2023/02/18 00:35:03 - 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: 11325563 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 ------------------------------------------------------------ 2023/02/18 00:35:03 - mmengine - INFO - Config: model = dict( type='Recognizer2D', backbone=dict( type='ResNet', pretrained='https://download.pytorch.org/models/resnet50-11ad3fa6.pth', depth=50, norm_eval=False), cls_head=dict( type='TSNHead', num_classes=174, in_channels=2048, spatial_type='avg', consensus=dict(type='AvgConsensus', dim=1), dropout_ratio=0.5, init_std=0.01, average_clips='prob'), data_preprocessor=dict( type='ActionDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], format_shape='NCHW'), train_cfg=None, test_cfg=None) train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=5) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='MultiStepLR', begin=0, end=50, by_epoch=True, milestones=[20, 40], gamma=0.1) ] optim_wrapper = dict( optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001), clip_grad=dict(max_norm=40, norm_type=2)) 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=25, 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=32, 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=32, 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=25, 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') auto_scale_lr = dict(enable=False, base_batch_size=256) launcher = 'pytorch' work_dir = 'work_dirs/fix_flip/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2023/02/18 00:35:06 - 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 -------------------- 2023/02/18 00:35:08 - mmengine - INFO - These parameters in pretrained checkpoint are not loaded: {'fc.weight', 'fc.bias'} Name of parameter - Initialization information backbone.conv1.conv.weight - torch.Size([64, 3, 7, 7]): Initialized by user-defined `init_weights` in ResNet backbone.conv1.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.conv1.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv1.conv.weight - torch.Size([64, 64, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv1.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv1.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv2.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv2.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv3.conv.weight - torch.Size([256, 64, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv3.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.conv3.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.downsample.conv.weight - torch.Size([256, 64, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.downsample.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.0.downsample.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv1.conv.weight - torch.Size([64, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv1.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv1.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv2.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv2.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv3.conv.weight - torch.Size([256, 64, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv3.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.1.conv3.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv1.conv.weight - torch.Size([64, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv1.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv1.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv2.bn.weight - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv2.bn.bias - torch.Size([64]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv3.conv.weight - torch.Size([256, 64, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv3.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer1.2.conv3.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv1.conv.weight - torch.Size([128, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv1.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv1.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv2.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv2.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv3.conv.weight - torch.Size([512, 128, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv3.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.conv3.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.downsample.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.0.downsample.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv1.conv.weight - torch.Size([128, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv1.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv1.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv2.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv2.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv3.conv.weight - torch.Size([512, 128, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv3.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.1.conv3.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv1.conv.weight - torch.Size([128, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv1.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv1.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv2.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv2.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv3.conv.weight - torch.Size([512, 128, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv3.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.2.conv3.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv1.conv.weight - torch.Size([128, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv1.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv1.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv2.bn.weight - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv2.bn.bias - torch.Size([128]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv3.conv.weight - torch.Size([512, 128, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv3.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer2.3.conv3.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv1.conv.weight - torch.Size([256, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.downsample.conv.weight - torch.Size([1024, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.downsample.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.0.downsample.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv1.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.1.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv1.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.2.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv1.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.3.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv1.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.4.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv1.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv1.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv1.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv2.bn.weight - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv2.bn.bias - torch.Size([256]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv3.conv.weight - torch.Size([1024, 256, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv3.bn.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer3.5.conv3.bn.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv1.conv.weight - torch.Size([512, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv1.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv1.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv2.conv.weight - torch.Size([512, 512, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv2.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv2.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv3.bn.weight - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.conv3.bn.bias - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.downsample.conv.weight - torch.Size([2048, 1024, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.downsample.bn.weight - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.0.downsample.bn.bias - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv1.conv.weight - torch.Size([512, 2048, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv1.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv1.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv2.conv.weight - torch.Size([512, 512, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv2.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv2.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv3.bn.weight - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.1.conv3.bn.bias - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv1.conv.weight - torch.Size([512, 2048, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv1.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv1.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv2.conv.weight - torch.Size([512, 512, 3, 3]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv2.bn.weight - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv2.bn.bias - torch.Size([512]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv3.conv.weight - torch.Size([2048, 512, 1, 1]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv3.bn.weight - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet backbone.layer4.2.conv3.bn.bias - torch.Size([2048]): Initialized by user-defined `init_weights` in ResNet cls_head.fc_cls.weight - torch.Size([174, 2048]): Initialized by user-defined `init_weights` in TSNHead cls_head.fc_cls.bias - torch.Size([174]): Initialized by user-defined `init_weights` in TSNHead 2023/02/18 00:35:08 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb. 2023/02/18 00:36:01 - mmengine - INFO - Epoch(train) [1][ 20/660] lr: 1.0000e-02 eta: 1 day, 0:12:56 time: 2.6433 data_time: 1.9886 memory: 42708 grad_norm: 0.9339 loss: 5.1393 top1_acc: 0.0625 top5_acc: 0.0938 loss_cls: 5.1393 2023/02/18 00:36:13 - mmengine - INFO - Epoch(train) [1][ 40/660] lr: 1.0000e-02 eta: 14:57:37 time: 0.6247 data_time: 0.0299 memory: 42708 grad_norm: 1.1074 loss: 5.0120 top1_acc: 0.0938 top5_acc: 0.1562 loss_cls: 5.0120 2023/02/18 00:36:26 - mmengine - INFO - Epoch(train) [1][ 60/660] lr: 1.0000e-02 eta: 11:53:43 time: 0.6321 data_time: 0.0313 memory: 42708 grad_norm: 1.2275 loss: 4.9449 top1_acc: 0.0625 top5_acc: 0.0938 loss_cls: 4.9449 2023/02/18 00:36:38 - mmengine - INFO - Epoch(train) [1][ 80/660] lr: 1.0000e-02 eta: 10:21:02 time: 0.6274 data_time: 0.0282 memory: 42708 grad_norm: 1.2795 loss: 4.8736 top1_acc: 0.0000 top5_acc: 0.0625 loss_cls: 4.8736 2023/02/18 00:36:51 - mmengine - INFO - Epoch(train) [1][100/660] lr: 1.0000e-02 eta: 9:26:48 time: 0.6409 data_time: 0.0337 memory: 42708 grad_norm: 1.3316 loss: 4.8809 top1_acc: 0.0938 top5_acc: 0.2500 loss_cls: 4.8809 2023/02/18 00:37:04 - mmengine - INFO - Epoch(train) [1][120/660] lr: 1.0000e-02 eta: 8:49:17 time: 0.6266 data_time: 0.0279 memory: 42708 grad_norm: 1.4037 loss: 4.8140 top1_acc: 0.0312 top5_acc: 0.1250 loss_cls: 4.8140 2023/02/18 00:37:17 - mmengine - INFO - Epoch(train) [1][140/660] lr: 1.0000e-02 eta: 8:23:17 time: 0.6377 data_time: 0.0375 memory: 42708 grad_norm: 1.4785 loss: 4.7260 top1_acc: 0.0000 top5_acc: 0.1250 loss_cls: 4.7260 2023/02/18 00:37:29 - mmengine - INFO - Epoch(train) [1][160/660] lr: 1.0000e-02 eta: 8:02:46 time: 0.6234 data_time: 0.0291 memory: 42708 grad_norm: 1.5581 loss: 4.6806 top1_acc: 0.0312 top5_acc: 0.1562 loss_cls: 4.6806 2023/02/18 00:37:42 - mmengine - INFO - Epoch(train) [1][180/660] lr: 1.0000e-02 eta: 7:47:14 time: 0.6313 data_time: 0.0322 memory: 42708 grad_norm: 1.6429 loss: 4.6812 top1_acc: 0.0625 top5_acc: 0.2188 loss_cls: 4.6812 2023/02/18 00:37:54 - mmengine - INFO - Epoch(train) [1][200/660] lr: 1.0000e-02 eta: 7:34:22 time: 0.6241 data_time: 0.0299 memory: 42708 grad_norm: 1.7192 loss: 4.5634 top1_acc: 0.1562 top5_acc: 0.3125 loss_cls: 4.5634 2023/02/18 00:38:07 - mmengine - INFO - Epoch(train) [1][220/660] lr: 1.0000e-02 eta: 7:24:33 time: 0.6389 data_time: 0.0349 memory: 42708 grad_norm: 1.8051 loss: 4.5592 top1_acc: 0.0625 top5_acc: 0.2188 loss_cls: 4.5592 2023/02/18 00:38:19 - mmengine - INFO - Epoch(train) [1][240/660] lr: 1.0000e-02 eta: 7:15:42 time: 0.6253 data_time: 0.0285 memory: 42708 grad_norm: 1.8492 loss: 4.4856 top1_acc: 0.0938 top5_acc: 0.2500 loss_cls: 4.4856 2023/02/18 00:38:32 - mmengine - INFO - Epoch(train) [1][260/660] lr: 1.0000e-02 eta: 7:08:37 time: 0.6356 data_time: 0.0329 memory: 42708 grad_norm: 1.9233 loss: 4.3748 top1_acc: 0.0938 top5_acc: 0.1875 loss_cls: 4.3748 2023/02/18 00:38:45 - mmengine - INFO - Epoch(train) [1][280/660] lr: 1.0000e-02 eta: 7:02:09 time: 0.6264 data_time: 0.0283 memory: 42708 grad_norm: 2.0234 loss: 4.4292 top1_acc: 0.0938 top5_acc: 0.2188 loss_cls: 4.4292 2023/02/18 00:38:57 - mmengine - INFO - Epoch(train) [1][300/660] lr: 1.0000e-02 eta: 6:56:52 time: 0.6355 data_time: 0.0324 memory: 42708 grad_norm: 2.0790 loss: 4.3081 top1_acc: 0.1875 top5_acc: 0.4688 loss_cls: 4.3081 2023/02/18 00:39:10 - mmengine - INFO - Epoch(train) [1][320/660] lr: 1.0000e-02 eta: 6:51:52 time: 0.6259 data_time: 0.0274 memory: 42708 grad_norm: 2.1028 loss: 4.2507 top1_acc: 0.0625 top5_acc: 0.1875 loss_cls: 4.2507 2023/02/18 00:39:23 - mmengine - INFO - Epoch(train) [1][340/660] lr: 1.0000e-02 eta: 6:47:46 time: 0.6357 data_time: 0.0338 memory: 42708 grad_norm: 2.1766 loss: 4.3183 top1_acc: 0.0625 top5_acc: 0.2188 loss_cls: 4.3183 2023/02/18 00:39:35 - mmengine - INFO - Epoch(train) [1][360/660] lr: 1.0000e-02 eta: 6:43:44 time: 0.6241 data_time: 0.0281 memory: 42708 grad_norm: 2.2206 loss: 4.2480 top1_acc: 0.1562 top5_acc: 0.4062 loss_cls: 4.2480 2023/02/18 00:39:48 - mmengine - INFO - Epoch(train) [1][380/660] lr: 1.0000e-02 eta: 6:40:33 time: 0.6395 data_time: 0.0334 memory: 42708 grad_norm: 2.2328 loss: 4.1864 top1_acc: 0.1875 top5_acc: 0.3438 loss_cls: 4.1864 2023/02/18 00:40:00 - mmengine - INFO - Epoch(train) [1][400/660] lr: 1.0000e-02 eta: 6:37:23 time: 0.6295 data_time: 0.0304 memory: 42708 grad_norm: 2.2983 loss: 4.1788 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 4.1788 2023/02/18 00:40:13 - mmengine - INFO - Epoch(train) [1][420/660] lr: 1.0000e-02 eta: 6:34:37 time: 0.6339 data_time: 0.0322 memory: 42708 grad_norm: 2.3492 loss: 4.1531 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 4.1531 2023/02/18 00:40:26 - mmengine - INFO - Epoch(train) [1][440/660] lr: 1.0000e-02 eta: 6:31:53 time: 0.6255 data_time: 0.0294 memory: 42708 grad_norm: 2.3920 loss: 3.9969 top1_acc: 0.0625 top5_acc: 0.3750 loss_cls: 3.9969 2023/02/18 00:40:38 - mmengine - INFO - Epoch(train) [1][460/660] lr: 1.0000e-02 eta: 6:29:39 time: 0.6376 data_time: 0.0335 memory: 42708 grad_norm: 2.4153 loss: 4.0605 top1_acc: 0.0625 top5_acc: 0.1562 loss_cls: 4.0605 2023/02/18 00:40:51 - mmengine - INFO - Epoch(train) [1][480/660] lr: 1.0000e-02 eta: 6:27:17 time: 0.6241 data_time: 0.0310 memory: 42708 grad_norm: 2.4604 loss: 4.0749 top1_acc: 0.0938 top5_acc: 0.2812 loss_cls: 4.0749 2023/02/18 00:41:04 - mmengine - INFO - Epoch(train) [1][500/660] lr: 1.0000e-02 eta: 6:25:20 time: 0.6357 data_time: 0.0336 memory: 42708 grad_norm: 2.4731 loss: 3.9734 top1_acc: 0.0625 top5_acc: 0.3438 loss_cls: 3.9734 2023/02/18 00:41:16 - mmengine - INFO - Epoch(train) [1][520/660] lr: 1.0000e-02 eta: 6:23:16 time: 0.6239 data_time: 0.0316 memory: 42708 grad_norm: 2.4681 loss: 3.9763 top1_acc: 0.0938 top5_acc: 0.4062 loss_cls: 3.9763 2023/02/18 00:41:29 - mmengine - INFO - Epoch(train) [1][540/660] lr: 1.0000e-02 eta: 6:21:33 time: 0.6337 data_time: 0.0330 memory: 42708 grad_norm: 2.5288 loss: 3.9419 top1_acc: 0.2812 top5_acc: 0.4688 loss_cls: 3.9419 2023/02/18 00:41:41 - mmengine - INFO - Epoch(train) [1][560/660] lr: 1.0000e-02 eta: 6:19:51 time: 0.6294 data_time: 0.0306 memory: 42708 grad_norm: 2.5899 loss: 3.8300 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.8300 2023/02/18 00:41:54 - mmengine - INFO - Epoch(train) [1][580/660] lr: 1.0000e-02 eta: 6:18:20 time: 0.6339 data_time: 0.0324 memory: 42708 grad_norm: 2.6288 loss: 3.9526 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.9526 2023/02/18 00:42:06 - mmengine - INFO - Epoch(train) [1][600/660] lr: 1.0000e-02 eta: 6:16:44 time: 0.6245 data_time: 0.0291 memory: 42708 grad_norm: 2.6088 loss: 3.7464 top1_acc: 0.1250 top5_acc: 0.3750 loss_cls: 3.7464 2023/02/18 00:42:19 - mmengine - INFO - Epoch(train) [1][620/660] lr: 1.0000e-02 eta: 6:15:32 time: 0.6417 data_time: 0.0369 memory: 42708 grad_norm: 2.6596 loss: 3.8460 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.8460 2023/02/18 00:42:32 - mmengine - INFO - Epoch(train) [1][640/660] lr: 1.0000e-02 eta: 6:14:09 time: 0.6272 data_time: 0.0285 memory: 42708 grad_norm: 2.6841 loss: 3.7576 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.7576 2023/02/18 00:42:44 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 00:42:44 - mmengine - INFO - Epoch(train) [1][660/660] lr: 1.0000e-02 eta: 6:12:48 time: 0.6252 data_time: 0.0303 memory: 42708 grad_norm: 2.7361 loss: 3.7751 top1_acc: 0.1481 top5_acc: 0.4074 loss_cls: 3.7751 2023/02/18 00:42:59 - mmengine - INFO - Epoch(train) [2][ 20/660] lr: 1.0000e-02 eta: 6:13:00 time: 0.7195 data_time: 0.1219 memory: 42708 grad_norm: 2.6812 loss: 3.6869 top1_acc: 0.0938 top5_acc: 0.4375 loss_cls: 3.6869 2023/02/18 00:43:11 - mmengine - INFO - Epoch(train) [2][ 40/660] lr: 1.0000e-02 eta: 6:11:40 time: 0.6201 data_time: 0.0296 memory: 42708 grad_norm: 2.7380 loss: 3.6221 top1_acc: 0.2812 top5_acc: 0.4688 loss_cls: 3.6221 2023/02/18 00:43:24 - mmengine - INFO - Epoch(train) [2][ 60/660] lr: 1.0000e-02 eta: 6:10:31 time: 0.6296 data_time: 0.0321 memory: 42708 grad_norm: 2.7838 loss: 3.6748 top1_acc: 0.0625 top5_acc: 0.3125 loss_cls: 3.6748 2023/02/18 00:43:36 - mmengine - INFO - Epoch(train) [2][ 80/660] lr: 1.0000e-02 eta: 6:09:15 time: 0.6169 data_time: 0.0314 memory: 42708 grad_norm: 2.8031 loss: 3.6510 top1_acc: 0.1250 top5_acc: 0.4688 loss_cls: 3.6510 2023/02/18 00:43:49 - mmengine - INFO - Epoch(train) [2][100/660] lr: 1.0000e-02 eta: 6:08:07 time: 0.6230 data_time: 0.0322 memory: 42708 grad_norm: 2.8260 loss: 3.6518 top1_acc: 0.1250 top5_acc: 0.4062 loss_cls: 3.6518 2023/02/18 00:44:01 - mmengine - INFO - Epoch(train) [2][120/660] lr: 1.0000e-02 eta: 6:06:55 time: 0.6146 data_time: 0.0309 memory: 42708 grad_norm: 2.8229 loss: 3.5861 top1_acc: 0.1562 top5_acc: 0.3438 loss_cls: 3.5861 2023/02/18 00:44:13 - mmengine - INFO - Epoch(train) [2][140/660] lr: 1.0000e-02 eta: 6:05:54 time: 0.6246 data_time: 0.0342 memory: 42708 grad_norm: 2.8121 loss: 3.6381 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 3.6381 2023/02/18 00:44:26 - mmengine - INFO - Epoch(train) [2][160/660] lr: 1.0000e-02 eta: 6:04:53 time: 0.6210 data_time: 0.0294 memory: 42708 grad_norm: 2.8456 loss: 3.5215 top1_acc: 0.1562 top5_acc: 0.4688 loss_cls: 3.5215 2023/02/18 00:44:38 - mmengine - INFO - Epoch(train) [2][180/660] lr: 1.0000e-02 eta: 6:03:58 time: 0.6267 data_time: 0.0336 memory: 42708 grad_norm: 2.9105 loss: 3.5604 top1_acc: 0.2188 top5_acc: 0.3750 loss_cls: 3.5604 2023/02/18 00:44:51 - mmengine - INFO - Epoch(train) [2][200/660] lr: 1.0000e-02 eta: 6:03:02 time: 0.6219 data_time: 0.0316 memory: 42708 grad_norm: 2.9382 loss: 3.6005 top1_acc: 0.1875 top5_acc: 0.5312 loss_cls: 3.6005 2023/02/18 00:45:03 - mmengine - INFO - Epoch(train) [2][220/660] lr: 1.0000e-02 eta: 6:02:09 time: 0.6236 data_time: 0.0336 memory: 42708 grad_norm: 2.9003 loss: 3.4523 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 3.4523 2023/02/18 00:45:16 - mmengine - INFO - Epoch(train) [2][240/660] lr: 1.0000e-02 eta: 6:01:16 time: 0.6213 data_time: 0.0339 memory: 42708 grad_norm: 2.9270 loss: 3.5636 top1_acc: 0.1875 top5_acc: 0.5938 loss_cls: 3.5636 2023/02/18 00:45:28 - mmengine - INFO - Epoch(train) [2][260/660] lr: 1.0000e-02 eta: 6:00:27 time: 0.6247 data_time: 0.0353 memory: 42708 grad_norm: 2.8999 loss: 3.4932 top1_acc: 0.2188 top5_acc: 0.6562 loss_cls: 3.4932 2023/02/18 00:45:40 - mmengine - INFO - Epoch(train) [2][280/660] lr: 1.0000e-02 eta: 5:59:35 time: 0.6174 data_time: 0.0312 memory: 42708 grad_norm: 3.0010 loss: 3.5487 top1_acc: 0.1250 top5_acc: 0.4375 loss_cls: 3.5487 2023/02/18 00:45:53 - mmengine - INFO - Epoch(train) [2][300/660] lr: 1.0000e-02 eta: 5:58:50 time: 0.6262 data_time: 0.0335 memory: 42708 grad_norm: 2.9520 loss: 3.5101 top1_acc: 0.2188 top5_acc: 0.5000 loss_cls: 3.5101 2023/02/18 00:46:05 - mmengine - INFO - Epoch(train) [2][320/660] lr: 1.0000e-02 eta: 5:58:01 time: 0.6168 data_time: 0.0291 memory: 42708 grad_norm: 2.9335 loss: 3.4702 top1_acc: 0.2812 top5_acc: 0.5938 loss_cls: 3.4702 2023/02/18 00:46:18 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 00:46:18 - mmengine - INFO - Epoch(train) [2][340/660] lr: 1.0000e-02 eta: 5:57:17 time: 0.6240 data_time: 0.0340 memory: 42708 grad_norm: 3.0321 loss: 3.5156 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.5156 2023/02/18 00:46:30 - mmengine - INFO - Epoch(train) [2][360/660] lr: 1.0000e-02 eta: 5:56:30 time: 0.6164 data_time: 0.0300 memory: 42708 grad_norm: 2.9909 loss: 3.5901 top1_acc: 0.0938 top5_acc: 0.4688 loss_cls: 3.5901 2023/02/18 00:46:43 - mmengine - INFO - Epoch(train) [2][380/660] lr: 1.0000e-02 eta: 5:55:49 time: 0.6240 data_time: 0.0326 memory: 42708 grad_norm: 3.0074 loss: 3.3808 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 3.3808 2023/02/18 00:46:55 - mmengine - INFO - Epoch(train) [2][400/660] lr: 1.0000e-02 eta: 5:55:06 time: 0.6184 data_time: 0.0300 memory: 42708 grad_norm: 3.0104 loss: 3.3928 top1_acc: 0.1562 top5_acc: 0.5312 loss_cls: 3.3928 2023/02/18 00:47:08 - mmengine - INFO - Epoch(train) [2][420/660] lr: 1.0000e-02 eta: 5:54:32 time: 0.6321 data_time: 0.0321 memory: 42708 grad_norm: 2.9849 loss: 3.4129 top1_acc: 0.1562 top5_acc: 0.4688 loss_cls: 3.4129 2023/02/18 00:47:20 - mmengine - INFO - Epoch(train) [2][440/660] lr: 1.0000e-02 eta: 5:53:53 time: 0.6225 data_time: 0.0303 memory: 42708 grad_norm: 3.0345 loss: 3.4630 top1_acc: 0.1250 top5_acc: 0.4062 loss_cls: 3.4630 2023/02/18 00:47:33 - mmengine - INFO - Epoch(train) [2][460/660] lr: 1.0000e-02 eta: 5:53:18 time: 0.6267 data_time: 0.0320 memory: 42708 grad_norm: 3.0328 loss: 3.5100 top1_acc: 0.1875 top5_acc: 0.4688 loss_cls: 3.5100 2023/02/18 00:47:45 - mmengine - INFO - Epoch(train) [2][480/660] lr: 1.0000e-02 eta: 5:52:37 time: 0.6160 data_time: 0.0299 memory: 42708 grad_norm: 3.0455 loss: 3.4608 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 3.4608 2023/02/18 00:47:58 - mmengine - INFO - Epoch(train) [2][500/660] lr: 1.0000e-02 eta: 5:52:04 time: 0.6287 data_time: 0.0364 memory: 42708 grad_norm: 3.0782 loss: 3.3042 top1_acc: 0.2500 top5_acc: 0.4688 loss_cls: 3.3042 2023/02/18 00:48:10 - mmengine - INFO - Epoch(train) [2][520/660] lr: 1.0000e-02 eta: 5:51:24 time: 0.6138 data_time: 0.0304 memory: 42708 grad_norm: 3.0962 loss: 3.4198 top1_acc: 0.2188 top5_acc: 0.5312 loss_cls: 3.4198 2023/02/18 00:48:22 - mmengine - INFO - Epoch(train) [2][540/660] lr: 1.0000e-02 eta: 5:50:52 time: 0.6265 data_time: 0.0329 memory: 42708 grad_norm: 3.0917 loss: 3.4360 top1_acc: 0.2188 top5_acc: 0.5000 loss_cls: 3.4360 2023/02/18 00:48:35 - mmengine - INFO - Epoch(train) [2][560/660] lr: 1.0000e-02 eta: 5:50:16 time: 0.6180 data_time: 0.0320 memory: 42708 grad_norm: 3.0854 loss: 3.3408 top1_acc: 0.2188 top5_acc: 0.5312 loss_cls: 3.3408 2023/02/18 00:48:47 - mmengine - INFO - Epoch(train) [2][580/660] lr: 1.0000e-02 eta: 5:49:44 time: 0.6245 data_time: 0.0318 memory: 42708 grad_norm: 3.1014 loss: 3.3829 top1_acc: 0.2812 top5_acc: 0.7188 loss_cls: 3.3829 2023/02/18 00:49:00 - mmengine - INFO - Epoch(train) [2][600/660] lr: 1.0000e-02 eta: 5:49:08 time: 0.6154 data_time: 0.0300 memory: 42708 grad_norm: 3.0817 loss: 3.4162 top1_acc: 0.2500 top5_acc: 0.5312 loss_cls: 3.4162 2023/02/18 00:49:12 - mmengine - INFO - Epoch(train) [2][620/660] lr: 1.0000e-02 eta: 5:48:37 time: 0.6250 data_time: 0.0343 memory: 42708 grad_norm: 3.1278 loss: 3.4475 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.4475 2023/02/18 00:49:24 - mmengine - INFO - Epoch(train) [2][640/660] lr: 1.0000e-02 eta: 5:48:03 time: 0.6159 data_time: 0.0318 memory: 42708 grad_norm: 3.1222 loss: 3.3795 top1_acc: 0.3125 top5_acc: 0.4688 loss_cls: 3.3795 2023/02/18 00:49:37 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 00:49:37 - mmengine - INFO - Epoch(train) [2][660/660] lr: 1.0000e-02 eta: 5:47:28 time: 0.6136 data_time: 0.0291 memory: 42708 grad_norm: 3.1561 loss: 3.2239 top1_acc: 0.1111 top5_acc: 0.3333 loss_cls: 3.2239 2023/02/18 00:49:51 - mmengine - INFO - Epoch(train) [3][ 20/660] lr: 1.0000e-02 eta: 5:47:46 time: 0.7244 data_time: 0.1165 memory: 42708 grad_norm: 3.0851 loss: 3.2238 top1_acc: 0.2812 top5_acc: 0.5000 loss_cls: 3.2238 2023/02/18 00:50:04 - mmengine - INFO - Epoch(train) [3][ 40/660] lr: 1.0000e-02 eta: 5:47:17 time: 0.6253 data_time: 0.0297 memory: 42708 grad_norm: 3.1149 loss: 3.0445 top1_acc: 0.2500 top5_acc: 0.5938 loss_cls: 3.0445 2023/02/18 00:50:16 - mmengine - INFO - Epoch(train) [3][ 60/660] lr: 1.0000e-02 eta: 5:46:54 time: 0.6361 data_time: 0.0290 memory: 42708 grad_norm: 3.1459 loss: 3.1931 top1_acc: 0.2188 top5_acc: 0.4688 loss_cls: 3.1931 2023/02/18 00:50:29 - mmengine - INFO - Epoch(train) [3][ 80/660] lr: 1.0000e-02 eta: 5:46:27 time: 0.6278 data_time: 0.0280 memory: 42708 grad_norm: 3.1276 loss: 3.1595 top1_acc: 0.2812 top5_acc: 0.4688 loss_cls: 3.1595 2023/02/18 00:50:42 - mmengine - INFO - Epoch(train) [3][100/660] lr: 1.0000e-02 eta: 5:46:03 time: 0.6349 data_time: 0.0279 memory: 42708 grad_norm: 3.2085 loss: 3.1657 top1_acc: 0.1875 top5_acc: 0.4688 loss_cls: 3.1657 2023/02/18 00:50:54 - mmengine - INFO - Epoch(train) [3][120/660] lr: 1.0000e-02 eta: 5:45:37 time: 0.6277 data_time: 0.0284 memory: 42708 grad_norm: 3.1979 loss: 3.1332 top1_acc: 0.2812 top5_acc: 0.6875 loss_cls: 3.1332 2023/02/18 00:51:07 - mmengine - INFO - Epoch(train) [3][140/660] lr: 1.0000e-02 eta: 5:45:21 time: 0.6509 data_time: 0.0279 memory: 42708 grad_norm: 3.1796 loss: 3.2611 top1_acc: 0.2188 top5_acc: 0.5000 loss_cls: 3.2611 2023/02/18 00:51:20 - mmengine - INFO - Epoch(train) [3][160/660] lr: 1.0000e-02 eta: 5:44:54 time: 0.6239 data_time: 0.0315 memory: 42708 grad_norm: 3.2379 loss: 3.1195 top1_acc: 0.3125 top5_acc: 0.7188 loss_cls: 3.1195 2023/02/18 00:51:32 - mmengine - INFO - Epoch(train) [3][180/660] lr: 1.0000e-02 eta: 5:44:34 time: 0.6389 data_time: 0.0290 memory: 42708 grad_norm: 3.1897 loss: 3.1192 top1_acc: 0.3125 top5_acc: 0.6562 loss_cls: 3.1192 2023/02/18 00:51:45 - mmengine - INFO - Epoch(train) [3][200/660] lr: 1.0000e-02 eta: 5:44:06 time: 0.6216 data_time: 0.0281 memory: 42708 grad_norm: 3.2071 loss: 3.2510 top1_acc: 0.2188 top5_acc: 0.4062 loss_cls: 3.2510 2023/02/18 00:51:58 - mmengine - INFO - Epoch(train) [3][220/660] lr: 1.0000e-02 eta: 5:43:44 time: 0.6341 data_time: 0.0279 memory: 42708 grad_norm: 3.1944 loss: 3.1420 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 3.1420 2023/02/18 00:52:10 - mmengine - INFO - Epoch(train) [3][240/660] lr: 1.0000e-02 eta: 5:43:21 time: 0.6308 data_time: 0.0273 memory: 42708 grad_norm: 3.1965 loss: 3.0182 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.0182 2023/02/18 00:52:23 - mmengine - INFO - Epoch(train) [3][260/660] lr: 1.0000e-02 eta: 5:43:01 time: 0.6392 data_time: 0.0288 memory: 42708 grad_norm: 3.2364 loss: 3.1961 top1_acc: 0.2500 top5_acc: 0.5312 loss_cls: 3.1961 2023/02/18 00:52:35 - mmengine - INFO - Epoch(train) [3][280/660] lr: 1.0000e-02 eta: 5:42:36 time: 0.6244 data_time: 0.0285 memory: 42708 grad_norm: 3.2846 loss: 3.2299 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 3.2299 2023/02/18 00:52:48 - mmengine - INFO - Epoch(train) [3][300/660] lr: 1.0000e-02 eta: 5:42:19 time: 0.6449 data_time: 0.0273 memory: 42708 grad_norm: 3.2503 loss: 3.2036 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.2036 2023/02/18 00:53:01 - mmengine - INFO - Epoch(train) [3][320/660] lr: 1.0000e-02 eta: 5:41:56 time: 0.6262 data_time: 0.0267 memory: 42708 grad_norm: 3.2376 loss: 3.0769 top1_acc: 0.1562 top5_acc: 0.4375 loss_cls: 3.0769 2023/02/18 00:53:14 - mmengine - INFO - Epoch(train) [3][340/660] lr: 1.0000e-02 eta: 5:41:38 time: 0.6415 data_time: 0.0285 memory: 42708 grad_norm: 3.3017 loss: 3.0821 top1_acc: 0.3750 top5_acc: 0.4688 loss_cls: 3.0821 2023/02/18 00:53:26 - mmengine - INFO - Epoch(train) [3][360/660] lr: 1.0000e-02 eta: 5:41:13 time: 0.6231 data_time: 0.0260 memory: 42708 grad_norm: 3.2369 loss: 3.1785 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 3.1785 2023/02/18 00:53:39 - mmengine - INFO - Epoch(train) [3][380/660] lr: 1.0000e-02 eta: 5:40:56 time: 0.6417 data_time: 0.0274 memory: 42708 grad_norm: 3.2312 loss: 3.1013 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.1013 2023/02/18 00:53:52 - mmengine - INFO - Epoch(train) [3][400/660] lr: 1.0000e-02 eta: 5:40:36 time: 0.6362 data_time: 0.0260 memory: 42708 grad_norm: 3.2680 loss: 3.1037 top1_acc: 0.2188 top5_acc: 0.5938 loss_cls: 3.1037 2023/02/18 00:54:05 - mmengine - INFO - Epoch(train) [3][420/660] lr: 1.0000e-02 eta: 5:40:19 time: 0.6408 data_time: 0.0328 memory: 42708 grad_norm: 3.2848 loss: 3.1214 top1_acc: 0.1562 top5_acc: 0.5938 loss_cls: 3.1214 2023/02/18 00:54:17 - mmengine - INFO - Epoch(train) [3][440/660] lr: 1.0000e-02 eta: 5:39:55 time: 0.6229 data_time: 0.0272 memory: 42708 grad_norm: 3.2878 loss: 2.9694 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.9694 2023/02/18 00:54:30 - mmengine - INFO - Epoch(train) [3][460/660] lr: 1.0000e-02 eta: 5:39:38 time: 0.6412 data_time: 0.0283 memory: 42708 grad_norm: 3.2000 loss: 3.0305 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 3.0305 2023/02/18 00:54:42 - mmengine - INFO - Epoch(train) [3][480/660] lr: 1.0000e-02 eta: 5:39:18 time: 0.6327 data_time: 0.0265 memory: 42708 grad_norm: 3.2612 loss: 3.1000 top1_acc: 0.3125 top5_acc: 0.5938 loss_cls: 3.1000 2023/02/18 00:54:55 - mmengine - INFO - Epoch(train) [3][500/660] lr: 1.0000e-02 eta: 5:39:00 time: 0.6382 data_time: 0.0283 memory: 42708 grad_norm: 3.2662 loss: 3.2243 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 3.2243 2023/02/18 00:55:08 - mmengine - INFO - Epoch(train) [3][520/660] lr: 1.0000e-02 eta: 5:38:38 time: 0.6260 data_time: 0.0279 memory: 42708 grad_norm: 3.2825 loss: 3.0009 top1_acc: 0.1875 top5_acc: 0.4062 loss_cls: 3.0009 2023/02/18 00:55:21 - mmengine - INFO - Epoch(train) [3][540/660] lr: 1.0000e-02 eta: 5:38:20 time: 0.6392 data_time: 0.0283 memory: 42708 grad_norm: 3.2952 loss: 3.0600 top1_acc: 0.1562 top5_acc: 0.4375 loss_cls: 3.0600 2023/02/18 00:55:33 - mmengine - INFO - Epoch(train) [3][560/660] lr: 1.0000e-02 eta: 5:37:59 time: 0.6264 data_time: 0.0272 memory: 42708 grad_norm: 3.3195 loss: 2.9554 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.9554 2023/02/18 00:55:46 - mmengine - INFO - Epoch(train) [3][580/660] lr: 1.0000e-02 eta: 5:37:43 time: 0.6430 data_time: 0.0273 memory: 42708 grad_norm: 3.3121 loss: 3.1252 top1_acc: 0.0625 top5_acc: 0.4688 loss_cls: 3.1252 2023/02/18 00:55:59 - mmengine - INFO - Epoch(train) [3][600/660] lr: 1.0000e-02 eta: 5:37:23 time: 0.6299 data_time: 0.0256 memory: 42708 grad_norm: 3.2729 loss: 3.0619 top1_acc: 0.1875 top5_acc: 0.5000 loss_cls: 3.0619 2023/02/18 00:56:11 - mmengine - INFO - Epoch(train) [3][620/660] lr: 1.0000e-02 eta: 5:37:04 time: 0.6322 data_time: 0.0271 memory: 42708 grad_norm: 3.2800 loss: 3.1046 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.1046 2023/02/18 00:56:24 - mmengine - INFO - Epoch(train) [3][640/660] lr: 1.0000e-02 eta: 5:36:43 time: 0.6281 data_time: 0.0258 memory: 42708 grad_norm: 3.2892 loss: 3.1656 top1_acc: 0.2188 top5_acc: 0.5938 loss_cls: 3.1656 2023/02/18 00:56:36 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 00:56:36 - mmengine - INFO - Epoch(train) [3][660/660] lr: 1.0000e-02 eta: 5:36:20 time: 0.6184 data_time: 0.0240 memory: 42708 grad_norm: 3.3020 loss: 3.1360 top1_acc: 0.2593 top5_acc: 0.4815 loss_cls: 3.1360 2023/02/18 00:56:36 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/02/18 00:56:52 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 00:56:52 - mmengine - INFO - Epoch(train) [4][ 20/660] lr: 1.0000e-02 eta: 5:36:26 time: 0.7118 data_time: 0.1230 memory: 42708 grad_norm: 3.3172 loss: 2.9386 top1_acc: 0.0625 top5_acc: 0.5938 loss_cls: 2.9386 2023/02/18 00:57:04 - mmengine - INFO - Epoch(train) [4][ 40/660] lr: 1.0000e-02 eta: 5:36:04 time: 0.6200 data_time: 0.0270 memory: 42708 grad_norm: 3.3425 loss: 2.9405 top1_acc: 0.2188 top5_acc: 0.7500 loss_cls: 2.9405 2023/02/18 00:57:16 - mmengine - INFO - Epoch(train) [4][ 60/660] lr: 1.0000e-02 eta: 5:35:44 time: 0.6277 data_time: 0.0329 memory: 42708 grad_norm: 3.3591 loss: 3.0537 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 3.0537 2023/02/18 00:57:29 - mmengine - INFO - Epoch(train) [4][ 80/660] lr: 1.0000e-02 eta: 5:35:22 time: 0.6211 data_time: 0.0273 memory: 42708 grad_norm: 3.3548 loss: 2.8209 top1_acc: 0.2812 top5_acc: 0.6562 loss_cls: 2.8209 2023/02/18 00:57:42 - mmengine - INFO - Epoch(train) [4][100/660] lr: 1.0000e-02 eta: 5:35:04 time: 0.6332 data_time: 0.0323 memory: 42708 grad_norm: 3.3047 loss: 2.9997 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 2.9997 2023/02/18 00:57:54 - mmengine - INFO - Epoch(train) [4][120/660] lr: 1.0000e-02 eta: 5:34:45 time: 0.6296 data_time: 0.0254 memory: 42708 grad_norm: 3.3437 loss: 3.0762 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 3.0762 2023/02/18 00:58:07 - mmengine - INFO - Epoch(train) [4][140/660] lr: 1.0000e-02 eta: 5:34:28 time: 0.6363 data_time: 0.0330 memory: 42708 grad_norm: 3.3383 loss: 2.9740 top1_acc: 0.2500 top5_acc: 0.5938 loss_cls: 2.9740 2023/02/18 00:58:19 - mmengine - INFO - Epoch(train) [4][160/660] lr: 1.0000e-02 eta: 5:34:08 time: 0.6289 data_time: 0.0261 memory: 42708 grad_norm: 3.4188 loss: 2.9340 top1_acc: 0.2812 top5_acc: 0.5938 loss_cls: 2.9340 2023/02/18 00:58:32 - mmengine - INFO - Epoch(train) [4][180/660] lr: 1.0000e-02 eta: 5:33:54 time: 0.6434 data_time: 0.0380 memory: 42708 grad_norm: 3.3551 loss: 2.9629 top1_acc: 0.1250 top5_acc: 0.5000 loss_cls: 2.9629 2023/02/18 00:58:45 - mmengine - INFO - Epoch(train) [4][200/660] lr: 1.0000e-02 eta: 5:33:35 time: 0.6307 data_time: 0.0314 memory: 42708 grad_norm: 3.3150 loss: 2.9379 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.9379 2023/02/18 00:58:58 - mmengine - INFO - Epoch(train) [4][220/660] lr: 1.0000e-02 eta: 5:33:19 time: 0.6367 data_time: 0.0319 memory: 42708 grad_norm: 3.3880 loss: 3.0430 top1_acc: 0.2812 top5_acc: 0.5625 loss_cls: 3.0430 2023/02/18 00:59:10 - mmengine - INFO - Epoch(train) [4][240/660] lr: 1.0000e-02 eta: 5:33:02 time: 0.6360 data_time: 0.0264 memory: 42708 grad_norm: 3.3894 loss: 2.8556 top1_acc: 0.2500 top5_acc: 0.4688 loss_cls: 2.8556 2023/02/18 00:59:23 - mmengine - INFO - Epoch(train) [4][260/660] lr: 1.0000e-02 eta: 5:32:47 time: 0.6410 data_time: 0.0342 memory: 42708 grad_norm: 3.3393 loss: 2.8651 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.8651 2023/02/18 00:59:36 - mmengine - INFO - Epoch(train) [4][280/660] lr: 1.0000e-02 eta: 5:32:30 time: 0.6333 data_time: 0.0278 memory: 42708 grad_norm: 3.4101 loss: 2.8255 top1_acc: 0.3438 top5_acc: 0.6250 loss_cls: 2.8255 2023/02/18 00:59:49 - mmengine - INFO - Epoch(train) [4][300/660] lr: 1.0000e-02 eta: 5:32:15 time: 0.6425 data_time: 0.0315 memory: 42708 grad_norm: 3.4113 loss: 2.8385 top1_acc: 0.4062 top5_acc: 0.5625 loss_cls: 2.8385 2023/02/18 01:00:01 - mmengine - INFO - Epoch(train) [4][320/660] lr: 1.0000e-02 eta: 5:31:57 time: 0.6311 data_time: 0.0277 memory: 42708 grad_norm: 3.4050 loss: 3.0163 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 3.0163 2023/02/18 01:00:14 - mmengine - INFO - Epoch(train) [4][340/660] lr: 1.0000e-02 eta: 5:31:40 time: 0.6346 data_time: 0.0321 memory: 42708 grad_norm: 3.4032 loss: 2.9297 top1_acc: 0.2812 top5_acc: 0.5000 loss_cls: 2.9297 2023/02/18 01:00:27 - mmengine - INFO - Epoch(train) [4][360/660] lr: 1.0000e-02 eta: 5:31:22 time: 0.6298 data_time: 0.0274 memory: 42708 grad_norm: 3.4298 loss: 2.9034 top1_acc: 0.3125 top5_acc: 0.6562 loss_cls: 2.9034 2023/02/18 01:00:39 - mmengine - INFO - Epoch(train) [4][380/660] lr: 1.0000e-02 eta: 5:31:05 time: 0.6323 data_time: 0.0322 memory: 42708 grad_norm: 3.3404 loss: 2.9931 top1_acc: 0.2812 top5_acc: 0.4688 loss_cls: 2.9931 2023/02/18 01:00:52 - mmengine - INFO - Epoch(train) [4][400/660] lr: 1.0000e-02 eta: 5:30:49 time: 0.6365 data_time: 0.0293 memory: 42708 grad_norm: 3.3482 loss: 2.9174 top1_acc: 0.2812 top5_acc: 0.4375 loss_cls: 2.9174 2023/02/18 01:01:05 - mmengine - INFO - Epoch(train) [4][420/660] lr: 1.0000e-02 eta: 5:30:34 time: 0.6381 data_time: 0.0385 memory: 42708 grad_norm: 3.4134 loss: 2.8638 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.8638 2023/02/18 01:01:18 - mmengine - INFO - Epoch(train) [4][440/660] lr: 1.0000e-02 eta: 5:30:18 time: 0.6368 data_time: 0.0261 memory: 42708 grad_norm: 3.4021 loss: 2.9290 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.9290 2023/02/18 01:01:30 - mmengine - INFO - Epoch(train) [4][460/660] lr: 1.0000e-02 eta: 5:30:05 time: 0.6480 data_time: 0.0327 memory: 42708 grad_norm: 3.3463 loss: 2.9247 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.9247 2023/02/18 01:01:43 - mmengine - INFO - Epoch(train) [4][480/660] lr: 1.0000e-02 eta: 5:29:49 time: 0.6375 data_time: 0.0274 memory: 42708 grad_norm: 3.3777 loss: 2.8789 top1_acc: 0.2812 top5_acc: 0.7188 loss_cls: 2.8789 2023/02/18 01:01:56 - mmengine - INFO - Epoch(train) [4][500/660] lr: 1.0000e-02 eta: 5:29:34 time: 0.6404 data_time: 0.0346 memory: 42708 grad_norm: 3.3894 loss: 2.7859 top1_acc: 0.2812 top5_acc: 0.6562 loss_cls: 2.7859 2023/02/18 01:02:09 - mmengine - INFO - Epoch(train) [4][520/660] lr: 1.0000e-02 eta: 5:29:20 time: 0.6416 data_time: 0.0265 memory: 42708 grad_norm: 3.4392 loss: 2.9544 top1_acc: 0.2188 top5_acc: 0.6250 loss_cls: 2.9544 2023/02/18 01:02:22 - mmengine - INFO - Epoch(train) [4][540/660] lr: 1.0000e-02 eta: 5:29:06 time: 0.6436 data_time: 0.0345 memory: 42708 grad_norm: 3.3914 loss: 2.9190 top1_acc: 0.3438 top5_acc: 0.5312 loss_cls: 2.9190 2023/02/18 01:02:35 - mmengine - INFO - Epoch(train) [4][560/660] lr: 1.0000e-02 eta: 5:28:51 time: 0.6415 data_time: 0.0295 memory: 42708 grad_norm: 3.4344 loss: 2.9887 top1_acc: 0.2812 top5_acc: 0.6875 loss_cls: 2.9887 2023/02/18 01:02:47 - mmengine - INFO - Epoch(train) [4][580/660] lr: 1.0000e-02 eta: 5:28:37 time: 0.6413 data_time: 0.0322 memory: 42708 grad_norm: 3.4038 loss: 3.0162 top1_acc: 0.3438 top5_acc: 0.5625 loss_cls: 3.0162 2023/02/18 01:03:00 - mmengine - INFO - Epoch(train) [4][600/660] lr: 1.0000e-02 eta: 5:28:22 time: 0.6374 data_time: 0.0258 memory: 42708 grad_norm: 3.4844 loss: 2.9191 top1_acc: 0.3125 top5_acc: 0.5000 loss_cls: 2.9191 2023/02/18 01:03:13 - mmengine - INFO - Epoch(train) [4][620/660] lr: 1.0000e-02 eta: 5:28:07 time: 0.6425 data_time: 0.0322 memory: 42708 grad_norm: 3.3832 loss: 2.8571 top1_acc: 0.2812 top5_acc: 0.5625 loss_cls: 2.8571 2023/02/18 01:03:26 - mmengine - INFO - Epoch(train) [4][640/660] lr: 1.0000e-02 eta: 5:27:53 time: 0.6411 data_time: 0.0281 memory: 42708 grad_norm: 3.4785 loss: 2.9418 top1_acc: 0.2188 top5_acc: 0.4688 loss_cls: 2.9418 2023/02/18 01:03:38 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:03:38 - mmengine - INFO - Epoch(train) [4][660/660] lr: 1.0000e-02 eta: 5:27:34 time: 0.6216 data_time: 0.0262 memory: 42708 grad_norm: 3.4838 loss: 2.9640 top1_acc: 0.4444 top5_acc: 0.7778 loss_cls: 2.9640 2023/02/18 01:03:52 - mmengine - INFO - Epoch(train) [5][ 20/660] lr: 1.0000e-02 eta: 5:27:35 time: 0.7080 data_time: 0.1097 memory: 42708 grad_norm: 3.4257 loss: 2.7782 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.7782 2023/02/18 01:04:05 - mmengine - INFO - Epoch(train) [5][ 40/660] lr: 1.0000e-02 eta: 5:27:16 time: 0.6216 data_time: 0.0309 memory: 42708 grad_norm: 3.4522 loss: 2.8269 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.8269 2023/02/18 01:04:17 - mmengine - INFO - Epoch(train) [5][ 60/660] lr: 1.0000e-02 eta: 5:26:57 time: 0.6226 data_time: 0.0307 memory: 42708 grad_norm: 3.4156 loss: 2.8015 top1_acc: 0.2500 top5_acc: 0.5938 loss_cls: 2.8015 2023/02/18 01:04:30 - mmengine - INFO - Epoch(train) [5][ 80/660] lr: 1.0000e-02 eta: 5:26:37 time: 0.6143 data_time: 0.0275 memory: 42708 grad_norm: 3.4469 loss: 2.7231 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.7231 2023/02/18 01:04:42 - mmengine - INFO - Epoch(train) [5][100/660] lr: 1.0000e-02 eta: 5:26:19 time: 0.6252 data_time: 0.0312 memory: 42708 grad_norm: 3.4604 loss: 2.7698 top1_acc: 0.2188 top5_acc: 0.5625 loss_cls: 2.7698 2023/02/18 01:04:55 - mmengine - INFO - Epoch(train) [5][120/660] lr: 1.0000e-02 eta: 5:26:02 time: 0.6262 data_time: 0.0276 memory: 42708 grad_norm: 3.4682 loss: 2.7166 top1_acc: 0.3750 top5_acc: 0.5938 loss_cls: 2.7166 2023/02/18 01:05:07 - mmengine - INFO - Epoch(train) [5][140/660] lr: 1.0000e-02 eta: 5:25:46 time: 0.6329 data_time: 0.0318 memory: 42708 grad_norm: 3.5643 loss: 2.8354 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.8354 2023/02/18 01:05:20 - mmengine - INFO - Epoch(train) [5][160/660] lr: 1.0000e-02 eta: 5:25:29 time: 0.6297 data_time: 0.0297 memory: 42708 grad_norm: 3.4754 loss: 2.6471 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.6471 2023/02/18 01:05:33 - mmengine - INFO - Epoch(train) [5][180/660] lr: 1.0000e-02 eta: 5:25:14 time: 0.6353 data_time: 0.0308 memory: 42708 grad_norm: 3.4190 loss: 2.7951 top1_acc: 0.2188 top5_acc: 0.6875 loss_cls: 2.7951 2023/02/18 01:05:45 - mmengine - INFO - Epoch(train) [5][200/660] lr: 1.0000e-02 eta: 5:24:56 time: 0.6245 data_time: 0.0275 memory: 42708 grad_norm: 3.5096 loss: 2.8234 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.8234 2023/02/18 01:05:58 - mmengine - INFO - Epoch(train) [5][220/660] lr: 1.0000e-02 eta: 5:24:39 time: 0.6262 data_time: 0.0324 memory: 42708 grad_norm: 3.4824 loss: 2.7025 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.7025 2023/02/18 01:06:10 - mmengine - INFO - Epoch(train) [5][240/660] lr: 1.0000e-02 eta: 5:24:21 time: 0.6211 data_time: 0.0283 memory: 42708 grad_norm: 3.4657 loss: 2.7214 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.7214 2023/02/18 01:06:23 - mmengine - INFO - Epoch(train) [5][260/660] lr: 1.0000e-02 eta: 5:24:04 time: 0.6260 data_time: 0.0331 memory: 42708 grad_norm: 3.4917 loss: 2.6262 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.6262 2023/02/18 01:06:35 - mmengine - INFO - Epoch(train) [5][280/660] lr: 1.0000e-02 eta: 5:23:46 time: 0.6219 data_time: 0.0309 memory: 42708 grad_norm: 3.4452 loss: 2.6632 top1_acc: 0.2812 top5_acc: 0.6562 loss_cls: 2.6632 2023/02/18 01:06:48 - mmengine - INFO - Epoch(train) [5][300/660] lr: 1.0000e-02 eta: 5:23:29 time: 0.6254 data_time: 0.0331 memory: 42708 grad_norm: 3.5013 loss: 2.7952 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.7952 2023/02/18 01:07:00 - mmengine - INFO - Epoch(train) [5][320/660] lr: 1.0000e-02 eta: 5:23:10 time: 0.6169 data_time: 0.0264 memory: 42708 grad_norm: 3.4735 loss: 2.8132 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.8132 2023/02/18 01:07:12 - mmengine - INFO - Epoch(train) [5][340/660] lr: 1.0000e-02 eta: 5:22:54 time: 0.6295 data_time: 0.0321 memory: 42708 grad_norm: 3.4951 loss: 2.8614 top1_acc: 0.1562 top5_acc: 0.3750 loss_cls: 2.8614 2023/02/18 01:07:25 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:07:25 - mmengine - INFO - Epoch(train) [5][360/660] lr: 1.0000e-02 eta: 5:22:36 time: 0.6186 data_time: 0.0280 memory: 42708 grad_norm: 3.4393 loss: 2.6146 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.6146 2023/02/18 01:07:37 - mmengine - INFO - Epoch(train) [5][380/660] lr: 1.0000e-02 eta: 5:22:19 time: 0.6253 data_time: 0.0304 memory: 42708 grad_norm: 3.5492 loss: 2.7322 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.7322 2023/02/18 01:07:50 - mmengine - INFO - Epoch(train) [5][400/660] lr: 1.0000e-02 eta: 5:22:01 time: 0.6187 data_time: 0.0306 memory: 42708 grad_norm: 3.4768 loss: 2.7636 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.7636 2023/02/18 01:08:02 - mmengine - INFO - Epoch(train) [5][420/660] lr: 1.0000e-02 eta: 5:21:44 time: 0.6283 data_time: 0.0308 memory: 42708 grad_norm: 3.4781 loss: 2.6817 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6817 2023/02/18 01:08:15 - mmengine - INFO - Epoch(train) [5][440/660] lr: 1.0000e-02 eta: 5:21:26 time: 0.6183 data_time: 0.0281 memory: 42708 grad_norm: 3.5043 loss: 2.8330 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.8330 2023/02/18 01:08:27 - mmengine - INFO - Epoch(train) [5][460/660] lr: 1.0000e-02 eta: 5:21:09 time: 0.6225 data_time: 0.0317 memory: 42708 grad_norm: 3.4635 loss: 2.6195 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.6195 2023/02/18 01:08:40 - mmengine - INFO - Epoch(train) [5][480/660] lr: 1.0000e-02 eta: 5:20:56 time: 0.6444 data_time: 0.0301 memory: 42708 grad_norm: 3.4791 loss: 2.5879 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.5879 2023/02/18 01:08:53 - mmengine - INFO - Epoch(train) [5][500/660] lr: 1.0000e-02 eta: 5:20:41 time: 0.6328 data_time: 0.0378 memory: 42708 grad_norm: 3.5188 loss: 2.9197 top1_acc: 0.1562 top5_acc: 0.5625 loss_cls: 2.9197 2023/02/18 01:09:05 - mmengine - INFO - Epoch(train) [5][520/660] lr: 1.0000e-02 eta: 5:20:24 time: 0.6228 data_time: 0.0272 memory: 42708 grad_norm: 3.5211 loss: 2.8347 top1_acc: 0.1875 top5_acc: 0.5312 loss_cls: 2.8347 2023/02/18 01:09:18 - mmengine - INFO - Epoch(train) [5][540/660] lr: 1.0000e-02 eta: 5:20:09 time: 0.6326 data_time: 0.0321 memory: 42708 grad_norm: 3.5096 loss: 2.6192 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.6192 2023/02/18 01:09:30 - mmengine - INFO - Epoch(train) [5][560/660] lr: 1.0000e-02 eta: 5:19:51 time: 0.6174 data_time: 0.0261 memory: 42708 grad_norm: 3.4793 loss: 2.8502 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.8502 2023/02/18 01:09:43 - mmengine - INFO - Epoch(train) [5][580/660] lr: 1.0000e-02 eta: 5:19:35 time: 0.6232 data_time: 0.0314 memory: 42708 grad_norm: 3.5214 loss: 2.7274 top1_acc: 0.3125 top5_acc: 0.5312 loss_cls: 2.7274 2023/02/18 01:09:55 - mmengine - INFO - Epoch(train) [5][600/660] lr: 1.0000e-02 eta: 5:19:16 time: 0.6154 data_time: 0.0270 memory: 42708 grad_norm: 3.4286 loss: 2.5789 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 2.5789 2023/02/18 01:10:07 - mmengine - INFO - Epoch(train) [5][620/660] lr: 1.0000e-02 eta: 5:19:00 time: 0.6243 data_time: 0.0310 memory: 42708 grad_norm: 3.5967 loss: 2.5559 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.5559 2023/02/18 01:10:20 - mmengine - INFO - Epoch(train) [5][640/660] lr: 1.0000e-02 eta: 5:18:43 time: 0.6199 data_time: 0.0280 memory: 42708 grad_norm: 3.4930 loss: 2.8250 top1_acc: 0.2812 top5_acc: 0.5625 loss_cls: 2.8250 2023/02/18 01:10:32 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:10:32 - mmengine - INFO - Epoch(train) [5][660/660] lr: 1.0000e-02 eta: 5:18:24 time: 0.6084 data_time: 0.0272 memory: 42708 grad_norm: 3.5349 loss: 2.6862 top1_acc: 0.3333 top5_acc: 0.5926 loss_cls: 2.6862 2023/02/18 01:11:22 - mmengine - INFO - Epoch(val) [5][20/97] eta: 0:03:11 time: 2.4824 data_time: 2.2725 memory: 6154 2023/02/18 01:11:27 - mmengine - INFO - Epoch(val) [5][40/97] eta: 0:01:17 time: 0.2482 data_time: 0.0316 memory: 6154 2023/02/18 01:11:31 - mmengine - INFO - Epoch(val) [5][60/97] eta: 0:00:36 time: 0.2442 data_time: 0.0369 memory: 6154 2023/02/18 01:11:36 - mmengine - INFO - Epoch(val) [5][80/97] eta: 0:00:13 time: 0.2392 data_time: 0.0323 memory: 6154 2023/02/18 01:11:41 - mmengine - INFO - Epoch(val) [5][97/97] acc/top1: 0.2719 acc/top5: 0.5796 acc/mean1: 0.2029 2023/02/18 01:11:41 - mmengine - INFO - The best checkpoint with 0.2719 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2023/02/18 01:11:56 - mmengine - INFO - Epoch(train) [6][ 20/660] lr: 1.0000e-02 eta: 5:18:24 time: 0.7164 data_time: 0.1178 memory: 42708 grad_norm: 3.4665 loss: 2.5629 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5629 2023/02/18 01:12:08 - mmengine - INFO - Epoch(train) [6][ 40/660] lr: 1.0000e-02 eta: 5:18:06 time: 0.6169 data_time: 0.0297 memory: 42708 grad_norm: 3.5438 loss: 2.7296 top1_acc: 0.3125 top5_acc: 0.6562 loss_cls: 2.7296 2023/02/18 01:12:21 - mmengine - INFO - Epoch(train) [6][ 60/660] lr: 1.0000e-02 eta: 5:17:49 time: 0.6199 data_time: 0.0270 memory: 42708 grad_norm: 3.5080 loss: 2.5723 top1_acc: 0.2188 top5_acc: 0.6250 loss_cls: 2.5723 2023/02/18 01:12:33 - mmengine - INFO - Epoch(train) [6][ 80/660] lr: 1.0000e-02 eta: 5:17:31 time: 0.6148 data_time: 0.0240 memory: 42708 grad_norm: 3.5191 loss: 2.6870 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.6870 2023/02/18 01:12:45 - mmengine - INFO - Epoch(train) [6][100/660] lr: 1.0000e-02 eta: 5:17:16 time: 0.6273 data_time: 0.0288 memory: 42708 grad_norm: 3.5235 loss: 2.5652 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.5652 2023/02/18 01:12:58 - mmengine - INFO - Epoch(train) [6][120/660] lr: 1.0000e-02 eta: 5:16:59 time: 0.6229 data_time: 0.0255 memory: 42708 grad_norm: 3.5874 loss: 2.7392 top1_acc: 0.3125 top5_acc: 0.5312 loss_cls: 2.7392 2023/02/18 01:13:10 - mmengine - INFO - Epoch(train) [6][140/660] lr: 1.0000e-02 eta: 5:16:44 time: 0.6300 data_time: 0.0288 memory: 42708 grad_norm: 3.6190 loss: 2.6725 top1_acc: 0.1562 top5_acc: 0.7500 loss_cls: 2.6725 2023/02/18 01:13:23 - mmengine - INFO - Epoch(train) [6][160/660] lr: 1.0000e-02 eta: 5:16:27 time: 0.6154 data_time: 0.0252 memory: 42708 grad_norm: 3.6020 loss: 2.7046 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.7046 2023/02/18 01:13:35 - mmengine - INFO - Epoch(train) [6][180/660] lr: 1.0000e-02 eta: 5:16:12 time: 0.6301 data_time: 0.0331 memory: 42708 grad_norm: 3.5080 loss: 2.5945 top1_acc: 0.4688 top5_acc: 0.6875 loss_cls: 2.5945 2023/02/18 01:13:48 - mmengine - INFO - Epoch(train) [6][200/660] lr: 1.0000e-02 eta: 5:15:55 time: 0.6204 data_time: 0.0257 memory: 42708 grad_norm: 3.5341 loss: 2.6866 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.6866 2023/02/18 01:14:00 - mmengine - INFO - Epoch(train) [6][220/660] lr: 1.0000e-02 eta: 5:15:41 time: 0.6338 data_time: 0.0297 memory: 42708 grad_norm: 3.5955 loss: 2.7642 top1_acc: 0.2188 top5_acc: 0.5312 loss_cls: 2.7642 2023/02/18 01:14:13 - mmengine - INFO - Epoch(train) [6][240/660] lr: 1.0000e-02 eta: 5:15:25 time: 0.6232 data_time: 0.0255 memory: 42708 grad_norm: 3.5511 loss: 2.6297 top1_acc: 0.2812 top5_acc: 0.5938 loss_cls: 2.6297 2023/02/18 01:14:25 - mmengine - INFO - Epoch(train) [6][260/660] lr: 1.0000e-02 eta: 5:15:09 time: 0.6273 data_time: 0.0288 memory: 42708 grad_norm: 3.5145 loss: 2.8241 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 2.8241 2023/02/18 01:14:38 - mmengine - INFO - Epoch(train) [6][280/660] lr: 1.0000e-02 eta: 5:14:52 time: 0.6146 data_time: 0.0255 memory: 42708 grad_norm: 3.5576 loss: 2.6288 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.6288 2023/02/18 01:14:50 - mmengine - INFO - Epoch(train) [6][300/660] lr: 1.0000e-02 eta: 5:14:37 time: 0.6259 data_time: 0.0298 memory: 42708 grad_norm: 3.5738 loss: 2.6562 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.6562 2023/02/18 01:15:03 - mmengine - INFO - Epoch(train) [6][320/660] lr: 1.0000e-02 eta: 5:14:20 time: 0.6193 data_time: 0.0308 memory: 42708 grad_norm: 3.5507 loss: 2.6906 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6906 2023/02/18 01:15:15 - mmengine - INFO - Epoch(train) [6][340/660] lr: 1.0000e-02 eta: 5:14:05 time: 0.6257 data_time: 0.0289 memory: 42708 grad_norm: 3.5589 loss: 2.6120 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.6120 2023/02/18 01:15:28 - mmengine - INFO - Epoch(train) [6][360/660] lr: 1.0000e-02 eta: 5:13:48 time: 0.6219 data_time: 0.0279 memory: 42708 grad_norm: 3.6001 loss: 2.6823 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.6823 2023/02/18 01:15:40 - mmengine - INFO - Epoch(train) [6][380/660] lr: 1.0000e-02 eta: 5:13:33 time: 0.6267 data_time: 0.0288 memory: 42708 grad_norm: 3.6126 loss: 2.8287 top1_acc: 0.2500 top5_acc: 0.5312 loss_cls: 2.8287 2023/02/18 01:15:52 - mmengine - INFO - Epoch(train) [6][400/660] lr: 1.0000e-02 eta: 5:13:16 time: 0.6144 data_time: 0.0259 memory: 42708 grad_norm: 3.5900 loss: 2.6208 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 2.6208 2023/02/18 01:16:05 - mmengine - INFO - Epoch(train) [6][420/660] lr: 1.0000e-02 eta: 5:13:01 time: 0.6277 data_time: 0.0287 memory: 42708 grad_norm: 3.5101 loss: 2.6132 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.6132 2023/02/18 01:16:17 - mmengine - INFO - Epoch(train) [6][440/660] lr: 1.0000e-02 eta: 5:12:45 time: 0.6185 data_time: 0.0262 memory: 42708 grad_norm: 3.5908 loss: 2.6352 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.6352 2023/02/18 01:16:30 - mmengine - INFO - Epoch(train) [6][460/660] lr: 1.0000e-02 eta: 5:12:30 time: 0.6275 data_time: 0.0282 memory: 42708 grad_norm: 3.5702 loss: 2.5927 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5927 2023/02/18 01:16:42 - mmengine - INFO - Epoch(train) [6][480/660] lr: 1.0000e-02 eta: 5:12:13 time: 0.6155 data_time: 0.0256 memory: 42708 grad_norm: 3.6109 loss: 2.6605 top1_acc: 0.3438 top5_acc: 0.5625 loss_cls: 2.6605 2023/02/18 01:16:55 - mmengine - INFO - Epoch(train) [6][500/660] lr: 1.0000e-02 eta: 5:11:57 time: 0.6244 data_time: 0.0292 memory: 42708 grad_norm: 3.6595 loss: 2.6779 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 2.6779 2023/02/18 01:17:07 - mmengine - INFO - Epoch(train) [6][520/660] lr: 1.0000e-02 eta: 5:11:41 time: 0.6146 data_time: 0.0287 memory: 42708 grad_norm: 3.6179 loss: 2.6769 top1_acc: 0.2188 top5_acc: 0.5625 loss_cls: 2.6769 2023/02/18 01:17:19 - mmengine - INFO - Epoch(train) [6][540/660] lr: 1.0000e-02 eta: 5:11:25 time: 0.6237 data_time: 0.0309 memory: 42708 grad_norm: 3.6262 loss: 2.6652 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 2.6652 2023/02/18 01:17:32 - mmengine - INFO - Epoch(train) [6][560/660] lr: 1.0000e-02 eta: 5:11:09 time: 0.6192 data_time: 0.0249 memory: 42708 grad_norm: 3.6430 loss: 2.7277 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.7277 2023/02/18 01:17:44 - mmengine - INFO - Epoch(train) [6][580/660] lr: 1.0000e-02 eta: 5:10:54 time: 0.6255 data_time: 0.0296 memory: 42708 grad_norm: 3.5886 loss: 2.6283 top1_acc: 0.2812 top5_acc: 0.6250 loss_cls: 2.6283 2023/02/18 01:17:57 - mmengine - INFO - Epoch(train) [6][600/660] lr: 1.0000e-02 eta: 5:10:38 time: 0.6165 data_time: 0.0293 memory: 42708 grad_norm: 3.6196 loss: 2.7172 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.7172 2023/02/18 01:18:09 - mmengine - INFO - Epoch(train) [6][620/660] lr: 1.0000e-02 eta: 5:10:23 time: 0.6253 data_time: 0.0337 memory: 42708 grad_norm: 3.5820 loss: 2.7185 top1_acc: 0.2188 top5_acc: 0.6875 loss_cls: 2.7185 2023/02/18 01:18:22 - mmengine - INFO - Epoch(train) [6][640/660] lr: 1.0000e-02 eta: 5:10:06 time: 0.6172 data_time: 0.0249 memory: 42708 grad_norm: 3.6230 loss: 2.7392 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.7392 2023/02/18 01:18:34 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:18:34 - mmengine - INFO - Epoch(train) [6][660/660] lr: 1.0000e-02 eta: 5:09:49 time: 0.6109 data_time: 0.0256 memory: 42708 grad_norm: 3.6563 loss: 2.7943 top1_acc: 0.3704 top5_acc: 0.6667 loss_cls: 2.7943 2023/02/18 01:18:34 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/02/18 01:18:49 - mmengine - INFO - Epoch(train) [7][ 20/660] lr: 1.0000e-02 eta: 5:09:47 time: 0.7111 data_time: 0.1146 memory: 42708 grad_norm: 3.5599 loss: 2.6392 top1_acc: 0.2812 top5_acc: 0.5938 loss_cls: 2.6392 2023/02/18 01:19:03 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:19:03 - mmengine - INFO - Epoch(train) [7][ 40/660] lr: 1.0000e-02 eta: 5:09:40 time: 0.6829 data_time: 0.0295 memory: 42708 grad_norm: 3.5825 loss: 2.4096 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.4096 2023/02/18 01:19:15 - mmengine - INFO - Epoch(train) [7][ 60/660] lr: 1.0000e-02 eta: 5:09:25 time: 0.6262 data_time: 0.0340 memory: 42708 grad_norm: 3.5513 loss: 2.3476 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3476 2023/02/18 01:19:28 - mmengine - INFO - Epoch(train) [7][ 80/660] lr: 1.0000e-02 eta: 5:09:10 time: 0.6223 data_time: 0.0339 memory: 42708 grad_norm: 3.6617 loss: 2.4940 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.4940 2023/02/18 01:19:40 - mmengine - INFO - Epoch(train) [7][100/660] lr: 1.0000e-02 eta: 5:08:56 time: 0.6308 data_time: 0.0351 memory: 42708 grad_norm: 3.5869 loss: 2.6518 top1_acc: 0.3125 top5_acc: 0.5938 loss_cls: 2.6518 2023/02/18 01:19:53 - mmengine - INFO - Epoch(train) [7][120/660] lr: 1.0000e-02 eta: 5:08:40 time: 0.6235 data_time: 0.0283 memory: 42708 grad_norm: 3.6096 loss: 2.5403 top1_acc: 0.2500 top5_acc: 0.5938 loss_cls: 2.5403 2023/02/18 01:20:05 - mmengine - INFO - Epoch(train) [7][140/660] lr: 1.0000e-02 eta: 5:08:27 time: 0.6347 data_time: 0.0334 memory: 42708 grad_norm: 3.6902 loss: 2.6049 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.6049 2023/02/18 01:20:18 - mmengine - INFO - Epoch(train) [7][160/660] lr: 1.0000e-02 eta: 5:08:12 time: 0.6238 data_time: 0.0290 memory: 42708 grad_norm: 3.6551 loss: 2.5998 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.5998 2023/02/18 01:20:30 - mmengine - INFO - Epoch(train) [7][180/660] lr: 1.0000e-02 eta: 5:07:57 time: 0.6247 data_time: 0.0331 memory: 42708 grad_norm: 3.6367 loss: 2.4888 top1_acc: 0.3438 top5_acc: 0.4688 loss_cls: 2.4888 2023/02/18 01:20:43 - mmengine - INFO - Epoch(train) [7][200/660] lr: 1.0000e-02 eta: 5:07:41 time: 0.6209 data_time: 0.0291 memory: 42708 grad_norm: 3.6310 loss: 2.6041 top1_acc: 0.2188 top5_acc: 0.6250 loss_cls: 2.6041 2023/02/18 01:20:55 - mmengine - INFO - Epoch(train) [7][220/660] lr: 1.0000e-02 eta: 5:07:26 time: 0.6272 data_time: 0.0327 memory: 42708 grad_norm: 3.6265 loss: 2.5918 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 2.5918 2023/02/18 01:21:08 - mmengine - INFO - Epoch(train) [7][240/660] lr: 1.0000e-02 eta: 5:07:11 time: 0.6234 data_time: 0.0311 memory: 42708 grad_norm: 3.6785 loss: 2.4703 top1_acc: 0.2500 top5_acc: 0.5000 loss_cls: 2.4703 2023/02/18 01:21:20 - mmengine - INFO - Epoch(train) [7][260/660] lr: 1.0000e-02 eta: 5:06:57 time: 0.6261 data_time: 0.0353 memory: 42708 grad_norm: 3.6640 loss: 2.5064 top1_acc: 0.2812 top5_acc: 0.7500 loss_cls: 2.5064 2023/02/18 01:21:33 - mmengine - INFO - Epoch(train) [7][280/660] lr: 1.0000e-02 eta: 5:06:41 time: 0.6212 data_time: 0.0289 memory: 42708 grad_norm: 3.6608 loss: 2.5079 top1_acc: 0.2812 top5_acc: 0.8125 loss_cls: 2.5079 2023/02/18 01:21:45 - mmengine - INFO - Epoch(train) [7][300/660] lr: 1.0000e-02 eta: 5:06:27 time: 0.6310 data_time: 0.0354 memory: 42708 grad_norm: 3.6671 loss: 2.6057 top1_acc: 0.3125 top5_acc: 0.5938 loss_cls: 2.6057 2023/02/18 01:21:58 - mmengine - INFO - Epoch(train) [7][320/660] lr: 1.0000e-02 eta: 5:06:12 time: 0.6225 data_time: 0.0311 memory: 42708 grad_norm: 3.7308 loss: 2.5782 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.5782 2023/02/18 01:22:10 - mmengine - INFO - Epoch(train) [7][340/660] lr: 1.0000e-02 eta: 5:05:58 time: 0.6288 data_time: 0.0349 memory: 42708 grad_norm: 3.6706 loss: 2.5318 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.5318 2023/02/18 01:22:23 - mmengine - INFO - Epoch(train) [7][360/660] lr: 1.0000e-02 eta: 5:05:44 time: 0.6299 data_time: 0.0280 memory: 42708 grad_norm: 3.6726 loss: 2.4632 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 2.4632 2023/02/18 01:22:36 - mmengine - INFO - Epoch(train) [7][380/660] lr: 1.0000e-02 eta: 5:05:30 time: 0.6310 data_time: 0.0346 memory: 42708 grad_norm: 3.6446 loss: 2.5228 top1_acc: 0.3438 top5_acc: 0.7812 loss_cls: 2.5228 2023/02/18 01:22:48 - mmengine - INFO - Epoch(train) [7][400/660] lr: 1.0000e-02 eta: 5:05:15 time: 0.6224 data_time: 0.0277 memory: 42708 grad_norm: 3.7084 loss: 2.5549 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.5549 2023/02/18 01:23:01 - mmengine - INFO - Epoch(train) [7][420/660] lr: 1.0000e-02 eta: 5:05:01 time: 0.6295 data_time: 0.0354 memory: 42708 grad_norm: 3.6543 loss: 2.4642 top1_acc: 0.3750 top5_acc: 0.5938 loss_cls: 2.4642 2023/02/18 01:23:13 - mmengine - INFO - Epoch(train) [7][440/660] lr: 1.0000e-02 eta: 5:04:46 time: 0.6219 data_time: 0.0284 memory: 42708 grad_norm: 3.6404 loss: 2.6367 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.6367 2023/02/18 01:23:26 - mmengine - INFO - Epoch(train) [7][460/660] lr: 1.0000e-02 eta: 5:04:32 time: 0.6296 data_time: 0.0340 memory: 42708 grad_norm: 3.6848 loss: 2.6174 top1_acc: 0.2188 top5_acc: 0.5625 loss_cls: 2.6174 2023/02/18 01:23:38 - mmengine - INFO - Epoch(train) [7][480/660] lr: 1.0000e-02 eta: 5:04:17 time: 0.6213 data_time: 0.0280 memory: 42708 grad_norm: 3.7107 loss: 2.5754 top1_acc: 0.3438 top5_acc: 0.6250 loss_cls: 2.5754 2023/02/18 01:23:51 - mmengine - INFO - Epoch(train) [7][500/660] lr: 1.0000e-02 eta: 5:04:03 time: 0.6295 data_time: 0.0350 memory: 42708 grad_norm: 3.7209 loss: 2.4406 top1_acc: 0.3438 top5_acc: 0.6250 loss_cls: 2.4406 2023/02/18 01:24:03 - mmengine - INFO - Epoch(train) [7][520/660] lr: 1.0000e-02 eta: 5:03:48 time: 0.6248 data_time: 0.0310 memory: 42708 grad_norm: 3.6770 loss: 2.5306 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 2.5306 2023/02/18 01:24:16 - mmengine - INFO - Epoch(train) [7][540/660] lr: 1.0000e-02 eta: 5:03:35 time: 0.6380 data_time: 0.0348 memory: 42708 grad_norm: 3.6584 loss: 2.5831 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.5831 2023/02/18 01:24:28 - mmengine - INFO - Epoch(train) [7][560/660] lr: 1.0000e-02 eta: 5:03:20 time: 0.6215 data_time: 0.0285 memory: 42708 grad_norm: 3.7832 loss: 2.5333 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.5333 2023/02/18 01:24:41 - mmengine - INFO - Epoch(train) [7][580/660] lr: 1.0000e-02 eta: 5:03:07 time: 0.6359 data_time: 0.0336 memory: 42708 grad_norm: 3.7330 loss: 2.5453 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.5453 2023/02/18 01:24:54 - mmengine - INFO - Epoch(train) [7][600/660] lr: 1.0000e-02 eta: 5:02:53 time: 0.6307 data_time: 0.0294 memory: 42708 grad_norm: 3.6376 loss: 2.5081 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.5081 2023/02/18 01:25:06 - mmengine - INFO - Epoch(train) [7][620/660] lr: 1.0000e-02 eta: 5:02:39 time: 0.6318 data_time: 0.0337 memory: 42708 grad_norm: 3.6563 loss: 2.4168 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.4168 2023/02/18 01:25:19 - mmengine - INFO - Epoch(train) [7][640/660] lr: 1.0000e-02 eta: 5:02:25 time: 0.6238 data_time: 0.0311 memory: 42708 grad_norm: 3.6843 loss: 2.4996 top1_acc: 0.5312 top5_acc: 0.6562 loss_cls: 2.4996 2023/02/18 01:25:31 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:25:31 - mmengine - INFO - Epoch(train) [7][660/660] lr: 1.0000e-02 eta: 5:02:09 time: 0.6139 data_time: 0.0306 memory: 42708 grad_norm: 3.7049 loss: 2.5957 top1_acc: 0.5185 top5_acc: 0.6667 loss_cls: 2.5957 2023/02/18 01:25:46 - mmengine - INFO - Epoch(train) [8][ 20/660] lr: 1.0000e-02 eta: 5:02:06 time: 0.7207 data_time: 0.1090 memory: 42708 grad_norm: 3.6044 loss: 2.4370 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 2.4370 2023/02/18 01:25:58 - mmengine - INFO - Epoch(train) [8][ 40/660] lr: 1.0000e-02 eta: 5:01:51 time: 0.6228 data_time: 0.0314 memory: 42708 grad_norm: 3.6166 loss: 2.4921 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4921 2023/02/18 01:26:11 - mmengine - INFO - Epoch(train) [8][ 60/660] lr: 1.0000e-02 eta: 5:01:40 time: 0.6482 data_time: 0.0345 memory: 42708 grad_norm: 3.6530 loss: 2.3494 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.3494 2023/02/18 01:26:24 - mmengine - INFO - Epoch(train) [8][ 80/660] lr: 1.0000e-02 eta: 5:01:26 time: 0.6302 data_time: 0.0334 memory: 42708 grad_norm: 3.7416 loss: 2.3975 top1_acc: 0.2500 top5_acc: 0.5625 loss_cls: 2.3975 2023/02/18 01:26:36 - mmengine - INFO - Epoch(train) [8][100/660] lr: 1.0000e-02 eta: 5:01:14 time: 0.6446 data_time: 0.0339 memory: 42708 grad_norm: 3.6880 loss: 2.4077 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4077 2023/02/18 01:26:49 - mmengine - INFO - Epoch(train) [8][120/660] lr: 1.0000e-02 eta: 5:00:59 time: 0.6247 data_time: 0.0308 memory: 42708 grad_norm: 3.6878 loss: 2.5613 top1_acc: 0.3438 top5_acc: 0.6250 loss_cls: 2.5613 2023/02/18 01:27:02 - mmengine - INFO - Epoch(train) [8][140/660] lr: 1.0000e-02 eta: 5:00:46 time: 0.6403 data_time: 0.0329 memory: 42708 grad_norm: 3.7780 loss: 2.5568 top1_acc: 0.2812 top5_acc: 0.7188 loss_cls: 2.5568 2023/02/18 01:27:14 - mmengine - INFO - Epoch(train) [8][160/660] lr: 1.0000e-02 eta: 5:00:32 time: 0.6251 data_time: 0.0294 memory: 42708 grad_norm: 3.7057 loss: 2.5312 top1_acc: 0.3750 top5_acc: 0.5938 loss_cls: 2.5312 2023/02/18 01:27:27 - mmengine - INFO - Epoch(train) [8][180/660] lr: 1.0000e-02 eta: 5:00:19 time: 0.6349 data_time: 0.0317 memory: 42708 grad_norm: 3.7200 loss: 2.4300 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.4300 2023/02/18 01:27:40 - mmengine - INFO - Epoch(train) [8][200/660] lr: 1.0000e-02 eta: 5:00:04 time: 0.6255 data_time: 0.0314 memory: 42708 grad_norm: 3.7523 loss: 2.4538 top1_acc: 0.6250 top5_acc: 0.7188 loss_cls: 2.4538 2023/02/18 01:27:52 - mmengine - INFO - Epoch(train) [8][220/660] lr: 1.0000e-02 eta: 4:59:52 time: 0.6388 data_time: 0.0332 memory: 42708 grad_norm: 3.7559 loss: 2.5002 top1_acc: 0.2188 top5_acc: 0.5312 loss_cls: 2.5002 2023/02/18 01:28:05 - mmengine - INFO - Epoch(train) [8][240/660] lr: 1.0000e-02 eta: 4:59:38 time: 0.6300 data_time: 0.0301 memory: 42708 grad_norm: 3.7602 loss: 2.5935 top1_acc: 0.2812 top5_acc: 0.6562 loss_cls: 2.5935 2023/02/18 01:28:18 - mmengine - INFO - Epoch(train) [8][260/660] lr: 1.0000e-02 eta: 4:59:25 time: 0.6388 data_time: 0.0320 memory: 42708 grad_norm: 3.7685 loss: 2.3946 top1_acc: 0.5312 top5_acc: 0.6875 loss_cls: 2.3946 2023/02/18 01:28:30 - mmengine - INFO - Epoch(train) [8][280/660] lr: 1.0000e-02 eta: 4:59:11 time: 0.6251 data_time: 0.0325 memory: 42708 grad_norm: 3.6666 loss: 2.5513 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.5513 2023/02/18 01:28:43 - mmengine - INFO - Epoch(train) [8][300/660] lr: 1.0000e-02 eta: 4:58:58 time: 0.6404 data_time: 0.0325 memory: 42708 grad_norm: 3.8233 loss: 2.4450 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 2.4450 2023/02/18 01:28:56 - mmengine - INFO - Epoch(train) [8][320/660] lr: 1.0000e-02 eta: 4:58:44 time: 0.6290 data_time: 0.0304 memory: 42708 grad_norm: 3.7312 loss: 2.4676 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4676 2023/02/18 01:29:08 - mmengine - INFO - Epoch(train) [8][340/660] lr: 1.0000e-02 eta: 4:58:32 time: 0.6467 data_time: 0.0346 memory: 42708 grad_norm: 3.6880 loss: 2.5343 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5343 2023/02/18 01:29:21 - mmengine - INFO - Epoch(train) [8][360/660] lr: 1.0000e-02 eta: 4:58:19 time: 0.6316 data_time: 0.0354 memory: 42708 grad_norm: 3.7220 loss: 2.4699 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.4699 2023/02/18 01:29:34 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:29:34 - mmengine - INFO - Epoch(train) [8][380/660] lr: 1.0000e-02 eta: 4:58:07 time: 0.6469 data_time: 0.0366 memory: 42708 grad_norm: 3.6604 loss: 2.4723 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.4723 2023/02/18 01:29:47 - mmengine - INFO - Epoch(train) [8][400/660] lr: 1.0000e-02 eta: 4:57:53 time: 0.6293 data_time: 0.0308 memory: 42708 grad_norm: 3.7267 loss: 2.2926 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2926 2023/02/18 01:29:59 - mmengine - INFO - Epoch(train) [8][420/660] lr: 1.0000e-02 eta: 4:57:41 time: 0.6416 data_time: 0.0335 memory: 42708 grad_norm: 3.7467 loss: 2.4065 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.4065 2023/02/18 01:30:12 - mmengine - INFO - Epoch(train) [8][440/660] lr: 1.0000e-02 eta: 4:57:27 time: 0.6276 data_time: 0.0304 memory: 42708 grad_norm: 3.6859 loss: 2.4045 top1_acc: 0.3438 top5_acc: 0.5000 loss_cls: 2.4045 2023/02/18 01:30:25 - mmengine - INFO - Epoch(train) [8][460/660] lr: 1.0000e-02 eta: 4:57:14 time: 0.6369 data_time: 0.0333 memory: 42708 grad_norm: 3.7543 loss: 2.2947 top1_acc: 0.4062 top5_acc: 0.6250 loss_cls: 2.2947 2023/02/18 01:30:37 - mmengine - INFO - Epoch(train) [8][480/660] lr: 1.0000e-02 eta: 4:56:59 time: 0.6244 data_time: 0.0316 memory: 42708 grad_norm: 3.7367 loss: 2.5821 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.5821 2023/02/18 01:30:50 - mmengine - INFO - Epoch(train) [8][500/660] lr: 1.0000e-02 eta: 4:56:46 time: 0.6369 data_time: 0.0336 memory: 42708 grad_norm: 3.8387 loss: 2.4176 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.4176 2023/02/18 01:31:03 - mmengine - INFO - Epoch(train) [8][520/660] lr: 1.0000e-02 eta: 4:56:32 time: 0.6252 data_time: 0.0316 memory: 42708 grad_norm: 3.7240 loss: 2.3661 top1_acc: 0.2500 top5_acc: 0.6562 loss_cls: 2.3661 2023/02/18 01:31:15 - mmengine - INFO - Epoch(train) [8][540/660] lr: 1.0000e-02 eta: 4:56:19 time: 0.6410 data_time: 0.0345 memory: 42708 grad_norm: 3.7416 loss: 2.4956 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.4956 2023/02/18 01:31:28 - mmengine - INFO - Epoch(train) [8][560/660] lr: 1.0000e-02 eta: 4:56:06 time: 0.6311 data_time: 0.0299 memory: 42708 grad_norm: 3.6818 loss: 2.3627 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.3627 2023/02/18 01:31:41 - mmengine - INFO - Epoch(train) [8][580/660] lr: 1.0000e-02 eta: 4:55:53 time: 0.6409 data_time: 0.0354 memory: 42708 grad_norm: 3.8228 loss: 2.5378 top1_acc: 0.2812 top5_acc: 0.5625 loss_cls: 2.5378 2023/02/18 01:31:53 - mmengine - INFO - Epoch(train) [8][600/660] lr: 1.0000e-02 eta: 4:55:39 time: 0.6256 data_time: 0.0305 memory: 42708 grad_norm: 3.7492 loss: 2.6291 top1_acc: 0.4375 top5_acc: 0.5938 loss_cls: 2.6291 2023/02/18 01:32:06 - mmengine - INFO - Epoch(train) [8][620/660] lr: 1.0000e-02 eta: 4:55:27 time: 0.6470 data_time: 0.0334 memory: 42708 grad_norm: 3.7572 loss: 2.4756 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.4756 2023/02/18 01:32:19 - mmengine - INFO - Epoch(train) [8][640/660] lr: 1.0000e-02 eta: 4:55:14 time: 0.6299 data_time: 0.0330 memory: 42708 grad_norm: 3.8083 loss: 2.6117 top1_acc: 0.3125 top5_acc: 0.5625 loss_cls: 2.6117 2023/02/18 01:32:31 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:32:31 - mmengine - INFO - Epoch(train) [8][660/660] lr: 1.0000e-02 eta: 4:54:59 time: 0.6206 data_time: 0.0324 memory: 42708 grad_norm: 3.7806 loss: 2.4151 top1_acc: 0.3333 top5_acc: 0.6296 loss_cls: 2.4151 2023/02/18 01:32:46 - mmengine - INFO - Epoch(train) [9][ 20/660] lr: 1.0000e-02 eta: 4:54:55 time: 0.7206 data_time: 0.1182 memory: 42708 grad_norm: 3.7060 loss: 2.3279 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3279 2023/02/18 01:32:58 - mmengine - INFO - Epoch(train) [9][ 40/660] lr: 1.0000e-02 eta: 4:54:40 time: 0.6194 data_time: 0.0297 memory: 42708 grad_norm: 3.6920 loss: 2.3778 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.3778 2023/02/18 01:33:11 - mmengine - INFO - Epoch(train) [9][ 60/660] lr: 1.0000e-02 eta: 4:54:27 time: 0.6333 data_time: 0.0328 memory: 42708 grad_norm: 3.7156 loss: 2.3201 top1_acc: 0.3438 top5_acc: 0.8750 loss_cls: 2.3201 2023/02/18 01:33:23 - mmengine - INFO - Epoch(train) [9][ 80/660] lr: 1.0000e-02 eta: 4:54:13 time: 0.6277 data_time: 0.0309 memory: 42708 grad_norm: 3.8444 loss: 2.3369 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.3369 2023/02/18 01:33:36 - mmengine - INFO - Epoch(train) [9][100/660] lr: 1.0000e-02 eta: 4:54:00 time: 0.6373 data_time: 0.0321 memory: 42708 grad_norm: 3.8236 loss: 2.3678 top1_acc: 0.5625 top5_acc: 0.6875 loss_cls: 2.3678 2023/02/18 01:33:49 - mmengine - INFO - Epoch(train) [9][120/660] lr: 1.0000e-02 eta: 4:53:46 time: 0.6311 data_time: 0.0313 memory: 42708 grad_norm: 3.7373 loss: 2.5040 top1_acc: 0.2812 top5_acc: 0.6875 loss_cls: 2.5040 2023/02/18 01:34:02 - mmengine - INFO - Epoch(train) [9][140/660] lr: 1.0000e-02 eta: 4:53:35 time: 0.6486 data_time: 0.0345 memory: 42708 grad_norm: 3.8253 loss: 2.4525 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.4525 2023/02/18 01:34:14 - mmengine - INFO - Epoch(train) [9][160/660] lr: 1.0000e-02 eta: 4:53:21 time: 0.6327 data_time: 0.0306 memory: 42708 grad_norm: 3.7862 loss: 2.5024 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.5024 2023/02/18 01:34:27 - mmengine - INFO - Epoch(train) [9][180/660] lr: 1.0000e-02 eta: 4:53:09 time: 0.6494 data_time: 0.0332 memory: 42708 grad_norm: 3.7772 loss: 2.3519 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.3519 2023/02/18 01:34:40 - mmengine - INFO - Epoch(train) [9][200/660] lr: 1.0000e-02 eta: 4:52:56 time: 0.6287 data_time: 0.0320 memory: 42708 grad_norm: 3.8238 loss: 2.2846 top1_acc: 0.3750 top5_acc: 0.6250 loss_cls: 2.2846 2023/02/18 01:34:53 - mmengine - INFO - Epoch(train) [9][220/660] lr: 1.0000e-02 eta: 4:52:44 time: 0.6498 data_time: 0.0353 memory: 42708 grad_norm: 3.7823 loss: 2.3038 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.3038 2023/02/18 01:35:05 - mmengine - INFO - Epoch(train) [9][240/660] lr: 1.0000e-02 eta: 4:52:31 time: 0.6328 data_time: 0.0308 memory: 42708 grad_norm: 3.8575 loss: 2.4863 top1_acc: 0.1875 top5_acc: 0.6875 loss_cls: 2.4863 2023/02/18 01:35:18 - mmengine - INFO - Epoch(train) [9][260/660] lr: 1.0000e-02 eta: 4:52:18 time: 0.6427 data_time: 0.0328 memory: 42708 grad_norm: 3.8582 loss: 2.3397 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 2.3397 2023/02/18 01:35:31 - mmengine - INFO - Epoch(train) [9][280/660] lr: 1.0000e-02 eta: 4:52:05 time: 0.6301 data_time: 0.0309 memory: 42708 grad_norm: 3.7681 loss: 2.3523 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 2.3523 2023/02/18 01:35:44 - mmengine - INFO - Epoch(train) [9][300/660] lr: 1.0000e-02 eta: 4:51:53 time: 0.6492 data_time: 0.0340 memory: 42708 grad_norm: 3.7496 loss: 2.2543 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.2543 2023/02/18 01:35:57 - mmengine - INFO - Epoch(train) [9][320/660] lr: 1.0000e-02 eta: 4:51:39 time: 0.6287 data_time: 0.0306 memory: 42708 grad_norm: 3.8294 loss: 2.3710 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 2.3710 2023/02/18 01:36:09 - mmengine - INFO - Epoch(train) [9][340/660] lr: 1.0000e-02 eta: 4:51:27 time: 0.6471 data_time: 0.0346 memory: 42708 grad_norm: 3.7889 loss: 2.3369 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 2.3369 2023/02/18 01:36:22 - mmengine - INFO - Epoch(train) [9][360/660] lr: 1.0000e-02 eta: 4:51:14 time: 0.6316 data_time: 0.0303 memory: 42708 grad_norm: 3.8309 loss: 2.3740 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.3740 2023/02/18 01:36:35 - mmengine - INFO - Epoch(train) [9][380/660] lr: 1.0000e-02 eta: 4:51:02 time: 0.6450 data_time: 0.0341 memory: 42708 grad_norm: 3.8244 loss: 2.4346 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.4346 2023/02/18 01:36:48 - mmengine - INFO - Epoch(train) [9][400/660] lr: 1.0000e-02 eta: 4:50:48 time: 0.6296 data_time: 0.0324 memory: 42708 grad_norm: 3.7202 loss: 2.3753 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 2.3753 2023/02/18 01:37:00 - mmengine - INFO - Epoch(train) [9][420/660] lr: 1.0000e-02 eta: 4:50:36 time: 0.6428 data_time: 0.0344 memory: 42708 grad_norm: 3.7754 loss: 2.3039 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.3039 2023/02/18 01:37:13 - mmengine - INFO - Epoch(train) [9][440/660] lr: 1.0000e-02 eta: 4:50:22 time: 0.6266 data_time: 0.0294 memory: 42708 grad_norm: 3.9110 loss: 2.3315 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.3315 2023/02/18 01:37:26 - mmengine - INFO - Epoch(train) [9][460/660] lr: 1.0000e-02 eta: 4:50:09 time: 0.6411 data_time: 0.0366 memory: 42708 grad_norm: 3.8792 loss: 2.3478 top1_acc: 0.2812 top5_acc: 0.5938 loss_cls: 2.3478 2023/02/18 01:37:38 - mmengine - INFO - Epoch(train) [9][480/660] lr: 1.0000e-02 eta: 4:49:56 time: 0.6334 data_time: 0.0318 memory: 42708 grad_norm: 3.8646 loss: 2.4637 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 2.4637 2023/02/18 01:37:51 - mmengine - INFO - Epoch(train) [9][500/660] lr: 1.0000e-02 eta: 4:49:44 time: 0.6437 data_time: 0.0327 memory: 42708 grad_norm: 3.9447 loss: 2.4128 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 2.4128 2023/02/18 01:38:04 - mmengine - INFO - Epoch(train) [9][520/660] lr: 1.0000e-02 eta: 4:49:31 time: 0.6398 data_time: 0.0298 memory: 42708 grad_norm: 3.8565 loss: 2.2691 top1_acc: 0.4688 top5_acc: 0.5938 loss_cls: 2.2691 2023/02/18 01:38:17 - mmengine - INFO - Epoch(train) [9][540/660] lr: 1.0000e-02 eta: 4:49:19 time: 0.6514 data_time: 0.0359 memory: 42708 grad_norm: 3.8359 loss: 2.4299 top1_acc: 0.3438 top5_acc: 0.8125 loss_cls: 2.4299 2023/02/18 01:38:30 - mmengine - INFO - Epoch(train) [9][560/660] lr: 1.0000e-02 eta: 4:49:06 time: 0.6345 data_time: 0.0309 memory: 42708 grad_norm: 3.8216 loss: 2.3312 top1_acc: 0.2188 top5_acc: 0.7812 loss_cls: 2.3312 2023/02/18 01:38:43 - mmengine - INFO - Epoch(train) [9][580/660] lr: 1.0000e-02 eta: 4:48:54 time: 0.6454 data_time: 0.0349 memory: 42708 grad_norm: 3.8386 loss: 2.2815 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 2.2815 2023/02/18 01:38:55 - mmengine - INFO - Epoch(train) [9][600/660] lr: 1.0000e-02 eta: 4:48:41 time: 0.6368 data_time: 0.0309 memory: 42708 grad_norm: 3.8709 loss: 2.2107 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 2.2107 2023/02/18 01:39:08 - mmengine - INFO - Epoch(train) [9][620/660] lr: 1.0000e-02 eta: 4:48:29 time: 0.6419 data_time: 0.0335 memory: 42708 grad_norm: 3.7730 loss: 2.4065 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.4065 2023/02/18 01:39:21 - mmengine - INFO - Epoch(train) [9][640/660] lr: 1.0000e-02 eta: 4:48:15 time: 0.6315 data_time: 0.0298 memory: 42708 grad_norm: 3.8732 loss: 2.3054 top1_acc: 0.2188 top5_acc: 0.6562 loss_cls: 2.3054 2023/02/18 01:39:33 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:39:33 - mmengine - INFO - Epoch(train) [9][660/660] lr: 1.0000e-02 eta: 4:48:00 time: 0.6149 data_time: 0.0302 memory: 42708 grad_norm: 3.8924 loss: 2.3719 top1_acc: 0.3333 top5_acc: 0.7407 loss_cls: 2.3719 2023/02/18 01:39:33 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/02/18 01:39:49 - mmengine - INFO - Epoch(train) [10][ 20/660] lr: 1.0000e-02 eta: 4:47:54 time: 0.7134 data_time: 0.1131 memory: 42708 grad_norm: 3.8073 loss: 2.2590 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.2590 2023/02/18 01:40:01 - mmengine - INFO - Epoch(train) [10][ 40/660] lr: 1.0000e-02 eta: 4:47:40 time: 0.6202 data_time: 0.0257 memory: 42708 grad_norm: 3.7414 loss: 2.3171 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.3171 2023/02/18 01:40:14 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:40:14 - mmengine - INFO - Epoch(train) [10][ 60/660] lr: 1.0000e-02 eta: 4:47:26 time: 0.6272 data_time: 0.0284 memory: 42708 grad_norm: 3.8298 loss: 2.4028 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 2.4028 2023/02/18 01:40:26 - mmengine - INFO - Epoch(train) [10][ 80/660] lr: 1.0000e-02 eta: 4:47:11 time: 0.6198 data_time: 0.0261 memory: 42708 grad_norm: 3.8277 loss: 2.3202 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.3202 2023/02/18 01:40:39 - mmengine - INFO - Epoch(train) [10][100/660] lr: 1.0000e-02 eta: 4:46:58 time: 0.6332 data_time: 0.0282 memory: 42708 grad_norm: 3.8576 loss: 2.2040 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 2.2040 2023/02/18 01:40:51 - mmengine - INFO - Epoch(train) [10][120/660] lr: 1.0000e-02 eta: 4:46:44 time: 0.6244 data_time: 0.0282 memory: 42708 grad_norm: 3.8042 loss: 2.1901 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.1901 2023/02/18 01:41:04 - mmengine - INFO - Epoch(train) [10][140/660] lr: 1.0000e-02 eta: 4:46:31 time: 0.6304 data_time: 0.0282 memory: 42708 grad_norm: 3.8087 loss: 2.3792 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.3792 2023/02/18 01:41:16 - mmengine - INFO - Epoch(train) [10][160/660] lr: 1.0000e-02 eta: 4:46:17 time: 0.6269 data_time: 0.0276 memory: 42708 grad_norm: 3.8647 loss: 2.5024 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.5024 2023/02/18 01:41:29 - mmengine - INFO - Epoch(train) [10][180/660] lr: 1.0000e-02 eta: 4:46:04 time: 0.6368 data_time: 0.0298 memory: 42708 grad_norm: 3.8576 loss: 2.4152 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 2.4152 2023/02/18 01:41:42 - mmengine - INFO - Epoch(train) [10][200/660] lr: 1.0000e-02 eta: 4:45:50 time: 0.6277 data_time: 0.0291 memory: 42708 grad_norm: 3.8807 loss: 2.2754 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.2754 2023/02/18 01:41:54 - mmengine - INFO - Epoch(train) [10][220/660] lr: 1.0000e-02 eta: 4:45:37 time: 0.6339 data_time: 0.0330 memory: 42708 grad_norm: 3.8748 loss: 2.3418 top1_acc: 0.4375 top5_acc: 0.5938 loss_cls: 2.3418 2023/02/18 01:42:07 - mmengine - INFO - Epoch(train) [10][240/660] lr: 1.0000e-02 eta: 4:45:24 time: 0.6353 data_time: 0.0312 memory: 42708 grad_norm: 3.7611 loss: 2.2753 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.2753 2023/02/18 01:42:20 - mmengine - INFO - Epoch(train) [10][260/660] lr: 1.0000e-02 eta: 4:45:11 time: 0.6391 data_time: 0.0301 memory: 42708 grad_norm: 3.8736 loss: 2.3735 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.3735 2023/02/18 01:42:32 - mmengine - INFO - Epoch(train) [10][280/660] lr: 1.0000e-02 eta: 4:44:58 time: 0.6302 data_time: 0.0303 memory: 42708 grad_norm: 3.8829 loss: 2.3386 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.3386 2023/02/18 01:42:45 - mmengine - INFO - Epoch(train) [10][300/660] lr: 1.0000e-02 eta: 4:44:45 time: 0.6351 data_time: 0.0289 memory: 42708 grad_norm: 3.8371 loss: 2.2376 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.2376 2023/02/18 01:42:58 - mmengine - INFO - Epoch(train) [10][320/660] lr: 1.0000e-02 eta: 4:44:32 time: 0.6362 data_time: 0.0306 memory: 42708 grad_norm: 3.8330 loss: 2.3139 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 2.3139 2023/02/18 01:43:11 - mmengine - INFO - Epoch(train) [10][340/660] lr: 1.0000e-02 eta: 4:44:18 time: 0.6322 data_time: 0.0318 memory: 42708 grad_norm: 3.9028 loss: 2.3247 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 2.3247 2023/02/18 01:43:23 - mmengine - INFO - Epoch(train) [10][360/660] lr: 1.0000e-02 eta: 4:44:05 time: 0.6333 data_time: 0.0317 memory: 42708 grad_norm: 3.8515 loss: 2.2072 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.2072 2023/02/18 01:43:36 - mmengine - INFO - Epoch(train) [10][380/660] lr: 1.0000e-02 eta: 4:43:52 time: 0.6369 data_time: 0.0300 memory: 42708 grad_norm: 3.8601 loss: 2.2422 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 2.2422 2023/02/18 01:43:49 - mmengine - INFO - Epoch(train) [10][400/660] lr: 1.0000e-02 eta: 4:43:39 time: 0.6295 data_time: 0.0316 memory: 42708 grad_norm: 3.8710 loss: 2.3339 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.3339 2023/02/18 01:44:01 - mmengine - INFO - Epoch(train) [10][420/660] lr: 1.0000e-02 eta: 4:43:26 time: 0.6337 data_time: 0.0305 memory: 42708 grad_norm: 3.8888 loss: 2.2260 top1_acc: 0.4688 top5_acc: 0.6875 loss_cls: 2.2260 2023/02/18 01:44:14 - mmengine - INFO - Epoch(train) [10][440/660] lr: 1.0000e-02 eta: 4:43:12 time: 0.6336 data_time: 0.0329 memory: 42708 grad_norm: 3.9525 loss: 2.3044 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.3044 2023/02/18 01:44:27 - mmengine - INFO - Epoch(train) [10][460/660] lr: 1.0000e-02 eta: 4:43:00 time: 0.6394 data_time: 0.0302 memory: 42708 grad_norm: 3.8789 loss: 2.3355 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 2.3355 2023/02/18 01:44:39 - mmengine - INFO - Epoch(train) [10][480/660] lr: 1.0000e-02 eta: 4:42:47 time: 0.6373 data_time: 0.0316 memory: 42708 grad_norm: 3.9447 loss: 2.3857 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3857 2023/02/18 01:44:52 - mmengine - INFO - Epoch(train) [10][500/660] lr: 1.0000e-02 eta: 4:42:34 time: 0.6376 data_time: 0.0299 memory: 42708 grad_norm: 3.8648 loss: 2.3791 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.3791 2023/02/18 01:45:05 - mmengine - INFO - Epoch(train) [10][520/660] lr: 1.0000e-02 eta: 4:42:21 time: 0.6337 data_time: 0.0322 memory: 42708 grad_norm: 3.8689 loss: 2.3631 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 2.3631 2023/02/18 01:45:18 - mmengine - INFO - Epoch(train) [10][540/660] lr: 1.0000e-02 eta: 4:42:08 time: 0.6366 data_time: 0.0271 memory: 42708 grad_norm: 3.8985 loss: 2.3527 top1_acc: 0.2812 top5_acc: 0.6562 loss_cls: 2.3527 2023/02/18 01:45:30 - mmengine - INFO - Epoch(train) [10][560/660] lr: 1.0000e-02 eta: 4:41:55 time: 0.6339 data_time: 0.0316 memory: 42708 grad_norm: 3.8454 loss: 2.2420 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.2420 2023/02/18 01:45:43 - mmengine - INFO - Epoch(train) [10][580/660] lr: 1.0000e-02 eta: 4:41:42 time: 0.6357 data_time: 0.0279 memory: 42708 grad_norm: 3.8766 loss: 2.3675 top1_acc: 0.4062 top5_acc: 0.6250 loss_cls: 2.3675 2023/02/18 01:45:56 - mmengine - INFO - Epoch(train) [10][600/660] lr: 1.0000e-02 eta: 4:41:29 time: 0.6346 data_time: 0.0323 memory: 42708 grad_norm: 3.8859 loss: 2.3439 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.3439 2023/02/18 01:46:09 - mmengine - INFO - Epoch(train) [10][620/660] lr: 1.0000e-02 eta: 4:41:16 time: 0.6415 data_time: 0.0291 memory: 42708 grad_norm: 3.8538 loss: 2.1247 top1_acc: 0.3750 top5_acc: 0.7812 loss_cls: 2.1247 2023/02/18 01:46:21 - mmengine - INFO - Epoch(train) [10][640/660] lr: 1.0000e-02 eta: 4:41:04 time: 0.6397 data_time: 0.0327 memory: 42708 grad_norm: 3.8853 loss: 2.1194 top1_acc: 0.4062 top5_acc: 0.5938 loss_cls: 2.1194 2023/02/18 01:46:34 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:46:34 - mmengine - INFO - Epoch(train) [10][660/660] lr: 1.0000e-02 eta: 4:40:50 time: 0.6219 data_time: 0.0276 memory: 42708 grad_norm: 3.9071 loss: 2.3855 top1_acc: 0.3333 top5_acc: 0.5926 loss_cls: 2.3855 2023/02/18 01:46:40 - mmengine - INFO - Epoch(val) [10][20/97] eta: 0:00:25 time: 0.3347 data_time: 0.1211 memory: 6154 2023/02/18 01:46:45 - mmengine - INFO - Epoch(val) [10][40/97] eta: 0:00:16 time: 0.2465 data_time: 0.0321 memory: 6154 2023/02/18 01:46:51 - mmengine - INFO - Epoch(val) [10][60/97] eta: 0:00:10 time: 0.2590 data_time: 0.0451 memory: 6154 2023/02/18 01:46:55 - mmengine - INFO - Epoch(val) [10][80/97] eta: 0:00:04 time: 0.2409 data_time: 0.0330 memory: 6154 2023/02/18 01:47:00 - mmengine - INFO - Epoch(val) [10][97/97] acc/top1: 0.3263 acc/top5: 0.6419 acc/mean1: 0.2559 2023/02/18 01:47:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_5.pth is removed 2023/02/18 01:47:01 - mmengine - INFO - The best checkpoint with 0.3263 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2023/02/18 01:47:15 - mmengine - INFO - Epoch(train) [11][ 20/660] lr: 1.0000e-02 eta: 4:40:43 time: 0.7107 data_time: 0.1155 memory: 42708 grad_norm: 3.8812 loss: 1.9979 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.9979 2023/02/18 01:47:28 - mmengine - INFO - Epoch(train) [11][ 40/660] lr: 1.0000e-02 eta: 4:40:30 time: 0.6394 data_time: 0.0285 memory: 42708 grad_norm: 3.8837 loss: 2.1857 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 2.1857 2023/02/18 01:47:41 - mmengine - INFO - Epoch(train) [11][ 60/660] lr: 1.0000e-02 eta: 4:40:19 time: 0.6608 data_time: 0.0371 memory: 42708 grad_norm: 3.9652 loss: 2.1233 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 2.1233 2023/02/18 01:47:54 - mmengine - INFO - Epoch(train) [11][ 80/660] lr: 1.0000e-02 eta: 4:40:06 time: 0.6348 data_time: 0.0290 memory: 42708 grad_norm: 3.8719 loss: 2.3152 top1_acc: 0.2812 top5_acc: 0.6875 loss_cls: 2.3152 2023/02/18 01:48:07 - mmengine - INFO - Epoch(train) [11][100/660] lr: 1.0000e-02 eta: 4:39:54 time: 0.6540 data_time: 0.0363 memory: 42708 grad_norm: 3.9189 loss: 2.3704 top1_acc: 0.4062 top5_acc: 0.5938 loss_cls: 2.3704 2023/02/18 01:48:19 - mmengine - INFO - Epoch(train) [11][120/660] lr: 1.0000e-02 eta: 4:39:41 time: 0.6366 data_time: 0.0288 memory: 42708 grad_norm: 3.8714 loss: 2.3031 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 2.3031 2023/02/18 01:48:32 - mmengine - INFO - Epoch(train) [11][140/660] lr: 1.0000e-02 eta: 4:39:29 time: 0.6493 data_time: 0.0336 memory: 42708 grad_norm: 3.9413 loss: 2.0890 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 2.0890 2023/02/18 01:48:45 - mmengine - INFO - Epoch(train) [11][160/660] lr: 1.0000e-02 eta: 4:39:17 time: 0.6382 data_time: 0.0293 memory: 42708 grad_norm: 3.9206 loss: 2.1098 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.1098 2023/02/18 01:48:58 - mmengine - INFO - Epoch(train) [11][180/660] lr: 1.0000e-02 eta: 4:39:05 time: 0.6514 data_time: 0.0347 memory: 42708 grad_norm: 3.9520 loss: 2.1275 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 2.1275 2023/02/18 01:49:11 - mmengine - INFO - Epoch(train) [11][200/660] lr: 1.0000e-02 eta: 4:38:52 time: 0.6394 data_time: 0.0296 memory: 42708 grad_norm: 3.9016 loss: 2.2239 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 2.2239 2023/02/18 01:49:24 - mmengine - INFO - Epoch(train) [11][220/660] lr: 1.0000e-02 eta: 4:38:41 time: 0.6576 data_time: 0.0360 memory: 42708 grad_norm: 3.8723 loss: 2.1983 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.1983 2023/02/18 01:49:37 - mmengine - INFO - Epoch(train) [11][240/660] lr: 1.0000e-02 eta: 4:38:28 time: 0.6394 data_time: 0.0363 memory: 42708 grad_norm: 3.9584 loss: 2.3037 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.3037 2023/02/18 01:49:50 - mmengine - INFO - Epoch(train) [11][260/660] lr: 1.0000e-02 eta: 4:38:16 time: 0.6474 data_time: 0.0346 memory: 42708 grad_norm: 3.9595 loss: 2.2443 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.2443 2023/02/18 01:50:02 - mmengine - INFO - Epoch(train) [11][280/660] lr: 1.0000e-02 eta: 4:38:03 time: 0.6300 data_time: 0.0302 memory: 42708 grad_norm: 3.8840 loss: 2.2465 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.2465 2023/02/18 01:50:15 - mmengine - INFO - Epoch(train) [11][300/660] lr: 1.0000e-02 eta: 4:37:51 time: 0.6515 data_time: 0.0334 memory: 42708 grad_norm: 3.8551 loss: 2.3418 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.3418 2023/02/18 01:50:28 - mmengine - INFO - Epoch(train) [11][320/660] lr: 1.0000e-02 eta: 4:37:37 time: 0.6315 data_time: 0.0307 memory: 42708 grad_norm: 3.9998 loss: 2.2476 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 2.2476 2023/02/18 01:50:41 - mmengine - INFO - Epoch(train) [11][340/660] lr: 1.0000e-02 eta: 4:37:26 time: 0.6534 data_time: 0.0334 memory: 42708 grad_norm: 3.8909 loss: 2.3230 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.3230 2023/02/18 01:50:54 - mmengine - INFO - Epoch(train) [11][360/660] lr: 1.0000e-02 eta: 4:37:12 time: 0.6307 data_time: 0.0317 memory: 42708 grad_norm: 3.9876 loss: 2.3148 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.3148 2023/02/18 01:51:07 - mmengine - INFO - Epoch(train) [11][380/660] lr: 1.0000e-02 eta: 4:37:00 time: 0.6464 data_time: 0.0331 memory: 42708 grad_norm: 3.8505 loss: 2.1603 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.1603 2023/02/18 01:51:19 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:51:19 - mmengine - INFO - Epoch(train) [11][400/660] lr: 1.0000e-02 eta: 4:36:47 time: 0.6289 data_time: 0.0309 memory: 42708 grad_norm: 3.8649 loss: 2.2458 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.2458 2023/02/18 01:51:32 - mmengine - INFO - Epoch(train) [11][420/660] lr: 1.0000e-02 eta: 4:36:34 time: 0.6443 data_time: 0.0335 memory: 42708 grad_norm: 3.9652 loss: 2.1555 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 2.1555 2023/02/18 01:51:45 - mmengine - INFO - Epoch(train) [11][440/660] lr: 1.0000e-02 eta: 4:36:21 time: 0.6283 data_time: 0.0287 memory: 42708 grad_norm: 3.9226 loss: 2.2458 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.2458 2023/02/18 01:51:58 - mmengine - INFO - Epoch(train) [11][460/660] lr: 1.0000e-02 eta: 4:36:09 time: 0.6470 data_time: 0.0331 memory: 42708 grad_norm: 3.9428 loss: 2.1896 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.1896 2023/02/18 01:52:10 - mmengine - INFO - Epoch(train) [11][480/660] lr: 1.0000e-02 eta: 4:35:55 time: 0.6323 data_time: 0.0310 memory: 42708 grad_norm: 3.8866 loss: 2.2050 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 2.2050 2023/02/18 01:52:23 - mmengine - INFO - Epoch(train) [11][500/660] lr: 1.0000e-02 eta: 4:35:43 time: 0.6452 data_time: 0.0359 memory: 42708 grad_norm: 3.9806 loss: 2.1437 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1437 2023/02/18 01:52:36 - mmengine - INFO - Epoch(train) [11][520/660] lr: 1.0000e-02 eta: 4:35:30 time: 0.6324 data_time: 0.0290 memory: 42708 grad_norm: 3.9704 loss: 2.2395 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.2395 2023/02/18 01:52:49 - mmengine - INFO - Epoch(train) [11][540/660] lr: 1.0000e-02 eta: 4:35:18 time: 0.6487 data_time: 0.0340 memory: 42708 grad_norm: 4.0028 loss: 2.2187 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.2187 2023/02/18 01:53:01 - mmengine - INFO - Epoch(train) [11][560/660] lr: 1.0000e-02 eta: 4:35:04 time: 0.6304 data_time: 0.0300 memory: 42708 grad_norm: 4.0224 loss: 2.3025 top1_acc: 0.3125 top5_acc: 0.7188 loss_cls: 2.3025 2023/02/18 01:53:14 - mmengine - INFO - Epoch(train) [11][580/660] lr: 1.0000e-02 eta: 4:34:52 time: 0.6510 data_time: 0.0341 memory: 42708 grad_norm: 3.9218 loss: 2.3158 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.3158 2023/02/18 01:53:27 - mmengine - INFO - Epoch(train) [11][600/660] lr: 1.0000e-02 eta: 4:34:39 time: 0.6340 data_time: 0.0298 memory: 42708 grad_norm: 3.9617 loss: 2.2789 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.2789 2023/02/18 01:53:40 - mmengine - INFO - Epoch(train) [11][620/660] lr: 1.0000e-02 eta: 4:34:27 time: 0.6473 data_time: 0.0353 memory: 42708 grad_norm: 3.9171 loss: 2.2622 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.2622 2023/02/18 01:53:53 - mmengine - INFO - Epoch(train) [11][640/660] lr: 1.0000e-02 eta: 4:34:14 time: 0.6312 data_time: 0.0303 memory: 42708 grad_norm: 3.9719 loss: 2.2686 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 2.2686 2023/02/18 01:54:05 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 01:54:05 - mmengine - INFO - Epoch(train) [11][660/660] lr: 1.0000e-02 eta: 4:34:00 time: 0.6221 data_time: 0.0289 memory: 42708 grad_norm: 3.8293 loss: 2.1329 top1_acc: 0.4074 top5_acc: 0.6296 loss_cls: 2.1329 2023/02/18 01:54:20 - mmengine - INFO - Epoch(train) [12][ 20/660] lr: 1.0000e-02 eta: 4:33:54 time: 0.7337 data_time: 0.1173 memory: 42708 grad_norm: 3.9114 loss: 2.0234 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0234 2023/02/18 01:54:32 - mmengine - INFO - Epoch(train) [12][ 40/660] lr: 1.0000e-02 eta: 4:33:40 time: 0.6231 data_time: 0.0261 memory: 42708 grad_norm: 3.8774 loss: 2.2131 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.2131 2023/02/18 01:54:45 - mmengine - INFO - Epoch(train) [12][ 60/660] lr: 1.0000e-02 eta: 4:33:26 time: 0.6287 data_time: 0.0290 memory: 42708 grad_norm: 4.0030 loss: 2.0396 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 2.0396 2023/02/18 01:54:57 - mmengine - INFO - Epoch(train) [12][ 80/660] lr: 1.0000e-02 eta: 4:33:13 time: 0.6218 data_time: 0.0298 memory: 42708 grad_norm: 4.0092 loss: 2.2682 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.2682 2023/02/18 01:55:10 - mmengine - INFO - Epoch(train) [12][100/660] lr: 1.0000e-02 eta: 4:32:59 time: 0.6244 data_time: 0.0274 memory: 42708 grad_norm: 3.9918 loss: 2.2233 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 2.2233 2023/02/18 01:55:22 - mmengine - INFO - Epoch(train) [12][120/660] lr: 1.0000e-02 eta: 4:32:45 time: 0.6180 data_time: 0.0270 memory: 42708 grad_norm: 4.0099 loss: 2.1069 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1069 2023/02/18 01:55:35 - mmengine - INFO - Epoch(train) [12][140/660] lr: 1.0000e-02 eta: 4:32:31 time: 0.6262 data_time: 0.0270 memory: 42708 grad_norm: 3.9318 loss: 2.2306 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.2306 2023/02/18 01:55:47 - mmengine - INFO - Epoch(train) [12][160/660] lr: 1.0000e-02 eta: 4:32:17 time: 0.6200 data_time: 0.0263 memory: 42708 grad_norm: 3.9852 loss: 2.1027 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1027 2023/02/18 01:56:00 - mmengine - INFO - Epoch(train) [12][180/660] lr: 1.0000e-02 eta: 4:32:03 time: 0.6300 data_time: 0.0297 memory: 42708 grad_norm: 4.0336 loss: 2.0881 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.0881 2023/02/18 01:56:12 - mmengine - INFO - Epoch(train) [12][200/660] lr: 1.0000e-02 eta: 4:31:49 time: 0.6176 data_time: 0.0266 memory: 42708 grad_norm: 3.9867 loss: 2.1724 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 2.1724 2023/02/18 01:56:25 - mmengine - INFO - Epoch(train) [12][220/660] lr: 1.0000e-02 eta: 4:31:36 time: 0.6299 data_time: 0.0285 memory: 42708 grad_norm: 3.9511 loss: 2.1535 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.1535 2023/02/18 01:56:37 - mmengine - INFO - Epoch(train) [12][240/660] lr: 1.0000e-02 eta: 4:31:22 time: 0.6239 data_time: 0.0262 memory: 42708 grad_norm: 3.9917 loss: 2.2555 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 2.2555 2023/02/18 01:56:50 - mmengine - INFO - Epoch(train) [12][260/660] lr: 1.0000e-02 eta: 4:31:09 time: 0.6311 data_time: 0.0287 memory: 42708 grad_norm: 4.0173 loss: 2.0596 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 2.0596 2023/02/18 01:57:02 - mmengine - INFO - Epoch(train) [12][280/660] lr: 1.0000e-02 eta: 4:30:55 time: 0.6201 data_time: 0.0271 memory: 42708 grad_norm: 3.9905 loss: 2.1899 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.1899 2023/02/18 01:57:15 - mmengine - INFO - Epoch(train) [12][300/660] lr: 1.0000e-02 eta: 4:30:41 time: 0.6250 data_time: 0.0265 memory: 42708 grad_norm: 3.9778 loss: 2.2126 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 2.2126 2023/02/18 01:57:27 - mmengine - INFO - Epoch(train) [12][320/660] lr: 1.0000e-02 eta: 4:30:27 time: 0.6203 data_time: 0.0260 memory: 42708 grad_norm: 3.9995 loss: 2.3019 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.3019 2023/02/18 01:57:40 - mmengine - INFO - Epoch(train) [12][340/660] lr: 1.0000e-02 eta: 4:30:13 time: 0.6243 data_time: 0.0282 memory: 42708 grad_norm: 4.0470 loss: 2.1147 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 2.1147 2023/02/18 01:57:52 - mmengine - INFO - Epoch(train) [12][360/660] lr: 1.0000e-02 eta: 4:30:00 time: 0.6227 data_time: 0.0338 memory: 42708 grad_norm: 4.0147 loss: 2.2568 top1_acc: 0.3438 top5_acc: 0.5938 loss_cls: 2.2568 2023/02/18 01:58:05 - mmengine - INFO - Epoch(train) [12][380/660] lr: 1.0000e-02 eta: 4:29:46 time: 0.6267 data_time: 0.0298 memory: 42708 grad_norm: 4.0048 loss: 2.1612 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.1612 2023/02/18 01:58:17 - mmengine - INFO - Epoch(train) [12][400/660] lr: 1.0000e-02 eta: 4:29:32 time: 0.6231 data_time: 0.0288 memory: 42708 grad_norm: 3.9920 loss: 2.2669 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 2.2669 2023/02/18 01:58:30 - mmengine - INFO - Epoch(train) [12][420/660] lr: 1.0000e-02 eta: 4:29:19 time: 0.6258 data_time: 0.0297 memory: 42708 grad_norm: 3.9494 loss: 2.1884 top1_acc: 0.4062 top5_acc: 0.6250 loss_cls: 2.1884 2023/02/18 01:58:42 - mmengine - INFO - Epoch(train) [12][440/660] lr: 1.0000e-02 eta: 4:29:05 time: 0.6202 data_time: 0.0305 memory: 42708 grad_norm: 3.9871 loss: 2.1778 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 2.1778 2023/02/18 01:58:54 - mmengine - INFO - Epoch(train) [12][460/660] lr: 1.0000e-02 eta: 4:28:51 time: 0.6271 data_time: 0.0274 memory: 42708 grad_norm: 3.8715 loss: 2.1809 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.1809 2023/02/18 01:59:07 - mmengine - INFO - Epoch(train) [12][480/660] lr: 1.0000e-02 eta: 4:28:37 time: 0.6146 data_time: 0.0286 memory: 42708 grad_norm: 4.0067 loss: 2.2137 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.2137 2023/02/18 01:59:19 - mmengine - INFO - Epoch(train) [12][500/660] lr: 1.0000e-02 eta: 4:28:24 time: 0.6302 data_time: 0.0285 memory: 42708 grad_norm: 3.9875 loss: 2.3342 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.3342 2023/02/18 01:59:32 - mmengine - INFO - Epoch(train) [12][520/660] lr: 1.0000e-02 eta: 4:28:10 time: 0.6171 data_time: 0.0281 memory: 42708 grad_norm: 3.9927 loss: 2.1050 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 2.1050 2023/02/18 01:59:44 - mmengine - INFO - Epoch(train) [12][540/660] lr: 1.0000e-02 eta: 4:27:56 time: 0.6253 data_time: 0.0301 memory: 42708 grad_norm: 3.9579 loss: 2.0737 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0737 2023/02/18 01:59:57 - mmengine - INFO - Epoch(train) [12][560/660] lr: 1.0000e-02 eta: 4:27:42 time: 0.6147 data_time: 0.0271 memory: 42708 grad_norm: 4.1206 loss: 2.1341 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 2.1341 2023/02/18 02:00:09 - mmengine - INFO - Epoch(train) [12][580/660] lr: 1.0000e-02 eta: 4:27:28 time: 0.6198 data_time: 0.0274 memory: 42708 grad_norm: 3.9572 loss: 2.0459 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 2.0459 2023/02/18 02:00:21 - mmengine - INFO - Epoch(train) [12][600/660] lr: 1.0000e-02 eta: 4:27:14 time: 0.6157 data_time: 0.0272 memory: 42708 grad_norm: 4.0676 loss: 2.0347 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0347 2023/02/18 02:00:34 - mmengine - INFO - Epoch(train) [12][620/660] lr: 1.0000e-02 eta: 4:27:00 time: 0.6285 data_time: 0.0302 memory: 42708 grad_norm: 3.9893 loss: 2.1866 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 2.1866 2023/02/18 02:00:46 - mmengine - INFO - Epoch(train) [12][640/660] lr: 1.0000e-02 eta: 4:26:46 time: 0.6188 data_time: 0.0345 memory: 42708 grad_norm: 3.9561 loss: 2.1503 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.1503 2023/02/18 02:00:58 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:00:58 - mmengine - INFO - Epoch(train) [12][660/660] lr: 1.0000e-02 eta: 4:26:32 time: 0.6127 data_time: 0.0269 memory: 42708 grad_norm: 4.0211 loss: 2.1454 top1_acc: 0.4074 top5_acc: 0.6667 loss_cls: 2.1454 2023/02/18 02:00:58 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/02/18 02:01:14 - mmengine - INFO - Epoch(train) [13][ 20/660] lr: 1.0000e-02 eta: 4:26:24 time: 0.7123 data_time: 0.1150 memory: 42708 grad_norm: 3.9983 loss: 2.2048 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.2048 2023/02/18 02:01:26 - mmengine - INFO - Epoch(train) [13][ 40/660] lr: 1.0000e-02 eta: 4:26:10 time: 0.6250 data_time: 0.0291 memory: 42708 grad_norm: 3.9607 loss: 2.0273 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.0273 2023/02/18 02:01:39 - mmengine - INFO - Epoch(train) [13][ 60/660] lr: 1.0000e-02 eta: 4:25:57 time: 0.6262 data_time: 0.0287 memory: 42708 grad_norm: 3.9596 loss: 2.1559 top1_acc: 0.3125 top5_acc: 0.6250 loss_cls: 2.1559 2023/02/18 02:01:51 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:01:51 - mmengine - INFO - Epoch(train) [13][ 80/660] lr: 1.0000e-02 eta: 4:25:43 time: 0.6216 data_time: 0.0297 memory: 42708 grad_norm: 3.9812 loss: 2.1464 top1_acc: 0.4688 top5_acc: 0.6250 loss_cls: 2.1464 2023/02/18 02:02:04 - mmengine - INFO - Epoch(train) [13][100/660] lr: 1.0000e-02 eta: 4:25:30 time: 0.6298 data_time: 0.0299 memory: 42708 grad_norm: 4.0474 loss: 2.1487 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1487 2023/02/18 02:02:16 - mmengine - INFO - Epoch(train) [13][120/660] lr: 1.0000e-02 eta: 4:25:16 time: 0.6241 data_time: 0.0280 memory: 42708 grad_norm: 4.0332 loss: 2.1258 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 2.1258 2023/02/18 02:02:29 - mmengine - INFO - Epoch(train) [13][140/660] lr: 1.0000e-02 eta: 4:25:03 time: 0.6351 data_time: 0.0325 memory: 42708 grad_norm: 4.0375 loss: 2.2137 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 2.2137 2023/02/18 02:02:42 - mmengine - INFO - Epoch(train) [13][160/660] lr: 1.0000e-02 eta: 4:24:50 time: 0.6195 data_time: 0.0257 memory: 42708 grad_norm: 4.0500 loss: 2.0428 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.0428 2023/02/18 02:02:54 - mmengine - INFO - Epoch(train) [13][180/660] lr: 1.0000e-02 eta: 4:24:36 time: 0.6324 data_time: 0.0289 memory: 42708 grad_norm: 4.0537 loss: 2.1419 top1_acc: 0.5000 top5_acc: 0.6250 loss_cls: 2.1419 2023/02/18 02:03:07 - mmengine - INFO - Epoch(train) [13][200/660] lr: 1.0000e-02 eta: 4:24:23 time: 0.6210 data_time: 0.0269 memory: 42708 grad_norm: 4.0866 loss: 2.1941 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.1941 2023/02/18 02:03:19 - mmengine - INFO - Epoch(train) [13][220/660] lr: 1.0000e-02 eta: 4:24:10 time: 0.6373 data_time: 0.0289 memory: 42708 grad_norm: 4.1092 loss: 2.0898 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.0898 2023/02/18 02:03:32 - mmengine - INFO - Epoch(train) [13][240/660] lr: 1.0000e-02 eta: 4:23:56 time: 0.6217 data_time: 0.0299 memory: 42708 grad_norm: 4.0656 loss: 2.0730 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.0730 2023/02/18 02:03:44 - mmengine - INFO - Epoch(train) [13][260/660] lr: 1.0000e-02 eta: 4:23:43 time: 0.6268 data_time: 0.0278 memory: 42708 grad_norm: 4.0015 loss: 2.0676 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0676 2023/02/18 02:03:57 - mmengine - INFO - Epoch(train) [13][280/660] lr: 1.0000e-02 eta: 4:23:29 time: 0.6271 data_time: 0.0279 memory: 42708 grad_norm: 4.1178 loss: 2.0795 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 2.0795 2023/02/18 02:04:10 - mmengine - INFO - Epoch(train) [13][300/660] lr: 1.0000e-02 eta: 4:23:16 time: 0.6343 data_time: 0.0273 memory: 42708 grad_norm: 4.1613 loss: 2.0783 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0783 2023/02/18 02:04:22 - mmengine - INFO - Epoch(train) [13][320/660] lr: 1.0000e-02 eta: 4:23:03 time: 0.6207 data_time: 0.0278 memory: 42708 grad_norm: 4.0411 loss: 2.0820 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0820 2023/02/18 02:04:35 - mmengine - INFO - Epoch(train) [13][340/660] lr: 1.0000e-02 eta: 4:22:50 time: 0.6329 data_time: 0.0287 memory: 42708 grad_norm: 4.0096 loss: 2.0493 top1_acc: 0.6250 top5_acc: 0.7500 loss_cls: 2.0493 2023/02/18 02:04:47 - mmengine - INFO - Epoch(train) [13][360/660] lr: 1.0000e-02 eta: 4:22:36 time: 0.6202 data_time: 0.0286 memory: 42708 grad_norm: 4.0861 loss: 2.1040 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 2.1040 2023/02/18 02:05:00 - mmengine - INFO - Epoch(train) [13][380/660] lr: 1.0000e-02 eta: 4:22:23 time: 0.6324 data_time: 0.0295 memory: 42708 grad_norm: 4.0880 loss: 2.1571 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 2.1571 2023/02/18 02:05:12 - mmengine - INFO - Epoch(train) [13][400/660] lr: 1.0000e-02 eta: 4:22:09 time: 0.6260 data_time: 0.0280 memory: 42708 grad_norm: 4.0694 loss: 2.0663 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0663 2023/02/18 02:05:25 - mmengine - INFO - Epoch(train) [13][420/660] lr: 1.0000e-02 eta: 4:21:57 time: 0.6359 data_time: 0.0296 memory: 42708 grad_norm: 4.0923 loss: 2.1035 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.1035 2023/02/18 02:05:37 - mmengine - INFO - Epoch(train) [13][440/660] lr: 1.0000e-02 eta: 4:21:43 time: 0.6249 data_time: 0.0285 memory: 42708 grad_norm: 4.0227 loss: 2.2016 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 2.2016 2023/02/18 02:05:50 - mmengine - INFO - Epoch(train) [13][460/660] lr: 1.0000e-02 eta: 4:21:30 time: 0.6334 data_time: 0.0277 memory: 42708 grad_norm: 4.0482 loss: 2.1252 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.1252 2023/02/18 02:06:03 - mmengine - INFO - Epoch(train) [13][480/660] lr: 1.0000e-02 eta: 4:21:17 time: 0.6346 data_time: 0.0328 memory: 42708 grad_norm: 4.0699 loss: 2.2331 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 2.2331 2023/02/18 02:06:16 - mmengine - INFO - Epoch(train) [13][500/660] lr: 1.0000e-02 eta: 4:21:05 time: 0.6412 data_time: 0.0286 memory: 42708 grad_norm: 4.0324 loss: 2.0810 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0810 2023/02/18 02:06:28 - mmengine - INFO - Epoch(train) [13][520/660] lr: 1.0000e-02 eta: 4:20:51 time: 0.6226 data_time: 0.0276 memory: 42708 grad_norm: 4.1521 loss: 2.1933 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 2.1933 2023/02/18 02:06:41 - mmengine - INFO - Epoch(train) [13][540/660] lr: 1.0000e-02 eta: 4:20:38 time: 0.6354 data_time: 0.0281 memory: 42708 grad_norm: 4.0910 loss: 2.1979 top1_acc: 0.4688 top5_acc: 0.6562 loss_cls: 2.1979 2023/02/18 02:06:53 - mmengine - INFO - Epoch(train) [13][560/660] lr: 1.0000e-02 eta: 4:20:25 time: 0.6302 data_time: 0.0280 memory: 42708 grad_norm: 4.0891 loss: 2.0330 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 2.0330 2023/02/18 02:07:06 - mmengine - INFO - Epoch(train) [13][580/660] lr: 1.0000e-02 eta: 4:20:13 time: 0.6418 data_time: 0.0295 memory: 42708 grad_norm: 4.0965 loss: 2.3207 top1_acc: 0.4375 top5_acc: 0.6250 loss_cls: 2.3207 2023/02/18 02:07:19 - mmengine - INFO - Epoch(train) [13][600/660] lr: 1.0000e-02 eta: 4:19:59 time: 0.6232 data_time: 0.0288 memory: 42708 grad_norm: 4.1307 loss: 2.1334 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.1334 2023/02/18 02:07:31 - mmengine - INFO - Epoch(train) [13][620/660] lr: 1.0000e-02 eta: 4:19:46 time: 0.6323 data_time: 0.0298 memory: 42708 grad_norm: 4.0245 loss: 2.0279 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 2.0279 2023/02/18 02:07:44 - mmengine - INFO - Epoch(train) [13][640/660] lr: 1.0000e-02 eta: 4:19:32 time: 0.6221 data_time: 0.0289 memory: 42708 grad_norm: 4.1103 loss: 2.1492 top1_acc: 0.5625 top5_acc: 0.7188 loss_cls: 2.1492 2023/02/18 02:07:56 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:07:56 - mmengine - INFO - Epoch(train) [13][660/660] lr: 1.0000e-02 eta: 4:19:18 time: 0.6128 data_time: 0.0260 memory: 42708 grad_norm: 4.0391 loss: 2.0816 top1_acc: 0.5556 top5_acc: 0.8148 loss_cls: 2.0816 2023/02/18 02:08:10 - mmengine - INFO - Epoch(train) [14][ 20/660] lr: 1.0000e-02 eta: 4:19:10 time: 0.7200 data_time: 0.1113 memory: 42708 grad_norm: 4.0565 loss: 2.0176 top1_acc: 0.2812 top5_acc: 0.8125 loss_cls: 2.0176 2023/02/18 02:08:23 - mmengine - INFO - Epoch(train) [14][ 40/660] lr: 1.0000e-02 eta: 4:18:57 time: 0.6249 data_time: 0.0276 memory: 42708 grad_norm: 4.0324 loss: 1.9597 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9597 2023/02/18 02:08:36 - mmengine - INFO - Epoch(train) [14][ 60/660] lr: 1.0000e-02 eta: 4:18:44 time: 0.6435 data_time: 0.0284 memory: 42708 grad_norm: 4.0725 loss: 2.0702 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.0702 2023/02/18 02:08:48 - mmengine - INFO - Epoch(train) [14][ 80/660] lr: 1.0000e-02 eta: 4:18:31 time: 0.6193 data_time: 0.0286 memory: 42708 grad_norm: 4.0867 loss: 1.9050 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9050 2023/02/18 02:09:01 - mmengine - INFO - Epoch(train) [14][100/660] lr: 1.0000e-02 eta: 4:18:18 time: 0.6303 data_time: 0.0265 memory: 42708 grad_norm: 4.0862 loss: 2.0289 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 2.0289 2023/02/18 02:09:13 - mmengine - INFO - Epoch(train) [14][120/660] lr: 1.0000e-02 eta: 4:18:04 time: 0.6268 data_time: 0.0311 memory: 42708 grad_norm: 4.1192 loss: 2.0970 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 2.0970 2023/02/18 02:09:26 - mmengine - INFO - Epoch(train) [14][140/660] lr: 1.0000e-02 eta: 4:17:51 time: 0.6290 data_time: 0.0276 memory: 42708 grad_norm: 4.1255 loss: 2.2038 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 2.2038 2023/02/18 02:09:38 - mmengine - INFO - Epoch(train) [14][160/660] lr: 1.0000e-02 eta: 4:17:38 time: 0.6297 data_time: 0.0256 memory: 42708 grad_norm: 4.0923 loss: 2.1140 top1_acc: 0.4688 top5_acc: 0.5312 loss_cls: 2.1140 2023/02/18 02:09:51 - mmengine - INFO - Epoch(train) [14][180/660] lr: 1.0000e-02 eta: 4:17:25 time: 0.6331 data_time: 0.0297 memory: 42708 grad_norm: 4.0799 loss: 2.0426 top1_acc: 0.3438 top5_acc: 0.8125 loss_cls: 2.0426 2023/02/18 02:10:04 - mmengine - INFO - Epoch(train) [14][200/660] lr: 1.0000e-02 eta: 4:17:11 time: 0.6251 data_time: 0.0260 memory: 42708 grad_norm: 4.1746 loss: 2.0507 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 2.0507 2023/02/18 02:10:16 - mmengine - INFO - Epoch(train) [14][220/660] lr: 1.0000e-02 eta: 4:16:58 time: 0.6303 data_time: 0.0284 memory: 42708 grad_norm: 4.2211 loss: 2.0626 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.0626 2023/02/18 02:10:29 - mmengine - INFO - Epoch(train) [14][240/660] lr: 1.0000e-02 eta: 4:16:45 time: 0.6213 data_time: 0.0253 memory: 42708 grad_norm: 4.0889 loss: 1.9735 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 1.9735 2023/02/18 02:10:41 - mmengine - INFO - Epoch(train) [14][260/660] lr: 1.0000e-02 eta: 4:16:32 time: 0.6312 data_time: 0.0293 memory: 42708 grad_norm: 4.1189 loss: 2.0094 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 2.0094 2023/02/18 02:10:54 - mmengine - INFO - Epoch(train) [14][280/660] lr: 1.0000e-02 eta: 4:16:18 time: 0.6239 data_time: 0.0270 memory: 42708 grad_norm: 4.1903 loss: 2.0396 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 2.0396 2023/02/18 02:11:06 - mmengine - INFO - Epoch(train) [14][300/660] lr: 1.0000e-02 eta: 4:16:05 time: 0.6295 data_time: 0.0279 memory: 42708 grad_norm: 4.1074 loss: 2.1502 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 2.1502 2023/02/18 02:11:19 - mmengine - INFO - Epoch(train) [14][320/660] lr: 1.0000e-02 eta: 4:15:51 time: 0.6218 data_time: 0.0269 memory: 42708 grad_norm: 4.1366 loss: 1.8923 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8923 2023/02/18 02:11:32 - mmengine - INFO - Epoch(train) [14][340/660] lr: 1.0000e-02 eta: 4:15:39 time: 0.6352 data_time: 0.0280 memory: 42708 grad_norm: 4.0950 loss: 1.9444 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.9444 2023/02/18 02:11:44 - mmengine - INFO - Epoch(train) [14][360/660] lr: 1.0000e-02 eta: 4:15:25 time: 0.6267 data_time: 0.0256 memory: 42708 grad_norm: 4.1433 loss: 2.0452 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 2.0452 2023/02/18 02:11:57 - mmengine - INFO - Epoch(train) [14][380/660] lr: 1.0000e-02 eta: 4:15:12 time: 0.6325 data_time: 0.0310 memory: 42708 grad_norm: 4.2410 loss: 2.0395 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 2.0395 2023/02/18 02:12:09 - mmengine - INFO - Epoch(train) [14][400/660] lr: 1.0000e-02 eta: 4:14:59 time: 0.6258 data_time: 0.0266 memory: 42708 grad_norm: 4.1097 loss: 2.0324 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.0324 2023/02/18 02:12:22 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:12:22 - mmengine - INFO - Epoch(train) [14][420/660] lr: 1.0000e-02 eta: 4:14:46 time: 0.6319 data_time: 0.0278 memory: 42708 grad_norm: 4.1699 loss: 2.0285 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 2.0285 2023/02/18 02:12:34 - mmengine - INFO - Epoch(train) [14][440/660] lr: 1.0000e-02 eta: 4:14:33 time: 0.6237 data_time: 0.0250 memory: 42708 grad_norm: 4.1341 loss: 2.1107 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 2.1107 2023/02/18 02:12:47 - mmengine - INFO - Epoch(train) [14][460/660] lr: 1.0000e-02 eta: 4:14:20 time: 0.6310 data_time: 0.0280 memory: 42708 grad_norm: 4.1553 loss: 2.0592 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.0592 2023/02/18 02:12:59 - mmengine - INFO - Epoch(train) [14][480/660] lr: 1.0000e-02 eta: 4:14:06 time: 0.6195 data_time: 0.0289 memory: 42708 grad_norm: 4.1519 loss: 2.0083 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 2.0083 2023/02/18 02:13:12 - mmengine - INFO - Epoch(train) [14][500/660] lr: 1.0000e-02 eta: 4:13:53 time: 0.6313 data_time: 0.0274 memory: 42708 grad_norm: 4.1169 loss: 2.1247 top1_acc: 0.3438 top5_acc: 0.7188 loss_cls: 2.1247 2023/02/18 02:13:25 - mmengine - INFO - Epoch(train) [14][520/660] lr: 1.0000e-02 eta: 4:13:40 time: 0.6272 data_time: 0.0263 memory: 42708 grad_norm: 4.1736 loss: 1.9531 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 1.9531 2023/02/18 02:13:37 - mmengine - INFO - Epoch(train) [14][540/660] lr: 1.0000e-02 eta: 4:13:27 time: 0.6360 data_time: 0.0281 memory: 42708 grad_norm: 4.1340 loss: 2.0371 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 2.0371 2023/02/18 02:13:50 - mmengine - INFO - Epoch(train) [14][560/660] lr: 1.0000e-02 eta: 4:13:13 time: 0.6219 data_time: 0.0266 memory: 42708 grad_norm: 4.1911 loss: 2.1529 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.1529 2023/02/18 02:14:02 - mmengine - INFO - Epoch(train) [14][580/660] lr: 1.0000e-02 eta: 4:13:01 time: 0.6357 data_time: 0.0276 memory: 42708 grad_norm: 4.1643 loss: 2.1319 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 2.1319 2023/02/18 02:14:15 - mmengine - INFO - Epoch(train) [14][600/660] lr: 1.0000e-02 eta: 4:12:47 time: 0.6240 data_time: 0.0255 memory: 42708 grad_norm: 4.1728 loss: 2.0358 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 2.0358 2023/02/18 02:14:27 - mmengine - INFO - Epoch(train) [14][620/660] lr: 1.0000e-02 eta: 4:12:34 time: 0.6271 data_time: 0.0273 memory: 42708 grad_norm: 4.1201 loss: 2.1258 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1258 2023/02/18 02:14:40 - mmengine - INFO - Epoch(train) [14][640/660] lr: 1.0000e-02 eta: 4:12:21 time: 0.6247 data_time: 0.0261 memory: 42708 grad_norm: 4.0447 loss: 2.1537 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 2.1537 2023/02/18 02:14:52 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:14:52 - mmengine - INFO - Epoch(train) [14][660/660] lr: 1.0000e-02 eta: 4:12:07 time: 0.6207 data_time: 0.0289 memory: 42708 grad_norm: 4.2396 loss: 2.0509 top1_acc: 0.3333 top5_acc: 0.5926 loss_cls: 2.0509 2023/02/18 02:15:07 - mmengine - INFO - Epoch(train) [15][ 20/660] lr: 1.0000e-02 eta: 4:11:58 time: 0.7123 data_time: 0.1102 memory: 42708 grad_norm: 4.0427 loss: 1.9690 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9690 2023/02/18 02:15:19 - mmengine - INFO - Epoch(train) [15][ 40/660] lr: 1.0000e-02 eta: 4:11:44 time: 0.6146 data_time: 0.0269 memory: 42708 grad_norm: 4.1058 loss: 1.9449 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 1.9449 2023/02/18 02:15:31 - mmengine - INFO - Epoch(train) [15][ 60/660] lr: 1.0000e-02 eta: 4:11:30 time: 0.6149 data_time: 0.0263 memory: 42708 grad_norm: 4.0434 loss: 1.9681 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.9681 2023/02/18 02:15:44 - mmengine - INFO - Epoch(train) [15][ 80/660] lr: 1.0000e-02 eta: 4:11:17 time: 0.6159 data_time: 0.0275 memory: 42708 grad_norm: 4.1102 loss: 2.0798 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0798 2023/02/18 02:15:56 - mmengine - INFO - Epoch(train) [15][100/660] lr: 1.0000e-02 eta: 4:11:03 time: 0.6152 data_time: 0.0254 memory: 42708 grad_norm: 4.2940 loss: 2.0994 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.0994 2023/02/18 02:16:08 - mmengine - INFO - Epoch(train) [15][120/660] lr: 1.0000e-02 eta: 4:10:49 time: 0.6149 data_time: 0.0276 memory: 42708 grad_norm: 4.1917 loss: 1.8973 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 1.8973 2023/02/18 02:16:20 - mmengine - INFO - Epoch(train) [15][140/660] lr: 1.0000e-02 eta: 4:10:35 time: 0.6151 data_time: 0.0256 memory: 42708 grad_norm: 4.1759 loss: 1.9976 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.9976 2023/02/18 02:16:33 - mmengine - INFO - Epoch(train) [15][160/660] lr: 1.0000e-02 eta: 4:10:21 time: 0.6175 data_time: 0.0262 memory: 42708 grad_norm: 4.2168 loss: 2.0843 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.0843 2023/02/18 02:16:45 - mmengine - INFO - Epoch(train) [15][180/660] lr: 1.0000e-02 eta: 4:10:08 time: 0.6186 data_time: 0.0252 memory: 42708 grad_norm: 4.2195 loss: 1.9859 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 1.9859 2023/02/18 02:16:57 - mmengine - INFO - Epoch(train) [15][200/660] lr: 1.0000e-02 eta: 4:09:54 time: 0.6150 data_time: 0.0277 memory: 42708 grad_norm: 4.2192 loss: 1.9564 top1_acc: 0.4375 top5_acc: 0.8438 loss_cls: 1.9564 2023/02/18 02:17:10 - mmengine - INFO - Epoch(train) [15][220/660] lr: 1.0000e-02 eta: 4:09:40 time: 0.6157 data_time: 0.0250 memory: 42708 grad_norm: 4.1292 loss: 1.9876 top1_acc: 0.5625 top5_acc: 0.7188 loss_cls: 1.9876 2023/02/18 02:17:22 - mmengine - INFO - Epoch(train) [15][240/660] lr: 1.0000e-02 eta: 4:09:27 time: 0.6166 data_time: 0.0271 memory: 42708 grad_norm: 4.1319 loss: 2.0630 top1_acc: 0.4062 top5_acc: 0.6250 loss_cls: 2.0630 2023/02/18 02:17:34 - mmengine - INFO - Epoch(train) [15][260/660] lr: 1.0000e-02 eta: 4:09:13 time: 0.6157 data_time: 0.0264 memory: 42708 grad_norm: 4.2226 loss: 2.1552 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 2.1552 2023/02/18 02:17:47 - mmengine - INFO - Epoch(train) [15][280/660] lr: 1.0000e-02 eta: 4:08:59 time: 0.6146 data_time: 0.0299 memory: 42708 grad_norm: 4.0240 loss: 1.9244 top1_acc: 0.3750 top5_acc: 0.7812 loss_cls: 1.9244 2023/02/18 02:18:58 - mmengine - INFO - Epoch(train) [15][300/660] lr: 1.0000e-02 eta: 4:11:11 time: 3.5696 data_time: 0.0270 memory: 42708 grad_norm: 4.2041 loss: 1.9914 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.9914 2023/02/18 02:19:10 - mmengine - INFO - Epoch(train) [15][320/660] lr: 1.0000e-02 eta: 4:10:56 time: 0.6132 data_time: 0.0268 memory: 42708 grad_norm: 4.2694 loss: 2.0683 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 2.0683 2023/02/18 02:19:23 - mmengine - INFO - Epoch(train) [15][340/660] lr: 1.0000e-02 eta: 4:10:42 time: 0.6157 data_time: 0.0267 memory: 42708 grad_norm: 4.2233 loss: 2.1712 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.1712 2023/02/18 02:19:35 - mmengine - INFO - Epoch(train) [15][360/660] lr: 1.0000e-02 eta: 4:10:28 time: 0.6134 data_time: 0.0275 memory: 42708 grad_norm: 4.1136 loss: 1.9867 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.9867 2023/02/18 02:19:47 - mmengine - INFO - Epoch(train) [15][380/660] lr: 1.0000e-02 eta: 4:10:14 time: 0.6219 data_time: 0.0262 memory: 42708 grad_norm: 4.0996 loss: 1.9250 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.9250 2023/02/18 02:20:00 - mmengine - INFO - Epoch(train) [15][400/660] lr: 1.0000e-02 eta: 4:10:00 time: 0.6168 data_time: 0.0258 memory: 42708 grad_norm: 4.1319 loss: 1.9482 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.9482 2023/02/18 02:20:12 - mmengine - INFO - Epoch(train) [15][420/660] lr: 1.0000e-02 eta: 4:09:46 time: 0.6177 data_time: 0.0253 memory: 42708 grad_norm: 4.1964 loss: 1.9711 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 1.9711 2023/02/18 02:20:24 - mmengine - INFO - Epoch(train) [15][440/660] lr: 1.0000e-02 eta: 4:09:32 time: 0.6171 data_time: 0.0260 memory: 42708 grad_norm: 4.1478 loss: 2.0925 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 2.0925 2023/02/18 02:20:37 - mmengine - INFO - Epoch(train) [15][460/660] lr: 1.0000e-02 eta: 4:09:18 time: 0.6203 data_time: 0.0260 memory: 42708 grad_norm: 4.1422 loss: 2.0064 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 2.0064 2023/02/18 02:20:49 - mmengine - INFO - Epoch(train) [15][480/660] lr: 1.0000e-02 eta: 4:09:04 time: 0.6131 data_time: 0.0272 memory: 42708 grad_norm: 4.2094 loss: 2.1179 top1_acc: 0.3125 top5_acc: 0.7188 loss_cls: 2.1179 2023/02/18 02:21:01 - mmengine - INFO - Epoch(train) [15][500/660] lr: 1.0000e-02 eta: 4:08:50 time: 0.6179 data_time: 0.0260 memory: 42708 grad_norm: 4.1084 loss: 2.0533 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 2.0533 2023/02/18 02:21:14 - mmengine - INFO - Epoch(train) [15][520/660] lr: 1.0000e-02 eta: 4:08:36 time: 0.6154 data_time: 0.0280 memory: 42708 grad_norm: 4.2004 loss: 2.0754 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.0754 2023/02/18 02:21:26 - mmengine - INFO - Epoch(train) [15][540/660] lr: 1.0000e-02 eta: 4:08:22 time: 0.6192 data_time: 0.0272 memory: 42708 grad_norm: 4.1624 loss: 2.0644 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 2.0644 2023/02/18 02:21:38 - mmengine - INFO - Epoch(train) [15][560/660] lr: 1.0000e-02 eta: 4:08:08 time: 0.6157 data_time: 0.0308 memory: 42708 grad_norm: 4.1956 loss: 1.9984 top1_acc: 0.4062 top5_acc: 0.8438 loss_cls: 1.9984 2023/02/18 02:21:51 - mmengine - INFO - Epoch(train) [15][580/660] lr: 1.0000e-02 eta: 4:07:54 time: 0.6146 data_time: 0.0270 memory: 42708 grad_norm: 4.2066 loss: 2.1288 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 2.1288 2023/02/18 02:22:03 - mmengine - INFO - Epoch(train) [15][600/660] lr: 1.0000e-02 eta: 4:07:39 time: 0.6127 data_time: 0.0268 memory: 42708 grad_norm: 4.2757 loss: 2.1563 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 2.1563 2023/02/18 02:22:15 - mmengine - INFO - Epoch(train) [15][620/660] lr: 1.0000e-02 eta: 4:07:25 time: 0.6170 data_time: 0.0259 memory: 42708 grad_norm: 4.2212 loss: 1.9773 top1_acc: 0.3750 top5_acc: 0.6562 loss_cls: 1.9773 2023/02/18 02:22:28 - mmengine - INFO - Epoch(train) [15][640/660] lr: 1.0000e-02 eta: 4:07:12 time: 0.6227 data_time: 0.0277 memory: 42708 grad_norm: 4.2208 loss: 2.0916 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.0916 2023/02/18 02:22:40 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:22:40 - mmengine - INFO - Epoch(train) [15][660/660] lr: 1.0000e-02 eta: 4:06:57 time: 0.6075 data_time: 0.0238 memory: 42708 grad_norm: 4.2226 loss: 2.1041 top1_acc: 0.4444 top5_acc: 0.7778 loss_cls: 2.1041 2023/02/18 02:22:40 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/02/18 02:22:48 - mmengine - INFO - Epoch(val) [15][20/97] eta: 0:00:26 time: 0.3421 data_time: 0.1205 memory: 6154 2023/02/18 02:22:53 - mmengine - INFO - Epoch(val) [15][40/97] eta: 0:00:16 time: 0.2419 data_time: 0.0313 memory: 6154 2023/02/18 02:22:58 - mmengine - INFO - Epoch(val) [15][60/97] eta: 0:00:10 time: 0.2503 data_time: 0.0404 memory: 6154 2023/02/18 02:23:02 - mmengine - INFO - Epoch(val) [15][80/97] eta: 0:00:04 time: 0.2370 data_time: 0.0297 memory: 6154 2023/02/18 02:23:07 - mmengine - INFO - Epoch(val) [15][97/97] acc/top1: 0.3315 acc/top5: 0.6437 acc/mean1: 0.2689 2023/02/18 02:23:07 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_10.pth is removed 2023/02/18 02:23:08 - mmengine - INFO - The best checkpoint with 0.3315 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2023/02/18 02:23:22 - mmengine - INFO - Epoch(train) [16][ 20/660] lr: 1.0000e-02 eta: 4:06:48 time: 0.7144 data_time: 0.1154 memory: 42708 grad_norm: 4.0415 loss: 1.8483 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.8483 2023/02/18 02:23:34 - mmengine - INFO - Epoch(train) [16][ 40/660] lr: 1.0000e-02 eta: 4:06:34 time: 0.6181 data_time: 0.0298 memory: 42708 grad_norm: 4.1229 loss: 1.9152 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.9152 2023/02/18 02:23:47 - mmengine - INFO - Epoch(train) [16][ 60/660] lr: 1.0000e-02 eta: 4:06:21 time: 0.6317 data_time: 0.0315 memory: 42708 grad_norm: 4.2106 loss: 2.0109 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 2.0109 2023/02/18 02:23:59 - mmengine - INFO - Epoch(train) [16][ 80/660] lr: 1.0000e-02 eta: 4:06:07 time: 0.6194 data_time: 0.0306 memory: 42708 grad_norm: 4.1432 loss: 1.9371 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.9371 2023/02/18 02:24:12 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:24:12 - mmengine - INFO - Epoch(train) [16][100/660] lr: 1.0000e-02 eta: 4:05:53 time: 0.6309 data_time: 0.0316 memory: 42708 grad_norm: 4.1629 loss: 2.0122 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 2.0122 2023/02/18 02:24:24 - mmengine - INFO - Epoch(train) [16][120/660] lr: 1.0000e-02 eta: 4:05:40 time: 0.6209 data_time: 0.0289 memory: 42708 grad_norm: 4.2701 loss: 1.9882 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.9882 2023/02/18 02:24:37 - mmengine - INFO - Epoch(train) [16][140/660] lr: 1.0000e-02 eta: 4:05:26 time: 0.6284 data_time: 0.0316 memory: 42708 grad_norm: 4.1769 loss: 2.0342 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0342 2023/02/18 02:24:49 - mmengine - INFO - Epoch(train) [16][160/660] lr: 1.0000e-02 eta: 4:05:12 time: 0.6202 data_time: 0.0306 memory: 42708 grad_norm: 4.2785 loss: 2.0055 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 2.0055 2023/02/18 02:25:02 - mmengine - INFO - Epoch(train) [16][180/660] lr: 1.0000e-02 eta: 4:04:59 time: 0.6325 data_time: 0.0347 memory: 42708 grad_norm: 4.2253 loss: 2.0271 top1_acc: 0.3438 top5_acc: 0.6875 loss_cls: 2.0271 2023/02/18 02:25:15 - mmengine - INFO - Epoch(train) [16][200/660] lr: 1.0000e-02 eta: 4:04:46 time: 0.6250 data_time: 0.0311 memory: 42708 grad_norm: 4.1571 loss: 1.9755 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.9755 2023/02/18 02:25:27 - mmengine - INFO - Epoch(train) [16][220/660] lr: 1.0000e-02 eta: 4:04:32 time: 0.6319 data_time: 0.0372 memory: 42708 grad_norm: 4.1708 loss: 1.9116 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.9116 2023/02/18 02:25:40 - mmengine - INFO - Epoch(train) [16][240/660] lr: 1.0000e-02 eta: 4:04:19 time: 0.6225 data_time: 0.0326 memory: 42708 grad_norm: 4.2329 loss: 1.9252 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.9252 2023/02/18 02:25:52 - mmengine - INFO - Epoch(train) [16][260/660] lr: 1.0000e-02 eta: 4:04:05 time: 0.6303 data_time: 0.0358 memory: 42708 grad_norm: 4.2928 loss: 2.0230 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0230 2023/02/18 02:26:05 - mmengine - INFO - Epoch(train) [16][280/660] lr: 1.0000e-02 eta: 4:03:52 time: 0.6256 data_time: 0.0306 memory: 42708 grad_norm: 4.2029 loss: 1.9692 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.9692 2023/02/18 02:26:17 - mmengine - INFO - Epoch(train) [16][300/660] lr: 1.0000e-02 eta: 4:03:39 time: 0.6347 data_time: 0.0344 memory: 42708 grad_norm: 4.2019 loss: 1.9385 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 1.9385 2023/02/18 02:26:30 - mmengine - INFO - Epoch(train) [16][320/660] lr: 1.0000e-02 eta: 4:03:25 time: 0.6227 data_time: 0.0329 memory: 42708 grad_norm: 4.2600 loss: 1.8700 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 1.8700 2023/02/18 02:26:42 - mmengine - INFO - Epoch(train) [16][340/660] lr: 1.0000e-02 eta: 4:03:12 time: 0.6282 data_time: 0.0332 memory: 42708 grad_norm: 4.2695 loss: 2.0442 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 2.0442 2023/02/18 02:26:55 - mmengine - INFO - Epoch(train) [16][360/660] lr: 1.0000e-02 eta: 4:02:58 time: 0.6180 data_time: 0.0282 memory: 42708 grad_norm: 4.2679 loss: 2.0422 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0422 2023/02/18 02:27:07 - mmengine - INFO - Epoch(train) [16][380/660] lr: 1.0000e-02 eta: 4:02:44 time: 0.6268 data_time: 0.0328 memory: 42708 grad_norm: 4.2117 loss: 1.9125 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.9125 2023/02/18 02:27:20 - mmengine - INFO - Epoch(train) [16][400/660] lr: 1.0000e-02 eta: 4:02:31 time: 0.6207 data_time: 0.0295 memory: 42708 grad_norm: 4.2189 loss: 1.8994 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8994 2023/02/18 02:27:32 - mmengine - INFO - Epoch(train) [16][420/660] lr: 1.0000e-02 eta: 4:02:17 time: 0.6317 data_time: 0.0333 memory: 42708 grad_norm: 4.2423 loss: 2.0773 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.0773 2023/02/18 02:27:45 - mmengine - INFO - Epoch(train) [16][440/660] lr: 1.0000e-02 eta: 4:02:04 time: 0.6199 data_time: 0.0284 memory: 42708 grad_norm: 4.2556 loss: 1.9905 top1_acc: 0.4375 top5_acc: 0.8438 loss_cls: 1.9905 2023/02/18 02:27:57 - mmengine - INFO - Epoch(train) [16][460/660] lr: 1.0000e-02 eta: 4:01:50 time: 0.6257 data_time: 0.0323 memory: 42708 grad_norm: 4.1991 loss: 2.0452 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 2.0452 2023/02/18 02:28:10 - mmengine - INFO - Epoch(train) [16][480/660] lr: 1.0000e-02 eta: 4:01:37 time: 0.6200 data_time: 0.0311 memory: 42708 grad_norm: 4.3272 loss: 1.9531 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 1.9531 2023/02/18 02:28:22 - mmengine - INFO - Epoch(train) [16][500/660] lr: 1.0000e-02 eta: 4:01:23 time: 0.6301 data_time: 0.0340 memory: 42708 grad_norm: 4.1605 loss: 1.8490 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.8490 2023/02/18 02:28:35 - mmengine - INFO - Epoch(train) [16][520/660] lr: 1.0000e-02 eta: 4:01:10 time: 0.6217 data_time: 0.0317 memory: 42708 grad_norm: 4.2346 loss: 2.0556 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 2.0556 2023/02/18 02:28:47 - mmengine - INFO - Epoch(train) [16][540/660] lr: 1.0000e-02 eta: 4:00:56 time: 0.6243 data_time: 0.0321 memory: 42708 grad_norm: 4.3029 loss: 2.0521 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 2.0521 2023/02/18 02:29:00 - mmengine - INFO - Epoch(train) [16][560/660] lr: 1.0000e-02 eta: 4:00:42 time: 0.6178 data_time: 0.0298 memory: 42708 grad_norm: 4.2486 loss: 1.9305 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9305 2023/02/18 02:29:12 - mmengine - INFO - Epoch(train) [16][580/660] lr: 1.0000e-02 eta: 4:00:29 time: 0.6293 data_time: 0.0345 memory: 42708 grad_norm: 4.2715 loss: 2.0691 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 2.0691 2023/02/18 02:29:25 - mmengine - INFO - Epoch(train) [16][600/660] lr: 1.0000e-02 eta: 4:00:15 time: 0.6248 data_time: 0.0314 memory: 42708 grad_norm: 4.2513 loss: 1.9183 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.9183 2023/02/18 02:29:37 - mmengine - INFO - Epoch(train) [16][620/660] lr: 1.0000e-02 eta: 4:00:02 time: 0.6282 data_time: 0.0334 memory: 42708 grad_norm: 4.2437 loss: 1.9505 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.9505 2023/02/18 02:29:50 - mmengine - INFO - Epoch(train) [16][640/660] lr: 1.0000e-02 eta: 3:59:48 time: 0.6182 data_time: 0.0297 memory: 42708 grad_norm: 4.2233 loss: 1.9612 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9612 2023/02/18 02:30:02 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:30:02 - mmengine - INFO - Epoch(train) [16][660/660] lr: 1.0000e-02 eta: 3:59:35 time: 0.6181 data_time: 0.0293 memory: 42708 grad_norm: 4.1595 loss: 1.9584 top1_acc: 0.5556 top5_acc: 0.7778 loss_cls: 1.9584 2023/02/18 02:30:16 - mmengine - INFO - Epoch(train) [17][ 20/660] lr: 1.0000e-02 eta: 3:59:25 time: 0.7200 data_time: 0.1147 memory: 42708 grad_norm: 4.1492 loss: 1.9228 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.9228 2023/02/18 02:30:29 - mmengine - INFO - Epoch(train) [17][ 40/660] lr: 1.0000e-02 eta: 3:59:11 time: 0.6152 data_time: 0.0301 memory: 42708 grad_norm: 4.2065 loss: 1.8729 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.8729 2023/02/18 02:30:41 - mmengine - INFO - Epoch(train) [17][ 60/660] lr: 1.0000e-02 eta: 3:58:58 time: 0.6264 data_time: 0.0367 memory: 42708 grad_norm: 4.2615 loss: 1.9248 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.9248 2023/02/18 02:30:54 - mmengine - INFO - Epoch(train) [17][ 80/660] lr: 1.0000e-02 eta: 3:58:44 time: 0.6266 data_time: 0.0283 memory: 42708 grad_norm: 4.2229 loss: 1.9452 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.9452 2023/02/18 02:31:06 - mmengine - INFO - Epoch(train) [17][100/660] lr: 1.0000e-02 eta: 3:58:31 time: 0.6306 data_time: 0.0333 memory: 42708 grad_norm: 4.2771 loss: 1.9296 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9296 2023/02/18 02:31:19 - mmengine - INFO - Epoch(train) [17][120/660] lr: 1.0000e-02 eta: 3:58:17 time: 0.6208 data_time: 0.0305 memory: 42708 grad_norm: 4.2747 loss: 1.8740 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8740 2023/02/18 02:31:31 - mmengine - INFO - Epoch(train) [17][140/660] lr: 1.0000e-02 eta: 3:58:04 time: 0.6262 data_time: 0.0350 memory: 42708 grad_norm: 4.1955 loss: 1.8638 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8638 2023/02/18 02:31:44 - mmengine - INFO - Epoch(train) [17][160/660] lr: 1.0000e-02 eta: 3:57:50 time: 0.6177 data_time: 0.0277 memory: 42708 grad_norm: 4.3079 loss: 1.9644 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 1.9644 2023/02/18 02:31:56 - mmengine - INFO - Epoch(train) [17][180/660] lr: 1.0000e-02 eta: 3:57:37 time: 0.6359 data_time: 0.0350 memory: 42708 grad_norm: 4.2359 loss: 1.9416 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.9416 2023/02/18 02:32:09 - mmengine - INFO - Epoch(train) [17][200/660] lr: 1.0000e-02 eta: 3:57:24 time: 0.6253 data_time: 0.0328 memory: 42708 grad_norm: 4.2991 loss: 1.8623 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.8623 2023/02/18 02:32:21 - mmengine - INFO - Epoch(train) [17][220/660] lr: 1.0000e-02 eta: 3:57:11 time: 0.6295 data_time: 0.0346 memory: 42708 grad_norm: 4.2391 loss: 1.8334 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.8334 2023/02/18 02:32:34 - mmengine - INFO - Epoch(train) [17][240/660] lr: 1.0000e-02 eta: 3:56:57 time: 0.6212 data_time: 0.0299 memory: 42708 grad_norm: 4.2608 loss: 1.9080 top1_acc: 0.4688 top5_acc: 0.6875 loss_cls: 1.9080 2023/02/18 02:32:47 - mmengine - INFO - Epoch(train) [17][260/660] lr: 1.0000e-02 eta: 3:56:44 time: 0.6314 data_time: 0.0369 memory: 42708 grad_norm: 4.2263 loss: 1.8668 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.8668 2023/02/18 02:32:59 - mmengine - INFO - Epoch(train) [17][280/660] lr: 1.0000e-02 eta: 3:56:30 time: 0.6200 data_time: 0.0284 memory: 42708 grad_norm: 4.2879 loss: 1.9331 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9331 2023/02/18 02:33:12 - mmengine - INFO - Epoch(train) [17][300/660] lr: 1.0000e-02 eta: 3:56:17 time: 0.6340 data_time: 0.0377 memory: 42708 grad_norm: 4.2209 loss: 1.9551 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 1.9551 2023/02/18 02:33:24 - mmengine - INFO - Epoch(train) [17][320/660] lr: 1.0000e-02 eta: 3:56:04 time: 0.6212 data_time: 0.0290 memory: 42708 grad_norm: 4.2314 loss: 1.9119 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.9119 2023/02/18 02:33:37 - mmengine - INFO - Epoch(train) [17][340/660] lr: 1.0000e-02 eta: 3:55:50 time: 0.6294 data_time: 0.0342 memory: 42708 grad_norm: 4.3008 loss: 2.1640 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 2.1640 2023/02/18 02:33:49 - mmengine - INFO - Epoch(train) [17][360/660] lr: 1.0000e-02 eta: 3:55:37 time: 0.6161 data_time: 0.0291 memory: 42708 grad_norm: 4.3695 loss: 1.9605 top1_acc: 0.5312 top5_acc: 0.6875 loss_cls: 1.9605 2023/02/18 02:34:02 - mmengine - INFO - Epoch(train) [17][380/660] lr: 1.0000e-02 eta: 3:55:23 time: 0.6323 data_time: 0.0333 memory: 42708 grad_norm: 4.3135 loss: 1.9859 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 1.9859 2023/02/18 02:34:14 - mmengine - INFO - Epoch(train) [17][400/660] lr: 1.0000e-02 eta: 3:55:10 time: 0.6175 data_time: 0.0293 memory: 42708 grad_norm: 4.3642 loss: 2.0083 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 2.0083 2023/02/18 02:34:27 - mmengine - INFO - Epoch(train) [17][420/660] lr: 1.0000e-02 eta: 3:54:56 time: 0.6276 data_time: 0.0340 memory: 42708 grad_norm: 4.2442 loss: 1.9439 top1_acc: 0.3438 top5_acc: 0.6562 loss_cls: 1.9439 2023/02/18 02:34:39 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:34:39 - mmengine - INFO - Epoch(train) [17][440/660] lr: 1.0000e-02 eta: 3:54:43 time: 0.6208 data_time: 0.0311 memory: 42708 grad_norm: 4.2584 loss: 2.0242 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 2.0242 2023/02/18 02:34:52 - mmengine - INFO - Epoch(train) [17][460/660] lr: 1.0000e-02 eta: 3:54:30 time: 0.6305 data_time: 0.0346 memory: 42708 grad_norm: 4.2589 loss: 1.8891 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.8891 2023/02/18 02:35:04 - mmengine - INFO - Epoch(train) [17][480/660] lr: 1.0000e-02 eta: 3:54:16 time: 0.6230 data_time: 0.0295 memory: 42708 grad_norm: 4.2664 loss: 1.9176 top1_acc: 0.4375 top5_acc: 0.6562 loss_cls: 1.9176 2023/02/18 02:35:17 - mmengine - INFO - Epoch(train) [17][500/660] lr: 1.0000e-02 eta: 3:54:03 time: 0.6298 data_time: 0.0332 memory: 42708 grad_norm: 4.2498 loss: 1.9463 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.9463 2023/02/18 02:35:29 - mmengine - INFO - Epoch(train) [17][520/660] lr: 1.0000e-02 eta: 3:53:50 time: 0.6258 data_time: 0.0292 memory: 42708 grad_norm: 4.2843 loss: 2.0602 top1_acc: 0.3438 top5_acc: 0.8125 loss_cls: 2.0602 2023/02/18 02:35:42 - mmengine - INFO - Epoch(train) [17][540/660] lr: 1.0000e-02 eta: 3:53:36 time: 0.6290 data_time: 0.0364 memory: 42708 grad_norm: 4.2804 loss: 1.9107 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.9107 2023/02/18 02:35:54 - mmengine - INFO - Epoch(train) [17][560/660] lr: 1.0000e-02 eta: 3:53:23 time: 0.6243 data_time: 0.0324 memory: 42708 grad_norm: 4.2660 loss: 1.8518 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8518 2023/02/18 02:36:07 - mmengine - INFO - Epoch(train) [17][580/660] lr: 1.0000e-02 eta: 3:53:10 time: 0.6270 data_time: 0.0333 memory: 42708 grad_norm: 4.3022 loss: 1.8941 top1_acc: 0.4375 top5_acc: 0.5000 loss_cls: 1.8941 2023/02/18 02:36:19 - mmengine - INFO - Epoch(train) [17][600/660] lr: 1.0000e-02 eta: 3:52:56 time: 0.6171 data_time: 0.0290 memory: 42708 grad_norm: 4.3144 loss: 2.0550 top1_acc: 0.3750 top5_acc: 0.7812 loss_cls: 2.0550 2023/02/18 02:36:32 - mmengine - INFO - Epoch(train) [17][620/660] lr: 1.0000e-02 eta: 3:52:43 time: 0.6290 data_time: 0.0347 memory: 42708 grad_norm: 4.4136 loss: 1.9401 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.9401 2023/02/18 02:36:44 - mmengine - INFO - Epoch(train) [17][640/660] lr: 1.0000e-02 eta: 3:52:29 time: 0.6191 data_time: 0.0282 memory: 42708 grad_norm: 4.3385 loss: 2.0449 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 2.0449 2023/02/18 02:36:56 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:36:56 - mmengine - INFO - Epoch(train) [17][660/660] lr: 1.0000e-02 eta: 3:52:15 time: 0.6125 data_time: 0.0292 memory: 42708 grad_norm: 4.3098 loss: 2.0486 top1_acc: 0.4815 top5_acc: 0.7778 loss_cls: 2.0486 2023/02/18 02:37:11 - mmengine - INFO - Epoch(train) [18][ 20/660] lr: 1.0000e-02 eta: 3:52:05 time: 0.7093 data_time: 0.1128 memory: 42708 grad_norm: 4.1035 loss: 1.8150 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.8150 2023/02/18 02:37:23 - mmengine - INFO - Epoch(train) [18][ 40/660] lr: 1.0000e-02 eta: 3:51:52 time: 0.6256 data_time: 0.0276 memory: 42708 grad_norm: 4.1773 loss: 1.8128 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.8128 2023/02/18 02:37:36 - mmengine - INFO - Epoch(train) [18][ 60/660] lr: 1.0000e-02 eta: 3:51:39 time: 0.6303 data_time: 0.0347 memory: 42708 grad_norm: 4.3204 loss: 1.9859 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.9859 2023/02/18 02:37:48 - mmengine - INFO - Epoch(train) [18][ 80/660] lr: 1.0000e-02 eta: 3:51:25 time: 0.6189 data_time: 0.0292 memory: 42708 grad_norm: 4.1909 loss: 1.8260 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8260 2023/02/18 02:38:01 - mmengine - INFO - Epoch(train) [18][100/660] lr: 1.0000e-02 eta: 3:51:12 time: 0.6310 data_time: 0.0342 memory: 42708 grad_norm: 4.2916 loss: 1.8316 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8316 2023/02/18 02:38:13 - mmengine - INFO - Epoch(train) [18][120/660] lr: 1.0000e-02 eta: 3:50:58 time: 0.6249 data_time: 0.0372 memory: 42708 grad_norm: 4.3409 loss: 1.7658 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.7658 2023/02/18 02:38:26 - mmengine - INFO - Epoch(train) [18][140/660] lr: 1.0000e-02 eta: 3:50:45 time: 0.6260 data_time: 0.0326 memory: 42708 grad_norm: 4.3729 loss: 1.9219 top1_acc: 0.3438 top5_acc: 0.7812 loss_cls: 1.9219 2023/02/18 02:38:38 - mmengine - INFO - Epoch(train) [18][160/660] lr: 1.0000e-02 eta: 3:50:32 time: 0.6199 data_time: 0.0299 memory: 42708 grad_norm: 4.3550 loss: 1.9010 top1_acc: 0.4688 top5_acc: 0.6875 loss_cls: 1.9010 2023/02/18 02:38:50 - mmengine - INFO - Epoch(train) [18][180/660] lr: 1.0000e-02 eta: 3:50:18 time: 0.6227 data_time: 0.0318 memory: 42708 grad_norm: 4.3492 loss: 1.8728 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.8728 2023/02/18 02:39:03 - mmengine - INFO - Epoch(train) [18][200/660] lr: 1.0000e-02 eta: 3:50:04 time: 0.6164 data_time: 0.0282 memory: 42708 grad_norm: 4.3947 loss: 1.8744 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.8744 2023/02/18 02:39:15 - mmengine - INFO - Epoch(train) [18][220/660] lr: 1.0000e-02 eta: 3:49:51 time: 0.6250 data_time: 0.0334 memory: 42708 grad_norm: 4.3233 loss: 1.9290 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.9290 2023/02/18 02:39:28 - mmengine - INFO - Epoch(train) [18][240/660] lr: 1.0000e-02 eta: 3:49:37 time: 0.6173 data_time: 0.0295 memory: 42708 grad_norm: 4.3132 loss: 1.8989 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.8989 2023/02/18 02:39:40 - mmengine - INFO - Epoch(train) [18][260/660] lr: 1.0000e-02 eta: 3:49:24 time: 0.6310 data_time: 0.0369 memory: 42708 grad_norm: 4.3695 loss: 1.9778 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.9778 2023/02/18 02:39:53 - mmengine - INFO - Epoch(train) [18][280/660] lr: 1.0000e-02 eta: 3:49:11 time: 0.6212 data_time: 0.0299 memory: 42708 grad_norm: 4.3361 loss: 1.8626 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8626 2023/02/18 02:40:05 - mmengine - INFO - Epoch(train) [18][300/660] lr: 1.0000e-02 eta: 3:48:57 time: 0.6242 data_time: 0.0321 memory: 42708 grad_norm: 4.3897 loss: 2.0398 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0398 2023/02/18 02:40:18 - mmengine - INFO - Epoch(train) [18][320/660] lr: 1.0000e-02 eta: 3:48:44 time: 0.6220 data_time: 0.0292 memory: 42708 grad_norm: 4.3175 loss: 1.8097 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.8097 2023/02/18 02:40:30 - mmengine - INFO - Epoch(train) [18][340/660] lr: 1.0000e-02 eta: 3:48:31 time: 0.6292 data_time: 0.0338 memory: 42708 grad_norm: 4.4151 loss: 2.1440 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 2.1440 2023/02/18 02:40:43 - mmengine - INFO - Epoch(train) [18][360/660] lr: 1.0000e-02 eta: 3:48:17 time: 0.6215 data_time: 0.0327 memory: 42708 grad_norm: 4.3521 loss: 1.9772 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.9772 2023/02/18 02:40:55 - mmengine - INFO - Epoch(train) [18][380/660] lr: 1.0000e-02 eta: 3:48:04 time: 0.6292 data_time: 0.0332 memory: 42708 grad_norm: 4.4858 loss: 1.8759 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.8759 2023/02/18 02:41:08 - mmengine - INFO - Epoch(train) [18][400/660] lr: 1.0000e-02 eta: 3:47:51 time: 0.6202 data_time: 0.0305 memory: 42708 grad_norm: 4.4064 loss: 1.8287 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8287 2023/02/18 02:41:20 - mmengine - INFO - Epoch(train) [18][420/660] lr: 1.0000e-02 eta: 3:47:38 time: 0.6328 data_time: 0.0332 memory: 42708 grad_norm: 4.3721 loss: 1.8806 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.8806 2023/02/18 02:41:33 - mmengine - INFO - Epoch(train) [18][440/660] lr: 1.0000e-02 eta: 3:47:24 time: 0.6185 data_time: 0.0305 memory: 42708 grad_norm: 4.4538 loss: 1.9178 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.9178 2023/02/18 02:41:45 - mmengine - INFO - Epoch(train) [18][460/660] lr: 1.0000e-02 eta: 3:47:11 time: 0.6297 data_time: 0.0349 memory: 42708 grad_norm: 4.4406 loss: 1.8610 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.8610 2023/02/18 02:41:58 - mmengine - INFO - Epoch(train) [18][480/660] lr: 1.0000e-02 eta: 3:46:57 time: 0.6177 data_time: 0.0300 memory: 42708 grad_norm: 4.2927 loss: 1.9254 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.9254 2023/02/18 02:42:10 - mmengine - INFO - Epoch(train) [18][500/660] lr: 1.0000e-02 eta: 3:46:44 time: 0.6306 data_time: 0.0344 memory: 42708 grad_norm: 4.3797 loss: 1.8758 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.8758 2023/02/18 02:42:23 - mmengine - INFO - Epoch(train) [18][520/660] lr: 1.0000e-02 eta: 3:46:31 time: 0.6173 data_time: 0.0295 memory: 42708 grad_norm: 4.4682 loss: 1.9282 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 1.9282 2023/02/18 02:42:35 - mmengine - INFO - Epoch(train) [18][540/660] lr: 1.0000e-02 eta: 3:46:17 time: 0.6264 data_time: 0.0327 memory: 42708 grad_norm: 4.2958 loss: 1.8223 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.8223 2023/02/18 02:42:48 - mmengine - INFO - Epoch(train) [18][560/660] lr: 1.0000e-02 eta: 3:46:04 time: 0.6213 data_time: 0.0280 memory: 42708 grad_norm: 4.3228 loss: 1.9417 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.9417 2023/02/18 02:43:00 - mmengine - INFO - Epoch(train) [18][580/660] lr: 1.0000e-02 eta: 3:45:51 time: 0.6296 data_time: 0.0372 memory: 42708 grad_norm: 4.3767 loss: 1.8797 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.8797 2023/02/18 02:43:13 - mmengine - INFO - Epoch(train) [18][600/660] lr: 1.0000e-02 eta: 3:45:37 time: 0.6203 data_time: 0.0294 memory: 42708 grad_norm: 4.3734 loss: 1.8816 top1_acc: 0.4375 top5_acc: 0.8438 loss_cls: 1.8816 2023/02/18 02:43:25 - mmengine - INFO - Epoch(train) [18][620/660] lr: 1.0000e-02 eta: 3:45:24 time: 0.6332 data_time: 0.0339 memory: 42708 grad_norm: 4.4030 loss: 1.8859 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.8859 2023/02/18 02:43:38 - mmengine - INFO - Epoch(train) [18][640/660] lr: 1.0000e-02 eta: 3:45:11 time: 0.6160 data_time: 0.0294 memory: 42708 grad_norm: 4.2397 loss: 2.0334 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 2.0334 2023/02/18 02:43:50 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:43:50 - mmengine - INFO - Epoch(train) [18][660/660] lr: 1.0000e-02 eta: 3:44:57 time: 0.6157 data_time: 0.0291 memory: 42708 grad_norm: 4.4375 loss: 1.9483 top1_acc: 0.5556 top5_acc: 0.7407 loss_cls: 1.9483 2023/02/18 02:43:50 - mmengine - INFO - Saving checkpoint at 18 epochs 2023/02/18 02:44:05 - mmengine - INFO - Epoch(train) [19][ 20/660] lr: 1.0000e-02 eta: 3:44:47 time: 0.7221 data_time: 0.1194 memory: 42708 grad_norm: 4.3085 loss: 1.8010 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.8010 2023/02/18 02:44:18 - mmengine - INFO - Epoch(train) [19][ 40/660] lr: 1.0000e-02 eta: 3:44:34 time: 0.6204 data_time: 0.0289 memory: 42708 grad_norm: 4.3501 loss: 1.9095 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 1.9095 2023/02/18 02:44:31 - mmengine - INFO - Epoch(train) [19][ 60/660] lr: 1.0000e-02 eta: 3:44:22 time: 0.6508 data_time: 0.0371 memory: 42708 grad_norm: 4.3070 loss: 1.8585 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.8585 2023/02/18 02:44:43 - mmengine - INFO - Epoch(train) [19][ 80/660] lr: 1.0000e-02 eta: 3:44:08 time: 0.6262 data_time: 0.0309 memory: 42708 grad_norm: 4.4025 loss: 1.7594 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.7594 2023/02/18 02:44:56 - mmengine - INFO - Epoch(train) [19][100/660] lr: 1.0000e-02 eta: 3:43:56 time: 0.6408 data_time: 0.0338 memory: 42708 grad_norm: 4.3804 loss: 1.7376 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.7376 2023/02/18 02:45:09 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:45:09 - mmengine - INFO - Epoch(train) [19][120/660] lr: 1.0000e-02 eta: 3:43:42 time: 0.6227 data_time: 0.0282 memory: 42708 grad_norm: 4.3193 loss: 1.8137 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.8137 2023/02/18 02:45:21 - mmengine - INFO - Epoch(train) [19][140/660] lr: 1.0000e-02 eta: 3:43:29 time: 0.6334 data_time: 0.0316 memory: 42708 grad_norm: 4.4027 loss: 1.8708 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8708 2023/02/18 02:45:34 - mmengine - INFO - Epoch(train) [19][160/660] lr: 1.0000e-02 eta: 3:43:16 time: 0.6262 data_time: 0.0283 memory: 42708 grad_norm: 4.2979 loss: 1.7557 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.7557 2023/02/18 02:45:47 - mmengine - INFO - Epoch(train) [19][180/660] lr: 1.0000e-02 eta: 3:43:03 time: 0.6366 data_time: 0.0334 memory: 42708 grad_norm: 4.4199 loss: 1.8822 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.8822 2023/02/18 02:45:59 - mmengine - INFO - Epoch(train) [19][200/660] lr: 1.0000e-02 eta: 3:42:50 time: 0.6276 data_time: 0.0311 memory: 42708 grad_norm: 4.4227 loss: 1.8476 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.8476 2023/02/18 02:46:12 - mmengine - INFO - Epoch(train) [19][220/660] lr: 1.0000e-02 eta: 3:42:37 time: 0.6395 data_time: 0.0341 memory: 42708 grad_norm: 4.4074 loss: 1.7792 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.7792 2023/02/18 02:46:24 - mmengine - INFO - Epoch(train) [19][240/660] lr: 1.0000e-02 eta: 3:42:24 time: 0.6250 data_time: 0.0301 memory: 42708 grad_norm: 4.5296 loss: 1.8273 top1_acc: 0.3125 top5_acc: 0.7188 loss_cls: 1.8273 2023/02/18 02:46:37 - mmengine - INFO - Epoch(train) [19][260/660] lr: 1.0000e-02 eta: 3:42:11 time: 0.6354 data_time: 0.0328 memory: 42708 grad_norm: 4.3989 loss: 1.8042 top1_acc: 0.5312 top5_acc: 0.6562 loss_cls: 1.8042 2023/02/18 02:46:50 - mmengine - INFO - Epoch(train) [19][280/660] lr: 1.0000e-02 eta: 3:41:58 time: 0.6281 data_time: 0.0290 memory: 42708 grad_norm: 4.3527 loss: 1.8576 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.8576 2023/02/18 02:47:02 - mmengine - INFO - Epoch(train) [19][300/660] lr: 1.0000e-02 eta: 3:41:45 time: 0.6392 data_time: 0.0350 memory: 42708 grad_norm: 4.4405 loss: 1.8383 top1_acc: 0.3125 top5_acc: 0.6562 loss_cls: 1.8383 2023/02/18 02:47:15 - mmengine - INFO - Epoch(train) [19][320/660] lr: 1.0000e-02 eta: 3:41:32 time: 0.6258 data_time: 0.0295 memory: 42708 grad_norm: 4.3775 loss: 1.9375 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.9375 2023/02/18 02:47:28 - mmengine - INFO - Epoch(train) [19][340/660] lr: 1.0000e-02 eta: 3:41:19 time: 0.6388 data_time: 0.0335 memory: 42708 grad_norm: 4.5134 loss: 1.9036 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.9036 2023/02/18 02:47:40 - mmengine - INFO - Epoch(train) [19][360/660] lr: 1.0000e-02 eta: 3:41:06 time: 0.6285 data_time: 0.0316 memory: 42708 grad_norm: 4.4704 loss: 1.8801 top1_acc: 0.4688 top5_acc: 0.6562 loss_cls: 1.8801 2023/02/18 02:47:53 - mmengine - INFO - Epoch(train) [19][380/660] lr: 1.0000e-02 eta: 3:40:53 time: 0.6379 data_time: 0.0334 memory: 42708 grad_norm: 4.5023 loss: 1.9229 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.9229 2023/02/18 02:48:06 - mmengine - INFO - Epoch(train) [19][400/660] lr: 1.0000e-02 eta: 3:40:40 time: 0.6292 data_time: 0.0292 memory: 42708 grad_norm: 4.4021 loss: 1.7495 top1_acc: 0.5938 top5_acc: 0.7188 loss_cls: 1.7495 2023/02/18 02:48:18 - mmengine - INFO - Epoch(train) [19][420/660] lr: 1.0000e-02 eta: 3:40:27 time: 0.6417 data_time: 0.0320 memory: 42708 grad_norm: 4.3448 loss: 1.8266 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8266 2023/02/18 02:48:31 - mmengine - INFO - Epoch(train) [19][440/660] lr: 1.0000e-02 eta: 3:40:14 time: 0.6276 data_time: 0.0294 memory: 42708 grad_norm: 4.5058 loss: 1.8700 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.8700 2023/02/18 02:48:44 - mmengine - INFO - Epoch(train) [19][460/660] lr: 1.0000e-02 eta: 3:40:01 time: 0.6375 data_time: 0.0329 memory: 42708 grad_norm: 4.4158 loss: 1.8746 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8746 2023/02/18 02:48:56 - mmengine - INFO - Epoch(train) [19][480/660] lr: 1.0000e-02 eta: 3:39:48 time: 0.6340 data_time: 0.0284 memory: 42708 grad_norm: 4.3777 loss: 1.7424 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.7424 2023/02/18 02:49:09 - mmengine - INFO - Epoch(train) [19][500/660] lr: 1.0000e-02 eta: 3:39:35 time: 0.6332 data_time: 0.0317 memory: 42708 grad_norm: 4.4632 loss: 1.7635 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.7635 2023/02/18 02:49:22 - mmengine - INFO - Epoch(train) [19][520/660] lr: 1.0000e-02 eta: 3:39:22 time: 0.6270 data_time: 0.0280 memory: 42708 grad_norm: 4.3537 loss: 1.9964 top1_acc: 0.3438 top5_acc: 0.8125 loss_cls: 1.9964 2023/02/18 02:49:34 - mmengine - INFO - Epoch(train) [19][540/660] lr: 1.0000e-02 eta: 3:39:09 time: 0.6360 data_time: 0.0322 memory: 42708 grad_norm: 4.3684 loss: 1.8381 top1_acc: 0.3438 top5_acc: 0.8125 loss_cls: 1.8381 2023/02/18 02:49:47 - mmengine - INFO - Epoch(train) [19][560/660] lr: 1.0000e-02 eta: 3:38:56 time: 0.6295 data_time: 0.0273 memory: 42708 grad_norm: 4.3282 loss: 1.8570 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.8570 2023/02/18 02:50:00 - mmengine - INFO - Epoch(train) [19][580/660] lr: 1.0000e-02 eta: 3:38:43 time: 0.6366 data_time: 0.0344 memory: 42708 grad_norm: 4.4044 loss: 1.9545 top1_acc: 0.2500 top5_acc: 0.7188 loss_cls: 1.9545 2023/02/18 02:50:12 - mmengine - INFO - Epoch(train) [19][600/660] lr: 1.0000e-02 eta: 3:38:30 time: 0.6271 data_time: 0.0298 memory: 42708 grad_norm: 4.4814 loss: 1.9021 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 1.9021 2023/02/18 02:50:25 - mmengine - INFO - Epoch(train) [19][620/660] lr: 1.0000e-02 eta: 3:38:17 time: 0.6332 data_time: 0.0319 memory: 42708 grad_norm: 4.4227 loss: 1.8206 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.8206 2023/02/18 02:50:37 - mmengine - INFO - Epoch(train) [19][640/660] lr: 1.0000e-02 eta: 3:38:04 time: 0.6257 data_time: 0.0269 memory: 42708 grad_norm: 4.4069 loss: 1.9624 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.9624 2023/02/18 02:50:50 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:50:50 - mmengine - INFO - Epoch(train) [19][660/660] lr: 1.0000e-02 eta: 3:37:51 time: 0.6187 data_time: 0.0266 memory: 42708 grad_norm: 4.4924 loss: 1.8767 top1_acc: 0.4815 top5_acc: 0.7778 loss_cls: 1.8767 2023/02/18 02:51:04 - mmengine - INFO - Epoch(train) [20][ 20/660] lr: 1.0000e-02 eta: 3:37:40 time: 0.7100 data_time: 0.1155 memory: 42708 grad_norm: 4.2799 loss: 1.8510 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.8510 2023/02/18 02:51:17 - mmengine - INFO - Epoch(train) [20][ 40/660] lr: 1.0000e-02 eta: 3:37:27 time: 0.6244 data_time: 0.0304 memory: 42708 grad_norm: 4.2632 loss: 1.7212 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.7212 2023/02/18 02:51:29 - mmengine - INFO - Epoch(train) [20][ 60/660] lr: 1.0000e-02 eta: 3:37:14 time: 0.6295 data_time: 0.0350 memory: 42708 grad_norm: 4.3548 loss: 1.7318 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.7318 2023/02/18 02:51:42 - mmengine - INFO - Epoch(train) [20][ 80/660] lr: 1.0000e-02 eta: 3:37:00 time: 0.6223 data_time: 0.0310 memory: 42708 grad_norm: 4.4328 loss: 1.7571 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7571 2023/02/18 02:51:54 - mmengine - INFO - Epoch(train) [20][100/660] lr: 1.0000e-02 eta: 3:36:47 time: 0.6302 data_time: 0.0343 memory: 42708 grad_norm: 4.3213 loss: 1.8759 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.8759 2023/02/18 02:52:07 - mmengine - INFO - Epoch(train) [20][120/660] lr: 1.0000e-02 eta: 3:36:34 time: 0.6225 data_time: 0.0305 memory: 42708 grad_norm: 4.4632 loss: 1.8545 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.8545 2023/02/18 02:52:19 - mmengine - INFO - Epoch(train) [20][140/660] lr: 1.0000e-02 eta: 3:36:21 time: 0.6331 data_time: 0.0335 memory: 42708 grad_norm: 4.4097 loss: 1.7602 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.7602 2023/02/18 02:52:32 - mmengine - INFO - Epoch(train) [20][160/660] lr: 1.0000e-02 eta: 3:36:08 time: 0.6286 data_time: 0.0344 memory: 42708 grad_norm: 4.3615 loss: 1.8028 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.8028 2023/02/18 02:52:44 - mmengine - INFO - Epoch(train) [20][180/660] lr: 1.0000e-02 eta: 3:35:55 time: 0.6291 data_time: 0.0345 memory: 42708 grad_norm: 4.4562 loss: 1.8584 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.8584 2023/02/18 02:52:57 - mmengine - INFO - Epoch(train) [20][200/660] lr: 1.0000e-02 eta: 3:35:41 time: 0.6173 data_time: 0.0310 memory: 42708 grad_norm: 4.5259 loss: 1.9294 top1_acc: 0.3750 top5_acc: 0.7188 loss_cls: 1.9294 2023/02/18 02:53:09 - mmengine - INFO - Epoch(train) [20][220/660] lr: 1.0000e-02 eta: 3:35:28 time: 0.6310 data_time: 0.0344 memory: 42708 grad_norm: 4.3485 loss: 1.7762 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.7762 2023/02/18 02:53:22 - mmengine - INFO - Epoch(train) [20][240/660] lr: 1.0000e-02 eta: 3:35:15 time: 0.6242 data_time: 0.0305 memory: 42708 grad_norm: 4.4434 loss: 1.8069 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.8069 2023/02/18 02:53:35 - mmengine - INFO - Epoch(train) [20][260/660] lr: 1.0000e-02 eta: 3:35:02 time: 0.6318 data_time: 0.0369 memory: 42708 grad_norm: 4.4020 loss: 1.7778 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.7778 2023/02/18 02:53:47 - mmengine - INFO - Epoch(train) [20][280/660] lr: 1.0000e-02 eta: 3:34:49 time: 0.6262 data_time: 0.0299 memory: 42708 grad_norm: 4.4451 loss: 1.7609 top1_acc: 0.4062 top5_acc: 0.6875 loss_cls: 1.7609 2023/02/18 02:54:00 - mmengine - INFO - Epoch(train) [20][300/660] lr: 1.0000e-02 eta: 3:34:36 time: 0.6292 data_time: 0.0335 memory: 42708 grad_norm: 4.4146 loss: 1.7791 top1_acc: 0.7500 top5_acc: 0.8438 loss_cls: 1.7791 2023/02/18 02:54:12 - mmengine - INFO - Epoch(train) [20][320/660] lr: 1.0000e-02 eta: 3:34:23 time: 0.6206 data_time: 0.0292 memory: 42708 grad_norm: 4.4314 loss: 1.8044 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.8044 2023/02/18 02:54:25 - mmengine - INFO - Epoch(train) [20][340/660] lr: 1.0000e-02 eta: 3:34:10 time: 0.6308 data_time: 0.0352 memory: 42708 grad_norm: 4.4603 loss: 1.7919 top1_acc: 0.4062 top5_acc: 0.7188 loss_cls: 1.7919 2023/02/18 02:54:37 - mmengine - INFO - Epoch(train) [20][360/660] lr: 1.0000e-02 eta: 3:33:56 time: 0.6248 data_time: 0.0301 memory: 42708 grad_norm: 4.3936 loss: 1.8621 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.8621 2023/02/18 02:54:50 - mmengine - INFO - Epoch(train) [20][380/660] lr: 1.0000e-02 eta: 3:33:43 time: 0.6307 data_time: 0.0376 memory: 42708 grad_norm: 4.4226 loss: 1.8551 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.8551 2023/02/18 02:55:02 - mmengine - INFO - Epoch(train) [20][400/660] lr: 1.0000e-02 eta: 3:33:30 time: 0.6242 data_time: 0.0304 memory: 42708 grad_norm: 4.4396 loss: 1.8896 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.8896 2023/02/18 02:55:15 - mmengine - INFO - Epoch(train) [20][420/660] lr: 1.0000e-02 eta: 3:33:17 time: 0.6293 data_time: 0.0362 memory: 42708 grad_norm: 4.4986 loss: 1.8950 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.8950 2023/02/18 02:55:27 - mmengine - INFO - Epoch(train) [20][440/660] lr: 1.0000e-02 eta: 3:33:04 time: 0.6234 data_time: 0.0325 memory: 42708 grad_norm: 4.4719 loss: 1.7894 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.7894 2023/02/18 02:55:40 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:55:40 - mmengine - INFO - Epoch(train) [20][460/660] lr: 1.0000e-02 eta: 3:32:51 time: 0.6358 data_time: 0.0386 memory: 42708 grad_norm: 4.4684 loss: 1.8100 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.8100 2023/02/18 02:55:52 - mmengine - INFO - Epoch(train) [20][480/660] lr: 1.0000e-02 eta: 3:32:38 time: 0.6171 data_time: 0.0312 memory: 42708 grad_norm: 4.4121 loss: 1.9581 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 1.9581 2023/02/18 02:56:05 - mmengine - INFO - Epoch(train) [20][500/660] lr: 1.0000e-02 eta: 3:32:25 time: 0.6295 data_time: 0.0350 memory: 42708 grad_norm: 4.5447 loss: 1.7709 top1_acc: 0.4688 top5_acc: 0.9375 loss_cls: 1.7709 2023/02/18 02:56:18 - mmengine - INFO - Epoch(train) [20][520/660] lr: 1.0000e-02 eta: 3:32:11 time: 0.6264 data_time: 0.0342 memory: 42708 grad_norm: 4.4250 loss: 1.8474 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.8474 2023/02/18 02:56:30 - mmengine - INFO - Epoch(train) [20][540/660] lr: 1.0000e-02 eta: 3:31:58 time: 0.6254 data_time: 0.0354 memory: 42708 grad_norm: 4.4245 loss: 1.8514 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.8514 2023/02/18 02:56:42 - mmengine - INFO - Epoch(train) [20][560/660] lr: 1.0000e-02 eta: 3:31:45 time: 0.6222 data_time: 0.0310 memory: 42708 grad_norm: 4.3864 loss: 1.7897 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.7897 2023/02/18 02:56:55 - mmengine - INFO - Epoch(train) [20][580/660] lr: 1.0000e-02 eta: 3:31:32 time: 0.6288 data_time: 0.0365 memory: 42708 grad_norm: 4.3779 loss: 1.8260 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.8260 2023/02/18 02:57:08 - mmengine - INFO - Epoch(train) [20][600/660] lr: 1.0000e-02 eta: 3:31:19 time: 0.6252 data_time: 0.0299 memory: 42708 grad_norm: 4.4926 loss: 1.8988 top1_acc: 0.4688 top5_acc: 0.6875 loss_cls: 1.8988 2023/02/18 02:57:20 - mmengine - INFO - Epoch(train) [20][620/660] lr: 1.0000e-02 eta: 3:31:06 time: 0.6336 data_time: 0.0363 memory: 42708 grad_norm: 4.4986 loss: 1.7397 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.7397 2023/02/18 02:57:33 - mmengine - INFO - Epoch(train) [20][640/660] lr: 1.0000e-02 eta: 3:30:52 time: 0.6175 data_time: 0.0316 memory: 42708 grad_norm: 4.4054 loss: 1.6869 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.6869 2023/02/18 02:57:45 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 02:57:45 - mmengine - INFO - Epoch(train) [20][660/660] lr: 1.0000e-02 eta: 3:30:39 time: 0.6144 data_time: 0.0305 memory: 42708 grad_norm: 4.4522 loss: 1.8153 top1_acc: 0.4815 top5_acc: 0.8148 loss_cls: 1.8153 2023/02/18 02:57:52 - mmengine - INFO - Epoch(val) [20][20/97] eta: 0:00:26 time: 0.3391 data_time: 0.1183 memory: 6154 2023/02/18 02:57:57 - mmengine - INFO - Epoch(val) [20][40/97] eta: 0:00:16 time: 0.2438 data_time: 0.0335 memory: 6154 2023/02/18 02:58:02 - mmengine - INFO - Epoch(val) [20][60/97] eta: 0:00:10 time: 0.2527 data_time: 0.0421 memory: 6154 2023/02/18 02:58:06 - mmengine - INFO - Epoch(val) [20][80/97] eta: 0:00:04 time: 0.2418 data_time: 0.0335 memory: 6154 2023/02/18 02:58:11 - mmengine - INFO - Epoch(val) [20][97/97] acc/top1: 0.3168 acc/top5: 0.6229 acc/mean1: 0.2560 2023/02/18 02:58:26 - mmengine - INFO - Epoch(train) [21][ 20/660] lr: 1.0000e-03 eta: 3:30:29 time: 0.7327 data_time: 0.1161 memory: 42708 grad_norm: 4.3721 loss: 1.7609 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.7609 2023/02/18 02:58:38 - mmengine - INFO - Epoch(train) [21][ 40/660] lr: 1.0000e-03 eta: 3:30:16 time: 0.6246 data_time: 0.0296 memory: 42708 grad_norm: 4.2884 loss: 1.7388 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.7388 2023/02/18 02:58:51 - mmengine - INFO - Epoch(train) [21][ 60/660] lr: 1.0000e-03 eta: 3:30:03 time: 0.6338 data_time: 0.0374 memory: 42708 grad_norm: 4.1701 loss: 1.6555 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.6555 2023/02/18 02:59:03 - mmengine - INFO - Epoch(train) [21][ 80/660] lr: 1.0000e-03 eta: 3:29:50 time: 0.6279 data_time: 0.0317 memory: 42708 grad_norm: 4.0744 loss: 1.6577 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.6577 2023/02/18 02:59:16 - mmengine - INFO - Epoch(train) [21][100/660] lr: 1.0000e-03 eta: 3:29:37 time: 0.6363 data_time: 0.0374 memory: 42708 grad_norm: 4.0848 loss: 1.7082 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.7082 2023/02/18 02:59:29 - mmengine - INFO - Epoch(train) [21][120/660] lr: 1.0000e-03 eta: 3:29:24 time: 0.6263 data_time: 0.0342 memory: 42708 grad_norm: 4.1817 loss: 1.6946 top1_acc: 0.4062 top5_acc: 0.8750 loss_cls: 1.6946 2023/02/18 02:59:41 - mmengine - INFO - Epoch(train) [21][140/660] lr: 1.0000e-03 eta: 3:29:11 time: 0.6383 data_time: 0.0354 memory: 42708 grad_norm: 4.1788 loss: 1.7118 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.7118 2023/02/18 02:59:54 - mmengine - INFO - Epoch(train) [21][160/660] lr: 1.0000e-03 eta: 3:28:58 time: 0.6247 data_time: 0.0300 memory: 42708 grad_norm: 4.1273 loss: 1.4854 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4854 2023/02/18 03:00:07 - mmengine - INFO - Epoch(train) [21][180/660] lr: 1.0000e-03 eta: 3:28:45 time: 0.6407 data_time: 0.0332 memory: 42708 grad_norm: 4.0691 loss: 1.5905 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.5905 2023/02/18 03:00:19 - mmengine - INFO - Epoch(train) [21][200/660] lr: 1.0000e-03 eta: 3:28:32 time: 0.6261 data_time: 0.0305 memory: 42708 grad_norm: 4.0570 loss: 1.5400 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.5400 2023/02/18 03:00:32 - mmengine - INFO - Epoch(train) [21][220/660] lr: 1.0000e-03 eta: 3:28:19 time: 0.6349 data_time: 0.0349 memory: 42708 grad_norm: 4.1824 loss: 1.5811 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.5811 2023/02/18 03:00:44 - mmengine - INFO - Epoch(train) [21][240/660] lr: 1.0000e-03 eta: 3:28:06 time: 0.6241 data_time: 0.0310 memory: 42708 grad_norm: 4.1121 loss: 1.6984 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.6984 2023/02/18 03:00:57 - mmengine - INFO - Epoch(train) [21][260/660] lr: 1.0000e-03 eta: 3:27:53 time: 0.6329 data_time: 0.0343 memory: 42708 grad_norm: 4.1792 loss: 1.5788 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 1.5788 2023/02/18 03:01:09 - mmengine - INFO - Epoch(train) [21][280/660] lr: 1.0000e-03 eta: 3:27:40 time: 0.6232 data_time: 0.0293 memory: 42708 grad_norm: 4.1587 loss: 1.5991 top1_acc: 0.6562 top5_acc: 0.7500 loss_cls: 1.5991 2023/02/18 03:01:22 - mmengine - INFO - Epoch(train) [21][300/660] lr: 1.0000e-03 eta: 3:27:27 time: 0.6381 data_time: 0.0351 memory: 42708 grad_norm: 4.1531 loss: 1.5516 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 1.5516 2023/02/18 03:01:35 - mmengine - INFO - Epoch(train) [21][320/660] lr: 1.0000e-03 eta: 3:27:14 time: 0.6257 data_time: 0.0311 memory: 42708 grad_norm: 4.1946 loss: 1.6077 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.6077 2023/02/18 03:01:47 - mmengine - INFO - Epoch(train) [21][340/660] lr: 1.0000e-03 eta: 3:27:01 time: 0.6375 data_time: 0.0347 memory: 42708 grad_norm: 4.2059 loss: 1.6921 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 1.6921 2023/02/18 03:02:00 - mmengine - INFO - Epoch(train) [21][360/660] lr: 1.0000e-03 eta: 3:26:48 time: 0.6226 data_time: 0.0301 memory: 42708 grad_norm: 4.1472 loss: 1.6755 top1_acc: 0.4375 top5_acc: 0.6875 loss_cls: 1.6755 2023/02/18 03:02:13 - mmengine - INFO - Epoch(train) [21][380/660] lr: 1.0000e-03 eta: 3:26:35 time: 0.6438 data_time: 0.0359 memory: 42708 grad_norm: 4.1873 loss: 1.6033 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.6033 2023/02/18 03:02:25 - mmengine - INFO - Epoch(train) [21][400/660] lr: 1.0000e-03 eta: 3:26:22 time: 0.6305 data_time: 0.0348 memory: 42708 grad_norm: 4.1805 loss: 1.6087 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.6087 2023/02/18 03:02:38 - mmengine - INFO - Epoch(train) [21][420/660] lr: 1.0000e-03 eta: 3:26:10 time: 0.6369 data_time: 0.0357 memory: 42708 grad_norm: 4.0853 loss: 1.6668 top1_acc: 0.4062 top5_acc: 0.5938 loss_cls: 1.6668 2023/02/18 03:02:51 - mmengine - INFO - Epoch(train) [21][440/660] lr: 1.0000e-03 eta: 3:25:56 time: 0.6246 data_time: 0.0310 memory: 42708 grad_norm: 4.1053 loss: 1.5132 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 1.5132 2023/02/18 03:03:03 - mmengine - INFO - Epoch(train) [21][460/660] lr: 1.0000e-03 eta: 3:25:43 time: 0.6322 data_time: 0.0342 memory: 42708 grad_norm: 4.1957 loss: 1.6118 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.6118 2023/02/18 03:03:16 - mmengine - INFO - Epoch(train) [21][480/660] lr: 1.0000e-03 eta: 3:25:30 time: 0.6201 data_time: 0.0314 memory: 42708 grad_norm: 4.1539 loss: 1.6407 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.6407 2023/02/18 03:03:28 - mmengine - INFO - Epoch(train) [21][500/660] lr: 1.0000e-03 eta: 3:25:17 time: 0.6361 data_time: 0.0350 memory: 42708 grad_norm: 4.0432 loss: 1.6267 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.6267 2023/02/18 03:03:41 - mmengine - INFO - Epoch(train) [21][520/660] lr: 1.0000e-03 eta: 3:25:04 time: 0.6223 data_time: 0.0307 memory: 42708 grad_norm: 4.1919 loss: 1.6001 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.6001 2023/02/18 03:03:54 - mmengine - INFO - Epoch(train) [21][540/660] lr: 1.0000e-03 eta: 3:24:51 time: 0.6364 data_time: 0.0389 memory: 42708 grad_norm: 4.1140 loss: 1.6288 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 1.6288 2023/02/18 03:04:06 - mmengine - INFO - Epoch(train) [21][560/660] lr: 1.0000e-03 eta: 3:24:38 time: 0.6254 data_time: 0.0302 memory: 42708 grad_norm: 4.2580 loss: 1.6262 top1_acc: 0.4062 top5_acc: 0.8750 loss_cls: 1.6262 2023/02/18 03:04:19 - mmengine - INFO - Epoch(train) [21][580/660] lr: 1.0000e-03 eta: 3:24:25 time: 0.6349 data_time: 0.0339 memory: 42708 grad_norm: 4.0762 loss: 1.6459 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.6459 2023/02/18 03:04:31 - mmengine - INFO - Epoch(train) [21][600/660] lr: 1.0000e-03 eta: 3:24:12 time: 0.6261 data_time: 0.0298 memory: 42708 grad_norm: 4.0970 loss: 1.5366 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.5366 2023/02/18 03:04:44 - mmengine - INFO - Epoch(train) [21][620/660] lr: 1.0000e-03 eta: 3:23:59 time: 0.6359 data_time: 0.0351 memory: 42708 grad_norm: 4.1637 loss: 1.5155 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.5155 2023/02/18 03:04:57 - mmengine - INFO - Epoch(train) [21][640/660] lr: 1.0000e-03 eta: 3:23:46 time: 0.6283 data_time: 0.0361 memory: 42708 grad_norm: 4.2535 loss: 1.5711 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.5711 2023/02/18 03:05:09 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:05:09 - mmengine - INFO - Epoch(train) [21][660/660] lr: 1.0000e-03 eta: 3:23:33 time: 0.6194 data_time: 0.0295 memory: 42708 grad_norm: 4.2194 loss: 1.5525 top1_acc: 0.3704 top5_acc: 0.8889 loss_cls: 1.5525 2023/02/18 03:05:09 - mmengine - INFO - Saving checkpoint at 21 epochs 2023/02/18 03:05:24 - mmengine - INFO - Epoch(train) [22][ 20/660] lr: 1.0000e-03 eta: 3:23:22 time: 0.7076 data_time: 0.1178 memory: 42708 grad_norm: 4.0772 loss: 1.5373 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.5373 2023/02/18 03:05:37 - mmengine - INFO - Epoch(train) [22][ 40/660] lr: 1.0000e-03 eta: 3:23:09 time: 0.6211 data_time: 0.0309 memory: 42708 grad_norm: 4.1625 loss: 1.5835 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.5835 2023/02/18 03:05:49 - mmengine - INFO - Epoch(train) [22][ 60/660] lr: 1.0000e-03 eta: 3:22:56 time: 0.6250 data_time: 0.0341 memory: 42708 grad_norm: 4.0962 loss: 1.5403 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.5403 2023/02/18 03:06:02 - mmengine - INFO - Epoch(train) [22][ 80/660] lr: 1.0000e-03 eta: 3:22:43 time: 0.6204 data_time: 0.0325 memory: 42708 grad_norm: 4.1636 loss: 1.5476 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.5476 2023/02/18 03:06:14 - mmengine - INFO - Epoch(train) [22][100/660] lr: 1.0000e-03 eta: 3:22:30 time: 0.6357 data_time: 0.0365 memory: 42708 grad_norm: 4.2696 loss: 1.5006 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.5006 2023/02/18 03:06:27 - mmengine - INFO - Epoch(train) [22][120/660] lr: 1.0000e-03 eta: 3:22:17 time: 0.6250 data_time: 0.0310 memory: 42708 grad_norm: 4.1539 loss: 1.5910 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.5910 2023/02/18 03:06:39 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:06:39 - mmengine - INFO - Epoch(train) [22][140/660] lr: 1.0000e-03 eta: 3:22:04 time: 0.6334 data_time: 0.0347 memory: 42708 grad_norm: 4.1700 loss: 1.6435 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.6435 2023/02/18 03:06:52 - mmengine - INFO - Epoch(train) [22][160/660] lr: 1.0000e-03 eta: 3:21:51 time: 0.6206 data_time: 0.0328 memory: 42708 grad_norm: 4.1289 loss: 1.6407 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.6407 2023/02/18 03:07:05 - mmengine - INFO - Epoch(train) [22][180/660] lr: 1.0000e-03 eta: 3:21:38 time: 0.6413 data_time: 0.0344 memory: 42708 grad_norm: 4.1263 loss: 1.5127 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.5127 2023/02/18 03:07:17 - mmengine - INFO - Epoch(train) [22][200/660] lr: 1.0000e-03 eta: 3:21:25 time: 0.6229 data_time: 0.0307 memory: 42708 grad_norm: 4.1852 loss: 1.5506 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5506 2023/02/18 03:07:30 - mmengine - INFO - Epoch(train) [22][220/660] lr: 1.0000e-03 eta: 3:21:12 time: 0.6336 data_time: 0.0351 memory: 42708 grad_norm: 4.1556 loss: 1.5858 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.5858 2023/02/18 03:07:42 - mmengine - INFO - Epoch(train) [22][240/660] lr: 1.0000e-03 eta: 3:20:59 time: 0.6224 data_time: 0.0323 memory: 42708 grad_norm: 4.2678 loss: 1.4813 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4813 2023/02/18 03:07:55 - mmengine - INFO - Epoch(train) [22][260/660] lr: 1.0000e-03 eta: 3:20:46 time: 0.6339 data_time: 0.0347 memory: 42708 grad_norm: 4.1628 loss: 1.5568 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5568 2023/02/18 03:08:07 - mmengine - INFO - Epoch(train) [22][280/660] lr: 1.0000e-03 eta: 3:20:33 time: 0.6236 data_time: 0.0313 memory: 42708 grad_norm: 4.1934 loss: 1.4209 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4209 2023/02/18 03:08:20 - mmengine - INFO - Epoch(train) [22][300/660] lr: 1.0000e-03 eta: 3:20:20 time: 0.6342 data_time: 0.0370 memory: 42708 grad_norm: 4.1432 loss: 1.5216 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.5216 2023/02/18 03:08:33 - mmengine - INFO - Epoch(train) [22][320/660] lr: 1.0000e-03 eta: 3:20:07 time: 0.6281 data_time: 0.0318 memory: 42708 grad_norm: 4.2322 loss: 1.6442 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.6442 2023/02/18 03:08:46 - mmengine - INFO - Epoch(train) [22][340/660] lr: 1.0000e-03 eta: 3:19:54 time: 0.6429 data_time: 0.0410 memory: 42708 grad_norm: 4.1178 loss: 1.5115 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.5115 2023/02/18 03:08:58 - mmengine - INFO - Epoch(train) [22][360/660] lr: 1.0000e-03 eta: 3:19:41 time: 0.6240 data_time: 0.0340 memory: 42708 grad_norm: 4.1902 loss: 1.5935 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.5935 2023/02/18 03:09:11 - mmengine - INFO - Epoch(train) [22][380/660] lr: 1.0000e-03 eta: 3:19:28 time: 0.6348 data_time: 0.0367 memory: 42708 grad_norm: 4.2822 loss: 1.6451 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.6451 2023/02/18 03:09:23 - mmengine - INFO - Epoch(train) [22][400/660] lr: 1.0000e-03 eta: 3:19:15 time: 0.6251 data_time: 0.0347 memory: 42708 grad_norm: 4.2386 loss: 1.5225 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.5225 2023/02/18 03:09:36 - mmengine - INFO - Epoch(train) [22][420/660] lr: 1.0000e-03 eta: 3:19:02 time: 0.6344 data_time: 0.0387 memory: 42708 grad_norm: 4.1217 loss: 1.5222 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.5222 2023/02/18 03:09:48 - mmengine - INFO - Epoch(train) [22][440/660] lr: 1.0000e-03 eta: 3:18:49 time: 0.6213 data_time: 0.0327 memory: 42708 grad_norm: 4.2186 loss: 1.4355 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.4355 2023/02/18 03:10:01 - mmengine - INFO - Epoch(train) [22][460/660] lr: 1.0000e-03 eta: 3:18:36 time: 0.6323 data_time: 0.0369 memory: 42708 grad_norm: 4.2392 loss: 1.5320 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.5320 2023/02/18 03:10:14 - mmengine - INFO - Epoch(train) [22][480/660] lr: 1.0000e-03 eta: 3:18:23 time: 0.6247 data_time: 0.0355 memory: 42708 grad_norm: 4.1702 loss: 1.6014 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 1.6014 2023/02/18 03:10:26 - mmengine - INFO - Epoch(train) [22][500/660] lr: 1.0000e-03 eta: 3:18:10 time: 0.6354 data_time: 0.0370 memory: 42708 grad_norm: 4.2127 loss: 1.5176 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.5176 2023/02/18 03:10:39 - mmengine - INFO - Epoch(train) [22][520/660] lr: 1.0000e-03 eta: 3:17:57 time: 0.6219 data_time: 0.0312 memory: 42708 grad_norm: 4.1908 loss: 1.6617 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.6617 2023/02/18 03:10:51 - mmengine - INFO - Epoch(train) [22][540/660] lr: 1.0000e-03 eta: 3:17:44 time: 0.6352 data_time: 0.0374 memory: 42708 grad_norm: 4.1802 loss: 1.5126 top1_acc: 0.7500 top5_acc: 0.8438 loss_cls: 1.5126 2023/02/18 03:11:04 - mmengine - INFO - Epoch(train) [22][560/660] lr: 1.0000e-03 eta: 3:17:31 time: 0.6243 data_time: 0.0354 memory: 42708 grad_norm: 4.2209 loss: 1.5373 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.5373 2023/02/18 03:11:17 - mmengine - INFO - Epoch(train) [22][580/660] lr: 1.0000e-03 eta: 3:17:18 time: 0.6371 data_time: 0.0381 memory: 42708 grad_norm: 4.2094 loss: 1.4915 top1_acc: 0.4375 top5_acc: 0.8438 loss_cls: 1.4915 2023/02/18 03:11:29 - mmengine - INFO - Epoch(train) [22][600/660] lr: 1.0000e-03 eta: 3:17:05 time: 0.6235 data_time: 0.0326 memory: 42708 grad_norm: 4.1679 loss: 1.5447 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.5447 2023/02/18 03:11:42 - mmengine - INFO - Epoch(train) [22][620/660] lr: 1.0000e-03 eta: 3:16:52 time: 0.6335 data_time: 0.0357 memory: 42708 grad_norm: 4.2035 loss: 1.6196 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.6196 2023/02/18 03:11:54 - mmengine - INFO - Epoch(train) [22][640/660] lr: 1.0000e-03 eta: 3:16:39 time: 0.6238 data_time: 0.0331 memory: 42708 grad_norm: 4.3249 loss: 1.5935 top1_acc: 0.7500 top5_acc: 0.8438 loss_cls: 1.5935 2023/02/18 03:12:07 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:12:07 - mmengine - INFO - Epoch(train) [22][660/660] lr: 1.0000e-03 eta: 3:16:26 time: 0.6165 data_time: 0.0320 memory: 42708 grad_norm: 4.2061 loss: 1.5646 top1_acc: 0.6667 top5_acc: 0.8148 loss_cls: 1.5646 2023/02/18 03:12:21 - mmengine - INFO - Epoch(train) [23][ 20/660] lr: 1.0000e-03 eta: 3:16:15 time: 0.7136 data_time: 0.1233 memory: 42708 grad_norm: 4.2434 loss: 1.5742 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.5742 2023/02/18 03:12:33 - mmengine - INFO - Epoch(train) [23][ 40/660] lr: 1.0000e-03 eta: 3:16:02 time: 0.6169 data_time: 0.0336 memory: 42708 grad_norm: 4.1169 loss: 1.5643 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.5643 2023/02/18 03:12:46 - mmengine - INFO - Epoch(train) [23][ 60/660] lr: 1.0000e-03 eta: 3:15:49 time: 0.6294 data_time: 0.0384 memory: 42708 grad_norm: 4.1999 loss: 1.5420 top1_acc: 0.5000 top5_acc: 0.9688 loss_cls: 1.5420 2023/02/18 03:12:58 - mmengine - INFO - Epoch(train) [23][ 80/660] lr: 1.0000e-03 eta: 3:15:36 time: 0.6207 data_time: 0.0313 memory: 42708 grad_norm: 4.3166 loss: 1.6246 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.6246 2023/02/18 03:13:11 - mmengine - INFO - Epoch(train) [23][100/660] lr: 1.0000e-03 eta: 3:15:23 time: 0.6473 data_time: 0.0368 memory: 42708 grad_norm: 4.2244 loss: 1.5804 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.5804 2023/02/18 03:13:24 - mmengine - INFO - Epoch(train) [23][120/660] lr: 1.0000e-03 eta: 3:15:10 time: 0.6269 data_time: 0.0316 memory: 42708 grad_norm: 4.2048 loss: 1.5858 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.5858 2023/02/18 03:13:36 - mmengine - INFO - Epoch(train) [23][140/660] lr: 1.0000e-03 eta: 3:14:57 time: 0.6399 data_time: 0.0378 memory: 42708 grad_norm: 4.2810 loss: 1.5051 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.5051 2023/02/18 03:13:49 - mmengine - INFO - Epoch(train) [23][160/660] lr: 1.0000e-03 eta: 3:14:44 time: 0.6227 data_time: 0.0333 memory: 42708 grad_norm: 4.2787 loss: 1.5853 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.5853 2023/02/18 03:14:02 - mmengine - INFO - Epoch(train) [23][180/660] lr: 1.0000e-03 eta: 3:14:31 time: 0.6370 data_time: 0.0344 memory: 42708 grad_norm: 4.2305 loss: 1.4115 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4115 2023/02/18 03:14:14 - mmengine - INFO - Epoch(train) [23][200/660] lr: 1.0000e-03 eta: 3:14:18 time: 0.6234 data_time: 0.0310 memory: 42708 grad_norm: 4.3114 loss: 1.4591 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.4591 2023/02/18 03:14:27 - mmengine - INFO - Epoch(train) [23][220/660] lr: 1.0000e-03 eta: 3:14:06 time: 0.6363 data_time: 0.0348 memory: 42708 grad_norm: 4.1874 loss: 1.5097 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.5097 2023/02/18 03:14:39 - mmengine - INFO - Epoch(train) [23][240/660] lr: 1.0000e-03 eta: 3:13:52 time: 0.6248 data_time: 0.0328 memory: 42708 grad_norm: 4.1597 loss: 1.4411 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4411 2023/02/18 03:14:52 - mmengine - INFO - Epoch(train) [23][260/660] lr: 1.0000e-03 eta: 3:13:40 time: 0.6346 data_time: 0.0347 memory: 42708 grad_norm: 4.2442 loss: 1.5767 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.5767 2023/02/18 03:15:05 - mmengine - INFO - Epoch(train) [23][280/660] lr: 1.0000e-03 eta: 3:13:27 time: 0.6267 data_time: 0.0322 memory: 42708 grad_norm: 4.3935 loss: 1.6119 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.6119 2023/02/18 03:15:17 - mmengine - INFO - Epoch(train) [23][300/660] lr: 1.0000e-03 eta: 3:13:14 time: 0.6342 data_time: 0.0351 memory: 42708 grad_norm: 4.2078 loss: 1.5608 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.5608 2023/02/18 03:15:30 - mmengine - INFO - Epoch(train) [23][320/660] lr: 1.0000e-03 eta: 3:13:01 time: 0.6250 data_time: 0.0315 memory: 42708 grad_norm: 4.2587 loss: 1.4843 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.4843 2023/02/18 03:15:43 - mmengine - INFO - Epoch(train) [23][340/660] lr: 1.0000e-03 eta: 3:12:48 time: 0.6431 data_time: 0.0349 memory: 42708 grad_norm: 4.1985 loss: 1.4330 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4330 2023/02/18 03:15:55 - mmengine - INFO - Epoch(train) [23][360/660] lr: 1.0000e-03 eta: 3:12:35 time: 0.6233 data_time: 0.0315 memory: 42708 grad_norm: 4.3023 loss: 1.5310 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.5310 2023/02/18 03:16:08 - mmengine - INFO - Epoch(train) [23][380/660] lr: 1.0000e-03 eta: 3:12:22 time: 0.6406 data_time: 0.0352 memory: 42708 grad_norm: 4.2622 loss: 1.6523 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.6523 2023/02/18 03:16:20 - mmengine - INFO - Epoch(train) [23][400/660] lr: 1.0000e-03 eta: 3:12:09 time: 0.6268 data_time: 0.0333 memory: 42708 grad_norm: 4.2331 loss: 1.4900 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4900 2023/02/18 03:16:33 - mmengine - INFO - Epoch(train) [23][420/660] lr: 1.0000e-03 eta: 3:11:56 time: 0.6358 data_time: 0.0378 memory: 42708 grad_norm: 4.2620 loss: 1.4448 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4448 2023/02/18 03:16:46 - mmengine - INFO - Epoch(train) [23][440/660] lr: 1.0000e-03 eta: 3:11:43 time: 0.6230 data_time: 0.0321 memory: 42708 grad_norm: 4.2830 loss: 1.4785 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4785 2023/02/18 03:16:58 - mmengine - INFO - Epoch(train) [23][460/660] lr: 1.0000e-03 eta: 3:11:31 time: 0.6369 data_time: 0.0360 memory: 42708 grad_norm: 4.2315 loss: 1.4286 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.4286 2023/02/18 03:17:11 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:17:11 - mmengine - INFO - Epoch(train) [23][480/660] lr: 1.0000e-03 eta: 3:11:17 time: 0.6234 data_time: 0.0344 memory: 42708 grad_norm: 4.3136 loss: 1.5001 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.5001 2023/02/18 03:17:24 - mmengine - INFO - Epoch(train) [23][500/660] lr: 1.0000e-03 eta: 3:11:05 time: 0.6374 data_time: 0.0345 memory: 42708 grad_norm: 4.1615 loss: 1.4016 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.4016 2023/02/18 03:17:36 - mmengine - INFO - Epoch(train) [23][520/660] lr: 1.0000e-03 eta: 3:10:52 time: 0.6198 data_time: 0.0320 memory: 42708 grad_norm: 4.2803 loss: 1.5248 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.5248 2023/02/18 03:17:49 - mmengine - INFO - Epoch(train) [23][540/660] lr: 1.0000e-03 eta: 3:10:39 time: 0.6292 data_time: 0.0340 memory: 42708 grad_norm: 4.2542 loss: 1.4726 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.4726 2023/02/18 03:18:01 - mmengine - INFO - Epoch(train) [23][560/660] lr: 1.0000e-03 eta: 3:10:26 time: 0.6253 data_time: 0.0327 memory: 42708 grad_norm: 4.3058 loss: 1.5586 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.5586 2023/02/18 03:18:14 - mmengine - INFO - Epoch(train) [23][580/660] lr: 1.0000e-03 eta: 3:10:13 time: 0.6385 data_time: 0.0313 memory: 42708 grad_norm: 4.4138 loss: 1.5064 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.5064 2023/02/18 03:18:26 - mmengine - INFO - Epoch(train) [23][600/660] lr: 1.0000e-03 eta: 3:10:00 time: 0.6232 data_time: 0.0327 memory: 42708 grad_norm: 4.2488 loss: 1.5797 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5797 2023/02/18 03:18:39 - mmengine - INFO - Epoch(train) [23][620/660] lr: 1.0000e-03 eta: 3:09:47 time: 0.6340 data_time: 0.0342 memory: 42708 grad_norm: 4.2833 loss: 1.4550 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.4550 2023/02/18 03:18:52 - mmengine - INFO - Epoch(train) [23][640/660] lr: 1.0000e-03 eta: 3:09:34 time: 0.6254 data_time: 0.0314 memory: 42708 grad_norm: 4.2868 loss: 1.6239 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.6239 2023/02/18 03:19:04 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:19:04 - mmengine - INFO - Epoch(train) [23][660/660] lr: 1.0000e-03 eta: 3:09:21 time: 0.6149 data_time: 0.0289 memory: 42708 grad_norm: 4.2994 loss: 1.4925 top1_acc: 0.7778 top5_acc: 1.0000 loss_cls: 1.4925 2023/02/18 03:19:18 - mmengine - INFO - Epoch(train) [24][ 20/660] lr: 1.0000e-03 eta: 3:09:10 time: 0.7208 data_time: 0.1130 memory: 42708 grad_norm: 4.3234 loss: 1.5900 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.5900 2023/02/18 03:19:31 - mmengine - INFO - Epoch(train) [24][ 40/660] lr: 1.0000e-03 eta: 3:08:57 time: 0.6290 data_time: 0.0292 memory: 42708 grad_norm: 4.2360 loss: 1.5081 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.5081 2023/02/18 03:19:44 - mmengine - INFO - Epoch(train) [24][ 60/660] lr: 1.0000e-03 eta: 3:08:44 time: 0.6337 data_time: 0.0343 memory: 42708 grad_norm: 4.2653 loss: 1.5413 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.5413 2023/02/18 03:19:56 - mmengine - INFO - Epoch(train) [24][ 80/660] lr: 1.0000e-03 eta: 3:08:31 time: 0.6254 data_time: 0.0283 memory: 42708 grad_norm: 4.2268 loss: 1.4860 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.4860 2023/02/18 03:20:09 - mmengine - INFO - Epoch(train) [24][100/660] lr: 1.0000e-03 eta: 3:08:18 time: 0.6457 data_time: 0.0280 memory: 42708 grad_norm: 4.3274 loss: 1.5294 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 1.5294 2023/02/18 03:20:22 - mmengine - INFO - Epoch(train) [24][120/660] lr: 1.0000e-03 eta: 3:08:06 time: 0.6334 data_time: 0.0272 memory: 42708 grad_norm: 4.3195 loss: 1.4758 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.4758 2023/02/18 03:20:34 - mmengine - INFO - Epoch(train) [24][140/660] lr: 1.0000e-03 eta: 3:07:53 time: 0.6412 data_time: 0.0252 memory: 42708 grad_norm: 4.2979 loss: 1.5083 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.5083 2023/02/18 03:20:47 - mmengine - INFO - Epoch(train) [24][160/660] lr: 1.0000e-03 eta: 3:07:40 time: 0.6407 data_time: 0.0282 memory: 42708 grad_norm: 4.3572 loss: 1.5905 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 1.5905 2023/02/18 03:21:00 - mmengine - INFO - Epoch(train) [24][180/660] lr: 1.0000e-03 eta: 3:07:28 time: 0.6484 data_time: 0.0265 memory: 42708 grad_norm: 4.3208 loss: 1.4281 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4281 2023/02/18 03:21:13 - mmengine - INFO - Epoch(train) [24][200/660] lr: 1.0000e-03 eta: 3:07:15 time: 0.6331 data_time: 0.0270 memory: 42708 grad_norm: 4.2864 loss: 1.4450 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.4450 2023/02/18 03:21:26 - mmengine - INFO - Epoch(train) [24][220/660] lr: 1.0000e-03 eta: 3:07:02 time: 0.6417 data_time: 0.0254 memory: 42708 grad_norm: 4.2431 loss: 1.5370 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.5370 2023/02/18 03:21:39 - mmengine - INFO - Epoch(train) [24][240/660] lr: 1.0000e-03 eta: 3:06:50 time: 0.6452 data_time: 0.0269 memory: 42708 grad_norm: 4.3377 loss: 1.5147 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.5147 2023/02/18 03:21:52 - mmengine - INFO - Epoch(train) [24][260/660] lr: 1.0000e-03 eta: 3:06:37 time: 0.6495 data_time: 0.0257 memory: 42708 grad_norm: 4.2970 loss: 1.5174 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.5174 2023/02/18 03:22:04 - mmengine - INFO - Epoch(train) [24][280/660] lr: 1.0000e-03 eta: 3:06:24 time: 0.6306 data_time: 0.0263 memory: 42708 grad_norm: 4.4520 loss: 1.5837 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.5837 2023/02/18 03:22:17 - mmengine - INFO - Epoch(train) [24][300/660] lr: 1.0000e-03 eta: 3:06:12 time: 0.6503 data_time: 0.0277 memory: 42708 grad_norm: 4.2586 loss: 1.4706 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 1.4706 2023/02/18 03:22:30 - mmengine - INFO - Epoch(train) [24][320/660] lr: 1.0000e-03 eta: 3:05:59 time: 0.6415 data_time: 0.0343 memory: 42708 grad_norm: 4.2860 loss: 1.5583 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.5583 2023/02/18 03:22:43 - mmengine - INFO - Epoch(train) [24][340/660] lr: 1.0000e-03 eta: 3:05:46 time: 0.6394 data_time: 0.0274 memory: 42708 grad_norm: 4.3298 loss: 1.4165 top1_acc: 0.5938 top5_acc: 1.0000 loss_cls: 1.4165 2023/02/18 03:22:55 - mmengine - INFO - Epoch(train) [24][360/660] lr: 1.0000e-03 eta: 3:05:33 time: 0.6310 data_time: 0.0268 memory: 42708 grad_norm: 4.3549 loss: 1.4899 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.4899 2023/02/18 03:23:08 - mmengine - INFO - Epoch(train) [24][380/660] lr: 1.0000e-03 eta: 3:05:21 time: 0.6426 data_time: 0.0259 memory: 42708 grad_norm: 4.4542 loss: 1.4845 top1_acc: 0.4688 top5_acc: 0.8125 loss_cls: 1.4845 2023/02/18 03:23:21 - mmengine - INFO - Epoch(train) [24][400/660] lr: 1.0000e-03 eta: 3:05:08 time: 0.6361 data_time: 0.0285 memory: 42708 grad_norm: 4.2814 loss: 1.4994 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.4994 2023/02/18 03:23:34 - mmengine - INFO - Epoch(train) [24][420/660] lr: 1.0000e-03 eta: 3:04:55 time: 0.6415 data_time: 0.0251 memory: 42708 grad_norm: 4.3557 loss: 1.5370 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.5370 2023/02/18 03:23:47 - mmengine - INFO - Epoch(train) [24][440/660] lr: 1.0000e-03 eta: 3:04:42 time: 0.6333 data_time: 0.0263 memory: 42708 grad_norm: 4.3421 loss: 1.5551 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.5551 2023/02/18 03:23:59 - mmengine - INFO - Epoch(train) [24][460/660] lr: 1.0000e-03 eta: 3:04:30 time: 0.6389 data_time: 0.0253 memory: 42708 grad_norm: 4.2310 loss: 1.5327 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.5327 2023/02/18 03:24:12 - mmengine - INFO - Epoch(train) [24][480/660] lr: 1.0000e-03 eta: 3:04:17 time: 0.6313 data_time: 0.0267 memory: 42708 grad_norm: 4.4010 loss: 1.6307 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.6307 2023/02/18 03:24:25 - mmengine - INFO - Epoch(train) [24][500/660] lr: 1.0000e-03 eta: 3:04:04 time: 0.6385 data_time: 0.0263 memory: 42708 grad_norm: 4.3604 loss: 1.5723 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.5723 2023/02/18 03:24:37 - mmengine - INFO - Epoch(train) [24][520/660] lr: 1.0000e-03 eta: 3:03:51 time: 0.6357 data_time: 0.0275 memory: 42708 grad_norm: 4.2951 loss: 1.5170 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.5170 2023/02/18 03:24:50 - mmengine - INFO - Epoch(train) [24][540/660] lr: 1.0000e-03 eta: 3:03:39 time: 0.6457 data_time: 0.0256 memory: 42708 grad_norm: 4.2486 loss: 1.5469 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.5469 2023/02/18 03:25:03 - mmengine - INFO - Epoch(train) [24][560/660] lr: 1.0000e-03 eta: 3:03:26 time: 0.6306 data_time: 0.0269 memory: 42708 grad_norm: 4.3361 loss: 1.6748 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 1.6748 2023/02/18 03:25:16 - mmengine - INFO - Epoch(train) [24][580/660] lr: 1.0000e-03 eta: 3:03:13 time: 0.6390 data_time: 0.0253 memory: 42708 grad_norm: 4.3352 loss: 1.5505 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.5505 2023/02/18 03:25:28 - mmengine - INFO - Epoch(train) [24][600/660] lr: 1.0000e-03 eta: 3:03:00 time: 0.6302 data_time: 0.0264 memory: 42708 grad_norm: 4.3454 loss: 1.5351 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.5351 2023/02/18 03:25:41 - mmengine - INFO - Epoch(train) [24][620/660] lr: 1.0000e-03 eta: 3:02:48 time: 0.6466 data_time: 0.0267 memory: 42708 grad_norm: 4.3165 loss: 1.5396 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.5396 2023/02/18 03:25:54 - mmengine - INFO - Epoch(train) [24][640/660] lr: 1.0000e-03 eta: 3:02:35 time: 0.6367 data_time: 0.0314 memory: 42708 grad_norm: 4.3932 loss: 1.4347 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4347 2023/02/18 03:26:07 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:26:07 - mmengine - INFO - Epoch(train) [24][660/660] lr: 1.0000e-03 eta: 3:02:22 time: 0.6259 data_time: 0.0242 memory: 42708 grad_norm: 4.2810 loss: 1.4936 top1_acc: 0.4815 top5_acc: 0.8889 loss_cls: 1.4936 2023/02/18 03:26:07 - mmengine - INFO - Saving checkpoint at 24 epochs 2023/02/18 03:26:22 - mmengine - INFO - Epoch(train) [25][ 20/660] lr: 1.0000e-03 eta: 3:02:11 time: 0.7137 data_time: 0.1166 memory: 42708 grad_norm: 4.3212 loss: 1.4954 top1_acc: 0.4062 top5_acc: 0.5938 loss_cls: 1.4954 2023/02/18 03:26:34 - mmengine - INFO - Epoch(train) [25][ 40/660] lr: 1.0000e-03 eta: 3:01:58 time: 0.6185 data_time: 0.0296 memory: 42708 grad_norm: 4.3126 loss: 1.3475 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3475 2023/02/18 03:26:47 - mmengine - INFO - Epoch(train) [25][ 60/660] lr: 1.0000e-03 eta: 3:01:45 time: 0.6344 data_time: 0.0274 memory: 42708 grad_norm: 4.3427 loss: 1.5119 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.5119 2023/02/18 03:27:00 - mmengine - INFO - Epoch(train) [25][ 80/660] lr: 1.0000e-03 eta: 3:01:32 time: 0.6257 data_time: 0.0260 memory: 42708 grad_norm: 4.3050 loss: 1.5408 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.5408 2023/02/18 03:27:12 - mmengine - INFO - Epoch(train) [25][100/660] lr: 1.0000e-03 eta: 3:01:19 time: 0.6338 data_time: 0.0280 memory: 42708 grad_norm: 4.3305 loss: 1.6357 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.6357 2023/02/18 03:27:25 - mmengine - INFO - Epoch(train) [25][120/660] lr: 1.0000e-03 eta: 3:01:06 time: 0.6263 data_time: 0.0307 memory: 42708 grad_norm: 4.3676 loss: 1.4865 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.4865 2023/02/18 03:27:37 - mmengine - INFO - Epoch(train) [25][140/660] lr: 1.0000e-03 eta: 3:00:53 time: 0.6353 data_time: 0.0283 memory: 42708 grad_norm: 4.3699 loss: 1.5475 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.5475 2023/02/18 03:27:50 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:27:50 - mmengine - INFO - Epoch(train) [25][160/660] lr: 1.0000e-03 eta: 3:00:40 time: 0.6270 data_time: 0.0268 memory: 42708 grad_norm: 4.3731 loss: 1.4882 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4882 2023/02/18 03:28:03 - mmengine - INFO - Epoch(train) [25][180/660] lr: 1.0000e-03 eta: 3:00:27 time: 0.6373 data_time: 0.0274 memory: 42708 grad_norm: 4.2852 loss: 1.4514 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4514 2023/02/18 03:28:15 - mmengine - INFO - Epoch(train) [25][200/660] lr: 1.0000e-03 eta: 3:00:14 time: 0.6286 data_time: 0.0278 memory: 42708 grad_norm: 4.3121 loss: 1.4578 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4578 2023/02/18 03:28:28 - mmengine - INFO - Epoch(train) [25][220/660] lr: 1.0000e-03 eta: 3:00:02 time: 0.6378 data_time: 0.0295 memory: 42708 grad_norm: 4.2927 loss: 1.5524 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.5524 2023/02/18 03:28:41 - mmengine - INFO - Epoch(train) [25][240/660] lr: 1.0000e-03 eta: 2:59:49 time: 0.6261 data_time: 0.0269 memory: 42708 grad_norm: 4.1919 loss: 1.4225 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.4225 2023/02/18 03:28:53 - mmengine - INFO - Epoch(train) [25][260/660] lr: 1.0000e-03 eta: 2:59:36 time: 0.6416 data_time: 0.0292 memory: 42708 grad_norm: 4.3455 loss: 1.5647 top1_acc: 0.6562 top5_acc: 0.7500 loss_cls: 1.5647 2023/02/18 03:29:06 - mmengine - INFO - Epoch(train) [25][280/660] lr: 1.0000e-03 eta: 2:59:23 time: 0.6204 data_time: 0.0259 memory: 42708 grad_norm: 4.3315 loss: 1.4924 top1_acc: 0.3438 top5_acc: 0.8750 loss_cls: 1.4924 2023/02/18 03:29:19 - mmengine - INFO - Epoch(train) [25][300/660] lr: 1.0000e-03 eta: 2:59:10 time: 0.6367 data_time: 0.0286 memory: 42708 grad_norm: 4.3803 loss: 1.5333 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.5333 2023/02/18 03:29:31 - mmengine - INFO - Epoch(train) [25][320/660] lr: 1.0000e-03 eta: 2:58:57 time: 0.6248 data_time: 0.0269 memory: 42708 grad_norm: 4.3441 loss: 1.5169 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.5169 2023/02/18 03:29:44 - mmengine - INFO - Epoch(train) [25][340/660] lr: 1.0000e-03 eta: 2:58:44 time: 0.6352 data_time: 0.0271 memory: 42708 grad_norm: 4.3605 loss: 1.5847 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.5847 2023/02/18 03:29:56 - mmengine - INFO - Epoch(train) [25][360/660] lr: 1.0000e-03 eta: 2:58:31 time: 0.6207 data_time: 0.0265 memory: 42708 grad_norm: 4.4375 loss: 1.4533 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.4533 2023/02/18 03:30:09 - mmengine - INFO - Epoch(train) [25][380/660] lr: 1.0000e-03 eta: 2:58:18 time: 0.6395 data_time: 0.0286 memory: 42708 grad_norm: 4.3449 loss: 1.4829 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.4829 2023/02/18 03:30:22 - mmengine - INFO - Epoch(train) [25][400/660] lr: 1.0000e-03 eta: 2:58:05 time: 0.6270 data_time: 0.0278 memory: 42708 grad_norm: 4.4004 loss: 1.3488 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3488 2023/02/18 03:30:34 - mmengine - INFO - Epoch(train) [25][420/660] lr: 1.0000e-03 eta: 2:57:53 time: 0.6434 data_time: 0.0326 memory: 42708 grad_norm: 4.2915 loss: 1.4157 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4157 2023/02/18 03:30:47 - mmengine - INFO - Epoch(train) [25][440/660] lr: 1.0000e-03 eta: 2:57:40 time: 0.6240 data_time: 0.0277 memory: 42708 grad_norm: 4.3426 loss: 1.5494 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.5494 2023/02/18 03:31:00 - mmengine - INFO - Epoch(train) [25][460/660] lr: 1.0000e-03 eta: 2:57:27 time: 0.6365 data_time: 0.0282 memory: 42708 grad_norm: 4.3936 loss: 1.4749 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.4749 2023/02/18 03:31:12 - mmengine - INFO - Epoch(train) [25][480/660] lr: 1.0000e-03 eta: 2:57:14 time: 0.6270 data_time: 0.0269 memory: 42708 grad_norm: 4.4343 loss: 1.5334 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.5334 2023/02/18 03:31:25 - mmengine - INFO - Epoch(train) [25][500/660] lr: 1.0000e-03 eta: 2:57:01 time: 0.6415 data_time: 0.0274 memory: 42708 grad_norm: 4.4082 loss: 1.4826 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4826 2023/02/18 03:31:38 - mmengine - INFO - Epoch(train) [25][520/660] lr: 1.0000e-03 eta: 2:56:49 time: 0.6324 data_time: 0.0275 memory: 42708 grad_norm: 4.4254 loss: 1.5233 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.5233 2023/02/18 03:31:51 - mmengine - INFO - Epoch(train) [25][540/660] lr: 1.0000e-03 eta: 2:56:36 time: 0.6465 data_time: 0.0280 memory: 42708 grad_norm: 4.4178 loss: 1.5887 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.5887 2023/02/18 03:32:03 - mmengine - INFO - Epoch(train) [25][560/660] lr: 1.0000e-03 eta: 2:56:23 time: 0.6246 data_time: 0.0277 memory: 42708 grad_norm: 4.3634 loss: 1.4612 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4612 2023/02/18 03:32:16 - mmengine - INFO - Epoch(train) [25][580/660] lr: 1.0000e-03 eta: 2:56:10 time: 0.6370 data_time: 0.0277 memory: 42708 grad_norm: 4.2811 loss: 1.5036 top1_acc: 0.4375 top5_acc: 0.7188 loss_cls: 1.5036 2023/02/18 03:32:28 - mmengine - INFO - Epoch(train) [25][600/660] lr: 1.0000e-03 eta: 2:55:57 time: 0.6267 data_time: 0.0290 memory: 42708 grad_norm: 4.3131 loss: 1.4612 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.4612 2023/02/18 03:32:41 - mmengine - INFO - Epoch(train) [25][620/660] lr: 1.0000e-03 eta: 2:55:44 time: 0.6347 data_time: 0.0288 memory: 42708 grad_norm: 4.4971 loss: 1.4350 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.4350 2023/02/18 03:32:53 - mmengine - INFO - Epoch(train) [25][640/660] lr: 1.0000e-03 eta: 2:55:31 time: 0.6191 data_time: 0.0274 memory: 42708 grad_norm: 4.3675 loss: 1.4861 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.4861 2023/02/18 03:33:06 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:33:06 - mmengine - INFO - Epoch(train) [25][660/660] lr: 1.0000e-03 eta: 2:55:18 time: 0.6107 data_time: 0.0260 memory: 42708 grad_norm: 4.3788 loss: 1.3810 top1_acc: 0.7407 top5_acc: 0.8519 loss_cls: 1.3810 2023/02/18 03:33:12 - mmengine - INFO - Epoch(val) [25][20/97] eta: 0:00:25 time: 0.3313 data_time: 0.1205 memory: 6154 2023/02/18 03:33:17 - mmengine - INFO - Epoch(val) [25][40/97] eta: 0:00:16 time: 0.2508 data_time: 0.0404 memory: 6154 2023/02/18 03:33:22 - mmengine - INFO - Epoch(val) [25][60/97] eta: 0:00:10 time: 0.2553 data_time: 0.0453 memory: 6154 2023/02/18 03:33:27 - mmengine - INFO - Epoch(val) [25][80/97] eta: 0:00:04 time: 0.2413 data_time: 0.0331 memory: 6154 2023/02/18 03:33:32 - mmengine - INFO - Epoch(val) [25][97/97] acc/top1: 0.3692 acc/top5: 0.6769 acc/mean1: 0.3024 2023/02/18 03:33:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/lilin/Repos/mmact_dev/mmaction2/work_dirs/fix_flip/tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb/best_acc/top1_epoch_15.pth is removed 2023/02/18 03:33:32 - mmengine - INFO - The best checkpoint with 0.3692 acc/top1 at 25 epoch is saved to best_acc/top1_epoch_25.pth. 2023/02/18 03:33:47 - mmengine - INFO - Epoch(train) [26][ 20/660] lr: 1.0000e-03 eta: 2:55:07 time: 0.7167 data_time: 0.1236 memory: 42708 grad_norm: 4.3236 loss: 1.4303 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4303 2023/02/18 03:33:59 - mmengine - INFO - Epoch(train) [26][ 40/660] lr: 1.0000e-03 eta: 2:54:54 time: 0.6244 data_time: 0.0329 memory: 42708 grad_norm: 4.3936 loss: 1.4312 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4312 2023/02/18 03:34:12 - mmengine - INFO - Epoch(train) [26][ 60/660] lr: 1.0000e-03 eta: 2:54:41 time: 0.6349 data_time: 0.0330 memory: 42708 grad_norm: 4.3375 loss: 1.4817 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.4817 2023/02/18 03:34:24 - mmengine - INFO - Epoch(train) [26][ 80/660] lr: 1.0000e-03 eta: 2:54:28 time: 0.6239 data_time: 0.0300 memory: 42708 grad_norm: 4.3003 loss: 1.4826 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.4826 2023/02/18 03:34:37 - mmengine - INFO - Epoch(train) [26][100/660] lr: 1.0000e-03 eta: 2:54:15 time: 0.6295 data_time: 0.0346 memory: 42708 grad_norm: 4.3727 loss: 1.4747 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.4747 2023/02/18 03:34:49 - mmengine - INFO - Epoch(train) [26][120/660] lr: 1.0000e-03 eta: 2:54:02 time: 0.6245 data_time: 0.0307 memory: 42708 grad_norm: 4.3525 loss: 1.5149 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.5149 2023/02/18 03:35:02 - mmengine - INFO - Epoch(train) [26][140/660] lr: 1.0000e-03 eta: 2:53:49 time: 0.6329 data_time: 0.0355 memory: 42708 grad_norm: 4.2961 loss: 1.3979 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.3979 2023/02/18 03:35:15 - mmengine - INFO - Epoch(train) [26][160/660] lr: 1.0000e-03 eta: 2:53:36 time: 0.6282 data_time: 0.0325 memory: 42708 grad_norm: 4.2967 loss: 1.4461 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.4461 2023/02/18 03:35:27 - mmengine - INFO - Epoch(train) [26][180/660] lr: 1.0000e-03 eta: 2:53:24 time: 0.6369 data_time: 0.0370 memory: 42708 grad_norm: 4.4425 loss: 1.5072 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.5072 2023/02/18 03:35:40 - mmengine - INFO - Epoch(train) [26][200/660] lr: 1.0000e-03 eta: 2:53:11 time: 0.6232 data_time: 0.0333 memory: 42708 grad_norm: 4.4334 loss: 1.4562 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4562 2023/02/18 03:35:53 - mmengine - INFO - Epoch(train) [26][220/660] lr: 1.0000e-03 eta: 2:52:58 time: 0.6375 data_time: 0.0403 memory: 42708 grad_norm: 4.3320 loss: 1.3691 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3691 2023/02/18 03:36:05 - mmengine - INFO - Epoch(train) [26][240/660] lr: 1.0000e-03 eta: 2:52:45 time: 0.6263 data_time: 0.0332 memory: 42708 grad_norm: 4.3416 loss: 1.5100 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.5100 2023/02/18 03:36:18 - mmengine - INFO - Epoch(train) [26][260/660] lr: 1.0000e-03 eta: 2:52:32 time: 0.6306 data_time: 0.0344 memory: 42708 grad_norm: 4.2894 loss: 1.4672 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.4672 2023/02/18 03:36:30 - mmengine - INFO - Epoch(train) [26][280/660] lr: 1.0000e-03 eta: 2:52:19 time: 0.6209 data_time: 0.0299 memory: 42708 grad_norm: 4.3054 loss: 1.4258 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.4258 2023/02/18 03:36:43 - mmengine - INFO - Epoch(train) [26][300/660] lr: 1.0000e-03 eta: 2:52:06 time: 0.6330 data_time: 0.0381 memory: 42708 grad_norm: 4.3199 loss: 1.3861 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.3861 2023/02/18 03:36:55 - mmengine - INFO - Epoch(train) [26][320/660] lr: 1.0000e-03 eta: 2:51:53 time: 0.6310 data_time: 0.0328 memory: 42708 grad_norm: 4.3503 loss: 1.5369 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5369 2023/02/18 03:37:08 - mmengine - INFO - Epoch(train) [26][340/660] lr: 1.0000e-03 eta: 2:51:40 time: 0.6306 data_time: 0.0359 memory: 42708 grad_norm: 4.3818 loss: 1.5518 top1_acc: 0.5312 top5_acc: 0.6875 loss_cls: 1.5518 2023/02/18 03:37:21 - mmengine - INFO - Epoch(train) [26][360/660] lr: 1.0000e-03 eta: 2:51:27 time: 0.6254 data_time: 0.0310 memory: 42708 grad_norm: 4.4872 loss: 1.5450 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.5450 2023/02/18 03:37:33 - mmengine - INFO - Epoch(train) [26][380/660] lr: 1.0000e-03 eta: 2:51:14 time: 0.6347 data_time: 0.0350 memory: 42708 grad_norm: 4.3983 loss: 1.4231 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.4231 2023/02/18 03:37:46 - mmengine - INFO - Epoch(train) [26][400/660] lr: 1.0000e-03 eta: 2:51:01 time: 0.6254 data_time: 0.0339 memory: 42708 grad_norm: 4.3135 loss: 1.4221 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.4221 2023/02/18 03:37:58 - mmengine - INFO - Epoch(train) [26][420/660] lr: 1.0000e-03 eta: 2:50:49 time: 0.6348 data_time: 0.0372 memory: 42708 grad_norm: 4.3963 loss: 1.4347 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.4347 2023/02/18 03:38:11 - mmengine - INFO - Epoch(train) [26][440/660] lr: 1.0000e-03 eta: 2:50:36 time: 0.6250 data_time: 0.0319 memory: 42708 grad_norm: 4.3974 loss: 1.5935 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.5935 2023/02/18 03:38:24 - mmengine - INFO - Epoch(train) [26][460/660] lr: 1.0000e-03 eta: 2:50:23 time: 0.6335 data_time: 0.0363 memory: 42708 grad_norm: 4.4574 loss: 1.4509 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.4509 2023/02/18 03:38:36 - mmengine - INFO - Epoch(train) [26][480/660] lr: 1.0000e-03 eta: 2:50:10 time: 0.6269 data_time: 0.0336 memory: 42708 grad_norm: 4.3309 loss: 1.5020 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.5020 2023/02/18 03:38:49 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:38:49 - mmengine - INFO - Epoch(train) [26][500/660] lr: 1.0000e-03 eta: 2:49:57 time: 0.6356 data_time: 0.0357 memory: 42708 grad_norm: 4.4849 loss: 1.4881 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.4881 2023/02/18 03:39:01 - mmengine - INFO - Epoch(train) [26][520/660] lr: 1.0000e-03 eta: 2:49:44 time: 0.6276 data_time: 0.0324 memory: 42708 grad_norm: 4.3993 loss: 1.4150 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4150 2023/02/18 03:39:14 - mmengine - INFO - Epoch(train) [26][540/660] lr: 1.0000e-03 eta: 2:49:32 time: 0.6398 data_time: 0.0402 memory: 42708 grad_norm: 4.4440 loss: 1.4688 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.4688 2023/02/18 03:39:27 - mmengine - INFO - Epoch(train) [26][560/660] lr: 1.0000e-03 eta: 2:49:19 time: 0.6281 data_time: 0.0349 memory: 42708 grad_norm: 4.4760 loss: 1.4078 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4078 2023/02/18 03:39:39 - mmengine - INFO - Epoch(train) [26][580/660] lr: 1.0000e-03 eta: 2:49:06 time: 0.6342 data_time: 0.0350 memory: 42708 grad_norm: 4.5095 loss: 1.4315 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4315 2023/02/18 03:39:52 - mmengine - INFO - Epoch(train) [26][600/660] lr: 1.0000e-03 eta: 2:48:53 time: 0.6222 data_time: 0.0326 memory: 42708 grad_norm: 4.4538 loss: 1.4826 top1_acc: 0.4062 top5_acc: 0.7500 loss_cls: 1.4826 2023/02/18 03:40:05 - mmengine - INFO - Epoch(train) [26][620/660] lr: 1.0000e-03 eta: 2:48:40 time: 0.6325 data_time: 0.0362 memory: 42708 grad_norm: 4.4605 loss: 1.5102 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.5102 2023/02/18 03:40:17 - mmengine - INFO - Epoch(train) [26][640/660] lr: 1.0000e-03 eta: 2:48:27 time: 0.6237 data_time: 0.0327 memory: 42708 grad_norm: 4.4994 loss: 1.3688 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3688 2023/02/18 03:40:29 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:40:29 - mmengine - INFO - Epoch(train) [26][660/660] lr: 1.0000e-03 eta: 2:48:14 time: 0.6152 data_time: 0.0298 memory: 42708 grad_norm: 4.4823 loss: 1.4282 top1_acc: 0.4074 top5_acc: 0.8519 loss_cls: 1.4282 2023/02/18 03:40:44 - mmengine - INFO - Epoch(train) [27][ 20/660] lr: 1.0000e-03 eta: 2:48:03 time: 0.7249 data_time: 0.1149 memory: 42708 grad_norm: 4.3111 loss: 1.4552 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.4552 2023/02/18 03:40:56 - mmengine - INFO - Epoch(train) [27][ 40/660] lr: 1.0000e-03 eta: 2:47:50 time: 0.6240 data_time: 0.0285 memory: 42708 grad_norm: 4.2379 loss: 1.4698 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.4698 2023/02/18 03:41:09 - mmengine - INFO - Epoch(train) [27][ 60/660] lr: 1.0000e-03 eta: 2:47:37 time: 0.6387 data_time: 0.0282 memory: 42708 grad_norm: 4.3965 loss: 1.4267 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 1.4267 2023/02/18 03:41:22 - mmengine - INFO - Epoch(train) [27][ 80/660] lr: 1.0000e-03 eta: 2:47:24 time: 0.6212 data_time: 0.0302 memory: 42708 grad_norm: 4.4426 loss: 1.3795 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.3795 2023/02/18 03:41:34 - mmengine - INFO - Epoch(train) [27][100/660] lr: 1.0000e-03 eta: 2:47:11 time: 0.6414 data_time: 0.0326 memory: 42708 grad_norm: 4.3870 loss: 1.5533 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.5533 2023/02/18 03:41:47 - mmengine - INFO - Epoch(train) [27][120/660] lr: 1.0000e-03 eta: 2:46:58 time: 0.6255 data_time: 0.0344 memory: 42708 grad_norm: 4.3987 loss: 1.4669 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.4669 2023/02/18 03:42:00 - mmengine - INFO - Epoch(train) [27][140/660] lr: 1.0000e-03 eta: 2:46:45 time: 0.6348 data_time: 0.0331 memory: 42708 grad_norm: 4.4822 loss: 1.5456 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.5456 2023/02/18 03:42:12 - mmengine - INFO - Epoch(train) [27][160/660] lr: 1.0000e-03 eta: 2:46:33 time: 0.6286 data_time: 0.0306 memory: 42708 grad_norm: 4.5232 loss: 1.5130 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.5130 2023/02/18 03:42:25 - mmengine - INFO - Epoch(train) [27][180/660] lr: 1.0000e-03 eta: 2:46:20 time: 0.6467 data_time: 0.0345 memory: 42708 grad_norm: 4.4031 loss: 1.4209 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.4209 2023/02/18 03:42:38 - mmengine - INFO - Epoch(train) [27][200/660] lr: 1.0000e-03 eta: 2:46:07 time: 0.6250 data_time: 0.0299 memory: 42708 grad_norm: 4.3842 loss: 1.4196 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.4196 2023/02/18 03:42:50 - mmengine - INFO - Epoch(train) [27][220/660] lr: 1.0000e-03 eta: 2:45:54 time: 0.6404 data_time: 0.0344 memory: 42708 grad_norm: 4.4259 loss: 1.5064 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.5064 2023/02/18 03:43:03 - mmengine - INFO - Epoch(train) [27][240/660] lr: 1.0000e-03 eta: 2:45:41 time: 0.6283 data_time: 0.0305 memory: 42708 grad_norm: 4.4311 loss: 1.4990 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.4990 2023/02/18 03:43:16 - mmengine - INFO - Epoch(train) [27][260/660] lr: 1.0000e-03 eta: 2:45:29 time: 0.6422 data_time: 0.0348 memory: 42708 grad_norm: 4.5316 loss: 1.5092 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.5092 2023/02/18 03:43:29 - mmengine - INFO - Epoch(train) [27][280/660] lr: 1.0000e-03 eta: 2:45:16 time: 0.6310 data_time: 0.0305 memory: 42708 grad_norm: 4.3946 loss: 1.5093 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.5093 2023/02/18 03:43:41 - mmengine - INFO - Epoch(train) [27][300/660] lr: 1.0000e-03 eta: 2:45:03 time: 0.6466 data_time: 0.0338 memory: 42708 grad_norm: 4.5001 loss: 1.4580 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4580 2023/02/18 03:43:54 - mmengine - INFO - Epoch(train) [27][320/660] lr: 1.0000e-03 eta: 2:44:50 time: 0.6313 data_time: 0.0334 memory: 42708 grad_norm: 4.4614 loss: 1.4447 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4447 2023/02/18 03:44:07 - mmengine - INFO - Epoch(train) [27][340/660] lr: 1.0000e-03 eta: 2:44:38 time: 0.6405 data_time: 0.0356 memory: 42708 grad_norm: 4.4666 loss: 1.5252 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.5252 2023/02/18 03:44:19 - mmengine - INFO - Epoch(train) [27][360/660] lr: 1.0000e-03 eta: 2:44:25 time: 0.6301 data_time: 0.0309 memory: 42708 grad_norm: 4.3561 loss: 1.4490 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4490 2023/02/18 03:44:32 - mmengine - INFO - Epoch(train) [27][380/660] lr: 1.0000e-03 eta: 2:44:12 time: 0.6362 data_time: 0.0351 memory: 42708 grad_norm: 4.4602 loss: 1.4042 top1_acc: 0.8125 top5_acc: 0.9688 loss_cls: 1.4042 2023/02/18 03:44:45 - mmengine - INFO - Epoch(train) [27][400/660] lr: 1.0000e-03 eta: 2:43:59 time: 0.6306 data_time: 0.0353 memory: 42708 grad_norm: 4.5235 loss: 1.3847 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.3847 2023/02/18 03:44:58 - mmengine - INFO - Epoch(train) [27][420/660] lr: 1.0000e-03 eta: 2:43:47 time: 0.6515 data_time: 0.0342 memory: 42708 grad_norm: 4.4522 loss: 1.4572 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4572 2023/02/18 03:45:11 - mmengine - INFO - Epoch(train) [27][440/660] lr: 1.0000e-03 eta: 2:43:34 time: 0.6328 data_time: 0.0314 memory: 42708 grad_norm: 4.4112 loss: 1.5001 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.5001 2023/02/18 03:45:23 - mmengine - INFO - Epoch(train) [27][460/660] lr: 1.0000e-03 eta: 2:43:21 time: 0.6420 data_time: 0.0345 memory: 42708 grad_norm: 4.4986 loss: 1.5081 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.5081 2023/02/18 03:45:36 - mmengine - INFO - Epoch(train) [27][480/660] lr: 1.0000e-03 eta: 2:43:08 time: 0.6310 data_time: 0.0303 memory: 42708 grad_norm: 4.3973 loss: 1.4091 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.4091 2023/02/18 03:45:49 - mmengine - INFO - Epoch(train) [27][500/660] lr: 1.0000e-03 eta: 2:42:56 time: 0.6474 data_time: 0.0341 memory: 42708 grad_norm: 4.4871 loss: 1.5280 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.5280 2023/02/18 03:46:02 - mmengine - INFO - Epoch(train) [27][520/660] lr: 1.0000e-03 eta: 2:42:43 time: 0.6342 data_time: 0.0355 memory: 42708 grad_norm: 4.4426 loss: 1.5076 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.5076 2023/02/18 03:46:15 - mmengine - INFO - Epoch(train) [27][540/660] lr: 1.0000e-03 eta: 2:42:31 time: 0.6476 data_time: 0.0355 memory: 42708 grad_norm: 4.4717 loss: 1.3585 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.3585 2023/02/18 03:46:27 - mmengine - INFO - Epoch(train) [27][560/660] lr: 1.0000e-03 eta: 2:42:18 time: 0.6294 data_time: 0.0323 memory: 42708 grad_norm: 4.5328 loss: 1.4282 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.4282 2023/02/18 03:46:40 - mmengine - INFO - Epoch(train) [27][580/660] lr: 1.0000e-03 eta: 2:42:05 time: 0.6433 data_time: 0.0341 memory: 42708 grad_norm: 4.4931 loss: 1.3875 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3875 2023/02/18 03:46:53 - mmengine - INFO - Epoch(train) [27][600/660] lr: 1.0000e-03 eta: 2:41:52 time: 0.6312 data_time: 0.0343 memory: 42708 grad_norm: 4.4807 loss: 1.5702 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.5702 2023/02/18 03:47:06 - mmengine - INFO - Epoch(train) [27][620/660] lr: 1.0000e-03 eta: 2:41:39 time: 0.6424 data_time: 0.0373 memory: 42708 grad_norm: 4.4674 loss: 1.4298 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.4298 2023/02/18 03:47:18 - mmengine - INFO - Epoch(train) [27][640/660] lr: 1.0000e-03 eta: 2:41:27 time: 0.6294 data_time: 0.0319 memory: 42708 grad_norm: 4.4765 loss: 1.5236 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.5236 2023/02/18 03:47:30 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:47:30 - mmengine - INFO - Epoch(train) [27][660/660] lr: 1.0000e-03 eta: 2:41:14 time: 0.6191 data_time: 0.0290 memory: 42708 grad_norm: 4.4289 loss: 1.4993 top1_acc: 0.4815 top5_acc: 0.7407 loss_cls: 1.4993 2023/02/18 03:47:30 - mmengine - INFO - Saving checkpoint at 27 epochs 2023/02/18 03:47:46 - mmengine - INFO - Epoch(train) [28][ 20/660] lr: 1.0000e-03 eta: 2:41:02 time: 0.7229 data_time: 0.1183 memory: 42708 grad_norm: 4.2792 loss: 1.3428 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.3428 2023/02/18 03:47:59 - mmengine - INFO - Epoch(train) [28][ 40/660] lr: 1.0000e-03 eta: 2:40:49 time: 0.6241 data_time: 0.0303 memory: 42708 grad_norm: 4.4021 loss: 1.4968 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.4968 2023/02/18 03:48:11 - mmengine - INFO - Epoch(train) [28][ 60/660] lr: 1.0000e-03 eta: 2:40:37 time: 0.6381 data_time: 0.0382 memory: 42708 grad_norm: 4.4297 loss: 1.4354 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.4354 2023/02/18 03:48:24 - mmengine - INFO - Epoch(train) [28][ 80/660] lr: 1.0000e-03 eta: 2:40:24 time: 0.6242 data_time: 0.0309 memory: 42708 grad_norm: 4.4934 loss: 1.4324 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.4324 2023/02/18 03:48:37 - mmengine - INFO - Epoch(train) [28][100/660] lr: 1.0000e-03 eta: 2:40:11 time: 0.6420 data_time: 0.0355 memory: 42708 grad_norm: 4.3929 loss: 1.4749 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.4749 2023/02/18 03:48:49 - mmengine - INFO - Epoch(train) [28][120/660] lr: 1.0000e-03 eta: 2:39:58 time: 0.6309 data_time: 0.0310 memory: 42708 grad_norm: 4.4049 loss: 1.4802 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.4802 2023/02/18 03:49:02 - mmengine - INFO - Epoch(train) [28][140/660] lr: 1.0000e-03 eta: 2:39:45 time: 0.6381 data_time: 0.0331 memory: 42708 grad_norm: 4.5144 loss: 1.3957 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.3957 2023/02/18 03:49:15 - mmengine - INFO - Epoch(train) [28][160/660] lr: 1.0000e-03 eta: 2:39:32 time: 0.6272 data_time: 0.0303 memory: 42708 grad_norm: 4.4564 loss: 1.5418 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.5418 2023/02/18 03:49:27 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:49:27 - mmengine - INFO - Epoch(train) [28][180/660] lr: 1.0000e-03 eta: 2:39:20 time: 0.6385 data_time: 0.0336 memory: 42708 grad_norm: 4.3649 loss: 1.4041 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.4041 2023/02/18 03:49:40 - mmengine - INFO - Epoch(train) [28][200/660] lr: 1.0000e-03 eta: 2:39:07 time: 0.6309 data_time: 0.0315 memory: 42708 grad_norm: 4.3433 loss: 1.4034 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.4034 2023/02/18 03:49:53 - mmengine - INFO - Epoch(train) [28][220/660] lr: 1.0000e-03 eta: 2:38:54 time: 0.6409 data_time: 0.0355 memory: 42708 grad_norm: 4.4639 loss: 1.3128 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3128 2023/02/18 03:50:05 - mmengine - INFO - Epoch(train) [28][240/660] lr: 1.0000e-03 eta: 2:38:41 time: 0.6255 data_time: 0.0305 memory: 42708 grad_norm: 4.4348 loss: 1.4026 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.4026 2023/02/18 03:50:18 - mmengine - INFO - Epoch(train) [28][260/660] lr: 1.0000e-03 eta: 2:38:28 time: 0.6360 data_time: 0.0340 memory: 42708 grad_norm: 4.4876 loss: 1.4766 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.4766 2023/02/18 03:50:31 - mmengine - INFO - Epoch(train) [28][280/660] lr: 1.0000e-03 eta: 2:38:16 time: 0.6299 data_time: 0.0323 memory: 42708 grad_norm: 4.4933 loss: 1.4676 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.4676 2023/02/18 03:50:43 - mmengine - INFO - Epoch(train) [28][300/660] lr: 1.0000e-03 eta: 2:38:03 time: 0.6401 data_time: 0.0367 memory: 42708 grad_norm: 4.4127 loss: 1.4691 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4691 2023/02/18 03:50:56 - mmengine - INFO - Epoch(train) [28][320/660] lr: 1.0000e-03 eta: 2:37:50 time: 0.6319 data_time: 0.0349 memory: 42708 grad_norm: 4.4395 loss: 1.4568 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4568 2023/02/18 03:51:09 - mmengine - INFO - Epoch(train) [28][340/660] lr: 1.0000e-03 eta: 2:37:37 time: 0.6452 data_time: 0.0382 memory: 42708 grad_norm: 4.6194 loss: 1.5281 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.5281 2023/02/18 03:51:22 - mmengine - INFO - Epoch(train) [28][360/660] lr: 1.0000e-03 eta: 2:37:24 time: 0.6273 data_time: 0.0327 memory: 42708 grad_norm: 4.5185 loss: 1.4278 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.4278 2023/02/18 03:51:34 - mmengine - INFO - Epoch(train) [28][380/660] lr: 1.0000e-03 eta: 2:37:12 time: 0.6374 data_time: 0.0347 memory: 42708 grad_norm: 4.4673 loss: 1.4659 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4659 2023/02/18 03:51:47 - mmengine - INFO - Epoch(train) [28][400/660] lr: 1.0000e-03 eta: 2:36:59 time: 0.6263 data_time: 0.0313 memory: 42708 grad_norm: 4.4706 loss: 1.4033 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4033 2023/02/18 03:52:00 - mmengine - INFO - Epoch(train) [28][420/660] lr: 1.0000e-03 eta: 2:36:46 time: 0.6377 data_time: 0.0343 memory: 42708 grad_norm: 4.5411 loss: 1.4622 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4622 2023/02/18 03:52:12 - mmengine - INFO - Epoch(train) [28][440/660] lr: 1.0000e-03 eta: 2:36:33 time: 0.6246 data_time: 0.0320 memory: 42708 grad_norm: 4.5206 loss: 1.4643 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.4643 2023/02/18 03:52:25 - mmengine - INFO - Epoch(train) [28][460/660] lr: 1.0000e-03 eta: 2:36:20 time: 0.6390 data_time: 0.0337 memory: 42708 grad_norm: 4.5425 loss: 1.5349 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.5349 2023/02/18 03:52:37 - mmengine - INFO - Epoch(train) [28][480/660] lr: 1.0000e-03 eta: 2:36:08 time: 0.6293 data_time: 0.0305 memory: 42708 grad_norm: 4.4740 loss: 1.4391 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4391 2023/02/18 03:52:50 - mmengine - INFO - Epoch(train) [28][500/660] lr: 1.0000e-03 eta: 2:35:55 time: 0.6395 data_time: 0.0348 memory: 42708 grad_norm: 4.4772 loss: 1.5024 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.5024 2023/02/18 03:53:03 - mmengine - INFO - Epoch(train) [28][520/660] lr: 1.0000e-03 eta: 2:35:42 time: 0.6251 data_time: 0.0316 memory: 42708 grad_norm: 4.5827 loss: 1.4746 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.4746 2023/02/18 03:53:16 - mmengine - INFO - Epoch(train) [28][540/660] lr: 1.0000e-03 eta: 2:35:29 time: 0.6430 data_time: 0.0331 memory: 42708 grad_norm: 4.5476 loss: 1.6277 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.6277 2023/02/18 03:53:28 - mmengine - INFO - Epoch(train) [28][560/660] lr: 1.0000e-03 eta: 2:35:16 time: 0.6320 data_time: 0.0312 memory: 42708 grad_norm: 4.5047 loss: 1.4833 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.4833 2023/02/18 03:53:41 - mmengine - INFO - Epoch(train) [28][580/660] lr: 1.0000e-03 eta: 2:35:04 time: 0.6478 data_time: 0.0377 memory: 42708 grad_norm: 4.5435 loss: 1.4631 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.4631 2023/02/18 03:53:54 - mmengine - INFO - Epoch(train) [28][600/660] lr: 1.0000e-03 eta: 2:34:51 time: 0.6295 data_time: 0.0345 memory: 42708 grad_norm: 4.5092 loss: 1.5010 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.5010 2023/02/18 03:54:06 - mmengine - INFO - Epoch(train) [28][620/660] lr: 1.0000e-03 eta: 2:34:38 time: 0.6369 data_time: 0.0360 memory: 42708 grad_norm: 4.5520 loss: 1.5253 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.5253 2023/02/18 03:54:19 - mmengine - INFO - Epoch(train) [28][640/660] lr: 1.0000e-03 eta: 2:34:25 time: 0.6290 data_time: 0.0315 memory: 42708 grad_norm: 4.5241 loss: 1.5326 top1_acc: 0.5625 top5_acc: 0.9688 loss_cls: 1.5326 2023/02/18 03:54:32 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 03:54:32 - mmengine - INFO - Epoch(train) [28][660/660] lr: 1.0000e-03 eta: 2:34:12 time: 0.6237 data_time: 0.0312 memory: 42708 grad_norm: 4.5413 loss: 1.4054 top1_acc: 0.6296 top5_acc: 1.0000 loss_cls: 1.4054 2023/02/18 03:54:46 - mmengine - INFO - Epoch(train) [29][ 20/660] lr: 1.0000e-03 eta: 2:34:01 time: 0.7306 data_time: 0.1181 memory: 42708 grad_norm: 4.5727 loss: 1.3772 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3772 2023/02/18 03:54:59 - mmengine - INFO - Epoch(train) [29][ 40/660] lr: 1.0000e-03 eta: 2:33:48 time: 0.6273 data_time: 0.0303 memory: 42708 grad_norm: 4.5107 loss: 1.5069 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.5069 2023/02/18 03:55:11 - mmengine - INFO - Epoch(train) [29][ 60/660] lr: 1.0000e-03 eta: 2:33:35 time: 0.6387 data_time: 0.0359 memory: 42708 grad_norm: 4.5057 loss: 1.4530 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4530 2023/02/18 03:55:24 - mmengine - INFO - Epoch(train) [29][ 80/660] lr: 1.0000e-03 eta: 2:33:23 time: 0.6251 data_time: 0.0295 memory: 42708 grad_norm: 4.5091 loss: 1.4551 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.4551 2023/02/18 03:55:37 - mmengine - INFO - Epoch(train) [29][100/660] lr: 1.0000e-03 eta: 2:33:10 time: 0.6391 data_time: 0.0354 memory: 42708 grad_norm: 4.4799 loss: 1.4041 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4041 2023/02/18 03:55:49 - mmengine - INFO - Epoch(train) [29][120/660] lr: 1.0000e-03 eta: 2:32:57 time: 0.6238 data_time: 0.0300 memory: 42708 grad_norm: 4.4665 loss: 1.3636 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.3636 2023/02/18 03:56:02 - mmengine - INFO - Epoch(train) [29][140/660] lr: 1.0000e-03 eta: 2:32:44 time: 0.6472 data_time: 0.0353 memory: 42708 grad_norm: 4.4836 loss: 1.4317 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.4317 2023/02/18 03:56:15 - mmengine - INFO - Epoch(train) [29][160/660] lr: 1.0000e-03 eta: 2:32:31 time: 0.6273 data_time: 0.0283 memory: 42708 grad_norm: 4.4806 loss: 1.4713 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4713 2023/02/18 03:56:27 - mmengine - INFO - Epoch(train) [29][180/660] lr: 1.0000e-03 eta: 2:32:19 time: 0.6342 data_time: 0.0366 memory: 42708 grad_norm: 4.6515 loss: 1.4490 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4490 2023/02/18 03:56:40 - mmengine - INFO - Epoch(train) [29][200/660] lr: 1.0000e-03 eta: 2:32:06 time: 0.6233 data_time: 0.0318 memory: 42708 grad_norm: 4.4867 loss: 1.4085 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.4085 2023/02/18 03:56:53 - mmengine - INFO - Epoch(train) [29][220/660] lr: 1.0000e-03 eta: 2:31:53 time: 0.6328 data_time: 0.0347 memory: 42708 grad_norm: 4.4625 loss: 1.5533 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.5533 2023/02/18 03:57:05 - mmengine - INFO - Epoch(train) [29][240/660] lr: 1.0000e-03 eta: 2:31:40 time: 0.6245 data_time: 0.0275 memory: 42708 grad_norm: 4.5761 loss: 1.5222 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.5222 2023/02/18 03:57:18 - mmengine - INFO - Epoch(train) [29][260/660] lr: 1.0000e-03 eta: 2:31:27 time: 0.6326 data_time: 0.0341 memory: 42708 grad_norm: 4.4408 loss: 1.3484 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.3484 2023/02/18 03:57:30 - mmengine - INFO - Epoch(train) [29][280/660] lr: 1.0000e-03 eta: 2:31:14 time: 0.6240 data_time: 0.0294 memory: 42708 grad_norm: 4.4293 loss: 1.4619 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.4619 2023/02/18 03:57:43 - mmengine - INFO - Epoch(train) [29][300/660] lr: 1.0000e-03 eta: 2:31:01 time: 0.6351 data_time: 0.0332 memory: 42708 grad_norm: 4.6760 loss: 1.5148 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.5148 2023/02/18 03:57:55 - mmengine - INFO - Epoch(train) [29][320/660] lr: 1.0000e-03 eta: 2:30:48 time: 0.6264 data_time: 0.0328 memory: 42708 grad_norm: 4.4871 loss: 1.4934 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.4934 2023/02/18 03:58:08 - mmengine - INFO - Epoch(train) [29][340/660] lr: 1.0000e-03 eta: 2:30:36 time: 0.6356 data_time: 0.0334 memory: 42708 grad_norm: 4.4790 loss: 1.4246 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.4246 2023/02/18 03:58:21 - mmengine - INFO - Epoch(train) [29][360/660] lr: 1.0000e-03 eta: 2:30:23 time: 0.6228 data_time: 0.0282 memory: 42708 grad_norm: 4.4591 loss: 1.3448 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3448 2023/02/18 03:58:33 - mmengine - INFO - Epoch(train) [29][380/660] lr: 1.0000e-03 eta: 2:30:10 time: 0.6418 data_time: 0.0335 memory: 42708 grad_norm: 4.5799 loss: 1.3515 top1_acc: 0.5938 top5_acc: 1.0000 loss_cls: 1.3515 2023/02/18 03:58:46 - mmengine - INFO - Epoch(train) [29][400/660] lr: 1.0000e-03 eta: 2:29:57 time: 0.6213 data_time: 0.0279 memory: 42708 grad_norm: 4.5675 loss: 1.4374 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.4374 2023/02/18 03:58:59 - mmengine - INFO - Epoch(train) [29][420/660] lr: 1.0000e-03 eta: 2:29:44 time: 0.6397 data_time: 0.0330 memory: 42708 grad_norm: 4.5349 loss: 1.4539 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4539 2023/02/18 03:59:11 - mmengine - INFO - Epoch(train) [29][440/660] lr: 1.0000e-03 eta: 2:29:31 time: 0.6279 data_time: 0.0316 memory: 42708 grad_norm: 4.5612 loss: 1.3606 top1_acc: 0.8125 top5_acc: 0.9688 loss_cls: 1.3606 2023/02/18 03:59:24 - mmengine - INFO - Epoch(train) [29][460/660] lr: 1.0000e-03 eta: 2:29:19 time: 0.6342 data_time: 0.0343 memory: 42708 grad_norm: 4.5185 loss: 1.4475 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4475 2023/02/18 03:59:36 - mmengine - INFO - Epoch(train) [29][480/660] lr: 1.0000e-03 eta: 2:29:06 time: 0.6233 data_time: 0.0286 memory: 42708 grad_norm: 4.4852 loss: 1.3885 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3885 2023/02/18 03:59:49 - mmengine - INFO - Epoch(train) [29][500/660] lr: 1.0000e-03 eta: 2:28:53 time: 0.6350 data_time: 0.0336 memory: 42708 grad_norm: 4.4466 loss: 1.4083 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.4083 2023/02/18 04:00:02 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:00:02 - mmengine - INFO - Epoch(train) [29][520/660] lr: 1.0000e-03 eta: 2:28:40 time: 0.6223 data_time: 0.0278 memory: 42708 grad_norm: 4.5309 loss: 1.3687 top1_acc: 0.7812 top5_acc: 0.8750 loss_cls: 1.3687 2023/02/18 04:00:14 - mmengine - INFO - Epoch(train) [29][540/660] lr: 1.0000e-03 eta: 2:28:27 time: 0.6405 data_time: 0.0350 memory: 42708 grad_norm: 4.4959 loss: 1.4995 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4995 2023/02/18 04:00:27 - mmengine - INFO - Epoch(train) [29][560/660] lr: 1.0000e-03 eta: 2:28:14 time: 0.6238 data_time: 0.0301 memory: 42708 grad_norm: 4.5472 loss: 1.4378 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.4378 2023/02/18 04:00:40 - mmengine - INFO - Epoch(train) [29][580/660] lr: 1.0000e-03 eta: 2:28:02 time: 0.6363 data_time: 0.0344 memory: 42708 grad_norm: 4.4839 loss: 1.3549 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3549 2023/02/18 04:00:52 - mmengine - INFO - Epoch(train) [29][600/660] lr: 1.0000e-03 eta: 2:27:49 time: 0.6220 data_time: 0.0277 memory: 42708 grad_norm: 4.5612 loss: 1.4241 top1_acc: 0.8125 top5_acc: 0.9688 loss_cls: 1.4241 2023/02/18 04:01:05 - mmengine - INFO - Epoch(train) [29][620/660] lr: 1.0000e-03 eta: 2:27:36 time: 0.6400 data_time: 0.0329 memory: 42708 grad_norm: 4.4986 loss: 1.3838 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3838 2023/02/18 04:01:17 - mmengine - INFO - Epoch(train) [29][640/660] lr: 1.0000e-03 eta: 2:27:23 time: 0.6256 data_time: 0.0294 memory: 42708 grad_norm: 4.6071 loss: 1.4439 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4439 2023/02/18 04:01:30 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:01:30 - mmengine - INFO - Epoch(train) [29][660/660] lr: 1.0000e-03 eta: 2:27:10 time: 0.6195 data_time: 0.0284 memory: 42708 grad_norm: 4.6005 loss: 1.3837 top1_acc: 0.6667 top5_acc: 0.7778 loss_cls: 1.3837 2023/02/18 04:01:44 - mmengine - INFO - Epoch(train) [30][ 20/660] lr: 1.0000e-03 eta: 2:26:58 time: 0.7240 data_time: 0.1201 memory: 42708 grad_norm: 4.5936 loss: 1.3797 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 1.3797 2023/02/18 04:01:57 - mmengine - INFO - Epoch(train) [30][ 40/660] lr: 1.0000e-03 eta: 2:26:46 time: 0.6266 data_time: 0.0343 memory: 42708 grad_norm: 4.6308 loss: 1.3684 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3684 2023/02/18 04:02:09 - mmengine - INFO - Epoch(train) [30][ 60/660] lr: 1.0000e-03 eta: 2:26:33 time: 0.6292 data_time: 0.0344 memory: 42708 grad_norm: 4.6257 loss: 1.5193 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.5193 2023/02/18 04:02:22 - mmengine - INFO - Epoch(train) [30][ 80/660] lr: 1.0000e-03 eta: 2:26:20 time: 0.6192 data_time: 0.0286 memory: 42708 grad_norm: 4.5021 loss: 1.4127 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.4127 2023/02/18 04:02:34 - mmengine - INFO - Epoch(train) [30][100/660] lr: 1.0000e-03 eta: 2:26:07 time: 0.6302 data_time: 0.0341 memory: 42708 grad_norm: 4.5004 loss: 1.4373 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.4373 2023/02/18 04:02:47 - mmengine - INFO - Epoch(train) [30][120/660] lr: 1.0000e-03 eta: 2:25:54 time: 0.6224 data_time: 0.0298 memory: 42708 grad_norm: 4.5056 loss: 1.4598 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.4598 2023/02/18 04:02:59 - mmengine - INFO - Epoch(train) [30][140/660] lr: 1.0000e-03 eta: 2:25:41 time: 0.6308 data_time: 0.0363 memory: 42708 grad_norm: 4.5734 loss: 1.5253 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.5253 2023/02/18 04:03:12 - mmengine - INFO - Epoch(train) [30][160/660] lr: 1.0000e-03 eta: 2:25:28 time: 0.6200 data_time: 0.0310 memory: 42708 grad_norm: 4.4879 loss: 1.5361 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.5361 2023/02/18 04:03:24 - mmengine - INFO - Epoch(train) [30][180/660] lr: 1.0000e-03 eta: 2:25:15 time: 0.6356 data_time: 0.0352 memory: 42708 grad_norm: 4.5358 loss: 1.3436 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.3436 2023/02/18 04:03:37 - mmengine - INFO - Epoch(train) [30][200/660] lr: 1.0000e-03 eta: 2:25:02 time: 0.6261 data_time: 0.0293 memory: 42708 grad_norm: 4.6030 loss: 1.3652 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.3652 2023/02/18 04:03:50 - mmengine - INFO - Epoch(train) [30][220/660] lr: 1.0000e-03 eta: 2:24:50 time: 0.6351 data_time: 0.0343 memory: 42708 grad_norm: 4.5336 loss: 1.3596 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.3596 2023/02/18 04:04:02 - mmengine - INFO - Epoch(train) [30][240/660] lr: 1.0000e-03 eta: 2:24:37 time: 0.6266 data_time: 0.0297 memory: 42708 grad_norm: 4.5515 loss: 1.4000 top1_acc: 0.5312 top5_acc: 0.9688 loss_cls: 1.4000 2023/02/18 04:04:15 - mmengine - INFO - Epoch(train) [30][260/660] lr: 1.0000e-03 eta: 2:24:24 time: 0.6319 data_time: 0.0341 memory: 42708 grad_norm: 4.6578 loss: 1.4330 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.4330 2023/02/18 04:04:27 - mmengine - INFO - Epoch(train) [30][280/660] lr: 1.0000e-03 eta: 2:24:11 time: 0.6290 data_time: 0.0297 memory: 42708 grad_norm: 4.4523 loss: 1.3761 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.3761 2023/02/18 04:04:40 - mmengine - INFO - Epoch(train) [30][300/660] lr: 1.0000e-03 eta: 2:23:58 time: 0.6356 data_time: 0.0382 memory: 42708 grad_norm: 4.4927 loss: 1.3636 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3636 2023/02/18 04:04:53 - mmengine - INFO - Epoch(train) [30][320/660] lr: 1.0000e-03 eta: 2:23:46 time: 0.6331 data_time: 0.0295 memory: 42708 grad_norm: 4.4737 loss: 1.4639 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.4639 2023/02/18 04:05:05 - mmengine - INFO - Epoch(train) [30][340/660] lr: 1.0000e-03 eta: 2:23:33 time: 0.6312 data_time: 0.0324 memory: 42708 grad_norm: 4.4962 loss: 1.3946 top1_acc: 0.3438 top5_acc: 0.7500 loss_cls: 1.3946 2023/02/18 04:05:18 - mmengine - INFO - Epoch(train) [30][360/660] lr: 1.0000e-03 eta: 2:23:20 time: 0.6264 data_time: 0.0304 memory: 42708 grad_norm: 4.4763 loss: 1.4302 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.4302 2023/02/18 04:05:31 - mmengine - INFO - Epoch(train) [30][380/660] lr: 1.0000e-03 eta: 2:23:07 time: 0.6302 data_time: 0.0330 memory: 42708 grad_norm: 4.5875 loss: 1.4739 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.4739 2023/02/18 04:05:43 - mmengine - INFO - Epoch(train) [30][400/660] lr: 1.0000e-03 eta: 2:22:54 time: 0.6343 data_time: 0.0312 memory: 42708 grad_norm: 4.5682 loss: 1.4689 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4689 2023/02/18 04:05:56 - mmengine - INFO - Epoch(train) [30][420/660] lr: 1.0000e-03 eta: 2:22:41 time: 0.6379 data_time: 0.0348 memory: 42708 grad_norm: 4.5093 loss: 1.4684 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.4684 2023/02/18 04:06:09 - mmengine - INFO - Epoch(train) [30][440/660] lr: 1.0000e-03 eta: 2:22:29 time: 0.6312 data_time: 0.0308 memory: 42708 grad_norm: 4.5305 loss: 1.4194 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4194 2023/02/18 04:06:21 - mmengine - INFO - Epoch(train) [30][460/660] lr: 1.0000e-03 eta: 2:22:16 time: 0.6348 data_time: 0.0338 memory: 42708 grad_norm: 4.6250 loss: 1.5007 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.5007 2023/02/18 04:06:34 - mmengine - INFO - Epoch(train) [30][480/660] lr: 1.0000e-03 eta: 2:22:03 time: 0.6286 data_time: 0.0286 memory: 42708 grad_norm: 4.6120 loss: 1.4184 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.4184 2023/02/18 04:06:47 - mmengine - INFO - Epoch(train) [30][500/660] lr: 1.0000e-03 eta: 2:21:50 time: 0.6398 data_time: 0.0357 memory: 42708 grad_norm: 4.5319 loss: 1.3163 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3163 2023/02/18 04:06:59 - mmengine - INFO - Epoch(train) [30][520/660] lr: 1.0000e-03 eta: 2:21:38 time: 0.6365 data_time: 0.0300 memory: 42708 grad_norm: 4.4724 loss: 1.4833 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4833 2023/02/18 04:07:12 - mmengine - INFO - Epoch(train) [30][540/660] lr: 1.0000e-03 eta: 2:21:25 time: 0.6347 data_time: 0.0344 memory: 42708 grad_norm: 4.6722 loss: 1.3717 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3717 2023/02/18 04:07:25 - mmengine - INFO - Epoch(train) [30][560/660] lr: 1.0000e-03 eta: 2:21:12 time: 0.6342 data_time: 0.0335 memory: 42708 grad_norm: 4.5256 loss: 1.3825 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.3825 2023/02/18 04:07:38 - mmengine - INFO - Epoch(train) [30][580/660] lr: 1.0000e-03 eta: 2:20:59 time: 0.6402 data_time: 0.0338 memory: 42708 grad_norm: 4.6281 loss: 1.5126 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.5126 2023/02/18 04:07:50 - mmengine - INFO - Epoch(train) [30][600/660] lr: 1.0000e-03 eta: 2:20:47 time: 0.6388 data_time: 0.0308 memory: 42708 grad_norm: 4.6435 loss: 1.4359 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4359 2023/02/18 04:08:03 - mmengine - INFO - Epoch(train) [30][620/660] lr: 1.0000e-03 eta: 2:20:34 time: 0.6351 data_time: 0.0345 memory: 42708 grad_norm: 4.5425 loss: 1.3463 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.3463 2023/02/18 04:09:47 - mmengine - INFO - Epoch(train) [30][640/660] lr: 1.0000e-03 eta: 2:21:22 time: 5.2155 data_time: 0.0272 memory: 42708 grad_norm: 4.5808 loss: 1.4295 top1_acc: 0.5312 top5_acc: 0.9688 loss_cls: 1.4295 2023/02/18 04:10:00 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:10:00 - mmengine - INFO - Epoch(train) [30][660/660] lr: 1.0000e-03 eta: 2:21:09 time: 0.6165 data_time: 0.0280 memory: 42708 grad_norm: 4.6732 loss: 1.4335 top1_acc: 0.6296 top5_acc: 0.8519 loss_cls: 1.4335 2023/02/18 04:10:00 - mmengine - INFO - Saving checkpoint at 30 epochs 2023/02/18 04:10:08 - mmengine - INFO - Epoch(val) [30][20/97] eta: 0:00:26 time: 0.3498 data_time: 0.1286 memory: 6154 2023/02/18 04:10:13 - mmengine - INFO - Epoch(val) [30][40/97] eta: 0:00:17 time: 0.2488 data_time: 0.0369 memory: 6154 2023/02/18 04:10:18 - mmengine - INFO - Epoch(val) [30][60/97] eta: 0:00:10 time: 0.2495 data_time: 0.0377 memory: 6154 2023/02/18 04:10:23 - mmengine - INFO - Epoch(val) [30][80/97] eta: 0:00:04 time: 0.2333 data_time: 0.0279 memory: 6154 2023/02/18 04:10:27 - mmengine - INFO - Epoch(val) [30][97/97] acc/top1: 0.3645 acc/top5: 0.6743 acc/mean1: 0.3003 2023/02/18 04:10:41 - mmengine - INFO - Epoch(train) [31][ 20/660] lr: 1.0000e-03 eta: 2:20:57 time: 0.7127 data_time: 0.1092 memory: 42708 grad_norm: 4.6237 loss: 1.3817 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3817 2023/02/18 04:10:53 - mmengine - INFO - Epoch(train) [31][ 40/660] lr: 1.0000e-03 eta: 2:20:44 time: 0.6154 data_time: 0.0239 memory: 42708 grad_norm: 4.4554 loss: 1.4012 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4012 2023/02/18 04:11:06 - mmengine - INFO - Epoch(train) [31][ 60/660] lr: 1.0000e-03 eta: 2:20:31 time: 0.6255 data_time: 0.0279 memory: 42708 grad_norm: 4.5478 loss: 1.3438 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3438 2023/02/18 04:11:18 - mmengine - INFO - Epoch(train) [31][ 80/660] lr: 1.0000e-03 eta: 2:20:18 time: 0.6156 data_time: 0.0236 memory: 42708 grad_norm: 4.6051 loss: 1.4376 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.4376 2023/02/18 04:11:31 - mmengine - INFO - Epoch(train) [31][100/660] lr: 1.0000e-03 eta: 2:20:05 time: 0.6243 data_time: 0.0309 memory: 42708 grad_norm: 4.6276 loss: 1.3507 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3507 2023/02/18 04:11:43 - mmengine - INFO - Epoch(train) [31][120/660] lr: 1.0000e-03 eta: 2:19:52 time: 0.6194 data_time: 0.0245 memory: 42708 grad_norm: 4.5379 loss: 1.3002 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3002 2023/02/18 04:11:56 - mmengine - INFO - Epoch(train) [31][140/660] lr: 1.0000e-03 eta: 2:19:39 time: 0.6267 data_time: 0.0274 memory: 42708 grad_norm: 4.6388 loss: 1.4637 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.4637 2023/02/18 04:12:08 - mmengine - INFO - Epoch(train) [31][160/660] lr: 1.0000e-03 eta: 2:19:25 time: 0.6186 data_time: 0.0251 memory: 42708 grad_norm: 4.5997 loss: 1.4104 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4104 2023/02/18 04:12:21 - mmengine - INFO - Epoch(train) [31][180/660] lr: 1.0000e-03 eta: 2:19:13 time: 0.6349 data_time: 0.0320 memory: 42708 grad_norm: 4.5513 loss: 1.3974 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3974 2023/02/18 04:12:33 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:12:33 - mmengine - INFO - Epoch(train) [31][200/660] lr: 1.0000e-03 eta: 2:19:00 time: 0.6265 data_time: 0.0262 memory: 42708 grad_norm: 4.4430 loss: 1.4554 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.4554 2023/02/18 04:12:46 - mmengine - INFO - Epoch(train) [31][220/660] lr: 1.0000e-03 eta: 2:18:47 time: 0.6309 data_time: 0.0299 memory: 42708 grad_norm: 4.6619 loss: 1.4211 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.4211 2023/02/18 04:12:58 - mmengine - INFO - Epoch(train) [31][240/660] lr: 1.0000e-03 eta: 2:18:34 time: 0.6302 data_time: 0.0246 memory: 42708 grad_norm: 4.5743 loss: 1.3300 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3300 2023/02/18 04:13:11 - mmengine - INFO - Epoch(train) [31][260/660] lr: 1.0000e-03 eta: 2:18:21 time: 0.6322 data_time: 0.0262 memory: 42708 grad_norm: 4.5458 loss: 1.3278 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.3278 2023/02/18 04:13:24 - mmengine - INFO - Epoch(train) [31][280/660] lr: 1.0000e-03 eta: 2:18:08 time: 0.6210 data_time: 0.0244 memory: 42708 grad_norm: 4.6767 loss: 1.4200 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4200 2023/02/18 04:13:36 - mmengine - INFO - Epoch(train) [31][300/660] lr: 1.0000e-03 eta: 2:17:55 time: 0.6275 data_time: 0.0271 memory: 42708 grad_norm: 4.5620 loss: 1.5081 top1_acc: 0.4062 top5_acc: 0.8438 loss_cls: 1.5081 2023/02/18 04:13:48 - mmengine - INFO - Epoch(train) [31][320/660] lr: 1.0000e-03 eta: 2:17:41 time: 0.6187 data_time: 0.0238 memory: 42708 grad_norm: 4.5396 loss: 1.4620 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4620 2023/02/18 04:14:01 - mmengine - INFO - Epoch(train) [31][340/660] lr: 1.0000e-03 eta: 2:17:28 time: 0.6282 data_time: 0.0277 memory: 42708 grad_norm: 4.6062 loss: 1.4472 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4472 2023/02/18 04:14:13 - mmengine - INFO - Epoch(train) [31][360/660] lr: 1.0000e-03 eta: 2:17:15 time: 0.6208 data_time: 0.0249 memory: 42708 grad_norm: 4.5381 loss: 1.4566 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4566 2023/02/18 04:14:26 - mmengine - INFO - Epoch(train) [31][380/660] lr: 1.0000e-03 eta: 2:17:02 time: 0.6328 data_time: 0.0276 memory: 42708 grad_norm: 4.6503 loss: 1.4287 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.4287 2023/02/18 04:14:39 - mmengine - INFO - Epoch(train) [31][400/660] lr: 1.0000e-03 eta: 2:16:49 time: 0.6213 data_time: 0.0244 memory: 42708 grad_norm: 4.5745 loss: 1.4142 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4142 2023/02/18 04:14:51 - mmengine - INFO - Epoch(train) [31][420/660] lr: 1.0000e-03 eta: 2:16:36 time: 0.6325 data_time: 0.0308 memory: 42708 grad_norm: 4.5643 loss: 1.3904 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3904 2023/02/18 04:15:04 - mmengine - INFO - Epoch(train) [31][440/660] lr: 1.0000e-03 eta: 2:16:23 time: 0.6187 data_time: 0.0244 memory: 42708 grad_norm: 4.5572 loss: 1.4586 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4586 2023/02/18 04:15:16 - mmengine - INFO - Epoch(train) [31][460/660] lr: 1.0000e-03 eta: 2:16:10 time: 0.6303 data_time: 0.0280 memory: 42708 grad_norm: 4.5412 loss: 1.3588 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3588 2023/02/18 04:15:29 - mmengine - INFO - Epoch(train) [31][480/660] lr: 1.0000e-03 eta: 2:15:57 time: 0.6291 data_time: 0.0242 memory: 42708 grad_norm: 4.6052 loss: 1.2548 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2548 2023/02/18 04:15:41 - mmengine - INFO - Epoch(train) [31][500/660] lr: 1.0000e-03 eta: 2:15:44 time: 0.6298 data_time: 0.0274 memory: 42708 grad_norm: 4.6317 loss: 1.4048 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4048 2023/02/18 04:15:54 - mmengine - INFO - Epoch(train) [31][520/660] lr: 1.0000e-03 eta: 2:15:31 time: 0.6210 data_time: 0.0252 memory: 42708 grad_norm: 4.5989 loss: 1.3661 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3661 2023/02/18 04:16:06 - mmengine - INFO - Epoch(train) [31][540/660] lr: 1.0000e-03 eta: 2:15:18 time: 0.6319 data_time: 0.0271 memory: 42708 grad_norm: 4.6069 loss: 1.3419 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3419 2023/02/18 04:16:19 - mmengine - INFO - Epoch(train) [31][560/660] lr: 1.0000e-03 eta: 2:15:05 time: 0.6207 data_time: 0.0250 memory: 42708 grad_norm: 4.7004 loss: 1.4068 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.4068 2023/02/18 04:16:31 - mmengine - INFO - Epoch(train) [31][580/660] lr: 1.0000e-03 eta: 2:14:52 time: 0.6288 data_time: 0.0265 memory: 42708 grad_norm: 4.5854 loss: 1.4099 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4099 2023/02/18 04:16:44 - mmengine - INFO - Epoch(train) [31][600/660] lr: 1.0000e-03 eta: 2:14:39 time: 0.6186 data_time: 0.0235 memory: 42708 grad_norm: 4.6734 loss: 1.4201 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.4201 2023/02/18 04:16:56 - mmengine - INFO - Epoch(train) [31][620/660] lr: 1.0000e-03 eta: 2:14:26 time: 0.6273 data_time: 0.0264 memory: 42708 grad_norm: 4.6600 loss: 1.2567 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.2567 2023/02/18 04:17:09 - mmengine - INFO - Epoch(train) [31][640/660] lr: 1.0000e-03 eta: 2:14:13 time: 0.6203 data_time: 0.0240 memory: 42708 grad_norm: 4.5922 loss: 1.3965 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.3965 2023/02/18 04:17:21 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:17:21 - mmengine - INFO - Epoch(train) [31][660/660] lr: 1.0000e-03 eta: 2:14:00 time: 0.6147 data_time: 0.0247 memory: 42708 grad_norm: 4.5970 loss: 1.3935 top1_acc: 0.6296 top5_acc: 0.8889 loss_cls: 1.3935 2023/02/18 04:17:36 - mmengine - INFO - Epoch(train) [32][ 20/660] lr: 1.0000e-03 eta: 2:13:48 time: 0.7277 data_time: 0.1167 memory: 42708 grad_norm: 4.5859 loss: 1.3717 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3717 2023/02/18 04:17:48 - mmengine - INFO - Epoch(train) [32][ 40/660] lr: 1.0000e-03 eta: 2:13:35 time: 0.6239 data_time: 0.0287 memory: 42708 grad_norm: 4.7726 loss: 1.4693 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.4693 2023/02/18 04:18:01 - mmengine - INFO - Epoch(train) [32][ 60/660] lr: 1.0000e-03 eta: 2:13:22 time: 0.6293 data_time: 0.0272 memory: 42708 grad_norm: 4.5918 loss: 1.4703 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.4703 2023/02/18 04:18:13 - mmengine - INFO - Epoch(train) [32][ 80/660] lr: 1.0000e-03 eta: 2:13:09 time: 0.6252 data_time: 0.0267 memory: 42708 grad_norm: 4.5665 loss: 1.4653 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4653 2023/02/18 04:18:26 - mmengine - INFO - Epoch(train) [32][100/660] lr: 1.0000e-03 eta: 2:12:56 time: 0.6282 data_time: 0.0280 memory: 42708 grad_norm: 4.6312 loss: 1.4702 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.4702 2023/02/18 04:18:38 - mmengine - INFO - Epoch(train) [32][120/660] lr: 1.0000e-03 eta: 2:12:43 time: 0.6157 data_time: 0.0289 memory: 42708 grad_norm: 4.5836 loss: 1.4847 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4847 2023/02/18 04:18:51 - mmengine - INFO - Epoch(train) [32][140/660] lr: 1.0000e-03 eta: 2:12:30 time: 0.6297 data_time: 0.0280 memory: 42708 grad_norm: 4.5667 loss: 1.2891 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2891 2023/02/18 04:19:03 - mmengine - INFO - Epoch(train) [32][160/660] lr: 1.0000e-03 eta: 2:12:17 time: 0.6179 data_time: 0.0272 memory: 42708 grad_norm: 4.6496 loss: 1.4409 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4409 2023/02/18 04:19:16 - mmengine - INFO - Epoch(train) [32][180/660] lr: 1.0000e-03 eta: 2:12:04 time: 0.6293 data_time: 0.0278 memory: 42708 grad_norm: 4.6169 loss: 1.3963 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3963 2023/02/18 04:19:28 - mmengine - INFO - Epoch(train) [32][200/660] lr: 1.0000e-03 eta: 2:11:51 time: 0.6215 data_time: 0.0277 memory: 42708 grad_norm: 4.5352 loss: 1.4546 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.4546 2023/02/18 04:19:41 - mmengine - INFO - Epoch(train) [32][220/660] lr: 1.0000e-03 eta: 2:11:38 time: 0.6293 data_time: 0.0293 memory: 42708 grad_norm: 4.5627 loss: 1.3445 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3445 2023/02/18 04:19:53 - mmengine - INFO - Epoch(train) [32][240/660] lr: 1.0000e-03 eta: 2:11:25 time: 0.6214 data_time: 0.0277 memory: 42708 grad_norm: 4.6414 loss: 1.3693 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.3693 2023/02/18 04:20:06 - mmengine - INFO - Epoch(train) [32][260/660] lr: 1.0000e-03 eta: 2:11:12 time: 0.6300 data_time: 0.0282 memory: 42708 grad_norm: 4.7202 loss: 1.4259 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4259 2023/02/18 04:20:18 - mmengine - INFO - Epoch(train) [32][280/660] lr: 1.0000e-03 eta: 2:10:59 time: 0.6267 data_time: 0.0271 memory: 42708 grad_norm: 4.5805 loss: 1.4409 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.4409 2023/02/18 04:20:31 - mmengine - INFO - Epoch(train) [32][300/660] lr: 1.0000e-03 eta: 2:10:46 time: 0.6381 data_time: 0.0270 memory: 42708 grad_norm: 4.6321 loss: 1.4493 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.4493 2023/02/18 04:20:43 - mmengine - INFO - Epoch(train) [32][320/660] lr: 1.0000e-03 eta: 2:10:33 time: 0.6182 data_time: 0.0270 memory: 42708 grad_norm: 4.5884 loss: 1.4736 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.4736 2023/02/18 04:20:56 - mmengine - INFO - Epoch(train) [32][340/660] lr: 1.0000e-03 eta: 2:10:20 time: 0.6288 data_time: 0.0284 memory: 42708 grad_norm: 4.5552 loss: 1.3184 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3184 2023/02/18 04:21:08 - mmengine - INFO - Epoch(train) [32][360/660] lr: 1.0000e-03 eta: 2:10:07 time: 0.6293 data_time: 0.0312 memory: 42708 grad_norm: 4.6548 loss: 1.3057 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3057 2023/02/18 04:21:21 - mmengine - INFO - Epoch(train) [32][380/660] lr: 1.0000e-03 eta: 2:09:54 time: 0.6283 data_time: 0.0271 memory: 42708 grad_norm: 4.6467 loss: 1.4104 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4104 2023/02/18 04:21:33 - mmengine - INFO - Epoch(train) [32][400/660] lr: 1.0000e-03 eta: 2:09:41 time: 0.6165 data_time: 0.0262 memory: 42708 grad_norm: 4.6057 loss: 1.4054 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.4054 2023/02/18 04:21:46 - mmengine - INFO - Epoch(train) [32][420/660] lr: 1.0000e-03 eta: 2:09:28 time: 0.6315 data_time: 0.0262 memory: 42708 grad_norm: 4.6933 loss: 1.4698 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.4698 2023/02/18 04:21:58 - mmengine - INFO - Epoch(train) [32][440/660] lr: 1.0000e-03 eta: 2:09:15 time: 0.6190 data_time: 0.0270 memory: 42708 grad_norm: 4.7000 loss: 1.3445 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3445 2023/02/18 04:22:11 - mmengine - INFO - Epoch(train) [32][460/660] lr: 1.0000e-03 eta: 2:09:02 time: 0.6296 data_time: 0.0282 memory: 42708 grad_norm: 4.5822 loss: 1.4097 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.4097 2023/02/18 04:22:23 - mmengine - INFO - Epoch(train) [32][480/660] lr: 1.0000e-03 eta: 2:08:49 time: 0.6191 data_time: 0.0283 memory: 42708 grad_norm: 4.6343 loss: 1.3333 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3333 2023/02/18 04:22:36 - mmengine - INFO - Epoch(train) [32][500/660] lr: 1.0000e-03 eta: 2:08:36 time: 0.6281 data_time: 0.0268 memory: 42708 grad_norm: 4.5961 loss: 1.3845 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3845 2023/02/18 04:22:48 - mmengine - INFO - Epoch(train) [32][520/660] lr: 1.0000e-03 eta: 2:08:23 time: 0.6221 data_time: 0.0292 memory: 42708 grad_norm: 4.7092 loss: 1.3852 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3852 2023/02/18 04:23:01 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:23:01 - mmengine - INFO - Epoch(train) [32][540/660] lr: 1.0000e-03 eta: 2:08:10 time: 0.6257 data_time: 0.0269 memory: 42708 grad_norm: 4.5878 loss: 1.4119 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.4119 2023/02/18 04:23:13 - mmengine - INFO - Epoch(train) [32][560/660] lr: 1.0000e-03 eta: 2:07:57 time: 0.6217 data_time: 0.0290 memory: 42708 grad_norm: 4.5484 loss: 1.4035 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.4035 2023/02/18 04:23:26 - mmengine - INFO - Epoch(train) [32][580/660] lr: 1.0000e-03 eta: 2:07:44 time: 0.6294 data_time: 0.0298 memory: 42708 grad_norm: 4.6665 loss: 1.4490 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4490 2023/02/18 04:23:38 - mmengine - INFO - Epoch(train) [32][600/660] lr: 1.0000e-03 eta: 2:07:31 time: 0.6185 data_time: 0.0277 memory: 42708 grad_norm: 4.6381 loss: 1.3419 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3419 2023/02/18 04:23:51 - mmengine - INFO - Epoch(train) [32][620/660] lr: 1.0000e-03 eta: 2:07:18 time: 0.6307 data_time: 0.0273 memory: 42708 grad_norm: 4.7249 loss: 1.4433 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.4433 2023/02/18 04:24:03 - mmengine - INFO - Epoch(train) [32][640/660] lr: 1.0000e-03 eta: 2:07:05 time: 0.6207 data_time: 0.0301 memory: 42708 grad_norm: 4.6941 loss: 1.3997 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3997 2023/02/18 04:24:16 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:24:16 - mmengine - INFO - Epoch(train) [32][660/660] lr: 1.0000e-03 eta: 2:06:52 time: 0.6165 data_time: 0.0286 memory: 42708 grad_norm: 4.7387 loss: 1.4375 top1_acc: 0.5556 top5_acc: 0.8519 loss_cls: 1.4375 2023/02/18 04:24:31 - mmengine - INFO - Epoch(train) [33][ 20/660] lr: 1.0000e-03 eta: 2:06:40 time: 0.7420 data_time: 0.1238 memory: 42708 grad_norm: 4.7412 loss: 1.4475 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.4475 2023/02/18 04:24:43 - mmengine - INFO - Epoch(train) [33][ 40/660] lr: 1.0000e-03 eta: 2:06:27 time: 0.6250 data_time: 0.0305 memory: 42708 grad_norm: 4.6183 loss: 1.3639 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3639 2023/02/18 04:24:56 - mmengine - INFO - Epoch(train) [33][ 60/660] lr: 1.0000e-03 eta: 2:06:15 time: 0.6701 data_time: 0.0656 memory: 42708 grad_norm: 4.6025 loss: 1.3788 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3788 2023/02/18 04:25:09 - mmengine - INFO - Epoch(train) [33][ 80/660] lr: 1.0000e-03 eta: 2:06:02 time: 0.6236 data_time: 0.0294 memory: 42708 grad_norm: 4.6167 loss: 1.3732 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.3732 2023/02/18 04:25:22 - mmengine - INFO - Epoch(train) [33][100/660] lr: 1.0000e-03 eta: 2:05:49 time: 0.6344 data_time: 0.0309 memory: 42708 grad_norm: 4.6682 loss: 1.3399 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3399 2023/02/18 04:25:34 - mmengine - INFO - Epoch(train) [33][120/660] lr: 1.0000e-03 eta: 2:05:36 time: 0.6263 data_time: 0.0297 memory: 42708 grad_norm: 4.6683 loss: 1.4566 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.4566 2023/02/18 04:25:47 - mmengine - INFO - Epoch(train) [33][140/660] lr: 1.0000e-03 eta: 2:05:23 time: 0.6379 data_time: 0.0362 memory: 42708 grad_norm: 4.7234 loss: 1.3063 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3063 2023/02/18 04:25:59 - mmengine - INFO - Epoch(train) [33][160/660] lr: 1.0000e-03 eta: 2:05:10 time: 0.6278 data_time: 0.0308 memory: 42708 grad_norm: 4.6771 loss: 1.4199 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.4199 2023/02/18 04:26:12 - mmengine - INFO - Epoch(train) [33][180/660] lr: 1.0000e-03 eta: 2:04:57 time: 0.6356 data_time: 0.0337 memory: 42708 grad_norm: 4.7441 loss: 1.3938 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.3938 2023/02/18 04:26:25 - mmengine - INFO - Epoch(train) [33][200/660] lr: 1.0000e-03 eta: 2:04:44 time: 0.6218 data_time: 0.0302 memory: 42708 grad_norm: 4.5162 loss: 1.4067 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.4067 2023/02/18 04:26:37 - mmengine - INFO - Epoch(train) [33][220/660] lr: 1.0000e-03 eta: 2:04:31 time: 0.6314 data_time: 0.0312 memory: 42708 grad_norm: 4.7338 loss: 1.5154 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.5154 2023/02/18 04:26:50 - mmengine - INFO - Epoch(train) [33][240/660] lr: 1.0000e-03 eta: 2:04:18 time: 0.6202 data_time: 0.0297 memory: 42708 grad_norm: 4.5995 loss: 1.4627 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.4627 2023/02/18 04:27:02 - mmengine - INFO - Epoch(train) [33][260/660] lr: 1.0000e-03 eta: 2:04:05 time: 0.6406 data_time: 0.0316 memory: 42708 grad_norm: 4.5623 loss: 1.2703 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.2703 2023/02/18 04:27:15 - mmengine - INFO - Epoch(train) [33][280/660] lr: 1.0000e-03 eta: 2:03:52 time: 0.6285 data_time: 0.0340 memory: 42708 grad_norm: 4.6303 loss: 1.3672 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3672 2023/02/18 04:27:28 - mmengine - INFO - Epoch(train) [33][300/660] lr: 1.0000e-03 eta: 2:03:40 time: 0.6418 data_time: 0.0317 memory: 42708 grad_norm: 4.6480 loss: 1.3720 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3720 2023/02/18 04:27:40 - mmengine - INFO - Epoch(train) [33][320/660] lr: 1.0000e-03 eta: 2:03:27 time: 0.6232 data_time: 0.0308 memory: 42708 grad_norm: 4.5277 loss: 1.3623 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3623 2023/02/18 04:27:53 - mmengine - INFO - Epoch(train) [33][340/660] lr: 1.0000e-03 eta: 2:03:14 time: 0.6420 data_time: 0.0332 memory: 42708 grad_norm: 4.6810 loss: 1.4908 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 1.4908 2023/02/18 04:28:06 - mmengine - INFO - Epoch(train) [33][360/660] lr: 1.0000e-03 eta: 2:03:01 time: 0.6254 data_time: 0.0304 memory: 42708 grad_norm: 4.7425 loss: 1.3951 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3951 2023/02/18 04:28:18 - mmengine - INFO - Epoch(train) [33][380/660] lr: 1.0000e-03 eta: 2:02:48 time: 0.6375 data_time: 0.0331 memory: 42708 grad_norm: 4.5183 loss: 1.4106 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4106 2023/02/18 04:28:31 - mmengine - INFO - Epoch(train) [33][400/660] lr: 1.0000e-03 eta: 2:02:35 time: 0.6275 data_time: 0.0314 memory: 42708 grad_norm: 4.7421 loss: 1.4681 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.4681 2023/02/18 04:28:44 - mmengine - INFO - Epoch(train) [33][420/660] lr: 1.0000e-03 eta: 2:02:22 time: 0.6356 data_time: 0.0333 memory: 42708 grad_norm: 4.6607 loss: 1.3210 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3210 2023/02/18 04:28:56 - mmengine - INFO - Epoch(train) [33][440/660] lr: 1.0000e-03 eta: 2:02:09 time: 0.6254 data_time: 0.0318 memory: 42708 grad_norm: 4.6395 loss: 1.5083 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.5083 2023/02/18 04:29:09 - mmengine - INFO - Epoch(train) [33][460/660] lr: 1.0000e-03 eta: 2:01:56 time: 0.6362 data_time: 0.0332 memory: 42708 grad_norm: 4.6328 loss: 1.4268 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.4268 2023/02/18 04:29:21 - mmengine - INFO - Epoch(train) [33][480/660] lr: 1.0000e-03 eta: 2:01:43 time: 0.6264 data_time: 0.0307 memory: 42708 grad_norm: 4.6929 loss: 1.3962 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3962 2023/02/18 04:29:34 - mmengine - INFO - Epoch(train) [33][500/660] lr: 1.0000e-03 eta: 2:01:30 time: 0.6362 data_time: 0.0336 memory: 42708 grad_norm: 4.6790 loss: 1.3575 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.3575 2023/02/18 04:29:47 - mmengine - INFO - Epoch(train) [33][520/660] lr: 1.0000e-03 eta: 2:01:18 time: 0.6290 data_time: 0.0333 memory: 42708 grad_norm: 4.5937 loss: 1.4008 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.4008 2023/02/18 04:30:00 - mmengine - INFO - Epoch(train) [33][540/660] lr: 1.0000e-03 eta: 2:01:05 time: 0.6390 data_time: 0.0347 memory: 42708 grad_norm: 4.7683 loss: 1.3900 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3900 2023/02/18 04:30:12 - mmengine - INFO - Epoch(train) [33][560/660] lr: 1.0000e-03 eta: 2:00:52 time: 0.6335 data_time: 0.0344 memory: 42708 grad_norm: 4.5592 loss: 1.3550 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3550 2023/02/18 04:30:25 - mmengine - INFO - Epoch(train) [33][580/660] lr: 1.0000e-03 eta: 2:00:39 time: 0.6388 data_time: 0.0334 memory: 42708 grad_norm: 4.7465 loss: 1.4502 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4502 2023/02/18 04:30:38 - mmengine - INFO - Epoch(train) [33][600/660] lr: 1.0000e-03 eta: 2:00:26 time: 0.6256 data_time: 0.0351 memory: 42708 grad_norm: 4.6353 loss: 1.4877 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.4877 2023/02/18 04:30:50 - mmengine - INFO - Epoch(train) [33][620/660] lr: 1.0000e-03 eta: 2:00:13 time: 0.6365 data_time: 0.0342 memory: 42708 grad_norm: 4.7218 loss: 1.3377 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.3377 2023/02/18 04:31:03 - mmengine - INFO - Epoch(train) [33][640/660] lr: 1.0000e-03 eta: 2:00:00 time: 0.6240 data_time: 0.0342 memory: 42708 grad_norm: 4.7894 loss: 1.4449 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.4449 2023/02/18 04:31:15 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:31:15 - mmengine - INFO - Epoch(train) [33][660/660] lr: 1.0000e-03 eta: 1:59:47 time: 0.6153 data_time: 0.0296 memory: 42708 grad_norm: 4.6651 loss: 1.3782 top1_acc: 0.7037 top5_acc: 0.8889 loss_cls: 1.3782 2023/02/18 04:31:15 - mmengine - INFO - Saving checkpoint at 33 epochs 2023/02/18 04:31:31 - mmengine - INFO - Epoch(train) [34][ 20/660] lr: 1.0000e-03 eta: 1:59:35 time: 0.7176 data_time: 0.1231 memory: 42708 grad_norm: 4.6397 loss: 1.3721 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.3721 2023/02/18 04:31:43 - mmengine - INFO - Epoch(train) [34][ 40/660] lr: 1.0000e-03 eta: 1:59:22 time: 0.6264 data_time: 0.0350 memory: 42708 grad_norm: 4.7139 loss: 1.4658 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4658 2023/02/18 04:31:56 - mmengine - INFO - Epoch(train) [34][ 60/660] lr: 1.0000e-03 eta: 1:59:09 time: 0.6294 data_time: 0.0328 memory: 42708 grad_norm: 4.6467 loss: 1.3332 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3332 2023/02/18 04:32:08 - mmengine - INFO - Epoch(train) [34][ 80/660] lr: 1.0000e-03 eta: 1:58:56 time: 0.6226 data_time: 0.0291 memory: 42708 grad_norm: 4.8188 loss: 1.4814 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.4814 2023/02/18 04:32:21 - mmengine - INFO - Epoch(train) [34][100/660] lr: 1.0000e-03 eta: 1:58:43 time: 0.6378 data_time: 0.0315 memory: 42708 grad_norm: 4.6632 loss: 1.4109 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.4109 2023/02/18 04:32:33 - mmengine - INFO - Epoch(train) [34][120/660] lr: 1.0000e-03 eta: 1:58:30 time: 0.6248 data_time: 0.0307 memory: 42708 grad_norm: 4.6327 loss: 1.3359 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3359 2023/02/18 04:32:46 - mmengine - INFO - Epoch(train) [34][140/660] lr: 1.0000e-03 eta: 1:58:18 time: 0.6468 data_time: 0.0334 memory: 42708 grad_norm: 4.6837 loss: 1.3241 top1_acc: 0.7188 top5_acc: 0.9688 loss_cls: 1.3241 2023/02/18 04:32:59 - mmengine - INFO - Epoch(train) [34][160/660] lr: 1.0000e-03 eta: 1:58:05 time: 0.6238 data_time: 0.0301 memory: 42708 grad_norm: 4.6557 loss: 1.4013 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4013 2023/02/18 04:33:11 - mmengine - INFO - Epoch(train) [34][180/660] lr: 1.0000e-03 eta: 1:57:52 time: 0.6330 data_time: 0.0323 memory: 42708 grad_norm: 4.6959 loss: 1.4842 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.4842 2023/02/18 04:33:24 - mmengine - INFO - Epoch(train) [34][200/660] lr: 1.0000e-03 eta: 1:57:39 time: 0.6259 data_time: 0.0289 memory: 42708 grad_norm: 4.6031 loss: 1.3837 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.3837 2023/02/18 04:33:37 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:33:37 - mmengine - INFO - Epoch(train) [34][220/660] lr: 1.0000e-03 eta: 1:57:26 time: 0.6372 data_time: 0.0356 memory: 42708 grad_norm: 4.7409 loss: 1.3858 top1_acc: 0.4062 top5_acc: 0.8438 loss_cls: 1.3858 2023/02/18 04:33:49 - mmengine - INFO - Epoch(train) [34][240/660] lr: 1.0000e-03 eta: 1:57:13 time: 0.6329 data_time: 0.0318 memory: 42708 grad_norm: 4.6714 loss: 1.4294 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.4294 2023/02/18 04:34:02 - mmengine - INFO - Epoch(train) [34][260/660] lr: 1.0000e-03 eta: 1:57:00 time: 0.6373 data_time: 0.0343 memory: 42708 grad_norm: 4.6650 loss: 1.3497 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.3497 2023/02/18 04:34:15 - mmengine - INFO - Epoch(train) [34][280/660] lr: 1.0000e-03 eta: 1:56:47 time: 0.6335 data_time: 0.0309 memory: 42708 grad_norm: 4.6435 loss: 1.3066 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3066 2023/02/18 04:34:27 - mmengine - INFO - Epoch(train) [34][300/660] lr: 1.0000e-03 eta: 1:56:34 time: 0.6341 data_time: 0.0340 memory: 42708 grad_norm: 4.6771 loss: 1.4273 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4273 2023/02/18 04:34:40 - mmengine - INFO - Epoch(train) [34][320/660] lr: 1.0000e-03 eta: 1:56:22 time: 0.6252 data_time: 0.0324 memory: 42708 grad_norm: 4.6953 loss: 1.3685 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.3685 2023/02/18 04:34:53 - mmengine - INFO - Epoch(train) [34][340/660] lr: 1.0000e-03 eta: 1:56:09 time: 0.6337 data_time: 0.0341 memory: 42708 grad_norm: 4.6433 loss: 1.4035 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.4035 2023/02/18 04:35:05 - mmengine - INFO - Epoch(train) [34][360/660] lr: 1.0000e-03 eta: 1:55:56 time: 0.6307 data_time: 0.0308 memory: 42708 grad_norm: 4.6598 loss: 1.4383 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.4383 2023/02/18 04:35:18 - mmengine - INFO - Epoch(train) [34][380/660] lr: 1.0000e-03 eta: 1:55:43 time: 0.6384 data_time: 0.0336 memory: 42708 grad_norm: 4.6682 loss: 1.3647 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.3647 2023/02/18 04:35:31 - mmengine - INFO - Epoch(train) [34][400/660] lr: 1.0000e-03 eta: 1:55:30 time: 0.6251 data_time: 0.0291 memory: 42708 grad_norm: 4.7386 loss: 1.4324 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4324 2023/02/18 04:35:43 - mmengine - INFO - Epoch(train) [34][420/660] lr: 1.0000e-03 eta: 1:55:17 time: 0.6399 data_time: 0.0344 memory: 42708 grad_norm: 4.7864 loss: 1.4545 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.4545 2023/02/18 04:35:56 - mmengine - INFO - Epoch(train) [34][440/660] lr: 1.0000e-03 eta: 1:55:04 time: 0.6278 data_time: 0.0302 memory: 42708 grad_norm: 4.6395 loss: 1.4058 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.4058 2023/02/18 04:36:09 - mmengine - INFO - Epoch(train) [34][460/660] lr: 1.0000e-03 eta: 1:54:51 time: 0.6398 data_time: 0.0353 memory: 42708 grad_norm: 4.8121 loss: 1.4199 top1_acc: 0.6875 top5_acc: 0.7812 loss_cls: 1.4199 2023/02/18 04:36:21 - mmengine - INFO - Epoch(train) [34][480/660] lr: 1.0000e-03 eta: 1:54:38 time: 0.6291 data_time: 0.0303 memory: 42708 grad_norm: 4.7659 loss: 1.4116 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4116 2023/02/18 04:36:34 - mmengine - INFO - Epoch(train) [34][500/660] lr: 1.0000e-03 eta: 1:54:26 time: 0.6383 data_time: 0.0336 memory: 42708 grad_norm: 4.6877 loss: 1.3019 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3019 2023/02/18 04:36:47 - mmengine - INFO - Epoch(train) [34][520/660] lr: 1.0000e-03 eta: 1:54:13 time: 0.6263 data_time: 0.0279 memory: 42708 grad_norm: 4.7432 loss: 1.2948 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2948 2023/02/18 04:36:59 - mmengine - INFO - Epoch(train) [34][540/660] lr: 1.0000e-03 eta: 1:54:00 time: 0.6405 data_time: 0.0347 memory: 42708 grad_norm: 4.7375 loss: 1.3613 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3613 2023/02/18 04:37:12 - mmengine - INFO - Epoch(train) [34][560/660] lr: 1.0000e-03 eta: 1:53:47 time: 0.6288 data_time: 0.0299 memory: 42708 grad_norm: 4.5822 loss: 1.3713 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3713 2023/02/18 04:37:25 - mmengine - INFO - Epoch(train) [34][580/660] lr: 1.0000e-03 eta: 1:53:34 time: 0.6411 data_time: 0.0363 memory: 42708 grad_norm: 4.6936 loss: 1.3867 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3867 2023/02/18 04:37:37 - mmengine - INFO - Epoch(train) [34][600/660] lr: 1.0000e-03 eta: 1:53:21 time: 0.6283 data_time: 0.0300 memory: 42708 grad_norm: 4.7608 loss: 1.3731 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3731 2023/02/18 04:37:50 - mmengine - INFO - Epoch(train) [34][620/660] lr: 1.0000e-03 eta: 1:53:08 time: 0.6389 data_time: 0.0384 memory: 42708 grad_norm: 4.6565 loss: 1.4810 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.4810 2023/02/18 04:38:03 - mmengine - INFO - Epoch(train) [34][640/660] lr: 1.0000e-03 eta: 1:52:55 time: 0.6274 data_time: 0.0280 memory: 42708 grad_norm: 4.6859 loss: 1.4715 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.4715 2023/02/18 04:38:15 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:38:15 - mmengine - INFO - Epoch(train) [34][660/660] lr: 1.0000e-03 eta: 1:52:42 time: 0.6192 data_time: 0.0288 memory: 42708 grad_norm: 4.7145 loss: 1.3708 top1_acc: 0.5185 top5_acc: 0.8519 loss_cls: 1.3708 2023/02/18 04:38:30 - mmengine - INFO - Epoch(train) [35][ 20/660] lr: 1.0000e-03 eta: 1:52:30 time: 0.7227 data_time: 0.1158 memory: 42708 grad_norm: 4.7277 loss: 1.4764 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.4764 2023/02/18 04:38:42 - mmengine - INFO - Epoch(train) [35][ 40/660] lr: 1.0000e-03 eta: 1:52:17 time: 0.6299 data_time: 0.0309 memory: 42708 grad_norm: 4.7077 loss: 1.3296 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3296 2023/02/18 04:38:55 - mmengine - INFO - Epoch(train) [35][ 60/660] lr: 1.0000e-03 eta: 1:52:05 time: 0.6427 data_time: 0.0343 memory: 42708 grad_norm: 4.7582 loss: 1.3885 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3885 2023/02/18 04:39:08 - mmengine - INFO - Epoch(train) [35][ 80/660] lr: 1.0000e-03 eta: 1:51:52 time: 0.6333 data_time: 0.0279 memory: 42708 grad_norm: 4.5925 loss: 1.3669 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3669 2023/02/18 04:39:21 - mmengine - INFO - Epoch(train) [35][100/660] lr: 1.0000e-03 eta: 1:51:39 time: 0.6441 data_time: 0.0365 memory: 42708 grad_norm: 4.6948 loss: 1.3215 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3215 2023/02/18 04:39:33 - mmengine - INFO - Epoch(train) [35][120/660] lr: 1.0000e-03 eta: 1:51:26 time: 0.6303 data_time: 0.0280 memory: 42708 grad_norm: 4.6259 loss: 1.3226 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3226 2023/02/18 04:39:46 - mmengine - INFO - Epoch(train) [35][140/660] lr: 1.0000e-03 eta: 1:51:13 time: 0.6393 data_time: 0.0345 memory: 42708 grad_norm: 4.7341 loss: 1.4841 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.4841 2023/02/18 04:39:59 - mmengine - INFO - Epoch(train) [35][160/660] lr: 1.0000e-03 eta: 1:51:00 time: 0.6360 data_time: 0.0294 memory: 42708 grad_norm: 4.6735 loss: 1.4125 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.4125 2023/02/18 04:40:11 - mmengine - INFO - Epoch(train) [35][180/660] lr: 1.0000e-03 eta: 1:50:48 time: 0.6405 data_time: 0.0366 memory: 42708 grad_norm: 4.7803 loss: 1.3601 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3601 2023/02/18 04:40:24 - mmengine - INFO - Epoch(train) [35][200/660] lr: 1.0000e-03 eta: 1:50:35 time: 0.6295 data_time: 0.0296 memory: 42708 grad_norm: 4.7653 loss: 1.4930 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4930 2023/02/18 04:40:37 - mmengine - INFO - Epoch(train) [35][220/660] lr: 1.0000e-03 eta: 1:50:22 time: 0.6425 data_time: 0.0337 memory: 42708 grad_norm: 4.7484 loss: 1.3605 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.3605 2023/02/18 04:40:50 - mmengine - INFO - Epoch(train) [35][240/660] lr: 1.0000e-03 eta: 1:50:09 time: 0.6296 data_time: 0.0307 memory: 42708 grad_norm: 4.6465 loss: 1.3196 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3196 2023/02/18 04:41:02 - mmengine - INFO - Epoch(train) [35][260/660] lr: 1.0000e-03 eta: 1:49:56 time: 0.6419 data_time: 0.0324 memory: 42708 grad_norm: 4.7543 loss: 1.2936 top1_acc: 0.4688 top5_acc: 0.9062 loss_cls: 1.2936 2023/02/18 04:41:15 - mmengine - INFO - Epoch(train) [35][280/660] lr: 1.0000e-03 eta: 1:49:43 time: 0.6273 data_time: 0.0295 memory: 42708 grad_norm: 4.7233 loss: 1.3007 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3007 2023/02/18 04:41:28 - mmengine - INFO - Epoch(train) [35][300/660] lr: 1.0000e-03 eta: 1:49:31 time: 0.6403 data_time: 0.0341 memory: 42708 grad_norm: 4.7039 loss: 1.4181 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.4181 2023/02/18 04:41:40 - mmengine - INFO - Epoch(train) [35][320/660] lr: 1.0000e-03 eta: 1:49:18 time: 0.6265 data_time: 0.0309 memory: 42708 grad_norm: 4.6008 loss: 1.3561 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3561 2023/02/18 04:41:53 - mmengine - INFO - Epoch(train) [35][340/660] lr: 1.0000e-03 eta: 1:49:05 time: 0.6342 data_time: 0.0331 memory: 42708 grad_norm: 4.7099 loss: 1.3698 top1_acc: 0.4062 top5_acc: 0.8750 loss_cls: 1.3698 2023/02/18 04:42:05 - mmengine - INFO - Epoch(train) [35][360/660] lr: 1.0000e-03 eta: 1:48:52 time: 0.6284 data_time: 0.0344 memory: 42708 grad_norm: 4.8320 loss: 1.4610 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.4610 2023/02/18 04:42:18 - mmengine - INFO - Epoch(train) [35][380/660] lr: 1.0000e-03 eta: 1:48:39 time: 0.6375 data_time: 0.0358 memory: 42708 grad_norm: 4.7214 loss: 1.3510 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3510 2023/02/18 04:42:31 - mmengine - INFO - Epoch(train) [35][400/660] lr: 1.0000e-03 eta: 1:48:26 time: 0.6301 data_time: 0.0318 memory: 42708 grad_norm: 4.7524 loss: 1.4092 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.4092 2023/02/18 04:42:44 - mmengine - INFO - Epoch(train) [35][420/660] lr: 1.0000e-03 eta: 1:48:13 time: 0.6371 data_time: 0.0329 memory: 42708 grad_norm: 4.8283 loss: 1.3788 top1_acc: 0.7500 top5_acc: 0.9688 loss_cls: 1.3788 2023/02/18 04:42:56 - mmengine - INFO - Epoch(train) [35][440/660] lr: 1.0000e-03 eta: 1:48:00 time: 0.6245 data_time: 0.0307 memory: 42708 grad_norm: 4.7430 loss: 1.3668 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3668 2023/02/18 04:43:09 - mmengine - INFO - Epoch(train) [35][460/660] lr: 1.0000e-03 eta: 1:47:48 time: 0.6446 data_time: 0.0334 memory: 42708 grad_norm: 4.7541 loss: 1.3819 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.3819 2023/02/18 04:43:22 - mmengine - INFO - Epoch(train) [35][480/660] lr: 1.0000e-03 eta: 1:47:35 time: 0.6288 data_time: 0.0316 memory: 42708 grad_norm: 4.6837 loss: 1.4067 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4067 2023/02/18 04:43:34 - mmengine - INFO - Epoch(train) [35][500/660] lr: 1.0000e-03 eta: 1:47:22 time: 0.6436 data_time: 0.0348 memory: 42708 grad_norm: 4.7412 loss: 1.3540 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.3540 2023/02/18 04:43:47 - mmengine - INFO - Epoch(train) [35][520/660] lr: 1.0000e-03 eta: 1:47:09 time: 0.6337 data_time: 0.0300 memory: 42708 grad_norm: 4.6660 loss: 1.3322 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 1.3322 2023/02/18 04:44:00 - mmengine - INFO - Epoch(train) [35][540/660] lr: 1.0000e-03 eta: 1:46:56 time: 0.6432 data_time: 0.0350 memory: 42708 grad_norm: 4.7450 loss: 1.3379 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3379 2023/02/18 04:44:13 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:44:13 - mmengine - INFO - Epoch(train) [35][560/660] lr: 1.0000e-03 eta: 1:46:43 time: 0.6283 data_time: 0.0299 memory: 42708 grad_norm: 4.7762 loss: 1.3624 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.3624 2023/02/18 04:44:25 - mmengine - INFO - Epoch(train) [35][580/660] lr: 1.0000e-03 eta: 1:46:30 time: 0.6405 data_time: 0.0349 memory: 42708 grad_norm: 4.8232 loss: 1.3931 top1_acc: 0.3750 top5_acc: 0.8438 loss_cls: 1.3931 2023/02/18 04:44:38 - mmengine - INFO - Epoch(train) [35][600/660] lr: 1.0000e-03 eta: 1:46:18 time: 0.6306 data_time: 0.0330 memory: 42708 grad_norm: 4.7092 loss: 1.3690 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3690 2023/02/18 04:44:51 - mmengine - INFO - Epoch(train) [35][620/660] lr: 1.0000e-03 eta: 1:46:05 time: 0.6404 data_time: 0.0397 memory: 42708 grad_norm: 4.6975 loss: 1.2277 top1_acc: 0.5625 top5_acc: 0.9688 loss_cls: 1.2277 2023/02/18 04:45:03 - mmengine - INFO - Epoch(train) [35][640/660] lr: 1.0000e-03 eta: 1:45:52 time: 0.6279 data_time: 0.0297 memory: 42708 grad_norm: 4.7014 loss: 1.3614 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3614 2023/02/18 04:45:16 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:45:16 - mmengine - INFO - Epoch(train) [35][660/660] lr: 1.0000e-03 eta: 1:45:39 time: 0.6198 data_time: 0.0287 memory: 42708 grad_norm: 4.7624 loss: 1.4177 top1_acc: 0.5556 top5_acc: 0.7778 loss_cls: 1.4177 2023/02/18 04:45:23 - mmengine - INFO - Epoch(val) [35][20/97] eta: 0:00:25 time: 0.3369 data_time: 0.1231 memory: 6154 2023/02/18 04:45:27 - mmengine - INFO - Epoch(val) [35][40/97] eta: 0:00:16 time: 0.2460 data_time: 0.0342 memory: 6154 2023/02/18 04:45:32 - mmengine - INFO - Epoch(val) [35][60/97] eta: 0:00:10 time: 0.2525 data_time: 0.0422 memory: 6154 2023/02/18 04:45:37 - mmengine - INFO - Epoch(val) [35][80/97] eta: 0:00:04 time: 0.2413 data_time: 0.0320 memory: 6154 2023/02/18 04:45:42 - mmengine - INFO - Epoch(val) [35][97/97] acc/top1: 0.3625 acc/top5: 0.6730 acc/mean1: 0.2973 2023/02/18 04:45:56 - mmengine - INFO - Epoch(train) [36][ 20/660] lr: 1.0000e-03 eta: 1:45:27 time: 0.7162 data_time: 0.1092 memory: 42708 grad_norm: 4.6240 loss: 1.2531 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.2531 2023/02/18 04:46:08 - mmengine - INFO - Epoch(train) [36][ 40/660] lr: 1.0000e-03 eta: 1:45:14 time: 0.6224 data_time: 0.0290 memory: 42708 grad_norm: 4.7922 loss: 1.3644 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3644 2023/02/18 04:46:21 - mmengine - INFO - Epoch(train) [36][ 60/660] lr: 1.0000e-03 eta: 1:45:01 time: 0.6290 data_time: 0.0279 memory: 42708 grad_norm: 4.6561 loss: 1.2349 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2349 2023/02/18 04:46:33 - mmengine - INFO - Epoch(train) [36][ 80/660] lr: 1.0000e-03 eta: 1:44:48 time: 0.6198 data_time: 0.0271 memory: 42708 grad_norm: 4.7938 loss: 1.3476 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3476 2023/02/18 04:46:46 - mmengine - INFO - Epoch(train) [36][100/660] lr: 1.0000e-03 eta: 1:44:35 time: 0.6275 data_time: 0.0284 memory: 42708 grad_norm: 4.7117 loss: 1.2948 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.2948 2023/02/18 04:46:58 - mmengine - INFO - Epoch(train) [36][120/660] lr: 1.0000e-03 eta: 1:44:22 time: 0.6257 data_time: 0.0263 memory: 42708 grad_norm: 4.7294 loss: 1.3596 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.3596 2023/02/18 04:47:11 - mmengine - INFO - Epoch(train) [36][140/660] lr: 1.0000e-03 eta: 1:44:09 time: 0.6331 data_time: 0.0281 memory: 42708 grad_norm: 4.7365 loss: 1.5162 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.5162 2023/02/18 04:47:24 - mmengine - INFO - Epoch(train) [36][160/660] lr: 1.0000e-03 eta: 1:43:56 time: 0.6200 data_time: 0.0256 memory: 42708 grad_norm: 4.6169 loss: 1.3909 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3909 2023/02/18 04:47:36 - mmengine - INFO - Epoch(train) [36][180/660] lr: 1.0000e-03 eta: 1:43:43 time: 0.6339 data_time: 0.0270 memory: 42708 grad_norm: 4.7158 loss: 1.4039 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4039 2023/02/18 04:47:49 - mmengine - INFO - Epoch(train) [36][200/660] lr: 1.0000e-03 eta: 1:43:30 time: 0.6234 data_time: 0.0264 memory: 42708 grad_norm: 4.7217 loss: 1.2291 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2291 2023/02/18 04:48:01 - mmengine - INFO - Epoch(train) [36][220/660] lr: 1.0000e-03 eta: 1:43:17 time: 0.6328 data_time: 0.0276 memory: 42708 grad_norm: 4.7464 loss: 1.3456 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3456 2023/02/18 04:48:14 - mmengine - INFO - Epoch(train) [36][240/660] lr: 1.0000e-03 eta: 1:43:05 time: 0.6329 data_time: 0.0270 memory: 42708 grad_norm: 4.7550 loss: 1.2957 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2957 2023/02/18 04:48:27 - mmengine - INFO - Epoch(train) [36][260/660] lr: 1.0000e-03 eta: 1:42:52 time: 0.6334 data_time: 0.0279 memory: 42708 grad_norm: 4.7685 loss: 1.3689 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3689 2023/02/18 04:48:39 - mmengine - INFO - Epoch(train) [36][280/660] lr: 1.0000e-03 eta: 1:42:39 time: 0.6247 data_time: 0.0282 memory: 42708 grad_norm: 4.8032 loss: 1.3501 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3501 2023/02/18 04:48:52 - mmengine - INFO - Epoch(train) [36][300/660] lr: 1.0000e-03 eta: 1:42:26 time: 0.6301 data_time: 0.0297 memory: 42708 grad_norm: 4.6850 loss: 1.3109 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3109 2023/02/18 04:49:04 - mmengine - INFO - Epoch(train) [36][320/660] lr: 1.0000e-03 eta: 1:42:13 time: 0.6229 data_time: 0.0279 memory: 42708 grad_norm: 4.6886 loss: 1.3624 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3624 2023/02/18 04:49:17 - mmengine - INFO - Epoch(train) [36][340/660] lr: 1.0000e-03 eta: 1:42:00 time: 0.6401 data_time: 0.0289 memory: 42708 grad_norm: 4.7480 loss: 1.3020 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3020 2023/02/18 04:49:29 - mmengine - INFO - Epoch(train) [36][360/660] lr: 1.0000e-03 eta: 1:41:47 time: 0.6225 data_time: 0.0277 memory: 42708 grad_norm: 4.7852 loss: 1.3943 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3943 2023/02/18 04:49:42 - mmengine - INFO - Epoch(train) [36][380/660] lr: 1.0000e-03 eta: 1:41:34 time: 0.6313 data_time: 0.0331 memory: 42708 grad_norm: 4.7774 loss: 1.3907 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3907 2023/02/18 04:49:55 - mmengine - INFO - Epoch(train) [36][400/660] lr: 1.0000e-03 eta: 1:41:21 time: 0.6231 data_time: 0.0298 memory: 42708 grad_norm: 4.8576 loss: 1.4108 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.4108 2023/02/18 04:50:07 - mmengine - INFO - Epoch(train) [36][420/660] lr: 1.0000e-03 eta: 1:41:09 time: 0.6294 data_time: 0.0283 memory: 42708 grad_norm: 4.7465 loss: 1.3014 top1_acc: 0.4688 top5_acc: 0.8438 loss_cls: 1.3014 2023/02/18 04:50:20 - mmengine - INFO - Epoch(train) [36][440/660] lr: 1.0000e-03 eta: 1:40:56 time: 0.6262 data_time: 0.0285 memory: 42708 grad_norm: 4.7526 loss: 1.3658 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3658 2023/02/18 04:50:32 - mmengine - INFO - Epoch(train) [36][460/660] lr: 1.0000e-03 eta: 1:40:43 time: 0.6309 data_time: 0.0276 memory: 42708 grad_norm: 4.7680 loss: 1.3690 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3690 2023/02/18 04:50:45 - mmengine - INFO - Epoch(train) [36][480/660] lr: 1.0000e-03 eta: 1:40:30 time: 0.6215 data_time: 0.0289 memory: 42708 grad_norm: 4.7485 loss: 1.2324 top1_acc: 0.4688 top5_acc: 0.9375 loss_cls: 1.2324 2023/02/18 04:50:57 - mmengine - INFO - Epoch(train) [36][500/660] lr: 1.0000e-03 eta: 1:40:17 time: 0.6321 data_time: 0.0302 memory: 42708 grad_norm: 4.7477 loss: 1.2538 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.2538 2023/02/18 04:51:10 - mmengine - INFO - Epoch(train) [36][520/660] lr: 1.0000e-03 eta: 1:40:04 time: 0.6231 data_time: 0.0262 memory: 42708 grad_norm: 4.8547 loss: 1.4664 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.4664 2023/02/18 04:51:22 - mmengine - INFO - Epoch(train) [36][540/660] lr: 1.0000e-03 eta: 1:39:51 time: 0.6309 data_time: 0.0280 memory: 42708 grad_norm: 4.8211 loss: 1.3859 top1_acc: 0.6562 top5_acc: 0.9688 loss_cls: 1.3859 2023/02/18 04:51:35 - mmengine - INFO - Epoch(train) [36][560/660] lr: 1.0000e-03 eta: 1:39:38 time: 0.6235 data_time: 0.0278 memory: 42708 grad_norm: 4.7862 loss: 1.3368 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3368 2023/02/18 04:51:48 - mmengine - INFO - Epoch(train) [36][580/660] lr: 1.0000e-03 eta: 1:39:25 time: 0.6320 data_time: 0.0273 memory: 42708 grad_norm: 4.8160 loss: 1.3392 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 1.3392 2023/02/18 04:52:00 - mmengine - INFO - Epoch(train) [36][600/660] lr: 1.0000e-03 eta: 1:39:12 time: 0.6282 data_time: 0.0271 memory: 42708 grad_norm: 4.7505 loss: 1.4250 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.4250 2023/02/18 04:52:13 - mmengine - INFO - Epoch(train) [36][620/660] lr: 1.0000e-03 eta: 1:39:00 time: 0.6285 data_time: 0.0264 memory: 42708 grad_norm: 4.8660 loss: 1.3996 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3996 2023/02/18 04:52:25 - mmengine - INFO - Epoch(train) [36][640/660] lr: 1.0000e-03 eta: 1:38:47 time: 0.6281 data_time: 0.0314 memory: 42708 grad_norm: 4.8838 loss: 1.4861 top1_acc: 0.4062 top5_acc: 0.6562 loss_cls: 1.4861 2023/02/18 04:52:38 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:52:38 - mmengine - INFO - Epoch(train) [36][660/660] lr: 1.0000e-03 eta: 1:38:34 time: 0.6161 data_time: 0.0242 memory: 42708 grad_norm: 4.8263 loss: 1.4497 top1_acc: 0.7407 top5_acc: 0.9259 loss_cls: 1.4497 2023/02/18 04:52:38 - mmengine - INFO - Saving checkpoint at 36 epochs 2023/02/18 04:52:53 - mmengine - INFO - Epoch(train) [37][ 20/660] lr: 1.0000e-03 eta: 1:38:21 time: 0.7149 data_time: 0.1229 memory: 42708 grad_norm: 4.7654 loss: 1.3834 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.3834 2023/02/18 04:53:06 - mmengine - INFO - Epoch(train) [37][ 40/660] lr: 1.0000e-03 eta: 1:38:08 time: 0.6203 data_time: 0.0292 memory: 42708 grad_norm: 4.7452 loss: 1.2619 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2619 2023/02/18 04:53:18 - mmengine - INFO - Epoch(train) [37][ 60/660] lr: 1.0000e-03 eta: 1:37:56 time: 0.6263 data_time: 0.0343 memory: 42708 grad_norm: 4.8386 loss: 1.3225 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3225 2023/02/18 04:53:31 - mmengine - INFO - Epoch(train) [37][ 80/660] lr: 1.0000e-03 eta: 1:37:43 time: 0.6175 data_time: 0.0330 memory: 42708 grad_norm: 4.6712 loss: 1.3146 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3146 2023/02/18 04:53:43 - mmengine - INFO - Epoch(train) [37][100/660] lr: 1.0000e-03 eta: 1:37:30 time: 0.6288 data_time: 0.0374 memory: 42708 grad_norm: 4.8228 loss: 1.3656 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3656 2023/02/18 04:53:55 - mmengine - INFO - Epoch(train) [37][120/660] lr: 1.0000e-03 eta: 1:37:17 time: 0.6164 data_time: 0.0278 memory: 42708 grad_norm: 4.5852 loss: 1.2596 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2596 2023/02/18 04:54:08 - mmengine - INFO - Epoch(train) [37][140/660] lr: 1.0000e-03 eta: 1:37:04 time: 0.6287 data_time: 0.0349 memory: 42708 grad_norm: 4.7942 loss: 1.3765 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3765 2023/02/18 04:54:21 - mmengine - INFO - Epoch(train) [37][160/660] lr: 1.0000e-03 eta: 1:36:51 time: 0.6236 data_time: 0.0374 memory: 42708 grad_norm: 4.6950 loss: 1.2924 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2924 2023/02/18 04:54:33 - mmengine - INFO - Epoch(train) [37][180/660] lr: 1.0000e-03 eta: 1:36:38 time: 0.6332 data_time: 0.0380 memory: 42708 grad_norm: 4.9080 loss: 1.3608 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3608 2023/02/18 04:54:46 - mmengine - INFO - Epoch(train) [37][200/660] lr: 1.0000e-03 eta: 1:36:25 time: 0.6205 data_time: 0.0309 memory: 42708 grad_norm: 4.7835 loss: 1.4289 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.4289 2023/02/18 04:54:58 - mmengine - INFO - Epoch(train) [37][220/660] lr: 1.0000e-03 eta: 1:36:12 time: 0.6257 data_time: 0.0353 memory: 42708 grad_norm: 4.8135 loss: 1.3127 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3127 2023/02/18 04:55:10 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:55:10 - mmengine - INFO - Epoch(train) [37][240/660] lr: 1.0000e-03 eta: 1:35:59 time: 0.6172 data_time: 0.0302 memory: 42708 grad_norm: 4.8371 loss: 1.4226 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.4226 2023/02/18 04:55:23 - mmengine - INFO - Epoch(train) [37][260/660] lr: 1.0000e-03 eta: 1:35:46 time: 0.6368 data_time: 0.0370 memory: 42708 grad_norm: 4.7677 loss: 1.2837 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2837 2023/02/18 04:55:36 - mmengine - INFO - Epoch(train) [37][280/660] lr: 1.0000e-03 eta: 1:35:33 time: 0.6226 data_time: 0.0316 memory: 42708 grad_norm: 4.7690 loss: 1.4206 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.4206 2023/02/18 04:55:48 - mmengine - INFO - Epoch(train) [37][300/660] lr: 1.0000e-03 eta: 1:35:21 time: 0.6267 data_time: 0.0335 memory: 42708 grad_norm: 4.7198 loss: 1.4525 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4525 2023/02/18 04:56:01 - mmengine - INFO - Epoch(train) [37][320/660] lr: 1.0000e-03 eta: 1:35:08 time: 0.6188 data_time: 0.0299 memory: 42708 grad_norm: 4.7962 loss: 1.3697 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3697 2023/02/18 04:56:13 - mmengine - INFO - Epoch(train) [37][340/660] lr: 1.0000e-03 eta: 1:34:55 time: 0.6248 data_time: 0.0348 memory: 42708 grad_norm: 4.9160 loss: 1.3514 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3514 2023/02/18 04:56:25 - mmengine - INFO - Epoch(train) [37][360/660] lr: 1.0000e-03 eta: 1:34:42 time: 0.6182 data_time: 0.0304 memory: 42708 grad_norm: 4.7954 loss: 1.3251 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3251 2023/02/18 04:56:38 - mmengine - INFO - Epoch(train) [37][380/660] lr: 1.0000e-03 eta: 1:34:29 time: 0.6255 data_time: 0.0367 memory: 42708 grad_norm: 4.6827 loss: 1.3170 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3170 2023/02/18 04:56:50 - mmengine - INFO - Epoch(train) [37][400/660] lr: 1.0000e-03 eta: 1:34:16 time: 0.6182 data_time: 0.0316 memory: 42708 grad_norm: 4.7517 loss: 1.4402 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4402 2023/02/18 04:57:03 - mmengine - INFO - Epoch(train) [37][420/660] lr: 1.0000e-03 eta: 1:34:03 time: 0.6305 data_time: 0.0404 memory: 42708 grad_norm: 4.7813 loss: 1.4082 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.4082 2023/02/18 04:57:15 - mmengine - INFO - Epoch(train) [37][440/660] lr: 1.0000e-03 eta: 1:33:50 time: 0.6181 data_time: 0.0299 memory: 42708 grad_norm: 4.8404 loss: 1.3570 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3570 2023/02/18 04:57:28 - mmengine - INFO - Epoch(train) [37][460/660] lr: 1.0000e-03 eta: 1:33:37 time: 0.6290 data_time: 0.0380 memory: 42708 grad_norm: 4.8316 loss: 1.3033 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.3033 2023/02/18 04:57:40 - mmengine - INFO - Epoch(train) [37][480/660] lr: 1.0000e-03 eta: 1:33:24 time: 0.6162 data_time: 0.0293 memory: 42708 grad_norm: 4.7326 loss: 1.2730 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.2730 2023/02/18 04:57:53 - mmengine - INFO - Epoch(train) [37][500/660] lr: 1.0000e-03 eta: 1:33:11 time: 0.6341 data_time: 0.0350 memory: 42708 grad_norm: 4.8054 loss: 1.3879 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.3879 2023/02/18 04:58:05 - mmengine - INFO - Epoch(train) [37][520/660] lr: 1.0000e-03 eta: 1:32:58 time: 0.6195 data_time: 0.0297 memory: 42708 grad_norm: 4.8158 loss: 1.3318 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3318 2023/02/18 04:58:18 - mmengine - INFO - Epoch(train) [37][540/660] lr: 1.0000e-03 eta: 1:32:46 time: 0.6316 data_time: 0.0392 memory: 42708 grad_norm: 4.8299 loss: 1.3278 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3278 2023/02/18 04:58:30 - mmengine - INFO - Epoch(train) [37][560/660] lr: 1.0000e-03 eta: 1:32:33 time: 0.6151 data_time: 0.0284 memory: 42708 grad_norm: 4.7474 loss: 1.3207 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.3207 2023/02/18 04:58:43 - mmengine - INFO - Epoch(train) [37][580/660] lr: 1.0000e-03 eta: 1:32:20 time: 0.6255 data_time: 0.0339 memory: 42708 grad_norm: 4.7606 loss: 1.4097 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.4097 2023/02/18 04:58:55 - mmengine - INFO - Epoch(train) [37][600/660] lr: 1.0000e-03 eta: 1:32:07 time: 0.6203 data_time: 0.0309 memory: 42708 grad_norm: 4.9038 loss: 1.3776 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3776 2023/02/18 04:59:08 - mmengine - INFO - Epoch(train) [37][620/660] lr: 1.0000e-03 eta: 1:31:54 time: 0.6257 data_time: 0.0350 memory: 42708 grad_norm: 4.8176 loss: 1.2895 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2895 2023/02/18 04:59:20 - mmengine - INFO - Epoch(train) [37][640/660] lr: 1.0000e-03 eta: 1:31:41 time: 0.6191 data_time: 0.0330 memory: 42708 grad_norm: 4.8146 loss: 1.3361 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3361 2023/02/18 04:59:32 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 04:59:32 - mmengine - INFO - Epoch(train) [37][660/660] lr: 1.0000e-03 eta: 1:31:28 time: 0.6138 data_time: 0.0291 memory: 42708 grad_norm: 4.9140 loss: 1.2856 top1_acc: 0.6296 top5_acc: 0.9630 loss_cls: 1.2856 2023/02/18 04:59:47 - mmengine - INFO - Epoch(train) [38][ 20/660] lr: 1.0000e-03 eta: 1:31:16 time: 0.7378 data_time: 0.1153 memory: 42708 grad_norm: 4.7267 loss: 1.2925 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.2925 2023/02/18 05:00:00 - mmengine - INFO - Epoch(train) [38][ 40/660] lr: 1.0000e-03 eta: 1:31:03 time: 0.6210 data_time: 0.0279 memory: 42708 grad_norm: 4.5578 loss: 1.2608 top1_acc: 0.7812 top5_acc: 0.8438 loss_cls: 1.2608 2023/02/18 05:00:12 - mmengine - INFO - Epoch(train) [38][ 60/660] lr: 1.0000e-03 eta: 1:30:50 time: 0.6281 data_time: 0.0274 memory: 42708 grad_norm: 4.7774 loss: 1.3559 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3559 2023/02/18 05:00:25 - mmengine - INFO - Epoch(train) [38][ 80/660] lr: 1.0000e-03 eta: 1:30:37 time: 0.6225 data_time: 0.0275 memory: 42708 grad_norm: 4.7981 loss: 1.3869 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3869 2023/02/18 05:00:37 - mmengine - INFO - Epoch(train) [38][100/660] lr: 1.0000e-03 eta: 1:30:24 time: 0.6321 data_time: 0.0270 memory: 42708 grad_norm: 4.8505 loss: 1.4398 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.4398 2023/02/18 05:00:50 - mmengine - INFO - Epoch(train) [38][120/660] lr: 1.0000e-03 eta: 1:30:11 time: 0.6212 data_time: 0.0288 memory: 42708 grad_norm: 4.7702 loss: 1.2716 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.2716 2023/02/18 05:01:02 - mmengine - INFO - Epoch(train) [38][140/660] lr: 1.0000e-03 eta: 1:29:59 time: 0.6287 data_time: 0.0271 memory: 42708 grad_norm: 4.8054 loss: 1.3174 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3174 2023/02/18 05:01:15 - mmengine - INFO - Epoch(train) [38][160/660] lr: 1.0000e-03 eta: 1:29:46 time: 0.6217 data_time: 0.0264 memory: 42708 grad_norm: 4.7258 loss: 1.3085 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3085 2023/02/18 05:01:27 - mmengine - INFO - Epoch(train) [38][180/660] lr: 1.0000e-03 eta: 1:29:33 time: 0.6289 data_time: 0.0277 memory: 42708 grad_norm: 4.7963 loss: 1.3456 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3456 2023/02/18 05:01:40 - mmengine - INFO - Epoch(train) [38][200/660] lr: 1.0000e-03 eta: 1:29:20 time: 0.6262 data_time: 0.0279 memory: 42708 grad_norm: 4.8944 loss: 1.3499 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3499 2023/02/18 05:01:52 - mmengine - INFO - Epoch(train) [38][220/660] lr: 1.0000e-03 eta: 1:29:07 time: 0.6328 data_time: 0.0290 memory: 42708 grad_norm: 4.9032 loss: 1.3814 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3814 2023/02/18 05:02:05 - mmengine - INFO - Epoch(train) [38][240/660] lr: 1.0000e-03 eta: 1:28:54 time: 0.6230 data_time: 0.0280 memory: 42708 grad_norm: 4.7700 loss: 1.3191 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.3191 2023/02/18 05:02:17 - mmengine - INFO - Epoch(train) [38][260/660] lr: 1.0000e-03 eta: 1:28:41 time: 0.6313 data_time: 0.0288 memory: 42708 grad_norm: 4.7403 loss: 1.2821 top1_acc: 0.5938 top5_acc: 1.0000 loss_cls: 1.2821 2023/02/18 05:02:30 - mmengine - INFO - Epoch(train) [38][280/660] lr: 1.0000e-03 eta: 1:28:28 time: 0.6267 data_time: 0.0277 memory: 42708 grad_norm: 4.7668 loss: 1.3085 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.3085 2023/02/18 05:02:43 - mmengine - INFO - Epoch(train) [38][300/660] lr: 1.0000e-03 eta: 1:28:15 time: 0.6258 data_time: 0.0281 memory: 42708 grad_norm: 4.8422 loss: 1.3061 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.3061 2023/02/18 05:02:55 - mmengine - INFO - Epoch(train) [38][320/660] lr: 1.0000e-03 eta: 1:28:03 time: 0.6172 data_time: 0.0268 memory: 42708 grad_norm: 4.8047 loss: 1.4631 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4631 2023/02/18 05:03:08 - mmengine - INFO - Epoch(train) [38][340/660] lr: 1.0000e-03 eta: 1:27:50 time: 0.6379 data_time: 0.0319 memory: 42708 grad_norm: 4.7711 loss: 1.3923 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3923 2023/02/18 05:03:20 - mmengine - INFO - Epoch(train) [38][360/660] lr: 1.0000e-03 eta: 1:27:37 time: 0.6232 data_time: 0.0291 memory: 42708 grad_norm: 4.7864 loss: 1.3485 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3485 2023/02/18 05:03:33 - mmengine - INFO - Epoch(train) [38][380/660] lr: 1.0000e-03 eta: 1:27:24 time: 0.6346 data_time: 0.0278 memory: 42708 grad_norm: 4.9874 loss: 1.4535 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.4535 2023/02/18 05:03:45 - mmengine - INFO - Epoch(train) [38][400/660] lr: 1.0000e-03 eta: 1:27:11 time: 0.6204 data_time: 0.0284 memory: 42708 grad_norm: 4.8059 loss: 1.3343 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3343 2023/02/18 05:03:58 - mmengine - INFO - Epoch(train) [38][420/660] lr: 1.0000e-03 eta: 1:26:58 time: 0.6303 data_time: 0.0278 memory: 42708 grad_norm: 4.7995 loss: 1.3224 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.3224 2023/02/18 05:04:10 - mmengine - INFO - Epoch(train) [38][440/660] lr: 1.0000e-03 eta: 1:26:45 time: 0.6235 data_time: 0.0295 memory: 42708 grad_norm: 4.8447 loss: 1.3582 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.3582 2023/02/18 05:04:23 - mmengine - INFO - Epoch(train) [38][460/660] lr: 1.0000e-03 eta: 1:26:33 time: 0.6329 data_time: 0.0280 memory: 42708 grad_norm: 4.8095 loss: 1.4240 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.4240 2023/02/18 05:04:35 - mmengine - INFO - Epoch(train) [38][480/660] lr: 1.0000e-03 eta: 1:26:20 time: 0.6241 data_time: 0.0294 memory: 42708 grad_norm: 4.8021 loss: 1.2730 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.2730 2023/02/18 05:04:48 - mmengine - INFO - Epoch(train) [38][500/660] lr: 1.0000e-03 eta: 1:26:07 time: 0.6310 data_time: 0.0282 memory: 42708 grad_norm: 4.9072 loss: 1.3470 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3470 2023/02/18 05:05:01 - mmengine - INFO - Epoch(train) [38][520/660] lr: 1.0000e-03 eta: 1:25:54 time: 0.6288 data_time: 0.0273 memory: 42708 grad_norm: 4.8063 loss: 1.4495 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4495 2023/02/18 05:05:13 - mmengine - INFO - Epoch(train) [38][540/660] lr: 1.0000e-03 eta: 1:25:41 time: 0.6332 data_time: 0.0287 memory: 42708 grad_norm: 4.8617 loss: 1.3173 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3173 2023/02/18 05:05:26 - mmengine - INFO - Epoch(train) [38][560/660] lr: 1.0000e-03 eta: 1:25:28 time: 0.6220 data_time: 0.0268 memory: 42708 grad_norm: 4.8448 loss: 1.2724 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.2724 2023/02/18 05:05:38 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:05:38 - mmengine - INFO - Epoch(train) [38][580/660] lr: 1.0000e-03 eta: 1:25:15 time: 0.6320 data_time: 0.0284 memory: 42708 grad_norm: 4.8719 loss: 1.3477 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3477 2023/02/18 05:05:51 - mmengine - INFO - Epoch(train) [38][600/660] lr: 1.0000e-03 eta: 1:25:02 time: 0.6221 data_time: 0.0278 memory: 42708 grad_norm: 4.7829 loss: 1.3358 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3358 2023/02/18 05:06:04 - mmengine - INFO - Epoch(train) [38][620/660] lr: 1.0000e-03 eta: 1:24:50 time: 0.6344 data_time: 0.0291 memory: 42708 grad_norm: 4.8119 loss: 1.2795 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.2795 2023/02/18 05:06:16 - mmengine - INFO - Epoch(train) [38][640/660] lr: 1.0000e-03 eta: 1:24:37 time: 0.6217 data_time: 0.0259 memory: 42708 grad_norm: 4.8745 loss: 1.3788 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3788 2023/02/18 05:06:28 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:06:28 - mmengine - INFO - Epoch(train) [38][660/660] lr: 1.0000e-03 eta: 1:24:24 time: 0.6227 data_time: 0.0259 memory: 42708 grad_norm: 4.7851 loss: 1.3730 top1_acc: 0.5556 top5_acc: 0.8519 loss_cls: 1.3730 2023/02/18 05:06:43 - mmengine - INFO - Epoch(train) [39][ 20/660] lr: 1.0000e-03 eta: 1:24:12 time: 0.7265 data_time: 0.1209 memory: 42708 grad_norm: 4.6640 loss: 1.3614 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3614 2023/02/18 05:06:56 - mmengine - INFO - Epoch(train) [39][ 40/660] lr: 1.0000e-03 eta: 1:23:59 time: 0.6350 data_time: 0.0345 memory: 42708 grad_norm: 4.8408 loss: 1.4004 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4004 2023/02/18 05:07:09 - mmengine - INFO - Epoch(train) [39][ 60/660] lr: 1.0000e-03 eta: 1:23:46 time: 0.6461 data_time: 0.0358 memory: 42708 grad_norm: 4.8161 loss: 1.2971 top1_acc: 0.8125 top5_acc: 0.9688 loss_cls: 1.2971 2023/02/18 05:07:21 - mmengine - INFO - Epoch(train) [39][ 80/660] lr: 1.0000e-03 eta: 1:23:33 time: 0.6353 data_time: 0.0290 memory: 42708 grad_norm: 4.7542 loss: 1.3662 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3662 2023/02/18 05:07:34 - mmengine - INFO - Epoch(train) [39][100/660] lr: 1.0000e-03 eta: 1:23:20 time: 0.6438 data_time: 0.0335 memory: 42708 grad_norm: 4.9321 loss: 1.3390 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3390 2023/02/18 05:07:47 - mmengine - INFO - Epoch(train) [39][120/660] lr: 1.0000e-03 eta: 1:23:08 time: 0.6316 data_time: 0.0283 memory: 42708 grad_norm: 4.7663 loss: 1.3139 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3139 2023/02/18 05:08:00 - mmengine - INFO - Epoch(train) [39][140/660] lr: 1.0000e-03 eta: 1:22:55 time: 0.6427 data_time: 0.0334 memory: 42708 grad_norm: 4.6145 loss: 1.3874 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3874 2023/02/18 05:08:12 - mmengine - INFO - Epoch(train) [39][160/660] lr: 1.0000e-03 eta: 1:22:42 time: 0.6347 data_time: 0.0283 memory: 42708 grad_norm: 4.7829 loss: 1.2476 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.2476 2023/02/18 05:08:25 - mmengine - INFO - Epoch(train) [39][180/660] lr: 1.0000e-03 eta: 1:22:29 time: 0.6438 data_time: 0.0355 memory: 42708 grad_norm: 4.8087 loss: 1.2822 top1_acc: 0.6562 top5_acc: 0.9688 loss_cls: 1.2822 2023/02/18 05:08:38 - mmengine - INFO - Epoch(train) [39][200/660] lr: 1.0000e-03 eta: 1:22:16 time: 0.6401 data_time: 0.0291 memory: 42708 grad_norm: 4.8705 loss: 1.3604 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3604 2023/02/18 05:08:51 - mmengine - INFO - Epoch(train) [39][220/660] lr: 1.0000e-03 eta: 1:22:04 time: 0.6483 data_time: 0.0352 memory: 42708 grad_norm: 4.7732 loss: 1.3786 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3786 2023/02/18 05:09:04 - mmengine - INFO - Epoch(train) [39][240/660] lr: 1.0000e-03 eta: 1:21:51 time: 0.6408 data_time: 0.0343 memory: 42708 grad_norm: 4.7972 loss: 1.3059 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3059 2023/02/18 05:09:17 - mmengine - INFO - Epoch(train) [39][260/660] lr: 1.0000e-03 eta: 1:21:38 time: 0.6464 data_time: 0.0346 memory: 42708 grad_norm: 4.8032 loss: 1.2482 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.2482 2023/02/18 05:09:30 - mmengine - INFO - Epoch(train) [39][280/660] lr: 1.0000e-03 eta: 1:21:25 time: 0.6368 data_time: 0.0310 memory: 42708 grad_norm: 5.0028 loss: 1.3788 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3788 2023/02/18 05:09:42 - mmengine - INFO - Epoch(train) [39][300/660] lr: 1.0000e-03 eta: 1:21:13 time: 0.6478 data_time: 0.0353 memory: 42708 grad_norm: 4.8575 loss: 1.3140 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3140 2023/02/18 05:09:55 - mmengine - INFO - Epoch(train) [39][320/660] lr: 1.0000e-03 eta: 1:21:00 time: 0.6429 data_time: 0.0297 memory: 42708 grad_norm: 4.7673 loss: 1.3307 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3307 2023/02/18 05:10:08 - mmengine - INFO - Epoch(train) [39][340/660] lr: 1.0000e-03 eta: 1:20:47 time: 0.6488 data_time: 0.0346 memory: 42708 grad_norm: 4.8295 loss: 1.3016 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3016 2023/02/18 05:10:21 - mmengine - INFO - Epoch(train) [39][360/660] lr: 1.0000e-03 eta: 1:20:34 time: 0.6369 data_time: 0.0328 memory: 42708 grad_norm: 4.9801 loss: 1.3858 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3858 2023/02/18 05:10:34 - mmengine - INFO - Epoch(train) [39][380/660] lr: 1.0000e-03 eta: 1:20:22 time: 0.6475 data_time: 0.0370 memory: 42708 grad_norm: 4.8865 loss: 1.4242 top1_acc: 0.5312 top5_acc: 0.6875 loss_cls: 1.4242 2023/02/18 05:10:47 - mmengine - INFO - Epoch(train) [39][400/660] lr: 1.0000e-03 eta: 1:20:09 time: 0.6372 data_time: 0.0316 memory: 42708 grad_norm: 4.9039 loss: 1.4151 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.4151 2023/02/18 05:11:00 - mmengine - INFO - Epoch(train) [39][420/660] lr: 1.0000e-03 eta: 1:19:56 time: 0.6473 data_time: 0.0342 memory: 42708 grad_norm: 4.8505 loss: 1.3324 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.3324 2023/02/18 05:11:12 - mmengine - INFO - Epoch(train) [39][440/660] lr: 1.0000e-03 eta: 1:19:43 time: 0.6407 data_time: 0.0299 memory: 42708 grad_norm: 4.8453 loss: 1.3194 top1_acc: 0.7188 top5_acc: 0.9688 loss_cls: 1.3194 2023/02/18 05:11:26 - mmengine - INFO - Epoch(train) [39][460/660] lr: 1.0000e-03 eta: 1:19:31 time: 0.6508 data_time: 0.0383 memory: 42708 grad_norm: 4.9089 loss: 1.2335 top1_acc: 0.8438 top5_acc: 1.0000 loss_cls: 1.2335 2023/02/18 05:11:38 - mmengine - INFO - Epoch(train) [39][480/660] lr: 1.0000e-03 eta: 1:19:18 time: 0.6354 data_time: 0.0317 memory: 42708 grad_norm: 4.8187 loss: 1.3913 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.3913 2023/02/18 05:11:51 - mmengine - INFO - Epoch(train) [39][500/660] lr: 1.0000e-03 eta: 1:19:05 time: 0.6457 data_time: 0.0368 memory: 42708 grad_norm: 4.8679 loss: 1.3595 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.3595 2023/02/18 05:12:04 - mmengine - INFO - Epoch(train) [39][520/660] lr: 1.0000e-03 eta: 1:18:52 time: 0.6473 data_time: 0.0317 memory: 42708 grad_norm: 4.8872 loss: 1.2759 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.2759 2023/02/18 05:12:17 - mmengine - INFO - Epoch(train) [39][540/660] lr: 1.0000e-03 eta: 1:18:39 time: 0.6517 data_time: 0.0363 memory: 42708 grad_norm: 4.8511 loss: 1.2922 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2922 2023/02/18 05:12:30 - mmengine - INFO - Epoch(train) [39][560/660] lr: 1.0000e-03 eta: 1:18:27 time: 0.6384 data_time: 0.0320 memory: 42708 grad_norm: 4.8554 loss: 1.2577 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.2577 2023/02/18 05:12:43 - mmengine - INFO - Epoch(train) [39][580/660] lr: 1.0000e-03 eta: 1:18:14 time: 0.6448 data_time: 0.0358 memory: 42708 grad_norm: 4.8013 loss: 1.2792 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.2792 2023/02/18 05:12:56 - mmengine - INFO - Epoch(train) [39][600/660] lr: 1.0000e-03 eta: 1:18:01 time: 0.6356 data_time: 0.0297 memory: 42708 grad_norm: 4.8527 loss: 1.3167 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3167 2023/02/18 05:13:09 - mmengine - INFO - Epoch(train) [39][620/660] lr: 1.0000e-03 eta: 1:17:48 time: 0.6545 data_time: 0.0394 memory: 42708 grad_norm: 4.7984 loss: 1.3172 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3172 2023/02/18 05:13:21 - mmengine - INFO - Epoch(train) [39][640/660] lr: 1.0000e-03 eta: 1:17:36 time: 0.6390 data_time: 0.0314 memory: 42708 grad_norm: 4.8101 loss: 1.4211 top1_acc: 0.6562 top5_acc: 0.7812 loss_cls: 1.4211 2023/02/18 05:13:34 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:13:34 - mmengine - INFO - Epoch(train) [39][660/660] lr: 1.0000e-03 eta: 1:17:23 time: 0.6254 data_time: 0.0282 memory: 42708 grad_norm: 4.8660 loss: 1.3154 top1_acc: 0.8519 top5_acc: 0.9259 loss_cls: 1.3154 2023/02/18 05:13:34 - mmengine - INFO - Saving checkpoint at 39 epochs 2023/02/18 05:13:50 - mmengine - INFO - Epoch(train) [40][ 20/660] lr: 1.0000e-03 eta: 1:17:10 time: 0.7186 data_time: 0.1186 memory: 42708 grad_norm: 4.8364 loss: 1.2310 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2310 2023/02/18 05:14:02 - mmengine - INFO - Epoch(train) [40][ 40/660] lr: 1.0000e-03 eta: 1:16:58 time: 0.6258 data_time: 0.0287 memory: 42708 grad_norm: 4.8335 loss: 1.3617 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3617 2023/02/18 05:14:15 - mmengine - INFO - Epoch(train) [40][ 60/660] lr: 1.0000e-03 eta: 1:16:45 time: 0.6382 data_time: 0.0313 memory: 42708 grad_norm: 4.9283 loss: 1.1987 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.1987 2023/02/18 05:14:27 - mmengine - INFO - Epoch(train) [40][ 80/660] lr: 1.0000e-03 eta: 1:16:32 time: 0.6292 data_time: 0.0274 memory: 42708 grad_norm: 4.8770 loss: 1.3829 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3829 2023/02/18 05:14:40 - mmengine - INFO - Epoch(train) [40][100/660] lr: 1.0000e-03 eta: 1:16:19 time: 0.6395 data_time: 0.0292 memory: 42708 grad_norm: 4.9935 loss: 1.4624 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.4624 2023/02/18 05:14:53 - mmengine - INFO - Epoch(train) [40][120/660] lr: 1.0000e-03 eta: 1:16:06 time: 0.6302 data_time: 0.0279 memory: 42708 grad_norm: 4.9197 loss: 1.2464 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2464 2023/02/18 05:15:06 - mmengine - INFO - Epoch(train) [40][140/660] lr: 1.0000e-03 eta: 1:15:53 time: 0.6386 data_time: 0.0286 memory: 42708 grad_norm: 4.8906 loss: 1.4804 top1_acc: 0.7812 top5_acc: 0.8438 loss_cls: 1.4804 2023/02/18 05:15:18 - mmengine - INFO - Epoch(train) [40][160/660] lr: 1.0000e-03 eta: 1:15:41 time: 0.6357 data_time: 0.0283 memory: 42708 grad_norm: 4.8584 loss: 1.2849 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.2849 2023/02/18 05:15:31 - mmengine - INFO - Epoch(train) [40][180/660] lr: 1.0000e-03 eta: 1:15:28 time: 0.6454 data_time: 0.0351 memory: 42708 grad_norm: 4.7755 loss: 1.3534 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3534 2023/02/18 05:15:44 - mmengine - INFO - Epoch(train) [40][200/660] lr: 1.0000e-03 eta: 1:15:15 time: 0.6321 data_time: 0.0283 memory: 42708 grad_norm: 4.8691 loss: 1.5117 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.5117 2023/02/18 05:15:57 - mmengine - INFO - Epoch(train) [40][220/660] lr: 1.0000e-03 eta: 1:15:02 time: 0.6438 data_time: 0.0292 memory: 42708 grad_norm: 4.9059 loss: 1.3095 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3095 2023/02/18 05:16:09 - mmengine - INFO - Epoch(train) [40][240/660] lr: 1.0000e-03 eta: 1:14:49 time: 0.6330 data_time: 0.0279 memory: 42708 grad_norm: 4.9054 loss: 1.3341 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3341 2023/02/18 05:16:22 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:16:22 - mmengine - INFO - Epoch(train) [40][260/660] lr: 1.0000e-03 eta: 1:14:37 time: 0.6369 data_time: 0.0283 memory: 42708 grad_norm: 4.9290 loss: 1.3221 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3221 2023/02/18 05:16:35 - mmengine - INFO - Epoch(train) [40][280/660] lr: 1.0000e-03 eta: 1:14:24 time: 0.6328 data_time: 0.0282 memory: 42708 grad_norm: 4.9139 loss: 1.4255 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4255 2023/02/18 05:16:48 - mmengine - INFO - Epoch(train) [40][300/660] lr: 1.0000e-03 eta: 1:14:11 time: 0.6392 data_time: 0.0297 memory: 42708 grad_norm: 4.8800 loss: 1.3149 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3149 2023/02/18 05:17:00 - mmengine - INFO - Epoch(train) [40][320/660] lr: 1.0000e-03 eta: 1:13:58 time: 0.6324 data_time: 0.0299 memory: 42708 grad_norm: 4.9307 loss: 1.2987 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.2987 2023/02/18 05:17:13 - mmengine - INFO - Epoch(train) [40][340/660] lr: 1.0000e-03 eta: 1:13:45 time: 0.6437 data_time: 0.0293 memory: 42708 grad_norm: 4.8052 loss: 1.3862 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3862 2023/02/18 05:17:26 - mmengine - INFO - Epoch(train) [40][360/660] lr: 1.0000e-03 eta: 1:13:33 time: 0.6359 data_time: 0.0282 memory: 42708 grad_norm: 4.8916 loss: 1.2487 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2487 2023/02/18 05:17:39 - mmengine - INFO - Epoch(train) [40][380/660] lr: 1.0000e-03 eta: 1:13:20 time: 0.6385 data_time: 0.0295 memory: 42708 grad_norm: 4.9795 loss: 1.2467 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.2467 2023/02/18 05:17:51 - mmengine - INFO - Epoch(train) [40][400/660] lr: 1.0000e-03 eta: 1:13:07 time: 0.6307 data_time: 0.0275 memory: 42708 grad_norm: 4.8140 loss: 1.2977 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.2977 2023/02/18 05:18:04 - mmengine - INFO - Epoch(train) [40][420/660] lr: 1.0000e-03 eta: 1:12:54 time: 0.6330 data_time: 0.0291 memory: 42708 grad_norm: 4.8792 loss: 1.3591 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3591 2023/02/18 05:18:17 - mmengine - INFO - Epoch(train) [40][440/660] lr: 1.0000e-03 eta: 1:12:41 time: 0.6346 data_time: 0.0287 memory: 42708 grad_norm: 4.9213 loss: 1.3476 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3476 2023/02/18 05:18:29 - mmengine - INFO - Epoch(train) [40][460/660] lr: 1.0000e-03 eta: 1:12:29 time: 0.6435 data_time: 0.0296 memory: 42708 grad_norm: 4.9087 loss: 1.4098 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.4098 2023/02/18 05:18:42 - mmengine - INFO - Epoch(train) [40][480/660] lr: 1.0000e-03 eta: 1:12:16 time: 0.6356 data_time: 0.0317 memory: 42708 grad_norm: 4.8988 loss: 1.3934 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3934 2023/02/18 05:18:55 - mmengine - INFO - Epoch(train) [40][500/660] lr: 1.0000e-03 eta: 1:12:03 time: 0.6394 data_time: 0.0306 memory: 42708 grad_norm: 4.9383 loss: 1.3968 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3968 2023/02/18 05:19:08 - mmengine - INFO - Epoch(train) [40][520/660] lr: 1.0000e-03 eta: 1:11:50 time: 0.6358 data_time: 0.0287 memory: 42708 grad_norm: 4.8846 loss: 1.3097 top1_acc: 0.7188 top5_acc: 0.8125 loss_cls: 1.3097 2023/02/18 05:19:20 - mmengine - INFO - Epoch(train) [40][540/660] lr: 1.0000e-03 eta: 1:11:37 time: 0.6402 data_time: 0.0307 memory: 42708 grad_norm: 4.9354 loss: 1.3333 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3333 2023/02/18 05:19:33 - mmengine - INFO - Epoch(train) [40][560/660] lr: 1.0000e-03 eta: 1:11:25 time: 0.6308 data_time: 0.0287 memory: 42708 grad_norm: 4.8092 loss: 1.2977 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2977 2023/02/18 05:19:46 - mmengine - INFO - Epoch(train) [40][580/660] lr: 1.0000e-03 eta: 1:11:12 time: 0.6396 data_time: 0.0297 memory: 42708 grad_norm: 4.8772 loss: 1.3562 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3562 2023/02/18 05:19:59 - mmengine - INFO - Epoch(train) [40][600/660] lr: 1.0000e-03 eta: 1:10:59 time: 0.6328 data_time: 0.0300 memory: 42708 grad_norm: 4.8698 loss: 1.3689 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.3689 2023/02/18 05:20:11 - mmengine - INFO - Epoch(train) [40][620/660] lr: 1.0000e-03 eta: 1:10:46 time: 0.6440 data_time: 0.0297 memory: 42708 grad_norm: 5.0221 loss: 1.4273 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.4273 2023/02/18 05:20:24 - mmengine - INFO - Epoch(train) [40][640/660] lr: 1.0000e-03 eta: 1:10:33 time: 0.6352 data_time: 0.0291 memory: 42708 grad_norm: 4.8931 loss: 1.2976 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2976 2023/02/18 05:20:36 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:20:36 - mmengine - INFO - Epoch(train) [40][660/660] lr: 1.0000e-03 eta: 1:10:20 time: 0.6194 data_time: 0.0261 memory: 42708 grad_norm: 4.8691 loss: 1.2586 top1_acc: 0.5556 top5_acc: 0.9259 loss_cls: 1.2586 2023/02/18 05:20:43 - mmengine - INFO - Epoch(val) [40][20/97] eta: 0:00:25 time: 0.3281 data_time: 0.1154 memory: 6154 2023/02/18 05:20:48 - mmengine - INFO - Epoch(val) [40][40/97] eta: 0:00:16 time: 0.2486 data_time: 0.0364 memory: 6154 2023/02/18 05:20:53 - mmengine - INFO - Epoch(val) [40][60/97] eta: 0:00:10 time: 0.2524 data_time: 0.0365 memory: 6154 2023/02/18 05:20:58 - mmengine - INFO - Epoch(val) [40][80/97] eta: 0:00:04 time: 0.2406 data_time: 0.0326 memory: 6154 2023/02/18 05:21:02 - mmengine - INFO - Epoch(val) [40][97/97] acc/top1: 0.3598 acc/top5: 0.6675 acc/mean1: 0.2969 2023/02/18 05:21:17 - mmengine - INFO - Epoch(train) [41][ 20/660] lr: 1.0000e-04 eta: 1:10:08 time: 0.7259 data_time: 0.1195 memory: 42708 grad_norm: 4.8863 loss: 1.2801 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.2801 2023/02/18 05:21:29 - mmengine - INFO - Epoch(train) [41][ 40/660] lr: 1.0000e-04 eta: 1:09:55 time: 0.6277 data_time: 0.0323 memory: 42708 grad_norm: 4.8098 loss: 1.3171 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3171 2023/02/18 05:21:42 - mmengine - INFO - Epoch(train) [41][ 60/660] lr: 1.0000e-04 eta: 1:09:42 time: 0.6354 data_time: 0.0354 memory: 42708 grad_norm: 4.9266 loss: 1.4383 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4383 2023/02/18 05:21:55 - mmengine - INFO - Epoch(train) [41][ 80/660] lr: 1.0000e-04 eta: 1:09:30 time: 0.6223 data_time: 0.0318 memory: 42708 grad_norm: 4.8239 loss: 1.3646 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3646 2023/02/18 05:22:07 - mmengine - INFO - Epoch(train) [41][100/660] lr: 1.0000e-04 eta: 1:09:17 time: 0.6361 data_time: 0.0346 memory: 42708 grad_norm: 4.9594 loss: 1.3544 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3544 2023/02/18 05:22:20 - mmengine - INFO - Epoch(train) [41][120/660] lr: 1.0000e-04 eta: 1:09:04 time: 0.6240 data_time: 0.0303 memory: 42708 grad_norm: 4.9084 loss: 1.3344 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.3344 2023/02/18 05:22:33 - mmengine - INFO - Epoch(train) [41][140/660] lr: 1.0000e-04 eta: 1:08:51 time: 0.6356 data_time: 0.0365 memory: 42708 grad_norm: 4.8422 loss: 1.2870 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.2870 2023/02/18 05:22:45 - mmengine - INFO - Epoch(train) [41][160/660] lr: 1.0000e-04 eta: 1:08:38 time: 0.6258 data_time: 0.0303 memory: 42708 grad_norm: 4.8444 loss: 1.2239 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2239 2023/02/18 05:22:58 - mmengine - INFO - Epoch(train) [41][180/660] lr: 1.0000e-04 eta: 1:08:25 time: 0.6361 data_time: 0.0371 memory: 42708 grad_norm: 4.8109 loss: 1.3398 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3398 2023/02/18 05:23:10 - mmengine - INFO - Epoch(train) [41][200/660] lr: 1.0000e-04 eta: 1:08:13 time: 0.6295 data_time: 0.0364 memory: 42708 grad_norm: 4.7300 loss: 1.3472 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.3472 2023/02/18 05:23:23 - mmengine - INFO - Epoch(train) [41][220/660] lr: 1.0000e-04 eta: 1:08:00 time: 0.6350 data_time: 0.0354 memory: 42708 grad_norm: 4.8081 loss: 1.3503 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3503 2023/02/18 05:23:36 - mmengine - INFO - Epoch(train) [41][240/660] lr: 1.0000e-04 eta: 1:07:47 time: 0.6223 data_time: 0.0314 memory: 42708 grad_norm: 4.7578 loss: 1.2283 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2283 2023/02/18 05:23:48 - mmengine - INFO - Epoch(train) [41][260/660] lr: 1.0000e-04 eta: 1:07:34 time: 0.6297 data_time: 0.0343 memory: 42708 grad_norm: 4.7819 loss: 1.1578 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.1578 2023/02/18 05:24:01 - mmengine - INFO - Epoch(train) [41][280/660] lr: 1.0000e-04 eta: 1:07:21 time: 0.6340 data_time: 0.0323 memory: 42708 grad_norm: 4.8391 loss: 1.3210 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3210 2023/02/18 05:24:14 - mmengine - INFO - Epoch(train) [41][300/660] lr: 1.0000e-04 eta: 1:07:08 time: 0.6416 data_time: 0.0352 memory: 42708 grad_norm: 4.9080 loss: 1.2349 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2349 2023/02/18 05:24:26 - mmengine - INFO - Epoch(train) [41][320/660] lr: 1.0000e-04 eta: 1:06:56 time: 0.6259 data_time: 0.0311 memory: 42708 grad_norm: 4.8782 loss: 1.2324 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.2324 2023/02/18 05:24:39 - mmengine - INFO - Epoch(train) [41][340/660] lr: 1.0000e-04 eta: 1:06:43 time: 0.6325 data_time: 0.0342 memory: 42708 grad_norm: 4.8477 loss: 1.3762 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3762 2023/02/18 05:24:51 - mmengine - INFO - Epoch(train) [41][360/660] lr: 1.0000e-04 eta: 1:06:30 time: 0.6250 data_time: 0.0300 memory: 42708 grad_norm: 4.8607 loss: 1.3202 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3202 2023/02/18 05:25:04 - mmengine - INFO - Epoch(train) [41][380/660] lr: 1.0000e-04 eta: 1:06:17 time: 0.6322 data_time: 0.0343 memory: 42708 grad_norm: 4.7892 loss: 1.2155 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2155 2023/02/18 05:25:17 - mmengine - INFO - Epoch(train) [41][400/660] lr: 1.0000e-04 eta: 1:06:04 time: 0.6265 data_time: 0.0316 memory: 42708 grad_norm: 4.7820 loss: 1.2845 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2845 2023/02/18 05:25:29 - mmengine - INFO - Epoch(train) [41][420/660] lr: 1.0000e-04 eta: 1:05:51 time: 0.6367 data_time: 0.0347 memory: 42708 grad_norm: 4.8850 loss: 1.3267 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3267 2023/02/18 05:25:42 - mmengine - INFO - Epoch(train) [41][440/660] lr: 1.0000e-04 eta: 1:05:39 time: 0.6270 data_time: 0.0322 memory: 42708 grad_norm: 4.7730 loss: 1.2627 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2627 2023/02/18 05:25:54 - mmengine - INFO - Epoch(train) [41][460/660] lr: 1.0000e-04 eta: 1:05:26 time: 0.6340 data_time: 0.0382 memory: 42708 grad_norm: 4.8627 loss: 1.1916 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.1916 2023/02/18 05:26:07 - mmengine - INFO - Epoch(train) [41][480/660] lr: 1.0000e-04 eta: 1:05:13 time: 0.6224 data_time: 0.0304 memory: 42708 grad_norm: 4.8439 loss: 1.1822 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.1822 2023/02/18 05:26:20 - mmengine - INFO - Epoch(train) [41][500/660] lr: 1.0000e-04 eta: 1:05:00 time: 0.6353 data_time: 0.0345 memory: 42708 grad_norm: 4.8821 loss: 1.2303 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.2303 2023/02/18 05:26:32 - mmengine - INFO - Epoch(train) [41][520/660] lr: 1.0000e-04 eta: 1:04:47 time: 0.6266 data_time: 0.0311 memory: 42708 grad_norm: 4.8856 loss: 1.2102 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.2102 2023/02/18 05:26:45 - mmengine - INFO - Epoch(train) [41][540/660] lr: 1.0000e-04 eta: 1:04:34 time: 0.6359 data_time: 0.0354 memory: 42708 grad_norm: 4.7472 loss: 1.4025 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.4025 2023/02/18 05:26:57 - mmengine - INFO - Epoch(train) [41][560/660] lr: 1.0000e-04 eta: 1:04:22 time: 0.6308 data_time: 0.0311 memory: 42708 grad_norm: 4.9391 loss: 1.2828 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2828 2023/02/18 05:27:10 - mmengine - INFO - Epoch(train) [41][580/660] lr: 1.0000e-04 eta: 1:04:09 time: 0.6427 data_time: 0.0350 memory: 42708 grad_norm: 4.8083 loss: 1.2900 top1_acc: 0.5000 top5_acc: 0.7812 loss_cls: 1.2900 2023/02/18 05:27:23 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:27:23 - mmengine - INFO - Epoch(train) [41][600/660] lr: 1.0000e-04 eta: 1:03:56 time: 0.6254 data_time: 0.0313 memory: 42708 grad_norm: 4.8360 loss: 1.1991 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1991 2023/02/18 05:27:36 - mmengine - INFO - Epoch(train) [41][620/660] lr: 1.0000e-04 eta: 1:03:43 time: 0.6339 data_time: 0.0350 memory: 42708 grad_norm: 5.0556 loss: 1.2144 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2144 2023/02/18 05:27:48 - mmengine - INFO - Epoch(train) [41][640/660] lr: 1.0000e-04 eta: 1:03:30 time: 0.6221 data_time: 0.0316 memory: 42708 grad_norm: 4.8835 loss: 1.2631 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2631 2023/02/18 05:28:00 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:28:00 - mmengine - INFO - Epoch(train) [41][660/660] lr: 1.0000e-04 eta: 1:03:17 time: 0.6188 data_time: 0.0304 memory: 42708 grad_norm: 4.8127 loss: 1.2336 top1_acc: 0.5556 top5_acc: 0.8519 loss_cls: 1.2336 2023/02/18 05:28:15 - mmengine - INFO - Epoch(train) [42][ 20/660] lr: 1.0000e-04 eta: 1:03:05 time: 0.7244 data_time: 0.1193 memory: 42708 grad_norm: 4.8019 loss: 1.1962 top1_acc: 0.7812 top5_acc: 1.0000 loss_cls: 1.1962 2023/02/18 05:28:27 - mmengine - INFO - Epoch(train) [42][ 40/660] lr: 1.0000e-04 eta: 1:02:52 time: 0.6188 data_time: 0.0357 memory: 42708 grad_norm: 4.7921 loss: 1.2927 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.2927 2023/02/18 05:28:40 - mmengine - INFO - Epoch(train) [42][ 60/660] lr: 1.0000e-04 eta: 1:02:39 time: 0.6305 data_time: 0.0333 memory: 42708 grad_norm: 4.8477 loss: 1.2805 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.2805 2023/02/18 05:28:52 - mmengine - INFO - Epoch(train) [42][ 80/660] lr: 1.0000e-04 eta: 1:02:26 time: 0.6179 data_time: 0.0281 memory: 42708 grad_norm: 4.8404 loss: 1.3356 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3356 2023/02/18 05:29:05 - mmengine - INFO - Epoch(train) [42][100/660] lr: 1.0000e-04 eta: 1:02:14 time: 0.6244 data_time: 0.0335 memory: 42708 grad_norm: 4.7634 loss: 1.1802 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.1802 2023/02/18 05:29:17 - mmengine - INFO - Epoch(train) [42][120/660] lr: 1.0000e-04 eta: 1:02:01 time: 0.6172 data_time: 0.0292 memory: 42708 grad_norm: 4.8958 loss: 1.3665 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3665 2023/02/18 05:29:30 - mmengine - INFO - Epoch(train) [42][140/660] lr: 1.0000e-04 eta: 1:01:48 time: 0.6274 data_time: 0.0343 memory: 42708 grad_norm: 4.8777 loss: 1.3002 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3002 2023/02/18 05:29:42 - mmengine - INFO - Epoch(train) [42][160/660] lr: 1.0000e-04 eta: 1:01:35 time: 0.6262 data_time: 0.0322 memory: 42708 grad_norm: 4.8668 loss: 1.3338 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3338 2023/02/18 05:29:55 - mmengine - INFO - Epoch(train) [42][180/660] lr: 1.0000e-04 eta: 1:01:22 time: 0.6330 data_time: 0.0361 memory: 42708 grad_norm: 4.7787 loss: 1.2458 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.2458 2023/02/18 05:30:07 - mmengine - INFO - Epoch(train) [42][200/660] lr: 1.0000e-04 eta: 1:01:09 time: 0.6325 data_time: 0.0306 memory: 42708 grad_norm: 4.7757 loss: 1.3143 top1_acc: 0.7500 top5_acc: 0.9688 loss_cls: 1.3143 2023/02/18 05:30:20 - mmengine - INFO - Epoch(train) [42][220/660] lr: 1.0000e-04 eta: 1:00:57 time: 0.6386 data_time: 0.0347 memory: 42708 grad_norm: 4.7849 loss: 1.2416 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2416 2023/02/18 05:30:33 - mmengine - INFO - Epoch(train) [42][240/660] lr: 1.0000e-04 eta: 1:00:44 time: 0.6283 data_time: 0.0317 memory: 42708 grad_norm: 4.8027 loss: 1.3767 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3767 2023/02/18 05:30:46 - mmengine - INFO - Epoch(train) [42][260/660] lr: 1.0000e-04 eta: 1:00:31 time: 0.6394 data_time: 0.0370 memory: 42708 grad_norm: 4.7717 loss: 1.2985 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.2985 2023/02/18 05:30:58 - mmengine - INFO - Epoch(train) [42][280/660] lr: 1.0000e-04 eta: 1:00:18 time: 0.6247 data_time: 0.0306 memory: 42708 grad_norm: 4.8137 loss: 1.3399 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.3399 2023/02/18 05:31:11 - mmengine - INFO - Epoch(train) [42][300/660] lr: 1.0000e-04 eta: 1:00:05 time: 0.6430 data_time: 0.0382 memory: 42708 grad_norm: 4.7224 loss: 1.3266 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3266 2023/02/18 05:31:23 - mmengine - INFO - Epoch(train) [42][320/660] lr: 1.0000e-04 eta: 0:59:52 time: 0.6265 data_time: 0.0313 memory: 42708 grad_norm: 4.7998 loss: 1.3434 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3434 2023/02/18 05:31:36 - mmengine - INFO - Epoch(train) [42][340/660] lr: 1.0000e-04 eta: 0:59:40 time: 0.6383 data_time: 0.0355 memory: 42708 grad_norm: 4.7575 loss: 1.2532 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.2532 2023/02/18 05:31:49 - mmengine - INFO - Epoch(train) [42][360/660] lr: 1.0000e-04 eta: 0:59:27 time: 0.6297 data_time: 0.0309 memory: 42708 grad_norm: 4.8117 loss: 1.3170 top1_acc: 0.4375 top5_acc: 0.7812 loss_cls: 1.3170 2023/02/18 05:32:02 - mmengine - INFO - Epoch(train) [42][380/660] lr: 1.0000e-04 eta: 0:59:14 time: 0.6456 data_time: 0.0342 memory: 42708 grad_norm: 4.8198 loss: 1.3499 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3499 2023/02/18 05:32:14 - mmengine - INFO - Epoch(train) [42][400/660] lr: 1.0000e-04 eta: 0:59:01 time: 0.6246 data_time: 0.0298 memory: 42708 grad_norm: 4.7838 loss: 1.2771 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2771 2023/02/18 05:32:27 - mmengine - INFO - Epoch(train) [42][420/660] lr: 1.0000e-04 eta: 0:58:48 time: 0.6427 data_time: 0.0349 memory: 42708 grad_norm: 4.7798 loss: 1.3032 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3032 2023/02/18 05:32:40 - mmengine - INFO - Epoch(train) [42][440/660] lr: 1.0000e-04 eta: 0:58:36 time: 0.6261 data_time: 0.0296 memory: 42708 grad_norm: 4.8249 loss: 1.2039 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.2039 2023/02/18 05:32:53 - mmengine - INFO - Epoch(train) [42][460/660] lr: 1.0000e-04 eta: 0:58:23 time: 0.6459 data_time: 0.0355 memory: 42708 grad_norm: 4.8615 loss: 1.2886 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2886 2023/02/18 05:33:05 - mmengine - INFO - Epoch(train) [42][480/660] lr: 1.0000e-04 eta: 0:58:10 time: 0.6311 data_time: 0.0301 memory: 42708 grad_norm: 4.8214 loss: 1.3917 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3917 2023/02/18 05:33:18 - mmengine - INFO - Epoch(train) [42][500/660] lr: 1.0000e-04 eta: 0:57:57 time: 0.6343 data_time: 0.0341 memory: 42708 grad_norm: 4.8362 loss: 1.2141 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.2141 2023/02/18 05:33:30 - mmengine - INFO - Epoch(train) [42][520/660] lr: 1.0000e-04 eta: 0:57:44 time: 0.6285 data_time: 0.0303 memory: 42708 grad_norm: 4.8804 loss: 1.2838 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2838 2023/02/18 05:33:43 - mmengine - INFO - Epoch(train) [42][540/660] lr: 1.0000e-04 eta: 0:57:32 time: 0.6395 data_time: 0.0340 memory: 42708 grad_norm: 4.7513 loss: 1.2844 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2844 2023/02/18 05:33:56 - mmengine - INFO - Epoch(train) [42][560/660] lr: 1.0000e-04 eta: 0:57:19 time: 0.6270 data_time: 0.0316 memory: 42708 grad_norm: 4.8651 loss: 1.3192 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3192 2023/02/18 05:34:09 - mmengine - INFO - Epoch(train) [42][580/660] lr: 1.0000e-04 eta: 0:57:06 time: 0.6396 data_time: 0.0384 memory: 42708 grad_norm: 4.8248 loss: 1.3189 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.3189 2023/02/18 05:34:21 - mmengine - INFO - Epoch(train) [42][600/660] lr: 1.0000e-04 eta: 0:56:53 time: 0.6236 data_time: 0.0278 memory: 42708 grad_norm: 4.8455 loss: 1.3442 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3442 2023/02/18 05:34:34 - mmengine - INFO - Epoch(train) [42][620/660] lr: 1.0000e-04 eta: 0:56:40 time: 0.6316 data_time: 0.0338 memory: 42708 grad_norm: 4.8775 loss: 1.3006 top1_acc: 0.5000 top5_acc: 0.9062 loss_cls: 1.3006 2023/02/18 05:34:46 - mmengine - INFO - Epoch(train) [42][640/660] lr: 1.0000e-04 eta: 0:56:28 time: 0.6250 data_time: 0.0318 memory: 42708 grad_norm: 4.6916 loss: 1.3598 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3598 2023/02/18 05:34:59 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:34:59 - mmengine - INFO - Epoch(train) [42][660/660] lr: 1.0000e-04 eta: 0:56:15 time: 0.6187 data_time: 0.0274 memory: 42708 grad_norm: 4.8831 loss: 1.2956 top1_acc: 0.4815 top5_acc: 0.7778 loss_cls: 1.2956 2023/02/18 05:34:59 - mmengine - INFO - Saving checkpoint at 42 epochs 2023/02/18 05:35:14 - mmengine - INFO - Epoch(train) [43][ 20/660] lr: 1.0000e-04 eta: 0:56:02 time: 0.7146 data_time: 0.1113 memory: 42708 grad_norm: 4.7216 loss: 1.2383 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.2383 2023/02/18 05:35:26 - mmengine - INFO - Epoch(train) [43][ 40/660] lr: 1.0000e-04 eta: 0:55:49 time: 0.6201 data_time: 0.0274 memory: 42708 grad_norm: 4.8291 loss: 1.2943 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.2943 2023/02/18 05:35:39 - mmengine - INFO - Epoch(train) [43][ 60/660] lr: 1.0000e-04 eta: 0:55:36 time: 0.6265 data_time: 0.0294 memory: 42708 grad_norm: 4.8895 loss: 1.3397 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3397 2023/02/18 05:35:51 - mmengine - INFO - Epoch(train) [43][ 80/660] lr: 1.0000e-04 eta: 0:55:24 time: 0.6210 data_time: 0.0265 memory: 42708 grad_norm: 4.7632 loss: 1.3177 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3177 2023/02/18 05:36:04 - mmengine - INFO - Epoch(train) [43][100/660] lr: 1.0000e-04 eta: 0:55:11 time: 0.6327 data_time: 0.0330 memory: 42708 grad_norm: 4.8772 loss: 1.2503 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2503 2023/02/18 05:36:16 - mmengine - INFO - Epoch(train) [43][120/660] lr: 1.0000e-04 eta: 0:54:58 time: 0.6172 data_time: 0.0267 memory: 42708 grad_norm: 4.8132 loss: 1.3398 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.3398 2023/02/18 05:36:29 - mmengine - INFO - Epoch(train) [43][140/660] lr: 1.0000e-04 eta: 0:54:45 time: 0.6278 data_time: 0.0280 memory: 42708 grad_norm: 4.7571 loss: 1.3145 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.3145 2023/02/18 05:36:41 - mmengine - INFO - Epoch(train) [43][160/660] lr: 1.0000e-04 eta: 0:54:32 time: 0.6227 data_time: 0.0261 memory: 42708 grad_norm: 4.7401 loss: 1.3662 top1_acc: 0.7500 top5_acc: 0.8438 loss_cls: 1.3662 2023/02/18 05:36:54 - mmengine - INFO - Epoch(train) [43][180/660] lr: 1.0000e-04 eta: 0:54:19 time: 0.6278 data_time: 0.0315 memory: 42708 grad_norm: 4.8108 loss: 1.1944 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.1944 2023/02/18 05:37:06 - mmengine - INFO - Epoch(train) [43][200/660] lr: 1.0000e-04 eta: 0:54:07 time: 0.6194 data_time: 0.0255 memory: 42708 grad_norm: 4.8131 loss: 1.2638 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2638 2023/02/18 05:37:19 - mmengine - INFO - Epoch(train) [43][220/660] lr: 1.0000e-04 eta: 0:53:54 time: 0.6385 data_time: 0.0277 memory: 42708 grad_norm: 4.9213 loss: 1.4176 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.4176 2023/02/18 05:37:32 - mmengine - INFO - Epoch(train) [43][240/660] lr: 1.0000e-04 eta: 0:53:41 time: 0.6257 data_time: 0.0264 memory: 42708 grad_norm: 4.7184 loss: 1.2614 top1_acc: 0.5000 top5_acc: 0.8438 loss_cls: 1.2614 2023/02/18 05:37:44 - mmengine - INFO - Epoch(train) [43][260/660] lr: 1.0000e-04 eta: 0:53:28 time: 0.6316 data_time: 0.0280 memory: 42708 grad_norm: 4.8108 loss: 1.3701 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3701 2023/02/18 05:37:57 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:37:57 - mmengine - INFO - Epoch(train) [43][280/660] lr: 1.0000e-04 eta: 0:53:15 time: 0.6206 data_time: 0.0257 memory: 42708 grad_norm: 4.8139 loss: 1.3752 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.3752 2023/02/18 05:38:09 - mmengine - INFO - Epoch(train) [43][300/660] lr: 1.0000e-04 eta: 0:53:03 time: 0.6325 data_time: 0.0277 memory: 42708 grad_norm: 4.8044 loss: 1.2604 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.2604 2023/02/18 05:38:22 - mmengine - INFO - Epoch(train) [43][320/660] lr: 1.0000e-04 eta: 0:52:50 time: 0.6207 data_time: 0.0265 memory: 42708 grad_norm: 4.7853 loss: 1.3126 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3126 2023/02/18 05:38:35 - mmengine - INFO - Epoch(train) [43][340/660] lr: 1.0000e-04 eta: 0:52:37 time: 0.6374 data_time: 0.0275 memory: 42708 grad_norm: 4.7875 loss: 1.2829 top1_acc: 0.7812 top5_acc: 0.8750 loss_cls: 1.2829 2023/02/18 05:38:47 - mmengine - INFO - Epoch(train) [43][360/660] lr: 1.0000e-04 eta: 0:52:24 time: 0.6240 data_time: 0.0307 memory: 42708 grad_norm: 4.9473 loss: 1.2755 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.2755 2023/02/18 05:39:00 - mmengine - INFO - Epoch(train) [43][380/660] lr: 1.0000e-04 eta: 0:52:11 time: 0.6330 data_time: 0.0277 memory: 42708 grad_norm: 4.7697 loss: 1.2556 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.2556 2023/02/18 05:39:12 - mmengine - INFO - Epoch(train) [43][400/660] lr: 1.0000e-04 eta: 0:51:58 time: 0.6189 data_time: 0.0261 memory: 42708 grad_norm: 4.7805 loss: 1.4078 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4078 2023/02/18 05:39:25 - mmengine - INFO - Epoch(train) [43][420/660] lr: 1.0000e-04 eta: 0:51:46 time: 0.6304 data_time: 0.0277 memory: 42708 grad_norm: 4.8142 loss: 1.2443 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2443 2023/02/18 05:39:37 - mmengine - INFO - Epoch(train) [43][440/660] lr: 1.0000e-04 eta: 0:51:33 time: 0.6330 data_time: 0.0263 memory: 42708 grad_norm: 4.7076 loss: 1.2315 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.2315 2023/02/18 05:39:50 - mmengine - INFO - Epoch(train) [43][460/660] lr: 1.0000e-04 eta: 0:51:20 time: 0.6295 data_time: 0.0279 memory: 42708 grad_norm: 4.8840 loss: 1.3142 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.3142 2023/02/18 05:40:02 - mmengine - INFO - Epoch(train) [43][480/660] lr: 1.0000e-04 eta: 0:51:07 time: 0.6197 data_time: 0.0255 memory: 42708 grad_norm: 4.8189 loss: 1.3101 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3101 2023/02/18 05:40:15 - mmengine - INFO - Epoch(train) [43][500/660] lr: 1.0000e-04 eta: 0:50:54 time: 0.6313 data_time: 0.0276 memory: 42708 grad_norm: 4.7835 loss: 1.3505 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3505 2023/02/18 05:40:27 - mmengine - INFO - Epoch(train) [43][520/660] lr: 1.0000e-04 eta: 0:50:41 time: 0.6193 data_time: 0.0253 memory: 42708 grad_norm: 4.7688 loss: 1.2835 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.2835 2023/02/18 05:40:40 - mmengine - INFO - Epoch(train) [43][540/660] lr: 1.0000e-04 eta: 0:50:29 time: 0.6311 data_time: 0.0275 memory: 42708 grad_norm: 4.8501 loss: 1.2543 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2543 2023/02/18 05:40:52 - mmengine - INFO - Epoch(train) [43][560/660] lr: 1.0000e-04 eta: 0:50:16 time: 0.6222 data_time: 0.0261 memory: 42708 grad_norm: 4.7892 loss: 1.2055 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2055 2023/02/18 05:41:05 - mmengine - INFO - Epoch(train) [43][580/660] lr: 1.0000e-04 eta: 0:50:03 time: 0.6315 data_time: 0.0273 memory: 42708 grad_norm: 4.8808 loss: 1.2788 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2788 2023/02/18 05:41:18 - mmengine - INFO - Epoch(train) [43][600/660] lr: 1.0000e-04 eta: 0:49:50 time: 0.6261 data_time: 0.0262 memory: 42708 grad_norm: 4.8203 loss: 1.3337 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.3337 2023/02/18 05:41:30 - mmengine - INFO - Epoch(train) [43][620/660] lr: 1.0000e-04 eta: 0:49:37 time: 0.6325 data_time: 0.0291 memory: 42708 grad_norm: 4.8172 loss: 1.2179 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.2179 2023/02/18 05:41:43 - mmengine - INFO - Epoch(train) [43][640/660] lr: 1.0000e-04 eta: 0:49:25 time: 0.6181 data_time: 0.0259 memory: 42708 grad_norm: 4.8295 loss: 1.2600 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.2600 2023/02/18 05:41:55 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:41:55 - mmengine - INFO - Epoch(train) [43][660/660] lr: 1.0000e-04 eta: 0:49:12 time: 0.6125 data_time: 0.0254 memory: 42708 grad_norm: 4.8062 loss: 1.2150 top1_acc: 0.5556 top5_acc: 0.9630 loss_cls: 1.2150 2023/02/18 05:42:09 - mmengine - INFO - Epoch(train) [44][ 20/660] lr: 1.0000e-04 eta: 0:48:59 time: 0.7251 data_time: 0.1187 memory: 42708 grad_norm: 4.7708 loss: 1.2233 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.2233 2023/02/18 05:42:22 - mmengine - INFO - Epoch(train) [44][ 40/660] lr: 1.0000e-04 eta: 0:48:46 time: 0.6243 data_time: 0.0318 memory: 42708 grad_norm: 4.8254 loss: 1.2985 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2985 2023/02/18 05:42:34 - mmengine - INFO - Epoch(train) [44][ 60/660] lr: 1.0000e-04 eta: 0:48:34 time: 0.6306 data_time: 0.0371 memory: 42708 grad_norm: 4.9047 loss: 1.3218 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3218 2023/02/18 05:42:47 - mmengine - INFO - Epoch(train) [44][ 80/660] lr: 1.0000e-04 eta: 0:48:21 time: 0.6186 data_time: 0.0321 memory: 42708 grad_norm: 4.9184 loss: 1.3345 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3345 2023/02/18 05:42:59 - mmengine - INFO - Epoch(train) [44][100/660] lr: 1.0000e-04 eta: 0:48:08 time: 0.6279 data_time: 0.0331 memory: 42708 grad_norm: 4.7961 loss: 1.1889 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.1889 2023/02/18 05:43:12 - mmengine - INFO - Epoch(train) [44][120/660] lr: 1.0000e-04 eta: 0:47:55 time: 0.6212 data_time: 0.0323 memory: 42708 grad_norm: 4.7841 loss: 1.2635 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2635 2023/02/18 05:43:24 - mmengine - INFO - Epoch(train) [44][140/660] lr: 1.0000e-04 eta: 0:47:42 time: 0.6284 data_time: 0.0368 memory: 42708 grad_norm: 4.7243 loss: 1.2508 top1_acc: 0.7812 top5_acc: 0.8750 loss_cls: 1.2508 2023/02/18 05:43:37 - mmengine - INFO - Epoch(train) [44][160/660] lr: 1.0000e-04 eta: 0:47:29 time: 0.6266 data_time: 0.0320 memory: 42708 grad_norm: 4.8553 loss: 1.1510 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.1510 2023/02/18 05:43:50 - mmengine - INFO - Epoch(train) [44][180/660] lr: 1.0000e-04 eta: 0:47:17 time: 0.6327 data_time: 0.0367 memory: 42708 grad_norm: 4.7031 loss: 1.1842 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.1842 2023/02/18 05:44:02 - mmengine - INFO - Epoch(train) [44][200/660] lr: 1.0000e-04 eta: 0:47:04 time: 0.6207 data_time: 0.0293 memory: 42708 grad_norm: 4.8626 loss: 1.3570 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.3570 2023/02/18 05:44:15 - mmengine - INFO - Epoch(train) [44][220/660] lr: 1.0000e-04 eta: 0:46:51 time: 0.6318 data_time: 0.0355 memory: 42708 grad_norm: 4.8792 loss: 1.3173 top1_acc: 0.4688 top5_acc: 0.7500 loss_cls: 1.3173 2023/02/18 05:44:27 - mmengine - INFO - Epoch(train) [44][240/660] lr: 1.0000e-04 eta: 0:46:38 time: 0.6221 data_time: 0.0297 memory: 42708 grad_norm: 4.6473 loss: 1.2107 top1_acc: 0.7188 top5_acc: 0.9688 loss_cls: 1.2107 2023/02/18 05:44:40 - mmengine - INFO - Epoch(train) [44][260/660] lr: 1.0000e-04 eta: 0:46:25 time: 0.6286 data_time: 0.0389 memory: 42708 grad_norm: 4.8486 loss: 1.3730 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.3730 2023/02/18 05:44:52 - mmengine - INFO - Epoch(train) [44][280/660] lr: 1.0000e-04 eta: 0:46:12 time: 0.6188 data_time: 0.0316 memory: 42708 grad_norm: 4.8509 loss: 1.2925 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.2925 2023/02/18 05:45:05 - mmengine - INFO - Epoch(train) [44][300/660] lr: 1.0000e-04 eta: 0:46:00 time: 0.6236 data_time: 0.0350 memory: 42708 grad_norm: 4.8057 loss: 1.3014 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.3014 2023/02/18 05:45:17 - mmengine - INFO - Epoch(train) [44][320/660] lr: 1.0000e-04 eta: 0:45:47 time: 0.6160 data_time: 0.0302 memory: 42708 grad_norm: 4.8478 loss: 1.3167 top1_acc: 0.5938 top5_acc: 0.9688 loss_cls: 1.3167 2023/02/18 05:45:29 - mmengine - INFO - Epoch(train) [44][340/660] lr: 1.0000e-04 eta: 0:45:34 time: 0.6306 data_time: 0.0358 memory: 42708 grad_norm: 4.7671 loss: 1.4097 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4097 2023/02/18 05:45:42 - mmengine - INFO - Epoch(train) [44][360/660] lr: 1.0000e-04 eta: 0:45:21 time: 0.6215 data_time: 0.0300 memory: 42708 grad_norm: 4.7297 loss: 1.2606 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.2606 2023/02/18 05:45:55 - mmengine - INFO - Epoch(train) [44][380/660] lr: 1.0000e-04 eta: 0:45:08 time: 0.6332 data_time: 0.0349 memory: 42708 grad_norm: 4.8200 loss: 1.3668 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.3668 2023/02/18 05:46:07 - mmengine - INFO - Epoch(train) [44][400/660] lr: 1.0000e-04 eta: 0:44:56 time: 0.6247 data_time: 0.0317 memory: 42708 grad_norm: 4.9096 loss: 1.1882 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1882 2023/02/18 05:46:20 - mmengine - INFO - Epoch(train) [44][420/660] lr: 1.0000e-04 eta: 0:44:43 time: 0.6261 data_time: 0.0338 memory: 42708 grad_norm: 4.7136 loss: 1.3100 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.3100 2023/02/18 05:46:32 - mmengine - INFO - Epoch(train) [44][440/660] lr: 1.0000e-04 eta: 0:44:30 time: 0.6210 data_time: 0.0326 memory: 42708 grad_norm: 4.7970 loss: 1.3055 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3055 2023/02/18 05:46:45 - mmengine - INFO - Epoch(train) [44][460/660] lr: 1.0000e-04 eta: 0:44:17 time: 0.6307 data_time: 0.0375 memory: 42708 grad_norm: 4.6963 loss: 1.2773 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.2773 2023/02/18 05:46:57 - mmengine - INFO - Epoch(train) [44][480/660] lr: 1.0000e-04 eta: 0:44:04 time: 0.6212 data_time: 0.0322 memory: 42708 grad_norm: 4.9050 loss: 1.3576 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3576 2023/02/18 05:47:10 - mmengine - INFO - Epoch(train) [44][500/660] lr: 1.0000e-04 eta: 0:43:51 time: 0.6308 data_time: 0.0351 memory: 42708 grad_norm: 4.8185 loss: 1.3420 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3420 2023/02/18 05:47:22 - mmengine - INFO - Epoch(train) [44][520/660] lr: 1.0000e-04 eta: 0:43:39 time: 0.6210 data_time: 0.0337 memory: 42708 grad_norm: 4.8419 loss: 1.1979 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.1979 2023/02/18 05:47:35 - mmengine - INFO - Epoch(train) [44][540/660] lr: 1.0000e-04 eta: 0:43:26 time: 0.6339 data_time: 0.0380 memory: 42708 grad_norm: 4.7843 loss: 1.2684 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.2684 2023/02/18 05:47:47 - mmengine - INFO - Epoch(train) [44][560/660] lr: 1.0000e-04 eta: 0:43:13 time: 0.6203 data_time: 0.0298 memory: 42708 grad_norm: 4.7662 loss: 1.1483 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.1483 2023/02/18 05:48:00 - mmengine - INFO - Epoch(train) [44][580/660] lr: 1.0000e-04 eta: 0:43:00 time: 0.6255 data_time: 0.0342 memory: 42708 grad_norm: 4.8360 loss: 1.3227 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3227 2023/02/18 05:48:12 - mmengine - INFO - Epoch(train) [44][600/660] lr: 1.0000e-04 eta: 0:42:47 time: 0.6218 data_time: 0.0295 memory: 42708 grad_norm: 4.8904 loss: 1.4038 top1_acc: 0.5938 top5_acc: 0.7500 loss_cls: 1.4038 2023/02/18 05:48:25 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:48:25 - mmengine - INFO - Epoch(train) [44][620/660] lr: 1.0000e-04 eta: 0:42:35 time: 0.6301 data_time: 0.0359 memory: 42708 grad_norm: 4.7894 loss: 1.2430 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.2430 2023/02/18 05:48:37 - mmengine - INFO - Epoch(train) [44][640/660] lr: 1.0000e-04 eta: 0:42:22 time: 0.6227 data_time: 0.0319 memory: 42708 grad_norm: 4.8939 loss: 1.3478 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3478 2023/02/18 05:48:49 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:48:49 - mmengine - INFO - Epoch(train) [44][660/660] lr: 1.0000e-04 eta: 0:42:09 time: 0.6152 data_time: 0.0285 memory: 42708 grad_norm: 4.8126 loss: 1.2032 top1_acc: 0.7407 top5_acc: 0.9630 loss_cls: 1.2032 2023/02/18 05:49:04 - mmengine - INFO - Epoch(train) [45][ 20/660] lr: 1.0000e-04 eta: 0:41:56 time: 0.7177 data_time: 0.1283 memory: 42708 grad_norm: 4.8507 loss: 1.2321 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.2321 2023/02/18 05:49:16 - mmengine - INFO - Epoch(train) [45][ 40/660] lr: 1.0000e-04 eta: 0:41:44 time: 0.6144 data_time: 0.0294 memory: 42708 grad_norm: 4.8238 loss: 1.4363 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.4363 2023/02/18 05:49:29 - mmengine - INFO - Epoch(train) [45][ 60/660] lr: 1.0000e-04 eta: 0:41:31 time: 0.6219 data_time: 0.0345 memory: 42708 grad_norm: 4.8206 loss: 1.3325 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.3325 2023/02/18 05:49:41 - mmengine - INFO - Epoch(train) [45][ 80/660] lr: 1.0000e-04 eta: 0:41:18 time: 0.6198 data_time: 0.0308 memory: 42708 grad_norm: 4.8564 loss: 1.2492 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.2492 2023/02/18 05:49:54 - mmengine - INFO - Epoch(train) [45][100/660] lr: 1.0000e-04 eta: 0:41:05 time: 0.6286 data_time: 0.0368 memory: 42708 grad_norm: 4.8466 loss: 1.2680 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.2680 2023/02/18 05:50:06 - mmengine - INFO - Epoch(train) [45][120/660] lr: 1.0000e-04 eta: 0:40:52 time: 0.6256 data_time: 0.0298 memory: 42708 grad_norm: 4.8812 loss: 1.3934 top1_acc: 0.8125 top5_acc: 0.9688 loss_cls: 1.3934 2023/02/18 05:50:19 - mmengine - INFO - Epoch(train) [45][140/660] lr: 1.0000e-04 eta: 0:40:39 time: 0.6298 data_time: 0.0339 memory: 42708 grad_norm: 4.8491 loss: 1.3466 top1_acc: 0.5312 top5_acc: 0.8438 loss_cls: 1.3466 2023/02/18 05:50:31 - mmengine - INFO - Epoch(train) [45][160/660] lr: 1.0000e-04 eta: 0:40:27 time: 0.6245 data_time: 0.0308 memory: 42708 grad_norm: 4.8527 loss: 1.2678 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.2678 2023/02/18 05:50:44 - mmengine - INFO - Epoch(train) [45][180/660] lr: 1.0000e-04 eta: 0:40:14 time: 0.6314 data_time: 0.0349 memory: 42708 grad_norm: 4.8925 loss: 1.3222 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3222 2023/02/18 05:50:56 - mmengine - INFO - Epoch(train) [45][200/660] lr: 1.0000e-04 eta: 0:40:01 time: 0.6259 data_time: 0.0320 memory: 42708 grad_norm: 4.8216 loss: 1.3060 top1_acc: 0.7500 top5_acc: 0.9688 loss_cls: 1.3060 2023/02/18 05:51:09 - mmengine - INFO - Epoch(train) [45][220/660] lr: 1.0000e-04 eta: 0:39:48 time: 0.6447 data_time: 0.0357 memory: 42708 grad_norm: 4.7971 loss: 1.1817 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.1817 2023/02/18 05:51:22 - mmengine - INFO - Epoch(train) [45][240/660] lr: 1.0000e-04 eta: 0:39:36 time: 0.6389 data_time: 0.0343 memory: 42708 grad_norm: 5.0826 loss: 1.3270 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3270 2023/02/18 05:51:35 - mmengine - INFO - Epoch(train) [45][260/660] lr: 1.0000e-04 eta: 0:39:23 time: 0.6374 data_time: 0.0351 memory: 42708 grad_norm: 4.8935 loss: 1.3404 top1_acc: 0.7188 top5_acc: 0.9688 loss_cls: 1.3404 2023/02/18 05:51:47 - mmengine - INFO - Epoch(train) [45][280/660] lr: 1.0000e-04 eta: 0:39:10 time: 0.6307 data_time: 0.0311 memory: 42708 grad_norm: 4.7916 loss: 1.3044 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3044 2023/02/18 05:52:00 - mmengine - INFO - Epoch(train) [45][300/660] lr: 1.0000e-04 eta: 0:38:57 time: 0.6377 data_time: 0.0392 memory: 42708 grad_norm: 4.7758 loss: 1.3419 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3419 2023/02/18 05:52:13 - mmengine - INFO - Epoch(train) [45][320/660] lr: 1.0000e-04 eta: 0:38:44 time: 0.6310 data_time: 0.0321 memory: 42708 grad_norm: 4.8077 loss: 1.3066 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3066 2023/02/18 05:52:26 - mmengine - INFO - Epoch(train) [45][340/660] lr: 1.0000e-04 eta: 0:38:32 time: 0.6405 data_time: 0.0332 memory: 42708 grad_norm: 4.9390 loss: 1.3503 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 1.3503 2023/02/18 05:52:38 - mmengine - INFO - Epoch(train) [45][360/660] lr: 1.0000e-04 eta: 0:38:19 time: 0.6346 data_time: 0.0314 memory: 42708 grad_norm: 4.7848 loss: 1.2954 top1_acc: 0.6250 top5_acc: 0.7812 loss_cls: 1.2954 2023/02/18 05:52:51 - mmengine - INFO - Epoch(train) [45][380/660] lr: 1.0000e-04 eta: 0:38:06 time: 0.6411 data_time: 0.0350 memory: 42708 grad_norm: 4.8726 loss: 1.3641 top1_acc: 0.5000 top5_acc: 0.6875 loss_cls: 1.3641 2023/02/18 05:53:04 - mmengine - INFO - Epoch(train) [45][400/660] lr: 1.0000e-04 eta: 0:37:53 time: 0.6331 data_time: 0.0299 memory: 42708 grad_norm: 4.7603 loss: 1.1994 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.1994 2023/02/18 05:53:17 - mmengine - INFO - Epoch(train) [45][420/660] lr: 1.0000e-04 eta: 0:37:41 time: 0.6478 data_time: 0.0355 memory: 42708 grad_norm: 4.9024 loss: 1.3554 top1_acc: 0.6875 top5_acc: 0.8438 loss_cls: 1.3554 2023/02/18 05:53:29 - mmengine - INFO - Epoch(train) [45][440/660] lr: 1.0000e-04 eta: 0:37:28 time: 0.6379 data_time: 0.0304 memory: 42708 grad_norm: 4.7514 loss: 1.2686 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.2686 2023/02/18 05:53:42 - mmengine - INFO - Epoch(train) [45][460/660] lr: 1.0000e-04 eta: 0:37:15 time: 0.6357 data_time: 0.0394 memory: 42708 grad_norm: 4.9280 loss: 1.3396 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.3396 2023/02/18 05:53:55 - mmengine - INFO - Epoch(train) [45][480/660] lr: 1.0000e-04 eta: 0:37:02 time: 0.6304 data_time: 0.0316 memory: 42708 grad_norm: 4.8452 loss: 1.3056 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3056 2023/02/18 05:54:08 - mmengine - INFO - Epoch(train) [45][500/660] lr: 1.0000e-04 eta: 0:36:49 time: 0.6400 data_time: 0.0358 memory: 42708 grad_norm: 4.7767 loss: 1.3167 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.3167 2023/02/18 05:54:20 - mmengine - INFO - Epoch(train) [45][520/660] lr: 1.0000e-04 eta: 0:36:37 time: 0.6313 data_time: 0.0328 memory: 42708 grad_norm: 4.7864 loss: 1.2471 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2471 2023/02/18 05:54:33 - mmengine - INFO - Epoch(train) [45][540/660] lr: 1.0000e-04 eta: 0:36:24 time: 0.6392 data_time: 0.0358 memory: 42708 grad_norm: 4.7373 loss: 1.2423 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2423 2023/02/18 05:54:46 - mmengine - INFO - Epoch(train) [45][560/660] lr: 1.0000e-04 eta: 0:36:11 time: 0.6280 data_time: 0.0306 memory: 42708 grad_norm: 4.7519 loss: 1.1986 top1_acc: 0.7188 top5_acc: 0.7812 loss_cls: 1.1986 2023/02/18 05:54:58 - mmengine - INFO - Epoch(train) [45][580/660] lr: 1.0000e-04 eta: 0:35:58 time: 0.6373 data_time: 0.0348 memory: 42708 grad_norm: 4.8796 loss: 1.3929 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3929 2023/02/18 05:55:11 - mmengine - INFO - Epoch(train) [45][600/660] lr: 1.0000e-04 eta: 0:35:45 time: 0.6294 data_time: 0.0324 memory: 42708 grad_norm: 4.9283 loss: 1.2890 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2890 2023/02/18 05:55:24 - mmengine - INFO - Epoch(train) [45][620/660] lr: 1.0000e-04 eta: 0:35:33 time: 0.6374 data_time: 0.0356 memory: 42708 grad_norm: 4.9478 loss: 1.2552 top1_acc: 0.7188 top5_acc: 0.7812 loss_cls: 1.2552 2023/02/18 05:55:36 - mmengine - INFO - Epoch(train) [45][640/660] lr: 1.0000e-04 eta: 0:35:20 time: 0.6329 data_time: 0.0332 memory: 42708 grad_norm: 4.7489 loss: 1.3096 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3096 2023/02/18 05:55:49 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:55:49 - mmengine - INFO - Epoch(train) [45][660/660] lr: 1.0000e-04 eta: 0:35:07 time: 0.6201 data_time: 0.0284 memory: 42708 grad_norm: 4.8445 loss: 1.2143 top1_acc: 0.7778 top5_acc: 0.9259 loss_cls: 1.2143 2023/02/18 05:55:49 - mmengine - INFO - Saving checkpoint at 45 epochs 2023/02/18 05:55:56 - mmengine - INFO - Epoch(val) [45][20/97] eta: 0:00:25 time: 0.3278 data_time: 0.1150 memory: 6154 2023/02/18 05:56:01 - mmengine - INFO - Epoch(val) [45][40/97] eta: 0:00:16 time: 0.2468 data_time: 0.0356 memory: 6154 2023/02/18 05:56:06 - mmengine - INFO - Epoch(val) [45][60/97] eta: 0:00:10 time: 0.2545 data_time: 0.0388 memory: 6154 2023/02/18 05:56:11 - mmengine - INFO - Epoch(val) [45][80/97] eta: 0:00:04 time: 0.2384 data_time: 0.0327 memory: 6154 2023/02/18 05:56:15 - mmengine - INFO - Epoch(val) [45][97/97] acc/top1: 0.3612 acc/top5: 0.6703 acc/mean1: 0.2970 2023/02/18 05:56:30 - mmengine - INFO - Epoch(train) [46][ 20/660] lr: 1.0000e-04 eta: 0:34:55 time: 0.7366 data_time: 0.1233 memory: 42708 grad_norm: 4.7704 loss: 1.3191 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3191 2023/02/18 05:56:43 - mmengine - INFO - Epoch(train) [46][ 40/660] lr: 1.0000e-04 eta: 0:34:42 time: 0.6252 data_time: 0.0307 memory: 42708 grad_norm: 4.9178 loss: 1.2564 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.2564 2023/02/18 05:56:56 - mmengine - INFO - Epoch(train) [46][ 60/660] lr: 1.0000e-04 eta: 0:34:29 time: 0.6442 data_time: 0.0324 memory: 42708 grad_norm: 4.8940 loss: 1.2866 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2866 2023/02/18 05:57:08 - mmengine - INFO - Epoch(train) [46][ 80/660] lr: 1.0000e-04 eta: 0:34:16 time: 0.6289 data_time: 0.0307 memory: 42708 grad_norm: 4.6394 loss: 1.2976 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.2976 2023/02/18 05:57:21 - mmengine - INFO - Epoch(train) [46][100/660] lr: 1.0000e-04 eta: 0:34:03 time: 0.6473 data_time: 0.0334 memory: 42708 grad_norm: 4.8622 loss: 1.3116 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3116 2023/02/18 05:57:34 - mmengine - INFO - Epoch(train) [46][120/660] lr: 1.0000e-04 eta: 0:33:51 time: 0.6279 data_time: 0.0295 memory: 42708 grad_norm: 4.8503 loss: 1.1977 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.1977 2023/02/18 05:57:47 - mmengine - INFO - Epoch(train) [46][140/660] lr: 1.0000e-04 eta: 0:33:38 time: 0.6475 data_time: 0.0346 memory: 42708 grad_norm: 4.9307 loss: 1.2224 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2224 2023/02/18 05:57:59 - mmengine - INFO - Epoch(train) [46][160/660] lr: 1.0000e-04 eta: 0:33:25 time: 0.6302 data_time: 0.0311 memory: 42708 grad_norm: 4.9280 loss: 1.2632 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.2632 2023/02/18 05:58:12 - mmengine - INFO - Epoch(train) [46][180/660] lr: 1.0000e-04 eta: 0:33:12 time: 0.6421 data_time: 0.0382 memory: 42708 grad_norm: 4.7435 loss: 1.3420 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3420 2023/02/18 05:58:25 - mmengine - INFO - Epoch(train) [46][200/660] lr: 1.0000e-04 eta: 0:33:00 time: 0.6322 data_time: 0.0311 memory: 42708 grad_norm: 4.8801 loss: 1.2689 top1_acc: 0.8125 top5_acc: 0.9062 loss_cls: 1.2689 2023/02/18 05:58:38 - mmengine - INFO - Epoch(train) [46][220/660] lr: 1.0000e-04 eta: 0:32:47 time: 0.6425 data_time: 0.0328 memory: 42708 grad_norm: 4.7976 loss: 1.2721 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.2721 2023/02/18 05:58:50 - mmengine - INFO - Epoch(train) [46][240/660] lr: 1.0000e-04 eta: 0:32:34 time: 0.6280 data_time: 0.0308 memory: 42708 grad_norm: 4.8919 loss: 1.2273 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.2273 2023/02/18 05:59:03 - mmengine - INFO - Epoch(train) [46][260/660] lr: 1.0000e-04 eta: 0:32:21 time: 0.6415 data_time: 0.0359 memory: 42708 grad_norm: 4.7618 loss: 1.1942 top1_acc: 0.7188 top5_acc: 1.0000 loss_cls: 1.1942 2023/02/18 05:59:16 - mmengine - INFO - Epoch(train) [46][280/660] lr: 1.0000e-04 eta: 0:32:08 time: 0.6282 data_time: 0.0317 memory: 42708 grad_norm: 4.8617 loss: 1.3390 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3390 2023/02/18 05:59:28 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 05:59:28 - mmengine - INFO - Epoch(train) [46][300/660] lr: 1.0000e-04 eta: 0:31:56 time: 0.6412 data_time: 0.0329 memory: 42708 grad_norm: 4.9328 loss: 1.2780 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.2780 2023/02/18 05:59:41 - mmengine - INFO - Epoch(train) [46][320/660] lr: 1.0000e-04 eta: 0:31:43 time: 0.6323 data_time: 0.0298 memory: 42708 grad_norm: 4.8484 loss: 1.3038 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3038 2023/02/18 05:59:54 - mmengine - INFO - Epoch(train) [46][340/660] lr: 1.0000e-04 eta: 0:31:30 time: 0.6409 data_time: 0.0320 memory: 42708 grad_norm: 4.8507 loss: 1.2921 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.2921 2023/02/18 06:00:07 - mmengine - INFO - Epoch(train) [46][360/660] lr: 1.0000e-04 eta: 0:31:17 time: 0.6363 data_time: 0.0303 memory: 42708 grad_norm: 4.9438 loss: 1.2623 top1_acc: 0.5625 top5_acc: 0.7812 loss_cls: 1.2623 2023/02/18 06:00:20 - mmengine - INFO - Epoch(train) [46][380/660] lr: 1.0000e-04 eta: 0:31:05 time: 0.6536 data_time: 0.0326 memory: 42708 grad_norm: 4.8525 loss: 1.3130 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.3130 2023/02/18 06:00:32 - mmengine - INFO - Epoch(train) [46][400/660] lr: 1.0000e-04 eta: 0:30:52 time: 0.6394 data_time: 0.0311 memory: 42708 grad_norm: 4.8905 loss: 1.2694 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.2694 2023/02/18 06:00:45 - mmengine - INFO - Epoch(train) [46][420/660] lr: 1.0000e-04 eta: 0:30:39 time: 0.6494 data_time: 0.0333 memory: 42708 grad_norm: 4.8124 loss: 1.2168 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2168 2023/02/18 06:00:58 - mmengine - INFO - Epoch(train) [46][440/660] lr: 1.0000e-04 eta: 0:30:26 time: 0.6360 data_time: 0.0330 memory: 42708 grad_norm: 4.9539 loss: 1.2290 top1_acc: 0.6250 top5_acc: 0.9688 loss_cls: 1.2290 2023/02/18 06:01:11 - mmengine - INFO - Epoch(train) [46][460/660] lr: 1.0000e-04 eta: 0:30:13 time: 0.6427 data_time: 0.0331 memory: 42708 grad_norm: 4.8566 loss: 1.4426 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.4426 2023/02/18 06:01:24 - mmengine - INFO - Epoch(train) [46][480/660] lr: 1.0000e-04 eta: 0:30:01 time: 0.6330 data_time: 0.0277 memory: 42708 grad_norm: 4.9917 loss: 1.3934 top1_acc: 0.4062 top5_acc: 0.7812 loss_cls: 1.3934 2023/02/18 06:01:37 - mmengine - INFO - Epoch(train) [46][500/660] lr: 1.0000e-04 eta: 0:29:48 time: 0.6466 data_time: 0.0314 memory: 42708 grad_norm: 4.7136 loss: 1.3727 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3727 2023/02/18 06:01:49 - mmengine - INFO - Epoch(train) [46][520/660] lr: 1.0000e-04 eta: 0:29:35 time: 0.6398 data_time: 0.0292 memory: 42708 grad_norm: 4.8081 loss: 1.2819 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2819 2023/02/18 06:02:02 - mmengine - INFO - Epoch(train) [46][540/660] lr: 1.0000e-04 eta: 0:29:22 time: 0.6504 data_time: 0.0314 memory: 42708 grad_norm: 4.8866 loss: 1.3383 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3383 2023/02/18 06:02:15 - mmengine - INFO - Epoch(train) [46][560/660] lr: 1.0000e-04 eta: 0:29:10 time: 0.6345 data_time: 0.0314 memory: 42708 grad_norm: 4.9469 loss: 1.2535 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.2535 2023/02/18 06:02:28 - mmengine - INFO - Epoch(train) [46][580/660] lr: 1.0000e-04 eta: 0:28:57 time: 0.6440 data_time: 0.0328 memory: 42708 grad_norm: 4.7694 loss: 1.1936 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1936 2023/02/18 06:02:41 - mmengine - INFO - Epoch(train) [46][600/660] lr: 1.0000e-04 eta: 0:28:44 time: 0.6399 data_time: 0.0310 memory: 42708 grad_norm: 4.8187 loss: 1.2998 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2998 2023/02/18 06:02:54 - mmengine - INFO - Epoch(train) [46][620/660] lr: 1.0000e-04 eta: 0:28:31 time: 0.6479 data_time: 0.0350 memory: 42708 grad_norm: 4.9041 loss: 1.2719 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.2719 2023/02/18 06:03:06 - mmengine - INFO - Epoch(train) [46][640/660] lr: 1.0000e-04 eta: 0:28:19 time: 0.6325 data_time: 0.0310 memory: 42708 grad_norm: 4.7992 loss: 1.2030 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.2030 2023/02/18 06:03:19 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:03:19 - mmengine - INFO - Epoch(train) [46][660/660] lr: 1.0000e-04 eta: 0:28:06 time: 0.6304 data_time: 0.0288 memory: 42708 grad_norm: 4.9583 loss: 1.2568 top1_acc: 0.6667 top5_acc: 0.9630 loss_cls: 1.2568 2023/02/18 06:03:34 - mmengine - INFO - Epoch(train) [47][ 20/660] lr: 1.0000e-04 eta: 0:27:53 time: 0.7287 data_time: 0.1176 memory: 42708 grad_norm: 4.7499 loss: 1.3514 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.3514 2023/02/18 06:03:46 - mmengine - INFO - Epoch(train) [47][ 40/660] lr: 1.0000e-04 eta: 0:27:40 time: 0.6216 data_time: 0.0285 memory: 42708 grad_norm: 4.8955 loss: 1.2641 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.2641 2023/02/18 06:03:59 - mmengine - INFO - Epoch(train) [47][ 60/660] lr: 1.0000e-04 eta: 0:27:28 time: 0.6378 data_time: 0.0334 memory: 42708 grad_norm: 4.8340 loss: 1.2870 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2870 2023/02/18 06:04:11 - mmengine - INFO - Epoch(train) [47][ 80/660] lr: 1.0000e-04 eta: 0:27:15 time: 0.6211 data_time: 0.0289 memory: 42708 grad_norm: 4.8740 loss: 1.3945 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.3945 2023/02/18 06:04:24 - mmengine - INFO - Epoch(train) [47][100/660] lr: 1.0000e-04 eta: 0:27:02 time: 0.6336 data_time: 0.0302 memory: 42708 grad_norm: 4.8193 loss: 1.2727 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2727 2023/02/18 06:04:37 - mmengine - INFO - Epoch(train) [47][120/660] lr: 1.0000e-04 eta: 0:26:49 time: 0.6280 data_time: 0.0287 memory: 42708 grad_norm: 4.8659 loss: 1.3960 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.3960 2023/02/18 06:04:49 - mmengine - INFO - Epoch(train) [47][140/660] lr: 1.0000e-04 eta: 0:26:36 time: 0.6355 data_time: 0.0317 memory: 42708 grad_norm: 4.7372 loss: 1.2280 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.2280 2023/02/18 06:05:02 - mmengine - INFO - Epoch(train) [47][160/660] lr: 1.0000e-04 eta: 0:26:24 time: 0.6207 data_time: 0.0286 memory: 42708 grad_norm: 4.9427 loss: 1.3058 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3058 2023/02/18 06:05:14 - mmengine - INFO - Epoch(train) [47][180/660] lr: 1.0000e-04 eta: 0:26:11 time: 0.6264 data_time: 0.0270 memory: 42708 grad_norm: 4.9879 loss: 1.4167 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 1.4167 2023/02/18 06:05:27 - mmengine - INFO - Epoch(train) [47][200/660] lr: 1.0000e-04 eta: 0:25:58 time: 0.6252 data_time: 0.0291 memory: 42708 grad_norm: 4.8086 loss: 1.3175 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.3175 2023/02/18 06:05:39 - mmengine - INFO - Epoch(train) [47][220/660] lr: 1.0000e-04 eta: 0:25:45 time: 0.6342 data_time: 0.0273 memory: 42708 grad_norm: 4.8802 loss: 1.1537 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1537 2023/02/18 06:05:52 - mmengine - INFO - Epoch(train) [47][240/660] lr: 1.0000e-04 eta: 0:25:32 time: 0.6167 data_time: 0.0267 memory: 42708 grad_norm: 4.8468 loss: 1.3072 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3072 2023/02/18 06:06:04 - mmengine - INFO - Epoch(train) [47][260/660] lr: 1.0000e-04 eta: 0:25:20 time: 0.6235 data_time: 0.0284 memory: 42708 grad_norm: 4.8919 loss: 1.3988 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3988 2023/02/18 06:06:17 - mmengine - INFO - Epoch(train) [47][280/660] lr: 1.0000e-04 eta: 0:25:07 time: 0.6174 data_time: 0.0282 memory: 42708 grad_norm: 4.8819 loss: 1.3636 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.3636 2023/02/18 06:06:29 - mmengine - INFO - Epoch(train) [47][300/660] lr: 1.0000e-04 eta: 0:24:54 time: 0.6264 data_time: 0.0283 memory: 42708 grad_norm: 4.8827 loss: 1.3613 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.3613 2023/02/18 06:06:42 - mmengine - INFO - Epoch(train) [47][320/660] lr: 1.0000e-04 eta: 0:24:41 time: 0.6255 data_time: 0.0310 memory: 42708 grad_norm: 4.7354 loss: 1.3472 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3472 2023/02/18 06:06:54 - mmengine - INFO - Epoch(train) [47][340/660] lr: 1.0000e-04 eta: 0:24:28 time: 0.6307 data_time: 0.0283 memory: 42708 grad_norm: 4.9052 loss: 1.2477 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.2477 2023/02/18 06:07:07 - mmengine - INFO - Epoch(train) [47][360/660] lr: 1.0000e-04 eta: 0:24:16 time: 0.6307 data_time: 0.0268 memory: 42708 grad_norm: 4.7461 loss: 1.1462 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.1462 2023/02/18 06:07:19 - mmengine - INFO - Epoch(train) [47][380/660] lr: 1.0000e-04 eta: 0:24:03 time: 0.6283 data_time: 0.0289 memory: 42708 grad_norm: 4.9417 loss: 1.3041 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3041 2023/02/18 06:07:32 - mmengine - INFO - Epoch(train) [47][400/660] lr: 1.0000e-04 eta: 0:23:50 time: 0.6128 data_time: 0.0280 memory: 42708 grad_norm: 4.8360 loss: 1.3218 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3218 2023/02/18 06:07:44 - mmengine - INFO - Epoch(train) [47][420/660] lr: 1.0000e-04 eta: 0:23:37 time: 0.6231 data_time: 0.0327 memory: 42708 grad_norm: 4.8081 loss: 1.4011 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4011 2023/02/18 06:07:56 - mmengine - INFO - Epoch(train) [47][440/660] lr: 1.0000e-04 eta: 0:23:24 time: 0.6165 data_time: 0.0301 memory: 42708 grad_norm: 4.6634 loss: 1.2541 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2541 2023/02/18 06:08:09 - mmengine - INFO - Epoch(train) [47][460/660] lr: 1.0000e-04 eta: 0:23:12 time: 0.6324 data_time: 0.0330 memory: 42708 grad_norm: 4.8438 loss: 1.2262 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2262 2023/02/18 06:08:22 - mmengine - INFO - Epoch(train) [47][480/660] lr: 1.0000e-04 eta: 0:22:59 time: 0.6210 data_time: 0.0299 memory: 42708 grad_norm: 4.8163 loss: 1.2608 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.2608 2023/02/18 06:08:34 - mmengine - INFO - Epoch(train) [47][500/660] lr: 1.0000e-04 eta: 0:22:46 time: 0.6227 data_time: 0.0341 memory: 42708 grad_norm: 4.8476 loss: 1.2813 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.2813 2023/02/18 06:08:46 - mmengine - INFO - Epoch(train) [47][520/660] lr: 1.0000e-04 eta: 0:22:33 time: 0.6155 data_time: 0.0300 memory: 42708 grad_norm: 4.8014 loss: 1.2071 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.2071 2023/02/18 06:08:59 - mmengine - INFO - Epoch(train) [47][540/660] lr: 1.0000e-04 eta: 0:22:20 time: 0.6281 data_time: 0.0338 memory: 42708 grad_norm: 4.8848 loss: 1.2941 top1_acc: 0.4688 top5_acc: 0.7188 loss_cls: 1.2941 2023/02/18 06:09:11 - mmengine - INFO - Epoch(train) [47][560/660] lr: 1.0000e-04 eta: 0:22:08 time: 0.6193 data_time: 0.0294 memory: 42708 grad_norm: 4.8300 loss: 1.3986 top1_acc: 0.5312 top5_acc: 0.7188 loss_cls: 1.3986 2023/02/18 06:09:24 - mmengine - INFO - Epoch(train) [47][580/660] lr: 1.0000e-04 eta: 0:21:55 time: 0.6271 data_time: 0.0363 memory: 42708 grad_norm: 4.9103 loss: 1.3836 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.3836 2023/02/18 06:09:36 - mmengine - INFO - Epoch(train) [47][600/660] lr: 1.0000e-04 eta: 0:21:42 time: 0.6226 data_time: 0.0301 memory: 42708 grad_norm: 4.9051 loss: 1.2173 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2173 2023/02/18 06:09:49 - mmengine - INFO - Epoch(train) [47][620/660] lr: 1.0000e-04 eta: 0:21:29 time: 0.6322 data_time: 0.0336 memory: 42708 grad_norm: 4.8349 loss: 1.3270 top1_acc: 0.5312 top5_acc: 0.9375 loss_cls: 1.3270 2023/02/18 06:10:01 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:10:01 - mmengine - INFO - Epoch(train) [47][640/660] lr: 1.0000e-04 eta: 0:21:17 time: 0.6171 data_time: 0.0301 memory: 42708 grad_norm: 4.9588 loss: 1.2868 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2868 2023/02/18 06:10:13 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:10:13 - mmengine - INFO - Epoch(train) [47][660/660] lr: 1.0000e-04 eta: 0:21:04 time: 0.6078 data_time: 0.0290 memory: 42708 grad_norm: 4.8418 loss: 1.3760 top1_acc: 0.5926 top5_acc: 0.7778 loss_cls: 1.3760 2023/02/18 06:10:28 - mmengine - INFO - Epoch(train) [48][ 20/660] lr: 1.0000e-04 eta: 0:20:51 time: 0.7254 data_time: 0.1189 memory: 42708 grad_norm: 4.8640 loss: 1.2904 top1_acc: 0.5625 top5_acc: 0.9688 loss_cls: 1.2904 2023/02/18 06:10:40 - mmengine - INFO - Epoch(train) [48][ 40/660] lr: 1.0000e-04 eta: 0:20:38 time: 0.6184 data_time: 0.0278 memory: 42708 grad_norm: 4.8496 loss: 1.2747 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2747 2023/02/18 06:10:53 - mmengine - INFO - Epoch(train) [48][ 60/660] lr: 1.0000e-04 eta: 0:20:25 time: 0.6302 data_time: 0.0283 memory: 42708 grad_norm: 4.9109 loss: 1.1851 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.1851 2023/02/18 06:11:05 - mmengine - INFO - Epoch(train) [48][ 80/660] lr: 1.0000e-04 eta: 0:20:13 time: 0.6217 data_time: 0.0270 memory: 42708 grad_norm: 4.8588 loss: 1.3805 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.3805 2023/02/18 06:11:18 - mmengine - INFO - Epoch(train) [48][100/660] lr: 1.0000e-04 eta: 0:20:00 time: 0.6376 data_time: 0.0298 memory: 42708 grad_norm: 4.9277 loss: 1.3607 top1_acc: 0.5312 top5_acc: 0.8750 loss_cls: 1.3607 2023/02/18 06:11:31 - mmengine - INFO - Epoch(train) [48][120/660] lr: 1.0000e-04 eta: 0:19:47 time: 0.6291 data_time: 0.0296 memory: 42708 grad_norm: 4.8190 loss: 1.4121 top1_acc: 0.5312 top5_acc: 0.7812 loss_cls: 1.4121 2023/02/18 06:11:44 - mmengine - INFO - Epoch(train) [48][140/660] lr: 1.0000e-04 eta: 0:19:34 time: 0.6485 data_time: 0.0329 memory: 42708 grad_norm: 4.8011 loss: 1.3507 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.3507 2023/02/18 06:11:57 - mmengine - INFO - Epoch(train) [48][160/660] lr: 1.0000e-04 eta: 0:19:22 time: 0.6416 data_time: 0.0328 memory: 42708 grad_norm: 4.8158 loss: 1.1674 top1_acc: 0.6875 top5_acc: 0.9062 loss_cls: 1.1674 2023/02/18 06:12:10 - mmengine - INFO - Epoch(train) [48][180/660] lr: 1.0000e-04 eta: 0:19:09 time: 0.6552 data_time: 0.0341 memory: 42708 grad_norm: 4.7817 loss: 1.2915 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.2915 2023/02/18 06:12:22 - mmengine - INFO - Epoch(train) [48][200/660] lr: 1.0000e-04 eta: 0:18:56 time: 0.6365 data_time: 0.0300 memory: 42708 grad_norm: 4.8726 loss: 1.3004 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3004 2023/02/18 06:12:35 - mmengine - INFO - Epoch(train) [48][220/660] lr: 1.0000e-04 eta: 0:18:43 time: 0.6544 data_time: 0.0341 memory: 42708 grad_norm: 4.9420 loss: 1.2016 top1_acc: 0.5312 top5_acc: 0.9062 loss_cls: 1.2016 2023/02/18 06:12:48 - mmengine - INFO - Epoch(train) [48][240/660] lr: 1.0000e-04 eta: 0:18:31 time: 0.6354 data_time: 0.0294 memory: 42708 grad_norm: 4.9417 loss: 1.2133 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.2133 2023/02/18 06:13:01 - mmengine - INFO - Epoch(train) [48][260/660] lr: 1.0000e-04 eta: 0:18:18 time: 0.6524 data_time: 0.0325 memory: 42708 grad_norm: 4.7613 loss: 1.1994 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.1994 2023/02/18 06:13:14 - mmengine - INFO - Epoch(train) [48][280/660] lr: 1.0000e-04 eta: 0:18:05 time: 0.6292 data_time: 0.0274 memory: 42708 grad_norm: 4.9745 loss: 1.3233 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3233 2023/02/18 06:13:27 - mmengine - INFO - Epoch(train) [48][300/660] lr: 1.0000e-04 eta: 0:17:52 time: 0.6466 data_time: 0.0328 memory: 42708 grad_norm: 4.9330 loss: 1.2841 top1_acc: 0.4062 top5_acc: 0.8438 loss_cls: 1.2841 2023/02/18 06:13:39 - mmengine - INFO - Epoch(train) [48][320/660] lr: 1.0000e-04 eta: 0:17:39 time: 0.6314 data_time: 0.0281 memory: 42708 grad_norm: 4.8134 loss: 1.2056 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.2056 2023/02/18 06:13:52 - mmengine - INFO - Epoch(train) [48][340/660] lr: 1.0000e-04 eta: 0:17:27 time: 0.6536 data_time: 0.0366 memory: 42708 grad_norm: 4.7971 loss: 1.2283 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.2283 2023/02/18 06:14:05 - mmengine - INFO - Epoch(train) [48][360/660] lr: 1.0000e-04 eta: 0:17:14 time: 0.6366 data_time: 0.0276 memory: 42708 grad_norm: 4.7150 loss: 1.2929 top1_acc: 0.7812 top5_acc: 0.9688 loss_cls: 1.2929 2023/02/18 06:14:18 - mmengine - INFO - Epoch(train) [48][380/660] lr: 1.0000e-04 eta: 0:17:01 time: 0.6494 data_time: 0.0327 memory: 42708 grad_norm: 4.8424 loss: 1.2140 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2140 2023/02/18 06:14:31 - mmengine - INFO - Epoch(train) [48][400/660] lr: 1.0000e-04 eta: 0:16:48 time: 0.6275 data_time: 0.0271 memory: 42708 grad_norm: 4.9130 loss: 1.3087 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.3087 2023/02/18 06:14:44 - mmengine - INFO - Epoch(train) [48][420/660] lr: 1.0000e-04 eta: 0:16:36 time: 0.6446 data_time: 0.0332 memory: 42708 grad_norm: 4.8382 loss: 1.2524 top1_acc: 0.6562 top5_acc: 0.8750 loss_cls: 1.2524 2023/02/18 06:14:56 - mmengine - INFO - Epoch(train) [48][440/660] lr: 1.0000e-04 eta: 0:16:23 time: 0.6324 data_time: 0.0276 memory: 42708 grad_norm: 4.8311 loss: 1.2232 top1_acc: 0.8438 top5_acc: 0.9688 loss_cls: 1.2232 2023/02/18 06:15:09 - mmengine - INFO - Epoch(train) [48][460/660] lr: 1.0000e-04 eta: 0:16:10 time: 0.6501 data_time: 0.0336 memory: 42708 grad_norm: 4.8887 loss: 1.2749 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2749 2023/02/18 06:15:22 - mmengine - INFO - Epoch(train) [48][480/660] lr: 1.0000e-04 eta: 0:15:57 time: 0.6298 data_time: 0.0275 memory: 42708 grad_norm: 4.6733 loss: 1.1868 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.1868 2023/02/18 06:15:35 - mmengine - INFO - Epoch(train) [48][500/660] lr: 1.0000e-04 eta: 0:15:45 time: 0.6518 data_time: 0.0333 memory: 42708 grad_norm: 4.8765 loss: 1.2980 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2980 2023/02/18 06:15:48 - mmengine - INFO - Epoch(train) [48][520/660] lr: 1.0000e-04 eta: 0:15:32 time: 0.6333 data_time: 0.0290 memory: 42708 grad_norm: 4.6703 loss: 1.2785 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 1.2785 2023/02/18 06:16:00 - mmengine - INFO - Epoch(train) [48][540/660] lr: 1.0000e-04 eta: 0:15:19 time: 0.6460 data_time: 0.0324 memory: 42708 grad_norm: 4.8301 loss: 1.3220 top1_acc: 0.5312 top5_acc: 0.8125 loss_cls: 1.3220 2023/02/18 06:16:13 - mmengine - INFO - Epoch(train) [48][560/660] lr: 1.0000e-04 eta: 0:15:06 time: 0.6304 data_time: 0.0281 memory: 42708 grad_norm: 4.8732 loss: 1.3439 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3439 2023/02/18 06:16:26 - mmengine - INFO - Epoch(train) [48][580/660] lr: 1.0000e-04 eta: 0:14:53 time: 0.6489 data_time: 0.0392 memory: 42708 grad_norm: 4.9523 loss: 1.1993 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.1993 2023/02/18 06:16:39 - mmengine - INFO - Epoch(train) [48][600/660] lr: 1.0000e-04 eta: 0:14:41 time: 0.6318 data_time: 0.0294 memory: 42708 grad_norm: 4.8675 loss: 1.2239 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.2239 2023/02/18 06:16:52 - mmengine - INFO - Epoch(train) [48][620/660] lr: 1.0000e-04 eta: 0:14:28 time: 0.6522 data_time: 0.0332 memory: 42708 grad_norm: 4.9050 loss: 1.2693 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2693 2023/02/18 06:17:18 - mmengine - INFO - Epoch(train) [48][640/660] lr: 1.0000e-04 eta: 0:14:16 time: 1.3162 data_time: 0.0298 memory: 42708 grad_norm: 4.8163 loss: 1.2255 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2255 2023/02/18 06:17:31 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:17:31 - mmengine - INFO - Epoch(train) [48][660/660] lr: 1.0000e-04 eta: 0:14:03 time: 0.6203 data_time: 0.0257 memory: 42708 grad_norm: 4.8582 loss: 1.3271 top1_acc: 0.5926 top5_acc: 0.8519 loss_cls: 1.3271 2023/02/18 06:17:31 - mmengine - INFO - Saving checkpoint at 48 epochs 2023/02/18 06:17:46 - mmengine - INFO - Epoch(train) [49][ 20/660] lr: 1.0000e-04 eta: 0:13:50 time: 0.7356 data_time: 0.1256 memory: 42708 grad_norm: 4.8519 loss: 1.4101 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.4101 2023/02/18 06:17:59 - mmengine - INFO - Epoch(train) [49][ 40/660] lr: 1.0000e-04 eta: 0:13:37 time: 0.6279 data_time: 0.0311 memory: 42708 grad_norm: 4.8237 loss: 1.3186 top1_acc: 0.6562 top5_acc: 0.8125 loss_cls: 1.3186 2023/02/18 06:18:12 - mmengine - INFO - Epoch(train) [49][ 60/660] lr: 1.0000e-04 eta: 0:13:25 time: 0.6416 data_time: 0.0367 memory: 42708 grad_norm: 4.9023 loss: 1.2445 top1_acc: 0.6562 top5_acc: 1.0000 loss_cls: 1.2445 2023/02/18 06:18:24 - mmengine - INFO - Epoch(train) [49][ 80/660] lr: 1.0000e-04 eta: 0:13:12 time: 0.6280 data_time: 0.0324 memory: 42708 grad_norm: 4.8961 loss: 1.2221 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2221 2023/02/18 06:18:37 - mmengine - INFO - Epoch(train) [49][100/660] lr: 1.0000e-04 eta: 0:12:59 time: 0.6507 data_time: 0.0346 memory: 42708 grad_norm: 4.8309 loss: 1.3030 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3030 2023/02/18 06:18:50 - mmengine - INFO - Epoch(train) [49][120/660] lr: 1.0000e-04 eta: 0:12:46 time: 0.6306 data_time: 0.0323 memory: 42708 grad_norm: 4.8196 loss: 1.3354 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.3354 2023/02/18 06:19:03 - mmengine - INFO - Epoch(train) [49][140/660] lr: 1.0000e-04 eta: 0:12:34 time: 0.6431 data_time: 0.0340 memory: 42708 grad_norm: 4.9153 loss: 1.2644 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.2644 2023/02/18 06:19:15 - mmengine - INFO - Epoch(train) [49][160/660] lr: 1.0000e-04 eta: 0:12:21 time: 0.6282 data_time: 0.0313 memory: 42708 grad_norm: 4.7465 loss: 1.2502 top1_acc: 0.5938 top5_acc: 1.0000 loss_cls: 1.2502 2023/02/18 06:19:28 - mmengine - INFO - Epoch(train) [49][180/660] lr: 1.0000e-04 eta: 0:12:08 time: 0.6347 data_time: 0.0335 memory: 42708 grad_norm: 4.8512 loss: 1.3096 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3096 2023/02/18 06:19:41 - mmengine - INFO - Epoch(train) [49][200/660] lr: 1.0000e-04 eta: 0:11:55 time: 0.6299 data_time: 0.0318 memory: 42708 grad_norm: 4.8384 loss: 1.2824 top1_acc: 0.7812 top5_acc: 0.9062 loss_cls: 1.2824 2023/02/18 06:19:54 - mmengine - INFO - Epoch(train) [49][220/660] lr: 1.0000e-04 eta: 0:11:42 time: 0.6533 data_time: 0.0393 memory: 42708 grad_norm: 4.9634 loss: 1.3497 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3497 2023/02/18 06:20:07 - mmengine - INFO - Epoch(train) [49][240/660] lr: 1.0000e-04 eta: 0:11:30 time: 0.6382 data_time: 0.0317 memory: 42708 grad_norm: 4.8109 loss: 1.3139 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.3139 2023/02/18 06:20:20 - mmengine - INFO - Epoch(train) [49][260/660] lr: 1.0000e-04 eta: 0:11:17 time: 0.6484 data_time: 0.0372 memory: 42708 grad_norm: 4.8204 loss: 1.2686 top1_acc: 0.5938 top5_acc: 0.9375 loss_cls: 1.2686 2023/02/18 06:20:32 - mmengine - INFO - Epoch(train) [49][280/660] lr: 1.0000e-04 eta: 0:11:04 time: 0.6376 data_time: 0.0309 memory: 42708 grad_norm: 4.8474 loss: 1.3176 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.3176 2023/02/18 06:20:45 - mmengine - INFO - Epoch(train) [49][300/660] lr: 1.0000e-04 eta: 0:10:51 time: 0.6461 data_time: 0.0392 memory: 42708 grad_norm: 4.7820 loss: 1.3140 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.3140 2023/02/18 06:20:58 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:20:58 - mmengine - INFO - Epoch(train) [49][320/660] lr: 1.0000e-04 eta: 0:10:39 time: 0.6371 data_time: 0.0316 memory: 42708 grad_norm: 4.8491 loss: 1.2679 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.2679 2023/02/18 06:21:11 - mmengine - INFO - Epoch(train) [49][340/660] lr: 1.0000e-04 eta: 0:10:26 time: 0.6454 data_time: 0.0363 memory: 42708 grad_norm: 4.8213 loss: 1.2780 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2780 2023/02/18 06:21:24 - mmengine - INFO - Epoch(train) [49][360/660] lr: 1.0000e-04 eta: 0:10:13 time: 0.6375 data_time: 0.0328 memory: 42708 grad_norm: 4.8478 loss: 1.3351 top1_acc: 0.5938 top5_acc: 0.8125 loss_cls: 1.3351 2023/02/18 06:21:37 - mmengine - INFO - Epoch(train) [49][380/660] lr: 1.0000e-04 eta: 0:10:00 time: 0.6447 data_time: 0.0365 memory: 42708 grad_norm: 5.0361 loss: 1.3160 top1_acc: 0.5312 top5_acc: 0.7500 loss_cls: 1.3160 2023/02/18 06:21:49 - mmengine - INFO - Epoch(train) [49][400/660] lr: 1.0000e-04 eta: 0:09:47 time: 0.6363 data_time: 0.0322 memory: 42708 grad_norm: 4.7659 loss: 1.2963 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.2963 2023/02/18 06:22:02 - mmengine - INFO - Epoch(train) [49][420/660] lr: 1.0000e-04 eta: 0:09:35 time: 0.6444 data_time: 0.0341 memory: 42708 grad_norm: 4.7037 loss: 1.3132 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.3132 2023/02/18 06:22:15 - mmengine - INFO - Epoch(train) [49][440/660] lr: 1.0000e-04 eta: 0:09:22 time: 0.6329 data_time: 0.0317 memory: 42708 grad_norm: 4.8265 loss: 1.2418 top1_acc: 0.7188 top5_acc: 0.9375 loss_cls: 1.2418 2023/02/18 06:22:28 - mmengine - INFO - Epoch(train) [49][460/660] lr: 1.0000e-04 eta: 0:09:09 time: 0.6414 data_time: 0.0380 memory: 42708 grad_norm: 4.7752 loss: 1.2848 top1_acc: 0.5000 top5_acc: 0.9688 loss_cls: 1.2848 2023/02/18 06:22:40 - mmengine - INFO - Epoch(train) [49][480/660] lr: 1.0000e-04 eta: 0:08:56 time: 0.6340 data_time: 0.0322 memory: 42708 grad_norm: 4.8052 loss: 1.1643 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.1643 2023/02/18 06:22:53 - mmengine - INFO - Epoch(train) [49][500/660] lr: 1.0000e-04 eta: 0:08:44 time: 0.6513 data_time: 0.0376 memory: 42708 grad_norm: 4.9922 loss: 1.2211 top1_acc: 0.7812 top5_acc: 0.9375 loss_cls: 1.2211 2023/02/18 06:23:06 - mmengine - INFO - Epoch(train) [49][520/660] lr: 1.0000e-04 eta: 0:08:31 time: 0.6339 data_time: 0.0305 memory: 42708 grad_norm: 4.8223 loss: 1.2375 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2375 2023/02/18 06:23:19 - mmengine - INFO - Epoch(train) [49][540/660] lr: 1.0000e-04 eta: 0:08:18 time: 0.6464 data_time: 0.0367 memory: 42708 grad_norm: 4.8893 loss: 1.3073 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.3073 2023/02/18 06:23:32 - mmengine - INFO - Epoch(train) [49][560/660] lr: 1.0000e-04 eta: 0:08:05 time: 0.6407 data_time: 0.0340 memory: 42708 grad_norm: 4.6922 loss: 1.2212 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2212 2023/02/18 06:23:45 - mmengine - INFO - Epoch(train) [49][580/660] lr: 1.0000e-04 eta: 0:07:52 time: 0.6475 data_time: 0.0362 memory: 42708 grad_norm: 4.9424 loss: 1.3186 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.3186 2023/02/18 06:23:57 - mmengine - INFO - Epoch(train) [49][600/660] lr: 1.0000e-04 eta: 0:07:40 time: 0.6376 data_time: 0.0308 memory: 42708 grad_norm: 4.7752 loss: 1.2961 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.2961 2023/02/18 06:24:10 - mmengine - INFO - Epoch(train) [49][620/660] lr: 1.0000e-04 eta: 0:07:27 time: 0.6464 data_time: 0.0366 memory: 42708 grad_norm: 4.7616 loss: 1.2587 top1_acc: 0.6562 top5_acc: 0.9688 loss_cls: 1.2587 2023/02/18 06:24:23 - mmengine - INFO - Epoch(train) [49][640/660] lr: 1.0000e-04 eta: 0:07:14 time: 0.6368 data_time: 0.0297 memory: 42708 grad_norm: 4.9475 loss: 1.2907 top1_acc: 0.6562 top5_acc: 0.9062 loss_cls: 1.2907 2023/02/18 06:24:36 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:24:36 - mmengine - INFO - Epoch(train) [49][660/660] lr: 1.0000e-04 eta: 0:07:01 time: 0.6210 data_time: 0.0308 memory: 42708 grad_norm: 4.8158 loss: 1.2705 top1_acc: 0.4444 top5_acc: 0.8148 loss_cls: 1.2705 2023/02/18 06:24:50 - mmengine - INFO - Epoch(train) [50][ 20/660] lr: 1.0000e-04 eta: 0:06:49 time: 0.7230 data_time: 0.1185 memory: 42708 grad_norm: 4.9130 loss: 1.3290 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.3290 2023/02/18 06:25:03 - mmengine - INFO - Epoch(train) [50][ 40/660] lr: 1.0000e-04 eta: 0:06:36 time: 0.6290 data_time: 0.0294 memory: 42708 grad_norm: 4.7192 loss: 1.2161 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.2161 2023/02/18 06:25:16 - mmengine - INFO - Epoch(train) [50][ 60/660] lr: 1.0000e-04 eta: 0:06:23 time: 0.6446 data_time: 0.0349 memory: 42708 grad_norm: 4.9128 loss: 1.3451 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3451 2023/02/18 06:25:28 - mmengine - INFO - Epoch(train) [50][ 80/660] lr: 1.0000e-04 eta: 0:06:10 time: 0.6274 data_time: 0.0287 memory: 42708 grad_norm: 4.8907 loss: 1.3143 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3143 2023/02/18 06:25:41 - mmengine - INFO - Epoch(train) [50][100/660] lr: 1.0000e-04 eta: 0:05:57 time: 0.6392 data_time: 0.0343 memory: 42708 grad_norm: 4.9049 loss: 1.3569 top1_acc: 0.6562 top5_acc: 0.9375 loss_cls: 1.3569 2023/02/18 06:25:54 - mmengine - INFO - Epoch(train) [50][120/660] lr: 1.0000e-04 eta: 0:05:45 time: 0.6391 data_time: 0.0385 memory: 42708 grad_norm: 4.7166 loss: 1.3331 top1_acc: 0.6562 top5_acc: 0.8438 loss_cls: 1.3331 2023/02/18 06:26:06 - mmengine - INFO - Epoch(train) [50][140/660] lr: 1.0000e-04 eta: 0:05:32 time: 0.6410 data_time: 0.0359 memory: 42708 grad_norm: 4.8440 loss: 1.3050 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3050 2023/02/18 06:26:19 - mmengine - INFO - Epoch(train) [50][160/660] lr: 1.0000e-04 eta: 0:05:19 time: 0.6307 data_time: 0.0316 memory: 42708 grad_norm: 4.9489 loss: 1.2785 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2785 2023/02/18 06:26:32 - mmengine - INFO - Epoch(train) [50][180/660] lr: 1.0000e-04 eta: 0:05:06 time: 0.6434 data_time: 0.0368 memory: 42708 grad_norm: 4.8951 loss: 1.2687 top1_acc: 0.7188 top5_acc: 0.9062 loss_cls: 1.2687 2023/02/18 06:26:45 - mmengine - INFO - Epoch(train) [50][200/660] lr: 1.0000e-04 eta: 0:04:53 time: 0.6309 data_time: 0.0284 memory: 42708 grad_norm: 4.8101 loss: 1.3064 top1_acc: 0.4688 top5_acc: 0.8750 loss_cls: 1.3064 2023/02/18 06:26:57 - mmengine - INFO - Epoch(train) [50][220/660] lr: 1.0000e-04 eta: 0:04:41 time: 0.6394 data_time: 0.0344 memory: 42708 grad_norm: 4.8411 loss: 1.2902 top1_acc: 0.5938 top5_acc: 0.7812 loss_cls: 1.2902 2023/02/18 06:27:10 - mmengine - INFO - Epoch(train) [50][240/660] lr: 1.0000e-04 eta: 0:04:28 time: 0.6283 data_time: 0.0286 memory: 42708 grad_norm: 4.8253 loss: 1.2330 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.2330 2023/02/18 06:27:23 - mmengine - INFO - Epoch(train) [50][260/660] lr: 1.0000e-04 eta: 0:04:15 time: 0.6351 data_time: 0.0357 memory: 42708 grad_norm: 4.7641 loss: 1.3044 top1_acc: 0.7500 top5_acc: 0.9062 loss_cls: 1.3044 2023/02/18 06:27:35 - mmengine - INFO - Epoch(train) [50][280/660] lr: 1.0000e-04 eta: 0:04:02 time: 0.6307 data_time: 0.0277 memory: 42708 grad_norm: 4.7728 loss: 1.2523 top1_acc: 0.8438 top5_acc: 1.0000 loss_cls: 1.2523 2023/02/18 06:27:48 - mmengine - INFO - Epoch(train) [50][300/660] lr: 1.0000e-04 eta: 0:03:50 time: 0.6396 data_time: 0.0362 memory: 42708 grad_norm: 4.8330 loss: 1.2339 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.2339 2023/02/18 06:28:01 - mmengine - INFO - Epoch(train) [50][320/660] lr: 1.0000e-04 eta: 0:03:37 time: 0.6242 data_time: 0.0286 memory: 42708 grad_norm: 4.8647 loss: 1.3275 top1_acc: 0.6250 top5_acc: 0.9062 loss_cls: 1.3275 2023/02/18 06:28:13 - mmengine - INFO - Epoch(train) [50][340/660] lr: 1.0000e-04 eta: 0:03:24 time: 0.6379 data_time: 0.0354 memory: 42708 grad_norm: 4.7299 loss: 1.2975 top1_acc: 0.6875 top5_acc: 0.9688 loss_cls: 1.2975 2023/02/18 06:28:26 - mmengine - INFO - Epoch(train) [50][360/660] lr: 1.0000e-04 eta: 0:03:11 time: 0.6272 data_time: 0.0277 memory: 42708 grad_norm: 4.8033 loss: 1.2789 top1_acc: 0.5000 top5_acc: 0.7188 loss_cls: 1.2789 2023/02/18 06:28:39 - mmengine - INFO - Epoch(train) [50][380/660] lr: 1.0000e-04 eta: 0:02:58 time: 0.6374 data_time: 0.0358 memory: 42708 grad_norm: 4.9722 loss: 1.2825 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.2825 2023/02/18 06:28:51 - mmengine - INFO - Epoch(train) [50][400/660] lr: 1.0000e-04 eta: 0:02:46 time: 0.6254 data_time: 0.0277 memory: 42708 grad_norm: 4.8760 loss: 1.2812 top1_acc: 0.5938 top5_acc: 0.8438 loss_cls: 1.2812 2023/02/18 06:29:04 - mmengine - INFO - Epoch(train) [50][420/660] lr: 1.0000e-04 eta: 0:02:33 time: 0.6428 data_time: 0.0388 memory: 42708 grad_norm: 4.8720 loss: 1.2323 top1_acc: 0.5625 top5_acc: 0.8438 loss_cls: 1.2323 2023/02/18 06:29:17 - mmengine - INFO - Epoch(train) [50][440/660] lr: 1.0000e-04 eta: 0:02:20 time: 0.6291 data_time: 0.0271 memory: 42708 grad_norm: 4.8005 loss: 1.2362 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2362 2023/02/18 06:29:29 - mmengine - INFO - Epoch(train) [50][460/660] lr: 1.0000e-04 eta: 0:02:07 time: 0.6366 data_time: 0.0355 memory: 42708 grad_norm: 4.9201 loss: 1.2575 top1_acc: 0.5625 top5_acc: 0.9062 loss_cls: 1.2575 2023/02/18 06:29:42 - mmengine - INFO - Epoch(train) [50][480/660] lr: 1.0000e-04 eta: 0:01:55 time: 0.6272 data_time: 0.0273 memory: 42708 grad_norm: 4.8158 loss: 1.2361 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2361 2023/02/18 06:29:55 - mmengine - INFO - Epoch(train) [50][500/660] lr: 1.0000e-04 eta: 0:01:42 time: 0.6362 data_time: 0.0344 memory: 42708 grad_norm: 4.9323 loss: 1.3205 top1_acc: 0.5938 top5_acc: 0.8750 loss_cls: 1.3205 2023/02/18 06:30:07 - mmengine - INFO - Epoch(train) [50][520/660] lr: 1.0000e-04 eta: 0:01:29 time: 0.6266 data_time: 0.0274 memory: 42708 grad_norm: 4.8443 loss: 1.3849 top1_acc: 0.4062 top5_acc: 0.8125 loss_cls: 1.3849 2023/02/18 06:30:20 - mmengine - INFO - Epoch(train) [50][540/660] lr: 1.0000e-04 eta: 0:01:16 time: 0.6399 data_time: 0.0330 memory: 42708 grad_norm: 4.8886 loss: 1.3521 top1_acc: 0.4688 top5_acc: 0.7812 loss_cls: 1.3521 2023/02/18 06:30:32 - mmengine - INFO - Epoch(train) [50][560/660] lr: 1.0000e-04 eta: 0:01:03 time: 0.6298 data_time: 0.0282 memory: 42708 grad_norm: 4.8637 loss: 1.2957 top1_acc: 0.7188 top5_acc: 0.8438 loss_cls: 1.2957 2023/02/18 06:30:45 - mmengine - INFO - Epoch(train) [50][580/660] lr: 1.0000e-04 eta: 0:00:51 time: 0.6421 data_time: 0.0338 memory: 42708 grad_norm: 4.8334 loss: 1.2445 top1_acc: 0.6250 top5_acc: 0.8438 loss_cls: 1.2445 2023/02/18 06:30:58 - mmengine - INFO - Epoch(train) [50][600/660] lr: 1.0000e-04 eta: 0:00:38 time: 0.6312 data_time: 0.0280 memory: 42708 grad_norm: 4.8502 loss: 1.2800 top1_acc: 0.7188 top5_acc: 0.8750 loss_cls: 1.2800 2023/02/18 06:31:11 - mmengine - INFO - Epoch(train) [50][620/660] lr: 1.0000e-04 eta: 0:00:25 time: 0.6399 data_time: 0.0343 memory: 42708 grad_norm: 4.8674 loss: 1.2824 top1_acc: 0.5938 top5_acc: 0.9062 loss_cls: 1.2824 2023/02/18 06:31:23 - mmengine - INFO - Epoch(train) [50][640/660] lr: 1.0000e-04 eta: 0:00:12 time: 0.6311 data_time: 0.0282 memory: 42708 grad_norm: 4.9092 loss: 1.2267 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.2267 2023/02/18 06:31:36 - mmengine - INFO - Exp name: tsn_imagenet-pretrained-r50_8xb32-1x1x16-50e_sthv2-rgb_20230218_003453 2023/02/18 06:31:36 - mmengine - INFO - Epoch(train) [50][660/660] lr: 1.0000e-04 eta: 0:00:00 time: 0.6201 data_time: 0.0339 memory: 42708 grad_norm: 4.9828 loss: 1.3040 top1_acc: 0.5926 top5_acc: 0.9259 loss_cls: 1.3040 2023/02/18 06:31:36 - mmengine - INFO - Saving checkpoint at 50 epochs 2023/02/18 06:31:44 - mmengine - INFO - Epoch(val) [50][20/97] eta: 0:00:25 time: 0.3349 data_time: 0.1224 memory: 6154 2023/02/18 06:31:48 - mmengine - INFO - Epoch(val) [50][40/97] eta: 0:00:16 time: 0.2440 data_time: 0.0318 memory: 6154 2023/02/18 06:31:53 - mmengine - INFO - Epoch(val) [50][60/97] eta: 0:00:10 time: 0.2494 data_time: 0.0402 memory: 6154 2023/02/18 06:31:58 - mmengine - INFO - Epoch(val) [50][80/97] eta: 0:00:04 time: 0.2410 data_time: 0.0353 memory: 6154 2023/02/18 06:32:03 - mmengine - INFO - Epoch(val) [50][97/97] acc/top1: 0.3603 acc/top5: 0.6690 acc/mean1: 0.2960