch(train) [46][ 380/1320] lr: 2.0000e-04 eta: 0:49:58 time: 0.4808 data_time: 0.0139 memory: 27031 grad_norm: 6.4617 loss: 0.7563 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7563 2023/02/17 20:31:03 - mmengine - INFO - Epoch(train) [46][ 400/1320] lr: 2.0000e-04 eta: 0:49:48 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 6.5713 loss: 0.7787 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.7787 2023/02/17 20:31:12 - mmengine - INFO - Epoch(train) [46][ 420/1320] lr: 2.0000e-04 eta: 0:49:38 time: 0.4810 data_time: 0.0147 memory: 27031 grad_norm: 6.8356 loss: 0.7357 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7357 2023/02/17 20:31:22 - mmengine - INFO - Epoch(train) [46][ 440/1320] lr: 2.0000e-04 eta: 0:49:29 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 6.8269 loss: 0.9653 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9653 2023/02/17 20:31:32 - mmengine - INFO - Epoch(train) [46][ 460/1320] lr: 2.0000e-04 eta: 0:49:19 time: 0.4808 data_time: 0.0145 memory: 27031 grad_norm: 6.6320 loss: 0.7464 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7464 2023/02/17 20:31:41 - mmengine - INFO - Epoch(train) [46][ 480/1320] lr: 2.0000e-04 eta: 0:49:09 time: 0.4806 data_time: 0.0141 memory: 27031 grad_norm: 6.6036 loss: 0.7546 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7546 2023/02/17 20:31:51 - mmengine - INFO - Epoch(train) [46][ 500/1320] lr: 2.0000e-04 eta: 0:49:00 time: 0.4805 data_time: 0.0137 memory: 27031 grad_norm: 6.6343 loss: 0.8590 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8590 2023/02/17 20:32:00 - mmengine - INFO - Epoch(train) [46][ 520/1320] lr: 2.0000e-04 eta: 0:48:50 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 6.5493 loss: 0.8327 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8327 2023/02/17 20:32:10 - mmengine - INFO - Epoch(train) [46][ 540/1320] lr: 2.0000e-04 eta: 0:48:40 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 6.6967 loss: 0.9053 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9053 2023/02/17 20:32:20 - mmengine - INFO - Epoch(train) [46][ 560/1320] lr: 2.0000e-04 eta: 0:48:31 time: 0.4812 data_time: 0.0153 memory: 27031 grad_norm: 6.7501 loss: 0.9488 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9488 2023/02/17 20:32:29 - mmengine - INFO - Epoch(train) [46][ 580/1320] lr: 2.0000e-04 eta: 0:48:21 time: 0.4829 data_time: 0.0164 memory: 27031 grad_norm: 6.7556 loss: 0.8662 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8662 2023/02/17 20:32:39 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:32:39 - mmengine - INFO - Epoch(train) [46][ 600/1320] lr: 2.0000e-04 eta: 0:48:12 time: 0.4797 data_time: 0.0134 memory: 27031 grad_norm: 6.7387 loss: 0.7367 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7367 2023/02/17 20:32:48 - mmengine - INFO - Epoch(train) [46][ 620/1320] lr: 2.0000e-04 eta: 0:48:02 time: 0.4810 data_time: 0.0150 memory: 27031 grad_norm: 6.7918 loss: 0.8496 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8496 2023/02/17 20:32:58 - mmengine - INFO - Epoch(train) [46][ 640/1320] lr: 2.0000e-04 eta: 0:47:52 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 6.7470 loss: 0.8166 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8166 2023/02/17 20:33:08 - mmengine - INFO - Epoch(train) [46][ 660/1320] lr: 2.0000e-04 eta: 0:47:43 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 6.9410 loss: 0.8326 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8326 2023/02/17 20:33:17 - mmengine - INFO - Epoch(train) [46][ 680/1320] lr: 2.0000e-04 eta: 0:47:33 time: 0.4817 data_time: 0.0147 memory: 27031 grad_norm: 6.7730 loss: 0.8304 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8304 2023/02/17 20:33:27 - mmengine - INFO - Epoch(train) [46][ 700/1320] lr: 2.0000e-04 eta: 0:47:23 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 6.9101 loss: 0.7588 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7588 2023/02/17 20:33:37 - mmengine - INFO - Epoch(train) [46][ 720/1320] lr: 2.0000e-04 eta: 0:47:14 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.8577 loss: 0.8056 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8056 2023/02/17 20:33:46 - mmengine - INFO - Epoch(train) [46][ 740/1320] lr: 2.0000e-04 eta: 0:47:04 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 6.6905 loss: 0.7252 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7252 2023/02/17 20:33:56 - mmengine - INFO - Epoch(train) [46][ 760/1320] lr: 2.0000e-04 eta: 0:46:54 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 6.6397 loss: 0.7865 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.7865 2023/02/17 20:34:05 - mmengine - INFO - Epoch(train) [46][ 780/1320] lr: 2.0000e-04 eta: 0:46:45 time: 0.4818 data_time: 0.0153 memory: 27031 grad_norm: 6.7913 loss: 0.7309 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7309 2023/02/17 20:34:15 - mmengine - INFO - Epoch(train) [46][ 800/1320] lr: 2.0000e-04 eta: 0:46:35 time: 0.4808 data_time: 0.0148 memory: 27031 grad_norm: 6.9141 loss: 0.7876 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7876 2023/02/17 20:34:25 - mmengine - INFO - Epoch(train) [46][ 820/1320] lr: 2.0000e-04 eta: 0:46:26 time: 0.4803 data_time: 0.0140 memory: 27031 grad_norm: 6.8340 loss: 0.8549 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8549 2023/02/17 20:34:34 - mmengine - INFO - Epoch(train) [46][ 840/1320] lr: 2.0000e-04 eta: 0:46:16 time: 0.4816 data_time: 0.0151 memory: 27031 grad_norm: 6.5108 loss: 0.7921 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.7921 2023/02/17 20:34:44 - mmengine - INFO - Epoch(train) [46][ 860/1320] lr: 2.0000e-04 eta: 0:46:06 time: 0.4806 data_time: 0.0144 memory: 27031 grad_norm: 6.9313 loss: 0.8471 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8471 2023/02/17 20:34:54 - mmengine - INFO - Epoch(train) [46][ 880/1320] lr: 2.0000e-04 eta: 0:45:57 time: 0.4819 data_time: 0.0143 memory: 27031 grad_norm: 6.7469 loss: 0.8909 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8909 2023/02/17 20:35:03 - mmengine - INFO - Epoch(train) [46][ 900/1320] lr: 2.0000e-04 eta: 0:45:47 time: 0.4817 data_time: 0.0151 memory: 27031 grad_norm: 6.5753 loss: 0.8781 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8781 2023/02/17 20:35:13 - mmengine - INFO - Epoch(train) [46][ 920/1320] lr: 2.0000e-04 eta: 0:45:37 time: 0.4800 data_time: 0.0144 memory: 27031 grad_norm: 6.8394 loss: 0.9137 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9137 2023/02/17 20:35:22 - mmengine - INFO - Epoch(train) [46][ 940/1320] lr: 2.0000e-04 eta: 0:45:28 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 6.7301 loss: 0.8505 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8505 2023/02/17 20:35:32 - mmengine - INFO - Epoch(train) [46][ 960/1320] lr: 2.0000e-04 eta: 0:45:18 time: 0.4812 data_time: 0.0151 memory: 27031 grad_norm: 6.4923 loss: 0.8513 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8513 2023/02/17 20:35:42 - mmengine - INFO - Epoch(train) [46][ 980/1320] lr: 2.0000e-04 eta: 0:45:08 time: 0.4797 data_time: 0.0136 memory: 27031 grad_norm: 6.6259 loss: 0.9061 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9061 2023/02/17 20:35:51 - mmengine - INFO - Epoch(train) [46][1000/1320] lr: 2.0000e-04 eta: 0:44:59 time: 0.4820 data_time: 0.0149 memory: 27031 grad_norm: 6.5744 loss: 0.7394 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7394 2023/02/17 20:36:01 - mmengine - INFO - Epoch(train) [46][1020/1320] lr: 2.0000e-04 eta: 0:44:49 time: 0.4795 data_time: 0.0139 memory: 27031 grad_norm: 6.7187 loss: 0.9724 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9724 2023/02/17 20:36:10 - mmengine - INFO - Epoch(train) [46][1040/1320] lr: 2.0000e-04 eta: 0:44:39 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 6.7391 loss: 0.8441 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8441 2023/02/17 20:36:20 - mmengine - INFO - Epoch(train) [46][1060/1320] lr: 2.0000e-04 eta: 0:44:30 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.7735 loss: 0.8724 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8724 2023/02/17 20:36:30 - mmengine - INFO - Epoch(train) [46][1080/1320] lr: 2.0000e-04 eta: 0:44:20 time: 0.4799 data_time: 0.0134 memory: 27031 grad_norm: 6.5892 loss: 0.9123 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9123 2023/02/17 20:36:39 - mmengine - INFO - Epoch(train) [46][1100/1320] lr: 2.0000e-04 eta: 0:44:11 time: 0.4810 data_time: 0.0152 memory: 27031 grad_norm: 6.7000 loss: 0.7997 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7997 2023/02/17 20:36:49 - mmengine - INFO - Epoch(train) [46][1120/1320] lr: 2.0000e-04 eta: 0:44:01 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.6895 loss: 0.7231 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7231 2023/02/17 20:36:59 - mmengine - INFO - Epoch(train) [46][1140/1320] lr: 2.0000e-04 eta: 0:43:51 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 6.5346 loss: 0.8064 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8064 2023/02/17 20:37:08 - mmengine - INFO - Epoch(train) [46][1160/1320] lr: 2.0000e-04 eta: 0:43:42 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 6.9598 loss: 0.7745 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7745 2023/02/17 20:37:18 - mmengine - INFO - Epoch(train) [46][1180/1320] lr: 2.0000e-04 eta: 0:43:32 time: 0.4811 data_time: 0.0144 memory: 27031 grad_norm: 6.6327 loss: 0.8019 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.8019 2023/02/17 20:37:27 - mmengine - INFO - Epoch(train) [46][1200/1320] lr: 2.0000e-04 eta: 0:43:22 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 6.7467 loss: 0.8179 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8179 2023/02/17 20:37:37 - mmengine - INFO - Epoch(train) [46][1220/1320] lr: 2.0000e-04 eta: 0:43:13 time: 0.4812 data_time: 0.0148 memory: 27031 grad_norm: 6.7982 loss: 0.7071 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7071 2023/02/17 20:37:47 - mmengine - INFO - Epoch(train) [46][1240/1320] lr: 2.0000e-04 eta: 0:43:03 time: 0.4806 data_time: 0.0141 memory: 27031 grad_norm: 6.7252 loss: 0.8212 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8212 2023/02/17 20:37:56 - mmengine - INFO - Epoch(train) [46][1260/1320] lr: 2.0000e-04 eta: 0:42:53 time: 0.4807 data_time: 0.0152 memory: 27031 grad_norm: 6.5370 loss: 0.6622 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6622 2023/02/17 20:38:06 - mmengine - INFO - Epoch(train) [46][1280/1320] lr: 2.0000e-04 eta: 0:42:44 time: 0.4816 data_time: 0.0148 memory: 27031 grad_norm: 6.8398 loss: 0.8310 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8310 2023/02/17 20:38:16 - mmengine - INFO - Epoch(train) [46][1300/1320] lr: 2.0000e-04 eta: 0:42:34 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 6.7209 loss: 0.7962 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7962 2023/02/17 20:38:25 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:38:25 - mmengine - INFO - Epoch(train) [46][1320/1320] lr: 2.0000e-04 eta: 0:42:24 time: 0.4765 data_time: 0.0175 memory: 27031 grad_norm: 6.7329 loss: 0.8480 top1_acc: 0.5455 top5_acc: 0.9091 loss_cls: 0.8480 2023/02/17 20:38:29 - mmengine - INFO - Epoch(val) [46][ 20/194] eta: 0:00:32 time: 0.1874 data_time: 0.0593 memory: 3265 2023/02/17 20:38:32 - mmengine - INFO - Epoch(val) [46][ 40/194] eta: 0:00:25 time: 0.1415 data_time: 0.0150 memory: 3265 2023/02/17 20:38:34 - mmengine - INFO - Epoch(val) [46][ 60/194] eta: 0:00:20 time: 0.1386 data_time: 0.0141 memory: 3265 2023/02/17 20:38:37 - mmengine - INFO - Epoch(val) [46][ 80/194] eta: 0:00:17 time: 0.1374 data_time: 0.0132 memory: 3265 2023/02/17 20:38:40 - mmengine - INFO - Epoch(val) [46][100/194] eta: 0:00:13 time: 0.1383 data_time: 0.0138 memory: 3265 2023/02/17 20:38:43 - mmengine - INFO - Epoch(val) [46][120/194] eta: 0:00:10 time: 0.1382 data_time: 0.0136 memory: 3265 2023/02/17 20:38:45 - mmengine - INFO - Epoch(val) [46][140/194] eta: 0:00:07 time: 0.1388 data_time: 0.0145 memory: 3265 2023/02/17 20:38:48 - mmengine - INFO - Epoch(val) [46][160/194] eta: 0:00:04 time: 0.1395 data_time: 0.0146 memory: 3265 2023/02/17 20:38:51 - mmengine - INFO - Epoch(val) [46][180/194] eta: 0:00:02 time: 0.1370 data_time: 0.0131 memory: 3265 2023/02/17 20:38:54 - mmengine - INFO - Epoch(val) [46][194/194] acc/top1: 0.6203 acc/top5: 0.8754 acc/mean1: 0.5607 2023/02/17 20:38:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_31.pth is removed 2023/02/17 20:38:55 - mmengine - INFO - The best checkpoint with 0.6203 acc/top1 at 46 epoch is saved to best_acc/top1_epoch_46.pth. 2023/02/17 20:39:05 - mmengine - INFO - Epoch(train) [47][ 20/1320] lr: 2.0000e-04 eta: 0:42:15 time: 0.5369 data_time: 0.0610 memory: 27031 grad_norm: 6.6614 loss: 0.8790 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8790 2023/02/17 20:39:15 - mmengine - INFO - Epoch(train) [47][ 40/1320] lr: 2.0000e-04 eta: 0:42:05 time: 0.4808 data_time: 0.0141 memory: 27031 grad_norm: 6.8269 loss: 0.7751 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 0.7751 2023/02/17 20:39:25 - mmengine - INFO - Epoch(train) [47][ 60/1320] lr: 2.0000e-04 eta: 0:41:56 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.8011 loss: 0.8271 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8271 2023/02/17 20:39:34 - mmengine - INFO - Epoch(train) [47][ 80/1320] lr: 2.0000e-04 eta: 0:41:46 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 6.8126 loss: 0.8335 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8335 2023/02/17 20:39:44 - mmengine - INFO - Epoch(train) [47][ 100/1320] lr: 2.0000e-04 eta: 0:41:36 time: 0.4807 data_time: 0.0141 memory: 27031 grad_norm: 6.5923 loss: 0.9008 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 0.9008 2023/02/17 20:39:53 - mmengine - INFO - Epoch(train) [47][ 120/1320] lr: 2.0000e-04 eta: 0:41:27 time: 0.4808 data_time: 0.0149 memory: 27031 grad_norm: 6.7221 loss: 0.7642 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7642 2023/02/17 20:40:03 - mmengine - INFO - Epoch(train) [47][ 140/1320] lr: 2.0000e-04 eta: 0:41:17 time: 0.4798 data_time: 0.0139 memory: 27031 grad_norm: 6.5693 loss: 0.7451 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7451 2023/02/17 20:40:13 - mmengine - INFO - Epoch(train) [47][ 160/1320] lr: 2.0000e-04 eta: 0:41:07 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 6.5372 loss: 0.7486 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7486 2023/02/17 20:40:22 - mmengine - INFO - Epoch(train) [47][ 180/1320] lr: 2.0000e-04 eta: 0:40:58 time: 0.4799 data_time: 0.0144 memory: 27031 grad_norm: 6.7895 loss: 0.7777 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7777 2023/02/17 20:40:32 - mmengine - INFO - Epoch(train) [47][ 200/1320] lr: 2.0000e-04 eta: 0:40:48 time: 0.4815 data_time: 0.0142 memory: 27031 grad_norm: 6.6673 loss: 0.8928 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8928 2023/02/17 20:40:42 - mmengine - INFO - Epoch(train) [47][ 220/1320] lr: 2.0000e-04 eta: 0:40:38 time: 0.4803 data_time: 0.0147 memory: 27031 grad_norm: 6.6346 loss: 0.7915 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7915 2023/02/17 20:40:51 - mmengine - INFO - Epoch(train) [47][ 240/1320] lr: 2.0000e-04 eta: 0:40:29 time: 0.4797 data_time: 0.0138 memory: 27031 grad_norm: 6.7286 loss: 0.8080 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8080 2023/02/17 20:41:01 - mmengine - INFO - Epoch(train) [47][ 260/1320] lr: 2.0000e-04 eta: 0:40:19 time: 0.4808 data_time: 0.0150 memory: 27031 grad_norm: 6.7430 loss: 0.6950 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6950 2023/02/17 20:41:10 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:41:10 - mmengine - INFO - Epoch(train) [47][ 280/1320] lr: 2.0000e-04 eta: 0:40:10 time: 0.4807 data_time: 0.0148 memory: 27031 grad_norm: 6.9716 loss: 0.7441 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7441 2023/02/17 20:41:20 - mmengine - INFO - Epoch(train) [47][ 300/1320] lr: 2.0000e-04 eta: 0:40:00 time: 0.4807 data_time: 0.0138 memory: 27031 grad_norm: 6.6528 loss: 0.7902 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7902 2023/02/17 20:41:30 - mmengine - INFO - Epoch(train) [47][ 320/1320] lr: 2.0000e-04 eta: 0:39:50 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.8164 loss: 0.8078 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8078 2023/02/17 20:41:39 - mmengine - INFO - Epoch(train) [47][ 340/1320] lr: 2.0000e-04 eta: 0:39:41 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.7608 loss: 0.8853 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8853 2023/02/17 20:41:49 - mmengine - INFO - Epoch(train) [47][ 360/1320] lr: 2.0000e-04 eta: 0:39:31 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.6479 loss: 0.9644 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9644 2023/02/17 20:41:58 - mmengine - INFO - Epoch(train) [47][ 380/1320] lr: 2.0000e-04 eta: 0:39:21 time: 0.4819 data_time: 0.0149 memory: 27031 grad_norm: 6.8346 loss: 0.9410 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.9410 2023/02/17 20:42:08 - mmengine - INFO - Epoch(train) [47][ 400/1320] lr: 2.0000e-04 eta: 0:39:12 time: 0.4798 data_time: 0.0138 memory: 27031 grad_norm: 6.8825 loss: 0.8540 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.8540 2023/02/17 20:42:18 - mmengine - INFO - Epoch(train) [47][ 420/1320] lr: 2.0000e-04 eta: 0:39:02 time: 0.4806 data_time: 0.0144 memory: 27031 grad_norm: 6.7920 loss: 0.7918 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.7918 2023/02/17 20:42:27 - mmengine - INFO - Epoch(train) [47][ 440/1320] lr: 2.0000e-04 eta: 0:38:52 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.5644 loss: 0.8760 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8760 2023/02/17 20:42:37 - mmengine - INFO - Epoch(train) [47][ 460/1320] lr: 2.0000e-04 eta: 0:38:43 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.8067 loss: 0.9244 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.9244 2023/02/17 20:42:47 - mmengine - INFO - Epoch(train) [47][ 480/1320] lr: 2.0000e-04 eta: 0:38:33 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 6.6531 loss: 0.8302 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8302 2023/02/17 20:42:56 - mmengine - INFO - Epoch(train) [47][ 500/1320] lr: 2.0000e-04 eta: 0:38:23 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.8328 loss: 0.7463 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7463 2023/02/17 20:43:06 - mmengine - INFO - Epoch(train) [47][ 520/1320] lr: 2.0000e-04 eta: 0:38:14 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.5130 loss: 0.6639 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6639 2023/02/17 20:43:15 - mmengine - INFO - Epoch(train) [47][ 540/1320] lr: 2.0000e-04 eta: 0:38:04 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 6.5198 loss: 0.7237 top1_acc: 0.7500 top5_acc: 0.7500 loss_cls: 0.7237 2023/02/17 20:43:25 - mmengine - INFO - Epoch(train) [47][ 560/1320] lr: 2.0000e-04 eta: 0:37:55 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 6.6336 loss: 0.6956 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6956 2023/02/17 20:43:35 - mmengine - INFO - Epoch(train) [47][ 580/1320] lr: 2.0000e-04 eta: 0:37:45 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.9156 loss: 0.7912 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7912 2023/02/17 20:43:44 - mmengine - INFO - Epoch(train) [47][ 600/1320] lr: 2.0000e-04 eta: 0:37:35 time: 0.4813 data_time: 0.0153 memory: 27031 grad_norm: 6.4928 loss: 0.8100 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8100 2023/02/17 20:43:54 - mmengine - INFO - Epoch(train) [47][ 620/1320] lr: 2.0000e-04 eta: 0:37:26 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 6.9369 loss: 0.7690 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.7690 2023/02/17 20:44:03 - mmengine - INFO - Epoch(train) [47][ 640/1320] lr: 2.0000e-04 eta: 0:37:16 time: 0.4805 data_time: 0.0140 memory: 27031 grad_norm: 6.7275 loss: 0.9473 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9473 2023/02/17 20:44:13 - mmengine - INFO - Epoch(train) [47][ 660/1320] lr: 2.0000e-04 eta: 0:37:06 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.7761 loss: 0.8203 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8203 2023/02/17 20:44:23 - mmengine - INFO - Epoch(train) [47][ 680/1320] lr: 2.0000e-04 eta: 0:36:57 time: 0.4821 data_time: 0.0153 memory: 27031 grad_norm: 6.6026 loss: 0.8387 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8387 2023/02/17 20:44:32 - mmengine - INFO - Epoch(train) [47][ 700/1320] lr: 2.0000e-04 eta: 0:36:47 time: 0.4819 data_time: 0.0146 memory: 27031 grad_norm: 6.8045 loss: 0.7695 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7695 2023/02/17 20:44:42 - mmengine - INFO - Epoch(train) [47][ 720/1320] lr: 2.0000e-04 eta: 0:36:37 time: 0.4801 data_time: 0.0139 memory: 27031 grad_norm: 6.7681 loss: 0.7475 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7475 2023/02/17 20:44:52 - mmengine - INFO - Epoch(train) [47][ 740/1320] lr: 2.0000e-04 eta: 0:36:28 time: 0.4808 data_time: 0.0140 memory: 27031 grad_norm: 6.7308 loss: 0.8684 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8684 2023/02/17 20:45:01 - mmengine - INFO - Epoch(train) [47][ 760/1320] lr: 2.0000e-04 eta: 0:36:18 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.8753 loss: 0.7890 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.7890 2023/02/17 20:45:11 - mmengine - INFO - Epoch(train) [47][ 780/1320] lr: 2.0000e-04 eta: 0:36:08 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 6.7554 loss: 0.8737 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8737 2023/02/17 20:45:20 - mmengine - INFO - Epoch(train) [47][ 800/1320] lr: 2.0000e-04 eta: 0:35:59 time: 0.4806 data_time: 0.0140 memory: 27031 grad_norm: 6.9154 loss: 0.7494 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7494 2023/02/17 20:45:30 - mmengine - INFO - Epoch(train) [47][ 820/1320] lr: 2.0000e-04 eta: 0:35:49 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 7.0010 loss: 0.8535 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8535 2023/02/17 20:45:40 - mmengine - INFO - Epoch(train) [47][ 840/1320] lr: 2.0000e-04 eta: 0:35:40 time: 0.4817 data_time: 0.0155 memory: 27031 grad_norm: 6.8141 loss: 0.8181 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8181 2023/02/17 20:45:49 - mmengine - INFO - Epoch(train) [47][ 860/1320] lr: 2.0000e-04 eta: 0:35:30 time: 0.4810 data_time: 0.0148 memory: 27031 grad_norm: 7.0312 loss: 0.8736 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 0.8736 2023/02/17 20:45:59 - mmengine - INFO - Epoch(train) [47][ 880/1320] lr: 2.0000e-04 eta: 0:35:20 time: 0.4803 data_time: 0.0139 memory: 27031 grad_norm: 6.6887 loss: 0.7439 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7439 2023/02/17 20:46:09 - mmengine - INFO - Epoch(train) [47][ 900/1320] lr: 2.0000e-04 eta: 0:35:11 time: 0.4809 data_time: 0.0151 memory: 27031 grad_norm: 6.6114 loss: 0.8227 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8227 2023/02/17 20:46:18 - mmengine - INFO - Epoch(train) [47][ 920/1320] lr: 2.0000e-04 eta: 0:35:01 time: 0.4820 data_time: 0.0152 memory: 27031 grad_norm: 6.7831 loss: 0.8124 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8124 2023/02/17 20:46:28 - mmengine - INFO - Epoch(train) [47][ 940/1320] lr: 2.0000e-04 eta: 0:34:51 time: 0.4796 data_time: 0.0140 memory: 27031 grad_norm: 6.6539 loss: 0.8377 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.8377 2023/02/17 20:46:37 - mmengine - INFO - Epoch(train) [47][ 960/1320] lr: 2.0000e-04 eta: 0:34:42 time: 0.4815 data_time: 0.0149 memory: 27031 grad_norm: 6.6721 loss: 0.7461 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7461 2023/02/17 20:46:47 - mmengine - INFO - Epoch(train) [47][ 980/1320] lr: 2.0000e-04 eta: 0:34:32 time: 0.4815 data_time: 0.0152 memory: 27031 grad_norm: 6.5700 loss: 0.7310 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.7310 2023/02/17 20:46:57 - mmengine - INFO - Epoch(train) [47][1000/1320] lr: 2.0000e-04 eta: 0:34:22 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.7687 loss: 0.7715 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7715 2023/02/17 20:47:06 - mmengine - INFO - Epoch(train) [47][1020/1320] lr: 2.0000e-04 eta: 0:34:13 time: 0.4813 data_time: 0.0149 memory: 27031 grad_norm: 6.7816 loss: 0.7972 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7972 2023/02/17 20:47:16 - mmengine - INFO - Epoch(train) [47][1040/1320] lr: 2.0000e-04 eta: 0:34:03 time: 0.4800 data_time: 0.0143 memory: 27031 grad_norm: 6.7296 loss: 0.7987 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7987 2023/02/17 20:47:26 - mmengine - INFO - Epoch(train) [47][1060/1320] lr: 2.0000e-04 eta: 0:33:54 time: 0.4817 data_time: 0.0148 memory: 27031 grad_norm: 6.8467 loss: 0.8608 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8608 2023/02/17 20:47:35 - mmengine - INFO - Epoch(train) [47][1080/1320] lr: 2.0000e-04 eta: 0:33:44 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 6.9673 loss: 0.7615 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7615 2023/02/17 20:47:45 - mmengine - INFO - Epoch(train) [47][1100/1320] lr: 2.0000e-04 eta: 0:33:34 time: 0.4809 data_time: 0.0151 memory: 27031 grad_norm: 6.7079 loss: 0.7381 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7381 2023/02/17 20:47:54 - mmengine - INFO - Epoch(train) [47][1120/1320] lr: 2.0000e-04 eta: 0:33:25 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.5355 loss: 0.6709 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6709 2023/02/17 20:48:04 - mmengine - INFO - Epoch(train) [47][1140/1320] lr: 2.0000e-04 eta: 0:33:15 time: 0.4807 data_time: 0.0141 memory: 27031 grad_norm: 6.9292 loss: 0.9272 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9272 2023/02/17 20:48:14 - mmengine - INFO - Epoch(train) [47][1160/1320] lr: 2.0000e-04 eta: 0:33:05 time: 0.4807 data_time: 0.0150 memory: 27031 grad_norm: 6.9464 loss: 0.6865 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6865 2023/02/17 20:48:23 - mmengine - INFO - Epoch(train) [47][1180/1320] lr: 2.0000e-04 eta: 0:32:56 time: 0.4821 data_time: 0.0151 memory: 27031 grad_norm: 6.8457 loss: 0.8791 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8791 2023/02/17 20:48:33 - mmengine - INFO - Epoch(train) [47][1200/1320] lr: 2.0000e-04 eta: 0:32:46 time: 0.4805 data_time: 0.0138 memory: 27031 grad_norm: 7.0037 loss: 0.8547 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8547 2023/02/17 20:48:43 - mmengine - INFO - Epoch(train) [47][1220/1320] lr: 2.0000e-04 eta: 0:32:36 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 6.7108 loss: 0.8179 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8179 2023/02/17 20:48:52 - mmengine - INFO - Epoch(train) [47][1240/1320] lr: 2.0000e-04 eta: 0:32:27 time: 0.4820 data_time: 0.0147 memory: 27031 grad_norm: 6.7420 loss: 0.7969 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.7969 2023/02/17 20:49:02 - mmengine - INFO - Epoch(train) [47][1260/1320] lr: 2.0000e-04 eta: 0:32:17 time: 0.4808 data_time: 0.0140 memory: 27031 grad_norm: 7.0951 loss: 0.7625 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7625 2023/02/17 20:49:11 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:49:11 - mmengine - INFO - Epoch(train) [47][1280/1320] lr: 2.0000e-04 eta: 0:32:07 time: 0.4812 data_time: 0.0154 memory: 27031 grad_norm: 6.7255 loss: 0.5644 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5644 2023/02/17 20:49:21 - mmengine - INFO - Epoch(train) [47][1300/1320] lr: 2.0000e-04 eta: 0:31:58 time: 0.4802 data_time: 0.0140 memory: 27031 grad_norm: 6.8457 loss: 0.8201 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8201 2023/02/17 20:49:31 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:49:31 - mmengine - INFO - Epoch(train) [47][1320/1320] lr: 2.0000e-04 eta: 0:31:48 time: 0.4749 data_time: 0.0156 memory: 27031 grad_norm: 6.9543 loss: 0.7216 top1_acc: 0.9091 top5_acc: 1.0000 loss_cls: 0.7216 2023/02/17 20:49:34 - mmengine - INFO - Epoch(val) [47][ 20/194] eta: 0:00:33 time: 0.1931 data_time: 0.0655 memory: 3265 2023/02/17 20:49:37 - mmengine - INFO - Epoch(val) [47][ 40/194] eta: 0:00:25 time: 0.1384 data_time: 0.0135 memory: 3265 2023/02/17 20:49:40 - mmengine - INFO - Epoch(val) [47][ 60/194] eta: 0:00:21 time: 0.1391 data_time: 0.0140 memory: 3265 2023/02/17 20:49:43 - mmengine - INFO - Epoch(val) [47][ 80/194] eta: 0:00:17 time: 0.1385 data_time: 0.0142 memory: 3265 2023/02/17 20:49:46 - mmengine - INFO - Epoch(val) [47][100/194] eta: 0:00:14 time: 0.1384 data_time: 0.0138 memory: 3265 2023/02/17 20:49:48 - mmengine - INFO - Epoch(val) [47][120/194] eta: 0:00:10 time: 0.1391 data_time: 0.0137 memory: 3265 2023/02/17 20:49:51 - mmengine - INFO - Epoch(val) [47][140/194] eta: 0:00:07 time: 0.1387 data_time: 0.0137 memory: 3265 2023/02/17 20:49:54 - mmengine - INFO - Epoch(val) [47][160/194] eta: 0:00:04 time: 0.1369 data_time: 0.0131 memory: 3265 2023/02/17 20:49:57 - mmengine - INFO - Epoch(val) [47][180/194] eta: 0:00:02 time: 0.1369 data_time: 0.0129 memory: 3265 2023/02/17 20:49:59 - mmengine - INFO - Epoch(val) [47][194/194] acc/top1: 0.6216 acc/top5: 0.8756 acc/mean1: 0.5611 2023/02/17 20:49:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_46.pth is removed 2023/02/17 20:50:00 - mmengine - INFO - The best checkpoint with 0.6216 acc/top1 at 47 epoch is saved to best_acc/top1_epoch_47.pth. 2023/02/17 20:50:11 - mmengine - INFO - Epoch(train) [48][ 20/1320] lr: 2.0000e-04 eta: 0:31:39 time: 0.5292 data_time: 0.0573 memory: 27031 grad_norm: 6.7366 loss: 0.7860 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7860 2023/02/17 20:50:20 - mmengine - INFO - Epoch(train) [48][ 40/1320] lr: 2.0000e-04 eta: 0:31:29 time: 0.4814 data_time: 0.0137 memory: 27031 grad_norm: 6.5862 loss: 0.6914 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6914 2023/02/17 20:50:30 - mmengine - INFO - Epoch(train) [48][ 60/1320] lr: 2.0000e-04 eta: 0:31:19 time: 0.4805 data_time: 0.0144 memory: 27031 grad_norm: 6.6574 loss: 0.8525 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8525 2023/02/17 20:50:40 - mmengine - INFO - Epoch(train) [48][ 80/1320] lr: 2.0000e-04 eta: 0:31:10 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 6.7782 loss: 0.7680 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 0.7680 2023/02/17 20:50:49 - mmengine - INFO - Epoch(train) [48][ 100/1320] lr: 2.0000e-04 eta: 0:31:00 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.6579 loss: 0.6681 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6681 2023/02/17 20:50:59 - mmengine - INFO - Epoch(train) [48][ 120/1320] lr: 2.0000e-04 eta: 0:30:50 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 6.8429 loss: 0.8333 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.8333 2023/02/17 20:51:08 - mmengine - INFO - Epoch(train) [48][ 140/1320] lr: 2.0000e-04 eta: 0:30:41 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 6.7061 loss: 0.7243 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7243 2023/02/17 20:51:18 - mmengine - INFO - Epoch(train) [48][ 160/1320] lr: 2.0000e-04 eta: 0:30:31 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.8839 loss: 0.9344 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9344 2023/02/17 20:51:28 - mmengine - INFO - Epoch(train) [48][ 180/1320] lr: 2.0000e-04 eta: 0:30:21 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 6.8398 loss: 0.8479 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8479 2023/02/17 20:51:37 - mmengine - INFO - Epoch(train) [48][ 200/1320] lr: 2.0000e-04 eta: 0:30:12 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.8252 loss: 0.7359 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7359 2023/02/17 20:51:47 - mmengine - INFO - Epoch(train) [48][ 220/1320] lr: 2.0000e-04 eta: 0:30:02 time: 0.4808 data_time: 0.0145 memory: 27031 grad_norm: 6.8073 loss: 0.6938 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6938 2023/02/17 20:51:56 - mmengine - INFO - Epoch(train) [48][ 240/1320] lr: 2.0000e-04 eta: 0:29:53 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 7.0368 loss: 0.8326 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8326 2023/02/17 20:52:06 - mmengine - INFO - Epoch(train) [48][ 260/1320] lr: 2.0000e-04 eta: 0:29:43 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 6.7769 loss: 0.8738 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8738 2023/02/17 20:52:16 - mmengine - INFO - Epoch(train) [48][ 280/1320] lr: 2.0000e-04 eta: 0:29:33 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.7451 loss: 0.7898 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.7898 2023/02/17 20:52:25 - mmengine - INFO - Epoch(train) [48][ 300/1320] lr: 2.0000e-04 eta: 0:29:24 time: 0.4821 data_time: 0.0158 memory: 27031 grad_norm: 6.8250 loss: 0.8488 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8488 2023/02/17 20:52:35 - mmengine - INFO - Epoch(train) [48][ 320/1320] lr: 2.0000e-04 eta: 0:29:14 time: 0.4806 data_time: 0.0152 memory: 27031 grad_norm: 6.8496 loss: 0.7387 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.7387 2023/02/17 20:52:45 - mmengine - INFO - Epoch(train) [48][ 340/1320] lr: 2.0000e-04 eta: 0:29:04 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 6.8336 loss: 0.6877 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6877 2023/02/17 20:52:54 - mmengine - INFO - Epoch(train) [48][ 360/1320] lr: 2.0000e-04 eta: 0:28:55 time: 0.4798 data_time: 0.0142 memory: 27031 grad_norm: 6.7132 loss: 0.7824 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7824 2023/02/17 20:53:04 - mmengine - INFO - Epoch(train) [48][ 380/1320] lr: 2.0000e-04 eta: 0:28:45 time: 0.4826 data_time: 0.0151 memory: 27031 grad_norm: 6.7735 loss: 0.7074 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7074 2023/02/17 20:53:13 - mmengine - INFO - Epoch(train) [48][ 400/1320] lr: 2.0000e-04 eta: 0:28:35 time: 0.4820 data_time: 0.0155 memory: 27031 grad_norm: 6.7592 loss: 0.8016 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8016 2023/02/17 20:53:23 - mmengine - INFO - Epoch(train) [48][ 420/1320] lr: 2.0000e-04 eta: 0:28:26 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 6.7236 loss: 0.8254 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8254 2023/02/17 20:53:33 - mmengine - INFO - Epoch(train) [48][ 440/1320] lr: 2.0000e-04 eta: 0:28:16 time: 0.4814 data_time: 0.0150 memory: 27031 grad_norm: 6.8442 loss: 0.7093 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7093 2023/02/17 20:53:42 - mmengine - INFO - Epoch(train) [48][ 460/1320] lr: 2.0000e-04 eta: 0:28:06 time: 0.4815 data_time: 0.0153 memory: 27031 grad_norm: 6.9928 loss: 0.7566 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.7566 2023/02/17 20:53:52 - mmengine - INFO - Epoch(train) [48][ 480/1320] lr: 2.0000e-04 eta: 0:27:57 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 6.8691 loss: 0.9625 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9625 2023/02/17 20:54:02 - mmengine - INFO - Epoch(train) [48][ 500/1320] lr: 2.0000e-04 eta: 0:27:47 time: 0.4808 data_time: 0.0143 memory: 27031 grad_norm: 6.7043 loss: 0.8061 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8061 2023/02/17 20:54:11 - mmengine - INFO - Epoch(train) [48][ 520/1320] lr: 2.0000e-04 eta: 0:27:38 time: 0.4802 data_time: 0.0137 memory: 27031 grad_norm: 6.7119 loss: 0.7588 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7588 2023/02/17 20:54:21 - mmengine - INFO - Epoch(train) [48][ 540/1320] lr: 2.0000e-04 eta: 0:27:28 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 6.7734 loss: 0.8694 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.8694 2023/02/17 20:54:30 - mmengine - INFO - Epoch(train) [48][ 560/1320] lr: 2.0000e-04 eta: 0:27:18 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.8702 loss: 0.9032 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9032 2023/02/17 20:54:40 - mmengine - INFO - Epoch(train) [48][ 580/1320] lr: 2.0000e-04 eta: 0:27:09 time: 0.4794 data_time: 0.0137 memory: 27031 grad_norm: 6.9644 loss: 0.7628 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.7628 2023/02/17 20:54:50 - mmengine - INFO - Epoch(train) [48][ 600/1320] lr: 2.0000e-04 eta: 0:26:59 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 6.8688 loss: 0.8026 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.8026 2023/02/17 20:54:59 - mmengine - INFO - Epoch(train) [48][ 620/1320] lr: 2.0000e-04 eta: 0:26:49 time: 0.4806 data_time: 0.0146 memory: 27031 grad_norm: 6.8864 loss: 0.7938 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7938 2023/02/17 20:55:09 - mmengine - INFO - Epoch(train) [48][ 640/1320] lr: 2.0000e-04 eta: 0:26:40 time: 0.4818 data_time: 0.0151 memory: 27031 grad_norm: 6.9280 loss: 0.7100 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7100 2023/02/17 20:55:19 - mmengine - INFO - Epoch(train) [48][ 660/1320] lr: 2.0000e-04 eta: 0:26:30 time: 0.4814 data_time: 0.0145 memory: 27031 grad_norm: 6.8861 loss: 0.8069 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8069 2023/02/17 20:55:28 - mmengine - INFO - Epoch(train) [48][ 680/1320] lr: 2.0000e-04 eta: 0:26:20 time: 0.4803 data_time: 0.0146 memory: 27031 grad_norm: 6.7620 loss: 0.7810 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7810 2023/02/17 20:55:38 - mmengine - INFO - Epoch(train) [48][ 700/1320] lr: 2.0000e-04 eta: 0:26:11 time: 0.4812 data_time: 0.0145 memory: 27031 grad_norm: 6.7636 loss: 0.8110 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8110 2023/02/17 20:55:47 - mmengine - INFO - Epoch(train) [48][ 720/1320] lr: 2.0000e-04 eta: 0:26:01 time: 0.4814 data_time: 0.0148 memory: 27031 grad_norm: 6.7398 loss: 0.6539 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6539 2023/02/17 20:55:57 - mmengine - INFO - Epoch(train) [48][ 740/1320] lr: 2.0000e-04 eta: 0:25:51 time: 0.4800 data_time: 0.0138 memory: 27031 grad_norm: 6.9790 loss: 0.8131 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8131 2023/02/17 20:56:07 - mmengine - INFO - Epoch(train) [48][ 760/1320] lr: 2.0000e-04 eta: 0:25:42 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 6.9309 loss: 0.7906 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7906 2023/02/17 20:56:16 - mmengine - INFO - Epoch(train) [48][ 780/1320] lr: 2.0000e-04 eta: 0:25:32 time: 0.4811 data_time: 0.0143 memory: 27031 grad_norm: 6.8870 loss: 0.7796 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7796 2023/02/17 20:56:26 - mmengine - INFO - Epoch(train) [48][ 800/1320] lr: 2.0000e-04 eta: 0:25:23 time: 0.4810 data_time: 0.0146 memory: 27031 grad_norm: 6.7789 loss: 0.7247 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7247 2023/02/17 20:56:35 - mmengine - INFO - Epoch(train) [48][ 820/1320] lr: 2.0000e-04 eta: 0:25:13 time: 0.4812 data_time: 0.0146 memory: 27031 grad_norm: 6.7277 loss: 0.8466 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8466 2023/02/17 20:56:45 - mmengine - INFO - Epoch(train) [48][ 840/1320] lr: 2.0000e-04 eta: 0:25:03 time: 0.4795 data_time: 0.0138 memory: 27031 grad_norm: 6.8911 loss: 0.7646 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7646 2023/02/17 20:56:55 - mmengine - INFO - Epoch(train) [48][ 860/1320] lr: 2.0000e-04 eta: 0:24:54 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 6.7956 loss: 0.7469 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7469 2023/02/17 20:57:04 - mmengine - INFO - Epoch(train) [48][ 880/1320] lr: 2.0000e-04 eta: 0:24:44 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.8134 loss: 0.7215 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7215 2023/02/17 20:57:14 - mmengine - INFO - Epoch(train) [48][ 900/1320] lr: 2.0000e-04 eta: 0:24:34 time: 0.4800 data_time: 0.0140 memory: 27031 grad_norm: 6.9215 loss: 0.8136 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.8136 2023/02/17 20:57:24 - mmengine - INFO - Epoch(train) [48][ 920/1320] lr: 2.0000e-04 eta: 0:24:25 time: 0.4822 data_time: 0.0159 memory: 27031 grad_norm: 6.8195 loss: 0.7855 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7855 2023/02/17 20:57:33 - mmengine - INFO - Epoch(train) [48][ 940/1320] lr: 2.0000e-04 eta: 0:24:15 time: 0.4809 data_time: 0.0142 memory: 27031 grad_norm: 6.6914 loss: 0.8241 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8241 2023/02/17 20:57:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 20:57:43 - mmengine - INFO - Epoch(train) [48][ 960/1320] lr: 2.0000e-04 eta: 0:24:05 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 6.9402 loss: 0.8574 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8574 2023/02/17 20:57:52 - mmengine - INFO - Epoch(train) [48][ 980/1320] lr: 2.0000e-04 eta: 0:23:56 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.9869 loss: 0.7883 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7883 2023/02/17 20:58:02 - mmengine - INFO - Epoch(train) [48][1000/1320] lr: 2.0000e-04 eta: 0:23:46 time: 0.4830 data_time: 0.0169 memory: 27031 grad_norm: 6.7503 loss: 0.7238 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7238 2023/02/17 20:58:12 - mmengine - INFO - Epoch(train) [48][1020/1320] lr: 2.0000e-04 eta: 0:23:37 time: 0.4811 data_time: 0.0145 memory: 27031 grad_norm: 6.6821 loss: 0.8009 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8009 2023/02/17 20:58:21 - mmengine - INFO - Epoch(train) [48][1040/1320] lr: 2.0000e-04 eta: 0:23:27 time: 0.4810 data_time: 0.0151 memory: 27031 grad_norm: 6.8272 loss: 0.8368 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8368 2023/02/17 20:58:31 - mmengine - INFO - Epoch(train) [48][1060/1320] lr: 2.0000e-04 eta: 0:23:17 time: 0.4804 data_time: 0.0144 memory: 27031 grad_norm: 6.7647 loss: 0.7549 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7549 2023/02/17 20:58:41 - mmengine - INFO - Epoch(train) [48][1080/1320] lr: 2.0000e-04 eta: 0:23:08 time: 0.4815 data_time: 0.0149 memory: 27031 grad_norm: 6.8822 loss: 0.7536 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7536 2023/02/17 20:58:50 - mmengine - INFO - Epoch(train) [48][1100/1320] lr: 2.0000e-04 eta: 0:22:58 time: 0.4813 data_time: 0.0145 memory: 27031 grad_norm: 6.7734 loss: 0.7402 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7402 2023/02/17 20:59:00 - mmengine - INFO - Epoch(train) [48][1120/1320] lr: 2.0000e-04 eta: 0:22:48 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 6.9800 loss: 0.8345 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8345 2023/02/17 20:59:09 - mmengine - INFO - Epoch(train) [48][1140/1320] lr: 2.0000e-04 eta: 0:22:39 time: 0.4814 data_time: 0.0148 memory: 27031 grad_norm: 6.9227 loss: 0.6548 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6548 2023/02/17 20:59:19 - mmengine - INFO - Epoch(train) [48][1160/1320] lr: 2.0000e-04 eta: 0:22:29 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 6.7568 loss: 0.6390 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6390 2023/02/17 20:59:29 - mmengine - INFO - Epoch(train) [48][1180/1320] lr: 2.0000e-04 eta: 0:22:19 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 6.8965 loss: 0.8328 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.8328 2023/02/17 20:59:38 - mmengine - INFO - Epoch(train) [48][1200/1320] lr: 2.0000e-04 eta: 0:22:10 time: 0.4821 data_time: 0.0156 memory: 27031 grad_norm: 7.0473 loss: 0.8069 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8069 2023/02/17 20:59:48 - mmengine - INFO - Epoch(train) [48][1220/1320] lr: 2.0000e-04 eta: 0:22:00 time: 0.4805 data_time: 0.0141 memory: 27031 grad_norm: 6.8572 loss: 1.0492 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0492 2023/02/17 20:59:58 - mmengine - INFO - Epoch(train) [48][1240/1320] lr: 2.0000e-04 eta: 0:21:50 time: 0.4810 data_time: 0.0151 memory: 27031 grad_norm: 7.0706 loss: 0.8052 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8052 2023/02/17 21:00:07 - mmengine - INFO - Epoch(train) [48][1260/1320] lr: 2.0000e-04 eta: 0:21:41 time: 0.4810 data_time: 0.0140 memory: 27031 grad_norm: 6.9815 loss: 0.7656 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7656 2023/02/17 21:00:17 - mmengine - INFO - Epoch(train) [48][1280/1320] lr: 2.0000e-04 eta: 0:21:31 time: 0.4804 data_time: 0.0140 memory: 27031 grad_norm: 7.0241 loss: 0.9164 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.9164 2023/02/17 21:00:26 - mmengine - INFO - Epoch(train) [48][1300/1320] lr: 2.0000e-04 eta: 0:21:22 time: 0.4808 data_time: 0.0144 memory: 27031 grad_norm: 6.8085 loss: 0.6838 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6838 2023/02/17 21:00:36 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 21:00:36 - mmengine - INFO - Epoch(train) [48][1320/1320] lr: 2.0000e-04 eta: 0:21:12 time: 0.4739 data_time: 0.0144 memory: 27031 grad_norm: 6.8854 loss: 0.7428 top1_acc: 0.8182 top5_acc: 1.0000 loss_cls: 0.7428 2023/02/17 21:00:36 - mmengine - INFO - Saving checkpoint at 48 epochs 2023/02/17 21:00:41 - mmengine - INFO - Epoch(val) [48][ 20/194] eta: 0:00:32 time: 0.1880 data_time: 0.0595 memory: 3265 2023/02/17 21:00:44 - mmengine - INFO - Epoch(val) [48][ 40/194] eta: 0:00:25 time: 0.1369 data_time: 0.0123 memory: 3265 2023/02/17 21:00:46 - mmengine - INFO - Epoch(val) [48][ 60/194] eta: 0:00:20 time: 0.1385 data_time: 0.0136 memory: 3265 2023/02/17 21:00:49 - mmengine - INFO - Epoch(val) [48][ 80/194] eta: 0:00:17 time: 0.1385 data_time: 0.0140 memory: 3265 2023/02/17 21:00:52 - mmengine - INFO - Epoch(val) [48][100/194] eta: 0:00:13 time: 0.1398 data_time: 0.0144 memory: 3265 2023/02/17 21:00:55 - mmengine - INFO - Epoch(val) [48][120/194] eta: 0:00:10 time: 0.1391 data_time: 0.0138 memory: 3265 2023/02/17 21:00:58 - mmengine - INFO - Epoch(val) [48][140/194] eta: 0:00:07 time: 0.1383 data_time: 0.0136 memory: 3265 2023/02/17 21:01:00 - mmengine - INFO - Epoch(val) [48][160/194] eta: 0:00:04 time: 0.1381 data_time: 0.0127 memory: 3265 2023/02/17 21:01:03 - mmengine - INFO - Epoch(val) [48][180/194] eta: 0:00:02 time: 0.1356 data_time: 0.0127 memory: 3265 2023/02/17 21:01:06 - mmengine - INFO - Epoch(val) [48][194/194] acc/top1: 0.6220 acc/top5: 0.8747 acc/mean1: 0.5607 2023/02/17 21:01:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_47.pth is removed 2023/02/17 21:01:07 - mmengine - INFO - The best checkpoint with 0.6220 acc/top1 at 48 epoch is saved to best_acc/top1_epoch_48.pth. 2023/02/17 21:01:17 - mmengine - INFO - Epoch(train) [49][ 20/1320] lr: 2.0000e-04 eta: 0:21:02 time: 0.5272 data_time: 0.0563 memory: 27031 grad_norm: 6.8930 loss: 0.8018 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8018 2023/02/17 21:01:27 - mmengine - INFO - Epoch(train) [49][ 40/1320] lr: 2.0000e-04 eta: 0:20:53 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 6.7930 loss: 0.6576 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6576 2023/02/17 21:01:36 - mmengine - INFO - Epoch(train) [49][ 60/1320] lr: 2.0000e-04 eta: 0:20:43 time: 0.4794 data_time: 0.0136 memory: 27031 grad_norm: 6.8588 loss: 0.9634 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9634 2023/02/17 21:01:46 - mmengine - INFO - Epoch(train) [49][ 80/1320] lr: 2.0000e-04 eta: 0:20:33 time: 0.4810 data_time: 0.0145 memory: 27031 grad_norm: 6.8874 loss: 0.9010 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.9010 2023/02/17 21:01:56 - mmengine - INFO - Epoch(train) [49][ 100/1320] lr: 2.0000e-04 eta: 0:20:24 time: 0.4807 data_time: 0.0141 memory: 27031 grad_norm: 6.9091 loss: 0.8709 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8709 2023/02/17 21:02:05 - mmengine - INFO - Epoch(train) [49][ 120/1320] lr: 2.0000e-04 eta: 0:20:14 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 7.0741 loss: 0.8682 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8682 2023/02/17 21:02:15 - mmengine - INFO - Epoch(train) [49][ 140/1320] lr: 2.0000e-04 eta: 0:20:04 time: 0.4806 data_time: 0.0143 memory: 27031 grad_norm: 6.8700 loss: 0.8377 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8377 2023/02/17 21:02:24 - mmengine - INFO - Epoch(train) [49][ 160/1320] lr: 2.0000e-04 eta: 0:19:55 time: 0.4809 data_time: 0.0143 memory: 27031 grad_norm: 6.7269 loss: 0.7661 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7661 2023/02/17 21:02:34 - mmengine - INFO - Epoch(train) [49][ 180/1320] lr: 2.0000e-04 eta: 0:19:45 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 7.0210 loss: 0.7915 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7915 2023/02/17 21:02:44 - mmengine - INFO - Epoch(train) [49][ 200/1320] lr: 2.0000e-04 eta: 0:19:36 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.8438 loss: 0.7944 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7944 2023/02/17 21:02:53 - mmengine - INFO - Epoch(train) [49][ 220/1320] lr: 2.0000e-04 eta: 0:19:26 time: 0.4806 data_time: 0.0141 memory: 27031 grad_norm: 6.8637 loss: 0.6718 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6718 2023/02/17 21:03:03 - mmengine - INFO - Epoch(train) [49][ 240/1320] lr: 2.0000e-04 eta: 0:19:16 time: 0.4811 data_time: 0.0146 memory: 27031 grad_norm: 6.7869 loss: 0.7369 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7369 2023/02/17 21:03:13 - mmengine - INFO - Epoch(train) [49][ 260/1320] lr: 2.0000e-04 eta: 0:19:07 time: 0.4802 data_time: 0.0140 memory: 27031 grad_norm: 6.8728 loss: 0.7230 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7230 2023/02/17 21:03:22 - mmengine - INFO - Epoch(train) [49][ 280/1320] lr: 2.0000e-04 eta: 0:18:57 time: 0.4806 data_time: 0.0145 memory: 27031 grad_norm: 6.9288 loss: 0.8716 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8716 2023/02/17 21:03:32 - mmengine - INFO - Epoch(train) [49][ 300/1320] lr: 2.0000e-04 eta: 0:18:47 time: 0.4805 data_time: 0.0150 memory: 27031 grad_norm: 6.6984 loss: 0.7776 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7776 2023/02/17 21:03:41 - mmengine - INFO - Epoch(train) [49][ 320/1320] lr: 2.0000e-04 eta: 0:18:38 time: 0.4808 data_time: 0.0137 memory: 27031 grad_norm: 6.8066 loss: 0.7526 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7526 2023/02/17 21:03:51 - mmengine - INFO - Epoch(train) [49][ 340/1320] lr: 2.0000e-04 eta: 0:18:28 time: 0.4811 data_time: 0.0147 memory: 27031 grad_norm: 6.6170 loss: 0.7874 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7874 2023/02/17 21:04:01 - mmengine - INFO - Epoch(train) [49][ 360/1320] lr: 2.0000e-04 eta: 0:18:18 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 7.0502 loss: 0.8594 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8594 2023/02/17 21:04:10 - mmengine - INFO - Epoch(train) [49][ 380/1320] lr: 2.0000e-04 eta: 0:18:09 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 7.1031 loss: 0.7474 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7474 2023/02/17 21:04:20 - mmengine - INFO - Epoch(train) [49][ 400/1320] lr: 2.0000e-04 eta: 0:17:59 time: 0.4816 data_time: 0.0145 memory: 27031 grad_norm: 6.6456 loss: 0.6973 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6973 2023/02/17 21:04:30 - mmengine - INFO - Epoch(train) [49][ 420/1320] lr: 2.0000e-04 eta: 0:17:50 time: 0.4805 data_time: 0.0142 memory: 27031 grad_norm: 6.8601 loss: 0.7356 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7356 2023/02/17 21:04:39 - mmengine - INFO - Epoch(train) [49][ 440/1320] lr: 2.0000e-04 eta: 0:17:40 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 6.7574 loss: 0.7564 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7564 2023/02/17 21:04:49 - mmengine - INFO - Epoch(train) [49][ 460/1320] lr: 2.0000e-04 eta: 0:17:30 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 6.7386 loss: 0.6546 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6546 2023/02/17 21:04:58 - mmengine - INFO - Epoch(train) [49][ 480/1320] lr: 2.0000e-04 eta: 0:17:21 time: 0.4816 data_time: 0.0154 memory: 27031 grad_norm: 6.6371 loss: 0.6728 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6728 2023/02/17 21:05:08 - mmengine - INFO - Epoch(train) [49][ 500/1320] lr: 2.0000e-04 eta: 0:17:11 time: 0.4814 data_time: 0.0149 memory: 27031 grad_norm: 6.9058 loss: 0.8959 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.8959 2023/02/17 21:05:18 - mmengine - INFO - Epoch(train) [49][ 520/1320] lr: 2.0000e-04 eta: 0:17:01 time: 0.4814 data_time: 0.0144 memory: 27031 grad_norm: 6.8700 loss: 0.7530 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7530 2023/02/17 21:05:27 - mmengine - INFO - Epoch(train) [49][ 540/1320] lr: 2.0000e-04 eta: 0:16:52 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.7614 loss: 0.6938 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6938 2023/02/17 21:05:37 - mmengine - INFO - Epoch(train) [49][ 560/1320] lr: 2.0000e-04 eta: 0:16:42 time: 0.4812 data_time: 0.0149 memory: 27031 grad_norm: 6.8915 loss: 0.6849 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6849 2023/02/17 21:05:47 - mmengine - INFO - Epoch(train) [49][ 580/1320] lr: 2.0000e-04 eta: 0:16:32 time: 0.4812 data_time: 0.0148 memory: 27031 grad_norm: 6.9869 loss: 0.7537 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7537 2023/02/17 21:05:56 - mmengine - INFO - Epoch(train) [49][ 600/1320] lr: 2.0000e-04 eta: 0:16:23 time: 0.4804 data_time: 0.0145 memory: 27031 grad_norm: 6.8669 loss: 0.8303 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.8303 2023/02/17 21:06:06 - mmengine - INFO - Epoch(train) [49][ 620/1320] lr: 2.0000e-04 eta: 0:16:13 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 6.8626 loss: 0.7054 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7054 2023/02/17 21:06:15 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 21:06:15 - mmengine - INFO - Epoch(train) [49][ 640/1320] lr: 2.0000e-04 eta: 0:16:03 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 6.9158 loss: 0.9198 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.9198 2023/02/17 21:06:25 - mmengine - INFO - Epoch(train) [49][ 660/1320] lr: 2.0000e-04 eta: 0:15:54 time: 0.4816 data_time: 0.0149 memory: 27031 grad_norm: 6.9742 loss: 0.8100 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8100 2023/02/17 21:06:35 - mmengine - INFO - Epoch(train) [49][ 680/1320] lr: 2.0000e-04 eta: 0:15:44 time: 0.4816 data_time: 0.0150 memory: 27031 grad_norm: 6.8350 loss: 0.7599 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7599 2023/02/17 21:06:44 - mmengine - INFO - Epoch(train) [49][ 700/1320] lr: 2.0000e-04 eta: 0:15:35 time: 0.4807 data_time: 0.0142 memory: 27031 grad_norm: 6.8866 loss: 0.5851 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5851 2023/02/17 21:06:54 - mmengine - INFO - Epoch(train) [49][ 720/1320] lr: 2.0000e-04 eta: 0:15:25 time: 0.4819 data_time: 0.0145 memory: 27031 grad_norm: 7.0136 loss: 0.8885 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8885 2023/02/17 21:07:04 - mmengine - INFO - Epoch(train) [49][ 740/1320] lr: 2.0000e-04 eta: 0:15:15 time: 0.4806 data_time: 0.0142 memory: 27031 grad_norm: 7.1040 loss: 0.8898 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8898 2023/02/17 21:07:13 - mmengine - INFO - Epoch(train) [49][ 760/1320] lr: 2.0000e-04 eta: 0:15:06 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.7504 loss: 0.7892 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7892 2023/02/17 21:07:23 - mmengine - INFO - Epoch(train) [49][ 780/1320] lr: 2.0000e-04 eta: 0:14:56 time: 0.4818 data_time: 0.0147 memory: 27031 grad_norm: 6.7677 loss: 0.7271 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7271 2023/02/17 21:07:32 - mmengine - INFO - Epoch(train) [49][ 800/1320] lr: 2.0000e-04 eta: 0:14:46 time: 0.4799 data_time: 0.0139 memory: 27031 grad_norm: 6.9275 loss: 0.6997 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.6997 2023/02/17 21:07:42 - mmengine - INFO - Epoch(train) [49][ 820/1320] lr: 2.0000e-04 eta: 0:14:37 time: 0.4830 data_time: 0.0164 memory: 27031 grad_norm: 6.8670 loss: 0.8639 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8639 2023/02/17 21:07:52 - mmengine - INFO - Epoch(train) [49][ 840/1320] lr: 2.0000e-04 eta: 0:14:27 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 6.8086 loss: 0.7478 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7478 2023/02/17 21:08:01 - mmengine - INFO - Epoch(train) [49][ 860/1320] lr: 2.0000e-04 eta: 0:14:17 time: 0.4804 data_time: 0.0138 memory: 27031 grad_norm: 6.9095 loss: 0.7822 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.7822 2023/02/17 21:08:11 - mmengine - INFO - Epoch(train) [49][ 880/1320] lr: 2.0000e-04 eta: 0:14:08 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 7.0975 loss: 0.8215 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8215 2023/02/17 21:08:21 - mmengine - INFO - Epoch(train) [49][ 900/1320] lr: 2.0000e-04 eta: 0:13:58 time: 0.4821 data_time: 0.0142 memory: 27031 grad_norm: 7.0858 loss: 0.7845 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7845 2023/02/17 21:08:30 - mmengine - INFO - Epoch(train) [49][ 920/1320] lr: 2.0000e-04 eta: 0:13:48 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 6.9014 loss: 0.7354 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7354 2023/02/17 21:08:40 - mmengine - INFO - Epoch(train) [49][ 940/1320] lr: 2.0000e-04 eta: 0:13:39 time: 0.4822 data_time: 0.0146 memory: 27031 grad_norm: 7.0409 loss: 0.8336 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8336 2023/02/17 21:08:49 - mmengine - INFO - Epoch(train) [49][ 960/1320] lr: 2.0000e-04 eta: 0:13:29 time: 0.4803 data_time: 0.0145 memory: 27031 grad_norm: 6.9623 loss: 0.8471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8471 2023/02/17 21:08:59 - mmengine - INFO - Epoch(train) [49][ 980/1320] lr: 2.0000e-04 eta: 0:13:20 time: 0.4805 data_time: 0.0151 memory: 27031 grad_norm: 7.0361 loss: 0.8884 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8884 2023/02/17 21:09:09 - mmengine - INFO - Epoch(train) [49][1000/1320] lr: 2.0000e-04 eta: 0:13:10 time: 0.4813 data_time: 0.0146 memory: 27031 grad_norm: 6.9246 loss: 0.7153 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7153 2023/02/17 21:09:18 - mmengine - INFO - Epoch(train) [49][1020/1320] lr: 2.0000e-04 eta: 0:13:00 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.9101 loss: 0.7021 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7021 2023/02/17 21:09:28 - mmengine - INFO - Epoch(train) [49][1040/1320] lr: 2.0000e-04 eta: 0:12:51 time: 0.4818 data_time: 0.0146 memory: 27031 grad_norm: 6.8518 loss: 0.8031 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8031 2023/02/17 21:09:38 - mmengine - INFO - Epoch(train) [49][1060/1320] lr: 2.0000e-04 eta: 0:12:41 time: 0.4800 data_time: 0.0140 memory: 27031 grad_norm: 6.9984 loss: 0.7107 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7107 2023/02/17 21:09:47 - mmengine - INFO - Epoch(train) [49][1080/1320] lr: 2.0000e-04 eta: 0:12:31 time: 0.4812 data_time: 0.0154 memory: 27031 grad_norm: 7.1061 loss: 0.8293 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8293 2023/02/17 21:09:57 - mmengine - INFO - Epoch(train) [49][1100/1320] lr: 2.0000e-04 eta: 0:12:22 time: 0.4802 data_time: 0.0150 memory: 27031 grad_norm: 7.0364 loss: 0.8574 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8574 2023/02/17 21:10:06 - mmengine - INFO - Epoch(train) [49][1120/1320] lr: 2.0000e-04 eta: 0:12:12 time: 0.4810 data_time: 0.0147 memory: 27031 grad_norm: 6.9747 loss: 0.7374 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7374 2023/02/17 21:10:16 - mmengine - INFO - Epoch(train) [49][1140/1320] lr: 2.0000e-04 eta: 0:12:02 time: 0.4807 data_time: 0.0147 memory: 27031 grad_norm: 6.8833 loss: 0.7976 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7976 2023/02/17 21:10:26 - mmengine - INFO - Epoch(train) [49][1160/1320] lr: 2.0000e-04 eta: 0:11:53 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 6.9753 loss: 0.6686 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6686 2023/02/17 21:10:35 - mmengine - INFO - Epoch(train) [49][1180/1320] lr: 2.0000e-04 eta: 0:11:43 time: 0.4807 data_time: 0.0139 memory: 27031 grad_norm: 6.7445 loss: 0.8015 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.8015 2023/02/17 21:10:45 - mmengine - INFO - Epoch(train) [49][1200/1320] lr: 2.0000e-04 eta: 0:11:34 time: 0.4817 data_time: 0.0154 memory: 27031 grad_norm: 6.8259 loss: 0.7948 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7948 2023/02/17 21:10:55 - mmengine - INFO - Epoch(train) [49][1220/1320] lr: 2.0000e-04 eta: 0:11:24 time: 0.4812 data_time: 0.0148 memory: 27031 grad_norm: 7.0857 loss: 0.7437 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7437 2023/02/17 21:11:04 - mmengine - INFO - Epoch(train) [49][1240/1320] lr: 2.0000e-04 eta: 0:11:14 time: 0.4808 data_time: 0.0142 memory: 27031 grad_norm: 6.8378 loss: 0.7946 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7946 2023/02/17 21:11:14 - mmengine - INFO - Epoch(train) [49][1260/1320] lr: 2.0000e-04 eta: 0:11:05 time: 0.4809 data_time: 0.0149 memory: 27031 grad_norm: 6.8993 loss: 0.7585 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7585 2023/02/17 21:11:23 - mmengine - INFO - Epoch(train) [49][1280/1320] lr: 2.0000e-04 eta: 0:10:55 time: 0.4804 data_time: 0.0137 memory: 27031 grad_norm: 6.7479 loss: 0.5506 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5506 2023/02/17 21:11:33 - mmengine - INFO - Epoch(train) [49][1300/1320] lr: 2.0000e-04 eta: 0:10:45 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 7.2372 loss: 0.8559 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.8559 2023/02/17 21:11:43 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 21:11:43 - mmengine - INFO - Epoch(train) [49][1320/1320] lr: 2.0000e-04 eta: 0:10:36 time: 0.4750 data_time: 0.0161 memory: 27031 grad_norm: 7.0246 loss: 0.8035 top1_acc: 0.6364 top5_acc: 0.9091 loss_cls: 0.8035 2023/02/17 21:11:46 - mmengine - INFO - Epoch(val) [49][ 20/194] eta: 0:00:32 time: 0.1840 data_time: 0.0575 memory: 3265 2023/02/17 21:11:49 - mmengine - INFO - Epoch(val) [49][ 40/194] eta: 0:00:24 time: 0.1374 data_time: 0.0126 memory: 3265 2023/02/17 21:11:52 - mmengine - INFO - Epoch(val) [49][ 60/194] eta: 0:00:20 time: 0.1380 data_time: 0.0136 memory: 3265 2023/02/17 21:11:55 - mmengine - INFO - Epoch(val) [49][ 80/194] eta: 0:00:17 time: 0.1377 data_time: 0.0133 memory: 3265 2023/02/17 21:11:57 - mmengine - INFO - Epoch(val) [49][100/194] eta: 0:00:13 time: 0.1372 data_time: 0.0131 memory: 3265 2023/02/17 21:12:00 - mmengine - INFO - Epoch(val) [49][120/194] eta: 0:00:10 time: 0.1381 data_time: 0.0138 memory: 3265 2023/02/17 21:12:03 - mmengine - INFO - Epoch(val) [49][140/194] eta: 0:00:07 time: 0.1380 data_time: 0.0139 memory: 3265 2023/02/17 21:12:06 - mmengine - INFO - Epoch(val) [49][160/194] eta: 0:00:04 time: 0.1395 data_time: 0.0144 memory: 3265 2023/02/17 21:12:08 - mmengine - INFO - Epoch(val) [49][180/194] eta: 0:00:02 time: 0.1386 data_time: 0.0142 memory: 3265 2023/02/17 21:12:11 - mmengine - INFO - Epoch(val) [49][194/194] acc/top1: 0.6214 acc/top5: 0.8755 acc/mean1: 0.5617 2023/02/17 21:12:22 - mmengine - INFO - Epoch(train) [50][ 20/1320] lr: 2.0000e-04 eta: 0:10:26 time: 0.5324 data_time: 0.0596 memory: 27031 grad_norm: 6.7965 loss: 0.7173 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7173 2023/02/17 21:12:32 - mmengine - INFO - Epoch(train) [50][ 40/1320] lr: 2.0000e-04 eta: 0:10:16 time: 0.4812 data_time: 0.0150 memory: 27031 grad_norm: 7.0083 loss: 0.7023 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7023 2023/02/17 21:12:41 - mmengine - INFO - Epoch(train) [50][ 60/1320] lr: 2.0000e-04 eta: 0:10:07 time: 0.4795 data_time: 0.0142 memory: 27031 grad_norm: 6.8260 loss: 0.7193 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7193 2023/02/17 21:12:51 - mmengine - INFO - Epoch(train) [50][ 80/1320] lr: 2.0000e-04 eta: 0:09:57 time: 0.4801 data_time: 0.0144 memory: 27031 grad_norm: 7.0817 loss: 0.8650 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.8650 2023/02/17 21:13:00 - mmengine - INFO - Epoch(train) [50][ 100/1320] lr: 2.0000e-04 eta: 0:09:48 time: 0.4808 data_time: 0.0147 memory: 27031 grad_norm: 6.7237 loss: 0.7309 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.7309 2023/02/17 21:13:10 - mmengine - INFO - Epoch(train) [50][ 120/1320] lr: 2.0000e-04 eta: 0:09:38 time: 0.4800 data_time: 0.0142 memory: 27031 grad_norm: 6.8463 loss: 0.8418 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8418 2023/02/17 21:13:20 - mmengine - INFO - Epoch(train) [50][ 140/1320] lr: 2.0000e-04 eta: 0:09:28 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 6.9924 loss: 0.7952 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.7952 2023/02/17 21:13:29 - mmengine - INFO - Epoch(train) [50][ 160/1320] lr: 2.0000e-04 eta: 0:09:19 time: 0.4801 data_time: 0.0140 memory: 27031 grad_norm: 6.6859 loss: 0.7009 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7009 2023/02/17 21:13:39 - mmengine - INFO - Epoch(train) [50][ 180/1320] lr: 2.0000e-04 eta: 0:09:09 time: 0.4804 data_time: 0.0143 memory: 27031 grad_norm: 6.9475 loss: 0.8120 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.8120 2023/02/17 21:13:49 - mmengine - INFO - Epoch(train) [50][ 200/1320] lr: 2.0000e-04 eta: 0:08:59 time: 0.4812 data_time: 0.0153 memory: 27031 grad_norm: 6.8027 loss: 0.8025 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8025 2023/02/17 21:13:58 - mmengine - INFO - Epoch(train) [50][ 220/1320] lr: 2.0000e-04 eta: 0:08:50 time: 0.4803 data_time: 0.0148 memory: 27031 grad_norm: 6.8582 loss: 0.6671 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6671 2023/02/17 21:14:08 - mmengine - INFO - Epoch(train) [50][ 240/1320] lr: 2.0000e-04 eta: 0:08:40 time: 0.4812 data_time: 0.0147 memory: 27031 grad_norm: 6.9925 loss: 0.6962 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6962 2023/02/17 21:14:17 - mmengine - INFO - Epoch(train) [50][ 260/1320] lr: 2.0000e-04 eta: 0:08:30 time: 0.4804 data_time: 0.0147 memory: 27031 grad_norm: 6.8992 loss: 0.6500 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6500 2023/02/17 21:14:27 - mmengine - INFO - Epoch(train) [50][ 280/1320] lr: 2.0000e-04 eta: 0:08:21 time: 0.4793 data_time: 0.0137 memory: 27031 grad_norm: 6.9983 loss: 0.7561 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7561 2023/02/17 21:14:37 - mmengine - INFO - Epoch(train) [50][ 300/1320] lr: 2.0000e-04 eta: 0:08:11 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 6.9529 loss: 0.8968 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8968 2023/02/17 21:14:46 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 21:14:46 - mmengine - INFO - Epoch(train) [50][ 320/1320] lr: 2.0000e-04 eta: 0:08:01 time: 0.4801 data_time: 0.0145 memory: 27031 grad_norm: 6.8658 loss: 0.7997 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7997 2023/02/17 21:14:56 - mmengine - INFO - Epoch(train) [50][ 340/1320] lr: 2.0000e-04 eta: 0:07:52 time: 0.4792 data_time: 0.0136 memory: 27031 grad_norm: 7.0531 loss: 0.9020 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9020 2023/02/17 21:15:05 - mmengine - INFO - Epoch(train) [50][ 360/1320] lr: 2.0000e-04 eta: 0:07:42 time: 0.4807 data_time: 0.0149 memory: 27031 grad_norm: 7.1270 loss: 0.8236 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8236 2023/02/17 21:15:15 - mmengine - INFO - Epoch(train) [50][ 380/1320] lr: 2.0000e-04 eta: 0:07:33 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.7094 loss: 0.7022 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7022 2023/02/17 21:15:25 - mmengine - INFO - Epoch(train) [50][ 400/1320] lr: 2.0000e-04 eta: 0:07:23 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 7.0327 loss: 0.7854 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7854 2023/02/17 21:15:34 - mmengine - INFO - Epoch(train) [50][ 420/1320] lr: 2.0000e-04 eta: 0:07:13 time: 0.4810 data_time: 0.0150 memory: 27031 grad_norm: 6.9802 loss: 0.8689 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.8689 2023/02/17 21:15:44 - mmengine - INFO - Epoch(train) [50][ 440/1320] lr: 2.0000e-04 eta: 0:07:04 time: 0.4798 data_time: 0.0141 memory: 27031 grad_norm: 6.8074 loss: 0.8921 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8921 2023/02/17 21:15:54 - mmengine - INFO - Epoch(train) [50][ 460/1320] lr: 2.0000e-04 eta: 0:06:54 time: 0.4809 data_time: 0.0150 memory: 27031 grad_norm: 6.8522 loss: 0.7867 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7867 2023/02/17 21:16:03 - mmengine - INFO - Epoch(train) [50][ 480/1320] lr: 2.0000e-04 eta: 0:06:44 time: 0.4805 data_time: 0.0146 memory: 27031 grad_norm: 6.9038 loss: 0.7647 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7647 2023/02/17 21:16:13 - mmengine - INFO - Epoch(train) [50][ 500/1320] lr: 2.0000e-04 eta: 0:06:35 time: 0.4798 data_time: 0.0135 memory: 27031 grad_norm: 6.7870 loss: 0.7873 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7873 2023/02/17 21:16:22 - mmengine - INFO - Epoch(train) [50][ 520/1320] lr: 2.0000e-04 eta: 0:06:25 time: 0.4817 data_time: 0.0150 memory: 27031 grad_norm: 6.8462 loss: 0.7476 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7476 2023/02/17 21:16:32 - mmengine - INFO - Epoch(train) [50][ 540/1320] lr: 2.0000e-04 eta: 0:06:15 time: 0.4807 data_time: 0.0146 memory: 27031 grad_norm: 6.9411 loss: 0.6623 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6623 2023/02/17 21:16:42 - mmengine - INFO - Epoch(train) [50][ 560/1320] lr: 2.0000e-04 eta: 0:06:06 time: 0.4806 data_time: 0.0148 memory: 27031 grad_norm: 6.8564 loss: 0.7340 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7340 2023/02/17 21:16:51 - mmengine - INFO - Epoch(train) [50][ 580/1320] lr: 2.0000e-04 eta: 0:05:56 time: 0.4809 data_time: 0.0148 memory: 27031 grad_norm: 7.0462 loss: 0.7520 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7520 2023/02/17 21:17:01 - mmengine - INFO - Epoch(train) [50][ 600/1320] lr: 2.0000e-04 eta: 0:05:47 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.7547 loss: 0.6353 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6353 2023/02/17 21:17:10 - mmengine - INFO - Epoch(train) [50][ 620/1320] lr: 2.0000e-04 eta: 0:05:37 time: 0.4813 data_time: 0.0152 memory: 27031 grad_norm: 6.8438 loss: 0.7160 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7160 2023/02/17 21:17:20 - mmengine - INFO - Epoch(train) [50][ 640/1320] lr: 2.0000e-04 eta: 0:05:27 time: 0.4809 data_time: 0.0145 memory: 27031 grad_norm: 7.0756 loss: 0.6979 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6979 2023/02/17 21:17:30 - mmengine - INFO - Epoch(train) [50][ 660/1320] lr: 2.0000e-04 eta: 0:05:18 time: 0.4812 data_time: 0.0153 memory: 27031 grad_norm: 6.9099 loss: 0.7363 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7363 2023/02/17 21:17:39 - mmengine - INFO - Epoch(train) [50][ 680/1320] lr: 2.0000e-04 eta: 0:05:08 time: 0.4815 data_time: 0.0148 memory: 27031 grad_norm: 7.0011 loss: 0.8183 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8183 2023/02/17 21:17:49 - mmengine - INFO - Epoch(train) [50][ 700/1320] lr: 2.0000e-04 eta: 0:04:58 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.9787 loss: 0.7186 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7186 2023/02/17 21:17:59 - mmengine - INFO - Epoch(train) [50][ 720/1320] lr: 2.0000e-04 eta: 0:04:49 time: 0.4809 data_time: 0.0147 memory: 27031 grad_norm: 6.9330 loss: 0.7074 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7074 2023/02/17 21:18:08 - mmengine - INFO - Epoch(train) [50][ 740/1320] lr: 2.0000e-04 eta: 0:04:39 time: 0.4808 data_time: 0.0146 memory: 27031 grad_norm: 6.8978 loss: 0.8406 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8406 2023/02/17 21:18:18 - mmengine - INFO - Epoch(train) [50][ 760/1320] lr: 2.0000e-04 eta: 0:04:29 time: 0.4801 data_time: 0.0142 memory: 27031 grad_norm: 7.0221 loss: 0.7126 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7126 2023/02/17 21:18:27 - mmengine - INFO - Epoch(train) [50][ 780/1320] lr: 2.0000e-04 eta: 0:04:20 time: 0.4816 data_time: 0.0151 memory: 27031 grad_norm: 6.8003 loss: 0.7382 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7382 2023/02/17 21:18:37 - mmengine - INFO - Epoch(train) [50][ 800/1320] lr: 2.0000e-04 eta: 0:04:10 time: 0.4811 data_time: 0.0140 memory: 27031 grad_norm: 7.0751 loss: 0.8184 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8184 2023/02/17 21:18:47 - mmengine - INFO - Epoch(train) [50][ 820/1320] lr: 2.0000e-04 eta: 0:04:00 time: 0.4807 data_time: 0.0139 memory: 27031 grad_norm: 6.7253 loss: 0.7112 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7112 2023/02/17 21:18:56 - mmengine - INFO - Epoch(train) [50][ 840/1320] lr: 2.0000e-04 eta: 0:03:51 time: 0.4813 data_time: 0.0148 memory: 27031 grad_norm: 6.7501 loss: 0.7901 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.7901 2023/02/17 21:19:06 - mmengine - INFO - Epoch(train) [50][ 860/1320] lr: 2.0000e-04 eta: 0:03:41 time: 0.4812 data_time: 0.0144 memory: 27031 grad_norm: 6.8710 loss: 0.7130 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7130 2023/02/17 21:19:16 - mmengine - INFO - Epoch(train) [50][ 880/1320] lr: 2.0000e-04 eta: 0:03:32 time: 0.4802 data_time: 0.0144 memory: 27031 grad_norm: 6.9101 loss: 0.6679 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6679 2023/02/17 21:19:25 - mmengine - INFO - Epoch(train) [50][ 900/1320] lr: 2.0000e-04 eta: 0:03:22 time: 0.4823 data_time: 0.0162 memory: 27031 grad_norm: 6.8100 loss: 0.8127 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.8127 2023/02/17 21:19:35 - mmengine - INFO - Epoch(train) [50][ 920/1320] lr: 2.0000e-04 eta: 0:03:12 time: 0.4801 data_time: 0.0141 memory: 27031 grad_norm: 7.1931 loss: 0.8271 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8271 2023/02/17 21:19:44 - mmengine - INFO - Epoch(train) [50][ 940/1320] lr: 2.0000e-04 eta: 0:03:03 time: 0.4813 data_time: 0.0149 memory: 27031 grad_norm: 6.8550 loss: 0.8074 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.8074 2023/02/17 21:19:54 - mmengine - INFO - Epoch(train) [50][ 960/1320] lr: 2.0000e-04 eta: 0:02:53 time: 0.4811 data_time: 0.0145 memory: 27031 grad_norm: 6.8585 loss: 0.8168 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.8168 2023/02/17 21:20:04 - mmengine - INFO - Epoch(train) [50][ 980/1320] lr: 2.0000e-04 eta: 0:02:43 time: 0.4805 data_time: 0.0139 memory: 27031 grad_norm: 6.9691 loss: 0.7621 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7621 2023/02/17 21:20:13 - mmengine - INFO - Epoch(train) [50][1000/1320] lr: 2.0000e-04 eta: 0:02:34 time: 0.4814 data_time: 0.0144 memory: 27031 grad_norm: 7.0016 loss: 0.8356 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8356 2023/02/17 21:20:23 - mmengine - INFO - Epoch(train) [50][1020/1320] lr: 2.0000e-04 eta: 0:02:24 time: 0.4807 data_time: 0.0145 memory: 27031 grad_norm: 6.8935 loss: 0.7337 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7337 2023/02/17 21:20:33 - mmengine - INFO - Epoch(train) [50][1040/1320] lr: 2.0000e-04 eta: 0:02:14 time: 0.4811 data_time: 0.0148 memory: 27031 grad_norm: 6.8903 loss: 0.7535 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7535 2023/02/17 21:20:42 - mmengine - INFO - Epoch(train) [50][1060/1320] lr: 2.0000e-04 eta: 0:02:05 time: 0.4813 data_time: 0.0151 memory: 27031 grad_norm: 6.8136 loss: 0.7841 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7841 2023/02/17 21:20:52 - mmengine - INFO - Epoch(train) [50][1080/1320] lr: 2.0000e-04 eta: 0:01:55 time: 0.4808 data_time: 0.0145 memory: 27031 grad_norm: 7.0085 loss: 0.7167 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.7167 2023/02/17 21:21:01 - mmengine - INFO - Epoch(train) [50][1100/1320] lr: 2.0000e-04 eta: 0:01:46 time: 0.4810 data_time: 0.0144 memory: 27031 grad_norm: 7.1216 loss: 0.8171 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8171 2023/02/17 21:21:11 - mmengine - INFO - Epoch(train) [50][1120/1320] lr: 2.0000e-04 eta: 0:01:36 time: 0.4807 data_time: 0.0143 memory: 27031 grad_norm: 6.9838 loss: 0.7542 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7542 2023/02/17 21:21:21 - mmengine - INFO - Epoch(train) [50][1140/1320] lr: 2.0000e-04 eta: 0:01:26 time: 0.4810 data_time: 0.0143 memory: 27031 grad_norm: 7.1811 loss: 0.8678 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.8678 2023/02/17 21:21:30 - mmengine - INFO - Epoch(train) [50][1160/1320] lr: 2.0000e-04 eta: 0:01:17 time: 0.4832 data_time: 0.0166 memory: 27031 grad_norm: 7.1364 loss: 0.6807 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6807 2023/02/17 21:21:40 - mmengine - INFO - Epoch(train) [50][1180/1320] lr: 2.0000e-04 eta: 0:01:07 time: 0.4809 data_time: 0.0149 memory: 27031 grad_norm: 7.0825 loss: 0.7593 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7593 2023/02/17 21:21:50 - mmengine - INFO - Epoch(train) [50][1200/1320] lr: 2.0000e-04 eta: 0:00:57 time: 0.4811 data_time: 0.0151 memory: 27031 grad_norm: 7.0287 loss: 0.9653 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9653 2023/02/17 21:21:59 - mmengine - INFO - Epoch(train) [50][1220/1320] lr: 2.0000e-04 eta: 0:00:48 time: 0.4821 data_time: 0.0160 memory: 27031 grad_norm: 6.7980 loss: 0.7511 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7511 2023/02/17 21:22:09 - mmengine - INFO - Epoch(train) [50][1240/1320] lr: 2.0000e-04 eta: 0:00:38 time: 0.4818 data_time: 0.0151 memory: 27031 grad_norm: 6.9452 loss: 0.7777 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7777 2023/02/17 21:22:19 - mmengine - INFO - Epoch(train) [50][1260/1320] lr: 2.0000e-04 eta: 0:00:28 time: 0.4827 data_time: 0.0166 memory: 27031 grad_norm: 7.0679 loss: 0.7256 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7256 2023/02/17 21:22:28 - mmengine - INFO - Epoch(train) [50][1280/1320] lr: 2.0000e-04 eta: 0:00:19 time: 0.4809 data_time: 0.0144 memory: 27031 grad_norm: 6.8028 loss: 0.6099 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6099 2023/02/17 21:22:38 - mmengine - INFO - Epoch(train) [50][1300/1320] lr: 2.0000e-04 eta: 0:00:09 time: 0.4820 data_time: 0.0148 memory: 27031 grad_norm: 6.8394 loss: 0.8040 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8040 2023/02/17 21:22:47 - mmengine - INFO - Exp name: tsm_imagenet-pretrained-r50_8xb16-1x1x16-50e_sthv2-rgb_20230217_120712 2023/02/17 21:22:47 - mmengine - INFO - Epoch(train) [50][1320/1320] lr: 2.0000e-04 eta: 0:00:00 time: 0.4749 data_time: 0.0156 memory: 27031 grad_norm: 7.1281 loss: 0.8968 top1_acc: 0.3636 top5_acc: 1.0000 loss_cls: 0.8968 2023/02/17 21:22:47 - mmengine - INFO - Saving checkpoint at 50 epochs 2023/02/17 21:22:52 - mmengine - INFO - Epoch(val) [50][ 20/194] eta: 0:00:32 time: 0.1854 data_time: 0.0576 memory: 3265 2023/02/17 21:22:55 - mmengine - INFO - Epoch(val) [50][ 40/194] eta: 0:00:24 time: 0.1384 data_time: 0.0127 memory: 3265 2023/02/17 21:22:58 - mmengine - INFO - Epoch(val) [50][ 60/194] eta: 0:00:20 time: 0.1402 data_time: 0.0146 memory: 3265 2023/02/17 21:23:01 - mmengine - INFO - Epoch(val) [50][ 80/194] eta: 0:00:17 time: 0.1372 data_time: 0.0131 memory: 3265 2023/02/17 21:23:03 - mmengine - INFO - Epoch(val) [50][100/194] eta: 0:00:13 time: 0.1380 data_time: 0.0137 memory: 3265 2023/02/17 21:23:06 - mmengine - INFO - Epoch(val) [50][120/194] eta: 0:00:10 time: 0.1396 data_time: 0.0139 memory: 3265 2023/02/17 21:23:09 - mmengine - INFO - Epoch(val) [50][140/194] eta: 0:00:07 time: 0.1363 data_time: 0.0128 memory: 3265 2023/02/17 21:23:12 - mmengine - INFO - Epoch(val) [50][160/194] eta: 0:00:04 time: 0.1379 data_time: 0.0133 memory: 3265 2023/02/17 21:23:14 - mmengine - INFO - Epoch(val) [50][180/194] eta: 0:00:02 time: 0.1377 data_time: 0.0136 memory: 3265 2023/02/17 21:23:17 - mmengine - INFO - Epoch(val) [50][194/194] acc/top1: 0.6216 acc/top5: 0.8743 acc/mean1: 0.5614