2023/04/17 19:22:26 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.16 (default, Jan 17 2023, 22:20:44) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1211924485 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /usr/local/cuda-11.7 NVCC: Cuda compilation tools, release 11.7, V11.7.99 GCC: gcc (GCC) 11.3.0 PyTorch: 1.13.1+cu116 PyTorch compiling details: PyTorch built with: - GCC 9.3 - 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 v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.6 - 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 8.8 (built against CUDA 11.8) - Built with CuDNN 8.3.2 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, 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, USE_ROCM=OFF, TorchVision: 0.14.1+cu116 OpenCV: 4.7.0 MMEngine: 0.7.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/04/17 19:22:26 - mmengine - INFO - Config: dataset_type = 'CIFAR10' data_preprocessor = dict( num_classes=10, mean=[125.307, 122.961, 113.8575], std=[51.5865, 50.847, 51.255], to_rgb=False) train_pipeline = [ dict(type='RandomCrop', crop_size=32, padding=4, _scope_='mmcls'), dict(type='RandomFlip', prob=0.5, direction='horizontal', _scope_='mmcls'), dict(type='PackClsInputs', _scope_='mmcls') ] test_pipeline = [dict(type='PackClsInputs', _scope_='mmcls')] train_dataloader = dict( batch_size=16, num_workers=2, dataset=dict( type='CIFAR10', data_prefix='data/cifar10', test_mode=False, pipeline=[ dict(type='RandomCrop', crop_size=32, padding=4), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackClsInputs') ], _scope_='mmcls'), sampler=dict(type='DefaultSampler', shuffle=True, _scope_='mmcls')) val_dataloader = dict( batch_size=16, num_workers=2, dataset=dict( type='CIFAR10', data_prefix='data/cifar10/', test_mode=True, pipeline=[dict(type='PackClsInputs')], _scope_='mmcls'), sampler=dict(type='DefaultSampler', shuffle=False, _scope_='mmcls')) val_evaluator = dict(type='Accuracy', topk=(1, ), _scope_='mmcls') test_dataloader = dict( batch_size=16, num_workers=2, dataset=dict( type='CIFAR10', data_prefix='data/cifar10/', test_mode=True, pipeline=[dict(type='PackClsInputs')], _scope_='mmcls'), sampler=dict(type='DefaultSampler', shuffle=False, _scope_='mmcls')) test_evaluator = dict(type='Accuracy', topk=(1, ), _scope_='mmcls') optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001, _scope_='mmcls')) param_scheduler = dict( type='MultiStepLR', by_epoch=True, milestones=[100, 150], gamma=0.1, _scope_='mmcls') train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1) val_cfg = dict(type='mmrazor.SingleTeacherDistillValLoop') test_cfg = dict() auto_scale_lr = dict(base_batch_size=128) default_scope = 'mmcls' default_hooks = dict( timer=dict(type='IterTimerHook', _scope_='mmcls'), logger=dict(type='LoggerHook', interval=100, _scope_='mmcls'), param_scheduler=dict(type='ParamSchedulerHook', _scope_='mmcls'), checkpoint=dict( type='CheckpointHook', interval=1, _scope_='mmdet', max_keep_ckpts=2), sampler_seed=dict(type='DistSamplerSeedHook', _scope_='mmcls'), visualization=dict( type='VisualizationHook', enable=False, _scope_='mmcls')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend', _scope_='mmcls')] visualizer = dict( type='ClsVisualizer', vis_backends=[dict(type='LocalVisBackend')], _scope_='mmcls') log_level = 'INFO' load_from = None resume = False randomness = dict(seed=None, deterministic=False) model = dict( _scope_='mmrazor', type='OverhaulFeatureDistillation', data_preprocessor=dict( type='ImgDataPreprocessor', mean=[125.307, 122.961, 113.8575], std=[51.5865, 50.847, 51.255], bgr_to_rgb=False), architecture=dict( cfg_path='mmrazor::vanilla/mmcls/wide-resnet/wrn16-w2_b16x8_cifar10.py', pretrained=False), teacher=dict( cfg_path='mmrazor::vanilla/mmcls/wide-resnet/wrn28-w4_b16x8_cifar10.py', pretrained=False), teacher_ckpt= 'https://download.openmmlab.com/mmrazor/v1/wide_resnet/wrn28_4_b16x8_cifar10_20220831_173536-d6f8725c.pth', calculate_student_loss=True, student_trainable=True, distiller=dict( type='OFDDistiller', student_recorders=dict( bb_1=dict(type='ModuleOutputs', source='backbone.layer2.0.bn1'), bb_2=dict(type='ModuleOutputs', source='backbone.layer3.0.bn1'), bb_3=dict(type='ModuleOutputs', source='backbone.bn1')), teacher_recorders=dict( bb_1=dict(type='ModuleOutputs', source='backbone.layer2.0.bn1'), bb_2=dict(type='ModuleOutputs', source='backbone.layer3.0.bn1'), bb_3=dict(type='ModuleOutputs', source='backbone.bn1')), distill_losses=dict( loss_1=dict(type='OFDLoss', loss_weight=0.25), loss_2=dict(type='OFDLoss', loss_weight=0.5), loss_3=dict(type='OFDLoss', loss_weight=1.0)), connectors=dict( loss_1_sfeat=dict( type='ConvModuleConnector', in_channel=32, out_channel=64, norm_cfg=dict(type='BN'), act_cfg=None), loss_1_tfeat=dict(type='OFDTeacherConnector'), loss_2_sfeat=dict( type='ConvModuleConnector', in_channel=64, out_channel=128, norm_cfg=dict(type='BN'), act_cfg=None), loss_2_tfeat=dict(type='OFDTeacherConnector'), loss_3_sfeat=dict( type='ConvModuleConnector', in_channel=128, out_channel=256, norm_cfg=dict(type='BN'), act_cfg=None), loss_3_tfeat=dict(type='OFDTeacherConnector')), loss_forward_mappings=dict( loss_1=dict( s_feature=dict( from_student=True, recorder='bb_1', connector='loss_1_sfeat'), t_feature=dict( from_student=False, recorder='bb_1', connector='loss_1_tfeat')), loss_2=dict( s_feature=dict( from_student=True, recorder='bb_2', connector='loss_2_sfeat'), t_feature=dict( from_student=False, recorder='bb_2', connector='loss_2_tfeat')), loss_3=dict( s_feature=dict( from_student=True, recorder='bb_3', connector='loss_3_sfeat'), t_feature=dict( from_student=False, recorder='bb_3', connector='loss_3_tfeat'))))) find_unused_parameters = True launcher = 'pytorch' work_dir = 'ofd' 2023/04/17 19:22:27 - mmengine - WARNING - The "model" registry in mmrazor did not set import location. Fallback to call `mmrazor.utils.register_all_modules` instead. 2023/04/17 19:22:28 - mmengine - WARNING - The "task util" registry in mmrazor did not set import location. Fallback to call `mmrazor.utils.register_all_modules` instead. 2023/04/17 19:22:29 - 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 (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) VisualizationHook (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 (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2023/04/17 19:22:31 - mmengine - WARNING - The "loop" registry in mmrazor did not set import location. Fallback to call `mmrazor.utils.register_all_modules` instead. 2023/04/17 19:22:34 - mmengine - WARNING - init_weights of ImageClassifier has been called more than once. Name of parameter - Initialization information architecture.backbone.conv1.weight - torch.Size([16, 3, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer1.0.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.0.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.0.conv1.weight - torch.Size([32, 16, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer1.0.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.0.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.0.conv2.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer1.0.downsample.weight - torch.Size([32, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer1.1.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.1.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.1.conv1.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer1.1.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.1.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer1.1.conv2.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer2.0.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.0.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.0.conv1.weight - torch.Size([64, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer2.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.0.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer2.0.downsample.weight - torch.Size([64, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer2.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.1.conv1.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer2.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer2.1.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer3.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.0.conv1.weight - torch.Size([128, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer3.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.0.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer3.0.downsample.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer3.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.1.conv1.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.layer3.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.layer3.1.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 architecture.backbone.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.backbone.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation architecture.head.fc.weight - torch.Size([10, 128]): NormalInit: mean=0, std=0.01, bias=0 architecture.head.fc.bias - torch.Size([10]): NormalInit: mean=0, std=0.01, bias=0 distiller.connectors.loss_1_sfeat.conv_module.conv.weight - torch.Size([64, 32, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_1_sfeat.conv_module.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_1_sfeat.conv_module.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_2_sfeat.conv_module.conv.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_2_sfeat.conv_module.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_2_sfeat.conv_module.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_3_sfeat.conv_module.conv.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_3_sfeat.conv_module.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation distiller.connectors.loss_3_sfeat.conv_module.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.conv1.weight - torch.Size([16, 3, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.conv1.weight - torch.Size([64, 16, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.0.downsample.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.conv1.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.conv1.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.conv1.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.conv1.weight - torch.Size([128, 64, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.0.downsample.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.conv1.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.conv1.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.conv1.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.conv1.weight - torch.Size([256, 128, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.0.downsample.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.conv1.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.conv1.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.conv1.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.backbone.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.head.fc.weight - torch.Size([10, 256]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation teacher.head.fc.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of OverhaulFeatureDistillation 2023/04/17 19:22:34 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/04/17 19:22:34 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/04/17 19:22:34 - mmengine - INFO - Checkpoints will be saved to /nvme/caoweihan.p/projects/mmrazor/ofd. 2023/04/17 19:22:44 - mmengine - INFO - Epoch(train) [1][100/391] lr: 1.0000e-01 eta: 2:06:47 time: 0.0218 data_time: 0.0034 memory: 227 loss: 10.0381 student.loss: 2.2080 distill.loss_1: 1.7499 distill.loss_2: 1.4516 distill.loss_3: 4.6286 2023/04/17 19:22:46 - mmengine - INFO - Epoch(train) [1][200/391] lr: 1.0000e-01 eta: 1:18:16 time: 0.0227 data_time: 0.0034 memory: 227 loss: 8.4616 student.loss: 1.8429 distill.loss_1: 1.0671 distill.loss_2: 1.3268 distill.loss_3: 4.2249 2023/04/17 19:22:48 - mmengine - INFO - Epoch(train) [1][300/391] lr: 1.0000e-01 eta: 1:01:55 time: 0.0251 data_time: 0.0034 memory: 227 loss: 7.4346 student.loss: 1.3792 distill.loss_1: 0.7942 distill.loss_2: 1.1818 distill.loss_3: 4.0795 2023/04/17 19:22:50 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:22:50 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/04/17 19:22:56 - mmengine - INFO - Epoch(val) [1][79/79] accuracy/top1: 53.5900 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0096 2023/04/17 19:22:59 - mmengine - INFO - Epoch(train) [2][100/391] lr: 1.0000e-01 eta: 0:50:00 time: 0.0229 data_time: 0.0042 memory: 227 loss: 6.1712 student.loss: 1.1332 distill.loss_1: 0.6045 distill.loss_2: 0.9332 distill.loss_3: 3.5004 2023/04/17 19:23:02 - mmengine - INFO - Epoch(train) [2][200/391] lr: 1.0000e-01 eta: 0:47:22 time: 0.0303 data_time: 0.0037 memory: 227 loss: 5.7844 student.loss: 1.1275 distill.loss_1: 0.5300 distill.loss_2: 0.8150 distill.loss_3: 3.3118 2023/04/17 19:23:04 - mmengine - INFO - Epoch(train) [2][300/391] lr: 1.0000e-01 eta: 0:45:04 time: 0.0228 data_time: 0.0034 memory: 227 loss: 4.9866 student.loss: 0.8474 distill.loss_1: 0.4982 distill.loss_2: 0.7415 distill.loss_3: 2.8995 2023/04/17 19:23:06 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:23:06 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/04/17 19:23:21 - mmengine - INFO - Epoch(val) [2][79/79] accuracy/top1: 73.5900 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0092 2023/04/17 19:23:28 - mmengine - INFO - Epoch(train) [3][100/391] lr: 1.0000e-01 eta: 0:48:30 time: 0.0220 data_time: 0.0034 memory: 227 loss: 4.3018 student.loss: 0.6400 distill.loss_1: 0.4571 distill.loss_2: 0.6310 distill.loss_3: 2.5737 2023/04/17 19:23:30 - mmengine - INFO - Epoch(train) [3][200/391] lr: 1.0000e-01 eta: 0:46:33 time: 0.0239 data_time: 0.0036 memory: 227 loss: 3.9245 student.loss: 0.4894 distill.loss_1: 0.4461 distill.loss_2: 0.6031 distill.loss_3: 2.3858 2023/04/17 19:23:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:23:33 - mmengine - INFO - Epoch(train) [3][300/391] lr: 1.0000e-01 eta: 0:44:53 time: 0.0231 data_time: 0.0036 memory: 227 loss: 3.9366 student.loss: 0.6269 distill.loss_1: 0.4144 distill.loss_2: 0.5667 distill.loss_3: 2.3286 2023/04/17 19:23:35 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:23:35 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/04/17 19:23:41 - mmengine - INFO - Epoch(val) [3][79/79] accuracy/top1: 80.2300 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 19:23:44 - mmengine - INFO - Epoch(train) [4][100/391] lr: 1.0000e-01 eta: 0:43:05 time: 0.0738 data_time: 0.0036 memory: 227 loss: 3.5878 student.loss: 0.4481 distill.loss_1: 0.3927 distill.loss_2: 0.5304 distill.loss_3: 2.2166 2023/04/17 19:23:51 - mmengine - INFO - Epoch(train) [4][200/391] lr: 1.0000e-01 eta: 0:46:39 time: 0.0252 data_time: 0.0043 memory: 227 loss: 3.7139 student.loss: 0.5806 distill.loss_1: 0.3744 distill.loss_2: 0.4952 distill.loss_3: 2.2637 2023/04/17 19:23:55 - mmengine - INFO - Epoch(train) [4][300/391] lr: 1.0000e-01 eta: 0:46:51 time: 0.0225 data_time: 0.0038 memory: 227 loss: 3.5430 student.loss: 0.5350 distill.loss_1: 0.3632 distill.loss_2: 0.4942 distill.loss_3: 2.1507 2023/04/17 19:23:57 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:23:57 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/04/17 19:24:03 - mmengine - INFO - Epoch(val) [4][79/79] accuracy/top1: 80.0200 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0094 2023/04/17 19:24:06 - mmengine - INFO - Epoch(train) [5][100/391] lr: 1.0000e-01 eta: 0:45:12 time: 0.0230 data_time: 0.0033 memory: 227 loss: 3.3663 student.loss: 0.5630 distill.loss_1: 0.3626 distill.loss_2: 0.4670 distill.loss_3: 1.9737 2023/04/17 19:24:08 - mmengine - INFO - Epoch(train) [5][200/391] lr: 1.0000e-01 eta: 0:44:21 time: 0.0234 data_time: 0.0035 memory: 227 loss: 3.0516 student.loss: 0.3539 distill.loss_1: 0.3547 distill.loss_2: 0.4551 distill.loss_3: 1.8880 2023/04/17 19:24:11 - mmengine - INFO - Epoch(train) [5][300/391] lr: 1.0000e-01 eta: 0:43:30 time: 0.0230 data_time: 0.0033 memory: 227 loss: 3.3918 student.loss: 0.5238 distill.loss_1: 0.3626 distill.loss_2: 0.4547 distill.loss_3: 2.0508 2023/04/17 19:24:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:13 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/04/17 19:24:19 - mmengine - INFO - Epoch(val) [5][79/79] accuracy/top1: 82.2300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:24:20 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:21 - mmengine - INFO - Epoch(train) [6][100/391] lr: 1.0000e-01 eta: 0:42:11 time: 0.0222 data_time: 0.0036 memory: 227 loss: 3.0823 student.loss: 0.4042 distill.loss_1: 0.3368 distill.loss_2: 0.4378 distill.loss_3: 1.9035 2023/04/17 19:24:24 - mmengine - INFO - Epoch(train) [6][200/391] lr: 1.0000e-01 eta: 0:41:31 time: 0.0239 data_time: 0.0034 memory: 227 loss: 3.1338 student.loss: 0.4557 distill.loss_1: 0.3368 distill.loss_2: 0.4245 distill.loss_3: 1.9167 2023/04/17 19:24:26 - mmengine - INFO - Epoch(train) [6][300/391] lr: 1.0000e-01 eta: 0:41:04 time: 0.0226 data_time: 0.0035 memory: 227 loss: 2.8857 student.loss: 0.3371 distill.loss_1: 0.3315 distill.loss_2: 0.4251 distill.loss_3: 1.7920 2023/04/17 19:24:28 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:28 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/04/17 19:24:35 - mmengine - INFO - Epoch(val) [6][79/79] accuracy/top1: 87.8100 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0096 2023/04/17 19:24:37 - mmengine - INFO - Epoch(train) [7][100/391] lr: 1.0000e-01 eta: 0:40:04 time: 0.0229 data_time: 0.0035 memory: 227 loss: 3.0590 student.loss: 0.4688 distill.loss_1: 0.3395 distill.loss_2: 0.4110 distill.loss_3: 1.8397 2023/04/17 19:24:39 - mmengine - INFO - Epoch(train) [7][200/391] lr: 1.0000e-01 eta: 0:39:33 time: 0.0221 data_time: 0.0033 memory: 227 loss: 2.9342 student.loss: 0.4155 distill.loss_1: 0.3208 distill.loss_2: 0.4054 distill.loss_3: 1.7925 2023/04/17 19:24:42 - mmengine - INFO - Epoch(train) [7][300/391] lr: 1.0000e-01 eta: 0:39:04 time: 0.0216 data_time: 0.0036 memory: 227 loss: 2.7993 student.loss: 0.3533 distill.loss_1: 0.3301 distill.loss_2: 0.4051 distill.loss_3: 1.7108 2023/04/17 19:24:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:44 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/04/17 19:24:49 - mmengine - INFO - Epoch(val) [7][79/79] accuracy/top1: 85.9300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 19:24:52 - mmengine - INFO - Epoch(train) [8][100/391] lr: 1.0000e-01 eta: 0:38:29 time: 0.0233 data_time: 0.0034 memory: 227 loss: 2.6873 student.loss: 0.2786 distill.loss_1: 0.3109 distill.loss_2: 0.3940 distill.loss_3: 1.7039 2023/04/17 19:24:55 - mmengine - INFO - Epoch(train) [8][200/391] lr: 1.0000e-01 eta: 0:38:04 time: 0.0221 data_time: 0.0033 memory: 227 loss: 2.7954 student.loss: 0.3634 distill.loss_1: 0.3100 distill.loss_2: 0.3878 distill.loss_3: 1.7343 2023/04/17 19:24:56 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:57 - mmengine - INFO - Epoch(train) [8][300/391] lr: 1.0000e-01 eta: 0:37:40 time: 0.0218 data_time: 0.0033 memory: 227 loss: 2.8490 student.loss: 0.4570 distill.loss_1: 0.3073 distill.loss_2: 0.3863 distill.loss_3: 1.6985 2023/04/17 19:24:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:24:59 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/04/17 19:25:04 - mmengine - INFO - Epoch(val) [8][79/79] accuracy/top1: 86.6800 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:25:07 - mmengine - INFO - Epoch(train) [9][100/391] lr: 1.0000e-01 eta: 0:37:14 time: 0.0238 data_time: 0.0034 memory: 227 loss: 2.5151 student.loss: 0.2481 distill.loss_1: 0.3151 distill.loss_2: 0.3885 distill.loss_3: 1.5634 2023/04/17 19:25:09 - mmengine - INFO - Epoch(train) [9][200/391] lr: 1.0000e-01 eta: 0:36:54 time: 0.0216 data_time: 0.0034 memory: 227 loss: 2.3787 student.loss: 0.2027 distill.loss_1: 0.2974 distill.loss_2: 0.3756 distill.loss_3: 1.5032 2023/04/17 19:25:12 - mmengine - INFO - Epoch(train) [9][300/391] lr: 1.0000e-01 eta: 0:36:36 time: 0.0224 data_time: 0.0037 memory: 227 loss: 2.5223 student.loss: 0.2937 distill.loss_1: 0.3039 distill.loss_2: 0.3742 distill.loss_3: 1.5504 2023/04/17 19:25:14 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:25:14 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/04/17 19:25:20 - mmengine - INFO - Epoch(val) [9][79/79] accuracy/top1: 85.8300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 19:25:22 - mmengine - INFO - Epoch(train) [10][100/391] lr: 1.0000e-01 eta: 0:36:07 time: 0.0222 data_time: 0.0034 memory: 227 loss: 2.5097 student.loss: 0.2679 distill.loss_1: 0.3009 distill.loss_2: 0.3746 distill.loss_3: 1.5663 2023/04/17 19:25:25 - mmengine - INFO - Epoch(train) [10][200/391] lr: 1.0000e-01 eta: 0:35:52 time: 0.0226 data_time: 0.0034 memory: 227 loss: 2.6136 student.loss: 0.2967 distill.loss_1: 0.2966 distill.loss_2: 0.3683 distill.loss_3: 1.6521 2023/04/17 19:25:27 - mmengine - INFO - Epoch(train) [10][300/391] lr: 1.0000e-01 eta: 0:35:37 time: 0.0216 data_time: 0.0034 memory: 227 loss: 2.6909 student.loss: 0.3635 distill.loss_1: 0.3013 distill.loss_2: 0.3711 distill.loss_3: 1.6550 2023/04/17 19:25:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:25:29 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/04/17 19:25:35 - mmengine - INFO - Epoch(val) [10][79/79] accuracy/top1: 89.6600 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0090 2023/04/17 19:25:37 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:25:37 - mmengine - INFO - Epoch(train) [11][100/391] lr: 1.0000e-01 eta: 0:35:12 time: 0.0222 data_time: 0.0038 memory: 227 loss: 2.4599 student.loss: 0.2366 distill.loss_1: 0.3022 distill.loss_2: 0.3713 distill.loss_3: 1.5499 2023/04/17 19:25:40 - mmengine - INFO - Epoch(train) [11][200/391] lr: 1.0000e-01 eta: 0:35:00 time: 0.0224 data_time: 0.0035 memory: 227 loss: 2.2979 student.loss: 0.2232 distill.loss_1: 0.2874 distill.loss_2: 0.3600 distill.loss_3: 1.4272 2023/04/17 19:25:42 - mmengine - INFO - Epoch(train) [11][300/391] lr: 1.0000e-01 eta: 0:34:46 time: 0.0222 data_time: 0.0033 memory: 227 loss: 2.3943 student.loss: 0.2426 distill.loss_1: 0.2938 distill.loss_2: 0.3652 distill.loss_3: 1.4927 2023/04/17 19:25:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:25:44 - mmengine - INFO - Saving checkpoint at 11 epochs 2023/04/17 19:25:50 - mmengine - INFO - Epoch(val) [11][79/79] accuracy/top1: 88.7500 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0096 2023/04/17 19:25:53 - mmengine - INFO - Epoch(train) [12][100/391] lr: 1.0000e-01 eta: 0:34:30 time: 0.0219 data_time: 0.0034 memory: 227 loss: 2.3021 student.loss: 0.2269 distill.loss_1: 0.2961 distill.loss_2: 0.3592 distill.loss_3: 1.4200 2023/04/17 19:25:55 - mmengine - INFO - Epoch(train) [12][200/391] lr: 1.0000e-01 eta: 0:34:19 time: 0.0220 data_time: 0.0034 memory: 227 loss: 2.4071 student.loss: 0.2811 distill.loss_1: 0.2906 distill.loss_2: 0.3542 distill.loss_3: 1.4813 2023/04/17 19:25:58 - mmengine - INFO - Epoch(train) [12][300/391] lr: 1.0000e-01 eta: 0:34:07 time: 0.0220 data_time: 0.0034 memory: 227 loss: 2.1503 student.loss: 0.1857 distill.loss_1: 0.2829 distill.loss_2: 0.3506 distill.loss_3: 1.3312 2023/04/17 19:26:00 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:00 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/04/17 19:26:05 - mmengine - INFO - Epoch(val) [12][79/79] accuracy/top1: 90.2200 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 19:26:08 - mmengine - INFO - Epoch(train) [13][100/391] lr: 1.0000e-01 eta: 0:33:53 time: 0.0222 data_time: 0.0035 memory: 227 loss: 2.3580 student.loss: 0.2713 distill.loss_1: 0.2830 distill.loss_2: 0.3489 distill.loss_3: 1.4547 2023/04/17 19:26:10 - mmengine - INFO - Epoch(train) [13][200/391] lr: 1.0000e-01 eta: 0:33:42 time: 0.0222 data_time: 0.0034 memory: 227 loss: 2.4907 student.loss: 0.3492 distill.loss_1: 0.2892 distill.loss_2: 0.3524 distill.loss_3: 1.5000 2023/04/17 19:26:13 - mmengine - INFO - Epoch(train) [13][300/391] lr: 1.0000e-01 eta: 0:33:32 time: 0.0220 data_time: 0.0034 memory: 227 loss: 2.3399 student.loss: 0.2225 distill.loss_1: 0.2869 distill.loss_2: 0.3528 distill.loss_3: 1.4777 2023/04/17 19:26:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:15 - mmengine - INFO - Saving checkpoint at 13 epochs 2023/04/17 19:26:20 - mmengine - INFO - Epoch(val) [13][79/79] accuracy/top1: 89.1300 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0100 2023/04/17 19:26:23 - mmengine - INFO - Epoch(train) [14][100/391] lr: 1.0000e-01 eta: 0:33:20 time: 0.0222 data_time: 0.0033 memory: 227 loss: 2.4418 student.loss: 0.2658 distill.loss_1: 0.2819 distill.loss_2: 0.3455 distill.loss_3: 1.5487 2023/04/17 19:26:25 - mmengine - INFO - Epoch(train) [14][200/391] lr: 1.0000e-01 eta: 0:33:09 time: 0.0219 data_time: 0.0033 memory: 227 loss: 2.1888 student.loss: 0.1729 distill.loss_1: 0.2808 distill.loss_2: 0.3460 distill.loss_3: 1.3892 2023/04/17 19:26:28 - mmengine - INFO - Epoch(train) [14][300/391] lr: 1.0000e-01 eta: 0:33:08 time: 0.0227 data_time: 0.0034 memory: 227 loss: 2.3098 student.loss: 0.2307 distill.loss_1: 0.2794 distill.loss_2: 0.3470 distill.loss_3: 1.4528 2023/04/17 19:26:30 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:30 - mmengine - INFO - Saving checkpoint at 14 epochs 2023/04/17 19:26:36 - mmengine - INFO - Epoch(val) [14][79/79] accuracy/top1: 88.5100 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0096 2023/04/17 19:26:39 - mmengine - INFO - Epoch(train) [15][100/391] lr: 1.0000e-01 eta: 0:32:55 time: 0.0217 data_time: 0.0034 memory: 227 loss: 2.2213 student.loss: 0.1594 distill.loss_1: 0.2898 distill.loss_2: 0.3517 distill.loss_3: 1.4204 2023/04/17 19:26:41 - mmengine - INFO - Epoch(train) [15][200/391] lr: 1.0000e-01 eta: 0:32:47 time: 0.0226 data_time: 0.0035 memory: 227 loss: 2.3250 student.loss: 0.2650 distill.loss_1: 0.2826 distill.loss_2: 0.3444 distill.loss_3: 1.4330 2023/04/17 19:26:43 - mmengine - INFO - Epoch(train) [15][300/391] lr: 1.0000e-01 eta: 0:32:38 time: 0.0221 data_time: 0.0034 memory: 227 loss: 2.2335 student.loss: 0.1728 distill.loss_1: 0.2938 distill.loss_2: 0.3489 distill.loss_3: 1.4180 2023/04/17 19:26:45 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:45 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/04/17 19:26:52 - mmengine - INFO - Epoch(val) [15][79/79] accuracy/top1: 89.8100 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0106 2023/04/17 19:26:54 - mmengine - INFO - Epoch(train) [16][100/391] lr: 1.0000e-01 eta: 0:32:26 time: 0.0231 data_time: 0.0034 memory: 227 loss: 2.2368 student.loss: 0.1996 distill.loss_1: 0.2903 distill.loss_2: 0.3435 distill.loss_3: 1.4035 2023/04/17 19:26:55 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:26:57 - mmengine - INFO - Epoch(train) [16][200/391] lr: 1.0000e-01 eta: 0:32:19 time: 0.0229 data_time: 0.0034 memory: 227 loss: 2.2986 student.loss: 0.2299 distill.loss_1: 0.2669 distill.loss_2: 0.3408 distill.loss_3: 1.4610 2023/04/17 19:26:59 - mmengine - INFO - Epoch(train) [16][300/391] lr: 1.0000e-01 eta: 0:32:12 time: 0.0228 data_time: 0.0034 memory: 227 loss: 2.1354 student.loss: 0.1541 distill.loss_1: 0.2779 distill.loss_2: 0.3383 distill.loss_3: 1.3650 2023/04/17 19:27:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:27:01 - mmengine - INFO - Saving checkpoint at 16 epochs 2023/04/17 19:27:07 - mmengine - INFO - Epoch(val) [16][79/79] accuracy/top1: 90.5800 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0098 2023/04/17 19:27:10 - mmengine - INFO - Epoch(train) [17][100/391] lr: 1.0000e-01 eta: 0:32:02 time: 0.0234 data_time: 0.0034 memory: 227 loss: 2.3263 student.loss: 0.2397 distill.loss_1: 0.2800 distill.loss_2: 0.3429 distill.loss_3: 1.4636 2023/04/17 19:27:12 - mmengine - INFO - Epoch(train) [17][200/391] lr: 1.0000e-01 eta: 0:31:55 time: 0.0228 data_time: 0.0035 memory: 227 loss: 1.9999 student.loss: 0.1352 distill.loss_1: 0.2720 distill.loss_2: 0.3356 distill.loss_3: 1.2570 2023/04/17 19:27:14 - mmengine - INFO - Epoch(train) [17][300/391] lr: 1.0000e-01 eta: 0:31:47 time: 0.0220 data_time: 0.0033 memory: 227 loss: 2.2084 student.loss: 0.2158 distill.loss_1: 0.2754 distill.loss_2: 0.3324 distill.loss_3: 1.3848 2023/04/17 19:27:16 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:27:16 - mmengine - INFO - Saving checkpoint at 17 epochs 2023/04/17 19:27:22 - mmengine - INFO - Epoch(val) [17][79/79] accuracy/top1: 90.0000 teacher.accuracy/top1: 95.4400data_time: 0.0036 time: 0.0097 2023/04/17 19:27:25 - mmengine - INFO - Epoch(train) [18][100/391] lr: 1.0000e-01 eta: 0:31:39 time: 0.0223 data_time: 0.0034 memory: 227 loss: 2.2795 student.loss: 0.3154 distill.loss_1: 0.2740 distill.loss_2: 0.3362 distill.loss_3: 1.3539 2023/04/17 19:27:27 - mmengine - INFO - Epoch(train) [18][200/391] lr: 1.0000e-01 eta: 0:31:32 time: 0.0234 data_time: 0.0034 memory: 227 loss: 2.1795 student.loss: 0.2166 distill.loss_1: 0.2751 distill.loss_2: 0.3373 distill.loss_3: 1.3505 2023/04/17 19:27:29 - mmengine - INFO - Epoch(train) [18][300/391] lr: 1.0000e-01 eta: 0:31:25 time: 0.0241 data_time: 0.0037 memory: 227 loss: 2.0842 student.loss: 0.1541 distill.loss_1: 0.2881 distill.loss_2: 0.3438 distill.loss_3: 1.2983 2023/04/17 19:27:30 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:27:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:27:31 - mmengine - INFO - Saving checkpoint at 18 epochs 2023/04/17 19:27:38 - mmengine - INFO - Epoch(val) [18][79/79] accuracy/top1: 89.1600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0097 2023/04/17 19:27:40 - mmengine - INFO - Epoch(train) [19][100/391] lr: 1.0000e-01 eta: 0:31:14 time: 0.0224 data_time: 0.0046 memory: 227 loss: 2.0950 student.loss: 0.1529 distill.loss_1: 0.2734 distill.loss_2: 0.3297 distill.loss_3: 1.3390 2023/04/17 19:27:42 - mmengine - INFO - Epoch(train) [19][200/391] lr: 1.0000e-01 eta: 0:31:07 time: 0.0225 data_time: 0.0038 memory: 227 loss: 2.1239 student.loss: 0.1838 distill.loss_1: 0.2778 distill.loss_2: 0.3330 distill.loss_3: 1.3292 2023/04/17 19:27:44 - mmengine - INFO - Epoch(train) [19][300/391] lr: 1.0000e-01 eta: 0:31:01 time: 0.0223 data_time: 0.0044 memory: 227 loss: 2.0019 student.loss: 0.1301 distill.loss_1: 0.2784 distill.loss_2: 0.3336 distill.loss_3: 1.2598 2023/04/17 19:27:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:27:47 - mmengine - INFO - Saving checkpoint at 19 epochs 2023/04/17 19:27:53 - mmengine - INFO - Epoch(val) [19][79/79] accuracy/top1: 90.3600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:27:55 - mmengine - INFO - Epoch(train) [20][100/391] lr: 1.0000e-01 eta: 0:30:52 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.9233 student.loss: 0.1095 distill.loss_1: 0.2696 distill.loss_2: 0.3310 distill.loss_3: 1.2133 2023/04/17 19:27:57 - mmengine - INFO - Epoch(train) [20][200/391] lr: 1.0000e-01 eta: 0:30:46 time: 0.0227 data_time: 0.0036 memory: 227 loss: 2.1167 student.loss: 0.2264 distill.loss_1: 0.2635 distill.loss_2: 0.3237 distill.loss_3: 1.3031 2023/04/17 19:28:00 - mmengine - INFO - Epoch(train) [20][300/391] lr: 1.0000e-01 eta: 0:30:40 time: 0.0224 data_time: 0.0036 memory: 227 loss: 2.1352 student.loss: 0.2221 distill.loss_1: 0.2753 distill.loss_2: 0.3286 distill.loss_3: 1.3091 2023/04/17 19:28:02 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:28:02 - mmengine - INFO - Saving checkpoint at 20 epochs 2023/04/17 19:28:08 - mmengine - INFO - Epoch(val) [20][79/79] accuracy/top1: 90.1100 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0097 2023/04/17 19:28:10 - mmengine - INFO - Epoch(train) [21][100/391] lr: 1.0000e-01 eta: 0:30:31 time: 0.0231 data_time: 0.0036 memory: 227 loss: 2.1481 student.loss: 0.1894 distill.loss_1: 0.2659 distill.loss_2: 0.3252 distill.loss_3: 1.3676 2023/04/17 19:28:12 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:28:12 - mmengine - INFO - Epoch(train) [21][200/391] lr: 1.0000e-01 eta: 0:30:26 time: 0.0225 data_time: 0.0035 memory: 227 loss: 2.2016 student.loss: 0.2350 distill.loss_1: 0.2708 distill.loss_2: 0.3323 distill.loss_3: 1.3636 2023/04/17 19:28:15 - mmengine - INFO - Epoch(train) [21][300/391] lr: 1.0000e-01 eta: 0:30:20 time: 0.0221 data_time: 0.0034 memory: 227 loss: 2.1986 student.loss: 0.2390 distill.loss_1: 0.2592 distill.loss_2: 0.3223 distill.loss_3: 1.3780 2023/04/17 19:28:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:28:17 - mmengine - INFO - Saving checkpoint at 21 epochs 2023/04/17 19:28:23 - mmengine - INFO - Epoch(val) [21][79/79] accuracy/top1: 88.5900 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 19:28:26 - mmengine - INFO - Epoch(train) [22][100/391] lr: 1.0000e-01 eta: 0:30:16 time: 0.0228 data_time: 0.0034 memory: 227 loss: 2.0697 student.loss: 0.1742 distill.loss_1: 0.2673 distill.loss_2: 0.3300 distill.loss_3: 1.2982 2023/04/17 19:28:28 - mmengine - INFO - Epoch(train) [22][200/391] lr: 1.0000e-01 eta: 0:30:10 time: 0.0224 data_time: 0.0034 memory: 227 loss: 2.1822 student.loss: 0.1910 distill.loss_1: 0.2728 distill.loss_2: 0.3300 distill.loss_3: 1.3884 2023/04/17 19:28:30 - mmengine - INFO - Epoch(train) [22][300/391] lr: 1.0000e-01 eta: 0:30:04 time: 0.0219 data_time: 0.0035 memory: 227 loss: 2.1462 student.loss: 0.2226 distill.loss_1: 0.2702 distill.loss_2: 0.3249 distill.loss_3: 1.3285 2023/04/17 19:28:32 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:28:32 - mmengine - INFO - Saving checkpoint at 22 epochs 2023/04/17 19:28:38 - mmengine - INFO - Epoch(val) [22][79/79] accuracy/top1: 91.7900 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0094 2023/04/17 19:28:41 - mmengine - INFO - Epoch(train) [23][100/391] lr: 1.0000e-01 eta: 0:29:59 time: 0.0275 data_time: 0.0048 memory: 227 loss: 2.1103 student.loss: 0.1821 distill.loss_1: 0.2622 distill.loss_2: 0.3197 distill.loss_3: 1.3463 2023/04/17 19:28:43 - mmengine - INFO - Epoch(train) [23][200/391] lr: 1.0000e-01 eta: 0:29:55 time: 0.0229 data_time: 0.0036 memory: 227 loss: 2.0482 student.loss: 0.1507 distill.loss_1: 0.2708 distill.loss_2: 0.3273 distill.loss_3: 1.2994 2023/04/17 19:28:46 - mmengine - INFO - Epoch(train) [23][300/391] lr: 1.0000e-01 eta: 0:29:52 time: 0.0223 data_time: 0.0036 memory: 227 loss: 2.0981 student.loss: 0.1482 distill.loss_1: 0.2678 distill.loss_2: 0.3219 distill.loss_3: 1.3603 2023/04/17 19:28:48 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:28:48 - mmengine - INFO - Saving checkpoint at 23 epochs 2023/04/17 19:28:57 - mmengine - INFO - Epoch(val) [23][79/79] accuracy/top1: 91.5800 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0169 2023/04/17 19:28:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:29:01 - mmengine - INFO - Epoch(train) [24][100/391] lr: 1.0000e-01 eta: 0:29:55 time: 0.0227 data_time: 0.0038 memory: 227 loss: 2.0816 student.loss: 0.1724 distill.loss_1: 0.2703 distill.loss_2: 0.3267 distill.loss_3: 1.3123 2023/04/17 19:29:04 - mmengine - INFO - Epoch(train) [24][200/391] lr: 1.0000e-01 eta: 0:29:49 time: 0.0220 data_time: 0.0036 memory: 227 loss: 2.1040 student.loss: 0.2224 distill.loss_1: 0.2678 distill.loss_2: 0.3216 distill.loss_3: 1.2922 2023/04/17 19:29:06 - mmengine - INFO - Epoch(train) [24][300/391] lr: 1.0000e-01 eta: 0:29:44 time: 0.0225 data_time: 0.0037 memory: 227 loss: 2.0501 student.loss: 0.1794 distill.loss_1: 0.2596 distill.loss_2: 0.3197 distill.loss_3: 1.2913 2023/04/17 19:29:08 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:29:08 - mmengine - INFO - Saving checkpoint at 24 epochs 2023/04/17 19:29:14 - mmengine - INFO - Epoch(val) [24][79/79] accuracy/top1: 90.0000 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0106 2023/04/17 19:29:17 - mmengine - INFO - Epoch(train) [25][100/391] lr: 1.0000e-01 eta: 0:29:41 time: 0.0365 data_time: 0.0035 memory: 227 loss: 1.9291 student.loss: 0.1314 distill.loss_1: 0.2537 distill.loss_2: 0.3150 distill.loss_3: 1.2290 2023/04/17 19:29:21 - mmengine - INFO - Epoch(train) [25][200/391] lr: 1.0000e-01 eta: 0:29:52 time: 0.0476 data_time: 0.0039 memory: 227 loss: 1.9427 student.loss: 0.1220 distill.loss_1: 0.2562 distill.loss_2: 0.3197 distill.loss_3: 1.2449 2023/04/17 19:29:26 - mmengine - INFO - Epoch(train) [25][300/391] lr: 1.0000e-01 eta: 0:30:02 time: 0.0276 data_time: 0.0037 memory: 227 loss: 2.2207 student.loss: 0.2412 distill.loss_1: 0.2613 distill.loss_2: 0.3253 distill.loss_3: 1.3928 2023/04/17 19:29:28 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:29:28 - mmengine - INFO - Saving checkpoint at 25 epochs 2023/04/17 19:29:35 - mmengine - INFO - Epoch(val) [25][79/79] accuracy/top1: 90.4300 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0096 2023/04/17 19:29:40 - mmengine - INFO - Epoch(train) [26][100/391] lr: 1.0000e-01 eta: 0:30:18 time: 0.0521 data_time: 0.0038 memory: 227 loss: 1.8224 student.loss: 0.0948 distill.loss_1: 0.2522 distill.loss_2: 0.3169 distill.loss_3: 1.1585 2023/04/17 19:29:44 - mmengine - INFO - Epoch(train) [26][200/391] lr: 1.0000e-01 eta: 0:30:20 time: 0.0339 data_time: 0.0034 memory: 227 loss: 2.0093 student.loss: 0.1274 distill.loss_1: 0.2590 distill.loss_2: 0.3192 distill.loss_3: 1.3036 2023/04/17 19:29:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:29:47 - mmengine - INFO - Epoch(train) [26][300/391] lr: 1.0000e-01 eta: 0:30:19 time: 0.0334 data_time: 0.0036 memory: 227 loss: 2.0273 student.loss: 0.1345 distill.loss_1: 0.2601 distill.loss_2: 0.3296 distill.loss_3: 1.3031 2023/04/17 19:29:50 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:29:50 - mmengine - INFO - Saving checkpoint at 26 epochs 2023/04/17 19:29:58 - mmengine - INFO - Epoch(val) [26][79/79] accuracy/top1: 91.0300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:30:02 - mmengine - INFO - Epoch(train) [27][100/391] lr: 1.0000e-01 eta: 0:30:31 time: 0.0357 data_time: 0.0037 memory: 227 loss: 2.1168 student.loss: 0.2240 distill.loss_1: 0.2653 distill.loss_2: 0.3235 distill.loss_3: 1.3040 2023/04/17 19:30:05 - mmengine - INFO - Epoch(train) [27][200/391] lr: 1.0000e-01 eta: 0:30:30 time: 0.0343 data_time: 0.0034 memory: 227 loss: 2.0819 student.loss: 0.1716 distill.loss_1: 0.2601 distill.loss_2: 0.3209 distill.loss_3: 1.3293 2023/04/17 19:30:09 - mmengine - INFO - Epoch(train) [27][300/391] lr: 1.0000e-01 eta: 0:30:35 time: 0.0431 data_time: 0.0040 memory: 227 loss: 2.0702 student.loss: 0.2303 distill.loss_1: 0.2541 distill.loss_2: 0.3156 distill.loss_3: 1.2702 2023/04/17 19:30:14 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:30:14 - mmengine - INFO - Saving checkpoint at 27 epochs 2023/04/17 19:30:21 - mmengine - INFO - Epoch(val) [27][79/79] accuracy/top1: 90.8700 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0093 2023/04/17 19:30:26 - mmengine - INFO - Epoch(train) [28][100/391] lr: 1.0000e-01 eta: 0:31:01 time: 0.0522 data_time: 0.0035 memory: 227 loss: 1.9971 student.loss: 0.1690 distill.loss_1: 0.2536 distill.loss_2: 0.3162 distill.loss_3: 1.2583 2023/04/17 19:30:32 - mmengine - INFO - Epoch(train) [28][200/391] lr: 1.0000e-01 eta: 0:31:14 time: 0.0442 data_time: 0.0034 memory: 227 loss: 2.1517 student.loss: 0.2546 distill.loss_1: 0.2583 distill.loss_2: 0.3186 distill.loss_3: 1.3201 2023/04/17 19:30:35 - mmengine - INFO - Epoch(train) [28][300/391] lr: 1.0000e-01 eta: 0:31:13 time: 0.0222 data_time: 0.0034 memory: 227 loss: 2.0760 student.loss: 0.1635 distill.loss_1: 0.2607 distill.loss_2: 0.3191 distill.loss_3: 1.3327 2023/04/17 19:30:38 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:30:38 - mmengine - INFO - Saving checkpoint at 28 epochs 2023/04/17 19:30:46 - mmengine - INFO - Epoch(val) [28][79/79] accuracy/top1: 91.4500 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0098 2023/04/17 19:30:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:30:50 - mmengine - INFO - Epoch(train) [29][100/391] lr: 1.0000e-01 eta: 0:31:23 time: 0.0348 data_time: 0.0037 memory: 227 loss: 2.0617 student.loss: 0.1868 distill.loss_1: 0.2555 distill.loss_2: 0.3129 distill.loss_3: 1.3066 2023/04/17 19:30:54 - mmengine - INFO - Epoch(train) [29][200/391] lr: 1.0000e-01 eta: 0:31:25 time: 0.0742 data_time: 0.0038 memory: 227 loss: 2.0316 student.loss: 0.1796 distill.loss_1: 0.2676 distill.loss_2: 0.3156 distill.loss_3: 1.2689 2023/04/17 19:30:59 - mmengine - INFO - Epoch(train) [29][300/391] lr: 1.0000e-01 eta: 0:31:33 time: 0.0517 data_time: 0.0040 memory: 227 loss: 1.9825 student.loss: 0.1399 distill.loss_1: 0.2626 distill.loss_2: 0.3207 distill.loss_3: 1.2594 2023/04/17 19:31:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:31:03 - mmengine - INFO - Saving checkpoint at 29 epochs 2023/04/17 19:31:10 - mmengine - INFO - Epoch(val) [29][79/79] accuracy/top1: 90.8400 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0099 2023/04/17 19:31:15 - mmengine - INFO - Epoch(train) [30][100/391] lr: 1.0000e-01 eta: 0:31:52 time: 0.0555 data_time: 0.0039 memory: 227 loss: 2.2310 student.loss: 0.2430 distill.loss_1: 0.2588 distill.loss_2: 0.3203 distill.loss_3: 1.4090 2023/04/17 19:31:20 - mmengine - INFO - Epoch(train) [30][200/391] lr: 1.0000e-01 eta: 0:31:59 time: 0.0222 data_time: 0.0035 memory: 227 loss: 2.0892 student.loss: 0.1791 distill.loss_1: 0.2682 distill.loss_2: 0.3174 distill.loss_3: 1.3245 2023/04/17 19:31:23 - mmengine - INFO - Epoch(train) [30][300/391] lr: 1.0000e-01 eta: 0:31:59 time: 0.0342 data_time: 0.0034 memory: 227 loss: 1.9587 student.loss: 0.1180 distill.loss_1: 0.2604 distill.loss_2: 0.3159 distill.loss_3: 1.2644 2023/04/17 19:31:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:31:27 - mmengine - INFO - Saving checkpoint at 30 epochs 2023/04/17 19:31:37 - mmengine - INFO - Epoch(val) [30][79/79] accuracy/top1: 91.2100 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:31:40 - mmengine - INFO - Epoch(train) [31][100/391] lr: 1.0000e-01 eta: 0:32:01 time: 0.0352 data_time: 0.0034 memory: 227 loss: 2.0256 student.loss: 0.1598 distill.loss_1: 0.2680 distill.loss_2: 0.3197 distill.loss_3: 1.2781 2023/04/17 19:31:43 - mmengine - INFO - Epoch(train) [31][200/391] lr: 1.0000e-01 eta: 0:32:03 time: 0.0285 data_time: 0.0043 memory: 227 loss: 1.9069 student.loss: 0.1328 distill.loss_1: 0.2591 distill.loss_2: 0.3194 distill.loss_3: 1.1956 2023/04/17 19:31:46 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:31:48 - mmengine - INFO - Epoch(train) [31][300/391] lr: 1.0000e-01 eta: 0:32:10 time: 0.0558 data_time: 0.0034 memory: 227 loss: 2.0700 student.loss: 0.2169 distill.loss_1: 0.2596 distill.loss_2: 0.3139 distill.loss_3: 1.2797 2023/04/17 19:31:52 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:31:52 - mmengine - INFO - Saving checkpoint at 31 epochs 2023/04/17 19:31:59 - mmengine - INFO - Epoch(val) [31][79/79] accuracy/top1: 90.7400 teacher.accuracy/top1: 95.4400data_time: 0.0036 time: 0.0099 2023/04/17 19:32:03 - mmengine - INFO - Epoch(train) [32][100/391] lr: 1.0000e-01 eta: 0:32:20 time: 0.0509 data_time: 0.0042 memory: 227 loss: 1.8421 student.loss: 0.1128 distill.loss_1: 0.2448 distill.loss_2: 0.3065 distill.loss_3: 1.1781 2023/04/17 19:32:08 - mmengine - INFO - Epoch(train) [32][200/391] lr: 1.0000e-01 eta: 0:32:30 time: 0.0508 data_time: 0.0037 memory: 227 loss: 2.0042 student.loss: 0.1694 distill.loss_1: 0.2510 distill.loss_2: 0.3128 distill.loss_3: 1.2709 2023/04/17 19:32:13 - mmengine - INFO - Epoch(train) [32][300/391] lr: 1.0000e-01 eta: 0:32:37 time: 0.0410 data_time: 0.0034 memory: 227 loss: 2.1274 student.loss: 0.2105 distill.loss_1: 0.2609 distill.loss_2: 0.3168 distill.loss_3: 1.3392 2023/04/17 19:32:20 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:32:20 - mmengine - INFO - Saving checkpoint at 32 epochs 2023/04/17 19:32:32 - mmengine - INFO - Epoch(val) [32][79/79] accuracy/top1: 90.7900 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0099 2023/04/17 19:32:36 - mmengine - INFO - Epoch(train) [33][100/391] lr: 1.0000e-01 eta: 0:33:01 time: 0.0695 data_time: 0.0035 memory: 227 loss: 1.9402 student.loss: 0.1388 distill.loss_1: 0.2580 distill.loss_2: 0.3191 distill.loss_3: 1.2243 2023/04/17 19:32:41 - mmengine - INFO - Epoch(train) [33][200/391] lr: 1.0000e-01 eta: 0:33:04 time: 0.0563 data_time: 0.0034 memory: 227 loss: 2.0879 student.loss: 0.1956 distill.loss_1: 0.2592 distill.loss_2: 0.3142 distill.loss_3: 1.3189 2023/04/17 19:32:46 - mmengine - INFO - Epoch(train) [33][300/391] lr: 1.0000e-01 eta: 0:33:12 time: 0.0392 data_time: 0.0039 memory: 227 loss: 2.0267 student.loss: 0.1867 distill.loss_1: 0.2473 distill.loss_2: 0.3100 distill.loss_3: 1.2828 2023/04/17 19:32:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:32:49 - mmengine - INFO - Saving checkpoint at 33 epochs 2023/04/17 19:32:56 - mmengine - INFO - Epoch(val) [33][79/79] accuracy/top1: 91.0100 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0108 2023/04/17 19:33:02 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:33:02 - mmengine - INFO - Epoch(train) [34][100/391] lr: 1.0000e-01 eta: 0:33:21 time: 0.0538 data_time: 0.0037 memory: 227 loss: 1.9149 student.loss: 0.1344 distill.loss_1: 0.2592 distill.loss_2: 0.3155 distill.loss_3: 1.2057 2023/04/17 19:33:05 - mmengine - INFO - Epoch(train) [34][200/391] lr: 1.0000e-01 eta: 0:33:21 time: 0.0341 data_time: 0.0036 memory: 227 loss: 1.8947 student.loss: 0.1049 distill.loss_1: 0.2646 distill.loss_2: 0.3179 distill.loss_3: 1.2072 2023/04/17 19:33:09 - mmengine - INFO - Epoch(train) [34][300/391] lr: 1.0000e-01 eta: 0:33:21 time: 0.0860 data_time: 0.0034 memory: 227 loss: 1.8924 student.loss: 0.1348 distill.loss_1: 0.2582 distill.loss_2: 0.3144 distill.loss_3: 1.1849 2023/04/17 19:33:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:33:13 - mmengine - INFO - Saving checkpoint at 34 epochs 2023/04/17 19:33:21 - mmengine - INFO - Epoch(val) [34][79/79] accuracy/top1: 90.8800 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:33:25 - mmengine - INFO - Epoch(train) [35][100/391] lr: 1.0000e-01 eta: 0:33:23 time: 0.0324 data_time: 0.0039 memory: 227 loss: 1.9880 student.loss: 0.1677 distill.loss_1: 0.2525 distill.loss_2: 0.3129 distill.loss_3: 1.2549 2023/04/17 19:33:29 - mmengine - INFO - Epoch(train) [35][200/391] lr: 1.0000e-01 eta: 0:33:26 time: 0.0564 data_time: 0.0041 memory: 227 loss: 1.9993 student.loss: 0.1556 distill.loss_1: 0.2554 distill.loss_2: 0.3134 distill.loss_3: 1.2749 2023/04/17 19:33:34 - mmengine - INFO - Epoch(train) [35][300/391] lr: 1.0000e-01 eta: 0:33:33 time: 0.0475 data_time: 0.0040 memory: 227 loss: 2.2089 student.loss: 0.2757 distill.loss_1: 0.2621 distill.loss_2: 0.3144 distill.loss_3: 1.3567 2023/04/17 19:33:38 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:33:38 - mmengine - INFO - Saving checkpoint at 35 epochs 2023/04/17 19:33:44 - mmengine - INFO - Epoch(val) [35][79/79] accuracy/top1: 90.1600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0097 2023/04/17 19:33:50 - mmengine - INFO - Epoch(train) [36][100/391] lr: 1.0000e-01 eta: 0:33:42 time: 0.0564 data_time: 0.0036 memory: 227 loss: 1.9034 student.loss: 0.1119 distill.loss_1: 0.2547 distill.loss_2: 0.3151 distill.loss_3: 1.2217 2023/04/17 19:33:54 - mmengine - INFO - Epoch(train) [36][200/391] lr: 1.0000e-01 eta: 0:33:44 time: 0.0361 data_time: 0.0035 memory: 227 loss: 1.8798 student.loss: 0.1220 distill.loss_1: 0.2563 distill.loss_2: 0.3085 distill.loss_3: 1.1930 2023/04/17 19:33:59 - mmengine - INFO - Epoch(train) [36][300/391] lr: 1.0000e-01 eta: 0:33:47 time: 0.0323 data_time: 0.0039 memory: 227 loss: 1.7573 student.loss: 0.0910 distill.loss_1: 0.2469 distill.loss_2: 0.3052 distill.loss_3: 1.1142 2023/04/17 19:33:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:34:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:34:03 - mmengine - INFO - Saving checkpoint at 36 epochs 2023/04/17 19:34:11 - mmengine - INFO - Epoch(val) [36][79/79] accuracy/top1: 90.7900 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:34:16 - mmengine - INFO - Epoch(train) [37][100/391] lr: 1.0000e-01 eta: 0:33:55 time: 0.0548 data_time: 0.0038 memory: 227 loss: 1.8562 student.loss: 0.0736 distill.loss_1: 0.2597 distill.loss_2: 0.3154 distill.loss_3: 1.2075 2023/04/17 19:34:21 - mmengine - INFO - Epoch(train) [37][200/391] lr: 1.0000e-01 eta: 0:34:01 time: 0.0551 data_time: 0.0037 memory: 227 loss: 1.8267 student.loss: 0.1212 distill.loss_1: 0.2529 distill.loss_2: 0.3094 distill.loss_3: 1.1433 2023/04/17 19:34:25 - mmengine - INFO - Epoch(train) [37][300/391] lr: 1.0000e-01 eta: 0:33:58 time: 0.0339 data_time: 0.0034 memory: 227 loss: 2.0287 student.loss: 0.1351 distill.loss_1: 0.2551 distill.loss_2: 0.3173 distill.loss_3: 1.3211 2023/04/17 19:34:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:34:29 - mmengine - INFO - Saving checkpoint at 37 epochs 2023/04/17 19:34:37 - mmengine - INFO - Epoch(val) [37][79/79] accuracy/top1: 92.1300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 19:34:40 - mmengine - INFO - Epoch(train) [38][100/391] lr: 1.0000e-01 eta: 0:33:57 time: 0.0340 data_time: 0.0041 memory: 227 loss: 1.9767 student.loss: 0.1651 distill.loss_1: 0.2478 distill.loss_2: 0.3077 distill.loss_3: 1.2560 2023/04/17 19:34:44 - mmengine - INFO - Epoch(train) [38][200/391] lr: 1.0000e-01 eta: 0:33:54 time: 0.0635 data_time: 0.0039 memory: 227 loss: 1.9178 student.loss: 0.1369 distill.loss_1: 0.2508 distill.loss_2: 0.3053 distill.loss_3: 1.2247 2023/04/17 19:34:48 - mmengine - INFO - Epoch(train) [38][300/391] lr: 1.0000e-01 eta: 0:33:56 time: 0.0549 data_time: 0.0037 memory: 227 loss: 1.9684 student.loss: 0.1339 distill.loss_1: 0.2561 distill.loss_2: 0.3102 distill.loss_3: 1.2682 2023/04/17 19:34:53 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:34:53 - mmengine - INFO - Saving checkpoint at 38 epochs 2023/04/17 19:35:01 - mmengine - INFO - Epoch(val) [38][79/79] accuracy/top1: 90.4000 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 19:35:06 - mmengine - INFO - Epoch(train) [39][100/391] lr: 1.0000e-01 eta: 0:34:06 time: 0.0562 data_time: 0.0036 memory: 227 loss: 1.8419 student.loss: 0.1458 distill.loss_1: 0.2425 distill.loss_2: 0.2975 distill.loss_3: 1.1560 2023/04/17 19:35:08 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:35:10 - mmengine - INFO - Epoch(train) [39][200/391] lr: 1.0000e-01 eta: 0:34:08 time: 0.0227 data_time: 0.0038 memory: 227 loss: 2.1548 student.loss: 0.2462 distill.loss_1: 0.2622 distill.loss_2: 0.3118 distill.loss_3: 1.3346 2023/04/17 19:35:13 - mmengine - INFO - Epoch(train) [39][300/391] lr: 1.0000e-01 eta: 0:34:04 time: 0.0503 data_time: 0.0041 memory: 227 loss: 2.0181 student.loss: 0.1876 distill.loss_1: 0.2533 distill.loss_2: 0.3102 distill.loss_3: 1.2670 2023/04/17 19:35:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:35:22 - mmengine - INFO - Saving checkpoint at 39 epochs 2023/04/17 19:35:29 - mmengine - INFO - Epoch(val) [39][79/79] accuracy/top1: 91.0300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 19:35:33 - mmengine - INFO - Epoch(train) [40][100/391] lr: 1.0000e-01 eta: 0:34:19 time: 0.0349 data_time: 0.0040 memory: 227 loss: 1.9453 student.loss: 0.1452 distill.loss_1: 0.2487 distill.loss_2: 0.3025 distill.loss_3: 1.2489 2023/04/17 19:35:38 - mmengine - INFO - Epoch(train) [40][200/391] lr: 1.0000e-01 eta: 0:34:23 time: 0.0543 data_time: 0.0035 memory: 227 loss: 1.8964 student.loss: 0.1299 distill.loss_1: 0.2428 distill.loss_2: 0.3024 distill.loss_3: 1.2214 2023/04/17 19:35:43 - mmengine - INFO - Epoch(train) [40][300/391] lr: 1.0000e-01 eta: 0:34:28 time: 0.0367 data_time: 0.0035 memory: 227 loss: 1.8330 student.loss: 0.1029 distill.loss_1: 0.2624 distill.loss_2: 0.3124 distill.loss_3: 1.1554 2023/04/17 19:35:46 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:35:46 - mmengine - INFO - Saving checkpoint at 40 epochs 2023/04/17 19:35:52 - mmengine - INFO - Epoch(val) [40][79/79] accuracy/top1: 91.0600 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0098 2023/04/17 19:35:55 - mmengine - INFO - Epoch(train) [41][100/391] lr: 1.0000e-01 eta: 0:34:19 time: 0.0234 data_time: 0.0039 memory: 227 loss: 1.9666 student.loss: 0.1212 distill.loss_1: 0.2490 distill.loss_2: 0.3103 distill.loss_3: 1.2861 2023/04/17 19:35:58 - mmengine - INFO - Epoch(train) [41][200/391] lr: 1.0000e-01 eta: 0:34:12 time: 0.0231 data_time: 0.0038 memory: 227 loss: 1.8771 student.loss: 0.1142 distill.loss_1: 0.2424 distill.loss_2: 0.3014 distill.loss_3: 1.2191 2023/04/17 19:36:06 - mmengine - INFO - Epoch(train) [41][300/391] lr: 1.0000e-01 eta: 0:34:30 time: 0.0944 data_time: 0.0036 memory: 227 loss: 1.9398 student.loss: 0.1464 distill.loss_1: 0.2568 distill.loss_2: 0.3121 distill.loss_3: 1.2245 2023/04/17 19:36:12 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:36:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:36:15 - mmengine - INFO - Saving checkpoint at 41 epochs 2023/04/17 19:36:32 - mmengine - INFO - Epoch(val) [41][79/79] accuracy/top1: 91.1800 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0096 2023/04/17 19:36:42 - mmengine - INFO - Epoch(train) [42][100/391] lr: 1.0000e-01 eta: 0:35:11 time: 0.0989 data_time: 0.0035 memory: 227 loss: 1.9185 student.loss: 0.1417 distill.loss_1: 0.2423 distill.loss_2: 0.3058 distill.loss_3: 1.2286 2023/04/17 19:36:52 - mmengine - INFO - Epoch(train) [42][200/391] lr: 1.0000e-01 eta: 0:35:33 time: 0.0986 data_time: 0.0034 memory: 227 loss: 1.9299 student.loss: 0.1234 distill.loss_1: 0.2625 distill.loss_2: 0.3161 distill.loss_3: 1.2279 2023/04/17 19:37:02 - mmengine - INFO - Epoch(train) [42][300/391] lr: 1.0000e-01 eta: 0:35:53 time: 0.0982 data_time: 0.0035 memory: 227 loss: 1.8912 student.loss: 0.1200 distill.loss_1: 0.2485 distill.loss_2: 0.3072 distill.loss_3: 1.2156 2023/04/17 19:37:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:37:11 - mmengine - INFO - Saving checkpoint at 42 epochs 2023/04/17 19:37:20 - mmengine - INFO - Epoch(val) [42][79/79] accuracy/top1: 90.1700 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0095 2023/04/17 19:37:23 - mmengine - INFO - Epoch(train) [43][100/391] lr: 1.0000e-01 eta: 0:36:04 time: 0.0222 data_time: 0.0036 memory: 227 loss: 1.9586 student.loss: 0.1476 distill.loss_1: 0.2491 distill.loss_2: 0.3129 distill.loss_3: 1.2489 2023/04/17 19:37:25 - mmengine - INFO - Epoch(train) [43][200/391] lr: 1.0000e-01 eta: 0:35:56 time: 0.0229 data_time: 0.0037 memory: 227 loss: 1.9249 student.loss: 0.1228 distill.loss_1: 0.2557 distill.loss_2: 0.3115 distill.loss_3: 1.2348 2023/04/17 19:37:27 - mmengine - INFO - Epoch(train) [43][300/391] lr: 1.0000e-01 eta: 0:35:49 time: 0.0240 data_time: 0.0040 memory: 227 loss: 2.0028 student.loss: 0.1372 distill.loss_1: 0.2552 distill.loss_2: 0.3095 distill.loss_3: 1.3010 2023/04/17 19:37:30 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:37:30 - mmengine - INFO - Saving checkpoint at 43 epochs 2023/04/17 19:37:36 - mmengine - INFO - Epoch(val) [43][79/79] accuracy/top1: 91.7300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 19:37:38 - mmengine - INFO - Epoch(train) [44][100/391] lr: 1.0000e-01 eta: 0:35:35 time: 0.0241 data_time: 0.0040 memory: 227 loss: 1.8299 student.loss: 0.1264 distill.loss_1: 0.2386 distill.loss_2: 0.3031 distill.loss_3: 1.1618 2023/04/17 19:37:41 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:37:42 - mmengine - INFO - Epoch(train) [44][200/391] lr: 1.0000e-01 eta: 0:35:33 time: 0.0888 data_time: 0.0039 memory: 227 loss: 2.0856 student.loss: 0.2172 distill.loss_1: 0.2585 distill.loss_2: 0.3065 distill.loss_3: 1.3034 2023/04/17 19:37:48 - mmengine - INFO - Epoch(train) [44][300/391] lr: 1.0000e-01 eta: 0:35:40 time: 0.0253 data_time: 0.0038 memory: 227 loss: 1.8723 student.loss: 0.1413 distill.loss_1: 0.2496 distill.loss_2: 0.3064 distill.loss_3: 1.1751 2023/04/17 19:37:52 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:37:52 - mmengine - INFO - Saving checkpoint at 44 epochs 2023/04/17 19:37:59 - mmengine - INFO - Epoch(val) [44][79/79] accuracy/top1: 90.2100 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:38:01 - mmengine - INFO - Epoch(train) [45][100/391] lr: 1.0000e-01 eta: 0:35:31 time: 0.0224 data_time: 0.0035 memory: 227 loss: 2.0575 student.loss: 0.2424 distill.loss_1: 0.2578 distill.loss_2: 0.3055 distill.loss_3: 1.2519 2023/04/17 19:38:03 - mmengine - INFO - Epoch(train) [45][200/391] lr: 1.0000e-01 eta: 0:35:24 time: 0.0222 data_time: 0.0035 memory: 227 loss: 1.7563 student.loss: 0.0723 distill.loss_1: 0.2422 distill.loss_2: 0.3065 distill.loss_3: 1.1353 2023/04/17 19:38:07 - mmengine - INFO - Epoch(train) [45][300/391] lr: 1.0000e-01 eta: 0:35:19 time: 0.0392 data_time: 0.0036 memory: 227 loss: 1.8994 student.loss: 0.1660 distill.loss_1: 0.2454 distill.loss_2: 0.3059 distill.loss_3: 1.1821 2023/04/17 19:38:10 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:38:10 - mmengine - INFO - Saving checkpoint at 45 epochs 2023/04/17 19:38:17 - mmengine - INFO - Epoch(val) [45][79/79] accuracy/top1: 90.9100 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0092 2023/04/17 19:38:20 - mmengine - INFO - Epoch(train) [46][100/391] lr: 1.0000e-01 eta: 0:35:10 time: 0.0300 data_time: 0.0034 memory: 227 loss: 1.9368 student.loss: 0.1641 distill.loss_1: 0.2450 distill.loss_2: 0.3097 distill.loss_3: 1.2180 2023/04/17 19:38:23 - mmengine - INFO - Epoch(train) [46][200/391] lr: 1.0000e-01 eta: 0:35:05 time: 0.0299 data_time: 0.0038 memory: 227 loss: 1.7979 student.loss: 0.1182 distill.loss_1: 0.2459 distill.loss_2: 0.3061 distill.loss_3: 1.1277 2023/04/17 19:38:26 - mmengine - INFO - Epoch(train) [46][300/391] lr: 1.0000e-01 eta: 0:35:00 time: 0.0301 data_time: 0.0038 memory: 227 loss: 2.0796 student.loss: 0.2385 distill.loss_1: 0.2505 distill.loss_2: 0.3094 distill.loss_3: 1.2812 2023/04/17 19:38:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:38:29 - mmengine - INFO - Saving checkpoint at 46 epochs 2023/04/17 19:38:37 - mmengine - INFO - Epoch(val) [46][79/79] accuracy/top1: 91.5500 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0107 2023/04/17 19:38:37 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:38:40 - mmengine - INFO - Epoch(train) [47][100/391] lr: 1.0000e-01 eta: 0:34:51 time: 0.0304 data_time: 0.0041 memory: 227 loss: 1.7550 student.loss: 0.1049 distill.loss_1: 0.2332 distill.loss_2: 0.2999 distill.loss_3: 1.1170 2023/04/17 19:38:43 - mmengine - INFO - Epoch(train) [47][200/391] lr: 1.0000e-01 eta: 0:34:46 time: 0.0296 data_time: 0.0034 memory: 227 loss: 1.8164 student.loss: 0.1172 distill.loss_1: 0.2477 distill.loss_2: 0.3053 distill.loss_3: 1.1462 2023/04/17 19:38:46 - mmengine - INFO - Epoch(train) [47][300/391] lr: 1.0000e-01 eta: 0:34:41 time: 0.0306 data_time: 0.0035 memory: 227 loss: 2.0986 student.loss: 0.2318 distill.loss_1: 0.2485 distill.loss_2: 0.3062 distill.loss_3: 1.3121 2023/04/17 19:38:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:38:49 - mmengine - INFO - Saving checkpoint at 47 epochs 2023/04/17 19:38:56 - mmengine - INFO - Epoch(val) [47][79/79] accuracy/top1: 90.7200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 19:38:59 - mmengine - INFO - Epoch(train) [48][100/391] lr: 1.0000e-01 eta: 0:34:32 time: 0.0282 data_time: 0.0036 memory: 227 loss: 1.9137 student.loss: 0.1573 distill.loss_1: 0.2532 distill.loss_2: 0.3046 distill.loss_3: 1.1986 2023/04/17 19:39:02 - mmengine - INFO - Epoch(train) [48][200/391] lr: 1.0000e-01 eta: 0:34:27 time: 0.0301 data_time: 0.0036 memory: 227 loss: 1.9147 student.loss: 0.1005 distill.loss_1: 0.2484 distill.loss_2: 0.3096 distill.loss_3: 1.2561 2023/04/17 19:39:05 - mmengine - INFO - Epoch(train) [48][300/391] lr: 1.0000e-01 eta: 0:34:22 time: 0.0289 data_time: 0.0036 memory: 227 loss: 2.0108 student.loss: 0.2071 distill.loss_1: 0.2383 distill.loss_2: 0.3014 distill.loss_3: 1.2640 2023/04/17 19:39:08 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:39:08 - mmengine - INFO - Saving checkpoint at 48 epochs 2023/04/17 19:39:15 - mmengine - INFO - Epoch(val) [48][79/79] accuracy/top1: 91.2300 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0100 2023/04/17 19:39:19 - mmengine - INFO - Epoch(train) [49][100/391] lr: 1.0000e-01 eta: 0:34:14 time: 0.0542 data_time: 0.0040 memory: 227 loss: 1.8857 student.loss: 0.1262 distill.loss_1: 0.2428 distill.loss_2: 0.3016 distill.loss_3: 1.2150 2023/04/17 19:39:22 - mmengine - INFO - Epoch(train) [49][200/391] lr: 1.0000e-01 eta: 0:34:09 time: 0.0289 data_time: 0.0037 memory: 227 loss: 1.8678 student.loss: 0.1223 distill.loss_1: 0.2545 distill.loss_2: 0.3106 distill.loss_3: 1.1804 2023/04/17 19:39:23 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:39:25 - mmengine - INFO - Epoch(train) [49][300/391] lr: 1.0000e-01 eta: 0:34:04 time: 0.0287 data_time: 0.0040 memory: 227 loss: 1.7997 student.loss: 0.1210 distill.loss_1: 0.2417 distill.loss_2: 0.2983 distill.loss_3: 1.1387 2023/04/17 19:39:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:39:28 - mmengine - INFO - Saving checkpoint at 49 epochs 2023/04/17 19:39:35 - mmengine - INFO - Epoch(val) [49][79/79] accuracy/top1: 88.8700 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0098 2023/04/17 19:39:38 - mmengine - INFO - Epoch(train) [50][100/391] lr: 1.0000e-01 eta: 0:33:57 time: 0.0319 data_time: 0.0041 memory: 227 loss: 1.7616 student.loss: 0.0856 distill.loss_1: 0.2381 distill.loss_2: 0.2993 distill.loss_3: 1.1386 2023/04/17 19:39:41 - mmengine - INFO - Epoch(train) [50][200/391] lr: 1.0000e-01 eta: 0:33:52 time: 0.0351 data_time: 0.0046 memory: 227 loss: 1.9586 student.loss: 0.1576 distill.loss_1: 0.2550 distill.loss_2: 0.3080 distill.loss_3: 1.2380 2023/04/17 19:39:44 - mmengine - INFO - Epoch(train) [50][300/391] lr: 1.0000e-01 eta: 0:33:48 time: 0.0285 data_time: 0.0038 memory: 227 loss: 1.9075 student.loss: 0.1510 distill.loss_1: 0.2551 distill.loss_2: 0.3098 distill.loss_3: 1.1917 2023/04/17 19:39:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:39:47 - mmengine - INFO - Saving checkpoint at 50 epochs 2023/04/17 19:39:54 - mmengine - INFO - Epoch(val) [50][79/79] accuracy/top1: 92.2300 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0111 2023/04/17 19:39:58 - mmengine - INFO - Epoch(train) [51][100/391] lr: 1.0000e-01 eta: 0:33:40 time: 0.0321 data_time: 0.0037 memory: 227 loss: 1.7523 student.loss: 0.0833 distill.loss_1: 0.2458 distill.loss_2: 0.3036 distill.loss_3: 1.1196 2023/04/17 19:40:01 - mmengine - INFO - Epoch(train) [51][200/391] lr: 1.0000e-01 eta: 0:33:35 time: 0.0292 data_time: 0.0044 memory: 227 loss: 1.8052 student.loss: 0.0707 distill.loss_1: 0.2464 distill.loss_2: 0.2997 distill.loss_3: 1.1884 2023/04/17 19:40:04 - mmengine - INFO - Epoch(train) [51][300/391] lr: 1.0000e-01 eta: 0:33:31 time: 0.0361 data_time: 0.0040 memory: 227 loss: 1.7922 student.loss: 0.0833 distill.loss_1: 0.2468 distill.loss_2: 0.3009 distill.loss_3: 1.1612 2023/04/17 19:40:07 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:40:07 - mmengine - INFO - Saving checkpoint at 51 epochs 2023/04/17 19:40:14 - mmengine - INFO - Epoch(val) [51][79/79] accuracy/top1: 90.1600 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0090 2023/04/17 19:40:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:40:18 - mmengine - INFO - Epoch(train) [52][100/391] lr: 1.0000e-01 eta: 0:33:24 time: 0.0346 data_time: 0.0034 memory: 227 loss: 1.7594 student.loss: 0.1037 distill.loss_1: 0.2430 distill.loss_2: 0.3032 distill.loss_3: 1.1095 2023/04/17 19:40:22 - mmengine - INFO - Epoch(train) [52][200/391] lr: 1.0000e-01 eta: 0:33:21 time: 0.0346 data_time: 0.0035 memory: 227 loss: 2.0560 student.loss: 0.1943 distill.loss_1: 0.2448 distill.loss_2: 0.3038 distill.loss_3: 1.3131 2023/04/17 19:40:25 - mmengine - INFO - Epoch(train) [52][300/391] lr: 1.0000e-01 eta: 0:33:17 time: 0.0319 data_time: 0.0036 memory: 227 loss: 1.8710 student.loss: 0.1258 distill.loss_1: 0.2383 distill.loss_2: 0.2993 distill.loss_3: 1.2076 2023/04/17 19:40:28 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:40:28 - mmengine - INFO - Saving checkpoint at 52 epochs 2023/04/17 19:40:35 - mmengine - INFO - Epoch(val) [52][79/79] accuracy/top1: 91.2800 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0106 2023/04/17 19:40:39 - mmengine - INFO - Epoch(train) [53][100/391] lr: 1.0000e-01 eta: 0:33:10 time: 0.0289 data_time: 0.0035 memory: 227 loss: 1.8050 student.loss: 0.0970 distill.loss_1: 0.2363 distill.loss_2: 0.3019 distill.loss_3: 1.1699 2023/04/17 19:40:42 - mmengine - INFO - Epoch(train) [53][200/391] lr: 1.0000e-01 eta: 0:33:06 time: 0.0338 data_time: 0.0051 memory: 227 loss: 2.0092 student.loss: 0.1716 distill.loss_1: 0.2483 distill.loss_2: 0.3012 distill.loss_3: 1.2881 2023/04/17 19:40:45 - mmengine - INFO - Epoch(train) [53][300/391] lr: 1.0000e-01 eta: 0:33:02 time: 0.0333 data_time: 0.0042 memory: 227 loss: 2.0462 student.loss: 0.2088 distill.loss_1: 0.2476 distill.loss_2: 0.3086 distill.loss_3: 1.2811 2023/04/17 19:40:48 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:40:48 - mmengine - INFO - Saving checkpoint at 53 epochs 2023/04/17 19:40:55 - mmengine - INFO - Epoch(val) [53][79/79] accuracy/top1: 91.7900 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0104 2023/04/17 19:40:59 - mmengine - INFO - Epoch(train) [54][100/391] lr: 1.0000e-01 eta: 0:32:55 time: 0.0292 data_time: 0.0041 memory: 227 loss: 1.7577 student.loss: 0.0753 distill.loss_1: 0.2512 distill.loss_2: 0.3080 distill.loss_3: 1.1231 2023/04/17 19:41:02 - mmengine - INFO - Epoch(train) [54][200/391] lr: 1.0000e-01 eta: 0:32:51 time: 0.0300 data_time: 0.0036 memory: 227 loss: 1.8561 student.loss: 0.1495 distill.loss_1: 0.2418 distill.loss_2: 0.3035 distill.loss_3: 1.1613 2023/04/17 19:41:04 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:41:05 - mmengine - INFO - Epoch(train) [54][300/391] lr: 1.0000e-01 eta: 0:32:47 time: 0.0367 data_time: 0.0038 memory: 227 loss: 1.8959 student.loss: 0.1694 distill.loss_1: 0.2324 distill.loss_2: 0.2968 distill.loss_3: 1.1974 2023/04/17 19:41:08 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:41:08 - mmengine - INFO - Saving checkpoint at 54 epochs 2023/04/17 19:41:16 - mmengine - INFO - Epoch(val) [54][79/79] accuracy/top1: 91.8300 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0097 2023/04/17 19:41:19 - mmengine - INFO - Epoch(train) [55][100/391] lr: 1.0000e-01 eta: 0:32:41 time: 0.0303 data_time: 0.0043 memory: 227 loss: 1.7923 student.loss: 0.0905 distill.loss_1: 0.2337 distill.loss_2: 0.2968 distill.loss_3: 1.1713 2023/04/17 19:41:23 - mmengine - INFO - Epoch(train) [55][200/391] lr: 1.0000e-01 eta: 0:32:37 time: 0.0298 data_time: 0.0034 memory: 227 loss: 1.8966 student.loss: 0.1558 distill.loss_1: 0.2469 distill.loss_2: 0.3006 distill.loss_3: 1.1932 2023/04/17 19:41:26 - mmengine - INFO - Epoch(train) [55][300/391] lr: 1.0000e-01 eta: 0:32:33 time: 0.0310 data_time: 0.0041 memory: 227 loss: 1.8962 student.loss: 0.1422 distill.loss_1: 0.2500 distill.loss_2: 0.3042 distill.loss_3: 1.1999 2023/04/17 19:41:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:41:29 - mmengine - INFO - Saving checkpoint at 55 epochs 2023/04/17 19:41:37 - mmengine - INFO - Epoch(val) [55][79/79] accuracy/top1: 90.7300 teacher.accuracy/top1: 95.4400data_time: 0.0038 time: 0.0105 2023/04/17 19:41:41 - mmengine - INFO - Epoch(train) [56][100/391] lr: 1.0000e-01 eta: 0:32:28 time: 0.0333 data_time: 0.0045 memory: 227 loss: 1.7322 student.loss: 0.1074 distill.loss_1: 0.2243 distill.loss_2: 0.2894 distill.loss_3: 1.1111 2023/04/17 19:41:45 - mmengine - INFO - Epoch(train) [56][200/391] lr: 1.0000e-01 eta: 0:32:25 time: 0.0338 data_time: 0.0044 memory: 227 loss: 1.8362 student.loss: 0.1481 distill.loss_1: 0.2391 distill.loss_2: 0.2958 distill.loss_3: 1.1532 2023/04/17 19:41:53 - mmengine - INFO - Epoch(train) [56][300/391] lr: 1.0000e-01 eta: 0:32:34 time: 0.0825 data_time: 0.0038 memory: 227 loss: 1.9684 student.loss: 0.1778 distill.loss_1: 0.2461 distill.loss_2: 0.3059 distill.loss_3: 1.2387 2023/04/17 19:41:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:41:59 - mmengine - INFO - Saving checkpoint at 56 epochs 2023/04/17 19:42:07 - mmengine - INFO - Epoch(val) [56][79/79] accuracy/top1: 91.1400 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0110 2023/04/17 19:42:10 - mmengine - INFO - Epoch(train) [57][100/391] lr: 1.0000e-01 eta: 0:32:35 time: 0.0351 data_time: 0.0056 memory: 227 loss: 1.9311 student.loss: 0.1513 distill.loss_1: 0.2434 distill.loss_2: 0.3030 distill.loss_3: 1.2334 2023/04/17 19:42:10 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:42:14 - mmengine - INFO - Epoch(train) [57][200/391] lr: 1.0000e-01 eta: 0:32:31 time: 0.0299 data_time: 0.0036 memory: 227 loss: 1.8889 student.loss: 0.1586 distill.loss_1: 0.2492 distill.loss_2: 0.2986 distill.loss_3: 1.1826 2023/04/17 19:42:17 - mmengine - INFO - Epoch(train) [57][300/391] lr: 1.0000e-01 eta: 0:32:27 time: 0.0313 data_time: 0.0041 memory: 227 loss: 1.7873 student.loss: 0.0752 distill.loss_1: 0.2514 distill.loss_2: 0.3020 distill.loss_3: 1.1586 2023/04/17 19:42:20 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:42:20 - mmengine - INFO - Saving checkpoint at 57 epochs 2023/04/17 19:42:28 - mmengine - INFO - Epoch(val) [57][79/79] accuracy/top1: 91.0500 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0109 2023/04/17 19:42:31 - mmengine - INFO - Epoch(train) [58][100/391] lr: 1.0000e-01 eta: 0:32:21 time: 0.0356 data_time: 0.0045 memory: 227 loss: 1.8860 student.loss: 0.1465 distill.loss_1: 0.2456 distill.loss_2: 0.3002 distill.loss_3: 1.1938 2023/04/17 19:42:35 - mmengine - INFO - Epoch(train) [58][200/391] lr: 1.0000e-01 eta: 0:32:17 time: 0.0371 data_time: 0.0045 memory: 227 loss: 1.9833 student.loss: 0.1642 distill.loss_1: 0.2539 distill.loss_2: 0.3078 distill.loss_3: 1.2574 2023/04/17 19:42:38 - mmengine - INFO - Epoch(train) [58][300/391] lr: 1.0000e-01 eta: 0:32:13 time: 0.0343 data_time: 0.0043 memory: 227 loss: 1.8252 student.loss: 0.1041 distill.loss_1: 0.2436 distill.loss_2: 0.3026 distill.loss_3: 1.1750 2023/04/17 19:42:41 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:42:41 - mmengine - INFO - Saving checkpoint at 58 epochs 2023/04/17 19:42:49 - mmengine - INFO - Epoch(val) [58][79/79] accuracy/top1: 91.1900 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0103 2023/04/17 19:42:52 - mmengine - INFO - Epoch(train) [59][100/391] lr: 1.0000e-01 eta: 0:32:06 time: 0.0326 data_time: 0.0046 memory: 227 loss: 2.0413 student.loss: 0.2312 distill.loss_1: 0.2487 distill.loss_2: 0.3059 distill.loss_3: 1.2556 2023/04/17 19:42:56 - mmengine - INFO - Epoch(train) [59][200/391] lr: 1.0000e-01 eta: 0:32:03 time: 0.0345 data_time: 0.0040 memory: 227 loss: 1.8784 student.loss: 0.1488 distill.loss_1: 0.2461 distill.loss_2: 0.2990 distill.loss_3: 1.1845 2023/04/17 19:42:59 - mmengine - INFO - Epoch(train) [59][300/391] lr: 1.0000e-01 eta: 0:31:59 time: 0.0348 data_time: 0.0044 memory: 227 loss: 1.7994 student.loss: 0.1056 distill.loss_1: 0.2430 distill.loss_2: 0.2982 distill.loss_3: 1.1526 2023/04/17 19:43:00 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:43:02 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:43:02 - mmengine - INFO - Saving checkpoint at 59 epochs 2023/04/17 19:43:10 - mmengine - INFO - Epoch(val) [59][79/79] accuracy/top1: 90.4300 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0112 2023/04/17 19:43:13 - mmengine - INFO - Epoch(train) [60][100/391] lr: 1.0000e-01 eta: 0:31:52 time: 0.0330 data_time: 0.0038 memory: 227 loss: 1.9113 student.loss: 0.2008 distill.loss_1: 0.2418 distill.loss_2: 0.2983 distill.loss_3: 1.1705 2023/04/17 19:43:17 - mmengine - INFO - Epoch(train) [60][200/391] lr: 1.0000e-01 eta: 0:31:48 time: 0.0346 data_time: 0.0043 memory: 227 loss: 1.8571 student.loss: 0.1473 distill.loss_1: 0.2502 distill.loss_2: 0.3006 distill.loss_3: 1.1590 2023/04/17 19:43:20 - mmengine - INFO - Epoch(train) [60][300/391] lr: 1.0000e-01 eta: 0:31:44 time: 0.0304 data_time: 0.0049 memory: 227 loss: 1.7335 student.loss: 0.0636 distill.loss_1: 0.2442 distill.loss_2: 0.3025 distill.loss_3: 1.1232 2023/04/17 19:43:23 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:43:23 - mmengine - INFO - Saving checkpoint at 60 epochs 2023/04/17 19:43:31 - mmengine - INFO - Epoch(val) [60][79/79] accuracy/top1: 91.9600 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0100 2023/04/17 19:43:34 - mmengine - INFO - Epoch(train) [61][100/391] lr: 1.0000e-01 eta: 0:31:38 time: 0.0298 data_time: 0.0035 memory: 227 loss: 1.7575 student.loss: 0.0829 distill.loss_1: 0.2365 distill.loss_2: 0.2994 distill.loss_3: 1.1387 2023/04/17 19:43:38 - mmengine - INFO - Epoch(train) [61][200/391] lr: 1.0000e-01 eta: 0:31:34 time: 0.0324 data_time: 0.0041 memory: 227 loss: 1.7903 student.loss: 0.0947 distill.loss_1: 0.2446 distill.loss_2: 0.3017 distill.loss_3: 1.1493 2023/04/17 19:43:41 - mmengine - INFO - Epoch(train) [61][300/391] lr: 1.0000e-01 eta: 0:31:31 time: 0.0342 data_time: 0.0039 memory: 227 loss: 1.8507 student.loss: 0.1259 distill.loss_1: 0.2437 distill.loss_2: 0.2982 distill.loss_3: 1.1829 2023/04/17 19:43:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:43:45 - mmengine - INFO - Saving checkpoint at 61 epochs 2023/04/17 19:43:52 - mmengine - INFO - Epoch(val) [61][79/79] accuracy/top1: 90.3100 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0099 2023/04/17 19:43:56 - mmengine - INFO - Epoch(train) [62][100/391] lr: 1.0000e-01 eta: 0:31:26 time: 0.0361 data_time: 0.0039 memory: 227 loss: 1.7947 student.loss: 0.0790 distill.loss_1: 0.2431 distill.loss_2: 0.3004 distill.loss_3: 1.1721 2023/04/17 19:43:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:43:59 - mmengine - INFO - Epoch(train) [62][200/391] lr: 1.0000e-01 eta: 0:31:22 time: 0.0330 data_time: 0.0041 memory: 227 loss: 1.7638 student.loss: 0.0524 distill.loss_1: 0.2318 distill.loss_2: 0.2975 distill.loss_3: 1.1821 2023/04/17 19:44:03 - mmengine - INFO - Epoch(train) [62][300/391] lr: 1.0000e-01 eta: 0:31:18 time: 0.0340 data_time: 0.0037 memory: 227 loss: 1.8631 student.loss: 0.1449 distill.loss_1: 0.2411 distill.loss_2: 0.2955 distill.loss_3: 1.1817 2023/04/17 19:44:06 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:44:06 - mmengine - INFO - Saving checkpoint at 62 epochs 2023/04/17 19:44:14 - mmengine - INFO - Epoch(val) [62][79/79] accuracy/top1: 90.9500 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0098 2023/04/17 19:44:18 - mmengine - INFO - Epoch(train) [63][100/391] lr: 1.0000e-01 eta: 0:31:13 time: 0.0328 data_time: 0.0039 memory: 227 loss: 1.7636 student.loss: 0.1061 distill.loss_1: 0.2353 distill.loss_2: 0.2938 distill.loss_3: 1.1285 2023/04/17 19:44:24 - mmengine - INFO - Epoch(train) [63][200/391] lr: 1.0000e-01 eta: 0:31:16 time: 0.0778 data_time: 0.0036 memory: 227 loss: 2.0068 student.loss: 0.2087 distill.loss_1: 0.2424 distill.loss_2: 0.2986 distill.loss_3: 1.2571 2023/04/17 19:44:29 - mmengine - INFO - Epoch(train) [63][300/391] lr: 1.0000e-01 eta: 0:31:16 time: 0.0415 data_time: 0.0159 memory: 227 loss: 1.8064 student.loss: 0.0982 distill.loss_1: 0.2454 distill.loss_2: 0.3011 distill.loss_3: 1.1617 2023/04/17 19:44:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:44:33 - mmengine - INFO - Saving checkpoint at 63 epochs 2023/04/17 19:44:41 - mmengine - INFO - Epoch(val) [63][79/79] accuracy/top1: 90.1400 teacher.accuracy/top1: 95.4400data_time: 0.0041 time: 0.0121 2023/04/17 19:44:45 - mmengine - INFO - Epoch(train) [64][100/391] lr: 1.0000e-01 eta: 0:31:11 time: 0.0403 data_time: 0.0045 memory: 227 loss: 1.8032 student.loss: 0.1041 distill.loss_1: 0.2405 distill.loss_2: 0.3033 distill.loss_3: 1.1554 2023/04/17 19:44:48 - mmengine - INFO - Epoch(train) [64][200/391] lr: 1.0000e-01 eta: 0:31:08 time: 0.0336 data_time: 0.0047 memory: 227 loss: 1.8448 student.loss: 0.1217 distill.loss_1: 0.2412 distill.loss_2: 0.2953 distill.loss_3: 1.1867 2023/04/17 19:44:52 - mmengine - INFO - Epoch(train) [64][300/391] lr: 1.0000e-01 eta: 0:31:04 time: 0.0343 data_time: 0.0049 memory: 227 loss: 1.8812 student.loss: 0.1306 distill.loss_1: 0.2419 distill.loss_2: 0.2956 distill.loss_3: 1.2131 2023/04/17 19:44:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:44:55 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:44:55 - mmengine - INFO - Saving checkpoint at 64 epochs 2023/04/17 19:45:02 - mmengine - INFO - Epoch(val) [64][79/79] accuracy/top1: 91.9400 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0102 2023/04/17 19:45:06 - mmengine - INFO - Epoch(train) [65][100/391] lr: 1.0000e-01 eta: 0:30:58 time: 0.0334 data_time: 0.0042 memory: 227 loss: 1.9701 student.loss: 0.1947 distill.loss_1: 0.2438 distill.loss_2: 0.2989 distill.loss_3: 1.2328 2023/04/17 19:45:09 - mmengine - INFO - Epoch(train) [65][200/391] lr: 1.0000e-01 eta: 0:30:54 time: 0.0355 data_time: 0.0043 memory: 227 loss: 1.7884 student.loss: 0.1102 distill.loss_1: 0.2368 distill.loss_2: 0.2953 distill.loss_3: 1.1461 2023/04/17 19:45:13 - mmengine - INFO - Epoch(train) [65][300/391] lr: 1.0000e-01 eta: 0:30:50 time: 0.0329 data_time: 0.0044 memory: 227 loss: 1.7986 student.loss: 0.1039 distill.loss_1: 0.2412 distill.loss_2: 0.3001 distill.loss_3: 1.1535 2023/04/17 19:45:16 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:45:16 - mmengine - INFO - Saving checkpoint at 65 epochs 2023/04/17 19:45:24 - mmengine - INFO - Epoch(val) [65][79/79] accuracy/top1: 91.3600 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 19:45:28 - mmengine - INFO - Epoch(train) [66][100/391] lr: 1.0000e-01 eta: 0:30:44 time: 0.0348 data_time: 0.0044 memory: 227 loss: 2.0222 student.loss: 0.2048 distill.loss_1: 0.2383 distill.loss_2: 0.2988 distill.loss_3: 1.2802 2023/04/17 19:45:31 - mmengine - INFO - Epoch(train) [66][200/391] lr: 1.0000e-01 eta: 0:30:40 time: 0.0374 data_time: 0.0052 memory: 227 loss: 1.8122 student.loss: 0.0932 distill.loss_1: 0.2543 distill.loss_2: 0.3035 distill.loss_3: 1.1612 2023/04/17 19:45:35 - mmengine - INFO - Epoch(train) [66][300/391] lr: 1.0000e-01 eta: 0:30:37 time: 0.0343 data_time: 0.0040 memory: 227 loss: 1.8628 student.loss: 0.1382 distill.loss_1: 0.2390 distill.loss_2: 0.2972 distill.loss_3: 1.1883 2023/04/17 19:45:38 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:45:38 - mmengine - INFO - Saving checkpoint at 66 epochs 2023/04/17 19:45:45 - mmengine - INFO - Epoch(val) [66][79/79] accuracy/top1: 91.8400 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0098 2023/04/17 19:45:49 - mmengine - INFO - Epoch(train) [67][100/391] lr: 1.0000e-01 eta: 0:30:31 time: 0.0340 data_time: 0.0046 memory: 227 loss: 2.0302 student.loss: 0.1766 distill.loss_1: 0.2505 distill.loss_2: 0.3045 distill.loss_3: 1.2987 2023/04/17 19:45:53 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:45:53 - mmengine - INFO - Epoch(train) [67][200/391] lr: 1.0000e-01 eta: 0:30:29 time: 0.0350 data_time: 0.0042 memory: 227 loss: 1.8908 student.loss: 0.1529 distill.loss_1: 0.2424 distill.loss_2: 0.2978 distill.loss_3: 1.1977 2023/04/17 19:45:56 - mmengine - INFO - Epoch(train) [67][300/391] lr: 1.0000e-01 eta: 0:30:25 time: 0.0358 data_time: 0.0045 memory: 227 loss: 1.7610 student.loss: 0.1018 distill.loss_1: 0.2345 distill.loss_2: 0.2917 distill.loss_3: 1.1330 2023/04/17 19:46:00 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:46:00 - mmengine - INFO - Saving checkpoint at 67 epochs 2023/04/17 19:46:07 - mmengine - INFO - Epoch(val) [67][79/79] accuracy/top1: 91.1700 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0105 2023/04/17 19:46:11 - mmengine - INFO - Epoch(train) [68][100/391] lr: 1.0000e-01 eta: 0:30:19 time: 0.0381 data_time: 0.0043 memory: 227 loss: 1.8422 student.loss: 0.0547 distill.loss_1: 0.2402 distill.loss_2: 0.2986 distill.loss_3: 1.2487 2023/04/17 19:46:14 - mmengine - INFO - Epoch(train) [68][200/391] lr: 1.0000e-01 eta: 0:30:16 time: 0.0370 data_time: 0.0046 memory: 227 loss: 1.7557 student.loss: 0.1393 distill.loss_1: 0.2416 distill.loss_2: 0.2926 distill.loss_3: 1.0822 2023/04/17 19:46:18 - mmengine - INFO - Epoch(train) [68][300/391] lr: 1.0000e-01 eta: 0:30:12 time: 0.0384 data_time: 0.0043 memory: 227 loss: 1.8931 student.loss: 0.1307 distill.loss_1: 0.2393 distill.loss_2: 0.3009 distill.loss_3: 1.2223 2023/04/17 19:46:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:46:21 - mmengine - INFO - Saving checkpoint at 68 epochs 2023/04/17 19:46:28 - mmengine - INFO - Epoch(val) [68][79/79] accuracy/top1: 91.3500 teacher.accuracy/top1: 95.4400data_time: 0.0038 time: 0.0114 2023/04/17 19:46:32 - mmengine - INFO - Epoch(train) [69][100/391] lr: 1.0000e-01 eta: 0:30:06 time: 0.0330 data_time: 0.0044 memory: 227 loss: 1.9481 student.loss: 0.1391 distill.loss_1: 0.2404 distill.loss_2: 0.2969 distill.loss_3: 1.2717 2023/04/17 19:46:35 - mmengine - INFO - Epoch(train) [69][200/391] lr: 1.0000e-01 eta: 0:30:03 time: 0.0320 data_time: 0.0046 memory: 227 loss: 1.7386 student.loss: 0.0876 distill.loss_1: 0.2306 distill.loss_2: 0.2957 distill.loss_3: 1.1246 2023/04/17 19:46:39 - mmengine - INFO - Epoch(train) [69][300/391] lr: 1.0000e-01 eta: 0:29:59 time: 0.0347 data_time: 0.0048 memory: 227 loss: 1.9765 student.loss: 0.1708 distill.loss_1: 0.2421 distill.loss_2: 0.3012 distill.loss_3: 1.2624 2023/04/17 19:46:42 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:46:42 - mmengine - INFO - Saving checkpoint at 69 epochs 2023/04/17 19:46:50 - mmengine - INFO - Epoch(val) [69][79/79] accuracy/top1: 92.3400 teacher.accuracy/top1: 95.4400data_time: 0.0042 time: 0.0128 2023/04/17 19:46:51 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:46:53 - mmengine - INFO - Epoch(train) [70][100/391] lr: 1.0000e-01 eta: 0:29:53 time: 0.0359 data_time: 0.0043 memory: 227 loss: 1.8745 student.loss: 0.1780 distill.loss_1: 0.2356 distill.loss_2: 0.2892 distill.loss_3: 1.1717 2023/04/17 19:46:57 - mmengine - INFO - Epoch(train) [70][200/391] lr: 1.0000e-01 eta: 0:29:49 time: 0.0369 data_time: 0.0043 memory: 227 loss: 1.7993 student.loss: 0.1006 distill.loss_1: 0.2451 distill.loss_2: 0.2998 distill.loss_3: 1.1538 2023/04/17 19:47:01 - mmengine - INFO - Epoch(train) [70][300/391] lr: 1.0000e-01 eta: 0:29:46 time: 0.0369 data_time: 0.0050 memory: 227 loss: 1.7927 student.loss: 0.1521 distill.loss_1: 0.2301 distill.loss_2: 0.2916 distill.loss_3: 1.1189 2023/04/17 19:47:04 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:47:04 - mmengine - INFO - Saving checkpoint at 70 epochs 2023/04/17 19:47:12 - mmengine - INFO - Epoch(val) [70][79/79] accuracy/top1: 91.7500 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0108 2023/04/17 19:47:16 - mmengine - INFO - Epoch(train) [71][100/391] lr: 1.0000e-01 eta: 0:29:40 time: 0.0377 data_time: 0.0040 memory: 227 loss: 1.8333 student.loss: 0.0888 distill.loss_1: 0.2399 distill.loss_2: 0.2938 distill.loss_3: 1.2108 2023/04/17 19:47:19 - mmengine - INFO - Epoch(train) [71][200/391] lr: 1.0000e-01 eta: 0:29:37 time: 0.0328 data_time: 0.0042 memory: 227 loss: 1.9229 student.loss: 0.1773 distill.loss_1: 0.2373 distill.loss_2: 0.2958 distill.loss_3: 1.2125 2023/04/17 19:47:23 - mmengine - INFO - Epoch(train) [71][300/391] lr: 1.0000e-01 eta: 0:29:34 time: 0.0369 data_time: 0.0035 memory: 227 loss: 1.8438 student.loss: 0.1235 distill.loss_1: 0.2292 distill.loss_2: 0.2890 distill.loss_3: 1.2021 2023/04/17 19:47:26 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:47:26 - mmengine - INFO - Saving checkpoint at 71 epochs 2023/04/17 19:47:34 - mmengine - INFO - Epoch(val) [71][79/79] accuracy/top1: 91.0700 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0097 2023/04/17 19:47:38 - mmengine - INFO - Epoch(train) [72][100/391] lr: 1.0000e-01 eta: 0:29:29 time: 0.0329 data_time: 0.0045 memory: 227 loss: 1.7832 student.loss: 0.0909 distill.loss_1: 0.2393 distill.loss_2: 0.2982 distill.loss_3: 1.1548 2023/04/17 19:47:42 - mmengine - INFO - Epoch(train) [72][200/391] lr: 1.0000e-01 eta: 0:29:25 time: 0.0363 data_time: 0.0043 memory: 227 loss: 1.8060 student.loss: 0.1015 distill.loss_1: 0.2454 distill.loss_2: 0.2975 distill.loss_3: 1.1616 2023/04/17 19:47:43 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:47:46 - mmengine - INFO - Epoch(train) [72][300/391] lr: 1.0000e-01 eta: 0:29:22 time: 0.0372 data_time: 0.0041 memory: 227 loss: 2.0345 student.loss: 0.2400 distill.loss_1: 0.2463 distill.loss_2: 0.3010 distill.loss_3: 1.2472 2023/04/17 19:47:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:47:49 - mmengine - INFO - Saving checkpoint at 72 epochs 2023/04/17 19:47:56 - mmengine - INFO - Epoch(val) [72][79/79] accuracy/top1: 91.7100 teacher.accuracy/top1: 95.4400data_time: 0.0038 time: 0.0107 2023/04/17 19:48:00 - mmengine - INFO - Epoch(train) [73][100/391] lr: 1.0000e-01 eta: 0:29:15 time: 0.0338 data_time: 0.0042 memory: 227 loss: 1.8036 student.loss: 0.0936 distill.loss_1: 0.2315 distill.loss_2: 0.2943 distill.loss_3: 1.1841 2023/04/17 19:48:04 - mmengine - INFO - Epoch(train) [73][200/391] lr: 1.0000e-01 eta: 0:29:12 time: 0.0345 data_time: 0.0043 memory: 227 loss: 1.9192 student.loss: 0.1747 distill.loss_1: 0.2433 distill.loss_2: 0.3016 distill.loss_3: 1.1997 2023/04/17 19:48:08 - mmengine - INFO - Epoch(train) [73][300/391] lr: 1.0000e-01 eta: 0:29:09 time: 0.0374 data_time: 0.0039 memory: 227 loss: 1.8524 student.loss: 0.1089 distill.loss_1: 0.2407 distill.loss_2: 0.2930 distill.loss_3: 1.2098 2023/04/17 19:48:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:48:11 - mmengine - INFO - Saving checkpoint at 73 epochs 2023/04/17 19:48:18 - mmengine - INFO - Epoch(val) [73][79/79] accuracy/top1: 91.0100 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0113 2023/04/17 19:48:22 - mmengine - INFO - Epoch(train) [74][100/391] lr: 1.0000e-01 eta: 0:29:03 time: 0.0366 data_time: 0.0045 memory: 227 loss: 1.8312 student.loss: 0.1260 distill.loss_1: 0.2294 distill.loss_2: 0.2950 distill.loss_3: 1.1807 2023/04/17 19:48:26 - mmengine - INFO - Epoch(train) [74][200/391] lr: 1.0000e-01 eta: 0:28:59 time: 0.0329 data_time: 0.0042 memory: 227 loss: 1.8063 student.loss: 0.1287 distill.loss_1: 0.2328 distill.loss_2: 0.2944 distill.loss_3: 1.1504 2023/04/17 19:48:29 - mmengine - INFO - Epoch(train) [74][300/391] lr: 1.0000e-01 eta: 0:28:56 time: 0.0328 data_time: 0.0040 memory: 227 loss: 1.9137 student.loss: 0.1433 distill.loss_1: 0.2384 distill.loss_2: 0.3021 distill.loss_3: 1.2299 2023/04/17 19:48:32 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:48:32 - mmengine - INFO - Saving checkpoint at 74 epochs 2023/04/17 19:48:40 - mmengine - INFO - Epoch(val) [74][79/79] accuracy/top1: 90.5000 teacher.accuracy/top1: 95.4400data_time: 0.0036 time: 0.0110 2023/04/17 19:48:43 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:48:44 - mmengine - INFO - Epoch(train) [75][100/391] lr: 1.0000e-01 eta: 0:28:50 time: 0.0378 data_time: 0.0042 memory: 227 loss: 1.8753 student.loss: 0.1498 distill.loss_1: 0.2435 distill.loss_2: 0.3000 distill.loss_3: 1.1820 2023/04/17 19:48:47 - mmengine - INFO - Epoch(train) [75][200/391] lr: 1.0000e-01 eta: 0:28:46 time: 0.0370 data_time: 0.0046 memory: 227 loss: 1.9018 student.loss: 0.1375 distill.loss_1: 0.2378 distill.loss_2: 0.2948 distill.loss_3: 1.2317 2023/04/17 19:48:51 - mmengine - INFO - Epoch(train) [75][300/391] lr: 1.0000e-01 eta: 0:28:43 time: 0.0369 data_time: 0.0043 memory: 227 loss: 1.8080 student.loss: 0.1136 distill.loss_1: 0.2355 distill.loss_2: 0.2911 distill.loss_3: 1.1678 2023/04/17 19:48:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:48:54 - mmengine - INFO - Saving checkpoint at 75 epochs 2023/04/17 19:49:02 - mmengine - INFO - Epoch(val) [75][79/79] accuracy/top1: 91.3100 teacher.accuracy/top1: 95.4400data_time: 0.0046 time: 0.0145 2023/04/17 19:49:06 - mmengine - INFO - Epoch(train) [76][100/391] lr: 1.0000e-01 eta: 0:28:37 time: 0.0398 data_time: 0.0041 memory: 227 loss: 1.8115 student.loss: 0.1102 distill.loss_1: 0.2322 distill.loss_2: 0.2961 distill.loss_3: 1.1729 2023/04/17 19:49:14 - mmengine - INFO - Epoch(train) [76][200/391] lr: 1.0000e-01 eta: 0:28:41 time: 0.0695 data_time: 0.0048 memory: 227 loss: 1.7158 student.loss: 0.0695 distill.loss_1: 0.2410 distill.loss_2: 0.2968 distill.loss_3: 1.1084 2023/04/17 19:49:18 - mmengine - INFO - Epoch(train) [76][300/391] lr: 1.0000e-01 eta: 0:28:39 time: 0.0389 data_time: 0.0045 memory: 227 loss: 1.8248 student.loss: 0.1278 distill.loss_1: 0.2345 distill.loss_2: 0.2928 distill.loss_3: 1.1697 2023/04/17 19:49:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:49:21 - mmengine - INFO - Saving checkpoint at 76 epochs 2023/04/17 19:49:29 - mmengine - INFO - Epoch(val) [76][79/79] accuracy/top1: 90.9300 teacher.accuracy/top1: 95.4400data_time: 0.0040 time: 0.0125 2023/04/17 19:49:33 - mmengine - INFO - Epoch(train) [77][100/391] lr: 1.0000e-01 eta: 0:28:32 time: 0.0339 data_time: 0.0043 memory: 227 loss: 1.8117 student.loss: 0.1213 distill.loss_1: 0.2354 distill.loss_2: 0.2973 distill.loss_3: 1.1575 2023/04/17 19:49:36 - mmengine - INFO - Epoch(train) [77][200/391] lr: 1.0000e-01 eta: 0:28:29 time: 0.0358 data_time: 0.0039 memory: 227 loss: 1.7770 student.loss: 0.1331 distill.loss_1: 0.2271 distill.loss_2: 0.2838 distill.loss_3: 1.1330 2023/04/17 19:49:39 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:49:40 - mmengine - INFO - Epoch(train) [77][300/391] lr: 1.0000e-01 eta: 0:28:25 time: 0.0373 data_time: 0.0041 memory: 227 loss: 1.8380 student.loss: 0.1159 distill.loss_1: 0.2412 distill.loss_2: 0.3015 distill.loss_3: 1.1794 2023/04/17 19:49:43 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:49:43 - mmengine - INFO - Saving checkpoint at 77 epochs 2023/04/17 19:49:50 - mmengine - INFO - Epoch(val) [77][79/79] accuracy/top1: 91.1800 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0101 2023/04/17 19:49:54 - mmengine - INFO - Epoch(train) [78][100/391] lr: 1.0000e-01 eta: 0:28:19 time: 0.0380 data_time: 0.0044 memory: 227 loss: 1.8078 student.loss: 0.1514 distill.loss_1: 0.2337 distill.loss_2: 0.2899 distill.loss_3: 1.1328 2023/04/17 19:49:58 - mmengine - INFO - Epoch(train) [78][200/391] lr: 1.0000e-01 eta: 0:28:15 time: 0.0387 data_time: 0.0044 memory: 227 loss: 1.7735 student.loss: 0.1206 distill.loss_1: 0.2336 distill.loss_2: 0.2891 distill.loss_3: 1.1301 2023/04/17 19:50:01 - mmengine - INFO - Epoch(train) [78][300/391] lr: 1.0000e-01 eta: 0:28:12 time: 0.0357 data_time: 0.0041 memory: 227 loss: 1.8083 student.loss: 0.1492 distill.loss_1: 0.2373 distill.loss_2: 0.2949 distill.loss_3: 1.1269 2023/04/17 19:50:05 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:50:05 - mmengine - INFO - Saving checkpoint at 78 epochs 2023/04/17 19:50:12 - mmengine - INFO - Epoch(val) [78][79/79] accuracy/top1: 92.3200 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:50:16 - mmengine - INFO - Epoch(train) [79][100/391] lr: 1.0000e-01 eta: 0:28:06 time: 0.0383 data_time: 0.0042 memory: 227 loss: 1.6956 student.loss: 0.0833 distill.loss_1: 0.2332 distill.loss_2: 0.2951 distill.loss_3: 1.0839 2023/04/17 19:50:20 - mmengine - INFO - Epoch(train) [79][200/391] lr: 1.0000e-01 eta: 0:28:03 time: 0.0374 data_time: 0.0041 memory: 227 loss: 1.7070 student.loss: 0.0943 distill.loss_1: 0.2372 distill.loss_2: 0.2932 distill.loss_3: 1.0824 2023/04/17 19:50:23 - mmengine - INFO - Epoch(train) [79][300/391] lr: 1.0000e-01 eta: 0:28:00 time: 0.0396 data_time: 0.0046 memory: 227 loss: 1.8645 student.loss: 0.1503 distill.loss_1: 0.2386 distill.loss_2: 0.2948 distill.loss_3: 1.1808 2023/04/17 19:50:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:50:27 - mmengine - INFO - Saving checkpoint at 79 epochs 2023/04/17 19:50:35 - mmengine - INFO - Epoch(val) [79][79/79] accuracy/top1: 91.3800 teacher.accuracy/top1: 95.4400data_time: 0.0040 time: 0.0108 2023/04/17 19:50:39 - mmengine - INFO - Epoch(train) [80][100/391] lr: 1.0000e-01 eta: 0:27:54 time: 0.0357 data_time: 0.0043 memory: 227 loss: 1.8955 student.loss: 0.1205 distill.loss_1: 0.2376 distill.loss_2: 0.2966 distill.loss_3: 1.2407 2023/04/17 19:50:40 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:50:43 - mmengine - INFO - Epoch(train) [80][200/391] lr: 1.0000e-01 eta: 0:27:50 time: 0.0338 data_time: 0.0044 memory: 227 loss: 1.7014 student.loss: 0.0716 distill.loss_1: 0.2435 distill.loss_2: 0.2945 distill.loss_3: 1.0917 2023/04/17 19:50:46 - mmengine - INFO - Epoch(train) [80][300/391] lr: 1.0000e-01 eta: 0:27:47 time: 0.0372 data_time: 0.0045 memory: 227 loss: 1.9081 student.loss: 0.1672 distill.loss_1: 0.2420 distill.loss_2: 0.2966 distill.loss_3: 1.2023 2023/04/17 19:50:50 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:50:50 - mmengine - INFO - Saving checkpoint at 80 epochs 2023/04/17 19:50:57 - mmengine - INFO - Epoch(val) [80][79/79] accuracy/top1: 91.4300 teacher.accuracy/top1: 95.4400data_time: 0.0043 time: 0.0119 2023/04/17 19:51:01 - mmengine - INFO - Epoch(train) [81][100/391] lr: 1.0000e-01 eta: 0:27:41 time: 0.0344 data_time: 0.0043 memory: 227 loss: 2.0285 student.loss: 0.2395 distill.loss_1: 0.2377 distill.loss_2: 0.2934 distill.loss_3: 1.2579 2023/04/17 19:51:04 - mmengine - INFO - Epoch(train) [81][200/391] lr: 1.0000e-01 eta: 0:27:38 time: 0.0383 data_time: 0.0040 memory: 227 loss: 1.6894 student.loss: 0.1008 distill.loss_1: 0.2338 distill.loss_2: 0.2874 distill.loss_3: 1.0674 2023/04/17 19:51:08 - mmengine - INFO - Epoch(train) [81][300/391] lr: 1.0000e-01 eta: 0:27:34 time: 0.0366 data_time: 0.0053 memory: 227 loss: 1.9150 student.loss: 0.1448 distill.loss_1: 0.2386 distill.loss_2: 0.2934 distill.loss_3: 1.2381 2023/04/17 19:51:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:51:12 - mmengine - INFO - Saving checkpoint at 81 epochs 2023/04/17 19:51:19 - mmengine - INFO - Epoch(val) [81][79/79] accuracy/top1: 91.3400 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:51:23 - mmengine - INFO - Epoch(train) [82][100/391] lr: 1.0000e-01 eta: 0:27:28 time: 0.0367 data_time: 0.0047 memory: 227 loss: 1.9893 student.loss: 0.1646 distill.loss_1: 0.2451 distill.loss_2: 0.2978 distill.loss_3: 1.2817 2023/04/17 19:51:27 - mmengine - INFO - Epoch(train) [82][200/391] lr: 1.0000e-01 eta: 0:27:25 time: 0.0339 data_time: 0.0045 memory: 227 loss: 1.6583 student.loss: 0.0622 distill.loss_1: 0.2373 distill.loss_2: 0.2922 distill.loss_3: 1.0667 2023/04/17 19:51:30 - mmengine - INFO - Epoch(train) [82][300/391] lr: 1.0000e-01 eta: 0:27:22 time: 0.0395 data_time: 0.0046 memory: 227 loss: 1.9462 student.loss: 0.1744 distill.loss_1: 0.2390 distill.loss_2: 0.2911 distill.loss_3: 1.2417 2023/04/17 19:51:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:51:34 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:51:34 - mmengine - INFO - Saving checkpoint at 82 epochs 2023/04/17 19:51:45 - mmengine - INFO - Epoch(val) [82][79/79] accuracy/top1: 89.1200 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0110 2023/04/17 19:51:49 - mmengine - INFO - Epoch(train) [83][100/391] lr: 1.0000e-01 eta: 0:27:17 time: 0.0367 data_time: 0.0044 memory: 227 loss: 1.7495 student.loss: 0.0821 distill.loss_1: 0.2383 distill.loss_2: 0.2932 distill.loss_3: 1.1359 2023/04/17 19:51:53 - mmengine - INFO - Epoch(train) [83][200/391] lr: 1.0000e-01 eta: 0:27:14 time: 0.0378 data_time: 0.0045 memory: 227 loss: 1.7803 student.loss: 0.1267 distill.loss_1: 0.2396 distill.loss_2: 0.2956 distill.loss_3: 1.1183 2023/04/17 19:51:57 - mmengine - INFO - Epoch(train) [83][300/391] lr: 1.0000e-01 eta: 0:27:10 time: 0.0384 data_time: 0.0045 memory: 227 loss: 1.8546 student.loss: 0.1079 distill.loss_1: 0.2427 distill.loss_2: 0.2978 distill.loss_3: 1.2062 2023/04/17 19:52:00 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:52:00 - mmengine - INFO - Saving checkpoint at 83 epochs 2023/04/17 19:52:08 - mmengine - INFO - Epoch(val) [83][79/79] accuracy/top1: 91.6500 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0106 2023/04/17 19:52:12 - mmengine - INFO - Epoch(train) [84][100/391] lr: 1.0000e-01 eta: 0:27:04 time: 0.0351 data_time: 0.0044 memory: 227 loss: 1.9088 student.loss: 0.1788 distill.loss_1: 0.2373 distill.loss_2: 0.2890 distill.loss_3: 1.2037 2023/04/17 19:52:16 - mmengine - INFO - Epoch(train) [84][200/391] lr: 1.0000e-01 eta: 0:27:01 time: 0.0351 data_time: 0.0049 memory: 227 loss: 1.6802 student.loss: 0.0707 distill.loss_1: 0.2296 distill.loss_2: 0.2876 distill.loss_3: 1.0923 2023/04/17 19:52:19 - mmengine - INFO - Epoch(train) [84][300/391] lr: 1.0000e-01 eta: 0:26:57 time: 0.0362 data_time: 0.0037 memory: 227 loss: 1.7433 student.loss: 0.0990 distill.loss_1: 0.2351 distill.loss_2: 0.2916 distill.loss_3: 1.1176 2023/04/17 19:52:22 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:52:22 - mmengine - INFO - Saving checkpoint at 84 epochs 2023/04/17 19:52:30 - mmengine - INFO - Epoch(val) [84][79/79] accuracy/top1: 90.1900 teacher.accuracy/top1: 95.4400data_time: 0.0039 time: 0.0108 2023/04/17 19:52:34 - mmengine - INFO - Epoch(train) [85][100/391] lr: 1.0000e-01 eta: 0:26:50 time: 0.0335 data_time: 0.0040 memory: 227 loss: 1.9100 student.loss: 0.1582 distill.loss_1: 0.2353 distill.loss_2: 0.2913 distill.loss_3: 1.2252 2023/04/17 19:52:36 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:52:37 - mmengine - INFO - Epoch(train) [85][200/391] lr: 1.0000e-01 eta: 0:26:47 time: 0.0350 data_time: 0.0045 memory: 227 loss: 1.7350 student.loss: 0.1040 distill.loss_1: 0.2317 distill.loss_2: 0.2929 distill.loss_3: 1.1064 2023/04/17 19:52:41 - mmengine - INFO - Epoch(train) [85][300/391] lr: 1.0000e-01 eta: 0:26:43 time: 0.0374 data_time: 0.0044 memory: 227 loss: 1.6147 student.loss: 0.0519 distill.loss_1: 0.2327 distill.loss_2: 0.2895 distill.loss_3: 1.0406 2023/04/17 19:52:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:52:44 - mmengine - INFO - Saving checkpoint at 85 epochs 2023/04/17 19:52:51 - mmengine - INFO - Epoch(val) [85][79/79] accuracy/top1: 90.9000 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0104 2023/04/17 19:52:55 - mmengine - INFO - Epoch(train) [86][100/391] lr: 1.0000e-01 eta: 0:26:37 time: 0.0353 data_time: 0.0051 memory: 227 loss: 1.8083 student.loss: 0.1067 distill.loss_1: 0.2339 distill.loss_2: 0.2926 distill.loss_3: 1.1751 2023/04/17 19:52:59 - mmengine - INFO - Epoch(train) [86][200/391] lr: 1.0000e-01 eta: 0:26:33 time: 0.0344 data_time: 0.0042 memory: 227 loss: 1.7983 student.loss: 0.1032 distill.loss_1: 0.2392 distill.loss_2: 0.2992 distill.loss_3: 1.1567 2023/04/17 19:53:03 - mmengine - INFO - Epoch(train) [86][300/391] lr: 1.0000e-01 eta: 0:26:30 time: 0.0392 data_time: 0.0041 memory: 227 loss: 1.6879 student.loss: 0.0557 distill.loss_1: 0.2326 distill.loss_2: 0.2921 distill.loss_3: 1.1075 2023/04/17 19:53:06 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:53:06 - mmengine - INFO - Saving checkpoint at 86 epochs 2023/04/17 19:53:17 - mmengine - INFO - Epoch(val) [86][79/79] accuracy/top1: 90.4400 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0664 2023/04/17 19:53:22 - mmengine - INFO - Epoch(train) [87][100/391] lr: 1.0000e-01 eta: 0:26:25 time: 0.0367 data_time: 0.0060 memory: 227 loss: 1.8032 student.loss: 0.1335 distill.loss_1: 0.2410 distill.loss_2: 0.2944 distill.loss_3: 1.1343 2023/04/17 19:53:26 - mmengine - INFO - Epoch(train) [87][200/391] lr: 1.0000e-01 eta: 0:26:22 time: 0.0374 data_time: 0.0046 memory: 227 loss: 1.8396 student.loss: 0.1517 distill.loss_1: 0.2305 distill.loss_2: 0.2877 distill.loss_3: 1.1697 2023/04/17 19:53:29 - mmengine - INFO - Epoch(train) [87][300/391] lr: 1.0000e-01 eta: 0:26:18 time: 0.0347 data_time: 0.0042 memory: 227 loss: 1.7056 student.loss: 0.0741 distill.loss_1: 0.2403 distill.loss_2: 0.2941 distill.loss_3: 1.0971 2023/04/17 19:53:32 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:53:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:53:33 - mmengine - INFO - Saving checkpoint at 87 epochs 2023/04/17 19:53:41 - mmengine - INFO - Epoch(val) [87][79/79] accuracy/top1: 91.7600 teacher.accuracy/top1: 95.4400data_time: 0.0039 time: 0.0113 2023/04/17 19:53:45 - mmengine - INFO - Epoch(train) [88][100/391] lr: 1.0000e-01 eta: 0:26:13 time: 0.0356 data_time: 0.0055 memory: 227 loss: 1.7857 student.loss: 0.1344 distill.loss_1: 0.2407 distill.loss_2: 0.2919 distill.loss_3: 1.1186 2023/04/17 19:53:48 - mmengine - INFO - Epoch(train) [88][200/391] lr: 1.0000e-01 eta: 0:26:09 time: 0.0365 data_time: 0.0047 memory: 227 loss: 1.6902 student.loss: 0.0830 distill.loss_1: 0.2363 distill.loss_2: 0.2856 distill.loss_3: 1.0854 2023/04/17 19:53:52 - mmengine - INFO - Epoch(train) [88][300/391] lr: 1.0000e-01 eta: 0:26:06 time: 0.0345 data_time: 0.0047 memory: 227 loss: 1.8915 student.loss: 0.1635 distill.loss_1: 0.2310 distill.loss_2: 0.2887 distill.loss_3: 1.2083 2023/04/17 19:53:55 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:53:55 - mmengine - INFO - Saving checkpoint at 88 epochs 2023/04/17 19:54:03 - mmengine - INFO - Epoch(val) [88][79/79] accuracy/top1: 90.9000 teacher.accuracy/top1: 95.4400data_time: 0.0038 time: 0.0114 2023/04/17 19:54:06 - mmengine - INFO - Epoch(train) [89][100/391] lr: 1.0000e-01 eta: 0:25:59 time: 0.0348 data_time: 0.0047 memory: 227 loss: 1.8737 student.loss: 0.1288 distill.loss_1: 0.2414 distill.loss_2: 0.2958 distill.loss_3: 1.2076 2023/04/17 19:54:10 - mmengine - INFO - Epoch(train) [89][200/391] lr: 1.0000e-01 eta: 0:25:55 time: 0.0338 data_time: 0.0050 memory: 227 loss: 1.7540 student.loss: 0.0916 distill.loss_1: 0.2412 distill.loss_2: 0.2942 distill.loss_3: 1.1270 2023/04/17 19:54:13 - mmengine - INFO - Epoch(train) [89][300/391] lr: 1.0000e-01 eta: 0:25:51 time: 0.0357 data_time: 0.0050 memory: 227 loss: 1.7561 student.loss: 0.0715 distill.loss_1: 0.2331 distill.loss_2: 0.2906 distill.loss_3: 1.1609 2023/04/17 19:54:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:54:17 - mmengine - INFO - Saving checkpoint at 89 epochs 2023/04/17 19:54:25 - mmengine - INFO - Epoch(val) [89][79/79] accuracy/top1: 91.8400 teacher.accuracy/top1: 95.4400data_time: 0.0038 time: 0.0112 2023/04/17 19:54:28 - mmengine - INFO - Epoch(train) [90][100/391] lr: 1.0000e-01 eta: 0:25:44 time: 0.0268 data_time: 0.0037 memory: 227 loss: 1.8400 student.loss: 0.1229 distill.loss_1: 0.2324 distill.loss_2: 0.2862 distill.loss_3: 1.1986 2023/04/17 19:54:30 - mmengine - INFO - Epoch(train) [90][200/391] lr: 1.0000e-01 eta: 0:25:39 time: 0.0249 data_time: 0.0039 memory: 227 loss: 1.8584 student.loss: 0.1509 distill.loss_1: 0.2310 distill.loss_2: 0.2891 distill.loss_3: 1.1874 2023/04/17 19:54:30 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:54:33 - mmengine - INFO - Epoch(train) [90][300/391] lr: 1.0000e-01 eta: 0:25:35 time: 0.0347 data_time: 0.0066 memory: 227 loss: 1.8454 student.loss: 0.1275 distill.loss_1: 0.2356 distill.loss_2: 0.2905 distill.loss_3: 1.1918 2023/04/17 19:54:36 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:54:36 - mmengine - INFO - Saving checkpoint at 90 epochs 2023/04/17 19:54:43 - mmengine - INFO - Epoch(val) [90][79/79] accuracy/top1: 91.7700 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0101 2023/04/17 19:54:46 - mmengine - INFO - Epoch(train) [91][100/391] lr: 1.0000e-01 eta: 0:25:26 time: 0.0230 data_time: 0.0042 memory: 227 loss: 1.7403 student.loss: 0.1408 distill.loss_1: 0.2309 distill.loss_2: 0.2834 distill.loss_3: 1.0852 2023/04/17 19:54:48 - mmengine - INFO - Epoch(train) [91][200/391] lr: 1.0000e-01 eta: 0:25:21 time: 0.0237 data_time: 0.0040 memory: 227 loss: 1.8655 student.loss: 0.1850 distill.loss_1: 0.2419 distill.loss_2: 0.2964 distill.loss_3: 1.1422 2023/04/17 19:54:54 - mmengine - INFO - Epoch(train) [91][300/391] lr: 1.0000e-01 eta: 0:25:21 time: 0.0886 data_time: 0.0038 memory: 227 loss: 1.8285 student.loss: 0.1111 distill.loss_1: 0.2455 distill.loss_2: 0.2982 distill.loss_3: 1.1737 2023/04/17 19:54:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:54:58 - mmengine - INFO - Saving checkpoint at 91 epochs 2023/04/17 19:55:04 - mmengine - INFO - Epoch(val) [91][79/79] accuracy/top1: 91.5900 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:55:07 - mmengine - INFO - Epoch(train) [92][100/391] lr: 1.0000e-01 eta: 0:25:14 time: 0.0234 data_time: 0.0035 memory: 227 loss: 1.7948 student.loss: 0.1656 distill.loss_1: 0.2352 distill.loss_2: 0.2877 distill.loss_3: 1.1064 2023/04/17 19:55:09 - mmengine - INFO - Epoch(train) [92][200/391] lr: 1.0000e-01 eta: 0:25:09 time: 0.0228 data_time: 0.0035 memory: 227 loss: 1.9687 student.loss: 0.2418 distill.loss_1: 0.2308 distill.loss_2: 0.2863 distill.loss_3: 1.2099 2023/04/17 19:55:11 - mmengine - INFO - Epoch(train) [92][300/391] lr: 1.0000e-01 eta: 0:25:04 time: 0.0229 data_time: 0.0034 memory: 227 loss: 1.8150 student.loss: 0.1203 distill.loss_1: 0.2395 distill.loss_2: 0.2951 distill.loss_3: 1.1601 2023/04/17 19:55:14 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:55:14 - mmengine - INFO - Saving checkpoint at 92 epochs 2023/04/17 19:55:19 - mmengine - INFO - Epoch(val) [92][79/79] accuracy/top1: 90.8900 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:55:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:55:22 - mmengine - INFO - Epoch(train) [93][100/391] lr: 1.0000e-01 eta: 0:24:55 time: 0.0239 data_time: 0.0040 memory: 227 loss: 1.9433 student.loss: 0.2121 distill.loss_1: 0.2360 distill.loss_2: 0.2927 distill.loss_3: 1.2025 2023/04/17 19:55:25 - mmengine - INFO - Epoch(train) [93][200/391] lr: 1.0000e-01 eta: 0:24:50 time: 0.0234 data_time: 0.0035 memory: 227 loss: 1.8269 student.loss: 0.1470 distill.loss_1: 0.2317 distill.loss_2: 0.2946 distill.loss_3: 1.1537 2023/04/17 19:55:27 - mmengine - INFO - Epoch(train) [93][300/391] lr: 1.0000e-01 eta: 0:24:45 time: 0.0233 data_time: 0.0041 memory: 227 loss: 1.7529 student.loss: 0.1023 distill.loss_1: 0.2433 distill.loss_2: 0.2928 distill.loss_3: 1.1146 2023/04/17 19:55:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:55:29 - mmengine - INFO - Saving checkpoint at 93 epochs 2023/04/17 19:55:36 - mmengine - INFO - Epoch(val) [93][79/79] accuracy/top1: 91.1700 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 19:55:39 - mmengine - INFO - Epoch(train) [94][100/391] lr: 1.0000e-01 eta: 0:24:36 time: 0.0233 data_time: 0.0039 memory: 227 loss: 1.7813 student.loss: 0.1127 distill.loss_1: 0.2319 distill.loss_2: 0.2864 distill.loss_3: 1.1504 2023/04/17 19:55:41 - mmengine - INFO - Epoch(train) [94][200/391] lr: 1.0000e-01 eta: 0:24:31 time: 0.0231 data_time: 0.0037 memory: 227 loss: 1.7416 student.loss: 0.0887 distill.loss_1: 0.2340 distill.loss_2: 0.2900 distill.loss_3: 1.1289 2023/04/17 19:55:43 - mmengine - INFO - Epoch(train) [94][300/391] lr: 1.0000e-01 eta: 0:24:27 time: 0.0230 data_time: 0.0036 memory: 227 loss: 1.8848 student.loss: 0.1264 distill.loss_1: 0.2348 distill.loss_2: 0.2957 distill.loss_3: 1.2279 2023/04/17 19:55:45 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:55:45 - mmengine - INFO - Saving checkpoint at 94 epochs 2023/04/17 19:55:51 - mmengine - INFO - Epoch(val) [94][79/79] accuracy/top1: 91.7900 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:55:54 - mmengine - INFO - Epoch(train) [95][100/391] lr: 1.0000e-01 eta: 0:24:18 time: 0.0238 data_time: 0.0036 memory: 227 loss: 1.8661 student.loss: 0.1156 distill.loss_1: 0.2358 distill.loss_2: 0.2899 distill.loss_3: 1.2247 2023/04/17 19:55:57 - mmengine - INFO - Epoch(train) [95][200/391] lr: 1.0000e-01 eta: 0:24:14 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.7702 student.loss: 0.0907 distill.loss_1: 0.2519 distill.loss_2: 0.2969 distill.loss_3: 1.1307 2023/04/17 19:55:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:55:59 - mmengine - INFO - Epoch(train) [95][300/391] lr: 1.0000e-01 eta: 0:24:09 time: 0.0235 data_time: 0.0035 memory: 227 loss: 1.7862 student.loss: 0.1081 distill.loss_1: 0.2362 distill.loss_2: 0.2921 distill.loss_3: 1.1498 2023/04/17 19:56:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:56:01 - mmengine - INFO - Saving checkpoint at 95 epochs 2023/04/17 19:56:08 - mmengine - INFO - Epoch(val) [95][79/79] accuracy/top1: 91.4200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:56:11 - mmengine - INFO - Epoch(train) [96][100/391] lr: 1.0000e-01 eta: 0:24:00 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.7277 student.loss: 0.0951 distill.loss_1: 0.2417 distill.loss_2: 0.2936 distill.loss_3: 1.0973 2023/04/17 19:56:13 - mmengine - INFO - Epoch(train) [96][200/391] lr: 1.0000e-01 eta: 0:23:56 time: 0.0234 data_time: 0.0037 memory: 227 loss: 1.5558 student.loss: 0.0765 distill.loss_1: 0.2250 distill.loss_2: 0.2815 distill.loss_3: 0.9729 2023/04/17 19:56:15 - mmengine - INFO - Epoch(train) [96][300/391] lr: 1.0000e-01 eta: 0:23:51 time: 0.0235 data_time: 0.0037 memory: 227 loss: 1.9065 student.loss: 0.1600 distill.loss_1: 0.2468 distill.loss_2: 0.2965 distill.loss_3: 1.2032 2023/04/17 19:56:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:56:18 - mmengine - INFO - Saving checkpoint at 96 epochs 2023/04/17 19:56:23 - mmengine - INFO - Epoch(val) [96][79/79] accuracy/top1: 92.3900 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:56:26 - mmengine - INFO - Epoch(train) [97][100/391] lr: 1.0000e-01 eta: 0:23:42 time: 0.0237 data_time: 0.0035 memory: 227 loss: 1.8622 student.loss: 0.1497 distill.loss_1: 0.2425 distill.loss_2: 0.2983 distill.loss_3: 1.1718 2023/04/17 19:56:28 - mmengine - INFO - Epoch(train) [97][200/391] lr: 1.0000e-01 eta: 0:23:38 time: 0.0247 data_time: 0.0035 memory: 227 loss: 1.7978 student.loss: 0.1071 distill.loss_1: 0.2314 distill.loss_2: 0.2890 distill.loss_3: 1.1702 2023/04/17 19:56:31 - mmengine - INFO - Epoch(train) [97][300/391] lr: 1.0000e-01 eta: 0:23:33 time: 0.0234 data_time: 0.0035 memory: 227 loss: 1.8605 student.loss: 0.1550 distill.loss_1: 0.2426 distill.loss_2: 0.2930 distill.loss_3: 1.1700 2023/04/17 19:56:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:56:33 - mmengine - INFO - Saving checkpoint at 97 epochs 2023/04/17 19:56:39 - mmengine - INFO - Epoch(val) [97][79/79] accuracy/top1: 92.1600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:56:41 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:56:42 - mmengine - INFO - Epoch(train) [98][100/391] lr: 1.0000e-01 eta: 0:23:24 time: 0.0234 data_time: 0.0038 memory: 227 loss: 1.6851 student.loss: 0.0703 distill.loss_1: 0.2305 distill.loss_2: 0.2906 distill.loss_3: 1.0937 2023/04/17 19:56:44 - mmengine - INFO - Epoch(train) [98][200/391] lr: 1.0000e-01 eta: 0:23:19 time: 0.0227 data_time: 0.0037 memory: 227 loss: 1.7517 student.loss: 0.0873 distill.loss_1: 0.2293 distill.loss_2: 0.2872 distill.loss_3: 1.1479 2023/04/17 19:56:46 - mmengine - INFO - Epoch(train) [98][300/391] lr: 1.0000e-01 eta: 0:23:15 time: 0.0242 data_time: 0.0036 memory: 227 loss: 1.8327 student.loss: 0.1364 distill.loss_1: 0.2448 distill.loss_2: 0.2898 distill.loss_3: 1.1617 2023/04/17 19:56:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:56:49 - mmengine - INFO - Saving checkpoint at 98 epochs 2023/04/17 19:56:55 - mmengine - INFO - Epoch(val) [98][79/79] accuracy/top1: 91.5200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 19:56:58 - mmengine - INFO - Epoch(train) [99][100/391] lr: 1.0000e-01 eta: 0:23:06 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.7168 student.loss: 0.0630 distill.loss_1: 0.2343 distill.loss_2: 0.2923 distill.loss_3: 1.1273 2023/04/17 19:57:00 - mmengine - INFO - Epoch(train) [99][200/391] lr: 1.0000e-01 eta: 0:23:02 time: 0.0242 data_time: 0.0036 memory: 227 loss: 1.6665 student.loss: 0.0755 distill.loss_1: 0.2332 distill.loss_2: 0.2888 distill.loss_3: 1.0690 2023/04/17 19:57:02 - mmengine - INFO - Epoch(train) [99][300/391] lr: 1.0000e-01 eta: 0:22:57 time: 0.0238 data_time: 0.0036 memory: 227 loss: 1.8141 student.loss: 0.1154 distill.loss_1: 0.2493 distill.loss_2: 0.2925 distill.loss_3: 1.1570 2023/04/17 19:57:05 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:57:05 - mmengine - INFO - Saving checkpoint at 99 epochs 2023/04/17 19:57:11 - mmengine - INFO - Epoch(val) [99][79/79] accuracy/top1: 91.2500 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:57:14 - mmengine - INFO - Epoch(train) [100][100/391] lr: 1.0000e-01 eta: 0:22:49 time: 0.0289 data_time: 0.0037 memory: 227 loss: 1.7461 student.loss: 0.1158 distill.loss_1: 0.2346 distill.loss_2: 0.2892 distill.loss_3: 1.1065 2023/04/17 19:57:16 - mmengine - INFO - Epoch(train) [100][200/391] lr: 1.0000e-01 eta: 0:22:45 time: 0.0385 data_time: 0.0037 memory: 227 loss: 1.7513 student.loss: 0.1199 distill.loss_1: 0.2351 distill.loss_2: 0.2897 distill.loss_3: 1.1066 2023/04/17 19:57:19 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:57:19 - mmengine - INFO - Epoch(train) [100][300/391] lr: 1.0000e-01 eta: 0:22:40 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.9511 student.loss: 0.1879 distill.loss_1: 0.2285 distill.loss_2: 0.2869 distill.loss_3: 1.2479 2023/04/17 19:57:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:57:21 - mmengine - INFO - Saving checkpoint at 100 epochs 2023/04/17 19:57:27 - mmengine - INFO - Epoch(val) [100][79/79] accuracy/top1: 91.1200 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0097 2023/04/17 19:57:30 - mmengine - INFO - Epoch(train) [101][100/391] lr: 1.0000e-02 eta: 0:22:32 time: 0.0235 data_time: 0.0037 memory: 227 loss: 1.5454 student.loss: 0.0507 distill.loss_1: 0.2184 distill.loss_2: 0.2706 distill.loss_3: 1.0056 2023/04/17 19:57:32 - mmengine - INFO - Epoch(train) [101][200/391] lr: 1.0000e-02 eta: 0:22:28 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.4884 student.loss: 0.0530 distill.loss_1: 0.2167 distill.loss_2: 0.2681 distill.loss_3: 0.9506 2023/04/17 19:57:35 - mmengine - INFO - Epoch(train) [101][300/391] lr: 1.0000e-02 eta: 0:22:23 time: 0.0233 data_time: 0.0036 memory: 227 loss: 1.4997 student.loss: 0.0474 distill.loss_1: 0.2181 distill.loss_2: 0.2687 distill.loss_3: 0.9655 2023/04/17 19:57:37 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:57:37 - mmengine - INFO - Saving checkpoint at 101 epochs 2023/04/17 19:57:43 - mmengine - INFO - Epoch(val) [101][79/79] accuracy/top1: 93.8900 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 19:57:45 - mmengine - INFO - Epoch(train) [102][100/391] lr: 1.0000e-02 eta: 0:22:15 time: 0.0233 data_time: 0.0035 memory: 227 loss: 1.5429 student.loss: 0.0557 distill.loss_1: 0.2066 distill.loss_2: 0.2585 distill.loss_3: 1.0220 2023/04/17 19:57:48 - mmengine - INFO - Epoch(train) [102][200/391] lr: 1.0000e-02 eta: 0:22:10 time: 0.0239 data_time: 0.0035 memory: 227 loss: 1.4904 student.loss: 0.0825 distill.loss_1: 0.2086 distill.loss_2: 0.2601 distill.loss_3: 0.9392 2023/04/17 19:57:50 - mmengine - INFO - Epoch(train) [102][300/391] lr: 1.0000e-02 eta: 0:22:06 time: 0.0231 data_time: 0.0035 memory: 227 loss: 1.5294 student.loss: 0.0395 distill.loss_1: 0.2165 distill.loss_2: 0.2589 distill.loss_3: 1.0145 2023/04/17 19:57:52 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:57:52 - mmengine - INFO - Saving checkpoint at 102 epochs 2023/04/17 19:57:59 - mmengine - INFO - Epoch(val) [102][79/79] accuracy/top1: 93.8200 teacher.accuracy/top1: 95.4400data_time: 0.0040 time: 0.0116 2023/04/17 19:58:02 - mmengine - INFO - Epoch(train) [103][100/391] lr: 1.0000e-02 eta: 0:21:58 time: 0.0234 data_time: 0.0038 memory: 227 loss: 1.4838 student.loss: 0.0507 distill.loss_1: 0.2104 distill.loss_2: 0.2618 distill.loss_3: 0.9609 2023/04/17 19:58:02 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:04 - mmengine - INFO - Epoch(train) [103][200/391] lr: 1.0000e-02 eta: 0:21:54 time: 0.0235 data_time: 0.0036 memory: 227 loss: 1.4652 student.loss: 0.0499 distill.loss_1: 0.2095 distill.loss_2: 0.2544 distill.loss_3: 0.9513 2023/04/17 19:58:07 - mmengine - INFO - Epoch(train) [103][300/391] lr: 1.0000e-02 eta: 0:21:49 time: 0.0235 data_time: 0.0036 memory: 227 loss: 1.4394 student.loss: 0.0352 distill.loss_1: 0.2070 distill.loss_2: 0.2564 distill.loss_3: 0.9408 2023/04/17 19:58:09 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:09 - mmengine - INFO - Saving checkpoint at 103 epochs 2023/04/17 19:58:15 - mmengine - INFO - Epoch(val) [103][79/79] accuracy/top1: 93.8200 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0097 2023/04/17 19:58:18 - mmengine - INFO - Epoch(train) [104][100/391] lr: 1.0000e-02 eta: 0:21:41 time: 0.0312 data_time: 0.0036 memory: 227 loss: 1.4741 student.loss: 0.0490 distill.loss_1: 0.2087 distill.loss_2: 0.2583 distill.loss_3: 0.9582 2023/04/17 19:58:20 - mmengine - INFO - Epoch(train) [104][200/391] lr: 1.0000e-02 eta: 0:21:37 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.5645 student.loss: 0.1049 distill.loss_1: 0.2095 distill.loss_2: 0.2589 distill.loss_3: 0.9912 2023/04/17 19:58:23 - mmengine - INFO - Epoch(train) [104][300/391] lr: 1.0000e-02 eta: 0:21:32 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.4569 student.loss: 0.0254 distill.loss_1: 0.2114 distill.loss_2: 0.2577 distill.loss_3: 0.9624 2023/04/17 19:58:25 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:25 - mmengine - INFO - Saving checkpoint at 104 epochs 2023/04/17 19:58:31 - mmengine - INFO - Epoch(val) [104][79/79] accuracy/top1: 93.8600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0100 2023/04/17 19:58:33 - mmengine - INFO - Epoch(train) [105][100/391] lr: 1.0000e-02 eta: 0:21:24 time: 0.0233 data_time: 0.0036 memory: 227 loss: 1.4371 student.loss: 0.0477 distill.loss_1: 0.2062 distill.loss_2: 0.2579 distill.loss_3: 0.9253 2023/04/17 19:58:36 - mmengine - INFO - Epoch(train) [105][200/391] lr: 1.0000e-02 eta: 0:21:20 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.4518 student.loss: 0.0329 distill.loss_1: 0.2113 distill.loss_2: 0.2576 distill.loss_3: 0.9500 2023/04/17 19:58:38 - mmengine - INFO - Epoch(train) [105][300/391] lr: 1.0000e-02 eta: 0:21:16 time: 0.0231 data_time: 0.0037 memory: 227 loss: 1.4489 student.loss: 0.0347 distill.loss_1: 0.2060 distill.loss_2: 0.2527 distill.loss_3: 0.9556 2023/04/17 19:58:39 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:40 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:40 - mmengine - INFO - Saving checkpoint at 105 epochs 2023/04/17 19:58:47 - mmengine - INFO - Epoch(val) [105][79/79] accuracy/top1: 94.1400 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 19:58:50 - mmengine - INFO - Epoch(train) [106][100/391] lr: 1.0000e-02 eta: 0:21:07 time: 0.0233 data_time: 0.0038 memory: 227 loss: 1.5199 student.loss: 0.0927 distill.loss_1: 0.2045 distill.loss_2: 0.2536 distill.loss_3: 0.9690 2023/04/17 19:58:52 - mmengine - INFO - Epoch(train) [106][200/391] lr: 1.0000e-02 eta: 0:21:03 time: 0.0256 data_time: 0.0036 memory: 227 loss: 1.4637 student.loss: 0.0600 distill.loss_1: 0.2133 distill.loss_2: 0.2548 distill.loss_3: 0.9355 2023/04/17 19:58:54 - mmengine - INFO - Epoch(train) [106][300/391] lr: 1.0000e-02 eta: 0:20:59 time: 0.0234 data_time: 0.0036 memory: 227 loss: 1.5769 student.loss: 0.0548 distill.loss_1: 0.2195 distill.loss_2: 0.2555 distill.loss_3: 1.0470 2023/04/17 19:58:57 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:58:57 - mmengine - INFO - Saving checkpoint at 106 epochs 2023/04/17 19:59:02 - mmengine - INFO - Epoch(val) [106][79/79] accuracy/top1: 94.0500 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0094 2023/04/17 19:59:05 - mmengine - INFO - Epoch(train) [107][100/391] lr: 1.0000e-02 eta: 0:20:51 time: 0.0233 data_time: 0.0040 memory: 227 loss: 1.3730 student.loss: 0.0224 distill.loss_1: 0.2037 distill.loss_2: 0.2523 distill.loss_3: 0.8946 2023/04/17 19:59:08 - mmengine - INFO - Epoch(train) [107][200/391] lr: 1.0000e-02 eta: 0:20:47 time: 0.0231 data_time: 0.0038 memory: 227 loss: 1.4575 student.loss: 0.0639 distill.loss_1: 0.2066 distill.loss_2: 0.2548 distill.loss_3: 0.9322 2023/04/17 19:59:10 - mmengine - INFO - Epoch(train) [107][300/391] lr: 1.0000e-02 eta: 0:20:43 time: 0.0243 data_time: 0.0036 memory: 227 loss: 1.4354 student.loss: 0.0450 distill.loss_1: 0.2064 distill.loss_2: 0.2529 distill.loss_3: 0.9310 2023/04/17 19:59:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:59:13 - mmengine - INFO - Saving checkpoint at 107 epochs 2023/04/17 19:59:19 - mmengine - INFO - Epoch(val) [107][79/79] accuracy/top1: 94.0800 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 19:59:21 - mmengine - INFO - Epoch(train) [108][100/391] lr: 1.0000e-02 eta: 0:20:35 time: 0.0235 data_time: 0.0037 memory: 227 loss: 1.4669 student.loss: 0.0272 distill.loss_1: 0.2103 distill.loss_2: 0.2549 distill.loss_3: 0.9745 2023/04/17 19:59:23 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:59:24 - mmengine - INFO - Epoch(train) [108][200/391] lr: 1.0000e-02 eta: 0:20:30 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.3903 student.loss: 0.0183 distill.loss_1: 0.2059 distill.loss_2: 0.2531 distill.loss_3: 0.9130 2023/04/17 19:59:26 - mmengine - INFO - Epoch(train) [108][300/391] lr: 1.0000e-02 eta: 0:20:26 time: 0.0233 data_time: 0.0037 memory: 227 loss: 1.3912 student.loss: 0.0155 distill.loss_1: 0.2019 distill.loss_2: 0.2534 distill.loss_3: 0.9204 2023/04/17 19:59:28 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:59:28 - mmengine - INFO - Saving checkpoint at 108 epochs 2023/04/17 19:59:35 - mmengine - INFO - Epoch(val) [108][79/79] accuracy/top1: 94.0700 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 19:59:38 - mmengine - INFO - Epoch(train) [109][100/391] lr: 1.0000e-02 eta: 0:20:19 time: 0.0286 data_time: 0.0048 memory: 227 loss: 1.4557 student.loss: 0.0369 distill.loss_1: 0.2094 distill.loss_2: 0.2545 distill.loss_3: 0.9549 2023/04/17 19:59:40 - mmengine - INFO - Epoch(train) [109][200/391] lr: 1.0000e-02 eta: 0:20:15 time: 0.0240 data_time: 0.0038 memory: 227 loss: 1.5081 student.loss: 0.0705 distill.loss_1: 0.2073 distill.loss_2: 0.2556 distill.loss_3: 0.9746 2023/04/17 19:59:43 - mmengine - INFO - Epoch(train) [109][300/391] lr: 1.0000e-02 eta: 0:20:10 time: 0.0253 data_time: 0.0037 memory: 227 loss: 1.3479 student.loss: 0.0152 distill.loss_1: 0.2085 distill.loss_2: 0.2516 distill.loss_3: 0.8726 2023/04/17 19:59:45 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 19:59:45 - mmengine - INFO - Saving checkpoint at 109 epochs 2023/04/17 19:59:52 - mmengine - INFO - Epoch(val) [109][79/79] accuracy/top1: 94.1400 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0596 2023/04/17 19:59:58 - mmengine - INFO - Epoch(train) [110][100/391] lr: 1.0000e-02 eta: 0:20:05 time: 0.0472 data_time: 0.0058 memory: 227 loss: 1.4020 student.loss: 0.0403 distill.loss_1: 0.2013 distill.loss_2: 0.2507 distill.loss_3: 0.9097 2023/04/17 20:00:00 - mmengine - INFO - Epoch(train) [110][200/391] lr: 1.0000e-02 eta: 0:20:01 time: 0.0236 data_time: 0.0043 memory: 227 loss: 1.5063 student.loss: 0.0655 distill.loss_1: 0.2135 distill.loss_2: 0.2530 distill.loss_3: 0.9742 2023/04/17 20:00:03 - mmengine - INFO - Epoch(train) [110][300/391] lr: 1.0000e-02 eta: 0:19:57 time: 0.0249 data_time: 0.0040 memory: 227 loss: 1.3998 student.loss: 0.0351 distill.loss_1: 0.2049 distill.loss_2: 0.2527 distill.loss_3: 0.9070 2023/04/17 20:00:05 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:05 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:05 - mmengine - INFO - Saving checkpoint at 110 epochs 2023/04/17 20:00:11 - mmengine - INFO - Epoch(val) [110][79/79] accuracy/top1: 94.0100 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0219 2023/04/17 20:00:14 - mmengine - INFO - Epoch(train) [111][100/391] lr: 1.0000e-02 eta: 0:19:49 time: 0.0231 data_time: 0.0038 memory: 227 loss: 1.3968 student.loss: 0.0446 distill.loss_1: 0.2049 distill.loss_2: 0.2520 distill.loss_3: 0.8952 2023/04/17 20:00:17 - mmengine - INFO - Epoch(train) [111][200/391] lr: 1.0000e-02 eta: 0:19:45 time: 0.0235 data_time: 0.0036 memory: 227 loss: 1.4279 student.loss: 0.0222 distill.loss_1: 0.2102 distill.loss_2: 0.2550 distill.loss_3: 0.9405 2023/04/17 20:00:19 - mmengine - INFO - Epoch(train) [111][300/391] lr: 1.0000e-02 eta: 0:19:41 time: 0.0243 data_time: 0.0039 memory: 227 loss: 1.3994 student.loss: 0.0209 distill.loss_1: 0.2090 distill.loss_2: 0.2543 distill.loss_3: 0.9153 2023/04/17 20:00:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:21 - mmengine - INFO - Saving checkpoint at 111 epochs 2023/04/17 20:00:28 - mmengine - INFO - Epoch(val) [111][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0101 2023/04/17 20:00:30 - mmengine - INFO - Epoch(train) [112][100/391] lr: 1.0000e-02 eta: 0:19:33 time: 0.0236 data_time: 0.0040 memory: 227 loss: 1.5335 student.loss: 0.0768 distill.loss_1: 0.2084 distill.loss_2: 0.2546 distill.loss_3: 0.9937 2023/04/17 20:00:33 - mmengine - INFO - Epoch(train) [112][200/391] lr: 1.0000e-02 eta: 0:19:29 time: 0.0382 data_time: 0.0041 memory: 227 loss: 1.3689 student.loss: 0.0364 distill.loss_1: 0.1980 distill.loss_2: 0.2461 distill.loss_3: 0.8883 2023/04/17 20:00:40 - mmengine - INFO - Epoch(train) [112][300/391] lr: 1.0000e-02 eta: 0:19:29 time: 0.0711 data_time: 0.0042 memory: 227 loss: 1.4932 student.loss: 0.0741 distill.loss_1: 0.2063 distill.loss_2: 0.2533 distill.loss_3: 0.9595 2023/04/17 20:00:43 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:43 - mmengine - INFO - Saving checkpoint at 112 epochs 2023/04/17 20:00:49 - mmengine - INFO - Epoch(val) [112][79/79] accuracy/top1: 94.0700 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:00:52 - mmengine - INFO - Epoch(train) [113][100/391] lr: 1.0000e-02 eta: 0:19:22 time: 0.0254 data_time: 0.0037 memory: 227 loss: 1.4490 student.loss: 0.0386 distill.loss_1: 0.2056 distill.loss_2: 0.2515 distill.loss_3: 0.9533 2023/04/17 20:00:54 - mmengine - INFO - Epoch(train) [113][200/391] lr: 1.0000e-02 eta: 0:19:17 time: 0.0235 data_time: 0.0036 memory: 227 loss: 1.3847 student.loss: 0.0201 distill.loss_1: 0.2073 distill.loss_2: 0.2511 distill.loss_3: 0.9063 2023/04/17 20:00:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:57 - mmengine - INFO - Epoch(train) [113][300/391] lr: 1.0000e-02 eta: 0:19:13 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.4115 student.loss: 0.0320 distill.loss_1: 0.2070 distill.loss_2: 0.2514 distill.loss_3: 0.9211 2023/04/17 20:00:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:00:59 - mmengine - INFO - Saving checkpoint at 113 epochs 2023/04/17 20:01:05 - mmengine - INFO - Epoch(val) [113][79/79] accuracy/top1: 94.0500 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 20:01:08 - mmengine - INFO - Epoch(train) [114][100/391] lr: 1.0000e-02 eta: 0:19:06 time: 0.0232 data_time: 0.0041 memory: 227 loss: 1.4186 student.loss: 0.0348 distill.loss_1: 0.2125 distill.loss_2: 0.2585 distill.loss_3: 0.9127 2023/04/17 20:01:10 - mmengine - INFO - Epoch(train) [114][200/391] lr: 1.0000e-02 eta: 0:19:02 time: 0.0237 data_time: 0.0043 memory: 227 loss: 1.4417 student.loss: 0.0395 distill.loss_1: 0.2135 distill.loss_2: 0.2494 distill.loss_3: 0.9393 2023/04/17 20:01:12 - mmengine - INFO - Epoch(train) [114][300/391] lr: 1.0000e-02 eta: 0:18:57 time: 0.0231 data_time: 0.0040 memory: 227 loss: 1.4513 student.loss: 0.0479 distill.loss_1: 0.2129 distill.loss_2: 0.2554 distill.loss_3: 0.9350 2023/04/17 20:01:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:01:15 - mmengine - INFO - Saving checkpoint at 114 epochs 2023/04/17 20:01:21 - mmengine - INFO - Epoch(val) [114][79/79] accuracy/top1: 94.0800 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0095 2023/04/17 20:01:24 - mmengine - INFO - Epoch(train) [115][100/391] lr: 1.0000e-02 eta: 0:18:50 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.4097 student.loss: 0.0262 distill.loss_1: 0.2032 distill.loss_2: 0.2530 distill.loss_3: 0.9274 2023/04/17 20:01:26 - mmengine - INFO - Epoch(train) [115][200/391] lr: 1.0000e-02 eta: 0:18:46 time: 0.0236 data_time: 0.0036 memory: 227 loss: 1.4084 student.loss: 0.0470 distill.loss_1: 0.2090 distill.loss_2: 0.2509 distill.loss_3: 0.9015 2023/04/17 20:01:29 - mmengine - INFO - Epoch(train) [115][300/391] lr: 1.0000e-02 eta: 0:18:42 time: 0.0234 data_time: 0.0036 memory: 227 loss: 1.4434 student.loss: 0.0385 distill.loss_1: 0.2103 distill.loss_2: 0.2554 distill.loss_3: 0.9393 2023/04/17 20:01:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:01:31 - mmengine - INFO - Saving checkpoint at 115 epochs 2023/04/17 20:01:37 - mmengine - INFO - Epoch(val) [115][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0096 2023/04/17 20:01:38 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:01:40 - mmengine - INFO - Epoch(train) [116][100/391] lr: 1.0000e-02 eta: 0:18:34 time: 0.0242 data_time: 0.0036 memory: 227 loss: 1.3758 student.loss: 0.0235 distill.loss_1: 0.2136 distill.loss_2: 0.2557 distill.loss_3: 0.8830 2023/04/17 20:01:42 - mmengine - INFO - Epoch(train) [116][200/391] lr: 1.0000e-02 eta: 0:18:30 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.4621 student.loss: 0.0644 distill.loss_1: 0.2028 distill.loss_2: 0.2513 distill.loss_3: 0.9436 2023/04/17 20:01:45 - mmengine - INFO - Epoch(train) [116][300/391] lr: 1.0000e-02 eta: 0:18:26 time: 0.0313 data_time: 0.0036 memory: 227 loss: 1.4406 student.loss: 0.0540 distill.loss_1: 0.2083 distill.loss_2: 0.2483 distill.loss_3: 0.9300 2023/04/17 20:01:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:01:47 - mmengine - INFO - Saving checkpoint at 116 epochs 2023/04/17 20:01:53 - mmengine - INFO - Epoch(val) [116][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0100 2023/04/17 20:01:56 - mmengine - INFO - Epoch(train) [117][100/391] lr: 1.0000e-02 eta: 0:18:19 time: 0.0243 data_time: 0.0040 memory: 227 loss: 1.4901 student.loss: 0.0340 distill.loss_1: 0.2065 distill.loss_2: 0.2475 distill.loss_3: 1.0022 2023/04/17 20:01:58 - mmengine - INFO - Epoch(train) [117][200/391] lr: 1.0000e-02 eta: 0:18:15 time: 0.0245 data_time: 0.0039 memory: 227 loss: 1.4171 student.loss: 0.0345 distill.loss_1: 0.2111 distill.loss_2: 0.2502 distill.loss_3: 0.9213 2023/04/17 20:02:01 - mmengine - INFO - Epoch(train) [117][300/391] lr: 1.0000e-02 eta: 0:18:11 time: 0.0275 data_time: 0.0036 memory: 227 loss: 1.4632 student.loss: 0.0610 distill.loss_1: 0.2060 distill.loss_2: 0.2508 distill.loss_3: 0.9454 2023/04/17 20:02:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:03 - mmengine - INFO - Saving checkpoint at 117 epochs 2023/04/17 20:02:09 - mmengine - INFO - Epoch(val) [117][79/79] accuracy/top1: 93.9400 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:02:12 - mmengine - INFO - Epoch(train) [118][100/391] lr: 1.0000e-02 eta: 0:18:03 time: 0.0242 data_time: 0.0036 memory: 227 loss: 1.3787 student.loss: 0.0232 distill.loss_1: 0.2089 distill.loss_2: 0.2508 distill.loss_3: 0.8958 2023/04/17 20:02:14 - mmengine - INFO - Epoch(train) [118][200/391] lr: 1.0000e-02 eta: 0:17:59 time: 0.0231 data_time: 0.0036 memory: 227 loss: 1.4375 student.loss: 0.0307 distill.loss_1: 0.2066 distill.loss_2: 0.2502 distill.loss_3: 0.9501 2023/04/17 20:02:16 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:17 - mmengine - INFO - Epoch(train) [118][300/391] lr: 1.0000e-02 eta: 0:17:55 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.3210 student.loss: 0.0191 distill.loss_1: 0.2114 distill.loss_2: 0.2509 distill.loss_3: 0.8396 2023/04/17 20:02:19 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:19 - mmengine - INFO - Saving checkpoint at 118 epochs 2023/04/17 20:02:24 - mmengine - INFO - Epoch(val) [118][79/79] accuracy/top1: 94.1200 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0094 2023/04/17 20:02:27 - mmengine - INFO - Epoch(train) [119][100/391] lr: 1.0000e-02 eta: 0:17:48 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.4511 student.loss: 0.0512 distill.loss_1: 0.2094 distill.loss_2: 0.2532 distill.loss_3: 0.9373 2023/04/17 20:02:30 - mmengine - INFO - Epoch(train) [119][200/391] lr: 1.0000e-02 eta: 0:17:44 time: 0.0236 data_time: 0.0037 memory: 227 loss: 1.5242 student.loss: 0.0725 distill.loss_1: 0.2081 distill.loss_2: 0.2515 distill.loss_3: 0.9922 2023/04/17 20:02:32 - mmengine - INFO - Epoch(train) [119][300/391] lr: 1.0000e-02 eta: 0:17:40 time: 0.0236 data_time: 0.0036 memory: 227 loss: 1.3933 student.loss: 0.0303 distill.loss_1: 0.1974 distill.loss_2: 0.2424 distill.loss_3: 0.9231 2023/04/17 20:02:34 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:34 - mmengine - INFO - Saving checkpoint at 119 epochs 2023/04/17 20:02:40 - mmengine - INFO - Epoch(val) [119][79/79] accuracy/top1: 94.1600 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0096 2023/04/17 20:02:43 - mmengine - INFO - Epoch(train) [120][100/391] lr: 1.0000e-02 eta: 0:17:33 time: 0.0353 data_time: 0.0042 memory: 227 loss: 1.3637 student.loss: 0.0227 distill.loss_1: 0.2019 distill.loss_2: 0.2467 distill.loss_3: 0.8924 2023/04/17 20:02:46 - mmengine - INFO - Epoch(train) [120][200/391] lr: 1.0000e-02 eta: 0:17:29 time: 0.0232 data_time: 0.0037 memory: 227 loss: 1.4239 student.loss: 0.0264 distill.loss_1: 0.2024 distill.loss_2: 0.2471 distill.loss_3: 0.9481 2023/04/17 20:02:48 - mmengine - INFO - Epoch(train) [120][300/391] lr: 1.0000e-02 eta: 0:17:25 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.3578 student.loss: 0.0258 distill.loss_1: 0.2001 distill.loss_2: 0.2440 distill.loss_3: 0.8878 2023/04/17 20:02:50 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:50 - mmengine - INFO - Saving checkpoint at 120 epochs 2023/04/17 20:02:56 - mmengine - INFO - Epoch(val) [120][79/79] accuracy/top1: 94.1900 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0100 2023/04/17 20:02:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:02:59 - mmengine - INFO - Epoch(train) [121][100/391] lr: 1.0000e-02 eta: 0:17:18 time: 0.0234 data_time: 0.0039 memory: 227 loss: 1.4241 student.loss: 0.0197 distill.loss_1: 0.2144 distill.loss_2: 0.2523 distill.loss_3: 0.9378 2023/04/17 20:03:01 - mmengine - INFO - Epoch(train) [121][200/391] lr: 1.0000e-02 eta: 0:17:14 time: 0.0235 data_time: 0.0040 memory: 227 loss: 1.4230 student.loss: 0.0593 distill.loss_1: 0.1947 distill.loss_2: 0.2438 distill.loss_3: 0.9251 2023/04/17 20:03:04 - mmengine - INFO - Epoch(train) [121][300/391] lr: 1.0000e-02 eta: 0:17:10 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.4214 student.loss: 0.0362 distill.loss_1: 0.2049 distill.loss_2: 0.2510 distill.loss_3: 0.9293 2023/04/17 20:03:06 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:03:06 - mmengine - INFO - Saving checkpoint at 121 epochs 2023/04/17 20:03:12 - mmengine - INFO - Epoch(val) [121][79/79] accuracy/top1: 94.0100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0094 2023/04/17 20:03:15 - mmengine - INFO - Epoch(train) [122][100/391] lr: 1.0000e-02 eta: 0:17:02 time: 0.0252 data_time: 0.0041 memory: 227 loss: 1.5074 student.loss: 0.0412 distill.loss_1: 0.2218 distill.loss_2: 0.2565 distill.loss_3: 0.9879 2023/04/17 20:03:17 - mmengine - INFO - Epoch(train) [122][200/391] lr: 1.0000e-02 eta: 0:16:58 time: 0.0241 data_time: 0.0041 memory: 227 loss: 1.4182 student.loss: 0.0368 distill.loss_1: 0.2070 distill.loss_2: 0.2472 distill.loss_3: 0.9272 2023/04/17 20:03:20 - mmengine - INFO - Epoch(train) [122][300/391] lr: 1.0000e-02 eta: 0:16:55 time: 0.0239 data_time: 0.0040 memory: 227 loss: 1.4514 student.loss: 0.0289 distill.loss_1: 0.2150 distill.loss_2: 0.2499 distill.loss_3: 0.9576 2023/04/17 20:03:22 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:03:22 - mmengine - INFO - Saving checkpoint at 122 epochs 2023/04/17 20:03:28 - mmengine - INFO - Epoch(val) [122][79/79] accuracy/top1: 93.9900 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:03:31 - mmengine - INFO - Epoch(train) [123][100/391] lr: 1.0000e-02 eta: 0:16:48 time: 0.0238 data_time: 0.0037 memory: 227 loss: 1.3912 student.loss: 0.0290 distill.loss_1: 0.2119 distill.loss_2: 0.2562 distill.loss_3: 0.8941 2023/04/17 20:03:34 - mmengine - INFO - Epoch(train) [123][200/391] lr: 1.0000e-02 eta: 0:16:44 time: 0.0240 data_time: 0.0042 memory: 227 loss: 1.4070 student.loss: 0.0361 distill.loss_1: 0.2023 distill.loss_2: 0.2435 distill.loss_3: 0.9250 2023/04/17 20:03:37 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:03:37 - mmengine - INFO - Epoch(train) [123][300/391] lr: 1.0000e-02 eta: 0:16:40 time: 0.0376 data_time: 0.0043 memory: 227 loss: 1.4824 student.loss: 0.0658 distill.loss_1: 0.2004 distill.loss_2: 0.2455 distill.loss_3: 0.9708 2023/04/17 20:03:39 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:03:39 - mmengine - INFO - Saving checkpoint at 123 epochs 2023/04/17 20:03:45 - mmengine - INFO - Epoch(val) [123][79/79] accuracy/top1: 94.0100 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:03:48 - mmengine - INFO - Epoch(train) [124][100/391] lr: 1.0000e-02 eta: 0:16:33 time: 0.0241 data_time: 0.0041 memory: 227 loss: 1.4967 student.loss: 0.0643 distill.loss_1: 0.2042 distill.loss_2: 0.2486 distill.loss_3: 0.9795 2023/04/17 20:03:50 - mmengine - INFO - Epoch(train) [124][200/391] lr: 1.0000e-02 eta: 0:16:29 time: 0.0234 data_time: 0.0041 memory: 227 loss: 1.3915 student.loss: 0.0275 distill.loss_1: 0.2083 distill.loss_2: 0.2478 distill.loss_3: 0.9079 2023/04/17 20:03:52 - mmengine - INFO - Epoch(train) [124][300/391] lr: 1.0000e-02 eta: 0:16:25 time: 0.0238 data_time: 0.0041 memory: 227 loss: 1.3725 student.loss: 0.0115 distill.loss_1: 0.2017 distill.loss_2: 0.2460 distill.loss_3: 0.9132 2023/04/17 20:03:55 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:03:55 - mmengine - INFO - Saving checkpoint at 124 epochs 2023/04/17 20:04:00 - mmengine - INFO - Epoch(val) [124][79/79] accuracy/top1: 94.0700 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0097 2023/04/17 20:04:03 - mmengine - INFO - Epoch(train) [125][100/391] lr: 1.0000e-02 eta: 0:16:18 time: 0.0244 data_time: 0.0040 memory: 227 loss: 1.3757 student.loss: 0.0203 distill.loss_1: 0.2049 distill.loss_2: 0.2474 distill.loss_3: 0.9031 2023/04/17 20:04:06 - mmengine - INFO - Epoch(train) [125][200/391] lr: 1.0000e-02 eta: 0:16:14 time: 0.0244 data_time: 0.0040 memory: 227 loss: 1.3858 student.loss: 0.0170 distill.loss_1: 0.2058 distill.loss_2: 0.2479 distill.loss_3: 0.9151 2023/04/17 20:04:08 - mmengine - INFO - Epoch(train) [125][300/391] lr: 1.0000e-02 eta: 0:16:10 time: 0.0235 data_time: 0.0037 memory: 227 loss: 1.4417 student.loss: 0.0302 distill.loss_1: 0.2078 distill.loss_2: 0.2493 distill.loss_3: 0.9544 2023/04/17 20:04:10 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:10 - mmengine - INFO - Saving checkpoint at 125 epochs 2023/04/17 20:04:17 - mmengine - INFO - Epoch(val) [125][79/79] accuracy/top1: 94.1000 teacher.accuracy/top1: 95.4400data_time: 0.0069 time: 0.0132 2023/04/17 20:04:20 - mmengine - INFO - Epoch(train) [126][100/391] lr: 1.0000e-02 eta: 0:16:03 time: 0.0254 data_time: 0.0041 memory: 227 loss: 1.4029 student.loss: 0.0202 distill.loss_1: 0.2088 distill.loss_2: 0.2504 distill.loss_3: 0.9234 2023/04/17 20:04:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:22 - mmengine - INFO - Epoch(train) [126][200/391] lr: 1.0000e-02 eta: 0:15:59 time: 0.0239 data_time: 0.0038 memory: 227 loss: 1.4403 student.loss: 0.0555 distill.loss_1: 0.2029 distill.loss_2: 0.2471 distill.loss_3: 0.9348 2023/04/17 20:04:25 - mmengine - INFO - Epoch(train) [126][300/391] lr: 1.0000e-02 eta: 0:15:56 time: 0.0248 data_time: 0.0037 memory: 227 loss: 1.4064 student.loss: 0.0505 distill.loss_1: 0.1981 distill.loss_2: 0.2457 distill.loss_3: 0.9121 2023/04/17 20:04:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:27 - mmengine - INFO - Saving checkpoint at 126 epochs 2023/04/17 20:04:33 - mmengine - INFO - Epoch(val) [126][79/79] accuracy/top1: 94.1000 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0098 2023/04/17 20:04:36 - mmengine - INFO - Epoch(train) [127][100/391] lr: 1.0000e-02 eta: 0:15:49 time: 0.0243 data_time: 0.0036 memory: 227 loss: 1.3675 student.loss: 0.0238 distill.loss_1: 0.2050 distill.loss_2: 0.2491 distill.loss_3: 0.8896 2023/04/17 20:04:38 - mmengine - INFO - Epoch(train) [127][200/391] lr: 1.0000e-02 eta: 0:15:45 time: 0.0237 data_time: 0.0037 memory: 227 loss: 1.4291 student.loss: 0.0407 distill.loss_1: 0.2040 distill.loss_2: 0.2431 distill.loss_3: 0.9413 2023/04/17 20:04:40 - mmengine - INFO - Epoch(train) [127][300/391] lr: 1.0000e-02 eta: 0:15:41 time: 0.0245 data_time: 0.0037 memory: 227 loss: 1.5238 student.loss: 0.1040 distill.loss_1: 0.2086 distill.loss_2: 0.2492 distill.loss_3: 0.9619 2023/04/17 20:04:43 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:43 - mmengine - INFO - Saving checkpoint at 127 epochs 2023/04/17 20:04:49 - mmengine - INFO - Epoch(val) [127][79/79] accuracy/top1: 94.1300 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0096 2023/04/17 20:04:52 - mmengine - INFO - Epoch(train) [128][100/391] lr: 1.0000e-02 eta: 0:15:34 time: 0.0238 data_time: 0.0042 memory: 227 loss: 1.4050 student.loss: 0.0344 distill.loss_1: 0.2067 distill.loss_2: 0.2501 distill.loss_3: 0.9138 2023/04/17 20:04:54 - mmengine - INFO - Epoch(train) [128][200/391] lr: 1.0000e-02 eta: 0:15:30 time: 0.0278 data_time: 0.0046 memory: 227 loss: 1.3916 student.loss: 0.0298 distill.loss_1: 0.2066 distill.loss_2: 0.2470 distill.loss_3: 0.9081 2023/04/17 20:04:57 - mmengine - INFO - Epoch(train) [128][300/391] lr: 1.0000e-02 eta: 0:15:26 time: 0.0236 data_time: 0.0045 memory: 227 loss: 1.4485 student.loss: 0.0224 distill.loss_1: 0.2096 distill.loss_2: 0.2480 distill.loss_3: 0.9685 2023/04/17 20:04:58 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:04:59 - mmengine - INFO - Saving checkpoint at 128 epochs 2023/04/17 20:05:06 - mmengine - INFO - Epoch(val) [128][79/79] accuracy/top1: 94.1000 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0099 2023/04/17 20:05:11 - mmengine - INFO - Epoch(train) [129][100/391] lr: 1.0000e-02 eta: 0:15:21 time: 0.1014 data_time: 0.0038 memory: 227 loss: 1.3920 student.loss: 0.0358 distill.loss_1: 0.2086 distill.loss_2: 0.2489 distill.loss_3: 0.8987 2023/04/17 20:05:17 - mmengine - INFO - Epoch(train) [129][200/391] lr: 1.0000e-02 eta: 0:15:19 time: 0.0426 data_time: 0.0039 memory: 227 loss: 1.4141 student.loss: 0.0446 distill.loss_1: 0.2060 distill.loss_2: 0.2485 distill.loss_3: 0.9150 2023/04/17 20:05:20 - mmengine - INFO - Epoch(train) [129][300/391] lr: 1.0000e-02 eta: 0:15:16 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.4087 student.loss: 0.0645 distill.loss_1: 0.2068 distill.loss_2: 0.2492 distill.loss_3: 0.8882 2023/04/17 20:05:22 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:05:22 - mmengine - INFO - Saving checkpoint at 129 epochs 2023/04/17 20:05:28 - mmengine - INFO - Epoch(val) [129][79/79] accuracy/top1: 93.8800 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 20:05:31 - mmengine - INFO - Epoch(train) [130][100/391] lr: 1.0000e-02 eta: 0:15:09 time: 0.0244 data_time: 0.0037 memory: 227 loss: 1.3594 student.loss: 0.0125 distill.loss_1: 0.2055 distill.loss_2: 0.2474 distill.loss_3: 0.8940 2023/04/17 20:05:33 - mmengine - INFO - Epoch(train) [130][200/391] lr: 1.0000e-02 eta: 0:15:05 time: 0.0244 data_time: 0.0036 memory: 227 loss: 1.4324 student.loss: 0.0282 distill.loss_1: 0.2098 distill.loss_2: 0.2511 distill.loss_3: 0.9433 2023/04/17 20:05:36 - mmengine - INFO - Epoch(train) [130][300/391] lr: 1.0000e-02 eta: 0:15:01 time: 0.0240 data_time: 0.0037 memory: 227 loss: 1.3388 student.loss: 0.0154 distill.loss_1: 0.2006 distill.loss_2: 0.2445 distill.loss_3: 0.8784 2023/04/17 20:05:38 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:05:38 - mmengine - INFO - Saving checkpoint at 130 epochs 2023/04/17 20:05:44 - mmengine - INFO - Epoch(val) [130][79/79] accuracy/top1: 94.2500 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 20:05:47 - mmengine - INFO - Epoch(train) [131][100/391] lr: 1.0000e-02 eta: 0:14:54 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.4192 student.loss: 0.0344 distill.loss_1: 0.2010 distill.loss_2: 0.2482 distill.loss_3: 0.9355 2023/04/17 20:05:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:05:50 - mmengine - INFO - Epoch(train) [131][200/391] lr: 1.0000e-02 eta: 0:14:50 time: 0.0232 data_time: 0.0037 memory: 227 loss: 1.4453 student.loss: 0.0386 distill.loss_1: 0.2080 distill.loss_2: 0.2471 distill.loss_3: 0.9517 2023/04/17 20:05:52 - mmengine - INFO - Epoch(train) [131][300/391] lr: 1.0000e-02 eta: 0:14:47 time: 0.0236 data_time: 0.0037 memory: 227 loss: 1.4286 student.loss: 0.0336 distill.loss_1: 0.2058 distill.loss_2: 0.2503 distill.loss_3: 0.9389 2023/04/17 20:05:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:05:54 - mmengine - INFO - Saving checkpoint at 131 epochs 2023/04/17 20:06:00 - mmengine - INFO - Epoch(val) [131][79/79] accuracy/top1: 93.7900 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0096 2023/04/17 20:06:03 - mmengine - INFO - Epoch(train) [132][100/391] lr: 1.0000e-02 eta: 0:14:40 time: 0.0329 data_time: 0.0041 memory: 227 loss: 1.4129 student.loss: 0.0272 distill.loss_1: 0.2003 distill.loss_2: 0.2474 distill.loss_3: 0.9379 2023/04/17 20:06:06 - mmengine - INFO - Epoch(train) [132][200/391] lr: 1.0000e-02 eta: 0:14:36 time: 0.0238 data_time: 0.0040 memory: 227 loss: 1.3779 student.loss: 0.0116 distill.loss_1: 0.1988 distill.loss_2: 0.2437 distill.loss_3: 0.9238 2023/04/17 20:06:08 - mmengine - INFO - Epoch(train) [132][300/391] lr: 1.0000e-02 eta: 0:14:33 time: 0.0234 data_time: 0.0036 memory: 227 loss: 1.3821 student.loss: 0.0300 distill.loss_1: 0.2144 distill.loss_2: 0.2490 distill.loss_3: 0.8887 2023/04/17 20:06:10 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:06:11 - mmengine - INFO - Saving checkpoint at 132 epochs 2023/04/17 20:06:16 - mmengine - INFO - Epoch(val) [132][79/79] accuracy/top1: 94.1200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:06:19 - mmengine - INFO - Epoch(train) [133][100/391] lr: 1.0000e-02 eta: 0:14:26 time: 0.0247 data_time: 0.0038 memory: 227 loss: 1.3772 student.loss: 0.0091 distill.loss_1: 0.2019 distill.loss_2: 0.2478 distill.loss_3: 0.9184 2023/04/17 20:06:22 - mmengine - INFO - Epoch(train) [133][200/391] lr: 1.0000e-02 eta: 0:14:22 time: 0.0252 data_time: 0.0035 memory: 227 loss: 1.4770 student.loss: 0.0749 distill.loss_1: 0.2074 distill.loss_2: 0.2503 distill.loss_3: 0.9444 2023/04/17 20:06:24 - mmengine - INFO - Epoch(train) [133][300/391] lr: 1.0000e-02 eta: 0:14:18 time: 0.0247 data_time: 0.0036 memory: 227 loss: 1.3698 student.loss: 0.0237 distill.loss_1: 0.2123 distill.loss_2: 0.2525 distill.loss_3: 0.8814 2023/04/17 20:06:26 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:06:26 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:06:26 - mmengine - INFO - Saving checkpoint at 133 epochs 2023/04/17 20:06:32 - mmengine - INFO - Epoch(val) [133][79/79] accuracy/top1: 94.0400 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 20:06:35 - mmengine - INFO - Epoch(train) [134][100/391] lr: 1.0000e-02 eta: 0:14:12 time: 0.0237 data_time: 0.0038 memory: 227 loss: 1.4224 student.loss: 0.0359 distill.loss_1: 0.2061 distill.loss_2: 0.2492 distill.loss_3: 0.9313 2023/04/17 20:06:38 - mmengine - INFO - Epoch(train) [134][200/391] lr: 1.0000e-02 eta: 0:14:08 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.3342 student.loss: 0.0182 distill.loss_1: 0.2011 distill.loss_2: 0.2451 distill.loss_3: 0.8697 2023/04/17 20:06:40 - mmengine - INFO - Epoch(train) [134][300/391] lr: 1.0000e-02 eta: 0:14:04 time: 0.0238 data_time: 0.0037 memory: 227 loss: 1.3080 student.loss: 0.0069 distill.loss_1: 0.1984 distill.loss_2: 0.2418 distill.loss_3: 0.8609 2023/04/17 20:06:42 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:06:42 - mmengine - INFO - Saving checkpoint at 134 epochs 2023/04/17 20:06:49 - mmengine - INFO - Epoch(val) [134][79/79] accuracy/top1: 94.0900 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:06:52 - mmengine - INFO - Epoch(train) [135][100/391] lr: 1.0000e-02 eta: 0:13:57 time: 0.0244 data_time: 0.0042 memory: 227 loss: 1.3216 student.loss: 0.0245 distill.loss_1: 0.2015 distill.loss_2: 0.2436 distill.loss_3: 0.8520 2023/04/17 20:06:54 - mmengine - INFO - Epoch(train) [135][200/391] lr: 1.0000e-02 eta: 0:13:54 time: 0.0237 data_time: 0.0040 memory: 227 loss: 1.3635 student.loss: 0.0273 distill.loss_1: 0.1995 distill.loss_2: 0.2432 distill.loss_3: 0.8936 2023/04/17 20:06:57 - mmengine - INFO - Epoch(train) [135][300/391] lr: 1.0000e-02 eta: 0:13:50 time: 0.0240 data_time: 0.0037 memory: 227 loss: 1.3739 student.loss: 0.0387 distill.loss_1: 0.1990 distill.loss_2: 0.2448 distill.loss_3: 0.8913 2023/04/17 20:06:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:06:59 - mmengine - INFO - Saving checkpoint at 135 epochs 2023/04/17 20:07:05 - mmengine - INFO - Epoch(val) [135][79/79] accuracy/top1: 94.0900 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0096 2023/04/17 20:07:08 - mmengine - INFO - Epoch(train) [136][100/391] lr: 1.0000e-02 eta: 0:13:43 time: 0.0319 data_time: 0.0040 memory: 227 loss: 1.3499 student.loss: 0.0094 distill.loss_1: 0.2027 distill.loss_2: 0.2438 distill.loss_3: 0.8940 2023/04/17 20:07:10 - mmengine - INFO - Epoch(train) [136][200/391] lr: 1.0000e-02 eta: 0:13:40 time: 0.0239 data_time: 0.0042 memory: 227 loss: 1.4289 student.loss: 0.0341 distill.loss_1: 0.2113 distill.loss_2: 0.2486 distill.loss_3: 0.9348 2023/04/17 20:07:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:07:13 - mmengine - INFO - Epoch(train) [136][300/391] lr: 1.0000e-02 eta: 0:13:36 time: 0.0238 data_time: 0.0039 memory: 227 loss: 1.3828 student.loss: 0.0226 distill.loss_1: 0.2097 distill.loss_2: 0.2484 distill.loss_3: 0.9022 2023/04/17 20:07:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:07:15 - mmengine - INFO - Saving checkpoint at 136 epochs 2023/04/17 20:07:21 - mmengine - INFO - Epoch(val) [136][79/79] accuracy/top1: 94.0800 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0091 2023/04/17 20:07:24 - mmengine - INFO - Epoch(train) [137][100/391] lr: 1.0000e-02 eta: 0:13:29 time: 0.0242 data_time: 0.0041 memory: 227 loss: 1.3321 student.loss: 0.0244 distill.loss_1: 0.2017 distill.loss_2: 0.2437 distill.loss_3: 0.8624 2023/04/17 20:07:27 - mmengine - INFO - Epoch(train) [137][200/391] lr: 1.0000e-02 eta: 0:13:26 time: 0.0356 data_time: 0.0036 memory: 227 loss: 1.4312 student.loss: 0.0400 distill.loss_1: 0.2097 distill.loss_2: 0.2494 distill.loss_3: 0.9321 2023/04/17 20:07:29 - mmengine - INFO - Epoch(train) [137][300/391] lr: 1.0000e-02 eta: 0:13:22 time: 0.0239 data_time: 0.0039 memory: 227 loss: 1.4118 student.loss: 0.0264 distill.loss_1: 0.1993 distill.loss_2: 0.2486 distill.loss_3: 0.9374 2023/04/17 20:07:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:07:31 - mmengine - INFO - Saving checkpoint at 137 epochs 2023/04/17 20:07:37 - mmengine - INFO - Epoch(val) [137][79/79] accuracy/top1: 93.9100 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0094 2023/04/17 20:07:40 - mmengine - INFO - Epoch(train) [138][100/391] lr: 1.0000e-02 eta: 0:13:15 time: 0.0290 data_time: 0.0045 memory: 227 loss: 1.3327 student.loss: 0.0086 distill.loss_1: 0.2053 distill.loss_2: 0.2485 distill.loss_3: 0.8703 2023/04/17 20:07:42 - mmengine - INFO - Epoch(train) [138][200/391] lr: 1.0000e-02 eta: 0:13:12 time: 0.0250 data_time: 0.0043 memory: 227 loss: 1.3411 student.loss: 0.0195 distill.loss_1: 0.2064 distill.loss_2: 0.2470 distill.loss_3: 0.8682 2023/04/17 20:07:45 - mmengine - INFO - Epoch(train) [138][300/391] lr: 1.0000e-02 eta: 0:13:08 time: 0.0239 data_time: 0.0043 memory: 227 loss: 1.3124 student.loss: 0.0132 distill.loss_1: 0.2105 distill.loss_2: 0.2490 distill.loss_3: 0.8398 2023/04/17 20:07:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:07:47 - mmengine - INFO - Saving checkpoint at 138 epochs 2023/04/17 20:07:53 - mmengine - INFO - Epoch(val) [138][79/79] accuracy/top1: 93.9100 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0097 2023/04/17 20:07:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:07:56 - mmengine - INFO - Epoch(train) [139][100/391] lr: 1.0000e-02 eta: 0:13:01 time: 0.0244 data_time: 0.0039 memory: 227 loss: 1.4073 student.loss: 0.0185 distill.loss_1: 0.2115 distill.loss_2: 0.2471 distill.loss_3: 0.9303 2023/04/17 20:07:58 - mmengine - INFO - Epoch(train) [139][200/391] lr: 1.0000e-02 eta: 0:12:58 time: 0.0238 data_time: 0.0039 memory: 227 loss: 1.3188 student.loss: 0.0258 distill.loss_1: 0.2026 distill.loss_2: 0.2416 distill.loss_3: 0.8488 2023/04/17 20:08:01 - mmengine - INFO - Epoch(train) [139][300/391] lr: 1.0000e-02 eta: 0:12:54 time: 0.0251 data_time: 0.0039 memory: 227 loss: 1.4251 student.loss: 0.0443 distill.loss_1: 0.1960 distill.loss_2: 0.2433 distill.loss_3: 0.9415 2023/04/17 20:08:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:08:03 - mmengine - INFO - Saving checkpoint at 139 epochs 2023/04/17 20:08:08 - mmengine - INFO - Epoch(val) [139][79/79] accuracy/top1: 94.1500 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:08:12 - mmengine - INFO - Epoch(train) [140][100/391] lr: 1.0000e-02 eta: 0:12:48 time: 0.0242 data_time: 0.0041 memory: 227 loss: 1.3724 student.loss: 0.0228 distill.loss_1: 0.2068 distill.loss_2: 0.2467 distill.loss_3: 0.8961 2023/04/17 20:08:14 - mmengine - INFO - Epoch(train) [140][200/391] lr: 1.0000e-02 eta: 0:12:44 time: 0.0241 data_time: 0.0039 memory: 227 loss: 1.3493 student.loss: 0.0151 distill.loss_1: 0.1978 distill.loss_2: 0.2449 distill.loss_3: 0.8915 2023/04/17 20:08:17 - mmengine - INFO - Epoch(train) [140][300/391] lr: 1.0000e-02 eta: 0:12:41 time: 0.0241 data_time: 0.0038 memory: 227 loss: 1.5359 student.loss: 0.0734 distill.loss_1: 0.2078 distill.loss_2: 0.2465 distill.loss_3: 1.0082 2023/04/17 20:08:19 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:08:19 - mmengine - INFO - Saving checkpoint at 140 epochs 2023/04/17 20:08:26 - mmengine - INFO - Epoch(val) [140][79/79] accuracy/top1: 94.1800 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0091 2023/04/17 20:08:29 - mmengine - INFO - Epoch(train) [141][100/391] lr: 1.0000e-02 eta: 0:12:34 time: 0.0247 data_time: 0.0036 memory: 227 loss: 1.2885 student.loss: 0.0183 distill.loss_1: 0.1957 distill.loss_2: 0.2413 distill.loss_3: 0.8332 2023/04/17 20:08:31 - mmengine - INFO - Epoch(train) [141][200/391] lr: 1.0000e-02 eta: 0:12:30 time: 0.0251 data_time: 0.0037 memory: 227 loss: 1.4210 student.loss: 0.0255 distill.loss_1: 0.2068 distill.loss_2: 0.2480 distill.loss_3: 0.9407 2023/04/17 20:08:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:08:34 - mmengine - INFO - Epoch(train) [141][300/391] lr: 1.0000e-02 eta: 0:12:27 time: 0.0234 data_time: 0.0037 memory: 227 loss: 1.2990 student.loss: 0.0288 distill.loss_1: 0.1987 distill.loss_2: 0.2417 distill.loss_3: 0.8297 2023/04/17 20:08:36 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:08:36 - mmengine - INFO - Saving checkpoint at 141 epochs 2023/04/17 20:08:42 - mmengine - INFO - Epoch(val) [141][79/79] accuracy/top1: 94.0400 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0101 2023/04/17 20:08:45 - mmengine - INFO - Epoch(train) [142][100/391] lr: 1.0000e-02 eta: 0:12:20 time: 0.0250 data_time: 0.0036 memory: 227 loss: 1.3339 student.loss: 0.0112 distill.loss_1: 0.2043 distill.loss_2: 0.2453 distill.loss_3: 0.8730 2023/04/17 20:08:48 - mmengine - INFO - Epoch(train) [142][200/391] lr: 1.0000e-02 eta: 0:12:17 time: 0.0242 data_time: 0.0039 memory: 227 loss: 1.3596 student.loss: 0.0436 distill.loss_1: 0.1986 distill.loss_2: 0.2411 distill.loss_3: 0.8763 2023/04/17 20:08:55 - mmengine - INFO - Epoch(train) [142][300/391] lr: 1.0000e-02 eta: 0:12:15 time: 0.0644 data_time: 0.0040 memory: 227 loss: 1.3577 student.loss: 0.0080 distill.loss_1: 0.2037 distill.loss_2: 0.2446 distill.loss_3: 0.9015 2023/04/17 20:08:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:08:59 - mmengine - INFO - Saving checkpoint at 142 epochs 2023/04/17 20:09:05 - mmengine - INFO - Epoch(val) [142][79/79] accuracy/top1: 93.9300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 20:09:08 - mmengine - INFO - Epoch(train) [143][100/391] lr: 1.0000e-02 eta: 0:12:09 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.4808 student.loss: 0.0535 distill.loss_1: 0.2145 distill.loss_2: 0.2505 distill.loss_3: 0.9622 2023/04/17 20:09:10 - mmengine - INFO - Epoch(train) [143][200/391] lr: 1.0000e-02 eta: 0:12:06 time: 0.0235 data_time: 0.0039 memory: 227 loss: 1.3754 student.loss: 0.0298 distill.loss_1: 0.2043 distill.loss_2: 0.2463 distill.loss_3: 0.8950 2023/04/17 20:09:12 - mmengine - INFO - Epoch(train) [143][300/391] lr: 1.0000e-02 eta: 0:12:02 time: 0.0234 data_time: 0.0039 memory: 227 loss: 1.3756 student.loss: 0.0366 distill.loss_1: 0.2078 distill.loss_2: 0.2452 distill.loss_3: 0.8860 2023/04/17 20:09:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:09:15 - mmengine - INFO - Saving checkpoint at 143 epochs 2023/04/17 20:09:21 - mmengine - INFO - Epoch(val) [143][79/79] accuracy/top1: 94.1600 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 20:09:24 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:09:24 - mmengine - INFO - Epoch(train) [144][100/391] lr: 1.0000e-02 eta: 0:11:56 time: 0.0242 data_time: 0.0037 memory: 227 loss: 1.3829 student.loss: 0.0657 distill.loss_1: 0.1974 distill.loss_2: 0.2418 distill.loss_3: 0.8781 2023/04/17 20:09:26 - mmengine - INFO - Epoch(train) [144][200/391] lr: 1.0000e-02 eta: 0:11:52 time: 0.0237 data_time: 0.0036 memory: 227 loss: 1.3960 student.loss: 0.0093 distill.loss_1: 0.2050 distill.loss_2: 0.2430 distill.loss_3: 0.9387 2023/04/17 20:09:29 - mmengine - INFO - Epoch(train) [144][300/391] lr: 1.0000e-02 eta: 0:11:48 time: 0.0250 data_time: 0.0037 memory: 227 loss: 1.3729 student.loss: 0.0197 distill.loss_1: 0.2014 distill.loss_2: 0.2464 distill.loss_3: 0.9055 2023/04/17 20:09:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:09:31 - mmengine - INFO - Saving checkpoint at 144 epochs 2023/04/17 20:09:37 - mmengine - INFO - Epoch(val) [144][79/79] accuracy/top1: 94.0300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:09:40 - mmengine - INFO - Epoch(train) [145][100/391] lr: 1.0000e-02 eta: 0:11:42 time: 0.0445 data_time: 0.0171 memory: 227 loss: 1.4070 student.loss: 0.0346 distill.loss_1: 0.2075 distill.loss_2: 0.2503 distill.loss_3: 0.9145 2023/04/17 20:09:42 - mmengine - INFO - Epoch(train) [145][200/391] lr: 1.0000e-02 eta: 0:11:38 time: 0.0245 data_time: 0.0039 memory: 227 loss: 1.3735 student.loss: 0.0286 distill.loss_1: 0.2036 distill.loss_2: 0.2453 distill.loss_3: 0.8960 2023/04/17 20:09:45 - mmengine - INFO - Epoch(train) [145][300/391] lr: 1.0000e-02 eta: 0:11:35 time: 0.0248 data_time: 0.0039 memory: 227 loss: 1.4690 student.loss: 0.0695 distill.loss_1: 0.1973 distill.loss_2: 0.2420 distill.loss_3: 0.9602 2023/04/17 20:09:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:09:47 - mmengine - INFO - Saving checkpoint at 145 epochs 2023/04/17 20:09:53 - mmengine - INFO - Epoch(val) [145][79/79] accuracy/top1: 94.0500 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0098 2023/04/17 20:09:56 - mmengine - INFO - Epoch(train) [146][100/391] lr: 1.0000e-02 eta: 0:11:28 time: 0.0245 data_time: 0.0037 memory: 227 loss: 1.3338 student.loss: 0.0099 distill.loss_1: 0.2105 distill.loss_2: 0.2477 distill.loss_3: 0.8657 2023/04/17 20:09:59 - mmengine - INFO - Epoch(train) [146][200/391] lr: 1.0000e-02 eta: 0:11:25 time: 0.0241 data_time: 0.0036 memory: 227 loss: 1.4131 student.loss: 0.0878 distill.loss_1: 0.2028 distill.loss_2: 0.2444 distill.loss_3: 0.8781 2023/04/17 20:10:01 - mmengine - INFO - Epoch(train) [146][300/391] lr: 1.0000e-02 eta: 0:11:21 time: 0.0241 data_time: 0.0038 memory: 227 loss: 1.3857 student.loss: 0.0193 distill.loss_1: 0.2051 distill.loss_2: 0.2454 distill.loss_3: 0.9160 2023/04/17 20:10:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:03 - mmengine - INFO - Saving checkpoint at 146 epochs 2023/04/17 20:10:10 - mmengine - INFO - Epoch(val) [146][79/79] accuracy/top1: 93.9700 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:10:12 - mmengine - INFO - Epoch(train) [147][100/391] lr: 1.0000e-02 eta: 0:11:15 time: 0.0267 data_time: 0.0039 memory: 227 loss: 1.3638 student.loss: 0.0212 distill.loss_1: 0.2044 distill.loss_2: 0.2469 distill.loss_3: 0.8914 2023/04/17 20:10:15 - mmengine - INFO - Epoch(train) [147][200/391] lr: 1.0000e-02 eta: 0:11:11 time: 0.0272 data_time: 0.0042 memory: 227 loss: 1.3777 student.loss: 0.0190 distill.loss_1: 0.1995 distill.loss_2: 0.2464 distill.loss_3: 0.9127 2023/04/17 20:10:18 - mmengine - INFO - Epoch(train) [147][300/391] lr: 1.0000e-02 eta: 0:11:08 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.3824 student.loss: 0.0420 distill.loss_1: 0.1964 distill.loss_2: 0.2394 distill.loss_3: 0.9046 2023/04/17 20:10:20 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:20 - mmengine - INFO - Saving checkpoint at 147 epochs 2023/04/17 20:10:25 - mmengine - INFO - Epoch(val) [147][79/79] accuracy/top1: 94.0800 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0099 2023/04/17 20:10:28 - mmengine - INFO - Epoch(train) [148][100/391] lr: 1.0000e-02 eta: 0:11:01 time: 0.0237 data_time: 0.0039 memory: 227 loss: 1.3834 student.loss: 0.0342 distill.loss_1: 0.2018 distill.loss_2: 0.2421 distill.loss_3: 0.9054 2023/04/17 20:10:31 - mmengine - INFO - Epoch(train) [148][200/391] lr: 1.0000e-02 eta: 0:10:58 time: 0.0240 data_time: 0.0040 memory: 227 loss: 1.3409 student.loss: 0.0083 distill.loss_1: 0.2074 distill.loss_2: 0.2439 distill.loss_3: 0.8814 2023/04/17 20:10:34 - mmengine - INFO - Epoch(train) [148][300/391] lr: 1.0000e-02 eta: 0:10:55 time: 0.0240 data_time: 0.0037 memory: 227 loss: 1.3609 student.loss: 0.0287 distill.loss_1: 0.2056 distill.loss_2: 0.2441 distill.loss_3: 0.8825 2023/04/17 20:10:36 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:36 - mmengine - INFO - Saving checkpoint at 148 epochs 2023/04/17 20:10:42 - mmengine - INFO - Epoch(val) [148][79/79] accuracy/top1: 94.0200 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0096 2023/04/17 20:10:45 - mmengine - INFO - Epoch(train) [149][100/391] lr: 1.0000e-02 eta: 0:10:48 time: 0.0242 data_time: 0.0037 memory: 227 loss: 1.3938 student.loss: 0.0406 distill.loss_1: 0.2064 distill.loss_2: 0.2456 distill.loss_3: 0.9011 2023/04/17 20:10:46 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:48 - mmengine - INFO - Epoch(train) [149][200/391] lr: 1.0000e-02 eta: 0:10:45 time: 0.0239 data_time: 0.0036 memory: 227 loss: 1.3737 student.loss: 0.0315 distill.loss_1: 0.2049 distill.loss_2: 0.2463 distill.loss_3: 0.8911 2023/04/17 20:10:50 - mmengine - INFO - Epoch(train) [149][300/391] lr: 1.0000e-02 eta: 0:10:41 time: 0.0244 data_time: 0.0037 memory: 227 loss: 1.3394 student.loss: 0.0179 distill.loss_1: 0.2036 distill.loss_2: 0.2426 distill.loss_3: 0.8753 2023/04/17 20:10:52 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:10:52 - mmengine - INFO - Saving checkpoint at 149 epochs 2023/04/17 20:10:58 - mmengine - INFO - Epoch(val) [149][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0097 2023/04/17 20:11:01 - mmengine - INFO - Epoch(train) [150][100/391] lr: 1.0000e-02 eta: 0:10:35 time: 0.0267 data_time: 0.0039 memory: 227 loss: 1.4175 student.loss: 0.0387 distill.loss_1: 0.2098 distill.loss_2: 0.2542 distill.loss_3: 0.9147 2023/04/17 20:11:04 - mmengine - INFO - Epoch(train) [150][200/391] lr: 1.0000e-02 eta: 0:10:31 time: 0.0237 data_time: 0.0037 memory: 227 loss: 1.3741 student.loss: 0.0244 distill.loss_1: 0.1997 distill.loss_2: 0.2415 distill.loss_3: 0.9085 2023/04/17 20:11:06 - mmengine - INFO - Epoch(train) [150][300/391] lr: 1.0000e-02 eta: 0:10:28 time: 0.0240 data_time: 0.0036 memory: 227 loss: 1.3687 student.loss: 0.0264 distill.loss_1: 0.2011 distill.loss_2: 0.2459 distill.loss_3: 0.8953 2023/04/17 20:11:08 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:11:08 - mmengine - INFO - Saving checkpoint at 150 epochs 2023/04/17 20:11:14 - mmengine - INFO - Epoch(val) [150][79/79] accuracy/top1: 93.6500 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:11:17 - mmengine - INFO - Epoch(train) [151][100/391] lr: 1.0000e-03 eta: 0:10:21 time: 0.0238 data_time: 0.0038 memory: 227 loss: 1.3927 student.loss: 0.0469 distill.loss_1: 0.2064 distill.loss_2: 0.2486 distill.loss_3: 0.8908 2023/04/17 20:11:19 - mmengine - INFO - Epoch(train) [151][200/391] lr: 1.0000e-03 eta: 0:10:18 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.4514 student.loss: 0.0073 distill.loss_1: 0.2243 distill.loss_2: 0.2528 distill.loss_3: 0.9671 2023/04/17 20:11:22 - mmengine - INFO - Epoch(train) [151][300/391] lr: 1.0000e-03 eta: 0:10:14 time: 0.0247 data_time: 0.0037 memory: 227 loss: 1.3538 student.loss: 0.0188 distill.loss_1: 0.2014 distill.loss_2: 0.2445 distill.loss_3: 0.8890 2023/04/17 20:11:23 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:11:24 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:11:24 - mmengine - INFO - Saving checkpoint at 151 epochs 2023/04/17 20:11:30 - mmengine - INFO - Epoch(val) [151][79/79] accuracy/top1: 94.0000 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:11:33 - mmengine - INFO - Epoch(train) [152][100/391] lr: 1.0000e-03 eta: 0:10:08 time: 0.0242 data_time: 0.0041 memory: 227 loss: 1.3134 student.loss: 0.0336 distill.loss_1: 0.2029 distill.loss_2: 0.2433 distill.loss_3: 0.8336 2023/04/17 20:11:35 - mmengine - INFO - Epoch(train) [152][200/391] lr: 1.0000e-03 eta: 0:10:05 time: 0.0240 data_time: 0.0041 memory: 227 loss: 1.2573 student.loss: 0.0096 distill.loss_1: 0.2012 distill.loss_2: 0.2422 distill.loss_3: 0.8043 2023/04/17 20:11:38 - mmengine - INFO - Epoch(train) [152][300/391] lr: 1.0000e-03 eta: 0:10:01 time: 0.0240 data_time: 0.0041 memory: 227 loss: 1.4095 student.loss: 0.0500 distill.loss_1: 0.1971 distill.loss_2: 0.2400 distill.loss_3: 0.9223 2023/04/17 20:11:40 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:11:40 - mmengine - INFO - Saving checkpoint at 152 epochs 2023/04/17 20:11:47 - mmengine - INFO - Epoch(val) [152][79/79] accuracy/top1: 94.0000 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0095 2023/04/17 20:11:49 - mmengine - INFO - Epoch(train) [153][100/391] lr: 1.0000e-03 eta: 0:09:55 time: 0.0273 data_time: 0.0039 memory: 227 loss: 1.3951 student.loss: 0.0211 distill.loss_1: 0.2041 distill.loss_2: 0.2450 distill.loss_3: 0.9250 2023/04/17 20:11:52 - mmengine - INFO - Epoch(train) [153][200/391] lr: 1.0000e-03 eta: 0:09:51 time: 0.0240 data_time: 0.0039 memory: 227 loss: 1.2654 student.loss: 0.0115 distill.loss_1: 0.1952 distill.loss_2: 0.2398 distill.loss_3: 0.8189 2023/04/17 20:11:54 - mmengine - INFO - Epoch(train) [153][300/391] lr: 1.0000e-03 eta: 0:09:48 time: 0.0247 data_time: 0.0039 memory: 227 loss: 1.4303 student.loss: 0.0367 distill.loss_1: 0.2013 distill.loss_2: 0.2442 distill.loss_3: 0.9481 2023/04/17 20:11:56 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:11:56 - mmengine - INFO - Saving checkpoint at 153 epochs 2023/04/17 20:12:02 - mmengine - INFO - Epoch(val) [153][79/79] accuracy/top1: 94.1200 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0096 2023/04/17 20:12:06 - mmengine - INFO - Epoch(train) [154][100/391] lr: 1.0000e-03 eta: 0:09:42 time: 0.0248 data_time: 0.0037 memory: 227 loss: 1.3850 student.loss: 0.0273 distill.loss_1: 0.1970 distill.loss_2: 0.2416 distill.loss_3: 0.9192 2023/04/17 20:12:07 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:12:08 - mmengine - INFO - Epoch(train) [154][200/391] lr: 1.0000e-03 eta: 0:09:38 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.3701 student.loss: 0.0180 distill.loss_1: 0.2074 distill.loss_2: 0.2490 distill.loss_3: 0.8956 2023/04/17 20:12:11 - mmengine - INFO - Epoch(train) [154][300/391] lr: 1.0000e-03 eta: 0:09:35 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.3446 student.loss: 0.0136 distill.loss_1: 0.2013 distill.loss_2: 0.2399 distill.loss_3: 0.8897 2023/04/17 20:12:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:12:13 - mmengine - INFO - Saving checkpoint at 154 epochs 2023/04/17 20:12:19 - mmengine - INFO - Epoch(val) [154][79/79] accuracy/top1: 94.0900 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0097 2023/04/17 20:12:21 - mmengine - INFO - Epoch(train) [155][100/391] lr: 1.0000e-03 eta: 0:09:28 time: 0.0248 data_time: 0.0037 memory: 227 loss: 1.3286 student.loss: 0.0046 distill.loss_1: 0.2030 distill.loss_2: 0.2426 distill.loss_3: 0.8784 2023/04/17 20:12:24 - mmengine - INFO - Epoch(train) [155][200/391] lr: 1.0000e-03 eta: 0:09:25 time: 0.0236 data_time: 0.0037 memory: 227 loss: 1.3006 student.loss: 0.0337 distill.loss_1: 0.1990 distill.loss_2: 0.2392 distill.loss_3: 0.8287 2023/04/17 20:12:26 - mmengine - INFO - Epoch(train) [155][300/391] lr: 1.0000e-03 eta: 0:09:22 time: 0.0235 data_time: 0.0039 memory: 227 loss: 1.3072 student.loss: 0.0133 distill.loss_1: 0.2017 distill.loss_2: 0.2404 distill.loss_3: 0.8519 2023/04/17 20:12:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:12:29 - mmengine - INFO - Saving checkpoint at 155 epochs 2023/04/17 20:12:35 - mmengine - INFO - Epoch(val) [155][79/79] accuracy/top1: 94.1200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:12:38 - mmengine - INFO - Epoch(train) [156][100/391] lr: 1.0000e-03 eta: 0:09:15 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.3652 student.loss: 0.0111 distill.loss_1: 0.2039 distill.loss_2: 0.2424 distill.loss_3: 0.9078 2023/04/17 20:12:40 - mmengine - INFO - Epoch(train) [156][200/391] lr: 1.0000e-03 eta: 0:09:12 time: 0.0245 data_time: 0.0037 memory: 227 loss: 1.3349 student.loss: 0.0417 distill.loss_1: 0.2017 distill.loss_2: 0.2420 distill.loss_3: 0.8495 2023/04/17 20:12:43 - mmengine - INFO - Epoch(train) [156][300/391] lr: 1.0000e-03 eta: 0:09:08 time: 0.0253 data_time: 0.0051 memory: 227 loss: 1.3084 student.loss: 0.0269 distill.loss_1: 0.1970 distill.loss_2: 0.2406 distill.loss_3: 0.8438 2023/04/17 20:12:45 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:12:45 - mmengine - INFO - Saving checkpoint at 156 epochs 2023/04/17 20:12:51 - mmengine - INFO - Epoch(val) [156][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0098 2023/04/17 20:12:51 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:12:53 - mmengine - INFO - Epoch(train) [157][100/391] lr: 1.0000e-03 eta: 0:09:02 time: 0.0235 data_time: 0.0036 memory: 227 loss: 1.3096 student.loss: 0.0050 distill.loss_1: 0.2055 distill.loss_2: 0.2441 distill.loss_3: 0.8550 2023/04/17 20:12:56 - mmengine - INFO - Epoch(train) [157][200/391] lr: 1.0000e-03 eta: 0:08:59 time: 0.0232 data_time: 0.0038 memory: 227 loss: 1.3112 student.loss: 0.0047 distill.loss_1: 0.1986 distill.loss_2: 0.2413 distill.loss_3: 0.8666 2023/04/17 20:12:58 - mmengine - INFO - Epoch(train) [157][300/391] lr: 1.0000e-03 eta: 0:08:55 time: 0.0235 data_time: 0.0037 memory: 227 loss: 1.3285 student.loss: 0.0157 distill.loss_1: 0.1975 distill.loss_2: 0.2410 distill.loss_3: 0.8743 2023/04/17 20:13:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:13:01 - mmengine - INFO - Saving checkpoint at 157 epochs 2023/04/17 20:13:07 - mmengine - INFO - Epoch(val) [157][79/79] accuracy/top1: 94.1500 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0097 2023/04/17 20:13:10 - mmengine - INFO - Epoch(train) [158][100/391] lr: 1.0000e-03 eta: 0:08:49 time: 0.0257 data_time: 0.0039 memory: 227 loss: 1.3789 student.loss: 0.0228 distill.loss_1: 0.1982 distill.loss_2: 0.2432 distill.loss_3: 0.9147 2023/04/17 20:13:12 - mmengine - INFO - Epoch(train) [158][200/391] lr: 1.0000e-03 eta: 0:08:46 time: 0.0237 data_time: 0.0039 memory: 227 loss: 1.3415 student.loss: 0.0093 distill.loss_1: 0.1980 distill.loss_2: 0.2428 distill.loss_3: 0.8913 2023/04/17 20:13:15 - mmengine - INFO - Epoch(train) [158][300/391] lr: 1.0000e-03 eta: 0:08:42 time: 0.0240 data_time: 0.0040 memory: 227 loss: 1.2774 student.loss: 0.0087 distill.loss_1: 0.2035 distill.loss_2: 0.2435 distill.loss_3: 0.8216 2023/04/17 20:13:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:13:17 - mmengine - INFO - Saving checkpoint at 158 epochs 2023/04/17 20:13:23 - mmengine - INFO - Epoch(val) [158][79/79] accuracy/top1: 94.1900 teacher.accuracy/top1: 95.4400data_time: 0.0036 time: 0.0103 2023/04/17 20:13:26 - mmengine - INFO - Epoch(train) [159][100/391] lr: 1.0000e-03 eta: 0:08:36 time: 0.0348 data_time: 0.0039 memory: 227 loss: 1.3940 student.loss: 0.0130 distill.loss_1: 0.2019 distill.loss_2: 0.2430 distill.loss_3: 0.9362 2023/04/17 20:13:28 - mmengine - INFO - Epoch(train) [159][200/391] lr: 1.0000e-03 eta: 0:08:33 time: 0.0244 data_time: 0.0037 memory: 227 loss: 1.4327 student.loss: 0.0472 distill.loss_1: 0.2030 distill.loss_2: 0.2437 distill.loss_3: 0.9388 2023/04/17 20:13:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:13:31 - mmengine - INFO - Epoch(train) [159][300/391] lr: 1.0000e-03 eta: 0:08:29 time: 0.0244 data_time: 0.0037 memory: 227 loss: 1.3077 student.loss: 0.0076 distill.loss_1: 0.1993 distill.loss_2: 0.2401 distill.loss_3: 0.8608 2023/04/17 20:13:34 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:13:34 - mmengine - INFO - Saving checkpoint at 159 epochs 2023/04/17 20:13:40 - mmengine - INFO - Epoch(val) [159][79/79] accuracy/top1: 94.0600 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 20:13:43 - mmengine - INFO - Epoch(train) [160][100/391] lr: 1.0000e-03 eta: 0:08:23 time: 0.0240 data_time: 0.0039 memory: 227 loss: 1.3103 student.loss: 0.0123 distill.loss_1: 0.2043 distill.loss_2: 0.2444 distill.loss_3: 0.8494 2023/04/17 20:13:45 - mmengine - INFO - Epoch(train) [160][200/391] lr: 1.0000e-03 eta: 0:08:20 time: 0.0249 data_time: 0.0037 memory: 227 loss: 1.3201 student.loss: 0.0192 distill.loss_1: 0.2032 distill.loss_2: 0.2433 distill.loss_3: 0.8544 2023/04/17 20:13:48 - mmengine - INFO - Epoch(train) [160][300/391] lr: 1.0000e-03 eta: 0:08:17 time: 0.0247 data_time: 0.0037 memory: 227 loss: 1.3441 student.loss: 0.0143 distill.loss_1: 0.2014 distill.loss_2: 0.2428 distill.loss_3: 0.8856 2023/04/17 20:13:50 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:13:50 - mmengine - INFO - Saving checkpoint at 160 epochs 2023/04/17 20:13:57 - mmengine - INFO - Epoch(val) [160][79/79] accuracy/top1: 94.1200 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0098 2023/04/17 20:13:59 - mmengine - INFO - Epoch(train) [161][100/391] lr: 1.0000e-03 eta: 0:08:10 time: 0.0238 data_time: 0.0042 memory: 227 loss: 1.3353 student.loss: 0.0196 distill.loss_1: 0.2040 distill.loss_2: 0.2438 distill.loss_3: 0.8679 2023/04/17 20:14:02 - mmengine - INFO - Epoch(train) [161][200/391] lr: 1.0000e-03 eta: 0:08:07 time: 0.0240 data_time: 0.0039 memory: 227 loss: 1.3088 student.loss: 0.0119 distill.loss_1: 0.1976 distill.loss_2: 0.2372 distill.loss_3: 0.8621 2023/04/17 20:14:04 - mmengine - INFO - Epoch(train) [161][300/391] lr: 1.0000e-03 eta: 0:08:04 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.3555 student.loss: 0.0084 distill.loss_1: 0.1998 distill.loss_2: 0.2438 distill.loss_3: 0.9036 2023/04/17 20:14:07 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:07 - mmengine - INFO - Saving checkpoint at 161 epochs 2023/04/17 20:14:12 - mmengine - INFO - Epoch(val) [161][79/79] accuracy/top1: 94.2200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0095 2023/04/17 20:14:14 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:15 - mmengine - INFO - Epoch(train) [162][100/391] lr: 1.0000e-03 eta: 0:07:57 time: 0.0245 data_time: 0.0038 memory: 227 loss: 1.3148 student.loss: 0.0072 distill.loss_1: 0.2023 distill.loss_2: 0.2403 distill.loss_3: 0.8650 2023/04/17 20:14:18 - mmengine - INFO - Epoch(train) [162][200/391] lr: 1.0000e-03 eta: 0:07:54 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.3858 student.loss: 0.0320 distill.loss_1: 0.2032 distill.loss_2: 0.2383 distill.loss_3: 0.9123 2023/04/17 20:14:20 - mmengine - INFO - Epoch(train) [162][300/391] lr: 1.0000e-03 eta: 0:07:51 time: 0.0255 data_time: 0.0037 memory: 227 loss: 1.2990 student.loss: 0.0201 distill.loss_1: 0.2004 distill.loss_2: 0.2438 distill.loss_3: 0.8347 2023/04/17 20:14:23 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:23 - mmengine - INFO - Saving checkpoint at 162 epochs 2023/04/17 20:14:29 - mmengine - INFO - Epoch(val) [162][79/79] accuracy/top1: 94.2300 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0093 2023/04/17 20:14:31 - mmengine - INFO - Epoch(train) [163][100/391] lr: 1.0000e-03 eta: 0:07:45 time: 0.0249 data_time: 0.0037 memory: 227 loss: 1.2703 student.loss: 0.0085 distill.loss_1: 0.1986 distill.loss_2: 0.2412 distill.loss_3: 0.8220 2023/04/17 20:14:34 - mmengine - INFO - Epoch(train) [163][200/391] lr: 1.0000e-03 eta: 0:07:41 time: 0.0244 data_time: 0.0038 memory: 227 loss: 1.3604 student.loss: 0.0101 distill.loss_1: 0.2076 distill.loss_2: 0.2497 distill.loss_3: 0.8930 2023/04/17 20:14:36 - mmengine - INFO - Epoch(train) [163][300/391] lr: 1.0000e-03 eta: 0:07:38 time: 0.0243 data_time: 0.0038 memory: 227 loss: 1.3029 student.loss: 0.0446 distill.loss_1: 0.2010 distill.loss_2: 0.2392 distill.loss_3: 0.8180 2023/04/17 20:14:39 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:39 - mmengine - INFO - Saving checkpoint at 163 epochs 2023/04/17 20:14:44 - mmengine - INFO - Epoch(val) [163][79/79] accuracy/top1: 94.2400 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0098 2023/04/17 20:14:47 - mmengine - INFO - Epoch(train) [164][100/391] lr: 1.0000e-03 eta: 0:07:32 time: 0.0237 data_time: 0.0037 memory: 227 loss: 1.3907 student.loss: 0.0128 distill.loss_1: 0.2083 distill.loss_2: 0.2501 distill.loss_3: 0.9195 2023/04/17 20:14:50 - mmengine - INFO - Epoch(train) [164][200/391] lr: 1.0000e-03 eta: 0:07:28 time: 0.0233 data_time: 0.0038 memory: 227 loss: 1.3758 student.loss: 0.0251 distill.loss_1: 0.2019 distill.loss_2: 0.2403 distill.loss_3: 0.9086 2023/04/17 20:14:51 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:52 - mmengine - INFO - Epoch(train) [164][300/391] lr: 1.0000e-03 eta: 0:07:25 time: 0.0236 data_time: 0.0039 memory: 227 loss: 1.3190 student.loss: 0.0097 distill.loss_1: 0.2107 distill.loss_2: 0.2451 distill.loss_3: 0.8535 2023/04/17 20:14:54 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:14:54 - mmengine - INFO - Saving checkpoint at 164 epochs 2023/04/17 20:15:01 - mmengine - INFO - Epoch(val) [164][79/79] accuracy/top1: 94.1600 teacher.accuracy/top1: 95.4400data_time: 0.0035 time: 0.0098 2023/04/17 20:15:04 - mmengine - INFO - Epoch(train) [165][100/391] lr: 1.0000e-03 eta: 0:07:19 time: 0.0249 data_time: 0.0037 memory: 227 loss: 1.4018 student.loss: 0.0510 distill.loss_1: 0.2023 distill.loss_2: 0.2453 distill.loss_3: 0.9033 2023/04/17 20:15:06 - mmengine - INFO - Epoch(train) [165][200/391] lr: 1.0000e-03 eta: 0:07:15 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.2694 student.loss: 0.0094 distill.loss_1: 0.2007 distill.loss_2: 0.2427 distill.loss_3: 0.8166 2023/04/17 20:15:09 - mmengine - INFO - Epoch(train) [165][300/391] lr: 1.0000e-03 eta: 0:07:12 time: 0.0246 data_time: 0.0036 memory: 227 loss: 1.2955 student.loss: 0.0118 distill.loss_1: 0.1942 distill.loss_2: 0.2372 distill.loss_3: 0.8523 2023/04/17 20:15:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:15:11 - mmengine - INFO - Saving checkpoint at 165 epochs 2023/04/17 20:15:17 - mmengine - INFO - Epoch(val) [165][79/79] accuracy/top1: 94.3100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0098 2023/04/17 20:15:20 - mmengine - INFO - Epoch(train) [166][100/391] lr: 1.0000e-03 eta: 0:07:06 time: 0.0236 data_time: 0.0040 memory: 227 loss: 1.3248 student.loss: 0.0205 distill.loss_1: 0.1947 distill.loss_2: 0.2402 distill.loss_3: 0.8695 2023/04/17 20:15:22 - mmengine - INFO - Epoch(train) [166][200/391] lr: 1.0000e-03 eta: 0:07:03 time: 0.0244 data_time: 0.0043 memory: 227 loss: 1.3368 student.loss: 0.0102 distill.loss_1: 0.1991 distill.loss_2: 0.2409 distill.loss_3: 0.8866 2023/04/17 20:15:25 - mmengine - INFO - Epoch(train) [166][300/391] lr: 1.0000e-03 eta: 0:07:00 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.3676 student.loss: 0.0291 distill.loss_1: 0.2054 distill.loss_2: 0.2396 distill.loss_3: 0.8935 2023/04/17 20:15:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:15:27 - mmengine - INFO - Saving checkpoint at 166 epochs 2023/04/17 20:15:33 - mmengine - INFO - Epoch(val) [166][79/79] accuracy/top1: 94.2300 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 20:15:37 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:15:37 - mmengine - INFO - Epoch(train) [167][100/391] lr: 1.0000e-03 eta: 0:06:53 time: 0.0245 data_time: 0.0038 memory: 227 loss: 1.3127 student.loss: 0.0073 distill.loss_1: 0.1996 distill.loss_2: 0.2454 distill.loss_3: 0.8604 2023/04/17 20:15:39 - mmengine - INFO - Epoch(train) [167][200/391] lr: 1.0000e-03 eta: 0:06:50 time: 0.0295 data_time: 0.0039 memory: 227 loss: 1.4091 student.loss: 0.0538 distill.loss_1: 0.2067 distill.loss_2: 0.2435 distill.loss_3: 0.9051 2023/04/17 20:15:42 - mmengine - INFO - Epoch(train) [167][300/391] lr: 1.0000e-03 eta: 0:06:47 time: 0.0237 data_time: 0.0037 memory: 227 loss: 1.2994 student.loss: 0.0140 distill.loss_1: 0.2082 distill.loss_2: 0.2426 distill.loss_3: 0.8346 2023/04/17 20:15:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:15:44 - mmengine - INFO - Saving checkpoint at 167 epochs 2023/04/17 20:15:51 - mmengine - INFO - Epoch(val) [167][79/79] accuracy/top1: 94.2400 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:15:54 - mmengine - INFO - Epoch(train) [168][100/391] lr: 1.0000e-03 eta: 0:06:41 time: 0.0241 data_time: 0.0038 memory: 227 loss: 1.4292 student.loss: 0.0283 distill.loss_1: 0.2097 distill.loss_2: 0.2490 distill.loss_3: 0.9423 2023/04/17 20:15:57 - mmengine - INFO - Epoch(train) [168][200/391] lr: 1.0000e-03 eta: 0:06:38 time: 0.0240 data_time: 0.0039 memory: 227 loss: 1.3963 student.loss: 0.0142 distill.loss_1: 0.2047 distill.loss_2: 0.2465 distill.loss_3: 0.9310 2023/04/17 20:15:59 - mmengine - INFO - Epoch(train) [168][300/391] lr: 1.0000e-03 eta: 0:06:34 time: 0.0240 data_time: 0.0037 memory: 227 loss: 1.3353 student.loss: 0.0538 distill.loss_1: 0.1977 distill.loss_2: 0.2384 distill.loss_3: 0.8454 2023/04/17 20:16:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:16:02 - mmengine - INFO - Saving checkpoint at 168 epochs 2023/04/17 20:16:07 - mmengine - INFO - Epoch(val) [168][79/79] accuracy/top1: 94.2100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0097 2023/04/17 20:16:10 - mmengine - INFO - Epoch(train) [169][100/391] lr: 1.0000e-03 eta: 0:06:28 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.4152 student.loss: 0.0510 distill.loss_1: 0.1998 distill.loss_2: 0.2428 distill.loss_3: 0.9216 2023/04/17 20:16:12 - mmengine - INFO - Epoch(train) [169][200/391] lr: 1.0000e-03 eta: 0:06:25 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.4899 student.loss: 0.0365 distill.loss_1: 0.2101 distill.loss_2: 0.2466 distill.loss_3: 0.9967 2023/04/17 20:16:15 - mmengine - INFO - Epoch(train) [169][300/391] lr: 1.0000e-03 eta: 0:06:22 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.2930 student.loss: 0.0169 distill.loss_1: 0.1999 distill.loss_2: 0.2409 distill.loss_3: 0.8353 2023/04/17 20:16:15 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:16:17 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:16:18 - mmengine - INFO - Saving checkpoint at 169 epochs 2023/04/17 20:16:23 - mmengine - INFO - Epoch(val) [169][79/79] accuracy/top1: 94.2400 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:16:27 - mmengine - INFO - Epoch(train) [170][100/391] lr: 1.0000e-03 eta: 0:06:16 time: 0.0245 data_time: 0.0039 memory: 227 loss: 1.3315 student.loss: 0.0227 distill.loss_1: 0.2027 distill.loss_2: 0.2441 distill.loss_3: 0.8621 2023/04/17 20:16:29 - mmengine - INFO - Epoch(train) [170][200/391] lr: 1.0000e-03 eta: 0:06:12 time: 0.0246 data_time: 0.0038 memory: 227 loss: 1.3175 student.loss: 0.0099 distill.loss_1: 0.2040 distill.loss_2: 0.2435 distill.loss_3: 0.8601 2023/04/17 20:16:32 - mmengine - INFO - Epoch(train) [170][300/391] lr: 1.0000e-03 eta: 0:06:09 time: 0.0245 data_time: 0.0038 memory: 227 loss: 1.3885 student.loss: 0.0266 distill.loss_1: 0.2052 distill.loss_2: 0.2460 distill.loss_3: 0.9108 2023/04/17 20:16:34 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:16:34 - mmengine - INFO - Saving checkpoint at 170 epochs 2023/04/17 20:16:40 - mmengine - INFO - Epoch(val) [170][79/79] accuracy/top1: 94.1300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0094 2023/04/17 20:16:44 - mmengine - INFO - Epoch(train) [171][100/391] lr: 1.0000e-03 eta: 0:06:03 time: 0.0252 data_time: 0.0038 memory: 227 loss: 1.3128 student.loss: 0.0174 distill.loss_1: 0.1997 distill.loss_2: 0.2417 distill.loss_3: 0.8540 2023/04/17 20:16:46 - mmengine - INFO - Epoch(train) [171][200/391] lr: 1.0000e-03 eta: 0:06:00 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.3064 student.loss: 0.0295 distill.loss_1: 0.1943 distill.loss_2: 0.2369 distill.loss_3: 0.8458 2023/04/17 20:16:49 - mmengine - INFO - Epoch(train) [171][300/391] lr: 1.0000e-03 eta: 0:05:57 time: 0.0240 data_time: 0.0037 memory: 227 loss: 1.3047 student.loss: 0.0215 distill.loss_1: 0.1982 distill.loss_2: 0.2398 distill.loss_3: 0.8452 2023/04/17 20:16:51 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:16:51 - mmengine - INFO - Saving checkpoint at 171 epochs 2023/04/17 20:16:57 - mmengine - INFO - Epoch(val) [171][79/79] accuracy/top1: 94.3000 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:17:00 - mmengine - INFO - Epoch(train) [172][100/391] lr: 1.0000e-03 eta: 0:05:50 time: 0.0246 data_time: 0.0041 memory: 227 loss: 1.3166 student.loss: 0.0144 distill.loss_1: 0.2015 distill.loss_2: 0.2414 distill.loss_3: 0.8594 2023/04/17 20:17:01 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:02 - mmengine - INFO - Epoch(train) [172][200/391] lr: 1.0000e-03 eta: 0:05:47 time: 0.0251 data_time: 0.0041 memory: 227 loss: 1.2907 student.loss: 0.0167 distill.loss_1: 0.1961 distill.loss_2: 0.2370 distill.loss_3: 0.8410 2023/04/17 20:17:05 - mmengine - INFO - Epoch(train) [172][300/391] lr: 1.0000e-03 eta: 0:05:44 time: 0.0251 data_time: 0.0043 memory: 227 loss: 1.3592 student.loss: 0.0518 distill.loss_1: 0.2030 distill.loss_2: 0.2417 distill.loss_3: 0.8627 2023/04/17 20:17:07 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:07 - mmengine - INFO - Saving checkpoint at 172 epochs 2023/04/17 20:17:13 - mmengine - INFO - Epoch(val) [172][79/79] accuracy/top1: 94.1300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0094 2023/04/17 20:17:17 - mmengine - INFO - Epoch(train) [173][100/391] lr: 1.0000e-03 eta: 0:05:38 time: 0.0352 data_time: 0.0037 memory: 227 loss: 1.3316 student.loss: 0.0256 distill.loss_1: 0.2045 distill.loss_2: 0.2405 distill.loss_3: 0.8610 2023/04/17 20:17:19 - mmengine - INFO - Epoch(train) [173][200/391] lr: 1.0000e-03 eta: 0:05:35 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.2945 student.loss: 0.0216 distill.loss_1: 0.2047 distill.loss_2: 0.2431 distill.loss_3: 0.8251 2023/04/17 20:17:22 - mmengine - INFO - Epoch(train) [173][300/391] lr: 1.0000e-03 eta: 0:05:31 time: 0.0241 data_time: 0.0041 memory: 227 loss: 1.3301 student.loss: 0.0055 distill.loss_1: 0.1959 distill.loss_2: 0.2408 distill.loss_3: 0.8878 2023/04/17 20:17:24 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:24 - mmengine - INFO - Saving checkpoint at 173 epochs 2023/04/17 20:17:30 - mmengine - INFO - Epoch(val) [173][79/79] accuracy/top1: 94.1000 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:17:33 - mmengine - INFO - Epoch(train) [174][100/391] lr: 1.0000e-03 eta: 0:05:25 time: 0.0242 data_time: 0.0037 memory: 227 loss: 1.3789 student.loss: 0.0156 distill.loss_1: 0.2028 distill.loss_2: 0.2444 distill.loss_3: 0.9161 2023/04/17 20:17:35 - mmengine - INFO - Epoch(train) [174][200/391] lr: 1.0000e-03 eta: 0:05:22 time: 0.0242 data_time: 0.0039 memory: 227 loss: 1.3659 student.loss: 0.0321 distill.loss_1: 0.2085 distill.loss_2: 0.2400 distill.loss_3: 0.8853 2023/04/17 20:17:37 - mmengine - INFO - Epoch(train) [174][300/391] lr: 1.0000e-03 eta: 0:05:19 time: 0.0241 data_time: 0.0038 memory: 227 loss: 1.3283 student.loss: 0.0249 distill.loss_1: 0.1979 distill.loss_2: 0.2385 distill.loss_3: 0.8669 2023/04/17 20:17:39 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:40 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:40 - mmengine - INFO - Saving checkpoint at 174 epochs 2023/04/17 20:17:45 - mmengine - INFO - Epoch(val) [174][79/79] accuracy/top1: 94.2300 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0093 2023/04/17 20:17:49 - mmengine - INFO - Epoch(train) [175][100/391] lr: 1.0000e-03 eta: 0:05:13 time: 0.0244 data_time: 0.0039 memory: 227 loss: 1.3635 student.loss: 0.0169 distill.loss_1: 0.1999 distill.loss_2: 0.2408 distill.loss_3: 0.9058 2023/04/17 20:17:51 - mmengine - INFO - Epoch(train) [175][200/391] lr: 1.0000e-03 eta: 0:05:10 time: 0.0243 data_time: 0.0039 memory: 227 loss: 1.2870 student.loss: 0.0055 distill.loss_1: 0.2033 distill.loss_2: 0.2427 distill.loss_3: 0.8356 2023/04/17 20:17:54 - mmengine - INFO - Epoch(train) [175][300/391] lr: 1.0000e-03 eta: 0:05:07 time: 0.0246 data_time: 0.0039 memory: 227 loss: 1.3615 student.loss: 0.0362 distill.loss_1: 0.1960 distill.loss_2: 0.2426 distill.loss_3: 0.8867 2023/04/17 20:17:56 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:17:56 - mmengine - INFO - Saving checkpoint at 175 epochs 2023/04/17 20:18:02 - mmengine - INFO - Epoch(val) [175][79/79] accuracy/top1: 94.1800 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:18:05 - mmengine - INFO - Epoch(train) [176][100/391] lr: 1.0000e-03 eta: 0:05:00 time: 0.0246 data_time: 0.0037 memory: 227 loss: 1.3295 student.loss: 0.0083 distill.loss_1: 0.1948 distill.loss_2: 0.2381 distill.loss_3: 0.8882 2023/04/17 20:18:08 - mmengine - INFO - Epoch(train) [176][200/391] lr: 1.0000e-03 eta: 0:04:57 time: 0.0246 data_time: 0.0040 memory: 227 loss: 1.3770 student.loss: 0.0353 distill.loss_1: 0.2019 distill.loss_2: 0.2416 distill.loss_3: 0.8982 2023/04/17 20:18:11 - mmengine - INFO - Epoch(train) [176][300/391] lr: 1.0000e-03 eta: 0:04:54 time: 0.0245 data_time: 0.0040 memory: 227 loss: 1.3582 student.loss: 0.0093 distill.loss_1: 0.2000 distill.loss_2: 0.2416 distill.loss_3: 0.9073 2023/04/17 20:18:13 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:18:13 - mmengine - INFO - Saving checkpoint at 176 epochs 2023/04/17 20:18:19 - mmengine - INFO - Epoch(val) [176][79/79] accuracy/top1: 94.2400 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:18:22 - mmengine - INFO - Epoch(train) [177][100/391] lr: 1.0000e-03 eta: 0:04:48 time: 0.0242 data_time: 0.0038 memory: 227 loss: 1.3572 student.loss: 0.0108 distill.loss_1: 0.2029 distill.loss_2: 0.2435 distill.loss_3: 0.9000 2023/04/17 20:18:24 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:18:25 - mmengine - INFO - Epoch(train) [177][200/391] lr: 1.0000e-03 eta: 0:04:45 time: 0.0242 data_time: 0.0038 memory: 227 loss: 1.3065 student.loss: 0.0202 distill.loss_1: 0.2072 distill.loss_2: 0.2468 distill.loss_3: 0.8322 2023/04/17 20:18:27 - mmengine - INFO - Epoch(train) [177][300/391] lr: 1.0000e-03 eta: 0:04:42 time: 0.0239 data_time: 0.0037 memory: 227 loss: 1.3034 student.loss: 0.0170 distill.loss_1: 0.2056 distill.loss_2: 0.2436 distill.loss_3: 0.8372 2023/04/17 20:18:29 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:18:30 - mmengine - INFO - Saving checkpoint at 177 epochs 2023/04/17 20:18:35 - mmengine - INFO - Epoch(val) [177][79/79] accuracy/top1: 94.2700 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 20:18:38 - mmengine - INFO - Epoch(train) [178][100/391] lr: 1.0000e-03 eta: 0:04:36 time: 0.0251 data_time: 0.0040 memory: 227 loss: 1.2730 student.loss: 0.0106 distill.loss_1: 0.1974 distill.loss_2: 0.2404 distill.loss_3: 0.8246 2023/04/17 20:18:41 - mmengine - INFO - Epoch(train) [178][200/391] lr: 1.0000e-03 eta: 0:04:32 time: 0.0247 data_time: 0.0038 memory: 227 loss: 1.3419 student.loss: 0.0253 distill.loss_1: 0.2020 distill.loss_2: 0.2424 distill.loss_3: 0.8722 2023/04/17 20:18:43 - mmengine - INFO - Epoch(train) [178][300/391] lr: 1.0000e-03 eta: 0:04:29 time: 0.0252 data_time: 0.0038 memory: 227 loss: 1.3220 student.loss: 0.0325 distill.loss_1: 0.1941 distill.loss_2: 0.2359 distill.loss_3: 0.8596 2023/04/17 20:18:45 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:18:45 - mmengine - INFO - Saving checkpoint at 178 epochs 2023/04/17 20:18:52 - mmengine - INFO - Epoch(val) [178][79/79] accuracy/top1: 94.1700 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 20:18:55 - mmengine - INFO - Epoch(train) [179][100/391] lr: 1.0000e-03 eta: 0:04:23 time: 0.0263 data_time: 0.0037 memory: 227 loss: 1.3632 student.loss: 0.0093 distill.loss_1: 0.2078 distill.loss_2: 0.2437 distill.loss_3: 0.9025 2023/04/17 20:18:57 - mmengine - INFO - Epoch(train) [179][200/391] lr: 1.0000e-03 eta: 0:04:20 time: 0.0244 data_time: 0.0038 memory: 227 loss: 1.3142 student.loss: 0.0181 distill.loss_1: 0.1982 distill.loss_2: 0.2444 distill.loss_3: 0.8536 2023/04/17 20:19:00 - mmengine - INFO - Epoch(train) [179][300/391] lr: 1.0000e-03 eta: 0:04:17 time: 0.0240 data_time: 0.0038 memory: 227 loss: 1.3491 student.loss: 0.0142 distill.loss_1: 0.2050 distill.loss_2: 0.2455 distill.loss_3: 0.8843 2023/04/17 20:19:02 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:02 - mmengine - INFO - Saving checkpoint at 179 epochs 2023/04/17 20:19:08 - mmengine - INFO - Epoch(val) [179][79/79] accuracy/top1: 94.2000 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:19:09 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:11 - mmengine - INFO - Epoch(train) [180][100/391] lr: 1.0000e-03 eta: 0:04:11 time: 0.0251 data_time: 0.0038 memory: 227 loss: 1.3022 student.loss: 0.0176 distill.loss_1: 0.2013 distill.loss_2: 0.2420 distill.loss_3: 0.8414 2023/04/17 20:19:13 - mmengine - INFO - Epoch(train) [180][200/391] lr: 1.0000e-03 eta: 0:04:08 time: 0.0242 data_time: 0.0038 memory: 227 loss: 1.3033 student.loss: 0.0235 distill.loss_1: 0.1967 distill.loss_2: 0.2394 distill.loss_3: 0.8437 2023/04/17 20:19:16 - mmengine - INFO - Epoch(train) [180][300/391] lr: 1.0000e-03 eta: 0:04:05 time: 0.0244 data_time: 0.0038 memory: 227 loss: 1.3521 student.loss: 0.0402 distill.loss_1: 0.2051 distill.loss_2: 0.2387 distill.loss_3: 0.8680 2023/04/17 20:19:18 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:18 - mmengine - INFO - Saving checkpoint at 180 epochs 2023/04/17 20:19:24 - mmengine - INFO - Epoch(val) [180][79/79] accuracy/top1: 94.3100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 20:19:27 - mmengine - INFO - Epoch(train) [181][100/391] lr: 1.0000e-03 eta: 0:03:59 time: 0.0244 data_time: 0.0041 memory: 227 loss: 1.3344 student.loss: 0.0224 distill.loss_1: 0.1996 distill.loss_2: 0.2447 distill.loss_3: 0.8677 2023/04/17 20:19:30 - mmengine - INFO - Epoch(train) [181][200/391] lr: 1.0000e-03 eta: 0:03:55 time: 0.0254 data_time: 0.0037 memory: 227 loss: 1.3238 student.loss: 0.0216 distill.loss_1: 0.2065 distill.loss_2: 0.2422 distill.loss_3: 0.8534 2023/04/17 20:19:32 - mmengine - INFO - Epoch(train) [181][300/391] lr: 1.0000e-03 eta: 0:03:52 time: 0.0240 data_time: 0.0038 memory: 227 loss: 1.3127 student.loss: 0.0228 distill.loss_1: 0.1997 distill.loss_2: 0.2408 distill.loss_3: 0.8494 2023/04/17 20:19:35 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:35 - mmengine - INFO - Saving checkpoint at 181 epochs 2023/04/17 20:19:41 - mmengine - INFO - Epoch(val) [181][79/79] accuracy/top1: 94.2600 teacher.accuracy/top1: 95.4400data_time: 0.0037 time: 0.0102 2023/04/17 20:19:43 - mmengine - INFO - Epoch(train) [182][100/391] lr: 1.0000e-03 eta: 0:03:46 time: 0.0240 data_time: 0.0044 memory: 227 loss: 1.3796 student.loss: 0.0485 distill.loss_1: 0.2068 distill.loss_2: 0.2425 distill.loss_3: 0.8818 2023/04/17 20:19:46 - mmengine - INFO - Epoch(train) [182][200/391] lr: 1.0000e-03 eta: 0:03:43 time: 0.0244 data_time: 0.0044 memory: 227 loss: 1.3170 student.loss: 0.0106 distill.loss_1: 0.1990 distill.loss_2: 0.2374 distill.loss_3: 0.8699 2023/04/17 20:19:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:48 - mmengine - INFO - Epoch(train) [182][300/391] lr: 1.0000e-03 eta: 0:03:40 time: 0.0243 data_time: 0.0042 memory: 227 loss: 1.2755 student.loss: 0.0066 distill.loss_1: 0.1926 distill.loss_2: 0.2393 distill.loss_3: 0.8371 2023/04/17 20:19:51 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:19:51 - mmengine - INFO - Saving checkpoint at 182 epochs 2023/04/17 20:19:57 - mmengine - INFO - Epoch(val) [182][79/79] accuracy/top1: 94.1100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0098 2023/04/17 20:20:00 - mmengine - INFO - Epoch(train) [183][100/391] lr: 1.0000e-03 eta: 0:03:34 time: 0.0250 data_time: 0.0038 memory: 227 loss: 1.3883 student.loss: 0.0176 distill.loss_1: 0.2064 distill.loss_2: 0.2459 distill.loss_3: 0.9184 2023/04/17 20:20:02 - mmengine - INFO - Epoch(train) [183][200/391] lr: 1.0000e-03 eta: 0:03:31 time: 0.0250 data_time: 0.0038 memory: 227 loss: 1.3835 student.loss: 0.0470 distill.loss_1: 0.2030 distill.loss_2: 0.2431 distill.loss_3: 0.8904 2023/04/17 20:20:05 - mmengine - INFO - Epoch(train) [183][300/391] lr: 1.0000e-03 eta: 0:03:28 time: 0.0246 data_time: 0.0039 memory: 227 loss: 1.3393 student.loss: 0.0247 distill.loss_1: 0.2023 distill.loss_2: 0.2423 distill.loss_3: 0.8699 2023/04/17 20:20:07 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:20:07 - mmengine - INFO - Saving checkpoint at 183 epochs 2023/04/17 20:20:14 - mmengine - INFO - Epoch(val) [183][79/79] accuracy/top1: 94.1500 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 20:20:17 - mmengine - INFO - Epoch(train) [184][100/391] lr: 1.0000e-03 eta: 0:03:22 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.3364 student.loss: 0.0129 distill.loss_1: 0.2018 distill.loss_2: 0.2424 distill.loss_3: 0.8792 2023/04/17 20:20:19 - mmengine - INFO - Epoch(train) [184][200/391] lr: 1.0000e-03 eta: 0:03:19 time: 0.0245 data_time: 0.0037 memory: 227 loss: 1.3196 student.loss: 0.0070 distill.loss_1: 0.2040 distill.loss_2: 0.2416 distill.loss_3: 0.8669 2023/04/17 20:20:22 - mmengine - INFO - Epoch(train) [184][300/391] lr: 1.0000e-03 eta: 0:03:15 time: 0.0243 data_time: 0.0037 memory: 227 loss: 1.4074 student.loss: 0.0358 distill.loss_1: 0.1975 distill.loss_2: 0.2377 distill.loss_3: 0.9364 2023/04/17 20:20:24 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:20:24 - mmengine - INFO - Saving checkpoint at 184 epochs 2023/04/17 20:20:30 - mmengine - INFO - Epoch(val) [184][79/79] accuracy/top1: 94.1800 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0094 2023/04/17 20:20:31 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:20:33 - mmengine - INFO - Epoch(train) [185][100/391] lr: 1.0000e-03 eta: 0:03:09 time: 0.0245 data_time: 0.0038 memory: 227 loss: 1.2518 student.loss: 0.0024 distill.loss_1: 0.2020 distill.loss_2: 0.2416 distill.loss_3: 0.8058 2023/04/17 20:20:35 - mmengine - INFO - Epoch(train) [185][200/391] lr: 1.0000e-03 eta: 0:03:06 time: 0.0252 data_time: 0.0038 memory: 227 loss: 1.3404 student.loss: 0.0288 distill.loss_1: 0.2075 distill.loss_2: 0.2451 distill.loss_3: 0.8590 2023/04/17 20:20:38 - mmengine - INFO - Epoch(train) [185][300/391] lr: 1.0000e-03 eta: 0:03:03 time: 0.0248 data_time: 0.0039 memory: 227 loss: 1.3143 student.loss: 0.0125 distill.loss_1: 0.2058 distill.loss_2: 0.2437 distill.loss_3: 0.8524 2023/04/17 20:20:41 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:20:41 - mmengine - INFO - Saving checkpoint at 185 epochs 2023/04/17 20:20:46 - mmengine - INFO - Epoch(val) [185][79/79] accuracy/top1: 94.2200 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:20:50 - mmengine - INFO - Epoch(train) [186][100/391] lr: 1.0000e-03 eta: 0:02:57 time: 0.0253 data_time: 0.0037 memory: 227 loss: 1.5080 student.loss: 0.0558 distill.loss_1: 0.1998 distill.loss_2: 0.2476 distill.loss_3: 1.0049 2023/04/17 20:20:52 - mmengine - INFO - Epoch(train) [186][200/391] lr: 1.0000e-03 eta: 0:02:54 time: 0.0265 data_time: 0.0040 memory: 227 loss: 1.3966 student.loss: 0.0699 distill.loss_1: 0.1975 distill.loss_2: 0.2412 distill.loss_3: 0.8881 2023/04/17 20:20:55 - mmengine - INFO - Epoch(train) [186][300/391] lr: 1.0000e-03 eta: 0:02:51 time: 0.0247 data_time: 0.0040 memory: 227 loss: 1.3256 student.loss: 0.0436 distill.loss_1: 0.2021 distill.loss_2: 0.2416 distill.loss_3: 0.8384 2023/04/17 20:20:57 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:20:57 - mmengine - INFO - Saving checkpoint at 186 epochs 2023/04/17 20:21:04 - mmengine - INFO - Epoch(val) [186][79/79] accuracy/top1: 94.1100 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 20:21:06 - mmengine - INFO - Epoch(train) [187][100/391] lr: 1.0000e-03 eta: 0:02:45 time: 0.0255 data_time: 0.0042 memory: 227 loss: 1.3338 student.loss: 0.0210 distill.loss_1: 0.1968 distill.loss_2: 0.2357 distill.loss_3: 0.8804 2023/04/17 20:21:09 - mmengine - INFO - Epoch(train) [187][200/391] lr: 1.0000e-03 eta: 0:02:42 time: 0.0246 data_time: 0.0042 memory: 227 loss: 1.3948 student.loss: 0.0170 distill.loss_1: 0.2091 distill.loss_2: 0.2459 distill.loss_3: 0.9228 2023/04/17 20:21:11 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:21:11 - mmengine - INFO - Epoch(train) [187][300/391] lr: 1.0000e-03 eta: 0:02:39 time: 0.0249 data_time: 0.0041 memory: 227 loss: 1.3476 student.loss: 0.0233 distill.loss_1: 0.2000 distill.loss_2: 0.2410 distill.loss_3: 0.8833 2023/04/17 20:21:14 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:21:14 - mmengine - INFO - Saving checkpoint at 187 epochs 2023/04/17 20:21:20 - mmengine - INFO - Epoch(val) [187][79/79] accuracy/top1: 94.1500 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0100 2023/04/17 20:21:23 - mmengine - INFO - Epoch(train) [188][100/391] lr: 1.0000e-03 eta: 0:02:33 time: 0.0252 data_time: 0.0037 memory: 227 loss: 1.3296 student.loss: 0.0183 distill.loss_1: 0.1979 distill.loss_2: 0.2404 distill.loss_3: 0.8730 2023/04/17 20:21:25 - mmengine - INFO - Epoch(train) [188][200/391] lr: 1.0000e-03 eta: 0:02:30 time: 0.0253 data_time: 0.0037 memory: 227 loss: 1.2782 student.loss: 0.0144 distill.loss_1: 0.1979 distill.loss_2: 0.2381 distill.loss_3: 0.8278 2023/04/17 20:21:28 - mmengine - INFO - Epoch(train) [188][300/391] lr: 1.0000e-03 eta: 0:02:27 time: 0.0251 data_time: 0.0037 memory: 227 loss: 1.3666 student.loss: 0.0269 distill.loss_1: 0.2001 distill.loss_2: 0.2407 distill.loss_3: 0.8989 2023/04/17 20:21:30 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:21:30 - mmengine - INFO - Saving checkpoint at 188 epochs 2023/04/17 20:21:36 - mmengine - INFO - Epoch(val) [188][79/79] accuracy/top1: 94.2700 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:21:39 - mmengine - INFO - Epoch(train) [189][100/391] lr: 1.0000e-03 eta: 0:02:21 time: 0.0241 data_time: 0.0038 memory: 227 loss: 1.3352 student.loss: 0.0110 distill.loss_1: 0.2016 distill.loss_2: 0.2463 distill.loss_3: 0.8764 2023/04/17 20:21:42 - mmengine - INFO - Epoch(train) [189][200/391] lr: 1.0000e-03 eta: 0:02:18 time: 0.0246 data_time: 0.0038 memory: 227 loss: 1.3246 student.loss: 0.0363 distill.loss_1: 0.2113 distill.loss_2: 0.2455 distill.loss_3: 0.8316 2023/04/17 20:21:44 - mmengine - INFO - Epoch(train) [189][300/391] lr: 1.0000e-03 eta: 0:02:15 time: 0.0240 data_time: 0.0038 memory: 227 loss: 1.3515 student.loss: 0.0182 distill.loss_1: 0.2036 distill.loss_2: 0.2426 distill.loss_3: 0.8871 2023/04/17 20:21:47 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:21:47 - mmengine - INFO - Saving checkpoint at 189 epochs 2023/04/17 20:21:52 - mmengine - INFO - Epoch(val) [189][79/79] accuracy/top1: 94.2500 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0091 2023/04/17 20:21:55 - mmengine - INFO - Epoch(train) [190][100/391] lr: 1.0000e-03 eta: 0:02:09 time: 0.0249 data_time: 0.0038 memory: 227 loss: 1.2825 student.loss: 0.0152 distill.loss_1: 0.2012 distill.loss_2: 0.2404 distill.loss_3: 0.8258 2023/04/17 20:21:56 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:21:58 - mmengine - INFO - Epoch(train) [190][200/391] lr: 1.0000e-03 eta: 0:02:06 time: 0.0255 data_time: 0.0038 memory: 227 loss: 1.2878 student.loss: 0.0358 distill.loss_1: 0.1939 distill.loss_2: 0.2365 distill.loss_3: 0.8216 2023/04/17 20:22:01 - mmengine - INFO - Epoch(train) [190][300/391] lr: 1.0000e-03 eta: 0:02:02 time: 0.0247 data_time: 0.0038 memory: 227 loss: 1.3418 student.loss: 0.0198 distill.loss_1: 0.2024 distill.loss_2: 0.2417 distill.loss_3: 0.8780 2023/04/17 20:22:03 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:22:03 - mmengine - INFO - Saving checkpoint at 190 epochs 2023/04/17 20:22:09 - mmengine - INFO - Epoch(val) [190][79/79] accuracy/top1: 94.1500 teacher.accuracy/top1: 95.4400data_time: 0.0029 time: 0.0092 2023/04/17 20:22:12 - mmengine - INFO - Epoch(train) [191][100/391] lr: 1.0000e-03 eta: 0:01:57 time: 0.0249 data_time: 0.0037 memory: 227 loss: 1.3420 student.loss: 0.0133 distill.loss_1: 0.2008 distill.loss_2: 0.2450 distill.loss_3: 0.8828 2023/04/17 20:22:15 - mmengine - INFO - Epoch(train) [191][200/391] lr: 1.0000e-03 eta: 0:01:53 time: 0.0256 data_time: 0.0037 memory: 227 loss: 1.3618 student.loss: 0.0401 distill.loss_1: 0.1990 distill.loss_2: 0.2432 distill.loss_3: 0.8796 2023/04/17 20:22:17 - mmengine - INFO - Epoch(train) [191][300/391] lr: 1.0000e-03 eta: 0:01:50 time: 0.0242 data_time: 0.0038 memory: 227 loss: 1.4145 student.loss: 0.0560 distill.loss_1: 0.1993 distill.loss_2: 0.2445 distill.loss_3: 0.9146 2023/04/17 20:22:19 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:22:19 - mmengine - INFO - Saving checkpoint at 191 epochs 2023/04/17 20:22:25 - mmengine - INFO - Epoch(val) [191][79/79] accuracy/top1: 94.2300 teacher.accuracy/top1: 95.4400data_time: 0.0034 time: 0.0098 2023/04/17 20:22:28 - mmengine - INFO - Epoch(train) [192][100/391] lr: 1.0000e-03 eta: 0:01:44 time: 0.0242 data_time: 0.0040 memory: 227 loss: 1.2888 student.loss: 0.0043 distill.loss_1: 0.2011 distill.loss_2: 0.2405 distill.loss_3: 0.8428 2023/04/17 20:22:30 - mmengine - INFO - Epoch(train) [192][200/391] lr: 1.0000e-03 eta: 0:01:41 time: 0.0244 data_time: 0.0040 memory: 227 loss: 1.3777 student.loss: 0.0280 distill.loss_1: 0.2040 distill.loss_2: 0.2409 distill.loss_3: 0.9047 2023/04/17 20:22:33 - mmengine - INFO - Epoch(train) [192][300/391] lr: 1.0000e-03 eta: 0:01:38 time: 0.0252 data_time: 0.0040 memory: 227 loss: 1.3661 student.loss: 0.0465 distill.loss_1: 0.1910 distill.loss_2: 0.2371 distill.loss_3: 0.8914 2023/04/17 20:22:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:22:35 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:22:35 - mmengine - INFO - Saving checkpoint at 192 epochs 2023/04/17 20:22:42 - mmengine - INFO - Epoch(val) [192][79/79] accuracy/top1: 94.2500 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0094 2023/04/17 20:22:45 - mmengine - INFO - Epoch(train) [193][100/391] lr: 1.0000e-03 eta: 0:01:32 time: 0.0260 data_time: 0.0046 memory: 227 loss: 1.4658 student.loss: 0.0369 distill.loss_1: 0.2121 distill.loss_2: 0.2470 distill.loss_3: 0.9698 2023/04/17 20:22:47 - mmengine - INFO - Epoch(train) [193][200/391] lr: 1.0000e-03 eta: 0:01:29 time: 0.0247 data_time: 0.0039 memory: 227 loss: 1.2993 student.loss: 0.0104 distill.loss_1: 0.2041 distill.loss_2: 0.2450 distill.loss_3: 0.8399 2023/04/17 20:22:50 - mmengine - INFO - Epoch(train) [193][300/391] lr: 1.0000e-03 eta: 0:01:26 time: 0.0247 data_time: 0.0039 memory: 227 loss: 1.3252 student.loss: 0.0091 distill.loss_1: 0.1941 distill.loss_2: 0.2389 distill.loss_3: 0.8830 2023/04/17 20:22:53 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:22:53 - mmengine - INFO - Saving checkpoint at 193 epochs 2023/04/17 20:22:59 - mmengine - INFO - Epoch(val) [193][79/79] accuracy/top1: 94.2000 teacher.accuracy/top1: 95.4400data_time: 0.0030 time: 0.0092 2023/04/17 20:23:02 - mmengine - INFO - Epoch(train) [194][100/391] lr: 1.0000e-03 eta: 0:01:20 time: 0.0258 data_time: 0.0038 memory: 227 loss: 1.3783 student.loss: 0.0249 distill.loss_1: 0.2040 distill.loss_2: 0.2404 distill.loss_3: 0.9091 2023/04/17 20:23:05 - mmengine - INFO - Epoch(train) [194][200/391] lr: 1.0000e-03 eta: 0:01:17 time: 0.0248 data_time: 0.0038 memory: 227 loss: 1.3434 student.loss: 0.0221 distill.loss_1: 0.1971 distill.loss_2: 0.2392 distill.loss_3: 0.8849 2023/04/17 20:23:07 - mmengine - INFO - Epoch(train) [194][300/391] lr: 1.0000e-03 eta: 0:01:14 time: 0.0241 data_time: 0.0037 memory: 227 loss: 1.3516 student.loss: 0.0142 distill.loss_1: 0.2013 distill.loss_2: 0.2424 distill.loss_3: 0.8936 2023/04/17 20:23:09 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:23:10 - mmengine - INFO - Saving checkpoint at 194 epochs 2023/04/17 20:23:16 - mmengine - INFO - Epoch(val) [194][79/79] accuracy/top1: 94.2000 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0093 2023/04/17 20:23:19 - mmengine - INFO - Epoch(train) [195][100/391] lr: 1.0000e-03 eta: 0:01:08 time: 0.0255 data_time: 0.0038 memory: 227 loss: 1.3305 student.loss: 0.0163 distill.loss_1: 0.2077 distill.loss_2: 0.2436 distill.loss_3: 0.8628 2023/04/17 20:23:21 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:23:22 - mmengine - INFO - Epoch(train) [195][200/391] lr: 1.0000e-03 eta: 0:01:05 time: 0.0248 data_time: 0.0038 memory: 227 loss: 1.3352 student.loss: 0.0123 distill.loss_1: 0.1982 distill.loss_2: 0.2406 distill.loss_3: 0.8841 2023/04/17 20:23:24 - mmengine - INFO - Epoch(train) [195][300/391] lr: 1.0000e-03 eta: 0:01:02 time: 0.0247 data_time: 0.0038 memory: 227 loss: 1.3631 student.loss: 0.0285 distill.loss_1: 0.2121 distill.loss_2: 0.2443 distill.loss_3: 0.8782 2023/04/17 20:23:27 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:23:27 - mmengine - INFO - Saving checkpoint at 195 epochs 2023/04/17 20:23:33 - mmengine - INFO - Epoch(val) [195][79/79] accuracy/top1: 94.1800 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0100 2023/04/17 20:23:36 - mmengine - INFO - Epoch(train) [196][100/391] lr: 1.0000e-03 eta: 0:00:56 time: 0.0245 data_time: 0.0042 memory: 227 loss: 1.3068 student.loss: 0.0104 distill.loss_1: 0.2108 distill.loss_2: 0.2450 distill.loss_3: 0.8406 2023/04/17 20:23:39 - mmengine - INFO - Epoch(train) [196][200/391] lr: 1.0000e-03 eta: 0:00:53 time: 0.0255 data_time: 0.0042 memory: 227 loss: 1.3341 student.loss: 0.0212 distill.loss_1: 0.2026 distill.loss_2: 0.2422 distill.loss_3: 0.8680 2023/04/17 20:23:41 - mmengine - INFO - Epoch(train) [196][300/391] lr: 1.0000e-03 eta: 0:00:50 time: 0.0248 data_time: 0.0038 memory: 227 loss: 1.3634 student.loss: 0.0503 distill.loss_1: 0.1960 distill.loss_2: 0.2372 distill.loss_3: 0.8800 2023/04/17 20:23:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:23:44 - mmengine - INFO - Saving checkpoint at 196 epochs 2023/04/17 20:23:50 - mmengine - INFO - Epoch(val) [196][79/79] accuracy/top1: 94.2300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0098 2023/04/17 20:23:53 - mmengine - INFO - Epoch(train) [197][100/391] lr: 1.0000e-03 eta: 0:00:44 time: 0.0246 data_time: 0.0038 memory: 227 loss: 1.3608 student.loss: 0.0634 distill.loss_1: 0.1991 distill.loss_2: 0.2412 distill.loss_3: 0.8570 2023/04/17 20:23:55 - mmengine - INFO - Epoch(train) [197][200/391] lr: 1.0000e-03 eta: 0:00:41 time: 0.0245 data_time: 0.0039 memory: 227 loss: 1.3430 student.loss: 0.0166 distill.loss_1: 0.1978 distill.loss_2: 0.2426 distill.loss_3: 0.8860 2023/04/17 20:23:58 - mmengine - INFO - Epoch(train) [197][300/391] lr: 1.0000e-03 eta: 0:00:38 time: 0.0260 data_time: 0.0039 memory: 227 loss: 1.3983 student.loss: 0.0112 distill.loss_1: 0.2105 distill.loss_2: 0.2453 distill.loss_3: 0.9314 2023/04/17 20:23:59 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:00 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:00 - mmengine - INFO - Saving checkpoint at 197 epochs 2023/04/17 20:24:06 - mmengine - INFO - Epoch(val) [197][79/79] accuracy/top1: 94.3200 teacher.accuracy/top1: 95.4400data_time: 0.0031 time: 0.0095 2023/04/17 20:24:09 - mmengine - INFO - Epoch(train) [198][100/391] lr: 1.0000e-03 eta: 0:00:32 time: 0.0248 data_time: 0.0041 memory: 227 loss: 1.3004 student.loss: 0.0062 distill.loss_1: 0.2020 distill.loss_2: 0.2381 distill.loss_3: 0.8540 2023/04/17 20:24:11 - mmengine - INFO - Epoch(train) [198][200/391] lr: 1.0000e-03 eta: 0:00:29 time: 0.0242 data_time: 0.0041 memory: 227 loss: 1.2947 student.loss: 0.0064 distill.loss_1: 0.2027 distill.loss_2: 0.2434 distill.loss_3: 0.8422 2023/04/17 20:24:14 - mmengine - INFO - Epoch(train) [198][300/391] lr: 1.0000e-03 eta: 0:00:26 time: 0.0238 data_time: 0.0038 memory: 227 loss: 1.3368 student.loss: 0.0070 distill.loss_1: 0.1976 distill.loss_2: 0.2408 distill.loss_3: 0.8914 2023/04/17 20:24:16 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:16 - mmengine - INFO - Saving checkpoint at 198 epochs 2023/04/17 20:24:22 - mmengine - INFO - Epoch(val) [198][79/79] accuracy/top1: 94.1300 teacher.accuracy/top1: 95.4400data_time: 0.0032 time: 0.0096 2023/04/17 20:24:25 - mmengine - INFO - Epoch(train) [199][100/391] lr: 1.0000e-03 eta: 0:00:20 time: 0.0272 data_time: 0.0039 memory: 227 loss: 1.3304 student.loss: 0.0073 distill.loss_1: 0.2184 distill.loss_2: 0.2505 distill.loss_3: 0.8542 2023/04/17 20:24:28 - mmengine - INFO - Epoch(train) [199][200/391] lr: 1.0000e-03 eta: 0:00:17 time: 0.0295 data_time: 0.0040 memory: 227 loss: 1.3809 student.loss: 0.0272 distill.loss_1: 0.2002 distill.loss_2: 0.2397 distill.loss_3: 0.9138 2023/04/17 20:24:30 - mmengine - INFO - Epoch(train) [199][300/391] lr: 1.0000e-03 eta: 0:00:14 time: 0.0262 data_time: 0.0038 memory: 227 loss: 1.3520 student.loss: 0.0178 distill.loss_1: 0.2027 distill.loss_2: 0.2417 distill.loss_3: 0.8899 2023/04/17 20:24:33 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:33 - mmengine - INFO - Saving checkpoint at 199 epochs 2023/04/17 20:24:39 - mmengine - INFO - Epoch(val) [199][79/79] accuracy/top1: 94.2000 teacher.accuracy/top1: 95.4400data_time: 0.0033 time: 0.0097 2023/04/17 20:24:41 - mmengine - INFO - Epoch(train) [200][100/391] lr: 1.0000e-03 eta: 0:00:08 time: 0.0248 data_time: 0.0041 memory: 227 loss: 1.3454 student.loss: 0.0315 distill.loss_1: 0.2060 distill.loss_2: 0.2399 distill.loss_3: 0.8680 2023/04/17 20:24:44 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:44 - mmengine - INFO - Epoch(train) [200][200/391] lr: 1.0000e-03 eta: 0:00:05 time: 0.0247 data_time: 0.0038 memory: 227 loss: 1.3356 student.loss: 0.0084 distill.loss_1: 0.2016 distill.loss_2: 0.2417 distill.loss_3: 0.8839 2023/04/17 20:24:46 - mmengine - INFO - Epoch(train) [200][300/391] lr: 1.0000e-03 eta: 0:00:02 time: 0.0244 data_time: 0.0038 memory: 227 loss: 1.3537 student.loss: 0.0113 distill.loss_1: 0.2034 distill.loss_2: 0.2414 distill.loss_3: 0.8975 2023/04/17 20:24:49 - mmengine - INFO - Exp name: ofd_backbone_resnet50_resnet18_8xb16_cifar10_20230417_192216 2023/04/17 20:24:49 - mmengine - INFO - Saving checkpoint at 200 epochs 2023/04/17 20:24:55 - mmengine - INFO - Epoch(val) [200][79/79] accuracy/top1: 94.2100 teacher.accuracy/top1: 95.4400data_time: 0.0036 time: 0.0103