2023/09/07 09:55:45 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.17 (default, Jul 5 2023, 21:04:15) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1021012455 GPU 0,1,2,3,4,5,6,7: Tesla V100-SXM2-32GB CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.2, V11.2.152 GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.8.0 MMEngine: 0.8.4 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 1021012455 Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/09/07 09:55:45 - mmengine - INFO - Config: crop_size = ( 640, 640, ) data_preprocessor = dict( bgr_to_rgb=True, mean=[ 122.7709, 116.746, 104.0937, ], pad_val=0, seg_pad_val=255, size_divisor=640, std=[ 68.5005, 66.6322, 70.3232, ], test_cfg=dict(size_divisor=32), type='SegDataPreProcessor') data_root = 'data/coco_stuff164k' dataset_type = 'COCOStuffDataset' default_hooks = dict( checkpoint=dict( by_epoch=False, interval=10000, save_best='mIoU', type='CheckpointHook'), logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'), param_scheduler=dict(type='ParamSchedulerHook'), sampler_seed=dict(type='DistSamplerSeedHook'), timer=dict(type='IterTimerHook'), visualization=dict(type='SegVisualizationHook')) default_scope = 'mmseg' env_cfg = dict( cudnn_benchmark=True, dist_cfg=dict(backend='nccl'), mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) img_ratios = [ 0.5, 0.75, 1.0, 1.25, 1.5, 1.75, ] launcher = 'pytorch' load_from = None log_level = 'INFO' log_processor = dict(by_epoch=False) model = dict( asymetric_input=True, data_preprocessor=dict( bgr_to_rgb=True, mean=[ 122.7709, 116.746, 104.0937, ], pad_val=0, seg_pad_val=255, size_divisor=640, std=[ 68.5005, 66.6322, 70.3232, ], test_cfg=dict(size_divisor=32), type='SegDataPreProcessor'), decode_head=dict( align_corners=False, deep_supervision_idxs=[ 7, ], loss_decode=[ dict( class_weight=[ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.1, ], loss_name='loss_cls_ce', loss_weight=2.0, naive_reduction=True, type='CrossEntropyLoss'), dict( loss_name='loss_mask_ce', loss_weight=5.0, type='CrossEntropyLoss', use_sigmoid=True), dict( eps=1, ignore_index=None, loss_name='loss_mask_dice', loss_weight=5.0, naive_dice=True, type='DiceLoss'), ], maskgen_cfg=dict( act_cfg=dict(type='QuickGELU'), cross_attn=False, embed_dims=1024, final_norm=True, frozen_exclude=[], mlp_ratio=4, norm_cfg=dict(eps=1e-05, type='LN'), num_heads=16, num_layers=6, out_dims=768, qkv_bias=True, sos_token_format='cls_token', sos_token_num=100), num_classes=171, san_cfg=dict( cfg_decoder=dict( embed_channels=256, mlp_channels=256, num_heads=16, num_layers=1, num_mlp=3, rescale=True), cfg_encoder=dict(mlp_ratio=4, num_encode_layer=8, num_heads=6), clip_channels=1024, embed_dims=240, fusion_index=[ 0, 1, 2, 3, ], in_channels=3, norm_cfg=dict(eps=1e-06, type='LN'), num_queries=100, patch_bias=True, patch_size=16), train_cfg=dict( assigner=dict( match_costs=[ dict(type='ClassificationCost', weight=2.0), dict( type='CrossEntropyLossCost', use_sigmoid=True, weight=5.0), dict(eps=1.0, pred_act=True, type='DiceCost', weight=5.0), ], type='HungarianAssigner'), importance_sample_ratio=0.75, num_points=12544, oversample_ratio=3.0), type='SideAdapterCLIPHead'), encoder_resolution=0.7, image_encoder=dict( act_cfg=dict(type='QuickGELU'), attn_drop_rate=0.0, drop_path_rate=0.0, drop_rate=0.0, embed_dims=1024, frozen_exclude=[ 'pos_embed', ], img_size=( 336, 336, ), in_channels=3, interpolate_mode='bicubic', mlp_ratio=4, norm_cfg=dict(eps=1e-05, type='LN'), norm_eval=False, num_heads=16, num_layers=18, out_indices=( 5, 11, 17, ), out_origin=True, output_cls_token=True, patch_bias=False, patch_pad=0, patch_size=14, pre_norm=True, qkv_bias=True, type='VisionTransformer', with_cls_token=True), pretrained='pretrain/clip_vit_large_patch14_336.pth', test_cfg=dict(mode='whole'), text_encoder=dict( cache_feature=True, cat_bg=True, dataset_name='coco-stuff164k', embed_dims=768, mlp_ratio=4, norm_cfg=dict(eps=1e-05, type='LN'), num_heads=12, num_layers=12, output_dims=768, templates='vild', type='CLIPTextEncoder'), train_cfg=dict(), type='MultimodalEncoderDecoder') norm_cfg = dict(requires_grad=True, type='SyncBN') num_classes = 171 optim_wrapper = dict( clip_grad=dict(max_norm=0.01, norm_type=2), loss_scale='dynamic', optimizer=dict( betas=( 0.9, 0.999, ), lr=0.0001, type='AdamW', weight_decay=0.0001), paramwise_cfg=dict( custom_keys=dict( cls_token=dict(decay_mult=0.0), img_encoder=dict(decay_mult=1.0, lr_mult=0.1), norm=dict(decay_mult=0.0), pos_embed=dict(decay_mult=0.0))), type='AmpOptimWrapper') optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005) param_scheduler = [ dict( begin=0, by_epoch=False, end=60000, eta_min=0.0, power=1.0, type='PolyLR'), ] resume = False test_cfg = dict(type='TestLoop') test_dataloader = dict( batch_size=1, dataset=dict( data_prefix=dict( img_path='images/val2017', seg_map_path='annotations/val2017'), data_root='data/coco_stuff164k', pipeline=[ dict(type='LoadImageFromFile'), dict(max_size=2560, scale=( 640, 640, ), type='ResizeShortestEdge'), dict(type='LoadAnnotations'), dict(type='PackSegInputs'), ], type='COCOStuffDataset'), num_workers=4, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) test_evaluator = dict( iou_metrics=[ 'mIoU', ], type='IoUMetric') test_pipeline = [ dict(type='LoadImageFromFile'), dict(max_size=2560, scale=( 640, 640, ), type='ResizeShortestEdge'), dict(type='LoadAnnotations'), dict(type='PackSegInputs'), ] train_cfg = dict( max_iters=60000, type='IterBasedTrainLoop', val_begin=55000, val_interval=500) train_dataloader = dict( batch_size=4, dataset=dict( data_prefix=dict( img_path='images/train2017', seg_map_path='annotations/train2017'), data_root='data/coco_stuff164k', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict( max_size=2560, resize_type='ResizeShortestEdge', scales=[ 320, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024, ], type='RandomChoiceResize'), dict(cat_max_ratio=1.0, crop_size=( 640, 640, ), type='RandomCrop'), dict(type='PhotoMetricDistortion'), dict(prob=0.5, type='RandomFlip'), dict(type='PackSegInputs'), ], type='COCOStuffDataset'), num_workers=4, persistent_workers=True, sampler=dict(shuffle=True, type='InfiniteSampler')) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict( max_size=2560, resize_type='ResizeShortestEdge', scales=[ 320, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024, ], type='RandomChoiceResize'), dict(cat_max_ratio=1.0, crop_size=( 640, 640, ), type='RandomCrop'), dict(type='PhotoMetricDistortion'), dict(prob=0.5, type='RandomFlip'), dict(type='PackSegInputs'), ] tta_model = dict(type='SegTTAModel') tta_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict( transforms=[ [ dict(keep_ratio=True, scale_factor=0.5, type='Resize'), dict(keep_ratio=True, scale_factor=0.75, type='Resize'), dict(keep_ratio=True, scale_factor=1.0, type='Resize'), dict(keep_ratio=True, scale_factor=1.25, type='Resize'), dict(keep_ratio=True, scale_factor=1.5, type='Resize'), dict(keep_ratio=True, scale_factor=1.75, type='Resize'), ], [ dict(direction='horizontal', prob=0.0, type='RandomFlip'), dict(direction='horizontal', prob=1.0, type='RandomFlip'), ], [ dict(type='LoadAnnotations'), ], [ dict(type='PackSegInputs'), ], ], type='TestTimeAug'), ] val_cfg = dict(type='ValLoop') val_dataloader = dict( batch_size=1, dataset=dict( data_prefix=dict( img_path='images/val2017', seg_map_path='annotations/val2017'), data_root='data/coco_stuff164k', pipeline=[ dict(type='LoadImageFromFile'), dict(max_size=2560, scale=( 640, 640, ), type='ResizeShortestEdge'), dict(type='LoadAnnotations'), dict(type='PackSegInputs'), ], type='COCOStuffDataset'), num_workers=4, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) val_evaluator = dict( iou_metrics=[ 'mIoU', ], type='IoUMetric') vis_backends = [ dict(type='LocalVisBackend'), ] visualizer = dict( name='visualizer', type='SegLocalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), ]) work_dir = 'train_l14_60k' 2023/09/07 09:55:55 - 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 (NORMAL ) SegVisualizationHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val: (VERY_HIGH ) RuntimeInfoHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) SegVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_val: (VERY_HIGH ) RuntimeInfoHook -------------------- after_train: (VERY_HIGH ) RuntimeInfoHook (VERY_LOW ) CheckpointHook -------------------- before_test: (VERY_HIGH ) RuntimeInfoHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) SegVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test: (VERY_HIGH ) RuntimeInfoHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- image_encoder.pos_embed:lr=0.0001 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- image_encoder.pos_embed:weight_decay=0.0 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- image_encoder.pos_embed:decay_mult=0.0 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.pos_embed:lr=0.0001 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.pos_embed:weight_decay=0.0 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.pos_embed:decay_mult=0.0 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.query_pos_embed:lr=0.0001 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.query_pos_embed:weight_decay=0.0 2023/09/07 09:56:02 - mmengine - INFO - paramwise_options -- decode_head.side_adapter_network.query_pos_embed:decay_mult=0.0 2023/09/07 09:56:03 - mmengine - WARNING - The prefix is not set in metric class IoUMetric. Name of parameter - Initialization information image_encoder.cls_token - torch.Size([1, 1, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.pos_embed - torch.Size([1, 577, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.patch_embed.projection.weight - torch.Size([1024, 3, 14, 14]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.ln_pre.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.ln_pre.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.0.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.1.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.2.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.3.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.4.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.5.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.6.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.7.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.8.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.9.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.10.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.11.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.12.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.13.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.14.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.15.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.16.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ln1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ln1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.attn.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.attn.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.attn.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.attn.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ln2.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ln2.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ffn.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ffn.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ffn.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in VisionTransformer image_encoder.layers.17.ffn.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in VisionTransformer text_encoder.positional_embedding - torch.Size([77, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.text_projection - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.logit_scale - torch.Size([]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.bg_embed - torch.Size([1, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.token_embedding.weight - torch.Size([49408, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.0.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.1.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.2.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.3.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.4.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.5.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.6.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.7.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.8.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.9.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.10.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.attentions.0.attn.in_proj_weight - torch.Size([2304, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.attentions.0.attn.in_proj_bias - torch.Size([2304]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.attentions.0.attn.out_proj.weight - torch.Size([768, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.attentions.0.attn.out_proj.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.ffns.0.layers.0.0.weight - torch.Size([3072, 768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.ffns.0.layers.0.0.bias - torch.Size([3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.ffns.0.layers.1.weight - torch.Size([768, 3072]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.ffns.0.layers.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.norms.0.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.norms.0.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.norms.1.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.transformer.11.norms.1.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.ln_final.weight - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder text_encoder.ln_final.bias - torch.Size([768]): Initialized by user-defined `init_weights` in CLIPTextEncoder decode_head.side_adapter_network.pos_embed - torch.Size([1, 1600, 240]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.query_pos_embed - torch.Size([1, 100, 240]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.query_embed - torch.Size([1, 100, 240]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.patch_embed.projection.weight - torch.Size([240, 3, 16, 16]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.patch_embed.projection.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.0.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.1.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.2.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.3.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.4.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.5.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.6.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ln1.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ln1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.attn.attn.in_proj_weight - torch.Size([720, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.attn.attn.in_proj_bias - torch.Size([720]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.attn.attn.out_proj.weight - torch.Size([240, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.attn.attn.out_proj.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ln2.weight - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ln2.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ffn.layers.0.0.weight - torch.Size([960, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ffn.layers.0.0.bias - torch.Size([960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ffn.layers.1.weight - torch.Size([240, 960]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.encode_layers.7.ffn.layers.1.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.0.0.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.0.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.0.1.conv.weight - torch.Size([240, 1024, 1, 1]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.conv_clips.0.1.conv.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.1.0.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.1.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.1.1.conv.weight - torch.Size([240, 1024, 1, 1]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.conv_clips.1.1.conv.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.2.0.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.2.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.2.1.conv.weight - torch.Size([240, 1024, 1, 1]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.conv_clips.2.1.conv.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.3.0.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.3.0.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.conv_clips.3.1.conv.weight - torch.Size([240, 1024, 1, 1]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.side_adapter_network.conv_clips.3.1.conv.bias - torch.Size([240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.0.weight - torch.Size([256, 240]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.1.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.query_mlp.layers.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.0.weight - torch.Size([256, 240, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.1.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.pix_mlp.layers.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.0.weight - torch.Size([256, 240, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.1.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.2.weight - torch.Size([4096, 256, 1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.attn_mlp.layers.2.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.bias_scaling.weight - torch.Size([1, 1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.side_adapter_network.mask_decoder.bias_scaling.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of MultimodalEncoderDecoder decode_head.rec_with_attnbias.layers.0.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.0.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.1.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.2.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.3.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.4.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.attentions.0.attn.in_proj_weight - torch.Size([3072, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.attentions.0.attn.in_proj_bias - torch.Size([3072]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.attentions.0.attn.out_proj.weight - torch.Size([1024, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.attentions.0.attn.out_proj.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.ffns.0.layers.0.0.weight - torch.Size([4096, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.ffns.0.layers.0.0.bias - torch.Size([4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.ffns.0.layers.1.weight - torch.Size([1024, 4096]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.ffns.0.layers.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.norms.0.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.norms.0.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.norms.1.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.layers.5.norms.1.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.ln_post.weight - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.ln_post.bias - torch.Size([1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead decode_head.rec_with_attnbias.proj.weight - torch.Size([768, 1024]): Initialized by user-defined `init_weights` in SideAdapterCLIPHead 2023/09/07 09:56:07 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/09/07 09:56:07 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/09/07 09:56:07 - mmengine - INFO - Checkpoints will be saved to /home/caoanqi/mmsegmentation/train_l14_60k. 2023/09/07 09:57:00 - mmengine - INFO - Iter(train) [ 50/60000] base_lr: 9.9918e-05 lr: 9.9918e-05 eta: 17:31:56 time: 0.9837 data_time: 0.0205 memory: 29308 grad_norm: 208.0480 loss: 32.6245 decode.loss_cls_ce: 10.5028 decode.loss_mask_ce: 1.5381 decode.loss_mask_dice: 4.2879 decode.d7.loss_cls_ce: 10.5032 decode.d7.loss_mask_ce: 1.5056 decode.d7.loss_mask_dice: 4.2868 2023/09/07 09:57:49 - mmengine - INFO - Iter(train) [ 100/60000] base_lr: 9.9835e-05 lr: 9.9835e-05 eta: 16:56:23 time: 0.9840 data_time: 0.0209 memory: 29188 grad_norm: 172.1752 loss: 25.3373 decode.loss_cls_ce: 6.4591 decode.loss_mask_ce: 1.7072 decode.loss_mask_dice: 4.4717 decode.d7.loss_cls_ce: 6.4983 decode.d7.loss_mask_ce: 1.7010 decode.d7.loss_mask_dice: 4.5000 2023/09/07 09:58:38 - mmengine - INFO - Iter(train) [ 150/60000] base_lr: 9.9752e-05 lr: 9.9752e-05 eta: 16:44:01 time: 0.9835 data_time: 0.0206 memory: 29123 grad_norm: 151.6601 loss: 20.7448 decode.loss_cls_ce: 5.4499 decode.loss_mask_ce: 1.6581 decode.loss_mask_dice: 3.2648 decode.d7.loss_cls_ce: 5.4421 decode.d7.loss_mask_ce: 1.6454 decode.d7.loss_mask_dice: 3.2844 2023/09/07 09:59:27 - mmengine - INFO - Iter(train) [ 200/60000] base_lr: 9.9668e-05 lr: 9.9668e-05 eta: 16:36:57 time: 0.9807 data_time: 0.0212 memory: 29310 grad_norm: 119.0327 loss: 19.5327 decode.loss_cls_ce: 4.9273 decode.loss_mask_ce: 1.5646 decode.loss_mask_dice: 3.2841 decode.d7.loss_cls_ce: 4.9253 decode.d7.loss_mask_ce: 1.5365 decode.d7.loss_mask_dice: 3.2950 2023/09/07 10:00:16 - mmengine - INFO - Iter(train) [ 250/60000] base_lr: 9.9585e-05 lr: 9.9585e-05 eta: 16:32:34 time: 0.9838 data_time: 0.0209 memory: 29152 grad_norm: 120.0839 loss: 18.2305 decode.loss_cls_ce: 4.5696 decode.loss_mask_ce: 1.5300 decode.loss_mask_dice: 3.0094 decode.d7.loss_cls_ce: 4.5779 decode.d7.loss_mask_ce: 1.5071 decode.d7.loss_mask_dice: 3.0365 2023/09/07 10:01:05 - mmengine - INFO - Iter(train) [ 300/60000] base_lr: 9.9502e-05 lr: 9.9502e-05 eta: 16:29:10 time: 0.9830 data_time: 0.0208 memory: 29341 grad_norm: 118.9548 loss: 15.2092 decode.loss_cls_ce: 3.9398 decode.loss_mask_ce: 1.3102 decode.loss_mask_dice: 2.3509 decode.d7.loss_cls_ce: 3.9390 decode.d7.loss_mask_ce: 1.3026 decode.d7.loss_mask_dice: 2.3667 2023/09/07 10:01:54 - mmengine - INFO - Iter(train) [ 350/60000] base_lr: 9.9418e-05 lr: 9.9418e-05 eta: 16:26:42 time: 0.9815 data_time: 0.0211 memory: 29166 grad_norm: 148.4554 loss: 18.6969 decode.loss_cls_ce: 4.7492 decode.loss_mask_ce: 1.5514 decode.loss_mask_dice: 3.0358 decode.d7.loss_cls_ce: 4.7505 decode.d7.loss_mask_ce: 1.5437 decode.d7.loss_mask_dice: 3.0663 2023/09/07 10:02:43 - mmengine - INFO - Iter(train) [ 400/60000] base_lr: 9.9335e-05 lr: 9.9335e-05 eta: 16:24:26 time: 0.9798 data_time: 0.0214 memory: 29183 grad_norm: 101.3082 loss: 17.7105 decode.loss_cls_ce: 4.4104 decode.loss_mask_ce: 1.4560 decode.loss_mask_dice: 2.9924 decode.d7.loss_cls_ce: 4.4278 decode.d7.loss_mask_ce: 1.4226 decode.d7.loss_mask_dice: 3.0013 2023/09/07 10:03:32 - mmengine - INFO - Iter(train) [ 450/60000] base_lr: 9.9252e-05 lr: 9.9252e-05 eta: 16:22:37 time: 0.9845 data_time: 0.0210 memory: 29215 grad_norm: 92.5841 loss: 17.5073 decode.loss_cls_ce: 4.2930 decode.loss_mask_ce: 1.5894 decode.loss_mask_dice: 2.8720 decode.d7.loss_cls_ce: 4.3064 decode.d7.loss_mask_ce: 1.5751 decode.d7.loss_mask_dice: 2.8712 2023/09/07 10:04:22 - mmengine - INFO - Iter(train) [ 500/60000] base_lr: 9.9168e-05 lr: 9.9168e-05 eta: 16:20:58 time: 0.9819 data_time: 0.0212 memory: 29154 grad_norm: 89.2687 loss: 14.2458 decode.loss_cls_ce: 3.3996 decode.loss_mask_ce: 1.2898 decode.loss_mask_dice: 2.4134 decode.d7.loss_cls_ce: 3.4050 decode.d7.loss_mask_ce: 1.2966 decode.d7.loss_mask_dice: 2.4414 2023/09/07 10:05:11 - mmengine - INFO - Iter(train) [ 550/60000] base_lr: 9.9085e-05 lr: 9.9085e-05 eta: 16:19:26 time: 0.9822 data_time: 0.0214 memory: 29412 grad_norm: 87.8318 loss: 13.0515 decode.loss_cls_ce: 3.4000 decode.loss_mask_ce: 1.0637 decode.loss_mask_dice: 2.0457 decode.d7.loss_cls_ce: 3.4294 decode.d7.loss_mask_ce: 1.0567 decode.d7.loss_mask_dice: 2.0560 2023/09/07 10:06:00 - mmengine - INFO - Iter(train) [ 600/60000] base_lr: 9.9002e-05 lr: 9.9002e-05 eta: 16:17:56 time: 0.9814 data_time: 0.0215 memory: 29292 grad_norm: 72.1711 loss: 15.2104 decode.loss_cls_ce: 3.6179 decode.loss_mask_ce: 1.3181 decode.loss_mask_dice: 2.6645 decode.d7.loss_cls_ce: 3.6491 decode.d7.loss_mask_ce: 1.2957 decode.d7.loss_mask_dice: 2.6650 2023/09/07 10:06:49 - mmengine - INFO - Iter(train) [ 650/60000] base_lr: 9.8918e-05 lr: 9.8918e-05 eta: 16:16:41 time: 0.9804 data_time: 0.0221 memory: 29156 grad_norm: 88.2436 loss: 13.6534 decode.loss_cls_ce: 3.3061 decode.loss_mask_ce: 1.1561 decode.loss_mask_dice: 2.3444 decode.d7.loss_cls_ce: 3.3245 decode.d7.loss_mask_ce: 1.1622 decode.d7.loss_mask_dice: 2.3602 2023/09/07 10:07:38 - mmengine - INFO - Iter(train) [ 700/60000] base_lr: 9.8835e-05 lr: 9.8835e-05 eta: 16:15:30 time: 0.9827 data_time: 0.0218 memory: 29194 grad_norm: 86.0793 loss: 12.1842 decode.loss_cls_ce: 3.0873 decode.loss_mask_ce: 1.1527 decode.loss_mask_dice: 1.8524 decode.d7.loss_cls_ce: 3.0714 decode.d7.loss_mask_ce: 1.1437 decode.d7.loss_mask_dice: 1.8767 2023/09/07 10:08:27 - mmengine - INFO - Iter(train) [ 750/60000] base_lr: 9.8752e-05 lr: 9.8752e-05 eta: 16:14:22 time: 0.9822 data_time: 0.0218 memory: 29207 grad_norm: 59.0073 loss: 13.3906 decode.loss_cls_ce: 3.3912 decode.loss_mask_ce: 1.1513 decode.loss_mask_dice: 2.1519 decode.d7.loss_cls_ce: 3.3934 decode.d7.loss_mask_ce: 1.1470 decode.d7.loss_mask_dice: 2.1559 2023/09/07 10:09:16 - mmengine - INFO - Iter(train) [ 800/60000] base_lr: 9.8668e-05 lr: 9.8668e-05 eta: 16:13:16 time: 0.9809 data_time: 0.0222 memory: 29153 grad_norm: 90.3434 loss: 11.8375 decode.loss_cls_ce: 2.7937 decode.loss_mask_ce: 1.1825 decode.loss_mask_dice: 1.9623 decode.d7.loss_cls_ce: 2.7700 decode.d7.loss_mask_ce: 1.1629 decode.d7.loss_mask_dice: 1.9661 2023/09/07 10:10:05 - mmengine - INFO - Iter(train) [ 850/60000] base_lr: 9.8585e-05 lr: 9.8585e-05 eta: 16:12:09 time: 0.9814 data_time: 0.0214 memory: 29155 grad_norm: 63.9516 loss: 12.9693 decode.loss_cls_ce: 3.0862 decode.loss_mask_ce: 1.1979 decode.loss_mask_dice: 2.2012 decode.d7.loss_cls_ce: 3.0953 decode.d7.loss_mask_ce: 1.1876 decode.d7.loss_mask_dice: 2.2012 2023/09/07 10:10:54 - mmengine - INFO - Iter(train) [ 900/60000] base_lr: 9.8502e-05 lr: 9.8502e-05 eta: 16:11:08 time: 0.9842 data_time: 0.0215 memory: 29267 grad_norm: 117.8918 loss: 12.5343 decode.loss_cls_ce: 3.0796 decode.loss_mask_ce: 1.2022 decode.loss_mask_dice: 1.9712 decode.d7.loss_cls_ce: 3.1263 decode.d7.loss_mask_ce: 1.1768 decode.d7.loss_mask_dice: 1.9782 2023/09/07 10:11:43 - mmengine - INFO - Iter(train) [ 950/60000] base_lr: 9.8418e-05 lr: 9.8418e-05 eta: 16:10:11 time: 0.9824 data_time: 0.0221 memory: 29141 grad_norm: 65.5055 loss: 10.8713 decode.loss_cls_ce: 2.7857 decode.loss_mask_ce: 1.0259 decode.loss_mask_dice: 1.6331 decode.d7.loss_cls_ce: 2.7972 decode.d7.loss_mask_ce: 1.0139 decode.d7.loss_mask_dice: 1.6155 2023/09/07 10:12:33 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 10:12:33 - mmengine - INFO - Iter(train) [ 1000/60000] base_lr: 9.8335e-05 lr: 9.8335e-05 eta: 16:09:10 time: 0.9824 data_time: 0.0215 memory: 29242 grad_norm: 59.5440 loss: 12.4569 decode.loss_cls_ce: 3.0335 decode.loss_mask_ce: 1.1031 decode.loss_mask_dice: 2.0770 decode.d7.loss_cls_ce: 3.0455 decode.d7.loss_mask_ce: 1.1018 decode.d7.loss_mask_dice: 2.0960 2023/09/07 10:13:22 - mmengine - INFO - Iter(train) [ 1050/60000] base_lr: 9.8252e-05 lr: 9.8252e-05 eta: 16:08:12 time: 0.9821 data_time: 0.0218 memory: 29138 grad_norm: 57.9321 loss: 12.2684 decode.loss_cls_ce: 3.0689 decode.loss_mask_ce: 1.0622 decode.loss_mask_dice: 2.0245 decode.d7.loss_cls_ce: 3.0331 decode.d7.loss_mask_ce: 1.0531 decode.d7.loss_mask_dice: 2.0265 2023/09/07 10:14:11 - mmengine - INFO - Iter(train) [ 1100/60000] base_lr: 9.8168e-05 lr: 9.8168e-05 eta: 16:07:16 time: 0.9826 data_time: 0.0221 memory: 29110 grad_norm: 59.2233 loss: 13.4016 decode.loss_cls_ce: 3.1977 decode.loss_mask_ce: 1.3147 decode.loss_mask_dice: 2.2186 decode.d7.loss_cls_ce: 3.1646 decode.d7.loss_mask_ce: 1.3039 decode.d7.loss_mask_dice: 2.2019 2023/09/07 10:15:00 - mmengine - INFO - Iter(train) [ 1150/60000] base_lr: 9.8085e-05 lr: 9.8085e-05 eta: 16:06:19 time: 0.9827 data_time: 0.0218 memory: 29202 grad_norm: 67.0546 loss: 14.1122 decode.loss_cls_ce: 3.1491 decode.loss_mask_ce: 1.3272 decode.loss_mask_dice: 2.5761 decode.d7.loss_cls_ce: 3.1530 decode.d7.loss_mask_ce: 1.3399 decode.d7.loss_mask_dice: 2.5668 2023/09/07 10:15:49 - mmengine - INFO - Iter(train) [ 1200/60000] base_lr: 9.8002e-05 lr: 9.8002e-05 eta: 16:05:22 time: 0.9820 data_time: 0.0219 memory: 29118 grad_norm: 58.8828 loss: 12.7741 decode.loss_cls_ce: 3.1277 decode.loss_mask_ce: 1.1332 decode.loss_mask_dice: 2.1389 decode.d7.loss_cls_ce: 3.1336 decode.d7.loss_mask_ce: 1.1176 decode.d7.loss_mask_dice: 2.1232 2023/09/07 10:16:38 - mmengine - INFO - Iter(train) [ 1250/60000] base_lr: 9.7918e-05 lr: 9.7918e-05 eta: 16:04:28 time: 0.9854 data_time: 0.0223 memory: 29177 grad_norm: 60.3632 loss: 11.6126 decode.loss_cls_ce: 2.8605 decode.loss_mask_ce: 1.1340 decode.loss_mask_dice: 1.8188 decode.d7.loss_cls_ce: 2.8664 decode.d7.loss_mask_ce: 1.1150 decode.d7.loss_mask_dice: 1.8179 2023/09/07 10:17:27 - mmengine - INFO - Iter(train) [ 1300/60000] base_lr: 9.7835e-05 lr: 9.7835e-05 eta: 16:03:33 time: 0.9826 data_time: 0.0218 memory: 29166 grad_norm: 54.1804 loss: 13.5547 decode.loss_cls_ce: 3.0551 decode.loss_mask_ce: 1.2438 decode.loss_mask_dice: 2.4562 decode.d7.loss_cls_ce: 3.0738 decode.d7.loss_mask_ce: 1.2477 decode.d7.loss_mask_dice: 2.4781 2023/09/07 10:18:16 - mmengine - INFO - Iter(train) [ 1350/60000] base_lr: 9.7752e-05 lr: 9.7752e-05 eta: 16:02:39 time: 0.9807 data_time: 0.0216 memory: 29191 grad_norm: 50.5108 loss: 11.6562 decode.loss_cls_ce: 2.7557 decode.loss_mask_ce: 0.9826 decode.loss_mask_dice: 2.0478 decode.d7.loss_cls_ce: 2.8302 decode.d7.loss_mask_ce: 0.9628 decode.d7.loss_mask_dice: 2.0770 2023/09/07 10:19:06 - mmengine - INFO - Iter(train) [ 1400/60000] base_lr: 9.7668e-05 lr: 9.7668e-05 eta: 16:01:45 time: 0.9829 data_time: 0.0220 memory: 29205 grad_norm: 46.2752 loss: 11.4704 decode.loss_cls_ce: 2.6811 decode.loss_mask_ce: 1.1684 decode.loss_mask_dice: 1.8896 decode.d7.loss_cls_ce: 2.6703 decode.d7.loss_mask_ce: 1.1681 decode.d7.loss_mask_dice: 1.8930 2023/09/07 10:19:55 - mmengine - INFO - Iter(train) [ 1450/60000] base_lr: 9.7585e-05 lr: 9.7585e-05 eta: 16:00:52 time: 0.9851 data_time: 0.0221 memory: 29279 grad_norm: 57.5212 loss: 14.7786 decode.loss_cls_ce: 3.3407 decode.loss_mask_ce: 1.3916 decode.loss_mask_dice: 2.6777 decode.d7.loss_cls_ce: 3.3278 decode.d7.loss_mask_ce: 1.3829 decode.d7.loss_mask_dice: 2.6579 2023/09/07 10:20:44 - mmengine - INFO - Iter(train) [ 1500/60000] base_lr: 9.7502e-05 lr: 9.7502e-05 eta: 16:00:00 time: 0.9837 data_time: 0.0214 memory: 29275 grad_norm: 48.3389 loss: 13.0158 decode.loss_cls_ce: 2.8021 decode.loss_mask_ce: 1.1225 decode.loss_mask_dice: 2.5629 decode.d7.loss_cls_ce: 2.8176 decode.d7.loss_mask_ce: 1.1235 decode.d7.loss_mask_dice: 2.5871 2023/09/07 10:21:33 - mmengine - INFO - Iter(train) [ 1550/60000] base_lr: 9.7418e-05 lr: 9.7418e-05 eta: 15:59:05 time: 0.9813 data_time: 0.0218 memory: 29182 grad_norm: 43.9602 loss: 12.9563 decode.loss_cls_ce: 3.0785 decode.loss_mask_ce: 1.1129 decode.loss_mask_dice: 2.2898 decode.d7.loss_cls_ce: 3.0721 decode.d7.loss_mask_ce: 1.1034 decode.d7.loss_mask_dice: 2.2996 2023/09/07 10:22:22 - mmengine - INFO - Iter(train) [ 1600/60000] base_lr: 9.7335e-05 lr: 9.7335e-05 eta: 15:58:13 time: 0.9806 data_time: 0.0216 memory: 29115 grad_norm: 39.5763 loss: 12.0649 decode.loss_cls_ce: 2.8894 decode.loss_mask_ce: 1.1296 decode.loss_mask_dice: 2.0183 decode.d7.loss_cls_ce: 2.8738 decode.d7.loss_mask_ce: 1.1271 decode.d7.loss_mask_dice: 2.0267 2023/09/07 10:23:11 - mmengine - INFO - Iter(train) [ 1650/60000] base_lr: 9.7252e-05 lr: 9.7252e-05 eta: 15:57:21 time: 0.9841 data_time: 0.0220 memory: 29186 grad_norm: 44.9892 loss: 13.8155 decode.loss_cls_ce: 3.1260 decode.loss_mask_ce: 1.2523 decode.loss_mask_dice: 2.5292 decode.d7.loss_cls_ce: 3.1114 decode.d7.loss_mask_ce: 1.2563 decode.d7.loss_mask_dice: 2.5404 2023/09/07 10:24:00 - mmengine - INFO - Iter(train) [ 1700/60000] base_lr: 9.7168e-05 lr: 9.7168e-05 eta: 15:56:29 time: 0.9817 data_time: 0.0215 memory: 29253 grad_norm: 42.1671 loss: 11.5921 decode.loss_cls_ce: 2.7687 decode.loss_mask_ce: 1.0981 decode.loss_mask_dice: 1.9455 decode.d7.loss_cls_ce: 2.7363 decode.d7.loss_mask_ce: 1.0914 decode.d7.loss_mask_dice: 1.9521 2023/09/07 10:24:50 - mmengine - INFO - Iter(train) [ 1750/60000] base_lr: 9.7085e-05 lr: 9.7085e-05 eta: 15:55:37 time: 0.9840 data_time: 0.0221 memory: 29254 grad_norm: 35.2296 loss: 14.7968 decode.loss_cls_ce: 3.2694 decode.loss_mask_ce: 1.2754 decode.loss_mask_dice: 2.8493 decode.d7.loss_cls_ce: 3.2879 decode.d7.loss_mask_ce: 1.2707 decode.d7.loss_mask_dice: 2.8440 2023/09/07 10:25:39 - mmengine - INFO - Iter(train) [ 1800/60000] base_lr: 9.7002e-05 lr: 9.7002e-05 eta: 15:54:44 time: 0.9830 data_time: 0.0218 memory: 29129 grad_norm: 63.5483 loss: 12.6028 decode.loss_cls_ce: 2.8181 decode.loss_mask_ce: 1.1526 decode.loss_mask_dice: 2.3303 decode.d7.loss_cls_ce: 2.8669 decode.d7.loss_mask_ce: 1.1293 decode.d7.loss_mask_dice: 2.3056 2023/09/07 10:26:28 - mmengine - INFO - Iter(train) [ 1850/60000] base_lr: 9.6918e-05 lr: 9.6918e-05 eta: 15:53:55 time: 0.9821 data_time: 0.0227 memory: 29163 grad_norm: 37.0462 loss: 12.1498 decode.loss_cls_ce: 2.7205 decode.loss_mask_ce: 1.0661 decode.loss_mask_dice: 2.2680 decode.d7.loss_cls_ce: 2.7893 decode.d7.loss_mask_ce: 1.0446 decode.d7.loss_mask_dice: 2.2613 2023/09/07 10:27:17 - mmengine - INFO - Iter(train) [ 1900/60000] base_lr: 9.6835e-05 lr: 9.6835e-05 eta: 15:53:03 time: 0.9819 data_time: 0.0220 memory: 29150 grad_norm: 41.0151 loss: 11.4224 decode.loss_cls_ce: 2.5584 decode.loss_mask_ce: 1.1201 decode.loss_mask_dice: 2.0242 decode.d7.loss_cls_ce: 2.5791 decode.d7.loss_mask_ce: 1.1234 decode.d7.loss_mask_dice: 2.0173 2023/09/07 10:28:06 - mmengine - INFO - Iter(train) [ 1950/60000] base_lr: 9.6752e-05 lr: 9.6752e-05 eta: 15:52:13 time: 0.9858 data_time: 0.0211 memory: 29170 grad_norm: 33.9099 loss: 12.5996 decode.loss_cls_ce: 2.9706 decode.loss_mask_ce: 1.0796 decode.loss_mask_dice: 2.2581 decode.d7.loss_cls_ce: 2.9646 decode.d7.loss_mask_ce: 1.0771 decode.d7.loss_mask_dice: 2.2496 2023/09/07 10:28:55 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 10:28:55 - mmengine - INFO - Iter(train) [ 2000/60000] base_lr: 9.6668e-05 lr: 9.6668e-05 eta: 15:51:21 time: 0.9823 data_time: 0.0224 memory: 29249 grad_norm: 59.3679 loss: 11.8034 decode.loss_cls_ce: 2.6722 decode.loss_mask_ce: 1.0504 decode.loss_mask_dice: 2.1776 decode.d7.loss_cls_ce: 2.6480 decode.d7.loss_mask_ce: 1.0591 decode.d7.loss_mask_dice: 2.1961 2023/09/07 10:29:44 - mmengine - INFO - Iter(train) [ 2050/60000] base_lr: 9.6585e-05 lr: 9.6585e-05 eta: 15:50:31 time: 0.9806 data_time: 0.0222 memory: 29266 grad_norm: 44.0217 loss: 12.1563 decode.loss_cls_ce: 2.6102 decode.loss_mask_ce: 1.0458 decode.loss_mask_dice: 2.4278 decode.d7.loss_cls_ce: 2.6149 decode.d7.loss_mask_ce: 1.0387 decode.d7.loss_mask_dice: 2.4189 2023/09/07 10:30:34 - mmengine - INFO - Iter(train) [ 2100/60000] base_lr: 9.6502e-05 lr: 9.6502e-05 eta: 15:49:41 time: 0.9832 data_time: 0.0219 memory: 29294 grad_norm: 40.0557 loss: 12.2900 decode.loss_cls_ce: 2.6072 decode.loss_mask_ce: 1.3337 decode.loss_mask_dice: 2.1983 decode.d7.loss_cls_ce: 2.6468 decode.d7.loss_mask_ce: 1.3108 decode.d7.loss_mask_dice: 2.1930 2023/09/07 10:31:23 - mmengine - INFO - Iter(train) [ 2150/60000] base_lr: 9.6418e-05 lr: 9.6418e-05 eta: 15:48:52 time: 0.9827 data_time: 0.0216 memory: 29303 grad_norm: 38.2530 loss: 11.8145 decode.loss_cls_ce: 2.6694 decode.loss_mask_ce: 0.9949 decode.loss_mask_dice: 2.2651 decode.d7.loss_cls_ce: 2.6403 decode.d7.loss_mask_ce: 0.9789 decode.d7.loss_mask_dice: 2.2659 2023/09/07 10:32:12 - mmengine - INFO - Iter(train) [ 2200/60000] base_lr: 9.6335e-05 lr: 9.6335e-05 eta: 15:48:02 time: 0.9838 data_time: 0.0222 memory: 29138 grad_norm: 36.2205 loss: 9.4970 decode.loss_cls_ce: 2.1605 decode.loss_mask_ce: 1.0153 decode.loss_mask_dice: 1.5685 decode.d7.loss_cls_ce: 2.1578 decode.d7.loss_mask_ce: 1.0171 decode.d7.loss_mask_dice: 1.5778 2023/09/07 10:33:01 - mmengine - INFO - Iter(train) [ 2250/60000] base_lr: 9.6252e-05 lr: 9.6252e-05 eta: 15:47:11 time: 0.9814 data_time: 0.0224 memory: 29149 grad_norm: 30.4604 loss: 10.5465 decode.loss_cls_ce: 2.3765 decode.loss_mask_ce: 1.0685 decode.loss_mask_dice: 1.8572 decode.d7.loss_cls_ce: 2.3270 decode.d7.loss_mask_ce: 1.0587 decode.d7.loss_mask_dice: 1.8587 2023/09/07 10:33:50 - mmengine - INFO - Iter(train) [ 2300/60000] base_lr: 9.6168e-05 lr: 9.6168e-05 eta: 15:46:21 time: 0.9853 data_time: 0.0219 memory: 29142 grad_norm: 33.3606 loss: 11.9627 decode.loss_cls_ce: 2.5799 decode.loss_mask_ce: 1.1710 decode.loss_mask_dice: 2.2117 decode.d7.loss_cls_ce: 2.6235 decode.d7.loss_mask_ce: 1.1579 decode.d7.loss_mask_dice: 2.2187 2023/09/07 10:34:40 - mmengine - INFO - Iter(train) [ 2350/60000] base_lr: 9.6085e-05 lr: 9.6085e-05 eta: 15:45:33 time: 0.9864 data_time: 0.0211 memory: 29217 grad_norm: 32.3101 loss: 11.2632 decode.loss_cls_ce: 2.6697 decode.loss_mask_ce: 0.9638 decode.loss_mask_dice: 2.0040 decode.d7.loss_cls_ce: 2.6468 decode.d7.loss_mask_ce: 0.9625 decode.d7.loss_mask_dice: 2.0164 2023/09/07 10:35:29 - mmengine - INFO - Iter(train) [ 2400/60000] base_lr: 9.6002e-05 lr: 9.6002e-05 eta: 15:44:42 time: 0.9812 data_time: 0.0223 memory: 29323 grad_norm: 34.9698 loss: 10.7776 decode.loss_cls_ce: 2.5699 decode.loss_mask_ce: 1.0327 decode.loss_mask_dice: 1.7912 decode.d7.loss_cls_ce: 2.5582 decode.d7.loss_mask_ce: 1.0317 decode.d7.loss_mask_dice: 1.7939 2023/09/07 10:36:18 - mmengine - INFO - Iter(train) [ 2450/60000] base_lr: 9.5918e-05 lr: 9.5918e-05 eta: 15:43:53 time: 0.9826 data_time: 0.0222 memory: 29268 grad_norm: 38.4848 loss: 11.0512 decode.loss_cls_ce: 2.5035 decode.loss_mask_ce: 0.9987 decode.loss_mask_dice: 2.0502 decode.d7.loss_cls_ce: 2.4524 decode.d7.loss_mask_ce: 0.9968 decode.d7.loss_mask_dice: 2.0496 2023/09/07 10:37:07 - mmengine - INFO - Iter(train) [ 2500/60000] base_lr: 9.5835e-05 lr: 9.5835e-05 eta: 15:43:03 time: 0.9823 data_time: 0.0216 memory: 29203 grad_norm: 34.4379 loss: 11.1354 decode.loss_cls_ce: 2.4652 decode.loss_mask_ce: 1.0275 decode.loss_mask_dice: 2.0785 decode.d7.loss_cls_ce: 2.4206 decode.d7.loss_mask_ce: 1.0383 decode.d7.loss_mask_dice: 2.1052 2023/09/07 10:37:56 - mmengine - INFO - Iter(train) [ 2550/60000] base_lr: 9.5752e-05 lr: 9.5752e-05 eta: 15:42:12 time: 0.9818 data_time: 0.0222 memory: 29266 grad_norm: 36.6009 loss: 12.2185 decode.loss_cls_ce: 2.6649 decode.loss_mask_ce: 1.0881 decode.loss_mask_dice: 2.3729 decode.d7.loss_cls_ce: 2.6359 decode.d7.loss_mask_ce: 1.0864 decode.d7.loss_mask_dice: 2.3703 2023/09/07 10:38:45 - mmengine - INFO - Iter(train) [ 2600/60000] base_lr: 9.5668e-05 lr: 9.5668e-05 eta: 15:41:22 time: 0.9824 data_time: 0.0224 memory: 29136 grad_norm: 30.8423 loss: 10.1415 decode.loss_cls_ce: 2.2433 decode.loss_mask_ce: 1.0601 decode.loss_mask_dice: 1.7498 decode.d7.loss_cls_ce: 2.2565 decode.d7.loss_mask_ce: 1.0611 decode.d7.loss_mask_dice: 1.7707 2023/09/07 10:39:35 - mmengine - INFO - Iter(train) [ 2650/60000] base_lr: 9.5585e-05 lr: 9.5585e-05 eta: 15:40:33 time: 0.9825 data_time: 0.0216 memory: 29182 grad_norm: 33.3962 loss: 11.6690 decode.loss_cls_ce: 2.6168 decode.loss_mask_ce: 1.1318 decode.loss_mask_dice: 2.0882 decode.d7.loss_cls_ce: 2.6187 decode.d7.loss_mask_ce: 1.1245 decode.d7.loss_mask_dice: 2.0890 2023/09/07 10:40:24 - mmengine - INFO - Iter(train) [ 2700/60000] base_lr: 9.5502e-05 lr: 9.5502e-05 eta: 15:39:42 time: 0.9805 data_time: 0.0221 memory: 29156 grad_norm: 36.3017 loss: 12.3683 decode.loss_cls_ce: 2.5505 decode.loss_mask_ce: 1.1817 decode.loss_mask_dice: 2.4353 decode.d7.loss_cls_ce: 2.5787 decode.d7.loss_mask_ce: 1.1718 decode.d7.loss_mask_dice: 2.4503 2023/09/07 10:41:13 - mmengine - INFO - Iter(train) [ 2750/60000] base_lr: 9.5418e-05 lr: 9.5418e-05 eta: 15:38:52 time: 0.9856 data_time: 0.0211 memory: 29090 grad_norm: 41.9020 loss: 9.0577 decode.loss_cls_ce: 1.9923 decode.loss_mask_ce: 0.8596 decode.loss_mask_dice: 1.6945 decode.d7.loss_cls_ce: 1.9384 decode.d7.loss_mask_ce: 0.8622 decode.d7.loss_mask_dice: 1.7106 2023/09/07 10:42:02 - mmengine - INFO - Iter(train) [ 2800/60000] base_lr: 9.5335e-05 lr: 9.5335e-05 eta: 15:38:04 time: 0.9860 data_time: 0.0215 memory: 29330 grad_norm: 35.0663 loss: 12.7959 decode.loss_cls_ce: 2.8586 decode.loss_mask_ce: 1.1364 decode.loss_mask_dice: 2.4217 decode.d7.loss_cls_ce: 2.8382 decode.d7.loss_mask_ce: 1.1422 decode.d7.loss_mask_dice: 2.3987 2023/09/07 10:42:51 - mmengine - INFO - Iter(train) [ 2850/60000] base_lr: 9.5252e-05 lr: 9.5252e-05 eta: 15:37:13 time: 0.9831 data_time: 0.0220 memory: 29218 grad_norm: 37.6788 loss: 11.4999 decode.loss_cls_ce: 2.6288 decode.loss_mask_ce: 1.1185 decode.loss_mask_dice: 2.0222 decode.d7.loss_cls_ce: 2.5891 decode.d7.loss_mask_ce: 1.1162 decode.d7.loss_mask_dice: 2.0251 2023/09/07 10:43:41 - mmengine - INFO - Iter(train) [ 2900/60000] base_lr: 9.5168e-05 lr: 9.5168e-05 eta: 15:36:24 time: 0.9857 data_time: 0.0218 memory: 29255 grad_norm: 37.0762 loss: 10.5735 decode.loss_cls_ce: 2.3457 decode.loss_mask_ce: 1.0374 decode.loss_mask_dice: 1.8862 decode.d7.loss_cls_ce: 2.3879 decode.d7.loss_mask_ce: 1.0263 decode.d7.loss_mask_dice: 1.8900 2023/09/07 10:44:30 - mmengine - INFO - Iter(train) [ 2950/60000] base_lr: 9.5085e-05 lr: 9.5085e-05 eta: 15:35:36 time: 0.9818 data_time: 0.0214 memory: 29165 grad_norm: 35.7468 loss: 9.4556 decode.loss_cls_ce: 2.0443 decode.loss_mask_ce: 0.9318 decode.loss_mask_dice: 1.7505 decode.d7.loss_cls_ce: 2.0550 decode.d7.loss_mask_ce: 0.9188 decode.d7.loss_mask_dice: 1.7552 2023/09/07 10:45:19 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 10:45:19 - mmengine - INFO - Iter(train) [ 3000/60000] base_lr: 9.5002e-05 lr: 9.5002e-05 eta: 15:34:46 time: 0.9845 data_time: 0.0215 memory: 29212 grad_norm: 27.8037 loss: 10.2846 decode.loss_cls_ce: 2.2649 decode.loss_mask_ce: 0.9609 decode.loss_mask_dice: 1.9271 decode.d7.loss_cls_ce: 2.2712 decode.d7.loss_mask_ce: 0.9605 decode.d7.loss_mask_dice: 1.8999 2023/09/07 10:46:08 - mmengine - INFO - Iter(train) [ 3050/60000] base_lr: 9.4918e-05 lr: 9.4918e-05 eta: 15:33:56 time: 0.9832 data_time: 0.0223 memory: 29178 grad_norm: 35.1002 loss: 11.7075 decode.loss_cls_ce: 2.4525 decode.loss_mask_ce: 1.2199 decode.loss_mask_dice: 2.1735 decode.d7.loss_cls_ce: 2.4392 decode.d7.loss_mask_ce: 1.2309 decode.d7.loss_mask_dice: 2.1916 2023/09/07 10:46:57 - mmengine - INFO - Iter(train) [ 3100/60000] base_lr: 9.4835e-05 lr: 9.4835e-05 eta: 15:33:06 time: 0.9840 data_time: 0.0218 memory: 29265 grad_norm: 35.7800 loss: 10.4411 decode.loss_cls_ce: 2.3823 decode.loss_mask_ce: 0.9981 decode.loss_mask_dice: 1.8451 decode.d7.loss_cls_ce: 2.3847 decode.d7.loss_mask_ce: 0.9956 decode.d7.loss_mask_dice: 1.8354 2023/09/07 10:47:46 - mmengine - INFO - Iter(train) [ 3150/60000] base_lr: 9.4752e-05 lr: 9.4752e-05 eta: 15:32:17 time: 0.9824 data_time: 0.0225 memory: 29203 grad_norm: 39.2535 loss: 10.7956 decode.loss_cls_ce: 2.4097 decode.loss_mask_ce: 0.9683 decode.loss_mask_dice: 2.0422 decode.d7.loss_cls_ce: 2.3712 decode.d7.loss_mask_ce: 0.9562 decode.d7.loss_mask_dice: 2.0481 2023/09/07 10:48:36 - mmengine - INFO - Iter(train) [ 3200/60000] base_lr: 9.4668e-05 lr: 9.4668e-05 eta: 15:31:27 time: 0.9837 data_time: 0.0214 memory: 29135 grad_norm: 32.2816 loss: 10.3481 decode.loss_cls_ce: 2.1289 decode.loss_mask_ce: 1.0568 decode.loss_mask_dice: 1.9818 decode.d7.loss_cls_ce: 2.1407 decode.d7.loss_mask_ce: 1.0572 decode.d7.loss_mask_dice: 1.9828 2023/09/07 10:49:25 - mmengine - INFO - Iter(train) [ 3250/60000] base_lr: 9.4585e-05 lr: 9.4585e-05 eta: 15:30:36 time: 0.9830 data_time: 0.0225 memory: 29191 grad_norm: 35.9784 loss: 12.1304 decode.loss_cls_ce: 2.6570 decode.loss_mask_ce: 1.1696 decode.loss_mask_dice: 2.2343 decode.d7.loss_cls_ce: 2.6937 decode.d7.loss_mask_ce: 1.1439 decode.d7.loss_mask_dice: 2.2318 2023/09/07 10:50:14 - mmengine - INFO - Iter(train) [ 3300/60000] base_lr: 9.4502e-05 lr: 9.4502e-05 eta: 15:29:46 time: 0.9815 data_time: 0.0223 memory: 29329 grad_norm: 37.9392 loss: 10.3997 decode.loss_cls_ce: 2.2844 decode.loss_mask_ce: 1.0174 decode.loss_mask_dice: 1.9123 decode.d7.loss_cls_ce: 2.2697 decode.d7.loss_mask_ce: 1.0169 decode.d7.loss_mask_dice: 1.8990 2023/09/07 10:51:03 - mmengine - INFO - Iter(train) [ 3350/60000] base_lr: 9.4418e-05 lr: 9.4418e-05 eta: 15:28:56 time: 0.9838 data_time: 0.0224 memory: 29294 grad_norm: 29.5290 loss: 9.6494 decode.loss_cls_ce: 2.1408 decode.loss_mask_ce: 0.9757 decode.loss_mask_dice: 1.7074 decode.d7.loss_cls_ce: 2.1097 decode.d7.loss_mask_ce: 0.9918 decode.d7.loss_mask_dice: 1.7241 2023/09/07 10:51:52 - mmengine - INFO - Iter(train) [ 3400/60000] base_lr: 9.4335e-05 lr: 9.4335e-05 eta: 15:28:06 time: 0.9845 data_time: 0.0215 memory: 29314 grad_norm: 33.3080 loss: 11.4711 decode.loss_cls_ce: 2.6828 decode.loss_mask_ce: 0.9544 decode.loss_mask_dice: 2.0885 decode.d7.loss_cls_ce: 2.7004 decode.d7.loss_mask_ce: 0.9506 decode.d7.loss_mask_dice: 2.0945 2023/09/07 10:52:41 - mmengine - INFO - Iter(train) [ 3450/60000] base_lr: 9.4252e-05 lr: 9.4252e-05 eta: 15:27:16 time: 0.9825 data_time: 0.0221 memory: 29253 grad_norm: 27.3595 loss: 8.3305 decode.loss_cls_ce: 1.9848 decode.loss_mask_ce: 0.8412 decode.loss_mask_dice: 1.3536 decode.d7.loss_cls_ce: 1.9514 decode.d7.loss_mask_ce: 0.8322 decode.d7.loss_mask_dice: 1.3675 2023/09/07 10:53:30 - mmengine - INFO - Iter(train) [ 3500/60000] base_lr: 9.4168e-05 lr: 9.4168e-05 eta: 15:26:27 time: 0.9835 data_time: 0.0231 memory: 29322 grad_norm: 35.8211 loss: 10.6233 decode.loss_cls_ce: 2.0757 decode.loss_mask_ce: 1.1633 decode.loss_mask_dice: 2.0504 decode.d7.loss_cls_ce: 2.1287 decode.d7.loss_mask_ce: 1.1473 decode.d7.loss_mask_dice: 2.0579 2023/09/07 10:54:20 - mmengine - INFO - Iter(train) [ 3550/60000] base_lr: 9.4085e-05 lr: 9.4085e-05 eta: 15:25:37 time: 0.9831 data_time: 0.0225 memory: 29141 grad_norm: 32.3121 loss: 11.0884 decode.loss_cls_ce: 2.5307 decode.loss_mask_ce: 1.0911 decode.loss_mask_dice: 1.9100 decode.d7.loss_cls_ce: 2.5296 decode.d7.loss_mask_ce: 1.1017 decode.d7.loss_mask_dice: 1.9252 2023/09/07 10:55:09 - mmengine - INFO - Iter(train) [ 3600/60000] base_lr: 9.4002e-05 lr: 9.4002e-05 eta: 15:24:47 time: 0.9835 data_time: 0.0227 memory: 29127 grad_norm: 44.4064 loss: 10.1567 decode.loss_cls_ce: 2.1861 decode.loss_mask_ce: 1.0689 decode.loss_mask_dice: 1.8392 decode.d7.loss_cls_ce: 2.1771 decode.d7.loss_mask_ce: 1.0604 decode.d7.loss_mask_dice: 1.8251 2023/09/07 10:55:58 - mmengine - INFO - Iter(train) [ 3650/60000] base_lr: 9.3918e-05 lr: 9.3918e-05 eta: 15:23:57 time: 0.9839 data_time: 0.0220 memory: 29227 grad_norm: 29.3395 loss: 10.8645 decode.loss_cls_ce: 2.2385 decode.loss_mask_ce: 1.0467 decode.loss_mask_dice: 2.1641 decode.d7.loss_cls_ce: 2.2116 decode.d7.loss_mask_ce: 1.0440 decode.d7.loss_mask_dice: 2.1597 2023/09/07 10:56:47 - mmengine - INFO - Iter(train) [ 3700/60000] base_lr: 9.3835e-05 lr: 9.3835e-05 eta: 15:23:08 time: 0.9826 data_time: 0.0222 memory: 29155 grad_norm: 37.8340 loss: 10.6965 decode.loss_cls_ce: 2.4747 decode.loss_mask_ce: 0.9419 decode.loss_mask_dice: 1.9587 decode.d7.loss_cls_ce: 2.4395 decode.d7.loss_mask_ce: 0.9369 decode.d7.loss_mask_dice: 1.9449 2023/09/07 10:57:36 - mmengine - INFO - Iter(train) [ 3750/60000] base_lr: 9.3752e-05 lr: 9.3752e-05 eta: 15:22:18 time: 0.9831 data_time: 0.0226 memory: 29167 grad_norm: 28.1945 loss: 9.4002 decode.loss_cls_ce: 2.2009 decode.loss_mask_ce: 0.9065 decode.loss_mask_dice: 1.6037 decode.d7.loss_cls_ce: 2.1860 decode.d7.loss_mask_ce: 0.9071 decode.d7.loss_mask_dice: 1.5960 2023/09/07 10:58:25 - mmengine - INFO - Iter(train) [ 3800/60000] base_lr: 9.3668e-05 lr: 9.3668e-05 eta: 15:21:29 time: 0.9853 data_time: 0.0223 memory: 29197 grad_norm: 28.6707 loss: 11.3677 decode.loss_cls_ce: 2.3058 decode.loss_mask_ce: 1.1293 decode.loss_mask_dice: 2.2431 decode.d7.loss_cls_ce: 2.2751 decode.d7.loss_mask_ce: 1.1327 decode.d7.loss_mask_dice: 2.2817 2023/09/07 10:59:15 - mmengine - INFO - Iter(train) [ 3850/60000] base_lr: 9.3585e-05 lr: 9.3585e-05 eta: 15:20:39 time: 0.9827 data_time: 0.0219 memory: 29255 grad_norm: 29.2017 loss: 10.9537 decode.loss_cls_ce: 2.3528 decode.loss_mask_ce: 0.9431 decode.loss_mask_dice: 2.1895 decode.d7.loss_cls_ce: 2.3543 decode.d7.loss_mask_ce: 0.9348 decode.d7.loss_mask_dice: 2.1792 2023/09/07 11:00:04 - mmengine - INFO - Iter(train) [ 3900/60000] base_lr: 9.3502e-05 lr: 9.3502e-05 eta: 15:19:49 time: 0.9833 data_time: 0.0220 memory: 29182 grad_norm: 27.8297 loss: 11.5451 decode.loss_cls_ce: 2.5673 decode.loss_mask_ce: 1.0897 decode.loss_mask_dice: 2.1202 decode.d7.loss_cls_ce: 2.5689 decode.d7.loss_mask_ce: 1.0768 decode.d7.loss_mask_dice: 2.1222 2023/09/07 11:00:53 - mmengine - INFO - Iter(train) [ 3950/60000] base_lr: 9.3418e-05 lr: 9.3418e-05 eta: 15:19:00 time: 0.9823 data_time: 0.0219 memory: 29216 grad_norm: 36.0966 loss: 11.3710 decode.loss_cls_ce: 2.4783 decode.loss_mask_ce: 1.1910 decode.loss_mask_dice: 1.9930 decode.d7.loss_cls_ce: 2.4754 decode.d7.loss_mask_ce: 1.2037 decode.d7.loss_mask_dice: 2.0296 2023/09/07 11:01:42 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 11:01:42 - mmengine - INFO - Iter(train) [ 4000/60000] base_lr: 9.3335e-05 lr: 9.3335e-05 eta: 15:18:11 time: 0.9841 data_time: 0.0216 memory: 29446 grad_norm: 28.3508 loss: 13.3290 decode.loss_cls_ce: 2.9149 decode.loss_mask_ce: 1.0546 decode.loss_mask_dice: 2.6758 decode.d7.loss_cls_ce: 2.9367 decode.d7.loss_mask_ce: 1.0444 decode.d7.loss_mask_dice: 2.7027 2023/09/07 11:02:31 - mmengine - INFO - Iter(train) [ 4050/60000] base_lr: 9.3252e-05 lr: 9.3252e-05 eta: 15:17:22 time: 0.9835 data_time: 0.0218 memory: 29210 grad_norm: 33.0849 loss: 9.1874 decode.loss_cls_ce: 2.1164 decode.loss_mask_ce: 0.9361 decode.loss_mask_dice: 1.5338 decode.d7.loss_cls_ce: 2.1304 decode.d7.loss_mask_ce: 0.9291 decode.d7.loss_mask_dice: 1.5416 2023/09/07 11:03:20 - mmengine - INFO - Iter(train) [ 4100/60000] base_lr: 9.3168e-05 lr: 9.3168e-05 eta: 15:16:32 time: 0.9851 data_time: 0.0215 memory: 29343 grad_norm: 29.1679 loss: 10.1066 decode.loss_cls_ce: 2.2473 decode.loss_mask_ce: 0.9167 decode.loss_mask_dice: 1.8806 decode.d7.loss_cls_ce: 2.2741 decode.d7.loss_mask_ce: 0.9068 decode.d7.loss_mask_dice: 1.8811 2023/09/07 11:04:10 - mmengine - INFO - Iter(train) [ 4150/60000] base_lr: 9.3085e-05 lr: 9.3085e-05 eta: 15:15:43 time: 0.9831 data_time: 0.0224 memory: 29239 grad_norm: 27.7997 loss: 9.9355 decode.loss_cls_ce: 2.0835 decode.loss_mask_ce: 0.9381 decode.loss_mask_dice: 1.9319 decode.d7.loss_cls_ce: 2.1084 decode.d7.loss_mask_ce: 0.9358 decode.d7.loss_mask_dice: 1.9378 2023/09/07 11:04:59 - mmengine - INFO - Iter(train) [ 4200/60000] base_lr: 9.3002e-05 lr: 9.3002e-05 eta: 15:14:54 time: 0.9864 data_time: 0.0208 memory: 29157 grad_norm: 24.2400 loss: 12.0140 decode.loss_cls_ce: 2.4944 decode.loss_mask_ce: 1.0963 decode.loss_mask_dice: 2.4359 decode.d7.loss_cls_ce: 2.4858 decode.d7.loss_mask_ce: 1.0862 decode.d7.loss_mask_dice: 2.4154 2023/09/07 11:05:48 - mmengine - INFO - Iter(train) [ 4250/60000] base_lr: 9.2918e-05 lr: 9.2918e-05 eta: 15:14:04 time: 0.9829 data_time: 0.0217 memory: 29111 grad_norm: 25.8026 loss: 9.8683 decode.loss_cls_ce: 2.1325 decode.loss_mask_ce: 0.9446 decode.loss_mask_dice: 1.8460 decode.d7.loss_cls_ce: 2.1663 decode.d7.loss_mask_ce: 0.9444 decode.d7.loss_mask_dice: 1.8345 2023/09/07 11:06:37 - mmengine - INFO - Iter(train) [ 4300/60000] base_lr: 9.2835e-05 lr: 9.2835e-05 eta: 15:13:15 time: 0.9861 data_time: 0.0217 memory: 29301 grad_norm: 30.8212 loss: 11.3765 decode.loss_cls_ce: 2.4626 decode.loss_mask_ce: 1.1213 decode.loss_mask_dice: 2.1167 decode.d7.loss_cls_ce: 2.4399 decode.d7.loss_mask_ce: 1.1253 decode.d7.loss_mask_dice: 2.1108 2023/09/07 11:07:26 - mmengine - INFO - Iter(train) [ 4350/60000] base_lr: 9.2752e-05 lr: 9.2752e-05 eta: 15:12:25 time: 0.9805 data_time: 0.0217 memory: 29204 grad_norm: 30.2371 loss: 10.9862 decode.loss_cls_ce: 2.3506 decode.loss_mask_ce: 0.9706 decode.loss_mask_dice: 2.1678 decode.d7.loss_cls_ce: 2.3394 decode.d7.loss_mask_ce: 0.9851 decode.d7.loss_mask_dice: 2.1726 2023/09/07 11:08:16 - mmengine - INFO - Iter(train) [ 4400/60000] base_lr: 9.2668e-05 lr: 9.2668e-05 eta: 15:11:36 time: 0.9839 data_time: 0.0220 memory: 29115 grad_norm: 26.2596 loss: 10.1781 decode.loss_cls_ce: 2.2046 decode.loss_mask_ce: 0.9468 decode.loss_mask_dice: 1.9570 decode.d7.loss_cls_ce: 2.1968 decode.d7.loss_mask_ce: 0.9414 decode.d7.loss_mask_dice: 1.9314 2023/09/07 11:09:05 - mmengine - INFO - Iter(train) [ 4450/60000] base_lr: 9.2585e-05 lr: 9.2585e-05 eta: 15:10:47 time: 0.9863 data_time: 0.0219 memory: 29109 grad_norm: 30.0551 loss: 9.5450 decode.loss_cls_ce: 2.0699 decode.loss_mask_ce: 1.0520 decode.loss_mask_dice: 1.6374 decode.d7.loss_cls_ce: 2.0764 decode.d7.loss_mask_ce: 1.0454 decode.d7.loss_mask_dice: 1.6639 2023/09/07 11:09:54 - mmengine - INFO - Iter(train) [ 4500/60000] base_lr: 9.2502e-05 lr: 9.2502e-05 eta: 15:09:57 time: 0.9830 data_time: 0.0219 memory: 29164 grad_norm: 31.3395 loss: 10.3649 decode.loss_cls_ce: 2.2307 decode.loss_mask_ce: 0.9450 decode.loss_mask_dice: 1.9951 decode.d7.loss_cls_ce: 2.2501 decode.d7.loss_mask_ce: 0.9469 decode.d7.loss_mask_dice: 1.9971 2023/09/07 11:10:43 - mmengine - INFO - Iter(train) [ 4550/60000] base_lr: 9.2418e-05 lr: 9.2418e-05 eta: 15:09:08 time: 0.9840 data_time: 0.0216 memory: 29331 grad_norm: 34.5000 loss: 9.3717 decode.loss_cls_ce: 2.0546 decode.loss_mask_ce: 0.8444 decode.loss_mask_dice: 1.7679 decode.d7.loss_cls_ce: 2.1148 decode.d7.loss_mask_ce: 0.8286 decode.d7.loss_mask_dice: 1.7615 2023/09/07 11:11:32 - mmengine - INFO - Iter(train) [ 4600/60000] base_lr: 9.2335e-05 lr: 9.2335e-05 eta: 15:08:18 time: 0.9823 data_time: 0.0215 memory: 29113 grad_norm: 41.9254 loss: 9.0739 decode.loss_cls_ce: 2.1652 decode.loss_mask_ce: 0.8566 decode.loss_mask_dice: 1.5282 decode.d7.loss_cls_ce: 2.1897 decode.d7.loss_mask_ce: 0.8306 decode.d7.loss_mask_dice: 1.5035 2023/09/07 11:12:21 - mmengine - INFO - Iter(train) [ 4650/60000] base_lr: 9.2252e-05 lr: 9.2252e-05 eta: 15:07:29 time: 0.9815 data_time: 0.0215 memory: 29117 grad_norm: 29.3764 loss: 8.7286 decode.loss_cls_ce: 2.0532 decode.loss_mask_ce: 0.8594 decode.loss_mask_dice: 1.4724 decode.d7.loss_cls_ce: 2.0269 decode.d7.loss_mask_ce: 0.8465 decode.d7.loss_mask_dice: 1.4702 2023/09/07 11:13:11 - mmengine - INFO - Iter(train) [ 4700/60000] base_lr: 9.2168e-05 lr: 9.2168e-05 eta: 15:06:39 time: 0.9817 data_time: 0.0222 memory: 29268 grad_norm: 44.1663 loss: 10.0996 decode.loss_cls_ce: 2.3080 decode.loss_mask_ce: 0.9455 decode.loss_mask_dice: 1.8130 decode.d7.loss_cls_ce: 2.2875 decode.d7.loss_mask_ce: 0.9450 decode.d7.loss_mask_dice: 1.8007 2023/09/07 11:14:00 - mmengine - INFO - Iter(train) [ 4750/60000] base_lr: 9.2085e-05 lr: 9.2085e-05 eta: 15:05:49 time: 0.9804 data_time: 0.0226 memory: 29130 grad_norm: 27.4759 loss: 9.8369 decode.loss_cls_ce: 2.1143 decode.loss_mask_ce: 1.0108 decode.loss_mask_dice: 1.7958 decode.d7.loss_cls_ce: 2.1076 decode.d7.loss_mask_ce: 1.0060 decode.d7.loss_mask_dice: 1.8024 2023/09/07 11:14:49 - mmengine - INFO - Iter(train) [ 4800/60000] base_lr: 9.2002e-05 lr: 9.2002e-05 eta: 15:05:00 time: 0.9838 data_time: 0.0225 memory: 29215 grad_norm: 24.6865 loss: 8.5802 decode.loss_cls_ce: 2.1115 decode.loss_mask_ce: 0.7063 decode.loss_mask_dice: 1.4588 decode.d7.loss_cls_ce: 2.0987 decode.d7.loss_mask_ce: 0.7230 decode.d7.loss_mask_dice: 1.4818 2023/09/07 11:15:38 - mmengine - INFO - Iter(train) [ 4850/60000] base_lr: 9.1918e-05 lr: 9.1918e-05 eta: 15:04:10 time: 0.9855 data_time: 0.0220 memory: 29242 grad_norm: 28.8297 loss: 9.9279 decode.loss_cls_ce: 2.2450 decode.loss_mask_ce: 0.9713 decode.loss_mask_dice: 1.7523 decode.d7.loss_cls_ce: 2.2520 decode.d7.loss_mask_ce: 0.9555 decode.d7.loss_mask_dice: 1.7518 2023/09/07 11:16:27 - mmengine - INFO - Iter(train) [ 4900/60000] base_lr: 9.1835e-05 lr: 9.1835e-05 eta: 15:03:20 time: 0.9821 data_time: 0.0220 memory: 29147 grad_norm: 31.8668 loss: 9.3713 decode.loss_cls_ce: 2.0009 decode.loss_mask_ce: 0.9403 decode.loss_mask_dice: 1.7498 decode.d7.loss_cls_ce: 1.9846 decode.d7.loss_mask_ce: 0.9433 decode.d7.loss_mask_dice: 1.7525 2023/09/07 11:17:16 - mmengine - INFO - Iter(train) [ 4950/60000] base_lr: 9.1752e-05 lr: 9.1752e-05 eta: 15:02:31 time: 0.9853 data_time: 0.0225 memory: 29227 grad_norm: 29.5336 loss: 10.9746 decode.loss_cls_ce: 2.4015 decode.loss_mask_ce: 0.9928 decode.loss_mask_dice: 2.1110 decode.d7.loss_cls_ce: 2.3567 decode.d7.loss_mask_ce: 1.0057 decode.d7.loss_mask_dice: 2.1069 2023/09/07 11:18:06 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 11:18:06 - mmengine - INFO - Iter(train) [ 5000/60000] base_lr: 9.1668e-05 lr: 9.1668e-05 eta: 15:01:43 time: 0.9851 data_time: 0.0219 memory: 29212 grad_norm: 30.6829 loss: 10.4803 decode.loss_cls_ce: 2.1235 decode.loss_mask_ce: 1.0306 decode.loss_mask_dice: 2.0740 decode.d7.loss_cls_ce: 2.1352 decode.d7.loss_mask_ce: 1.0422 decode.d7.loss_mask_dice: 2.0749 2023/09/07 11:18:55 - mmengine - INFO - Iter(train) [ 5050/60000] base_lr: 9.1585e-05 lr: 9.1585e-05 eta: 15:00:54 time: 0.9831 data_time: 0.0224 memory: 29137 grad_norm: 31.5508 loss: 8.6570 decode.loss_cls_ce: 1.8724 decode.loss_mask_ce: 0.8573 decode.loss_mask_dice: 1.5935 decode.d7.loss_cls_ce: 1.8914 decode.d7.loss_mask_ce: 0.8578 decode.d7.loss_mask_dice: 1.5847 2023/09/07 11:19:44 - mmengine - INFO - Iter(train) [ 5100/60000] base_lr: 9.1502e-05 lr: 9.1502e-05 eta: 15:00:05 time: 0.9837 data_time: 0.0227 memory: 29156 grad_norm: 25.5161 loss: 10.6830 decode.loss_cls_ce: 2.2144 decode.loss_mask_ce: 1.0271 decode.loss_mask_dice: 2.1006 decode.d7.loss_cls_ce: 2.2284 decode.d7.loss_mask_ce: 1.0292 decode.d7.loss_mask_dice: 2.0834 2023/09/07 11:20:33 - mmengine - INFO - Iter(train) [ 5150/60000] base_lr: 9.1418e-05 lr: 9.1418e-05 eta: 14:59:15 time: 0.9819 data_time: 0.0217 memory: 29192 grad_norm: 27.5486 loss: 10.1775 decode.loss_cls_ce: 2.2705 decode.loss_mask_ce: 0.9844 decode.loss_mask_dice: 1.8076 decode.d7.loss_cls_ce: 2.3194 decode.d7.loss_mask_ce: 0.9866 decode.d7.loss_mask_dice: 1.8090 2023/09/07 11:21:22 - mmengine - INFO - Iter(train) [ 5200/60000] base_lr: 9.1335e-05 lr: 9.1335e-05 eta: 14:58:26 time: 0.9853 data_time: 0.0223 memory: 29169 grad_norm: 28.7843 loss: 9.6638 decode.loss_cls_ce: 2.0054 decode.loss_mask_ce: 0.9215 decode.loss_mask_dice: 1.8981 decode.d7.loss_cls_ce: 2.0435 decode.d7.loss_mask_ce: 0.9018 decode.d7.loss_mask_dice: 1.8935 2023/09/07 11:22:11 - mmengine - INFO - Iter(train) [ 5250/60000] base_lr: 9.1252e-05 lr: 9.1252e-05 eta: 14:57:36 time: 0.9829 data_time: 0.0219 memory: 29317 grad_norm: 28.1354 loss: 10.1017 decode.loss_cls_ce: 2.1417 decode.loss_mask_ce: 0.8948 decode.loss_mask_dice: 2.0140 decode.d7.loss_cls_ce: 2.1239 decode.d7.loss_mask_ce: 0.9062 decode.d7.loss_mask_dice: 2.0210 2023/09/07 11:23:01 - mmengine - INFO - Iter(train) [ 5300/60000] base_lr: 9.1168e-05 lr: 9.1168e-05 eta: 14:56:47 time: 0.9839 data_time: 0.0217 memory: 29150 grad_norm: 26.3849 loss: 10.3586 decode.loss_cls_ce: 2.2095 decode.loss_mask_ce: 1.0067 decode.loss_mask_dice: 1.9562 decode.d7.loss_cls_ce: 2.1983 decode.d7.loss_mask_ce: 0.9966 decode.d7.loss_mask_dice: 1.9912 2023/09/07 11:23:50 - mmengine - INFO - Iter(train) [ 5350/60000] base_lr: 9.1085e-05 lr: 9.1085e-05 eta: 14:55:57 time: 0.9812 data_time: 0.0218 memory: 29239 grad_norm: 24.3713 loss: 10.7933 decode.loss_cls_ce: 2.3610 decode.loss_mask_ce: 0.9547 decode.loss_mask_dice: 2.1158 decode.d7.loss_cls_ce: 2.3033 decode.d7.loss_mask_ce: 0.9491 decode.d7.loss_mask_dice: 2.1094 2023/09/07 11:24:39 - mmengine - INFO - Iter(train) [ 5400/60000] base_lr: 9.1002e-05 lr: 9.1002e-05 eta: 14:55:07 time: 0.9819 data_time: 0.0224 memory: 29191 grad_norm: 28.2930 loss: 9.1498 decode.loss_cls_ce: 1.8865 decode.loss_mask_ce: 0.9890 decode.loss_mask_dice: 1.6994 decode.d7.loss_cls_ce: 1.9121 decode.d7.loss_mask_ce: 0.9818 decode.d7.loss_mask_dice: 1.6811 2023/09/07 11:25:28 - mmengine - INFO - Iter(train) [ 5450/60000] base_lr: 9.0918e-05 lr: 9.0918e-05 eta: 14:54:18 time: 0.9836 data_time: 0.0218 memory: 29153 grad_norm: 29.5700 loss: 10.2972 decode.loss_cls_ce: 2.2972 decode.loss_mask_ce: 0.9861 decode.loss_mask_dice: 1.8741 decode.d7.loss_cls_ce: 2.2830 decode.d7.loss_mask_ce: 0.9866 decode.d7.loss_mask_dice: 1.8702 2023/09/07 11:26:17 - mmengine - INFO - Iter(train) [ 5500/60000] base_lr: 9.0835e-05 lr: 9.0835e-05 eta: 14:53:28 time: 0.9835 data_time: 0.0216 memory: 29199 grad_norm: 27.7121 loss: 10.2968 decode.loss_cls_ce: 2.2339 decode.loss_mask_ce: 0.9586 decode.loss_mask_dice: 1.9570 decode.d7.loss_cls_ce: 2.2546 decode.d7.loss_mask_ce: 0.9392 decode.d7.loss_mask_dice: 1.9535 2023/09/07 11:27:06 - mmengine - INFO - Iter(train) [ 5550/60000] base_lr: 9.0752e-05 lr: 9.0752e-05 eta: 14:52:39 time: 0.9838 data_time: 0.0221 memory: 29209 grad_norm: 25.8905 loss: 9.6726 decode.loss_cls_ce: 2.1985 decode.loss_mask_ce: 0.9016 decode.loss_mask_dice: 1.7407 decode.d7.loss_cls_ce: 2.1482 decode.d7.loss_mask_ce: 0.9245 decode.d7.loss_mask_dice: 1.7590 2023/09/07 11:27:56 - mmengine - INFO - Iter(train) [ 5600/60000] base_lr: 9.0668e-05 lr: 9.0668e-05 eta: 14:51:50 time: 0.9834 data_time: 0.0220 memory: 29130 grad_norm: 40.7240 loss: 9.5834 decode.loss_cls_ce: 1.8802 decode.loss_mask_ce: 1.0310 decode.loss_mask_dice: 1.8818 decode.d7.loss_cls_ce: 1.9224 decode.d7.loss_mask_ce: 1.0125 decode.d7.loss_mask_dice: 1.8556 2023/09/07 11:28:45 - mmengine - INFO - Iter(train) [ 5650/60000] base_lr: 9.0585e-05 lr: 9.0585e-05 eta: 14:51:01 time: 0.9825 data_time: 0.0223 memory: 29190 grad_norm: 25.8300 loss: 10.8687 decode.loss_cls_ce: 2.3501 decode.loss_mask_ce: 0.9611 decode.loss_mask_dice: 2.1206 decode.d7.loss_cls_ce: 2.3417 decode.d7.loss_mask_ce: 0.9624 decode.d7.loss_mask_dice: 2.1328 2023/09/07 11:29:34 - mmengine - INFO - Iter(train) [ 5700/60000] base_lr: 9.0502e-05 lr: 9.0502e-05 eta: 14:50:12 time: 0.9842 data_time: 0.0222 memory: 29290 grad_norm: 26.1695 loss: 9.0493 decode.loss_cls_ce: 2.0749 decode.loss_mask_ce: 0.7836 decode.loss_mask_dice: 1.6488 decode.d7.loss_cls_ce: 2.1091 decode.d7.loss_mask_ce: 0.7868 decode.d7.loss_mask_dice: 1.6461 2023/09/07 11:30:23 - mmengine - INFO - Iter(train) [ 5750/60000] base_lr: 9.0418e-05 lr: 9.0418e-05 eta: 14:49:22 time: 0.9847 data_time: 0.0223 memory: 29178 grad_norm: 27.2927 loss: 10.2443 decode.loss_cls_ce: 2.2848 decode.loss_mask_ce: 0.9600 decode.loss_mask_dice: 1.8767 decode.d7.loss_cls_ce: 2.2813 decode.d7.loss_mask_ce: 0.9653 decode.d7.loss_mask_dice: 1.8761 2023/09/07 11:31:12 - mmengine - INFO - Iter(train) [ 5800/60000] base_lr: 9.0335e-05 lr: 9.0335e-05 eta: 14:48:33 time: 0.9817 data_time: 0.0217 memory: 29153 grad_norm: 23.9958 loss: 9.5308 decode.loss_cls_ce: 2.1375 decode.loss_mask_ce: 0.8501 decode.loss_mask_dice: 1.7853 decode.d7.loss_cls_ce: 2.1311 decode.d7.loss_mask_ce: 0.8452 decode.d7.loss_mask_dice: 1.7817 2023/09/07 11:32:01 - mmengine - INFO - Iter(train) [ 5850/60000] base_lr: 9.0252e-05 lr: 9.0252e-05 eta: 14:47:44 time: 0.9832 data_time: 0.0220 memory: 29253 grad_norm: 41.5256 loss: 11.0146 decode.loss_cls_ce: 2.4907 decode.loss_mask_ce: 1.0583 decode.loss_mask_dice: 1.9702 decode.d7.loss_cls_ce: 2.4830 decode.d7.loss_mask_ce: 1.0481 decode.d7.loss_mask_dice: 1.9642 2023/09/07 11:32:51 - mmengine - INFO - Iter(train) [ 5900/60000] base_lr: 9.0168e-05 lr: 9.0168e-05 eta: 14:46:55 time: 0.9847 data_time: 0.0220 memory: 29215 grad_norm: 26.1952 loss: 9.4723 decode.loss_cls_ce: 2.2116 decode.loss_mask_ce: 0.8262 decode.loss_mask_dice: 1.6969 decode.d7.loss_cls_ce: 2.2198 decode.d7.loss_mask_ce: 0.8156 decode.d7.loss_mask_dice: 1.7022 2023/09/07 11:33:40 - mmengine - INFO - Iter(train) [ 5950/60000] base_lr: 9.0085e-05 lr: 9.0085e-05 eta: 14:46:06 time: 0.9854 data_time: 0.0211 memory: 29142 grad_norm: 26.7705 loss: 9.6511 decode.loss_cls_ce: 2.0966 decode.loss_mask_ce: 0.8832 decode.loss_mask_dice: 1.8442 decode.d7.loss_cls_ce: 2.0833 decode.d7.loss_mask_ce: 0.8884 decode.d7.loss_mask_dice: 1.8555 2023/09/07 11:34:29 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 11:34:29 - mmengine - INFO - Iter(train) [ 6000/60000] base_lr: 9.0002e-05 lr: 9.0002e-05 eta: 14:45:17 time: 0.9830 data_time: 0.0206 memory: 29177 grad_norm: 25.4104 loss: 9.2137 decode.loss_cls_ce: 1.8400 decode.loss_mask_ce: 0.9366 decode.loss_mask_dice: 1.8076 decode.d7.loss_cls_ce: 1.8895 decode.d7.loss_mask_ce: 0.9262 decode.d7.loss_mask_dice: 1.8139 2023/09/07 11:35:18 - mmengine - INFO - Iter(train) [ 6050/60000] base_lr: 8.9918e-05 lr: 8.9918e-05 eta: 14:44:28 time: 0.9863 data_time: 0.0221 memory: 29132 grad_norm: 24.4631 loss: 9.4162 decode.loss_cls_ce: 2.0256 decode.loss_mask_ce: 0.8920 decode.loss_mask_dice: 1.7933 decode.d7.loss_cls_ce: 2.0175 decode.d7.loss_mask_ce: 0.8871 decode.d7.loss_mask_dice: 1.8007 2023/09/07 11:36:08 - mmengine - INFO - Iter(train) [ 6100/60000] base_lr: 8.9835e-05 lr: 8.9835e-05 eta: 14:43:39 time: 0.9845 data_time: 0.0217 memory: 29204 grad_norm: 24.1895 loss: 9.6860 decode.loss_cls_ce: 2.2054 decode.loss_mask_ce: 0.9718 decode.loss_mask_dice: 1.6832 decode.d7.loss_cls_ce: 2.1962 decode.d7.loss_mask_ce: 0.9654 decode.d7.loss_mask_dice: 1.6638 2023/09/07 11:36:57 - mmengine - INFO - Iter(train) [ 6150/60000] base_lr: 8.9751e-05 lr: 8.9751e-05 eta: 14:42:50 time: 0.9827 data_time: 0.0217 memory: 29347 grad_norm: 24.4408 loss: 8.4687 decode.loss_cls_ce: 1.8003 decode.loss_mask_ce: 0.8303 decode.loss_mask_dice: 1.5839 decode.d7.loss_cls_ce: 1.8333 decode.d7.loss_mask_ce: 0.8319 decode.d7.loss_mask_dice: 1.5890 2023/09/07 11:37:46 - mmengine - INFO - Iter(train) [ 6200/60000] base_lr: 8.9668e-05 lr: 8.9668e-05 eta: 14:42:00 time: 0.9828 data_time: 0.0223 memory: 29244 grad_norm: 26.9868 loss: 9.5170 decode.loss_cls_ce: 2.0967 decode.loss_mask_ce: 0.8838 decode.loss_mask_dice: 1.7595 decode.d7.loss_cls_ce: 2.1277 decode.d7.loss_mask_ce: 0.8804 decode.d7.loss_mask_dice: 1.7688 2023/09/07 11:38:35 - mmengine - INFO - Iter(train) [ 6250/60000] base_lr: 8.9585e-05 lr: 8.9585e-05 eta: 14:41:11 time: 0.9823 data_time: 0.0225 memory: 29183 grad_norm: 28.9523 loss: 9.2525 decode.loss_cls_ce: 1.9942 decode.loss_mask_ce: 0.9586 decode.loss_mask_dice: 1.6661 decode.d7.loss_cls_ce: 2.0196 decode.d7.loss_mask_ce: 0.9557 decode.d7.loss_mask_dice: 1.6584 2023/09/07 11:39:24 - mmengine - INFO - Iter(train) [ 6300/60000] base_lr: 8.9501e-05 lr: 8.9501e-05 eta: 14:40:22 time: 0.9842 data_time: 0.0226 memory: 29204 grad_norm: 24.3869 loss: 8.9403 decode.loss_cls_ce: 2.0186 decode.loss_mask_ce: 0.8390 decode.loss_mask_dice: 1.5988 decode.d7.loss_cls_ce: 2.0283 decode.d7.loss_mask_ce: 0.8477 decode.d7.loss_mask_dice: 1.6078 2023/09/07 11:40:13 - mmengine - INFO - Iter(train) [ 6350/60000] base_lr: 8.9418e-05 lr: 8.9418e-05 eta: 14:39:33 time: 0.9830 data_time: 0.0221 memory: 29111 grad_norm: 26.8318 loss: 8.7333 decode.loss_cls_ce: 2.0479 decode.loss_mask_ce: 0.7801 decode.loss_mask_dice: 1.5591 decode.d7.loss_cls_ce: 2.0206 decode.d7.loss_mask_ce: 0.7794 decode.d7.loss_mask_dice: 1.5462 2023/09/07 11:41:03 - mmengine - INFO - Iter(train) [ 6400/60000] base_lr: 8.9335e-05 lr: 8.9335e-05 eta: 14:38:44 time: 0.9864 data_time: 0.0214 memory: 29191 grad_norm: 26.2728 loss: 9.4931 decode.loss_cls_ce: 2.0471 decode.loss_mask_ce: 0.8712 decode.loss_mask_dice: 1.8169 decode.d7.loss_cls_ce: 2.0558 decode.d7.loss_mask_ce: 0.8723 decode.d7.loss_mask_dice: 1.8298 2023/09/07 11:41:52 - mmengine - INFO - Iter(train) [ 6450/60000] base_lr: 8.9251e-05 lr: 8.9251e-05 eta: 14:37:56 time: 0.9856 data_time: 0.0205 memory: 29156 grad_norm: 29.5463 loss: 10.2983 decode.loss_cls_ce: 2.1136 decode.loss_mask_ce: 1.0146 decode.loss_mask_dice: 2.0221 decode.d7.loss_cls_ce: 2.1093 decode.d7.loss_mask_ce: 0.9958 decode.d7.loss_mask_dice: 2.0429 2023/09/07 11:42:41 - mmengine - INFO - Iter(train) [ 6500/60000] base_lr: 8.9168e-05 lr: 8.9168e-05 eta: 14:37:07 time: 0.9868 data_time: 0.0209 memory: 29265 grad_norm: 26.1834 loss: 10.2425 decode.loss_cls_ce: 2.1747 decode.loss_mask_ce: 0.9449 decode.loss_mask_dice: 2.0106 decode.d7.loss_cls_ce: 2.1588 decode.d7.loss_mask_ce: 0.9276 decode.d7.loss_mask_dice: 2.0260 2023/09/07 11:43:30 - mmengine - INFO - Iter(train) [ 6550/60000] base_lr: 8.9085e-05 lr: 8.9085e-05 eta: 14:36:19 time: 0.9834 data_time: 0.0220 memory: 29157 grad_norm: 32.6307 loss: 10.4982 decode.loss_cls_ce: 2.3030 decode.loss_mask_ce: 0.9689 decode.loss_mask_dice: 1.9528 decode.d7.loss_cls_ce: 2.3304 decode.d7.loss_mask_ce: 0.9752 decode.d7.loss_mask_dice: 1.9680 2023/09/07 11:44:20 - mmengine - INFO - Iter(train) [ 6600/60000] base_lr: 8.9001e-05 lr: 8.9001e-05 eta: 14:35:30 time: 0.9821 data_time: 0.0222 memory: 29169 grad_norm: 27.7060 loss: 9.0390 decode.loss_cls_ce: 2.0737 decode.loss_mask_ce: 0.8877 decode.loss_mask_dice: 1.5750 decode.d7.loss_cls_ce: 2.0485 decode.d7.loss_mask_ce: 0.8882 decode.d7.loss_mask_dice: 1.5659 2023/09/07 11:45:09 - mmengine - INFO - Iter(train) [ 6650/60000] base_lr: 8.8918e-05 lr: 8.8918e-05 eta: 14:34:40 time: 0.9824 data_time: 0.0224 memory: 29253 grad_norm: 27.3298 loss: 9.0296 decode.loss_cls_ce: 2.0090 decode.loss_mask_ce: 0.9931 decode.loss_mask_dice: 1.5242 decode.d7.loss_cls_ce: 1.9769 decode.d7.loss_mask_ce: 0.9830 decode.d7.loss_mask_dice: 1.5434 2023/09/07 11:45:58 - mmengine - INFO - Iter(train) [ 6700/60000] base_lr: 8.8835e-05 lr: 8.8835e-05 eta: 14:33:52 time: 0.9872 data_time: 0.0217 memory: 29112 grad_norm: 23.5924 loss: 9.4461 decode.loss_cls_ce: 1.9888 decode.loss_mask_ce: 0.9525 decode.loss_mask_dice: 1.7902 decode.d7.loss_cls_ce: 1.9489 decode.d7.loss_mask_ce: 0.9593 decode.d7.loss_mask_dice: 1.8065 2023/09/07 11:46:47 - mmengine - INFO - Iter(train) [ 6750/60000] base_lr: 8.8751e-05 lr: 8.8751e-05 eta: 14:33:02 time: 0.9854 data_time: 0.0224 memory: 29203 grad_norm: 25.7228 loss: 9.4171 decode.loss_cls_ce: 1.9029 decode.loss_mask_ce: 1.0484 decode.loss_mask_dice: 1.7428 decode.d7.loss_cls_ce: 1.9507 decode.d7.loss_mask_ce: 1.0527 decode.d7.loss_mask_dice: 1.7195 2023/09/07 11:47:36 - mmengine - INFO - Iter(train) [ 6800/60000] base_lr: 8.8668e-05 lr: 8.8668e-05 eta: 14:32:13 time: 0.9815 data_time: 0.0216 memory: 29215 grad_norm: 24.6000 loss: 9.7845 decode.loss_cls_ce: 2.0229 decode.loss_mask_ce: 0.9937 decode.loss_mask_dice: 1.8685 decode.d7.loss_cls_ce: 2.0199 decode.d7.loss_mask_ce: 0.9918 decode.d7.loss_mask_dice: 1.8878 2023/09/07 11:48:26 - mmengine - INFO - Iter(train) [ 6850/60000] base_lr: 8.8585e-05 lr: 8.8585e-05 eta: 14:31:24 time: 0.9850 data_time: 0.0219 memory: 29242 grad_norm: 26.2782 loss: 11.3704 decode.loss_cls_ce: 2.3125 decode.loss_mask_ce: 1.0475 decode.loss_mask_dice: 2.3160 decode.d7.loss_cls_ce: 2.3500 decode.d7.loss_mask_ce: 1.0439 decode.d7.loss_mask_dice: 2.3006 2023/09/07 11:49:15 - mmengine - INFO - Iter(train) [ 6900/60000] base_lr: 8.8501e-05 lr: 8.8501e-05 eta: 14:30:34 time: 0.9824 data_time: 0.0222 memory: 29205 grad_norm: 22.4154 loss: 11.3942 decode.loss_cls_ce: 2.3491 decode.loss_mask_ce: 1.1006 decode.loss_mask_dice: 2.2448 decode.d7.loss_cls_ce: 2.3471 decode.d7.loss_mask_ce: 1.0982 decode.d7.loss_mask_dice: 2.2544 2023/09/07 11:50:04 - mmengine - INFO - Iter(train) [ 6950/60000] base_lr: 8.8418e-05 lr: 8.8418e-05 eta: 14:29:45 time: 0.9863 data_time: 0.0222 memory: 29202 grad_norm: 27.7998 loss: 10.7758 decode.loss_cls_ce: 2.2136 decode.loss_mask_ce: 1.0362 decode.loss_mask_dice: 2.1308 decode.d7.loss_cls_ce: 2.2253 decode.d7.loss_mask_ce: 1.0321 decode.d7.loss_mask_dice: 2.1377 2023/09/07 11:50:53 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 11:50:53 - mmengine - INFO - Iter(train) [ 7000/60000] base_lr: 8.8335e-05 lr: 8.8335e-05 eta: 14:28:56 time: 0.9821 data_time: 0.0220 memory: 29242 grad_norm: 25.7765 loss: 9.3639 decode.loss_cls_ce: 2.0496 decode.loss_mask_ce: 0.9814 decode.loss_mask_dice: 1.6415 decode.d7.loss_cls_ce: 2.0714 decode.d7.loss_mask_ce: 0.9798 decode.d7.loss_mask_dice: 1.6401 2023/09/07 11:51:42 - mmengine - INFO - Iter(train) [ 7050/60000] base_lr: 8.8251e-05 lr: 8.8251e-05 eta: 14:28:07 time: 0.9872 data_time: 0.0227 memory: 29117 grad_norm: 23.1379 loss: 9.7518 decode.loss_cls_ce: 2.1325 decode.loss_mask_ce: 0.8616 decode.loss_mask_dice: 1.8533 decode.d7.loss_cls_ce: 2.1677 decode.d7.loss_mask_ce: 0.8625 decode.d7.loss_mask_dice: 1.8743 2023/09/07 11:52:32 - mmengine - INFO - Iter(train) [ 7100/60000] base_lr: 8.8168e-05 lr: 8.8168e-05 eta: 14:27:17 time: 0.9813 data_time: 0.0221 memory: 29240 grad_norm: 24.8812 loss: 10.2451 decode.loss_cls_ce: 2.1015 decode.loss_mask_ce: 0.9634 decode.loss_mask_dice: 2.0719 decode.d7.loss_cls_ce: 2.0758 decode.d7.loss_mask_ce: 0.9639 decode.d7.loss_mask_dice: 2.0685 2023/09/07 11:53:21 - mmengine - INFO - Iter(train) [ 7150/60000] base_lr: 8.8085e-05 lr: 8.8085e-05 eta: 14:26:28 time: 0.9833 data_time: 0.0226 memory: 29132 grad_norm: 26.3078 loss: 9.6013 decode.loss_cls_ce: 2.1453 decode.loss_mask_ce: 0.9374 decode.loss_mask_dice: 1.7072 decode.d7.loss_cls_ce: 2.1730 decode.d7.loss_mask_ce: 0.9311 decode.d7.loss_mask_dice: 1.7073 2023/09/07 11:54:10 - mmengine - INFO - Iter(train) [ 7200/60000] base_lr: 8.8001e-05 lr: 8.8001e-05 eta: 14:25:39 time: 0.9832 data_time: 0.0217 memory: 29217 grad_norm: 25.0140 loss: 10.0514 decode.loss_cls_ce: 2.2284 decode.loss_mask_ce: 0.8478 decode.loss_mask_dice: 1.9570 decode.d7.loss_cls_ce: 2.1977 decode.d7.loss_mask_ce: 0.8524 decode.d7.loss_mask_dice: 1.9680 2023/09/07 11:54:59 - mmengine - INFO - Iter(train) [ 7250/60000] base_lr: 8.7918e-05 lr: 8.7918e-05 eta: 14:24:50 time: 0.9827 data_time: 0.0222 memory: 29252 grad_norm: 28.4789 loss: 9.6629 decode.loss_cls_ce: 2.2178 decode.loss_mask_ce: 0.8681 decode.loss_mask_dice: 1.7397 decode.d7.loss_cls_ce: 2.2064 decode.d7.loss_mask_ce: 0.8888 decode.d7.loss_mask_dice: 1.7420 2023/09/07 11:55:48 - mmengine - INFO - Iter(train) [ 7300/60000] base_lr: 8.7835e-05 lr: 8.7835e-05 eta: 14:24:01 time: 0.9824 data_time: 0.0219 memory: 29253 grad_norm: 28.1515 loss: 8.9824 decode.loss_cls_ce: 1.9440 decode.loss_mask_ce: 0.8346 decode.loss_mask_dice: 1.7286 decode.d7.loss_cls_ce: 1.9005 decode.d7.loss_mask_ce: 0.8424 decode.d7.loss_mask_dice: 1.7323 2023/09/07 11:56:37 - mmengine - INFO - Iter(train) [ 7350/60000] base_lr: 8.7751e-05 lr: 8.7751e-05 eta: 14:23:12 time: 0.9860 data_time: 0.0219 memory: 29130 grad_norm: 31.8576 loss: 9.4016 decode.loss_cls_ce: 2.0684 decode.loss_mask_ce: 0.9025 decode.loss_mask_dice: 1.7295 decode.d7.loss_cls_ce: 2.0597 decode.d7.loss_mask_ce: 0.9000 decode.d7.loss_mask_dice: 1.7414 2023/09/07 11:57:27 - mmengine - INFO - Iter(train) [ 7400/60000] base_lr: 8.7668e-05 lr: 8.7668e-05 eta: 14:22:23 time: 0.9830 data_time: 0.0223 memory: 29110 grad_norm: 32.5299 loss: 8.0126 decode.loss_cls_ce: 1.7732 decode.loss_mask_ce: 0.7593 decode.loss_mask_dice: 1.4639 decode.d7.loss_cls_ce: 1.7590 decode.d7.loss_mask_ce: 0.7697 decode.d7.loss_mask_dice: 1.4876 2023/09/07 11:58:16 - mmengine - INFO - Iter(train) [ 7450/60000] base_lr: 8.7585e-05 lr: 8.7585e-05 eta: 14:21:33 time: 0.9851 data_time: 0.0220 memory: 29226 grad_norm: 22.4133 loss: 8.6938 decode.loss_cls_ce: 1.8619 decode.loss_mask_ce: 0.8769 decode.loss_mask_dice: 1.6032 decode.d7.loss_cls_ce: 1.8898 decode.d7.loss_mask_ce: 0.8704 decode.d7.loss_mask_dice: 1.5914 2023/09/07 11:59:05 - mmengine - INFO - Iter(train) [ 7500/60000] base_lr: 8.7501e-05 lr: 8.7501e-05 eta: 14:20:45 time: 0.9841 data_time: 0.0221 memory: 29164 grad_norm: 25.3563 loss: 10.4763 decode.loss_cls_ce: 2.3209 decode.loss_mask_ce: 0.9466 decode.loss_mask_dice: 1.9236 decode.d7.loss_cls_ce: 2.4246 decode.d7.loss_mask_ce: 0.9328 decode.d7.loss_mask_dice: 1.9279 2023/09/07 11:59:54 - mmengine - INFO - Iter(train) [ 7550/60000] base_lr: 8.7418e-05 lr: 8.7418e-05 eta: 14:19:56 time: 0.9840 data_time: 0.0224 memory: 29179 grad_norm: 25.9138 loss: 11.2186 decode.loss_cls_ce: 2.4537 decode.loss_mask_ce: 1.1128 decode.loss_mask_dice: 2.0515 decode.d7.loss_cls_ce: 2.4404 decode.d7.loss_mask_ce: 1.1129 decode.d7.loss_mask_dice: 2.0473 2023/09/07 12:00:44 - mmengine - INFO - Iter(train) [ 7600/60000] base_lr: 8.7335e-05 lr: 8.7335e-05 eta: 14:19:06 time: 0.9847 data_time: 0.0223 memory: 29191 grad_norm: 25.0260 loss: 7.5376 decode.loss_cls_ce: 1.7136 decode.loss_mask_ce: 0.7864 decode.loss_mask_dice: 1.2476 decode.d7.loss_cls_ce: 1.7542 decode.d7.loss_mask_ce: 0.7838 decode.d7.loss_mask_dice: 1.2520 2023/09/07 12:01:33 - mmengine - INFO - Iter(train) [ 7650/60000] base_lr: 8.7251e-05 lr: 8.7251e-05 eta: 14:18:17 time: 0.9839 data_time: 0.0224 memory: 29224 grad_norm: 26.5783 loss: 9.3140 decode.loss_cls_ce: 2.0108 decode.loss_mask_ce: 0.8793 decode.loss_mask_dice: 1.7709 decode.d7.loss_cls_ce: 2.0184 decode.d7.loss_mask_ce: 0.8798 decode.d7.loss_mask_dice: 1.7548 2023/09/07 12:02:22 - mmengine - INFO - Iter(train) [ 7700/60000] base_lr: 8.7168e-05 lr: 8.7168e-05 eta: 14:17:28 time: 0.9838 data_time: 0.0218 memory: 29265 grad_norm: 23.9826 loss: 8.8499 decode.loss_cls_ce: 2.0210 decode.loss_mask_ce: 0.8563 decode.loss_mask_dice: 1.5631 decode.d7.loss_cls_ce: 1.9752 decode.d7.loss_mask_ce: 0.8674 decode.d7.loss_mask_dice: 1.5668 2023/09/07 12:03:11 - mmengine - INFO - Iter(train) [ 7750/60000] base_lr: 8.7085e-05 lr: 8.7085e-05 eta: 14:16:39 time: 0.9851 data_time: 0.0204 memory: 29251 grad_norm: 24.9191 loss: 9.1056 decode.loss_cls_ce: 1.8034 decode.loss_mask_ce: 0.9614 decode.loss_mask_dice: 1.7687 decode.d7.loss_cls_ce: 1.8327 decode.d7.loss_mask_ce: 0.9661 decode.d7.loss_mask_dice: 1.7733 2023/09/07 12:04:00 - mmengine - INFO - Iter(train) [ 7800/60000] base_lr: 8.7001e-05 lr: 8.7001e-05 eta: 14:15:50 time: 0.9846 data_time: 0.0214 memory: 29157 grad_norm: 24.8587 loss: 11.0146 decode.loss_cls_ce: 2.3407 decode.loss_mask_ce: 1.0419 decode.loss_mask_dice: 2.1383 decode.d7.loss_cls_ce: 2.2911 decode.d7.loss_mask_ce: 1.0443 decode.d7.loss_mask_dice: 2.1582 2023/09/07 12:04:49 - mmengine - INFO - Iter(train) [ 7850/60000] base_lr: 8.6918e-05 lr: 8.6918e-05 eta: 14:15:01 time: 0.9816 data_time: 0.0230 memory: 29216 grad_norm: 24.1934 loss: 9.6317 decode.loss_cls_ce: 2.1169 decode.loss_mask_ce: 0.8634 decode.loss_mask_dice: 1.8507 decode.d7.loss_cls_ce: 2.1024 decode.d7.loss_mask_ce: 0.8659 decode.d7.loss_mask_dice: 1.8325 2023/09/07 12:05:39 - mmengine - INFO - Iter(train) [ 7900/60000] base_lr: 8.6835e-05 lr: 8.6835e-05 eta: 14:14:12 time: 0.9849 data_time: 0.0217 memory: 29153 grad_norm: 33.4369 loss: 9.7880 decode.loss_cls_ce: 2.0219 decode.loss_mask_ce: 1.0083 decode.loss_mask_dice: 1.8608 decode.d7.loss_cls_ce: 2.0115 decode.d7.loss_mask_ce: 1.0236 decode.d7.loss_mask_dice: 1.8619 2023/09/07 12:06:28 - mmengine - INFO - Iter(train) [ 7950/60000] base_lr: 8.6751e-05 lr: 8.6751e-05 eta: 14:13:23 time: 0.9821 data_time: 0.0219 memory: 29266 grad_norm: 27.1130 loss: 8.9097 decode.loss_cls_ce: 1.9093 decode.loss_mask_ce: 0.9438 decode.loss_mask_dice: 1.5881 decode.d7.loss_cls_ce: 1.9278 decode.d7.loss_mask_ce: 0.9453 decode.d7.loss_mask_dice: 1.5954 2023/09/07 12:07:17 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 12:07:17 - mmengine - INFO - Iter(train) [ 8000/60000] base_lr: 8.6668e-05 lr: 8.6668e-05 eta: 14:12:33 time: 0.9837 data_time: 0.0223 memory: 29166 grad_norm: 24.5340 loss: 8.5523 decode.loss_cls_ce: 1.7269 decode.loss_mask_ce: 0.9402 decode.loss_mask_dice: 1.5966 decode.d7.loss_cls_ce: 1.7266 decode.d7.loss_mask_ce: 0.9425 decode.d7.loss_mask_dice: 1.6195 2023/09/07 12:08:06 - mmengine - INFO - Iter(train) [ 8050/60000] base_lr: 8.6585e-05 lr: 8.6585e-05 eta: 14:11:44 time: 0.9850 data_time: 0.0215 memory: 29176 grad_norm: 27.7905 loss: 9.4466 decode.loss_cls_ce: 1.9111 decode.loss_mask_ce: 0.8329 decode.loss_mask_dice: 1.9825 decode.d7.loss_cls_ce: 1.9130 decode.d7.loss_mask_ce: 0.8282 decode.d7.loss_mask_dice: 1.9789 2023/09/07 12:08:55 - mmengine - INFO - Iter(train) [ 8100/60000] base_lr: 8.6501e-05 lr: 8.6501e-05 eta: 14:10:55 time: 0.9847 data_time: 0.0218 memory: 29166 grad_norm: 23.9596 loss: 8.9043 decode.loss_cls_ce: 1.8170 decode.loss_mask_ce: 0.9497 decode.loss_mask_dice: 1.6995 decode.d7.loss_cls_ce: 1.8065 decode.d7.loss_mask_ce: 0.9348 decode.d7.loss_mask_dice: 1.6968 2023/09/07 12:09:45 - mmengine - INFO - Iter(train) [ 8150/60000] base_lr: 8.6418e-05 lr: 8.6418e-05 eta: 14:10:06 time: 0.9853 data_time: 0.0226 memory: 29266 grad_norm: 25.4964 loss: 8.9859 decode.loss_cls_ce: 1.9091 decode.loss_mask_ce: 0.9055 decode.loss_mask_dice: 1.6763 decode.d7.loss_cls_ce: 1.9353 decode.d7.loss_mask_ce: 0.8928 decode.d7.loss_mask_dice: 1.6669 2023/09/07 12:10:34 - mmengine - INFO - Iter(train) [ 8200/60000] base_lr: 8.6335e-05 lr: 8.6335e-05 eta: 14:09:17 time: 0.9823 data_time: 0.0225 memory: 29291 grad_norm: 24.7410 loss: 9.6447 decode.loss_cls_ce: 2.0964 decode.loss_mask_ce: 0.8711 decode.loss_mask_dice: 1.8500 decode.d7.loss_cls_ce: 2.0982 decode.d7.loss_mask_ce: 0.8629 decode.d7.loss_mask_dice: 1.8660 2023/09/07 12:11:23 - mmengine - INFO - Iter(train) [ 8250/60000] base_lr: 8.6251e-05 lr: 8.6251e-05 eta: 14:08:28 time: 0.9815 data_time: 0.0221 memory: 29248 grad_norm: 25.1561 loss: 10.5102 decode.loss_cls_ce: 2.1678 decode.loss_mask_ce: 0.9650 decode.loss_mask_dice: 2.1165 decode.d7.loss_cls_ce: 2.1752 decode.d7.loss_mask_ce: 0.9584 decode.d7.loss_mask_dice: 2.1272 2023/09/07 12:12:12 - mmengine - INFO - Iter(train) [ 8300/60000] base_lr: 8.6168e-05 lr: 8.6168e-05 eta: 14:07:39 time: 0.9834 data_time: 0.0225 memory: 29191 grad_norm: 24.1802 loss: 9.8656 decode.loss_cls_ce: 2.1167 decode.loss_mask_ce: 0.8985 decode.loss_mask_dice: 1.9095 decode.d7.loss_cls_ce: 2.1275 decode.d7.loss_mask_ce: 0.9122 decode.d7.loss_mask_dice: 1.9012 2023/09/07 12:13:02 - mmengine - INFO - Iter(train) [ 8350/60000] base_lr: 8.6085e-05 lr: 8.6085e-05 eta: 14:06:50 time: 0.9834 data_time: 0.0217 memory: 29178 grad_norm: 23.8273 loss: 9.1967 decode.loss_cls_ce: 1.9561 decode.loss_mask_ce: 0.9209 decode.loss_mask_dice: 1.7216 decode.d7.loss_cls_ce: 1.9745 decode.d7.loss_mask_ce: 0.9165 decode.d7.loss_mask_dice: 1.7070 2023/09/07 12:13:51 - mmengine - INFO - Iter(train) [ 8400/60000] base_lr: 8.6001e-05 lr: 8.6001e-05 eta: 14:06:00 time: 0.9825 data_time: 0.0225 memory: 29218 grad_norm: 24.1118 loss: 9.5604 decode.loss_cls_ce: 1.9026 decode.loss_mask_ce: 1.0938 decode.loss_mask_dice: 1.7923 decode.d7.loss_cls_ce: 1.8911 decode.d7.loss_mask_ce: 1.0840 decode.d7.loss_mask_dice: 1.7966 2023/09/07 12:14:40 - mmengine - INFO - Iter(train) [ 8450/60000] base_lr: 8.5918e-05 lr: 8.5918e-05 eta: 14:05:11 time: 0.9836 data_time: 0.0226 memory: 29225 grad_norm: 25.6552 loss: 10.5442 decode.loss_cls_ce: 2.2915 decode.loss_mask_ce: 0.9399 decode.loss_mask_dice: 2.0574 decode.d7.loss_cls_ce: 2.2788 decode.d7.loss_mask_ce: 0.9315 decode.d7.loss_mask_dice: 2.0452 2023/09/07 12:15:29 - mmengine - INFO - Iter(train) [ 8500/60000] base_lr: 8.5835e-05 lr: 8.5835e-05 eta: 14:04:22 time: 0.9844 data_time: 0.0219 memory: 29209 grad_norm: 22.2489 loss: 10.4305 decode.loss_cls_ce: 2.1463 decode.loss_mask_ce: 1.0510 decode.loss_mask_dice: 1.9935 decode.d7.loss_cls_ce: 2.1434 decode.d7.loss_mask_ce: 1.0705 decode.d7.loss_mask_dice: 2.0258 2023/09/07 12:16:18 - mmengine - INFO - Iter(train) [ 8550/60000] base_lr: 8.5751e-05 lr: 8.5751e-05 eta: 14:03:33 time: 0.9882 data_time: 0.0224 memory: 29167 grad_norm: 22.9694 loss: 9.7503 decode.loss_cls_ce: 1.8701 decode.loss_mask_ce: 0.9925 decode.loss_mask_dice: 2.0073 decode.d7.loss_cls_ce: 1.8842 decode.d7.loss_mask_ce: 0.9928 decode.d7.loss_mask_dice: 2.0035 2023/09/07 12:17:07 - mmengine - INFO - Iter(train) [ 8600/60000] base_lr: 8.5668e-05 lr: 8.5668e-05 eta: 14:02:44 time: 0.9843 data_time: 0.0223 memory: 29216 grad_norm: 22.7160 loss: 9.5575 decode.loss_cls_ce: 2.0134 decode.loss_mask_ce: 0.8953 decode.loss_mask_dice: 1.8709 decode.d7.loss_cls_ce: 2.0075 decode.d7.loss_mask_ce: 0.8994 decode.d7.loss_mask_dice: 1.8709 2023/09/07 12:17:57 - mmengine - INFO - Iter(train) [ 8650/60000] base_lr: 8.5585e-05 lr: 8.5585e-05 eta: 14:01:55 time: 0.9883 data_time: 0.0220 memory: 29128 grad_norm: 25.1728 loss: 9.8995 decode.loss_cls_ce: 2.0496 decode.loss_mask_ce: 1.0194 decode.loss_mask_dice: 1.8780 decode.d7.loss_cls_ce: 2.0614 decode.d7.loss_mask_ce: 1.0192 decode.d7.loss_mask_dice: 1.8719 2023/09/07 12:18:46 - mmengine - INFO - Iter(train) [ 8700/60000] base_lr: 8.5501e-05 lr: 8.5501e-05 eta: 14:01:05 time: 0.9826 data_time: 0.0222 memory: 29142 grad_norm: 25.3813 loss: 9.1977 decode.loss_cls_ce: 1.9672 decode.loss_mask_ce: 0.9251 decode.loss_mask_dice: 1.6923 decode.d7.loss_cls_ce: 1.9607 decode.d7.loss_mask_ce: 0.9286 decode.d7.loss_mask_dice: 1.7237 2023/09/07 12:19:35 - mmengine - INFO - Iter(train) [ 8750/60000] base_lr: 8.5418e-05 lr: 8.5418e-05 eta: 14:00:16 time: 0.9833 data_time: 0.0224 memory: 29318 grad_norm: 27.0113 loss: 9.8785 decode.loss_cls_ce: 2.0967 decode.loss_mask_ce: 0.9362 decode.loss_mask_dice: 1.8942 decode.d7.loss_cls_ce: 2.1277 decode.d7.loss_mask_ce: 0.9322 decode.d7.loss_mask_dice: 1.8915 2023/09/07 12:20:24 - mmengine - INFO - Iter(train) [ 8800/60000] base_lr: 8.5335e-05 lr: 8.5335e-05 eta: 13:59:27 time: 0.9823 data_time: 0.0225 memory: 29241 grad_norm: nan loss: 10.0938 decode.loss_cls_ce: 2.0203 decode.loss_mask_ce: 0.9683 decode.loss_mask_dice: 2.0663 decode.d7.loss_cls_ce: 1.9884 decode.d7.loss_mask_ce: 0.9829 decode.d7.loss_mask_dice: 2.0676 2023/09/07 12:21:13 - mmengine - INFO - Iter(train) [ 8850/60000] base_lr: 8.5251e-05 lr: 8.5251e-05 eta: 13:58:38 time: 0.9851 data_time: 0.0219 memory: 29208 grad_norm: 24.3154 loss: 10.4006 decode.loss_cls_ce: 1.9886 decode.loss_mask_ce: 1.0487 decode.loss_mask_dice: 2.1511 decode.d7.loss_cls_ce: 2.0114 decode.d7.loss_mask_ce: 1.0482 decode.d7.loss_mask_dice: 2.1527 2023/09/07 12:22:03 - mmengine - INFO - Iter(train) [ 8900/60000] base_lr: 8.5168e-05 lr: 8.5168e-05 eta: 13:57:49 time: 0.9843 data_time: 0.0221 memory: 29238 grad_norm: 22.4728 loss: 8.5696 decode.loss_cls_ce: 1.8746 decode.loss_mask_ce: 0.7093 decode.loss_mask_dice: 1.6981 decode.d7.loss_cls_ce: 1.8865 decode.d7.loss_mask_ce: 0.7086 decode.d7.loss_mask_dice: 1.6925 2023/09/07 12:22:52 - mmengine - INFO - Iter(train) [ 8950/60000] base_lr: 8.5085e-05 lr: 8.5085e-05 eta: 13:57:00 time: 0.9857 data_time: 0.0216 memory: 29332 grad_norm: 24.7276 loss: 8.6588 decode.loss_cls_ce: 1.9986 decode.loss_mask_ce: 0.7915 decode.loss_mask_dice: 1.5439 decode.d7.loss_cls_ce: 1.9926 decode.d7.loss_mask_ce: 0.7979 decode.d7.loss_mask_dice: 1.5343 2023/09/07 12:23:41 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 12:23:41 - mmengine - INFO - Iter(train) [ 9000/60000] base_lr: 8.5001e-05 lr: 8.5001e-05 eta: 13:56:11 time: 0.9833 data_time: 0.0224 memory: 29251 grad_norm: 23.6856 loss: 9.1193 decode.loss_cls_ce: 1.9556 decode.loss_mask_ce: 0.8831 decode.loss_mask_dice: 1.7207 decode.d7.loss_cls_ce: 1.9735 decode.d7.loss_mask_ce: 0.8744 decode.d7.loss_mask_dice: 1.7121 2023/09/07 12:24:30 - mmengine - INFO - Iter(train) [ 9050/60000] base_lr: 8.4918e-05 lr: 8.4918e-05 eta: 13:55:22 time: 0.9849 data_time: 0.0216 memory: 29319 grad_norm: 27.0783 loss: 11.2644 decode.loss_cls_ce: 2.3680 decode.loss_mask_ce: 1.0361 decode.loss_mask_dice: 2.2388 decode.d7.loss_cls_ce: 2.3631 decode.d7.loss_mask_ce: 1.0227 decode.d7.loss_mask_dice: 2.2358 2023/09/07 12:25:20 - mmengine - INFO - Iter(train) [ 9100/60000] base_lr: 8.4835e-05 lr: 8.4835e-05 eta: 13:54:33 time: 0.9835 data_time: 0.0220 memory: 29158 grad_norm: 25.6768 loss: 8.4179 decode.loss_cls_ce: 1.5813 decode.loss_mask_ce: 0.9227 decode.loss_mask_dice: 1.6963 decode.d7.loss_cls_ce: 1.6014 decode.d7.loss_mask_ce: 0.9168 decode.d7.loss_mask_dice: 1.6994 2023/09/07 12:26:09 - mmengine - INFO - Iter(train) [ 9150/60000] base_lr: 8.4751e-05 lr: 8.4751e-05 eta: 13:53:44 time: 0.9853 data_time: 0.0219 memory: 29117 grad_norm: 24.3922 loss: 9.9103 decode.loss_cls_ce: 2.0990 decode.loss_mask_ce: 0.8854 decode.loss_mask_dice: 1.9306 decode.d7.loss_cls_ce: 2.1458 decode.d7.loss_mask_ce: 0.9021 decode.d7.loss_mask_dice: 1.9474 2023/09/07 12:26:58 - mmengine - INFO - Iter(train) [ 9200/60000] base_lr: 8.4668e-05 lr: 8.4668e-05 eta: 13:52:55 time: 0.9837 data_time: 0.0217 memory: 29252 grad_norm: 22.7688 loss: 8.8704 decode.loss_cls_ce: 1.8535 decode.loss_mask_ce: 0.8583 decode.loss_mask_dice: 1.7186 decode.d7.loss_cls_ce: 1.8650 decode.d7.loss_mask_ce: 0.8610 decode.d7.loss_mask_dice: 1.7141 2023/09/07 12:27:47 - mmengine - INFO - Iter(train) [ 9250/60000] base_lr: 8.4585e-05 lr: 8.4585e-05 eta: 13:52:05 time: 0.9863 data_time: 0.0227 memory: 29138 grad_norm: 24.6429 loss: 10.4132 decode.loss_cls_ce: 2.1010 decode.loss_mask_ce: 1.0110 decode.loss_mask_dice: 2.0896 decode.d7.loss_cls_ce: 2.0879 decode.d7.loss_mask_ce: 1.0270 decode.d7.loss_mask_dice: 2.0967 2023/09/07 12:28:36 - mmengine - INFO - Iter(train) [ 9300/60000] base_lr: 8.4501e-05 lr: 8.4501e-05 eta: 13:51:16 time: 0.9836 data_time: 0.0218 memory: 29348 grad_norm: 27.1176 loss: 8.9438 decode.loss_cls_ce: 2.0097 decode.loss_mask_ce: 0.8628 decode.loss_mask_dice: 1.6116 decode.d7.loss_cls_ce: 1.9790 decode.d7.loss_mask_ce: 0.8782 decode.d7.loss_mask_dice: 1.6026 2023/09/07 12:29:26 - mmengine - INFO - Iter(train) [ 9350/60000] base_lr: 8.4418e-05 lr: 8.4418e-05 eta: 13:50:27 time: 0.9827 data_time: 0.0228 memory: 29243 grad_norm: 25.1274 loss: 11.5557 decode.loss_cls_ce: 2.2862 decode.loss_mask_ce: 1.1032 decode.loss_mask_dice: 2.3427 decode.d7.loss_cls_ce: 2.3094 decode.d7.loss_mask_ce: 1.1100 decode.d7.loss_mask_dice: 2.4042 2023/09/07 12:30:15 - mmengine - INFO - Iter(train) [ 9400/60000] base_lr: 8.4335e-05 lr: 8.4335e-05 eta: 13:49:38 time: 0.9835 data_time: 0.0223 memory: 29189 grad_norm: 25.5338 loss: 9.8217 decode.loss_cls_ce: 1.9750 decode.loss_mask_ce: 0.8759 decode.loss_mask_dice: 2.0552 decode.d7.loss_cls_ce: 1.9646 decode.d7.loss_mask_ce: 0.8955 decode.d7.loss_mask_dice: 2.0555 2023/09/07 12:31:04 - mmengine - INFO - Iter(train) [ 9450/60000] base_lr: 8.4251e-05 lr: 8.4251e-05 eta: 13:48:49 time: 0.9849 data_time: 0.0223 memory: 29306 grad_norm: 30.3575 loss: 9.5884 decode.loss_cls_ce: 2.0428 decode.loss_mask_ce: 0.8599 decode.loss_mask_dice: 1.9029 decode.d7.loss_cls_ce: 2.0239 decode.d7.loss_mask_ce: 0.8447 decode.d7.loss_mask_dice: 1.9142 2023/09/07 12:31:53 - mmengine - INFO - Iter(train) [ 9500/60000] base_lr: 8.4168e-05 lr: 8.4168e-05 eta: 13:48:00 time: 0.9852 data_time: 0.0227 memory: 29236 grad_norm: 27.8551 loss: 7.9469 decode.loss_cls_ce: 1.8406 decode.loss_mask_ce: 0.7337 decode.loss_mask_dice: 1.3833 decode.d7.loss_cls_ce: 1.8766 decode.d7.loss_mask_ce: 0.7290 decode.d7.loss_mask_dice: 1.3837 2023/09/07 12:32:43 - mmengine - INFO - Iter(train) [ 9550/60000] base_lr: 8.4085e-05 lr: 8.4085e-05 eta: 13:47:11 time: 0.9846 data_time: 0.0222 memory: 29124 grad_norm: 27.3179 loss: 8.5633 decode.loss_cls_ce: 1.8300 decode.loss_mask_ce: 0.8440 decode.loss_mask_dice: 1.6122 decode.d7.loss_cls_ce: 1.8197 decode.d7.loss_mask_ce: 0.8419 decode.d7.loss_mask_dice: 1.6155 2023/09/07 12:33:32 - mmengine - INFO - Iter(train) [ 9600/60000] base_lr: 8.4001e-05 lr: 8.4001e-05 eta: 13:46:22 time: 0.9854 data_time: 0.0223 memory: 29111 grad_norm: 25.4487 loss: 9.5296 decode.loss_cls_ce: 1.9755 decode.loss_mask_ce: 0.9162 decode.loss_mask_dice: 1.8730 decode.d7.loss_cls_ce: 1.9675 decode.d7.loss_mask_ce: 0.9242 decode.d7.loss_mask_dice: 1.8731 2023/09/07 12:34:21 - mmengine - INFO - Iter(train) [ 9650/60000] base_lr: 8.3918e-05 lr: 8.3918e-05 eta: 13:45:33 time: 0.9865 data_time: 0.0221 memory: 29165 grad_norm: 28.9070 loss: 9.7140 decode.loss_cls_ce: 2.0944 decode.loss_mask_ce: 0.8810 decode.loss_mask_dice: 1.9103 decode.d7.loss_cls_ce: 2.0522 decode.d7.loss_mask_ce: 0.8896 decode.d7.loss_mask_dice: 1.8865 2023/09/07 12:35:10 - mmengine - INFO - Iter(train) [ 9700/60000] base_lr: 8.3835e-05 lr: 8.3835e-05 eta: 13:44:44 time: 0.9851 data_time: 0.0223 memory: 29211 grad_norm: 24.5450 loss: 10.0181 decode.loss_cls_ce: 2.1498 decode.loss_mask_ce: 0.9104 decode.loss_mask_dice: 1.9438 decode.d7.loss_cls_ce: 2.1523 decode.d7.loss_mask_ce: 0.9169 decode.d7.loss_mask_dice: 1.9449 2023/09/07 12:35:59 - mmengine - INFO - Iter(train) [ 9750/60000] base_lr: 8.3751e-05 lr: 8.3751e-05 eta: 13:43:55 time: 0.9833 data_time: 0.0227 memory: 29239 grad_norm: 27.7238 loss: 8.8153 decode.loss_cls_ce: 1.9781 decode.loss_mask_ce: 0.9301 decode.loss_mask_dice: 1.5263 decode.d7.loss_cls_ce: 1.9528 decode.d7.loss_mask_ce: 0.9227 decode.d7.loss_mask_dice: 1.5053 2023/09/07 12:36:49 - mmengine - INFO - Iter(train) [ 9800/60000] base_lr: 8.3668e-05 lr: 8.3668e-05 eta: 13:43:06 time: 0.9821 data_time: 0.0219 memory: 29224 grad_norm: 25.7647 loss: 9.7566 decode.loss_cls_ce: 2.0847 decode.loss_mask_ce: 0.9844 decode.loss_mask_dice: 1.8156 decode.d7.loss_cls_ce: 2.1070 decode.d7.loss_mask_ce: 0.9711 decode.d7.loss_mask_dice: 1.7939 2023/09/07 12:37:38 - mmengine - INFO - Iter(train) [ 9850/60000] base_lr: 8.3585e-05 lr: 8.3585e-05 eta: 13:42:17 time: 0.9849 data_time: 0.0220 memory: 29516 grad_norm: 25.5159 loss: 10.5981 decode.loss_cls_ce: 2.1826 decode.loss_mask_ce: 0.9296 decode.loss_mask_dice: 2.1848 decode.d7.loss_cls_ce: 2.1637 decode.d7.loss_mask_ce: 0.9490 decode.d7.loss_mask_dice: 2.1884 2023/09/07 12:38:27 - mmengine - INFO - Iter(train) [ 9900/60000] base_lr: 8.3501e-05 lr: 8.3501e-05 eta: 13:41:27 time: 0.9846 data_time: 0.0224 memory: 29231 grad_norm: 24.5841 loss: 11.6856 decode.loss_cls_ce: 2.3994 decode.loss_mask_ce: 1.0387 decode.loss_mask_dice: 2.4151 decode.d7.loss_cls_ce: 2.3805 decode.d7.loss_mask_ce: 1.0355 decode.d7.loss_mask_dice: 2.4164 2023/09/07 12:39:16 - mmengine - INFO - Iter(train) [ 9950/60000] base_lr: 8.3418e-05 lr: 8.3418e-05 eta: 13:40:39 time: 0.9850 data_time: 0.0223 memory: 29176 grad_norm: 24.0892 loss: 10.4570 decode.loss_cls_ce: 2.1968 decode.loss_mask_ce: 0.9839 decode.loss_mask_dice: 2.0479 decode.d7.loss_cls_ce: 2.1743 decode.d7.loss_mask_ce: 1.0025 decode.d7.loss_mask_dice: 2.0516 2023/09/07 12:40:06 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 12:40:06 - mmengine - INFO - Iter(train) [10000/60000] base_lr: 8.3335e-05 lr: 8.3335e-05 eta: 13:39:50 time: 0.9896 data_time: 0.0218 memory: 29257 grad_norm: 23.4983 loss: 9.5866 decode.loss_cls_ce: 2.0355 decode.loss_mask_ce: 0.9648 decode.loss_mask_dice: 1.7931 decode.d7.loss_cls_ce: 2.0254 decode.d7.loss_mask_ce: 0.9736 decode.d7.loss_mask_dice: 1.7942 2023/09/07 12:40:06 - mmengine - INFO - Saving checkpoint at 10000 iterations 2023/09/07 12:41:02 - mmengine - INFO - Iter(train) [10050/60000] base_lr: 8.3251e-05 lr: 8.3251e-05 eta: 13:39:36 time: 0.9865 data_time: 0.0219 memory: 29267 grad_norm: 22.6447 loss: 8.7811 decode.loss_cls_ce: 1.8383 decode.loss_mask_ce: 0.8644 decode.loss_mask_dice: 1.7068 decode.d7.loss_cls_ce: 1.8049 decode.d7.loss_mask_ce: 0.8716 decode.d7.loss_mask_dice: 1.6951 2023/09/07 12:41:51 - mmengine - INFO - Iter(train) [10100/60000] base_lr: 8.3168e-05 lr: 8.3168e-05 eta: 13:38:47 time: 0.9866 data_time: 0.0213 memory: 29201 grad_norm: 27.8229 loss: 9.2661 decode.loss_cls_ce: 2.1721 decode.loss_mask_ce: 0.8077 decode.loss_mask_dice: 1.6524 decode.d7.loss_cls_ce: 2.1744 decode.d7.loss_mask_ce: 0.8115 decode.d7.loss_mask_dice: 1.6478 2023/09/07 12:42:40 - mmengine - INFO - Iter(train) [10150/60000] base_lr: 8.3085e-05 lr: 8.3085e-05 eta: 13:37:58 time: 0.9851 data_time: 0.0221 memory: 29281 grad_norm: 22.5980 loss: 9.4056 decode.loss_cls_ce: 1.8158 decode.loss_mask_ce: 0.9609 decode.loss_mask_dice: 1.9047 decode.d7.loss_cls_ce: 1.8299 decode.d7.loss_mask_ce: 0.9647 decode.d7.loss_mask_dice: 1.9295 2023/09/07 12:43:30 - mmengine - INFO - Iter(train) [10200/60000] base_lr: 8.3001e-05 lr: 8.3001e-05 eta: 13:37:09 time: 0.9863 data_time: 0.0214 memory: 29162 grad_norm: 27.7563 loss: 9.0154 decode.loss_cls_ce: 1.8891 decode.loss_mask_ce: 0.8732 decode.loss_mask_dice: 1.7264 decode.d7.loss_cls_ce: 1.9530 decode.d7.loss_mask_ce: 0.8668 decode.d7.loss_mask_dice: 1.7069 2023/09/07 12:44:19 - mmengine - INFO - Iter(train) [10250/60000] base_lr: 8.2918e-05 lr: 8.2918e-05 eta: 13:36:21 time: 0.9838 data_time: 0.0223 memory: 29338 grad_norm: 21.6771 loss: 9.2633 decode.loss_cls_ce: 2.0854 decode.loss_mask_ce: 0.8723 decode.loss_mask_dice: 1.6773 decode.d7.loss_cls_ce: 2.0740 decode.d7.loss_mask_ce: 0.8772 decode.d7.loss_mask_dice: 1.6771 2023/09/07 12:45:08 - mmengine - INFO - Iter(train) [10300/60000] base_lr: 8.2835e-05 lr: 8.2835e-05 eta: 13:35:31 time: 0.9835 data_time: 0.0221 memory: 29230 grad_norm: 21.2388 loss: 9.0389 decode.loss_cls_ce: 1.9086 decode.loss_mask_ce: 0.9282 decode.loss_mask_dice: 1.7149 decode.d7.loss_cls_ce: 1.8688 decode.d7.loss_mask_ce: 0.8979 decode.d7.loss_mask_dice: 1.7205 2023/09/07 12:45:58 - mmengine - INFO - Iter(train) [10350/60000] base_lr: 8.2751e-05 lr: 8.2751e-05 eta: 13:34:42 time: 0.9862 data_time: 0.0221 memory: 29303 grad_norm: 23.0048 loss: 9.4527 decode.loss_cls_ce: 1.9479 decode.loss_mask_ce: 1.0350 decode.loss_mask_dice: 1.7269 decode.d7.loss_cls_ce: 1.9633 decode.d7.loss_mask_ce: 1.0305 decode.d7.loss_mask_dice: 1.7491 2023/09/07 12:46:47 - mmengine - INFO - Iter(train) [10400/60000] base_lr: 8.2668e-05 lr: 8.2668e-05 eta: 13:33:53 time: 0.9854 data_time: 0.0219 memory: 29193 grad_norm: 21.0835 loss: 10.5034 decode.loss_cls_ce: 2.0686 decode.loss_mask_ce: 1.0324 decode.loss_mask_dice: 2.1588 decode.d7.loss_cls_ce: 2.0258 decode.d7.loss_mask_ce: 1.0191 decode.d7.loss_mask_dice: 2.1988 2023/09/07 12:47:36 - mmengine - INFO - Iter(train) [10450/60000] base_lr: 8.2585e-05 lr: 8.2585e-05 eta: 13:33:04 time: 0.9844 data_time: 0.0215 memory: 29192 grad_norm: 24.3222 loss: 9.7920 decode.loss_cls_ce: 2.0607 decode.loss_mask_ce: 0.8830 decode.loss_mask_dice: 1.9416 decode.d7.loss_cls_ce: 2.0704 decode.d7.loss_mask_ce: 0.8803 decode.d7.loss_mask_dice: 1.9560 2023/09/07 12:48:25 - mmengine - INFO - Iter(train) [10500/60000] base_lr: 8.2501e-05 lr: 8.2501e-05 eta: 13:32:15 time: 0.9846 data_time: 0.0225 memory: 29115 grad_norm: 30.3420 loss: 10.4615 decode.loss_cls_ce: 2.1034 decode.loss_mask_ce: 1.0267 decode.loss_mask_dice: 2.0887 decode.d7.loss_cls_ce: 2.1168 decode.d7.loss_mask_ce: 1.0268 decode.d7.loss_mask_dice: 2.0991 2023/09/07 12:49:15 - mmengine - INFO - Iter(train) [10550/60000] base_lr: 8.2418e-05 lr: 8.2418e-05 eta: 13:31:26 time: 0.9857 data_time: 0.0226 memory: 29138 grad_norm: 22.0151 loss: 9.7091 decode.loss_cls_ce: 1.9727 decode.loss_mask_ce: 1.0030 decode.loss_mask_dice: 1.8887 decode.d7.loss_cls_ce: 1.9923 decode.d7.loss_mask_ce: 0.9848 decode.d7.loss_mask_dice: 1.8677 2023/09/07 12:50:04 - mmengine - INFO - Iter(train) [10600/60000] base_lr: 8.2335e-05 lr: 8.2335e-05 eta: 13:30:36 time: 0.9835 data_time: 0.0222 memory: 29253 grad_norm: 23.6613 loss: 9.2513 decode.loss_cls_ce: 1.8574 decode.loss_mask_ce: 0.9600 decode.loss_mask_dice: 1.8317 decode.d7.loss_cls_ce: 1.8307 decode.d7.loss_mask_ce: 0.9565 decode.d7.loss_mask_dice: 1.8150 2023/09/07 12:50:53 - mmengine - INFO - Iter(train) [10650/60000] base_lr: 8.2251e-05 lr: 8.2251e-05 eta: 13:29:47 time: 0.9865 data_time: 0.0212 memory: 29175 grad_norm: 23.0950 loss: 8.4221 decode.loss_cls_ce: 1.9112 decode.loss_mask_ce: 0.7988 decode.loss_mask_dice: 1.4965 decode.d7.loss_cls_ce: 1.9139 decode.d7.loss_mask_ce: 0.7995 decode.d7.loss_mask_dice: 1.5023 2023/09/07 12:51:42 - mmengine - INFO - Iter(train) [10700/60000] base_lr: 8.2168e-05 lr: 8.2168e-05 eta: 13:28:58 time: 0.9867 data_time: 0.0222 memory: 29253 grad_norm: 23.0410 loss: 12.4575 decode.loss_cls_ce: 2.4928 decode.loss_mask_ce: 1.1335 decode.loss_mask_dice: 2.6096 decode.d7.loss_cls_ce: 2.4944 decode.d7.loss_mask_ce: 1.1223 decode.d7.loss_mask_dice: 2.6049 2023/09/07 12:52:31 - mmengine - INFO - Iter(train) [10750/60000] base_lr: 8.2085e-05 lr: 8.2085e-05 eta: 13:28:09 time: 0.9832 data_time: 0.0225 memory: 29189 grad_norm: 28.8906 loss: 10.7223 decode.loss_cls_ce: 2.2431 decode.loss_mask_ce: 1.0092 decode.loss_mask_dice: 2.1248 decode.d7.loss_cls_ce: 2.2086 decode.d7.loss_mask_ce: 1.0068 decode.d7.loss_mask_dice: 2.1297 2023/09/07 12:53:21 - mmengine - INFO - Iter(train) [10800/60000] base_lr: 8.2001e-05 lr: 8.2001e-05 eta: 13:27:20 time: 0.9862 data_time: 0.0217 memory: 29340 grad_norm: 22.3382 loss: 9.7907 decode.loss_cls_ce: 2.0818 decode.loss_mask_ce: 0.9629 decode.loss_mask_dice: 1.8243 decode.d7.loss_cls_ce: 2.0822 decode.d7.loss_mask_ce: 0.9783 decode.d7.loss_mask_dice: 1.8612 2023/09/07 12:54:10 - mmengine - INFO - Iter(train) [10850/60000] base_lr: 8.1918e-05 lr: 8.1918e-05 eta: 13:26:30 time: 0.9839 data_time: 0.0221 memory: 29244 grad_norm: 22.1167 loss: 9.8622 decode.loss_cls_ce: 2.0900 decode.loss_mask_ce: 0.9704 decode.loss_mask_dice: 1.8812 decode.d7.loss_cls_ce: 2.0956 decode.d7.loss_mask_ce: 0.9575 decode.d7.loss_mask_dice: 1.8676 2023/09/07 12:54:59 - mmengine - INFO - Iter(train) [10900/60000] base_lr: 8.1835e-05 lr: 8.1835e-05 eta: 13:25:41 time: 0.9849 data_time: 0.0225 memory: 29254 grad_norm: 20.9831 loss: 7.5720 decode.loss_cls_ce: 1.5745 decode.loss_mask_ce: 0.7317 decode.loss_mask_dice: 1.4856 decode.d7.loss_cls_ce: 1.5764 decode.d7.loss_mask_ce: 0.7391 decode.d7.loss_mask_dice: 1.4647 2023/09/07 12:55:48 - mmengine - INFO - Iter(train) [10950/60000] base_lr: 8.1751e-05 lr: 8.1751e-05 eta: 13:24:51 time: 0.9839 data_time: 0.0219 memory: 29262 grad_norm: 22.8874 loss: 9.1904 decode.loss_cls_ce: 1.9368 decode.loss_mask_ce: 0.8487 decode.loss_mask_dice: 1.7952 decode.d7.loss_cls_ce: 1.9661 decode.d7.loss_mask_ce: 0.8454 decode.d7.loss_mask_dice: 1.7982 2023/09/07 12:56:38 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 12:56:38 - mmengine - INFO - Iter(train) [11000/60000] base_lr: 8.1668e-05 lr: 8.1668e-05 eta: 13:24:02 time: 0.9846 data_time: 0.0224 memory: 29187 grad_norm: 21.1131 loss: 9.7231 decode.loss_cls_ce: 2.0574 decode.loss_mask_ce: 0.8255 decode.loss_mask_dice: 1.9685 decode.d7.loss_cls_ce: 2.0972 decode.d7.loss_mask_ce: 0.8134 decode.d7.loss_mask_dice: 1.9612 2023/09/07 12:57:27 - mmengine - INFO - Iter(train) [11050/60000] base_lr: 8.1585e-05 lr: 8.1585e-05 eta: 13:23:13 time: 0.9844 data_time: 0.0221 memory: 29153 grad_norm: 26.6673 loss: 7.8795 decode.loss_cls_ce: 1.6852 decode.loss_mask_ce: 0.8231 decode.loss_mask_dice: 1.4369 decode.d7.loss_cls_ce: 1.6760 decode.d7.loss_mask_ce: 0.8206 decode.d7.loss_mask_dice: 1.4377 2023/09/07 12:58:16 - mmengine - INFO - Iter(train) [11100/60000] base_lr: 8.1501e-05 lr: 8.1501e-05 eta: 13:22:24 time: 0.9842 data_time: 0.0224 memory: 29152 grad_norm: 22.5788 loss: 11.2012 decode.loss_cls_ce: 2.1665 decode.loss_mask_ce: 1.0513 decode.loss_mask_dice: 2.3746 decode.d7.loss_cls_ce: 2.1669 decode.d7.loss_mask_ce: 1.0532 decode.d7.loss_mask_dice: 2.3886 2023/09/07 12:59:05 - mmengine - INFO - Iter(train) [11150/60000] base_lr: 8.1418e-05 lr: 8.1418e-05 eta: 13:21:35 time: 0.9851 data_time: 0.0206 memory: 29138 grad_norm: 22.0624 loss: 7.7239 decode.loss_cls_ce: 1.6177 decode.loss_mask_ce: 0.7912 decode.loss_mask_dice: 1.4685 decode.d7.loss_cls_ce: 1.5758 decode.d7.loss_mask_ce: 0.7891 decode.d7.loss_mask_dice: 1.4815 2023/09/07 12:59:54 - mmengine - INFO - Iter(train) [11200/60000] base_lr: 8.1335e-05 lr: 8.1335e-05 eta: 13:20:45 time: 0.9812 data_time: 0.0217 memory: 29129 grad_norm: 21.6867 loss: 9.2292 decode.loss_cls_ce: 1.9965 decode.loss_mask_ce: 0.8924 decode.loss_mask_dice: 1.7436 decode.d7.loss_cls_ce: 2.0001 decode.d7.loss_mask_ce: 0.8719 decode.d7.loss_mask_dice: 1.7246 2023/09/07 13:00:44 - mmengine - INFO - Iter(train) [11250/60000] base_lr: 8.1251e-05 lr: 8.1251e-05 eta: 13:19:56 time: 0.9831 data_time: 0.0217 memory: 29361 grad_norm: 21.6701 loss: 8.6961 decode.loss_cls_ce: 1.8747 decode.loss_mask_ce: 0.8223 decode.loss_mask_dice: 1.6326 decode.d7.loss_cls_ce: 1.9033 decode.d7.loss_mask_ce: 0.8303 decode.d7.loss_mask_dice: 1.6328 2023/09/07 13:01:33 - mmengine - INFO - Iter(train) [11300/60000] base_lr: 8.1168e-05 lr: 8.1168e-05 eta: 13:19:06 time: 0.9860 data_time: 0.0211 memory: 29162 grad_norm: 26.5207 loss: 10.1099 decode.loss_cls_ce: 2.0309 decode.loss_mask_ce: 1.0819 decode.loss_mask_dice: 1.9324 decode.d7.loss_cls_ce: 2.0575 decode.d7.loss_mask_ce: 1.0678 decode.d7.loss_mask_dice: 1.9393 2023/09/07 13:02:22 - mmengine - INFO - Iter(train) [11350/60000] base_lr: 8.1085e-05 lr: 8.1085e-05 eta: 13:18:17 time: 0.9848 data_time: 0.0206 memory: 29216 grad_norm: 23.2612 loss: 7.8463 decode.loss_cls_ce: 1.6736 decode.loss_mask_ce: 0.7651 decode.loss_mask_dice: 1.4837 decode.d7.loss_cls_ce: 1.6616 decode.d7.loss_mask_ce: 0.7577 decode.d7.loss_mask_dice: 1.5046 2023/09/07 13:03:11 - mmengine - INFO - Iter(train) [11400/60000] base_lr: 8.1001e-05 lr: 8.1001e-05 eta: 13:17:28 time: 0.9817 data_time: 0.0218 memory: 29192 grad_norm: 20.8523 loss: 9.9114 decode.loss_cls_ce: 2.1137 decode.loss_mask_ce: 0.9058 decode.loss_mask_dice: 1.9216 decode.d7.loss_cls_ce: 2.1492 decode.d7.loss_mask_ce: 0.9089 decode.d7.loss_mask_dice: 1.9121 2023/09/07 13:04:01 - mmengine - INFO - Iter(train) [11450/60000] base_lr: 8.0918e-05 lr: 8.0918e-05 eta: 13:16:39 time: 0.9858 data_time: 0.0214 memory: 29141 grad_norm: 25.0185 loss: 8.9746 decode.loss_cls_ce: 1.9445 decode.loss_mask_ce: 0.9186 decode.loss_mask_dice: 1.6092 decode.d7.loss_cls_ce: 1.9630 decode.d7.loss_mask_ce: 0.9244 decode.d7.loss_mask_dice: 1.6150 2023/09/07 13:04:50 - mmengine - INFO - Iter(train) [11500/60000] base_lr: 8.0835e-05 lr: 8.0835e-05 eta: 13:15:49 time: 0.9826 data_time: 0.0231 memory: 29125 grad_norm: 22.3969 loss: 9.4218 decode.loss_cls_ce: 1.9621 decode.loss_mask_ce: 0.8441 decode.loss_mask_dice: 1.9079 decode.d7.loss_cls_ce: 1.9759 decode.d7.loss_mask_ce: 0.8434 decode.d7.loss_mask_dice: 1.8884 2023/09/07 13:05:39 - mmengine - INFO - Iter(train) [11550/60000] base_lr: 8.0751e-05 lr: 8.0751e-05 eta: 13:15:00 time: 0.9845 data_time: 0.0213 memory: 29162 grad_norm: 21.6120 loss: 10.4610 decode.loss_cls_ce: 2.0423 decode.loss_mask_ce: 1.0413 decode.loss_mask_dice: 2.1364 decode.d7.loss_cls_ce: 2.0606 decode.d7.loss_mask_ce: 1.0420 decode.d7.loss_mask_dice: 2.1384 2023/09/07 13:06:28 - mmengine - INFO - Iter(train) [11600/60000] base_lr: 8.0668e-05 lr: 8.0668e-05 eta: 13:14:10 time: 0.9845 data_time: 0.0203 memory: 29115 grad_norm: 22.1390 loss: 10.6878 decode.loss_cls_ce: 2.1119 decode.loss_mask_ce: 0.9801 decode.loss_mask_dice: 2.2587 decode.d7.loss_cls_ce: 2.0859 decode.d7.loss_mask_ce: 0.9774 decode.d7.loss_mask_dice: 2.2737 2023/09/07 13:07:17 - mmengine - INFO - Iter(train) [11650/60000] base_lr: 8.0585e-05 lr: 8.0585e-05 eta: 13:13:21 time: 0.9817 data_time: 0.0221 memory: 29346 grad_norm: 20.8138 loss: 9.1563 decode.loss_cls_ce: 2.0268 decode.loss_mask_ce: 0.8953 decode.loss_mask_dice: 1.6826 decode.d7.loss_cls_ce: 1.9869 decode.d7.loss_mask_ce: 0.8976 decode.d7.loss_mask_dice: 1.6671 2023/09/07 13:08:06 - mmengine - INFO - Iter(train) [11700/60000] base_lr: 8.0501e-05 lr: 8.0501e-05 eta: 13:12:32 time: 0.9858 data_time: 0.0216 memory: 29202 grad_norm: 24.0670 loss: 8.3124 decode.loss_cls_ce: 1.7743 decode.loss_mask_ce: 0.8101 decode.loss_mask_dice: 1.5574 decode.d7.loss_cls_ce: 1.8089 decode.d7.loss_mask_ce: 0.8033 decode.d7.loss_mask_dice: 1.5583 2023/09/07 13:08:56 - mmengine - INFO - Iter(train) [11750/60000] base_lr: 8.0418e-05 lr: 8.0418e-05 eta: 13:11:42 time: 0.9822 data_time: 0.0224 memory: 29306 grad_norm: 24.8020 loss: 8.4889 decode.loss_cls_ce: 1.8745 decode.loss_mask_ce: 0.8181 decode.loss_mask_dice: 1.5335 decode.d7.loss_cls_ce: 1.8982 decode.d7.loss_mask_ce: 0.8276 decode.d7.loss_mask_dice: 1.5370 2023/09/07 13:09:45 - mmengine - INFO - Iter(train) [11800/60000] base_lr: 8.0335e-05 lr: 8.0335e-05 eta: 13:10:53 time: 0.9853 data_time: 0.0214 memory: 29178 grad_norm: 23.9310 loss: 10.7181 decode.loss_cls_ce: 2.2408 decode.loss_mask_ce: 1.0422 decode.loss_mask_dice: 2.0816 decode.d7.loss_cls_ce: 2.2408 decode.d7.loss_mask_ce: 1.0449 decode.d7.loss_mask_dice: 2.0679 2023/09/07 13:10:34 - mmengine - INFO - Iter(train) [11850/60000] base_lr: 8.0251e-05 lr: 8.0251e-05 eta: 13:10:04 time: 0.9850 data_time: 0.0209 memory: 29266 grad_norm: 24.1184 loss: 10.5367 decode.loss_cls_ce: 2.1031 decode.loss_mask_ce: 1.1411 decode.loss_mask_dice: 2.0378 decode.d7.loss_cls_ce: 2.0879 decode.d7.loss_mask_ce: 1.1252 decode.d7.loss_mask_dice: 2.0417 2023/09/07 13:11:23 - mmengine - INFO - Iter(train) [11900/60000] base_lr: 8.0168e-05 lr: 8.0168e-05 eta: 13:09:14 time: 0.9843 data_time: 0.0220 memory: 29225 grad_norm: 27.4812 loss: 9.8919 decode.loss_cls_ce: 2.0450 decode.loss_mask_ce: 0.9655 decode.loss_mask_dice: 1.9455 decode.d7.loss_cls_ce: 2.0298 decode.d7.loss_mask_ce: 0.9704 decode.d7.loss_mask_dice: 1.9357 2023/09/07 13:12:13 - mmengine - INFO - Iter(train) [11950/60000] base_lr: 8.0085e-05 lr: 8.0085e-05 eta: 13:08:25 time: 0.9835 data_time: 0.0214 memory: 29176 grad_norm: 24.1134 loss: 8.6234 decode.loss_cls_ce: 1.9014 decode.loss_mask_ce: 0.8199 decode.loss_mask_dice: 1.5725 decode.d7.loss_cls_ce: 1.9171 decode.d7.loss_mask_ce: 0.8320 decode.d7.loss_mask_dice: 1.5805 2023/09/07 13:13:02 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 13:13:02 - mmengine - INFO - Iter(train) [12000/60000] base_lr: 8.0001e-05 lr: 8.0001e-05 eta: 13:07:35 time: 0.9823 data_time: 0.0223 memory: 29136 grad_norm: 19.8142 loss: 8.7941 decode.loss_cls_ce: 1.9691 decode.loss_mask_ce: 0.8411 decode.loss_mask_dice: 1.6019 decode.d7.loss_cls_ce: 1.9321 decode.d7.loss_mask_ce: 0.8471 decode.d7.loss_mask_dice: 1.6028 2023/09/07 13:13:51 - mmengine - INFO - Iter(train) [12050/60000] base_lr: 7.9918e-05 lr: 7.9918e-05 eta: 13:06:46 time: 0.9827 data_time: 0.0221 memory: 29179 grad_norm: 25.6747 loss: 8.7306 decode.loss_cls_ce: 1.9154 decode.loss_mask_ce: 0.8537 decode.loss_mask_dice: 1.5943 decode.d7.loss_cls_ce: 1.8980 decode.d7.loss_mask_ce: 0.8637 decode.d7.loss_mask_dice: 1.6055 2023/09/07 13:14:40 - mmengine - INFO - Iter(train) [12100/60000] base_lr: 7.9835e-05 lr: 7.9835e-05 eta: 13:05:56 time: 0.9822 data_time: 0.0215 memory: 29281 grad_norm: 22.5717 loss: 10.0763 decode.loss_cls_ce: 1.9935 decode.loss_mask_ce: 0.9055 decode.loss_mask_dice: 2.1336 decode.d7.loss_cls_ce: 2.0032 decode.d7.loss_mask_ce: 0.9024 decode.d7.loss_mask_dice: 2.1382 2023/09/07 13:15:29 - mmengine - INFO - Iter(train) [12150/60000] base_lr: 7.9751e-05 lr: 7.9751e-05 eta: 13:05:07 time: 0.9852 data_time: 0.0218 memory: 29257 grad_norm: 39.1091 loss: 8.4716 decode.loss_cls_ce: 1.7813 decode.loss_mask_ce: 0.8723 decode.loss_mask_dice: 1.5749 decode.d7.loss_cls_ce: 1.7623 decode.d7.loss_mask_ce: 0.8904 decode.d7.loss_mask_dice: 1.5905 2023/09/07 13:16:18 - mmengine - INFO - Iter(train) [12200/60000] base_lr: 7.9668e-05 lr: 7.9668e-05 eta: 13:04:18 time: 0.9865 data_time: 0.0217 memory: 29182 grad_norm: 23.4900 loss: 8.7364 decode.loss_cls_ce: 1.8365 decode.loss_mask_ce: 0.7896 decode.loss_mask_dice: 1.7435 decode.d7.loss_cls_ce: 1.8526 decode.d7.loss_mask_ce: 0.7742 decode.d7.loss_mask_dice: 1.7400 2023/09/07 13:17:08 - mmengine - INFO - Iter(train) [12250/60000] base_lr: 7.9585e-05 lr: 7.9585e-05 eta: 13:03:29 time: 0.9830 data_time: 0.0215 memory: 29148 grad_norm: 22.8765 loss: 8.5953 decode.loss_cls_ce: 1.7395 decode.loss_mask_ce: 0.9045 decode.loss_mask_dice: 1.6305 decode.d7.loss_cls_ce: 1.7818 decode.d7.loss_mask_ce: 0.8948 decode.d7.loss_mask_dice: 1.6443 2023/09/07 13:17:57 - mmengine - INFO - Iter(train) [12300/60000] base_lr: 7.9501e-05 lr: 7.9501e-05 eta: 13:02:39 time: 0.9861 data_time: 0.0217 memory: 29109 grad_norm: 23.9530 loss: 8.3075 decode.loss_cls_ce: 1.8720 decode.loss_mask_ce: 0.7569 decode.loss_mask_dice: 1.5135 decode.d7.loss_cls_ce: 1.8784 decode.d7.loss_mask_ce: 0.7584 decode.d7.loss_mask_dice: 1.5283 2023/09/07 13:18:46 - mmengine - INFO - Iter(train) [12350/60000] base_lr: 7.9418e-05 lr: 7.9418e-05 eta: 13:01:50 time: 0.9846 data_time: 0.0212 memory: 29343 grad_norm: 31.4178 loss: 8.6925 decode.loss_cls_ce: 1.9442 decode.loss_mask_ce: 0.8192 decode.loss_mask_dice: 1.5727 decode.d7.loss_cls_ce: 1.9410 decode.d7.loss_mask_ce: 0.8246 decode.d7.loss_mask_dice: 1.5908 2023/09/07 13:19:35 - mmengine - INFO - Iter(train) [12400/60000] base_lr: 7.9335e-05 lr: 7.9335e-05 eta: 13:01:01 time: 0.9848 data_time: 0.0211 memory: 29219 grad_norm: 22.4998 loss: 9.2484 decode.loss_cls_ce: 2.0044 decode.loss_mask_ce: 0.9096 decode.loss_mask_dice: 1.7211 decode.d7.loss_cls_ce: 1.9985 decode.d7.loss_mask_ce: 0.9016 decode.d7.loss_mask_dice: 1.7133 2023/09/07 13:20:25 - mmengine - INFO - Iter(train) [12450/60000] base_lr: 7.9251e-05 lr: 7.9251e-05 eta: 13:00:12 time: 0.9842 data_time: 0.0217 memory: 29156 grad_norm: 20.5163 loss: 9.4601 decode.loss_cls_ce: 2.1423 decode.loss_mask_ce: 0.8578 decode.loss_mask_dice: 1.7305 decode.d7.loss_cls_ce: 2.1359 decode.d7.loss_mask_ce: 0.8650 decode.d7.loss_mask_dice: 1.7285 2023/09/07 13:21:14 - mmengine - INFO - Iter(train) [12500/60000] base_lr: 7.9168e-05 lr: 7.9168e-05 eta: 12:59:22 time: 0.9822 data_time: 0.0215 memory: 29331 grad_norm: 25.4499 loss: 10.8245 decode.loss_cls_ce: 2.1839 decode.loss_mask_ce: 1.0376 decode.loss_mask_dice: 2.2095 decode.d7.loss_cls_ce: 2.1419 decode.d7.loss_mask_ce: 1.0297 decode.d7.loss_mask_dice: 2.2220 2023/09/07 13:22:03 - mmengine - INFO - Iter(train) [12550/60000] base_lr: 7.9085e-05 lr: 7.9085e-05 eta: 12:58:33 time: 0.9841 data_time: 0.0217 memory: 29190 grad_norm: 23.2149 loss: 10.0024 decode.loss_cls_ce: 1.9941 decode.loss_mask_ce: 0.8886 decode.loss_mask_dice: 2.1355 decode.d7.loss_cls_ce: 1.9671 decode.d7.loss_mask_ce: 0.8863 decode.d7.loss_mask_dice: 2.1309 2023/09/07 13:22:52 - mmengine - INFO - Iter(train) [12600/60000] base_lr: 7.9001e-05 lr: 7.9001e-05 eta: 12:57:43 time: 0.9839 data_time: 0.0221 memory: 29244 grad_norm: 21.2548 loss: 7.8451 decode.loss_cls_ce: 1.6303 decode.loss_mask_ce: 0.8794 decode.loss_mask_dice: 1.4203 decode.d7.loss_cls_ce: 1.5947 decode.d7.loss_mask_ce: 0.8893 decode.d7.loss_mask_dice: 1.4311 2023/09/07 13:23:41 - mmengine - INFO - Iter(train) [12650/60000] base_lr: 7.8918e-05 lr: 7.8918e-05 eta: 12:56:54 time: 0.9820 data_time: 0.0217 memory: 29277 grad_norm: 21.9484 loss: 11.1176 decode.loss_cls_ce: 2.3826 decode.loss_mask_ce: 0.9816 decode.loss_mask_dice: 2.2221 decode.d7.loss_cls_ce: 2.3385 decode.d7.loss_mask_ce: 0.9830 decode.d7.loss_mask_dice: 2.2097 2023/09/07 13:24:30 - mmengine - INFO - Iter(train) [12700/60000] base_lr: 7.8835e-05 lr: 7.8835e-05 eta: 12:56:05 time: 0.9837 data_time: 0.0216 memory: 29253 grad_norm: 22.5418 loss: 10.2285 decode.loss_cls_ce: 2.0082 decode.loss_mask_ce: 1.0411 decode.loss_mask_dice: 2.0680 decode.d7.loss_cls_ce: 1.9858 decode.d7.loss_mask_ce: 1.0422 decode.d7.loss_mask_dice: 2.0832 2023/09/07 13:25:20 - mmengine - INFO - Iter(train) [12750/60000] base_lr: 7.8751e-05 lr: 7.8751e-05 eta: 12:55:15 time: 0.9833 data_time: 0.0221 memory: 29188 grad_norm: 23.7414 loss: 7.7868 decode.loss_cls_ce: 1.6803 decode.loss_mask_ce: 0.8249 decode.loss_mask_dice: 1.4245 decode.d7.loss_cls_ce: 1.6241 decode.d7.loss_mask_ce: 0.8226 decode.d7.loss_mask_dice: 1.4105 2023/09/07 13:26:09 - mmengine - INFO - Iter(train) [12800/60000] base_lr: 7.8668e-05 lr: 7.8668e-05 eta: 12:54:26 time: 0.9854 data_time: 0.0220 memory: 29128 grad_norm: 21.5767 loss: 8.7753 decode.loss_cls_ce: 1.8738 decode.loss_mask_ce: 0.8138 decode.loss_mask_dice: 1.6737 decode.d7.loss_cls_ce: 1.9313 decode.d7.loss_mask_ce: 0.8111 decode.d7.loss_mask_dice: 1.6716 2023/09/07 13:26:58 - mmengine - INFO - Iter(train) [12850/60000] base_lr: 7.8585e-05 lr: 7.8585e-05 eta: 12:53:37 time: 0.9840 data_time: 0.0219 memory: 29203 grad_norm: 24.5079 loss: 8.9879 decode.loss_cls_ce: 1.8301 decode.loss_mask_ce: 0.8728 decode.loss_mask_dice: 1.8064 decode.d7.loss_cls_ce: 1.8195 decode.d7.loss_mask_ce: 0.8634 decode.d7.loss_mask_dice: 1.7958 2023/09/07 13:27:47 - mmengine - INFO - Iter(train) [12900/60000] base_lr: 7.8501e-05 lr: 7.8501e-05 eta: 12:52:48 time: 0.9837 data_time: 0.0221 memory: 29264 grad_norm: 20.0222 loss: 8.1929 decode.loss_cls_ce: 1.6378 decode.loss_mask_ce: 0.8278 decode.loss_mask_dice: 1.6212 decode.d7.loss_cls_ce: 1.6401 decode.d7.loss_mask_ce: 0.8326 decode.d7.loss_mask_dice: 1.6334 2023/09/07 13:28:37 - mmengine - INFO - Iter(train) [12950/60000] base_lr: 7.8418e-05 lr: 7.8418e-05 eta: 12:51:58 time: 0.9824 data_time: 0.0214 memory: 29313 grad_norm: 22.5940 loss: 9.2602 decode.loss_cls_ce: 1.8968 decode.loss_mask_ce: 0.8495 decode.loss_mask_dice: 1.8767 decode.d7.loss_cls_ce: 1.9080 decode.d7.loss_mask_ce: 0.8377 decode.d7.loss_mask_dice: 1.8915 2023/09/07 13:29:26 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 13:29:26 - mmengine - INFO - Iter(train) [13000/60000] base_lr: 7.8335e-05 lr: 7.8335e-05 eta: 12:51:09 time: 0.9826 data_time: 0.0222 memory: 29116 grad_norm: 24.5866 loss: 8.7074 decode.loss_cls_ce: 1.9715 decode.loss_mask_ce: 0.8433 decode.loss_mask_dice: 1.5367 decode.d7.loss_cls_ce: 1.9942 decode.d7.loss_mask_ce: 0.8400 decode.d7.loss_mask_dice: 1.5217 2023/09/07 13:30:15 - mmengine - INFO - Iter(train) [13050/60000] base_lr: 7.8251e-05 lr: 7.8251e-05 eta: 12:50:19 time: 0.9810 data_time: 0.0212 memory: 29152 grad_norm: 22.2171 loss: 7.6507 decode.loss_cls_ce: 1.7169 decode.loss_mask_ce: 0.6624 decode.loss_mask_dice: 1.4475 decode.d7.loss_cls_ce: 1.7372 decode.d7.loss_mask_ce: 0.6664 decode.d7.loss_mask_dice: 1.4204 2023/09/07 13:31:04 - mmengine - INFO - Iter(train) [13100/60000] base_lr: 7.8168e-05 lr: 7.8168e-05 eta: 12:49:30 time: 0.9848 data_time: 0.0216 memory: 29140 grad_norm: 22.1479 loss: 8.7370 decode.loss_cls_ce: 1.8359 decode.loss_mask_ce: 0.8562 decode.loss_mask_dice: 1.6955 decode.d7.loss_cls_ce: 1.7835 decode.d7.loss_mask_ce: 0.8600 decode.d7.loss_mask_dice: 1.7058 2023/09/07 13:31:53 - mmengine - INFO - Iter(train) [13150/60000] base_lr: 7.8085e-05 lr: 7.8085e-05 eta: 12:48:41 time: 0.9824 data_time: 0.0219 memory: 29227 grad_norm: 21.5451 loss: 9.3162 decode.loss_cls_ce: 2.1472 decode.loss_mask_ce: 0.9065 decode.loss_mask_dice: 1.6224 decode.d7.loss_cls_ce: 2.1103 decode.d7.loss_mask_ce: 0.9027 decode.d7.loss_mask_dice: 1.6271 2023/09/07 13:32:42 - mmengine - INFO - Iter(train) [13200/60000] base_lr: 7.8001e-05 lr: 7.8001e-05 eta: 12:47:51 time: 0.9828 data_time: 0.0219 memory: 29167 grad_norm: 25.2439 loss: 9.9337 decode.loss_cls_ce: 2.1449 decode.loss_mask_ce: 0.9404 decode.loss_mask_dice: 1.8762 decode.d7.loss_cls_ce: 2.1357 decode.d7.loss_mask_ce: 0.9514 decode.d7.loss_mask_dice: 1.8851 2023/09/07 13:33:32 - mmengine - INFO - Iter(train) [13250/60000] base_lr: 7.7918e-05 lr: 7.7918e-05 eta: 12:47:02 time: 0.9844 data_time: 0.0215 memory: 29268 grad_norm: 21.9387 loss: 9.7807 decode.loss_cls_ce: 1.9766 decode.loss_mask_ce: 0.8702 decode.loss_mask_dice: 2.0296 decode.d7.loss_cls_ce: 2.0030 decode.d7.loss_mask_ce: 0.8787 decode.d7.loss_mask_dice: 2.0225 2023/09/07 13:34:21 - mmengine - INFO - Iter(train) [13300/60000] base_lr: 7.7835e-05 lr: 7.7835e-05 eta: 12:46:13 time: 0.9854 data_time: 0.0216 memory: 29232 grad_norm: 23.6598 loss: 10.1147 decode.loss_cls_ce: 2.1579 decode.loss_mask_ce: 0.9291 decode.loss_mask_dice: 1.9765 decode.d7.loss_cls_ce: 2.1334 decode.d7.loss_mask_ce: 0.9302 decode.d7.loss_mask_dice: 1.9877 2023/09/07 13:35:10 - mmengine - INFO - Iter(train) [13350/60000] base_lr: 7.7751e-05 lr: 7.7751e-05 eta: 12:45:23 time: 0.9811 data_time: 0.0216 memory: 29185 grad_norm: nan loss: 9.8478 decode.loss_cls_ce: 1.8495 decode.loss_mask_ce: 1.0899 decode.loss_mask_dice: 1.9640 decode.d7.loss_cls_ce: 1.8886 decode.d7.loss_mask_ce: 1.0841 decode.d7.loss_mask_dice: 1.9717 2023/09/07 13:35:59 - mmengine - INFO - Iter(train) [13400/60000] base_lr: 7.7668e-05 lr: 7.7668e-05 eta: 12:44:34 time: 0.9824 data_time: 0.0215 memory: 29205 grad_norm: 23.3187 loss: 10.8505 decode.loss_cls_ce: 2.3560 decode.loss_mask_ce: 1.0193 decode.loss_mask_dice: 2.0578 decode.d7.loss_cls_ce: 2.3452 decode.d7.loss_mask_ce: 1.0160 decode.d7.loss_mask_dice: 2.0563 2023/09/07 13:36:48 - mmengine - INFO - Iter(train) [13450/60000] base_lr: 7.7585e-05 lr: 7.7585e-05 eta: 12:43:45 time: 0.9860 data_time: 0.0215 memory: 29241 grad_norm: 26.2939 loss: 9.4919 decode.loss_cls_ce: 2.0737 decode.loss_mask_ce: 0.9740 decode.loss_mask_dice: 1.7130 decode.d7.loss_cls_ce: 2.0402 decode.d7.loss_mask_ce: 0.9700 decode.d7.loss_mask_dice: 1.7210 2023/09/07 13:37:38 - mmengine - INFO - Iter(train) [13500/60000] base_lr: 7.7501e-05 lr: 7.7501e-05 eta: 12:42:55 time: 0.9862 data_time: 0.0215 memory: 29192 grad_norm: 20.0765 loss: 9.3796 decode.loss_cls_ce: 2.0027 decode.loss_mask_ce: 0.8709 decode.loss_mask_dice: 1.8060 decode.d7.loss_cls_ce: 2.0266 decode.d7.loss_mask_ce: 0.8734 decode.d7.loss_mask_dice: 1.8001 2023/09/07 13:38:27 - mmengine - INFO - Iter(train) [13550/60000] base_lr: 7.7418e-05 lr: 7.7418e-05 eta: 12:42:06 time: 0.9826 data_time: 0.0215 memory: 29241 grad_norm: 21.3855 loss: 8.5248 decode.loss_cls_ce: 1.7983 decode.loss_mask_ce: 0.8491 decode.loss_mask_dice: 1.6198 decode.d7.loss_cls_ce: 1.8092 decode.d7.loss_mask_ce: 0.8471 decode.d7.loss_mask_dice: 1.6014 2023/09/07 13:39:16 - mmengine - INFO - Iter(train) [13600/60000] base_lr: 7.7335e-05 lr: 7.7335e-05 eta: 12:41:17 time: 0.9866 data_time: 0.0214 memory: 29044 grad_norm: 19.0143 loss: 8.7588 decode.loss_cls_ce: 1.9337 decode.loss_mask_ce: 0.7568 decode.loss_mask_dice: 1.6929 decode.d7.loss_cls_ce: 1.9250 decode.d7.loss_mask_ce: 0.7499 decode.d7.loss_mask_dice: 1.7005 2023/09/07 13:40:05 - mmengine - INFO - Iter(train) [13650/60000] base_lr: 7.7251e-05 lr: 7.7251e-05 eta: 12:40:28 time: 0.9867 data_time: 0.0211 memory: 29178 grad_norm: 22.9728 loss: 9.8448 decode.loss_cls_ce: 2.1238 decode.loss_mask_ce: 0.9078 decode.loss_mask_dice: 1.8829 decode.d7.loss_cls_ce: 2.1230 decode.d7.loss_mask_ce: 0.9090 decode.d7.loss_mask_dice: 1.8982 2023/09/07 13:40:54 - mmengine - INFO - Iter(train) [13700/60000] base_lr: 7.7168e-05 lr: 7.7168e-05 eta: 12:39:38 time: 0.9842 data_time: 0.0217 memory: 29168 grad_norm: 22.1823 loss: 9.0105 decode.loss_cls_ce: 1.7388 decode.loss_mask_ce: 0.9126 decode.loss_mask_dice: 1.8373 decode.d7.loss_cls_ce: 1.7520 decode.d7.loss_mask_ce: 0.9191 decode.d7.loss_mask_dice: 1.8507 2023/09/07 13:41:44 - mmengine - INFO - Iter(train) [13750/60000] base_lr: 7.7085e-05 lr: 7.7085e-05 eta: 12:38:49 time: 0.9889 data_time: 0.0214 memory: 29151 grad_norm: 25.7299 loss: 9.3843 decode.loss_cls_ce: 1.9056 decode.loss_mask_ce: 0.9836 decode.loss_mask_dice: 1.8226 decode.d7.loss_cls_ce: 1.9034 decode.d7.loss_mask_ce: 0.9677 decode.d7.loss_mask_dice: 1.8014 2023/09/07 13:42:33 - mmengine - INFO - Iter(train) [13800/60000] base_lr: 7.7001e-05 lr: 7.7001e-05 eta: 12:38:00 time: 0.9821 data_time: 0.0223 memory: 29135 grad_norm: 22.2646 loss: 8.5483 decode.loss_cls_ce: 1.8278 decode.loss_mask_ce: 0.8080 decode.loss_mask_dice: 1.6607 decode.d7.loss_cls_ce: 1.7762 decode.d7.loss_mask_ce: 0.8178 decode.d7.loss_mask_dice: 1.6577 2023/09/07 13:43:22 - mmengine - INFO - Iter(train) [13850/60000] base_lr: 7.6918e-05 lr: 7.6918e-05 eta: 12:37:10 time: 0.9837 data_time: 0.0215 memory: 29178 grad_norm: 20.7372 loss: 9.8090 decode.loss_cls_ce: 1.9614 decode.loss_mask_ce: 0.9305 decode.loss_mask_dice: 2.0134 decode.d7.loss_cls_ce: 1.9684 decode.d7.loss_mask_ce: 0.9300 decode.d7.loss_mask_dice: 2.0054 2023/09/07 13:44:11 - mmengine - INFO - Iter(train) [13900/60000] base_lr: 7.6835e-05 lr: 7.6835e-05 eta: 12:36:21 time: 0.9839 data_time: 0.0216 memory: 29195 grad_norm: 21.7908 loss: 8.0267 decode.loss_cls_ce: 1.8558 decode.loss_mask_ce: 0.7875 decode.loss_mask_dice: 1.3721 decode.d7.loss_cls_ce: 1.8429 decode.d7.loss_mask_ce: 0.7956 decode.d7.loss_mask_dice: 1.3728 2023/09/07 13:45:00 - mmengine - INFO - Iter(train) [13950/60000] base_lr: 7.6751e-05 lr: 7.6751e-05 eta: 12:35:32 time: 0.9842 data_time: 0.0214 memory: 29176 grad_norm: 29.1658 loss: 8.3371 decode.loss_cls_ce: 1.7432 decode.loss_mask_ce: 0.8066 decode.loss_mask_dice: 1.6144 decode.d7.loss_cls_ce: 1.7386 decode.d7.loss_mask_ce: 0.8089 decode.d7.loss_mask_dice: 1.6254 2023/09/07 13:45:50 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 13:45:50 - mmengine - INFO - Iter(train) [14000/60000] base_lr: 7.6668e-05 lr: 7.6668e-05 eta: 12:34:42 time: 0.9838 data_time: 0.0213 memory: 29178 grad_norm: 21.8136 loss: 8.1583 decode.loss_cls_ce: 1.7646 decode.loss_mask_ce: 0.7841 decode.loss_mask_dice: 1.5030 decode.d7.loss_cls_ce: 1.7977 decode.d7.loss_mask_ce: 0.7958 decode.d7.loss_mask_dice: 1.5131 2023/09/07 13:46:39 - mmengine - INFO - Iter(train) [14050/60000] base_lr: 7.6585e-05 lr: 7.6585e-05 eta: 12:33:53 time: 0.9831 data_time: 0.0219 memory: 29231 grad_norm: 20.4647 loss: 8.2235 decode.loss_cls_ce: 1.7592 decode.loss_mask_ce: 0.8220 decode.loss_mask_dice: 1.5352 decode.d7.loss_cls_ce: 1.7416 decode.d7.loss_mask_ce: 0.8202 decode.d7.loss_mask_dice: 1.5454 2023/09/07 13:47:28 - mmengine - INFO - Iter(train) [14100/60000] base_lr: 7.6501e-05 lr: 7.6501e-05 eta: 12:33:03 time: 0.9846 data_time: 0.0216 memory: 29239 grad_norm: 23.2065 loss: 8.7747 decode.loss_cls_ce: 1.8651 decode.loss_mask_ce: 0.8300 decode.loss_mask_dice: 1.7083 decode.d7.loss_cls_ce: 1.8412 decode.d7.loss_mask_ce: 0.8326 decode.d7.loss_mask_dice: 1.6976 2023/09/07 13:48:17 - mmengine - INFO - Iter(train) [14150/60000] base_lr: 7.6418e-05 lr: 7.6418e-05 eta: 12:32:14 time: 0.9831 data_time: 0.0219 memory: 29140 grad_norm: 24.9939 loss: 7.6741 decode.loss_cls_ce: 1.5290 decode.loss_mask_ce: 0.8234 decode.loss_mask_dice: 1.4686 decode.d7.loss_cls_ce: 1.5334 decode.d7.loss_mask_ce: 0.8311 decode.d7.loss_mask_dice: 1.4886 2023/09/07 13:49:06 - mmengine - INFO - Iter(train) [14200/60000] base_lr: 7.6335e-05 lr: 7.6335e-05 eta: 12:31:25 time: 0.9821 data_time: 0.0223 memory: 29228 grad_norm: 19.2156 loss: 8.9161 decode.loss_cls_ce: 1.7952 decode.loss_mask_ce: 0.8688 decode.loss_mask_dice: 1.7761 decode.d7.loss_cls_ce: 1.7963 decode.d7.loss_mask_ce: 0.8755 decode.d7.loss_mask_dice: 1.8042 2023/09/07 13:49:55 - mmengine - INFO - Iter(train) [14250/60000] base_lr: 7.6251e-05 lr: 7.6251e-05 eta: 12:30:35 time: 0.9824 data_time: 0.0220 memory: 29164 grad_norm: 20.3299 loss: 8.1603 decode.loss_cls_ce: 1.6913 decode.loss_mask_ce: 0.8213 decode.loss_mask_dice: 1.5535 decode.d7.loss_cls_ce: 1.7039 decode.d7.loss_mask_ce: 0.8178 decode.d7.loss_mask_dice: 1.5725 2023/09/07 13:50:45 - mmengine - INFO - Iter(train) [14300/60000] base_lr: 7.6168e-05 lr: 7.6168e-05 eta: 12:29:46 time: 0.9838 data_time: 0.0218 memory: 29191 grad_norm: 21.2241 loss: 9.1459 decode.loss_cls_ce: 1.9558 decode.loss_mask_ce: 0.8506 decode.loss_mask_dice: 1.7770 decode.d7.loss_cls_ce: 1.9127 decode.d7.loss_mask_ce: 0.8637 decode.d7.loss_mask_dice: 1.7861 2023/09/07 13:51:34 - mmengine - INFO - Iter(train) [14350/60000] base_lr: 7.6085e-05 lr: 7.6085e-05 eta: 12:28:57 time: 0.9820 data_time: 0.0216 memory: 29179 grad_norm: 21.5951 loss: 8.8148 decode.loss_cls_ce: 1.7298 decode.loss_mask_ce: 0.8646 decode.loss_mask_dice: 1.7947 decode.d7.loss_cls_ce: 1.7497 decode.d7.loss_mask_ce: 0.8686 decode.d7.loss_mask_dice: 1.8074 2023/09/07 13:52:23 - mmengine - INFO - Iter(train) [14400/60000] base_lr: 7.6001e-05 lr: 7.6001e-05 eta: 12:28:07 time: 0.9834 data_time: 0.0221 memory: 29244 grad_norm: 21.9477 loss: 8.2445 decode.loss_cls_ce: 1.8050 decode.loss_mask_ce: 0.7905 decode.loss_mask_dice: 1.5363 decode.d7.loss_cls_ce: 1.7817 decode.d7.loss_mask_ce: 0.7933 decode.d7.loss_mask_dice: 1.5376 2023/09/07 13:53:12 - mmengine - INFO - Iter(train) [14450/60000] base_lr: 7.5918e-05 lr: 7.5918e-05 eta: 12:27:18 time: 0.9833 data_time: 0.0214 memory: 29189 grad_norm: 20.5012 loss: 9.0850 decode.loss_cls_ce: 1.8844 decode.loss_mask_ce: 0.8972 decode.loss_mask_dice: 1.7749 decode.d7.loss_cls_ce: 1.8665 decode.d7.loss_mask_ce: 0.8862 decode.d7.loss_mask_dice: 1.7758 2023/09/07 13:54:02 - mmengine - INFO - Iter(train) [14500/60000] base_lr: 7.5835e-05 lr: 7.5835e-05 eta: 12:26:29 time: 0.9819 data_time: 0.0224 memory: 29182 grad_norm: 23.6951 loss: 9.1030 decode.loss_cls_ce: 1.7703 decode.loss_mask_ce: 1.0028 decode.loss_mask_dice: 1.7535 decode.d7.loss_cls_ce: 1.7973 decode.d7.loss_mask_ce: 1.0145 decode.d7.loss_mask_dice: 1.7645 2023/09/07 13:54:51 - mmengine - INFO - Iter(train) [14550/60000] base_lr: 7.5751e-05 lr: 7.5751e-05 eta: 12:25:40 time: 0.9831 data_time: 0.0228 memory: 29140 grad_norm: 24.9467 loss: 8.4856 decode.loss_cls_ce: 1.8373 decode.loss_mask_ce: 0.8584 decode.loss_mask_dice: 1.5429 decode.d7.loss_cls_ce: 1.8308 decode.d7.loss_mask_ce: 0.8495 decode.d7.loss_mask_dice: 1.5667 2023/09/07 13:55:40 - mmengine - INFO - Iter(train) [14600/60000] base_lr: 7.5668e-05 lr: 7.5668e-05 eta: 12:24:51 time: 0.9867 data_time: 0.0213 memory: 29265 grad_norm: 22.2709 loss: 10.5537 decode.loss_cls_ce: 2.2421 decode.loss_mask_ce: 0.9844 decode.loss_mask_dice: 2.0549 decode.d7.loss_cls_ce: 2.2172 decode.d7.loss_mask_ce: 0.9817 decode.d7.loss_mask_dice: 2.0735 2023/09/07 13:56:29 - mmengine - INFO - Iter(train) [14650/60000] base_lr: 7.5585e-05 lr: 7.5585e-05 eta: 12:24:02 time: 0.9866 data_time: 0.0207 memory: 29392 grad_norm: 19.7602 loss: 8.3496 decode.loss_cls_ce: 1.8045 decode.loss_mask_ce: 0.8210 decode.loss_mask_dice: 1.5675 decode.d7.loss_cls_ce: 1.7721 decode.d7.loss_mask_ce: 0.8170 decode.d7.loss_mask_dice: 1.5675 2023/09/07 13:57:18 - mmengine - INFO - Iter(train) [14700/60000] base_lr: 7.5501e-05 lr: 7.5501e-05 eta: 12:23:12 time: 0.9860 data_time: 0.0213 memory: 29198 grad_norm: 21.1991 loss: 7.6529 decode.loss_cls_ce: 1.6379 decode.loss_mask_ce: 0.7934 decode.loss_mask_dice: 1.4219 decode.d7.loss_cls_ce: 1.5876 decode.d7.loss_mask_ce: 0.7970 decode.d7.loss_mask_dice: 1.4152 2023/09/07 13:58:08 - mmengine - INFO - Iter(train) [14750/60000] base_lr: 7.5418e-05 lr: 7.5418e-05 eta: 12:22:23 time: 0.9829 data_time: 0.0218 memory: 29129 grad_norm: 20.3042 loss: 8.7070 decode.loss_cls_ce: 1.9144 decode.loss_mask_ce: 0.8222 decode.loss_mask_dice: 1.6219 decode.d7.loss_cls_ce: 1.8942 decode.d7.loss_mask_ce: 0.8277 decode.d7.loss_mask_dice: 1.6266 2023/09/07 13:58:57 - mmengine - INFO - Iter(train) [14800/60000] base_lr: 7.5335e-05 lr: 7.5335e-05 eta: 12:21:34 time: 0.9875 data_time: 0.0220 memory: 29243 grad_norm: 23.2602 loss: 10.0877 decode.loss_cls_ce: 2.0832 decode.loss_mask_ce: 0.9168 decode.loss_mask_dice: 2.0447 decode.d7.loss_cls_ce: 2.0553 decode.d7.loss_mask_ce: 0.9218 decode.d7.loss_mask_dice: 2.0659 2023/09/07 13:59:46 - mmengine - INFO - Iter(train) [14850/60000] base_lr: 7.5251e-05 lr: 7.5251e-05 eta: 12:20:45 time: 0.9824 data_time: 0.0217 memory: 29368 grad_norm: 21.6789 loss: 8.1695 decode.loss_cls_ce: 1.7090 decode.loss_mask_ce: 0.7906 decode.loss_mask_dice: 1.6031 decode.d7.loss_cls_ce: 1.6593 decode.d7.loss_mask_ce: 0.7959 decode.d7.loss_mask_dice: 1.6116 2023/09/07 14:00:35 - mmengine - INFO - Iter(train) [14900/60000] base_lr: 7.5168e-05 lr: 7.5168e-05 eta: 12:19:55 time: 0.9838 data_time: 0.0219 memory: 29192 grad_norm: 24.8631 loss: 10.1041 decode.loss_cls_ce: 2.0945 decode.loss_mask_ce: 0.9399 decode.loss_mask_dice: 2.0212 decode.d7.loss_cls_ce: 2.0729 decode.d7.loss_mask_ce: 0.9449 decode.d7.loss_mask_dice: 2.0308 2023/09/07 14:01:25 - mmengine - INFO - Iter(train) [14950/60000] base_lr: 7.5085e-05 lr: 7.5085e-05 eta: 12:19:06 time: 0.9832 data_time: 0.0211 memory: 29226 grad_norm: 21.5145 loss: 8.8541 decode.loss_cls_ce: 2.0115 decode.loss_mask_ce: 0.8408 decode.loss_mask_dice: 1.5689 decode.d7.loss_cls_ce: 2.0073 decode.d7.loss_mask_ce: 0.8384 decode.d7.loss_mask_dice: 1.5873 2023/09/07 14:02:14 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 14:02:14 - mmengine - INFO - Iter(train) [15000/60000] base_lr: 7.5001e-05 lr: 7.5001e-05 eta: 12:18:17 time: 0.9852 data_time: 0.0213 memory: 29238 grad_norm: 23.3595 loss: 7.8839 decode.loss_cls_ce: 1.6720 decode.loss_mask_ce: 0.7927 decode.loss_mask_dice: 1.4748 decode.d7.loss_cls_ce: 1.6809 decode.d7.loss_mask_ce: 0.7883 decode.d7.loss_mask_dice: 1.4751 2023/09/07 14:03:03 - mmengine - INFO - Iter(train) [15050/60000] base_lr: 7.4918e-05 lr: 7.4918e-05 eta: 12:17:28 time: 0.9865 data_time: 0.0217 memory: 29155 grad_norm: 19.8898 loss: 7.2567 decode.loss_cls_ce: 1.6415 decode.loss_mask_ce: 0.6640 decode.loss_mask_dice: 1.3260 decode.d7.loss_cls_ce: 1.6513 decode.d7.loss_mask_ce: 0.6503 decode.d7.loss_mask_dice: 1.3237 2023/09/07 14:03:52 - mmengine - INFO - Iter(train) [15100/60000] base_lr: 7.4835e-05 lr: 7.4835e-05 eta: 12:16:39 time: 0.9861 data_time: 0.0213 memory: 29289 grad_norm: 23.3285 loss: 9.3683 decode.loss_cls_ce: 1.9423 decode.loss_mask_ce: 0.8210 decode.loss_mask_dice: 1.9063 decode.d7.loss_cls_ce: 1.9628 decode.d7.loss_mask_ce: 0.8211 decode.d7.loss_mask_dice: 1.9149 2023/09/07 14:04:42 - mmengine - INFO - Iter(train) [15150/60000] base_lr: 7.4751e-05 lr: 7.4751e-05 eta: 12:15:49 time: 0.9825 data_time: 0.0214 memory: 29141 grad_norm: 21.7060 loss: 9.5766 decode.loss_cls_ce: 2.0659 decode.loss_mask_ce: 0.8020 decode.loss_mask_dice: 1.9064 decode.d7.loss_cls_ce: 2.0651 decode.d7.loss_mask_ce: 0.8005 decode.d7.loss_mask_dice: 1.9366 2023/09/07 14:05:31 - mmengine - INFO - Iter(train) [15200/60000] base_lr: 7.4668e-05 lr: 7.4668e-05 eta: 12:15:00 time: 0.9852 data_time: 0.0216 memory: 29200 grad_norm: 25.3159 loss: 7.7245 decode.loss_cls_ce: 1.6007 decode.loss_mask_ce: 0.7620 decode.loss_mask_dice: 1.5114 decode.d7.loss_cls_ce: 1.5565 decode.d7.loss_mask_ce: 0.7714 decode.d7.loss_mask_dice: 1.5226 2023/09/07 14:06:20 - mmengine - INFO - Iter(train) [15250/60000] base_lr: 7.4585e-05 lr: 7.4585e-05 eta: 12:14:11 time: 0.9824 data_time: 0.0217 memory: 29176 grad_norm: 24.5916 loss: 9.4235 decode.loss_cls_ce: 1.9816 decode.loss_mask_ce: 0.8695 decode.loss_mask_dice: 1.8487 decode.d7.loss_cls_ce: 1.9936 decode.d7.loss_mask_ce: 0.8824 decode.d7.loss_mask_dice: 1.8477 2023/09/07 14:07:09 - mmengine - INFO - Iter(train) [15300/60000] base_lr: 7.4501e-05 lr: 7.4501e-05 eta: 12:13:22 time: 0.9833 data_time: 0.0219 memory: 29231 grad_norm: 20.9000 loss: 7.8278 decode.loss_cls_ce: 1.5935 decode.loss_mask_ce: 0.8056 decode.loss_mask_dice: 1.5181 decode.d7.loss_cls_ce: 1.5760 decode.d7.loss_mask_ce: 0.8181 decode.d7.loss_mask_dice: 1.5165 2023/09/07 14:07:58 - mmengine - INFO - Iter(train) [15350/60000] base_lr: 7.4418e-05 lr: 7.4418e-05 eta: 12:12:32 time: 0.9874 data_time: 0.0215 memory: 29213 grad_norm: 20.3143 loss: 6.9929 decode.loss_cls_ce: 1.4785 decode.loss_mask_ce: 0.7136 decode.loss_mask_dice: 1.3035 decode.d7.loss_cls_ce: 1.4810 decode.d7.loss_mask_ce: 0.7123 decode.d7.loss_mask_dice: 1.3039 2023/09/07 14:08:48 - mmengine - INFO - Iter(train) [15400/60000] base_lr: 7.4335e-05 lr: 7.4335e-05 eta: 12:11:43 time: 0.9863 data_time: 0.0213 memory: 29217 grad_norm: 21.9475 loss: 10.4148 decode.loss_cls_ce: 2.1425 decode.loss_mask_ce: 0.9400 decode.loss_mask_dice: 2.1169 decode.d7.loss_cls_ce: 2.1717 decode.d7.loss_mask_ce: 0.9549 decode.d7.loss_mask_dice: 2.0888 2023/09/07 14:09:37 - mmengine - INFO - Iter(train) [15450/60000] base_lr: 7.4251e-05 lr: 7.4251e-05 eta: 12:10:54 time: 0.9827 data_time: 0.0216 memory: 29267 grad_norm: 19.1543 loss: 8.1323 decode.loss_cls_ce: 1.6984 decode.loss_mask_ce: 0.8300 decode.loss_mask_dice: 1.5538 decode.d7.loss_cls_ce: 1.6977 decode.d7.loss_mask_ce: 0.8130 decode.d7.loss_mask_dice: 1.5393 2023/09/07 14:10:26 - mmengine - INFO - Iter(train) [15500/60000] base_lr: 7.4168e-05 lr: 7.4168e-05 eta: 12:10:05 time: 0.9838 data_time: 0.0223 memory: 29124 grad_norm: 19.5425 loss: 9.2450 decode.loss_cls_ce: 1.9633 decode.loss_mask_ce: 0.9590 decode.loss_mask_dice: 1.7067 decode.d7.loss_cls_ce: 1.9771 decode.d7.loss_mask_ce: 0.9522 decode.d7.loss_mask_dice: 1.6867 2023/09/07 14:11:15 - mmengine - INFO - Iter(train) [15550/60000] base_lr: 7.4085e-05 lr: 7.4085e-05 eta: 12:09:16 time: 0.9828 data_time: 0.0211 memory: 29218 grad_norm: 20.5086 loss: 7.8642 decode.loss_cls_ce: 1.7291 decode.loss_mask_ce: 0.7493 decode.loss_mask_dice: 1.4704 decode.d7.loss_cls_ce: 1.6918 decode.d7.loss_mask_ce: 0.7469 decode.d7.loss_mask_dice: 1.4767 2023/09/07 14:12:05 - mmengine - INFO - Iter(train) [15600/60000] base_lr: 7.4001e-05 lr: 7.4001e-05 eta: 12:08:27 time: 0.9876 data_time: 0.0222 memory: 29238 grad_norm: 19.4342 loss: 9.7397 decode.loss_cls_ce: 1.9504 decode.loss_mask_ce: 1.0129 decode.loss_mask_dice: 1.8917 decode.d7.loss_cls_ce: 1.9749 decode.d7.loss_mask_ce: 1.0189 decode.d7.loss_mask_dice: 1.8909 2023/09/07 14:12:54 - mmengine - INFO - Iter(train) [15650/60000] base_lr: 7.3918e-05 lr: 7.3918e-05 eta: 12:07:38 time: 0.9825 data_time: 0.0217 memory: 29100 grad_norm: 21.6282 loss: 9.1870 decode.loss_cls_ce: 2.0449 decode.loss_mask_ce: 0.8682 decode.loss_mask_dice: 1.6943 decode.d7.loss_cls_ce: 2.0240 decode.d7.loss_mask_ce: 0.8587 decode.d7.loss_mask_dice: 1.6968 2023/09/07 14:13:43 - mmengine - INFO - Iter(train) [15700/60000] base_lr: 7.3835e-05 lr: 7.3835e-05 eta: 12:06:48 time: 0.9832 data_time: 0.0221 memory: 29203 grad_norm: 22.5018 loss: 9.4582 decode.loss_cls_ce: 1.9541 decode.loss_mask_ce: 0.9599 decode.loss_mask_dice: 1.8239 decode.d7.loss_cls_ce: 1.9152 decode.d7.loss_mask_ce: 0.9700 decode.d7.loss_mask_dice: 1.8352 2023/09/07 14:14:32 - mmengine - INFO - Iter(train) [15750/60000] base_lr: 7.3751e-05 lr: 7.3751e-05 eta: 12:05:59 time: 0.9856 data_time: 0.0209 memory: 29212 grad_norm: 20.4538 loss: 9.3018 decode.loss_cls_ce: 1.8333 decode.loss_mask_ce: 0.8919 decode.loss_mask_dice: 1.9395 decode.d7.loss_cls_ce: 1.7988 decode.d7.loss_mask_ce: 0.8983 decode.d7.loss_mask_dice: 1.9398 2023/09/07 14:15:22 - mmengine - INFO - Iter(train) [15800/60000] base_lr: 7.3668e-05 lr: 7.3668e-05 eta: 12:05:10 time: 0.9889 data_time: 0.0214 memory: 29216 grad_norm: 21.9059 loss: 10.1209 decode.loss_cls_ce: 1.8999 decode.loss_mask_ce: 0.9592 decode.loss_mask_dice: 2.1826 decode.d7.loss_cls_ce: 1.9401 decode.d7.loss_mask_ce: 0.9475 decode.d7.loss_mask_dice: 2.1916 2023/09/07 14:16:11 - mmengine - INFO - Iter(train) [15850/60000] base_lr: 7.3585e-05 lr: 7.3585e-05 eta: 12:04:21 time: 0.9876 data_time: 0.0209 memory: 29253 grad_norm: 19.4055 loss: 9.6291 decode.loss_cls_ce: 1.9827 decode.loss_mask_ce: 0.8949 decode.loss_mask_dice: 1.9312 decode.d7.loss_cls_ce: 1.9915 decode.d7.loss_mask_ce: 0.8915 decode.d7.loss_mask_dice: 1.9372 2023/09/07 14:17:00 - mmengine - INFO - Iter(train) [15900/60000] base_lr: 7.3501e-05 lr: 7.3501e-05 eta: 12:03:32 time: 0.9854 data_time: 0.0212 memory: 29265 grad_norm: 21.3219 loss: 7.9232 decode.loss_cls_ce: 1.6938 decode.loss_mask_ce: 0.6993 decode.loss_mask_dice: 1.5522 decode.d7.loss_cls_ce: 1.7355 decode.d7.loss_mask_ce: 0.6910 decode.d7.loss_mask_dice: 1.5514 2023/09/07 14:17:50 - mmengine - INFO - Iter(train) [15950/60000] base_lr: 7.3418e-05 lr: 7.3418e-05 eta: 12:02:43 time: 0.9823 data_time: 0.0214 memory: 29231 grad_norm: 20.9790 loss: 7.3040 decode.loss_cls_ce: 1.5039 decode.loss_mask_ce: 0.7756 decode.loss_mask_dice: 1.3843 decode.d7.loss_cls_ce: 1.4780 decode.d7.loss_mask_ce: 0.7705 decode.d7.loss_mask_dice: 1.3917 2023/09/07 14:18:39 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 14:18:39 - mmengine - INFO - Iter(train) [16000/60000] base_lr: 7.3335e-05 lr: 7.3335e-05 eta: 12:01:54 time: 0.9836 data_time: 0.0216 memory: 29223 grad_norm: 19.0551 loss: 9.8580 decode.loss_cls_ce: 2.0309 decode.loss_mask_ce: 0.8863 decode.loss_mask_dice: 2.0183 decode.d7.loss_cls_ce: 2.0087 decode.d7.loss_mask_ce: 0.8795 decode.d7.loss_mask_dice: 2.0343 2023/09/07 14:19:28 - mmengine - INFO - Iter(train) [16050/60000] base_lr: 7.3251e-05 lr: 7.3251e-05 eta: 12:01:04 time: 0.9825 data_time: 0.0214 memory: 29126 grad_norm: 27.3137 loss: 9.0658 decode.loss_cls_ce: 1.9411 decode.loss_mask_ce: 0.8401 decode.loss_mask_dice: 1.7504 decode.d7.loss_cls_ce: 1.9246 decode.d7.loss_mask_ce: 0.8447 decode.d7.loss_mask_dice: 1.7649 2023/09/07 14:20:17 - mmengine - INFO - Iter(train) [16100/60000] base_lr: 7.3168e-05 lr: 7.3168e-05 eta: 12:00:15 time: 0.9861 data_time: 0.0207 memory: 29202 grad_norm: 21.6735 loss: 7.5840 decode.loss_cls_ce: 1.5065 decode.loss_mask_ce: 0.7466 decode.loss_mask_dice: 1.5317 decode.d7.loss_cls_ce: 1.5292 decode.d7.loss_mask_ce: 0.7396 decode.d7.loss_mask_dice: 1.5303 2023/09/07 14:21:06 - mmengine - INFO - Iter(train) [16150/60000] base_lr: 7.3085e-05 lr: 7.3085e-05 eta: 11:59:26 time: 0.9852 data_time: 0.0219 memory: 29152 grad_norm: 20.4611 loss: 8.9926 decode.loss_cls_ce: 1.7135 decode.loss_mask_ce: 0.9040 decode.loss_mask_dice: 1.8671 decode.d7.loss_cls_ce: 1.7583 decode.d7.loss_mask_ce: 0.8997 decode.d7.loss_mask_dice: 1.8499 2023/09/07 14:21:56 - mmengine - INFO - Iter(train) [16200/60000] base_lr: 7.3001e-05 lr: 7.3001e-05 eta: 11:58:37 time: 0.9819 data_time: 0.0216 memory: 29214 grad_norm: 19.0455 loss: 10.0493 decode.loss_cls_ce: 2.0121 decode.loss_mask_ce: 0.9931 decode.loss_mask_dice: 2.0306 decode.d7.loss_cls_ce: 1.9900 decode.d7.loss_mask_ce: 0.9985 decode.d7.loss_mask_dice: 2.0250 2023/09/07 14:22:45 - mmengine - INFO - Iter(train) [16250/60000] base_lr: 7.2918e-05 lr: 7.2918e-05 eta: 11:57:47 time: 0.9841 data_time: 0.0220 memory: 29205 grad_norm: 18.5568 loss: 7.5221 decode.loss_cls_ce: 1.5415 decode.loss_mask_ce: 0.7562 decode.loss_mask_dice: 1.4486 decode.d7.loss_cls_ce: 1.5810 decode.d7.loss_mask_ce: 0.7545 decode.d7.loss_mask_dice: 1.4404 2023/09/07 14:23:34 - mmengine - INFO - Iter(train) [16300/60000] base_lr: 7.2835e-05 lr: 7.2835e-05 eta: 11:56:58 time: 0.9831 data_time: 0.0218 memory: 29128 grad_norm: 21.7468 loss: 8.7570 decode.loss_cls_ce: 1.8794 decode.loss_mask_ce: 0.8929 decode.loss_mask_dice: 1.5909 decode.d7.loss_cls_ce: 1.9119 decode.d7.loss_mask_ce: 0.8885 decode.d7.loss_mask_dice: 1.5934 2023/09/07 14:24:23 - mmengine - INFO - Iter(train) [16350/60000] base_lr: 7.2751e-05 lr: 7.2751e-05 eta: 11:56:09 time: 0.9837 data_time: 0.0215 memory: 29084 grad_norm: 20.4081 loss: 8.8023 decode.loss_cls_ce: 1.8257 decode.loss_mask_ce: 0.8788 decode.loss_mask_dice: 1.6831 decode.d7.loss_cls_ce: 1.8376 decode.d7.loss_mask_ce: 0.8830 decode.d7.loss_mask_dice: 1.6941 2023/09/07 14:25:13 - mmengine - INFO - Iter(train) [16400/60000] base_lr: 7.2668e-05 lr: 7.2668e-05 eta: 11:55:20 time: 0.9836 data_time: 0.0213 memory: 29305 grad_norm: 21.2494 loss: 7.2724 decode.loss_cls_ce: 1.4805 decode.loss_mask_ce: 0.6575 decode.loss_mask_dice: 1.5237 decode.d7.loss_cls_ce: 1.4045 decode.d7.loss_mask_ce: 0.6769 decode.d7.loss_mask_dice: 1.5293 2023/09/07 14:26:02 - mmengine - INFO - Iter(train) [16450/60000] base_lr: 7.2585e-05 lr: 7.2585e-05 eta: 11:54:31 time: 0.9836 data_time: 0.0220 memory: 29173 grad_norm: 23.1952 loss: 8.2003 decode.loss_cls_ce: 1.7235 decode.loss_mask_ce: 0.9287 decode.loss_mask_dice: 1.4531 decode.d7.loss_cls_ce: 1.7290 decode.d7.loss_mask_ce: 0.9348 decode.d7.loss_mask_dice: 1.4311 2023/09/07 14:26:51 - mmengine - INFO - Iter(train) [16500/60000] base_lr: 7.2501e-05 lr: 7.2501e-05 eta: 11:53:41 time: 0.9827 data_time: 0.0223 memory: 29190 grad_norm: 20.3081 loss: 9.0321 decode.loss_cls_ce: 1.9029 decode.loss_mask_ce: 0.8492 decode.loss_mask_dice: 1.7326 decode.d7.loss_cls_ce: 1.9347 decode.d7.loss_mask_ce: 0.8559 decode.d7.loss_mask_dice: 1.7568 2023/09/07 14:27:40 - mmengine - INFO - Iter(train) [16550/60000] base_lr: 7.2418e-05 lr: 7.2418e-05 eta: 11:52:52 time: 0.9837 data_time: 0.0219 memory: 29141 grad_norm: 20.3605 loss: 8.1046 decode.loss_cls_ce: 1.7406 decode.loss_mask_ce: 0.8081 decode.loss_mask_dice: 1.4959 decode.d7.loss_cls_ce: 1.7636 decode.d7.loss_mask_ce: 0.8126 decode.d7.loss_mask_dice: 1.4836 2023/09/07 14:28:29 - mmengine - INFO - Iter(train) [16600/60000] base_lr: 7.2335e-05 lr: 7.2335e-05 eta: 11:52:03 time: 0.9861 data_time: 0.0251 memory: 29129 grad_norm: 19.6900 loss: 8.5000 decode.loss_cls_ce: 1.8142 decode.loss_mask_ce: 0.7797 decode.loss_mask_dice: 1.6270 decode.d7.loss_cls_ce: 1.8642 decode.d7.loss_mask_ce: 0.7745 decode.d7.loss_mask_dice: 1.6405 2023/09/07 14:29:19 - mmengine - INFO - Iter(train) [16650/60000] base_lr: 7.2251e-05 lr: 7.2251e-05 eta: 11:51:14 time: 0.9851 data_time: 0.0224 memory: 29149 grad_norm: 31.6959 loss: 8.0520 decode.loss_cls_ce: 1.8247 decode.loss_mask_ce: 0.7196 decode.loss_mask_dice: 1.5035 decode.d7.loss_cls_ce: 1.7805 decode.d7.loss_mask_ce: 0.7183 decode.d7.loss_mask_dice: 1.5053 2023/09/07 14:30:08 - mmengine - INFO - Iter(train) [16700/60000] base_lr: 7.2168e-05 lr: 7.2168e-05 eta: 11:50:24 time: 0.9842 data_time: 0.0217 memory: 29230 grad_norm: 23.9966 loss: 9.3654 decode.loss_cls_ce: 1.8076 decode.loss_mask_ce: 0.9091 decode.loss_mask_dice: 1.9518 decode.d7.loss_cls_ce: 1.8513 decode.d7.loss_mask_ce: 0.9014 decode.d7.loss_mask_dice: 1.9443 2023/09/07 14:30:57 - mmengine - INFO - Iter(train) [16750/60000] base_lr: 7.2085e-05 lr: 7.2085e-05 eta: 11:49:35 time: 0.9870 data_time: 0.0215 memory: 29204 grad_norm: 18.1806 loss: 8.5270 decode.loss_cls_ce: 1.5696 decode.loss_mask_ce: 0.8586 decode.loss_mask_dice: 1.7889 decode.d7.loss_cls_ce: 1.6484 decode.d7.loss_mask_ce: 0.8681 decode.d7.loss_mask_dice: 1.7933 2023/09/07 14:31:46 - mmengine - INFO - Iter(train) [16800/60000] base_lr: 7.2001e-05 lr: 7.2001e-05 eta: 11:48:46 time: 0.9846 data_time: 0.0225 memory: 29168 grad_norm: 19.5114 loss: 8.3885 decode.loss_cls_ce: 1.9348 decode.loss_mask_ce: 0.7635 decode.loss_mask_dice: 1.5012 decode.d7.loss_cls_ce: 1.9167 decode.d7.loss_mask_ce: 0.7676 decode.d7.loss_mask_dice: 1.5047 2023/09/07 14:32:35 - mmengine - INFO - Iter(train) [16850/60000] base_lr: 7.1918e-05 lr: 7.1918e-05 eta: 11:47:57 time: 0.9839 data_time: 0.0219 memory: 29331 grad_norm: 19.7957 loss: 9.0774 decode.loss_cls_ce: 1.8477 decode.loss_mask_ce: 0.8430 decode.loss_mask_dice: 1.8639 decode.d7.loss_cls_ce: 1.8034 decode.d7.loss_mask_ce: 0.8639 decode.d7.loss_mask_dice: 1.8555 2023/09/07 14:33:25 - mmengine - INFO - Iter(train) [16900/60000] base_lr: 7.1835e-05 lr: 7.1835e-05 eta: 11:47:07 time: 0.9868 data_time: 0.0215 memory: 29263 grad_norm: 20.4129 loss: 9.4790 decode.loss_cls_ce: 1.8964 decode.loss_mask_ce: 0.9194 decode.loss_mask_dice: 1.9178 decode.d7.loss_cls_ce: 1.9086 decode.d7.loss_mask_ce: 0.9192 decode.d7.loss_mask_dice: 1.9176 2023/09/07 14:34:14 - mmengine - INFO - Iter(train) [16950/60000] base_lr: 7.1751e-05 lr: 7.1751e-05 eta: 11:46:18 time: 0.9853 data_time: 0.0215 memory: 29115 grad_norm: 20.0082 loss: 8.8152 decode.loss_cls_ce: 1.9075 decode.loss_mask_ce: 0.8621 decode.loss_mask_dice: 1.6336 decode.d7.loss_cls_ce: 1.9282 decode.d7.loss_mask_ce: 0.8449 decode.d7.loss_mask_dice: 1.6389 2023/09/07 14:35:03 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 14:35:03 - mmengine - INFO - Iter(train) [17000/60000] base_lr: 7.1668e-05 lr: 7.1668e-05 eta: 11:45:29 time: 0.9859 data_time: 0.0217 memory: 29384 grad_norm: 19.4001 loss: 8.2978 decode.loss_cls_ce: 1.8819 decode.loss_mask_ce: 0.8844 decode.loss_mask_dice: 1.3994 decode.d7.loss_cls_ce: 1.8327 decode.d7.loss_mask_ce: 0.8972 decode.d7.loss_mask_dice: 1.4023 2023/09/07 14:35:52 - mmengine - INFO - Iter(train) [17050/60000] base_lr: 7.1585e-05 lr: 7.1585e-05 eta: 11:44:40 time: 0.9864 data_time: 0.0219 memory: 29250 grad_norm: 22.9866 loss: 9.1366 decode.loss_cls_ce: 1.8535 decode.loss_mask_ce: 0.8160 decode.loss_mask_dice: 1.8924 decode.d7.loss_cls_ce: 1.8655 decode.d7.loss_mask_ce: 0.8162 decode.d7.loss_mask_dice: 1.8928 2023/09/07 14:36:42 - mmengine - INFO - Iter(train) [17100/60000] base_lr: 7.1501e-05 lr: 7.1501e-05 eta: 11:43:51 time: 0.9844 data_time: 0.0223 memory: 29239 grad_norm: 21.0723 loss: 8.2892 decode.loss_cls_ce: 1.5751 decode.loss_mask_ce: 0.9016 decode.loss_mask_dice: 1.6570 decode.d7.loss_cls_ce: 1.6027 decode.d7.loss_mask_ce: 0.9021 decode.d7.loss_mask_dice: 1.6507 2023/09/07 14:37:31 - mmengine - INFO - Iter(train) [17150/60000] base_lr: 7.1418e-05 lr: 7.1418e-05 eta: 11:43:02 time: 0.9833 data_time: 0.0225 memory: 29163 grad_norm: 19.5450 loss: 10.2497 decode.loss_cls_ce: 2.0143 decode.loss_mask_ce: 1.0541 decode.loss_mask_dice: 2.0368 decode.d7.loss_cls_ce: 2.0254 decode.d7.loss_mask_ce: 1.0511 decode.d7.loss_mask_dice: 2.0681 2023/09/07 14:38:20 - mmengine - INFO - Iter(train) [17200/60000] base_lr: 7.1335e-05 lr: 7.1335e-05 eta: 11:42:12 time: 0.9854 data_time: 0.0217 memory: 29202 grad_norm: 19.8540 loss: 9.1077 decode.loss_cls_ce: 1.8901 decode.loss_mask_ce: 0.8701 decode.loss_mask_dice: 1.8083 decode.d7.loss_cls_ce: 1.8955 decode.d7.loss_mask_ce: 0.8576 decode.d7.loss_mask_dice: 1.7860 2023/09/07 14:39:09 - mmengine - INFO - Iter(train) [17250/60000] base_lr: 7.1251e-05 lr: 7.1251e-05 eta: 11:41:23 time: 0.9866 data_time: 0.0215 memory: 29160 grad_norm: 21.2676 loss: 8.3475 decode.loss_cls_ce: 1.7231 decode.loss_mask_ce: 0.8620 decode.loss_mask_dice: 1.6076 decode.d7.loss_cls_ce: 1.7250 decode.d7.loss_mask_ce: 0.8612 decode.d7.loss_mask_dice: 1.5686 2023/09/07 14:39:59 - mmengine - INFO - Iter(train) [17300/60000] base_lr: 7.1168e-05 lr: 7.1168e-05 eta: 11:40:34 time: 0.9838 data_time: 0.0219 memory: 29278 grad_norm: 25.0045 loss: 8.9640 decode.loss_cls_ce: 1.8582 decode.loss_mask_ce: 0.8395 decode.loss_mask_dice: 1.7605 decode.d7.loss_cls_ce: 1.9166 decode.d7.loss_mask_ce: 0.8338 decode.d7.loss_mask_dice: 1.7554 2023/09/07 14:40:48 - mmengine - INFO - Iter(train) [17350/60000] base_lr: 7.1085e-05 lr: 7.1085e-05 eta: 11:39:45 time: 0.9841 data_time: 0.0219 memory: 29109 grad_norm: 23.9198 loss: 8.1967 decode.loss_cls_ce: 1.6633 decode.loss_mask_ce: 0.8570 decode.loss_mask_dice: 1.5678 decode.d7.loss_cls_ce: 1.6689 decode.d7.loss_mask_ce: 0.8656 decode.d7.loss_mask_dice: 1.5742 2023/09/07 14:41:37 - mmengine - INFO - Iter(train) [17400/60000] base_lr: 7.1001e-05 lr: 7.1001e-05 eta: 11:38:56 time: 0.9846 data_time: 0.0222 memory: 29280 grad_norm: 21.4986 loss: 9.1378 decode.loss_cls_ce: 1.9912 decode.loss_mask_ce: 0.8800 decode.loss_mask_dice: 1.6806 decode.d7.loss_cls_ce: 2.0441 decode.d7.loss_mask_ce: 0.8624 decode.d7.loss_mask_dice: 1.6795 2023/09/07 14:42:26 - mmengine - INFO - Iter(train) [17450/60000] base_lr: 7.0918e-05 lr: 7.0918e-05 eta: 11:38:06 time: 0.9851 data_time: 0.0219 memory: 29217 grad_norm: 22.9447 loss: 9.4837 decode.loss_cls_ce: 2.0065 decode.loss_mask_ce: 0.8406 decode.loss_mask_dice: 1.8687 decode.d7.loss_cls_ce: 2.0702 decode.d7.loss_mask_ce: 0.8213 decode.d7.loss_mask_dice: 1.8765 2023/09/07 14:43:16 - mmengine - INFO - Iter(train) [17500/60000] base_lr: 7.0835e-05 lr: 7.0835e-05 eta: 11:37:17 time: 0.9847 data_time: 0.0220 memory: 29162 grad_norm: 21.3979 loss: 8.6032 decode.loss_cls_ce: 1.7990 decode.loss_mask_ce: 0.9784 decode.loss_mask_dice: 1.5148 decode.d7.loss_cls_ce: 1.8000 decode.d7.loss_mask_ce: 0.9840 decode.d7.loss_mask_dice: 1.5271 2023/09/07 14:44:05 - mmengine - INFO - Iter(train) [17550/60000] base_lr: 7.0751e-05 lr: 7.0751e-05 eta: 11:36:28 time: 0.9831 data_time: 0.0218 memory: 29202 grad_norm: 19.5334 loss: 8.2096 decode.loss_cls_ce: 1.8051 decode.loss_mask_ce: 0.8419 decode.loss_mask_dice: 1.4608 decode.d7.loss_cls_ce: 1.7869 decode.d7.loss_mask_ce: 0.8487 decode.d7.loss_mask_dice: 1.4663 2023/09/07 14:44:54 - mmengine - INFO - Iter(train) [17600/60000] base_lr: 7.0668e-05 lr: 7.0668e-05 eta: 11:35:39 time: 0.9833 data_time: 0.0225 memory: 29263 grad_norm: 21.9568 loss: 7.8864 decode.loss_cls_ce: 1.7713 decode.loss_mask_ce: 0.8358 decode.loss_mask_dice: 1.3339 decode.d7.loss_cls_ce: 1.7809 decode.d7.loss_mask_ce: 0.8283 decode.d7.loss_mask_dice: 1.3362 2023/09/07 14:45:43 - mmengine - INFO - Iter(train) [17650/60000] base_lr: 7.0585e-05 lr: 7.0585e-05 eta: 11:34:49 time: 0.9840 data_time: 0.0214 memory: 29163 grad_norm: 22.0181 loss: 8.9263 decode.loss_cls_ce: 1.8920 decode.loss_mask_ce: 0.8989 decode.loss_mask_dice: 1.6869 decode.d7.loss_cls_ce: 1.8593 decode.d7.loss_mask_ce: 0.9032 decode.d7.loss_mask_dice: 1.6860 2023/09/07 14:46:33 - mmengine - INFO - Iter(train) [17700/60000] base_lr: 7.0501e-05 lr: 7.0501e-05 eta: 11:34:01 time: 0.9879 data_time: 0.0213 memory: 29292 grad_norm: 21.7020 loss: 8.9362 decode.loss_cls_ce: 1.7548 decode.loss_mask_ce: 1.0295 decode.loss_mask_dice: 1.6864 decode.d7.loss_cls_ce: 1.7618 decode.d7.loss_mask_ce: 1.0088 decode.d7.loss_mask_dice: 1.6949 2023/09/07 14:47:22 - mmengine - INFO - Iter(train) [17750/60000] base_lr: 7.0418e-05 lr: 7.0418e-05 eta: 11:33:12 time: 0.9847 data_time: 0.0220 memory: 29358 grad_norm: 21.6361 loss: 9.6762 decode.loss_cls_ce: 1.9811 decode.loss_mask_ce: 0.8309 decode.loss_mask_dice: 2.0274 decode.d7.loss_cls_ce: 1.9857 decode.d7.loss_mask_ce: 0.8307 decode.d7.loss_mask_dice: 2.0204 2023/09/07 14:48:11 - mmengine - INFO - Iter(train) [17800/60000] base_lr: 7.0335e-05 lr: 7.0335e-05 eta: 11:32:23 time: 0.9850 data_time: 0.0218 memory: 29099 grad_norm: 21.0303 loss: 9.3626 decode.loss_cls_ce: 2.1108 decode.loss_mask_ce: 0.8265 decode.loss_mask_dice: 1.7484 decode.d7.loss_cls_ce: 2.0807 decode.d7.loss_mask_ce: 0.8280 decode.d7.loss_mask_dice: 1.7682 2023/09/07 14:49:01 - mmengine - INFO - Iter(train) [17850/60000] base_lr: 7.0251e-05 lr: 7.0251e-05 eta: 11:31:33 time: 0.9857 data_time: 0.0217 memory: 29175 grad_norm: 19.4160 loss: 9.3080 decode.loss_cls_ce: 1.8792 decode.loss_mask_ce: 0.8717 decode.loss_mask_dice: 1.8918 decode.d7.loss_cls_ce: 1.8954 decode.d7.loss_mask_ce: 0.8751 decode.d7.loss_mask_dice: 1.8949 2023/09/07 14:49:50 - mmengine - INFO - Iter(train) [17900/60000] base_lr: 7.0168e-05 lr: 7.0168e-05 eta: 11:30:44 time: 0.9827 data_time: 0.0209 memory: 29255 grad_norm: 20.0263 loss: 9.9747 decode.loss_cls_ce: 1.9479 decode.loss_mask_ce: 0.9522 decode.loss_mask_dice: 2.0815 decode.d7.loss_cls_ce: 1.9611 decode.d7.loss_mask_ce: 0.9527 decode.d7.loss_mask_dice: 2.0793 2023/09/07 14:50:39 - mmengine - INFO - Iter(train) [17950/60000] base_lr: 7.0085e-05 lr: 7.0085e-05 eta: 11:29:55 time: 0.9857 data_time: 0.0218 memory: 29153 grad_norm: 19.7813 loss: 8.3260 decode.loss_cls_ce: 1.8539 decode.loss_mask_ce: 0.7664 decode.loss_mask_dice: 1.5563 decode.d7.loss_cls_ce: 1.8313 decode.d7.loss_mask_ce: 0.7679 decode.d7.loss_mask_dice: 1.5502 2023/09/07 14:51:28 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 14:51:28 - mmengine - INFO - Iter(train) [18000/60000] base_lr: 7.0001e-05 lr: 7.0001e-05 eta: 11:29:06 time: 0.9850 data_time: 0.0215 memory: 29149 grad_norm: 23.3815 loss: 9.6346 decode.loss_cls_ce: 2.0066 decode.loss_mask_ce: 0.9056 decode.loss_mask_dice: 1.9055 decode.d7.loss_cls_ce: 1.9991 decode.d7.loss_mask_ce: 0.8954 decode.d7.loss_mask_dice: 1.9225 2023/09/07 14:52:17 - mmengine - INFO - Iter(train) [18050/60000] base_lr: 6.9918e-05 lr: 6.9918e-05 eta: 11:28:17 time: 0.9824 data_time: 0.0215 memory: 29213 grad_norm: 25.8431 loss: 8.0832 decode.loss_cls_ce: 1.7289 decode.loss_mask_ce: 0.7359 decode.loss_mask_dice: 1.5896 decode.d7.loss_cls_ce: 1.7038 decode.d7.loss_mask_ce: 0.7421 decode.d7.loss_mask_dice: 1.5828 2023/09/07 14:53:07 - mmengine - INFO - Iter(train) [18100/60000] base_lr: 6.9834e-05 lr: 6.9834e-05 eta: 11:27:27 time: 0.9844 data_time: 0.0222 memory: 29127 grad_norm: 21.6550 loss: 9.0743 decode.loss_cls_ce: 1.8701 decode.loss_mask_ce: 0.8624 decode.loss_mask_dice: 1.7944 decode.d7.loss_cls_ce: 1.9004 decode.d7.loss_mask_ce: 0.8620 decode.d7.loss_mask_dice: 1.7849 2023/09/07 14:53:56 - mmengine - INFO - Iter(train) [18150/60000] base_lr: 6.9751e-05 lr: 6.9751e-05 eta: 11:26:38 time: 0.9860 data_time: 0.0214 memory: 29195 grad_norm: 22.6469 loss: 8.1715 decode.loss_cls_ce: 1.7557 decode.loss_mask_ce: 0.7900 decode.loss_mask_dice: 1.5180 decode.d7.loss_cls_ce: 1.7837 decode.d7.loss_mask_ce: 0.7883 decode.d7.loss_mask_dice: 1.5358 2023/09/07 14:54:45 - mmengine - INFO - Iter(train) [18200/60000] base_lr: 6.9668e-05 lr: 6.9668e-05 eta: 11:25:49 time: 0.9848 data_time: 0.0217 memory: 29345 grad_norm: 22.2857 loss: 9.6619 decode.loss_cls_ce: 2.0362 decode.loss_mask_ce: 0.8820 decode.loss_mask_dice: 1.8939 decode.d7.loss_cls_ce: 2.0694 decode.d7.loss_mask_ce: 0.8890 decode.d7.loss_mask_dice: 1.8915 2023/09/07 14:55:34 - mmengine - INFO - Iter(train) [18250/60000] base_lr: 6.9584e-05 lr: 6.9584e-05 eta: 11:25:00 time: 0.9828 data_time: 0.0216 memory: 29176 grad_norm: 19.4787 loss: 8.3773 decode.loss_cls_ce: 1.7674 decode.loss_mask_ce: 0.8756 decode.loss_mask_dice: 1.5731 decode.d7.loss_cls_ce: 1.7376 decode.d7.loss_mask_ce: 0.8697 decode.d7.loss_mask_dice: 1.5539 2023/09/07 14:56:24 - mmengine - INFO - Iter(train) [18300/60000] base_lr: 6.9501e-05 lr: 6.9501e-05 eta: 11:24:10 time: 0.9849 data_time: 0.0221 memory: 29188 grad_norm: 20.3345 loss: 8.1101 decode.loss_cls_ce: 1.6562 decode.loss_mask_ce: 0.8136 decode.loss_mask_dice: 1.5890 decode.d7.loss_cls_ce: 1.6598 decode.d7.loss_mask_ce: 0.8129 decode.d7.loss_mask_dice: 1.5786 2023/09/07 14:57:13 - mmengine - INFO - Iter(train) [18350/60000] base_lr: 6.9418e-05 lr: 6.9418e-05 eta: 11:23:21 time: 0.9846 data_time: 0.0218 memory: 29190 grad_norm: 21.6205 loss: 8.2600 decode.loss_cls_ce: 1.8269 decode.loss_mask_ce: 0.7167 decode.loss_mask_dice: 1.5921 decode.d7.loss_cls_ce: 1.8409 decode.d7.loss_mask_ce: 0.7083 decode.d7.loss_mask_dice: 1.5751 2023/09/07 14:58:02 - mmengine - INFO - Iter(train) [18400/60000] base_lr: 6.9334e-05 lr: 6.9334e-05 eta: 11:22:32 time: 0.9854 data_time: 0.0222 memory: 29190 grad_norm: 22.1734 loss: 8.2365 decode.loss_cls_ce: 1.7509 decode.loss_mask_ce: 0.8576 decode.loss_mask_dice: 1.5032 decode.d7.loss_cls_ce: 1.7523 decode.d7.loss_mask_ce: 0.8635 decode.d7.loss_mask_dice: 1.5090 2023/09/07 14:58:51 - mmengine - INFO - Iter(train) [18450/60000] base_lr: 6.9251e-05 lr: 6.9251e-05 eta: 11:21:43 time: 0.9837 data_time: 0.0223 memory: 29282 grad_norm: 21.4970 loss: 8.8284 decode.loss_cls_ce: 1.8516 decode.loss_mask_ce: 0.8720 decode.loss_mask_dice: 1.6830 decode.d7.loss_cls_ce: 1.8663 decode.d7.loss_mask_ce: 0.8753 decode.d7.loss_mask_dice: 1.6802 2023/09/07 14:59:41 - mmengine - INFO - Iter(train) [18500/60000] base_lr: 6.9168e-05 lr: 6.9168e-05 eta: 11:20:54 time: 0.9848 data_time: 0.0216 memory: 29242 grad_norm: 20.6259 loss: 9.5474 decode.loss_cls_ce: 2.0513 decode.loss_mask_ce: 0.8244 decode.loss_mask_dice: 1.9020 decode.d7.loss_cls_ce: 2.0187 decode.d7.loss_mask_ce: 0.8297 decode.d7.loss_mask_dice: 1.9213 2023/09/07 15:00:30 - mmengine - INFO - Iter(train) [18550/60000] base_lr: 6.9084e-05 lr: 6.9084e-05 eta: 11:20:05 time: 0.9860 data_time: 0.0213 memory: 29187 grad_norm: 22.4428 loss: 8.0710 decode.loss_cls_ce: 1.7568 decode.loss_mask_ce: 0.7394 decode.loss_mask_dice: 1.5035 decode.d7.loss_cls_ce: 1.8076 decode.d7.loss_mask_ce: 0.7519 decode.d7.loss_mask_dice: 1.5117 2023/09/07 15:01:19 - mmengine - INFO - Iter(train) [18600/60000] base_lr: 6.9001e-05 lr: 6.9001e-05 eta: 11:19:15 time: 0.9856 data_time: 0.0215 memory: 29095 grad_norm: 24.7544 loss: 6.8923 decode.loss_cls_ce: 1.2232 decode.loss_mask_ce: 0.8305 decode.loss_mask_dice: 1.3690 decode.d7.loss_cls_ce: 1.2720 decode.d7.loss_mask_ce: 0.8215 decode.d7.loss_mask_dice: 1.3761 2023/09/07 15:02:08 - mmengine - INFO - Iter(train) [18650/60000] base_lr: 6.8918e-05 lr: 6.8918e-05 eta: 11:18:26 time: 0.9836 data_time: 0.0222 memory: 29294 grad_norm: 23.0105 loss: 8.2639 decode.loss_cls_ce: 1.7686 decode.loss_mask_ce: 0.8321 decode.loss_mask_dice: 1.5140 decode.d7.loss_cls_ce: 1.7964 decode.d7.loss_mask_ce: 0.8359 decode.d7.loss_mask_dice: 1.5169 2023/09/07 15:02:58 - mmengine - INFO - Iter(train) [18700/60000] base_lr: 6.8834e-05 lr: 6.8834e-05 eta: 11:17:37 time: 0.9862 data_time: 0.0221 memory: 29195 grad_norm: 23.7107 loss: 9.7235 decode.loss_cls_ce: 1.9206 decode.loss_mask_ce: 0.9717 decode.loss_mask_dice: 1.9895 decode.d7.loss_cls_ce: 1.8757 decode.d7.loss_mask_ce: 0.9722 decode.d7.loss_mask_dice: 1.9937 2023/09/07 15:03:47 - mmengine - INFO - Iter(train) [18750/60000] base_lr: 6.8751e-05 lr: 6.8751e-05 eta: 11:16:48 time: 0.9848 data_time: 0.0216 memory: 29153 grad_norm: 21.1479 loss: 8.1185 decode.loss_cls_ce: 1.6367 decode.loss_mask_ce: 0.8626 decode.loss_mask_dice: 1.5651 decode.d7.loss_cls_ce: 1.6380 decode.d7.loss_mask_ce: 0.8518 decode.d7.loss_mask_dice: 1.5643 2023/09/07 15:04:36 - mmengine - INFO - Iter(train) [18800/60000] base_lr: 6.8668e-05 lr: 6.8668e-05 eta: 11:15:59 time: 0.9863 data_time: 0.0216 memory: 29251 grad_norm: 20.0777 loss: 9.9868 decode.loss_cls_ce: 2.0736 decode.loss_mask_ce: 1.0018 decode.loss_mask_dice: 1.9482 decode.d7.loss_cls_ce: 2.0378 decode.d7.loss_mask_ce: 1.0048 decode.d7.loss_mask_dice: 1.9207 2023/09/07 15:05:25 - mmengine - INFO - Iter(train) [18850/60000] base_lr: 6.8584e-05 lr: 6.8584e-05 eta: 11:15:09 time: 0.9853 data_time: 0.0212 memory: 29101 grad_norm: 21.0388 loss: 9.2719 decode.loss_cls_ce: 1.7575 decode.loss_mask_ce: 0.9059 decode.loss_mask_dice: 1.9515 decode.d7.loss_cls_ce: 1.8057 decode.d7.loss_mask_ce: 0.8978 decode.d7.loss_mask_dice: 1.9536 2023/09/07 15:06:15 - mmengine - INFO - Iter(train) [18900/60000] base_lr: 6.8501e-05 lr: 6.8501e-05 eta: 11:14:20 time: 0.9877 data_time: 0.0215 memory: 29087 grad_norm: 20.0111 loss: 8.4460 decode.loss_cls_ce: 1.5859 decode.loss_mask_ce: 0.9029 decode.loss_mask_dice: 1.7152 decode.d7.loss_cls_ce: 1.5903 decode.d7.loss_mask_ce: 0.9176 decode.d7.loss_mask_dice: 1.7343 2023/09/07 15:07:04 - mmengine - INFO - Iter(train) [18950/60000] base_lr: 6.8418e-05 lr: 6.8418e-05 eta: 11:13:31 time: 0.9892 data_time: 0.0217 memory: 29168 grad_norm: 21.8615 loss: 8.8907 decode.loss_cls_ce: 1.7404 decode.loss_mask_ce: 0.9119 decode.loss_mask_dice: 1.7802 decode.d7.loss_cls_ce: 1.7777 decode.d7.loss_mask_ce: 0.9010 decode.d7.loss_mask_dice: 1.7795 2023/09/07 15:07:53 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 15:07:53 - mmengine - INFO - Iter(train) [19000/60000] base_lr: 6.8334e-05 lr: 6.8334e-05 eta: 11:12:42 time: 0.9827 data_time: 0.0217 memory: 29202 grad_norm: 21.0241 loss: 8.7989 decode.loss_cls_ce: 1.8127 decode.loss_mask_ce: 0.8546 decode.loss_mask_dice: 1.7266 decode.d7.loss_cls_ce: 1.8492 decode.d7.loss_mask_ce: 0.8373 decode.d7.loss_mask_dice: 1.7186 2023/09/07 15:08:42 - mmengine - INFO - Iter(train) [19050/60000] base_lr: 6.8251e-05 lr: 6.8251e-05 eta: 11:11:53 time: 0.9832 data_time: 0.0214 memory: 29191 grad_norm: 20.1885 loss: 7.8964 decode.loss_cls_ce: 1.6071 decode.loss_mask_ce: 0.8347 decode.loss_mask_dice: 1.5093 decode.d7.loss_cls_ce: 1.6124 decode.d7.loss_mask_ce: 0.8400 decode.d7.loss_mask_dice: 1.4929 2023/09/07 15:09:32 - mmengine - INFO - Iter(train) [19100/60000] base_lr: 6.8168e-05 lr: 6.8168e-05 eta: 11:11:03 time: 0.9871 data_time: 0.0220 memory: 29203 grad_norm: 20.4080 loss: 9.2204 decode.loss_cls_ce: 1.9228 decode.loss_mask_ce: 0.9626 decode.loss_mask_dice: 1.7233 decode.d7.loss_cls_ce: 1.9220 decode.d7.loss_mask_ce: 0.9716 decode.d7.loss_mask_dice: 1.7181 2023/09/07 15:10:21 - mmengine - INFO - Iter(train) [19150/60000] base_lr: 6.8084e-05 lr: 6.8084e-05 eta: 11:10:14 time: 0.9863 data_time: 0.0218 memory: 29216 grad_norm: 21.9234 loss: 7.5266 decode.loss_cls_ce: 1.4239 decode.loss_mask_ce: 0.8281 decode.loss_mask_dice: 1.5056 decode.d7.loss_cls_ce: 1.4457 decode.d7.loss_mask_ce: 0.8248 decode.d7.loss_mask_dice: 1.4984 2023/09/07 15:11:10 - mmengine - INFO - Iter(train) [19200/60000] base_lr: 6.8001e-05 lr: 6.8001e-05 eta: 11:09:25 time: 0.9832 data_time: 0.0219 memory: 29154 grad_norm: 21.1886 loss: 8.2105 decode.loss_cls_ce: 1.7277 decode.loss_mask_ce: 0.7782 decode.loss_mask_dice: 1.6085 decode.d7.loss_cls_ce: 1.7025 decode.d7.loss_mask_ce: 0.7801 decode.d7.loss_mask_dice: 1.6135 2023/09/07 15:11:59 - mmengine - INFO - Iter(train) [19250/60000] base_lr: 6.7918e-05 lr: 6.7918e-05 eta: 11:08:36 time: 0.9859 data_time: 0.0221 memory: 29181 grad_norm: 20.6767 loss: 8.6314 decode.loss_cls_ce: 1.8161 decode.loss_mask_ce: 0.8664 decode.loss_mask_dice: 1.6466 decode.d7.loss_cls_ce: 1.8075 decode.d7.loss_mask_ce: 0.8620 decode.d7.loss_mask_dice: 1.6327 2023/09/07 15:12:49 - mmengine - INFO - Iter(train) [19300/60000] base_lr: 6.7834e-05 lr: 6.7834e-05 eta: 11:07:47 time: 0.9874 data_time: 0.0214 memory: 29164 grad_norm: 20.1751 loss: 9.1596 decode.loss_cls_ce: 1.8311 decode.loss_mask_ce: 0.9703 decode.loss_mask_dice: 1.7497 decode.d7.loss_cls_ce: 1.8643 decode.d7.loss_mask_ce: 0.9829 decode.d7.loss_mask_dice: 1.7614 2023/09/07 15:13:38 - mmengine - INFO - Iter(train) [19350/60000] base_lr: 6.7751e-05 lr: 6.7751e-05 eta: 11:06:58 time: 0.9859 data_time: 0.0222 memory: 29254 grad_norm: 23.7940 loss: 9.5991 decode.loss_cls_ce: 1.9598 decode.loss_mask_ce: 0.9023 decode.loss_mask_dice: 1.9438 decode.d7.loss_cls_ce: 1.9074 decode.d7.loss_mask_ce: 0.9115 decode.d7.loss_mask_dice: 1.9742 2023/09/07 15:14:27 - mmengine - INFO - Iter(train) [19400/60000] base_lr: 6.7668e-05 lr: 6.7668e-05 eta: 11:06:08 time: 0.9829 data_time: 0.0223 memory: 29208 grad_norm: 18.5998 loss: 8.0452 decode.loss_cls_ce: 1.8213 decode.loss_mask_ce: 0.8145 decode.loss_mask_dice: 1.3733 decode.d7.loss_cls_ce: 1.8464 decode.d7.loss_mask_ce: 0.8189 decode.d7.loss_mask_dice: 1.3707 2023/09/07 15:15:16 - mmengine - INFO - Iter(train) [19450/60000] base_lr: 6.7584e-05 lr: 6.7584e-05 eta: 11:05:19 time: 0.9859 data_time: 0.0217 memory: 29370 grad_norm: 21.6771 loss: 9.4746 decode.loss_cls_ce: 1.8414 decode.loss_mask_ce: 1.0629 decode.loss_mask_dice: 1.8101 decode.d7.loss_cls_ce: 1.8690 decode.d7.loss_mask_ce: 1.0560 decode.d7.loss_mask_dice: 1.8353 2023/09/07 15:16:06 - mmengine - INFO - Iter(train) [19500/60000] base_lr: 6.7501e-05 lr: 6.7501e-05 eta: 11:04:30 time: 0.9853 data_time: 0.0217 memory: 29239 grad_norm: 20.9992 loss: 7.7240 decode.loss_cls_ce: 1.5098 decode.loss_mask_ce: 0.7571 decode.loss_mask_dice: 1.5890 decode.d7.loss_cls_ce: 1.5176 decode.d7.loss_mask_ce: 0.7678 decode.d7.loss_mask_dice: 1.5827 2023/09/07 15:16:55 - mmengine - INFO - Iter(train) [19550/60000] base_lr: 6.7418e-05 lr: 6.7418e-05 eta: 11:03:41 time: 0.9860 data_time: 0.0217 memory: 29219 grad_norm: 18.1750 loss: 7.9674 decode.loss_cls_ce: 1.7662 decode.loss_mask_ce: 0.7674 decode.loss_mask_dice: 1.4656 decode.d7.loss_cls_ce: 1.7429 decode.d7.loss_mask_ce: 0.7567 decode.d7.loss_mask_dice: 1.4686 2023/09/07 15:17:44 - mmengine - INFO - Iter(train) [19600/60000] base_lr: 6.7334e-05 lr: 6.7334e-05 eta: 11:02:52 time: 0.9840 data_time: 0.0215 memory: 29125 grad_norm: 20.3492 loss: 8.8691 decode.loss_cls_ce: 1.8464 decode.loss_mask_ce: 0.8945 decode.loss_mask_dice: 1.6877 decode.d7.loss_cls_ce: 1.8340 decode.d7.loss_mask_ce: 0.9119 decode.d7.loss_mask_dice: 1.6946 2023/09/07 15:18:33 - mmengine - INFO - Iter(train) [19650/60000] base_lr: 6.7251e-05 lr: 6.7251e-05 eta: 11:02:02 time: 0.9848 data_time: 0.0218 memory: 29281 grad_norm: 21.6025 loss: 7.3097 decode.loss_cls_ce: 1.5544 decode.loss_mask_ce: 0.8396 decode.loss_mask_dice: 1.2548 decode.d7.loss_cls_ce: 1.5587 decode.d7.loss_mask_ce: 0.8422 decode.d7.loss_mask_dice: 1.2599 2023/09/07 15:19:22 - mmengine - INFO - Iter(train) [19700/60000] base_lr: 6.7168e-05 lr: 6.7168e-05 eta: 11:01:13 time: 0.9839 data_time: 0.0215 memory: 29195 grad_norm: 19.1740 loss: 8.9951 decode.loss_cls_ce: 1.7898 decode.loss_mask_ce: 0.8865 decode.loss_mask_dice: 1.8137 decode.d7.loss_cls_ce: 1.7831 decode.d7.loss_mask_ce: 0.8946 decode.d7.loss_mask_dice: 1.8275 2023/09/07 15:20:12 - mmengine - INFO - Iter(train) [19750/60000] base_lr: 6.7084e-05 lr: 6.7084e-05 eta: 11:00:24 time: 0.9864 data_time: 0.0215 memory: 29229 grad_norm: 20.9416 loss: 9.1888 decode.loss_cls_ce: 1.9708 decode.loss_mask_ce: 0.8567 decode.loss_mask_dice: 1.7840 decode.d7.loss_cls_ce: 1.9526 decode.d7.loss_mask_ce: 0.8531 decode.d7.loss_mask_dice: 1.7717 2023/09/07 15:21:01 - mmengine - INFO - Iter(train) [19800/60000] base_lr: 6.7001e-05 lr: 6.7001e-05 eta: 10:59:35 time: 0.9834 data_time: 0.0222 memory: 29243 grad_norm: 20.4313 loss: 8.9084 decode.loss_cls_ce: 1.8294 decode.loss_mask_ce: 0.8899 decode.loss_mask_dice: 1.7490 decode.d7.loss_cls_ce: 1.8155 decode.d7.loss_mask_ce: 0.8854 decode.d7.loss_mask_dice: 1.7393 2023/09/07 15:21:50 - mmengine - INFO - Iter(train) [19850/60000] base_lr: 6.6918e-05 lr: 6.6918e-05 eta: 10:58:45 time: 0.9852 data_time: 0.0221 memory: 29264 grad_norm: 24.2461 loss: 9.1889 decode.loss_cls_ce: 1.7773 decode.loss_mask_ce: 0.9902 decode.loss_mask_dice: 1.8054 decode.d7.loss_cls_ce: 1.8351 decode.d7.loss_mask_ce: 0.9761 decode.d7.loss_mask_dice: 1.8050 2023/09/07 15:22:39 - mmengine - INFO - Iter(train) [19900/60000] base_lr: 6.6834e-05 lr: 6.6834e-05 eta: 10:57:56 time: 0.9831 data_time: 0.0217 memory: 29253 grad_norm: 19.7126 loss: 9.5440 decode.loss_cls_ce: 2.0535 decode.loss_mask_ce: 0.9279 decode.loss_mask_dice: 1.8009 decode.d7.loss_cls_ce: 2.0239 decode.d7.loss_mask_ce: 0.9318 decode.d7.loss_mask_dice: 1.8061 2023/09/07 15:23:29 - mmengine - INFO - Iter(train) [19950/60000] base_lr: 6.6751e-05 lr: 6.6751e-05 eta: 10:57:07 time: 0.9829 data_time: 0.0219 memory: 29243 grad_norm: 20.3478 loss: 8.8107 decode.loss_cls_ce: 1.7621 decode.loss_mask_ce: 0.8620 decode.loss_mask_dice: 1.7873 decode.d7.loss_cls_ce: 1.7626 decode.d7.loss_mask_ce: 0.8507 decode.d7.loss_mask_dice: 1.7860 2023/09/07 15:24:18 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 15:24:18 - mmengine - INFO - Iter(train) [20000/60000] base_lr: 6.6668e-05 lr: 6.6668e-05 eta: 10:56:18 time: 0.9844 data_time: 0.0212 memory: 29238 grad_norm: 22.4377 loss: 8.7980 decode.loss_cls_ce: 1.7046 decode.loss_mask_ce: 0.8715 decode.loss_mask_dice: 1.7799 decode.d7.loss_cls_ce: 1.7295 decode.d7.loss_mask_ce: 0.8851 decode.d7.loss_mask_dice: 1.8273 2023/09/07 15:24:18 - mmengine - INFO - Saving checkpoint at 20000 iterations 2023/09/07 15:25:14 - mmengine - INFO - Iter(train) [20050/60000] base_lr: 6.6584e-05 lr: 6.6584e-05 eta: 10:55:42 time: 0.9824 data_time: 0.0212 memory: 29278 grad_norm: 20.0215 loss: 9.4028 decode.loss_cls_ce: 1.9885 decode.loss_mask_ce: 0.8361 decode.loss_mask_dice: 1.8616 decode.d7.loss_cls_ce: 2.0208 decode.d7.loss_mask_ce: 0.8316 decode.d7.loss_mask_dice: 1.8642 2023/09/07 15:26:03 - mmengine - INFO - Iter(train) [20100/60000] base_lr: 6.6501e-05 lr: 6.6501e-05 eta: 10:54:53 time: 0.9856 data_time: 0.0217 memory: 29176 grad_norm: 21.0513 loss: 8.1499 decode.loss_cls_ce: 1.7489 decode.loss_mask_ce: 0.8415 decode.loss_mask_dice: 1.4988 decode.d7.loss_cls_ce: 1.7312 decode.d7.loss_mask_ce: 0.8370 decode.d7.loss_mask_dice: 1.4925 2023/09/07 15:26:53 - mmengine - INFO - Iter(train) [20150/60000] base_lr: 6.6418e-05 lr: 6.6418e-05 eta: 10:54:04 time: 0.9845 data_time: 0.0217 memory: 29215 grad_norm: 17.4870 loss: 8.9867 decode.loss_cls_ce: 1.8345 decode.loss_mask_ce: 0.9057 decode.loss_mask_dice: 1.7474 decode.d7.loss_cls_ce: 1.8416 decode.d7.loss_mask_ce: 0.9014 decode.d7.loss_mask_dice: 1.7562 2023/09/07 15:27:42 - mmengine - INFO - Iter(train) [20200/60000] base_lr: 6.6334e-05 lr: 6.6334e-05 eta: 10:53:15 time: 0.9880 data_time: 0.0215 memory: 29194 grad_norm: 19.3099 loss: 7.6699 decode.loss_cls_ce: 1.5927 decode.loss_mask_ce: 0.8091 decode.loss_mask_dice: 1.4359 decode.d7.loss_cls_ce: 1.5815 decode.d7.loss_mask_ce: 0.8147 decode.d7.loss_mask_dice: 1.4358 2023/09/07 15:28:31 - mmengine - INFO - Iter(train) [20250/60000] base_lr: 6.6251e-05 lr: 6.6251e-05 eta: 10:52:26 time: 0.9830 data_time: 0.0216 memory: 29166 grad_norm: 17.8337 loss: 7.3716 decode.loss_cls_ce: 1.6606 decode.loss_mask_ce: 0.7480 decode.loss_mask_dice: 1.2769 decode.d7.loss_cls_ce: 1.6522 decode.d7.loss_mask_ce: 0.7581 decode.d7.loss_mask_dice: 1.2758 2023/09/07 15:29:20 - mmengine - INFO - Iter(train) [20300/60000] base_lr: 6.6168e-05 lr: 6.6168e-05 eta: 10:51:36 time: 0.9883 data_time: 0.0215 memory: 29288 grad_norm: 17.1803 loss: 9.0195 decode.loss_cls_ce: 1.8072 decode.loss_mask_ce: 0.8961 decode.loss_mask_dice: 1.8348 decode.d7.loss_cls_ce: 1.7700 decode.d7.loss_mask_ce: 0.8724 decode.d7.loss_mask_dice: 1.8389 2023/09/07 15:30:10 - mmengine - INFO - Iter(train) [20350/60000] base_lr: 6.6084e-05 lr: 6.6084e-05 eta: 10:50:47 time: 0.9834 data_time: 0.0216 memory: 29148 grad_norm: 20.7428 loss: 8.2502 decode.loss_cls_ce: 1.7162 decode.loss_mask_ce: 0.8366 decode.loss_mask_dice: 1.5689 decode.d7.loss_cls_ce: 1.6886 decode.d7.loss_mask_ce: 0.8474 decode.d7.loss_mask_dice: 1.5926 2023/09/07 15:30:59 - mmengine - INFO - Iter(train) [20400/60000] base_lr: 6.6001e-05 lr: 6.6001e-05 eta: 10:49:58 time: 0.9833 data_time: 0.0216 memory: 29251 grad_norm: 20.7968 loss: 8.6151 decode.loss_cls_ce: 1.7069 decode.loss_mask_ce: 0.8849 decode.loss_mask_dice: 1.7304 decode.d7.loss_cls_ce: 1.6882 decode.d7.loss_mask_ce: 0.8788 decode.d7.loss_mask_dice: 1.7258 2023/09/07 15:31:48 - mmengine - INFO - Iter(train) [20450/60000] base_lr: 6.5918e-05 lr: 6.5918e-05 eta: 10:49:09 time: 0.9850 data_time: 0.0219 memory: 29219 grad_norm: 19.9734 loss: 9.3063 decode.loss_cls_ce: 1.7542 decode.loss_mask_ce: 0.9667 decode.loss_mask_dice: 1.9353 decode.d7.loss_cls_ce: 1.7415 decode.d7.loss_mask_ce: 0.9623 decode.d7.loss_mask_dice: 1.9464 2023/09/07 15:32:37 - mmengine - INFO - Iter(train) [20500/60000] base_lr: 6.5834e-05 lr: 6.5834e-05 eta: 10:48:20 time: 0.9886 data_time: 0.0213 memory: 29191 grad_norm: 24.7073 loss: 8.2171 decode.loss_cls_ce: 1.6619 decode.loss_mask_ce: 0.7980 decode.loss_mask_dice: 1.6499 decode.d7.loss_cls_ce: 1.6667 decode.d7.loss_mask_ce: 0.7925 decode.d7.loss_mask_dice: 1.6481 2023/09/07 15:33:27 - mmengine - INFO - Iter(train) [20550/60000] base_lr: 6.5751e-05 lr: 6.5751e-05 eta: 10:47:30 time: 0.9834 data_time: 0.0220 memory: 29385 grad_norm: 19.8334 loss: 7.8335 decode.loss_cls_ce: 1.5093 decode.loss_mask_ce: 0.8221 decode.loss_mask_dice: 1.5722 decode.d7.loss_cls_ce: 1.5403 decode.d7.loss_mask_ce: 0.8120 decode.d7.loss_mask_dice: 1.5776 2023/09/07 15:34:16 - mmengine - INFO - Iter(train) [20600/60000] base_lr: 6.5668e-05 lr: 6.5668e-05 eta: 10:46:41 time: 0.9826 data_time: 0.0216 memory: 29230 grad_norm: 18.7531 loss: 8.2627 decode.loss_cls_ce: 1.7002 decode.loss_mask_ce: 0.7808 decode.loss_mask_dice: 1.6685 decode.d7.loss_cls_ce: 1.6801 decode.d7.loss_mask_ce: 0.7825 decode.d7.loss_mask_dice: 1.6506 2023/09/07 15:35:05 - mmengine - INFO - Iter(train) [20650/60000] base_lr: 6.5584e-05 lr: 6.5584e-05 eta: 10:45:52 time: 0.9861 data_time: 0.0220 memory: 29140 grad_norm: 22.7600 loss: 10.8735 decode.loss_cls_ce: 2.0800 decode.loss_mask_ce: 1.0918 decode.loss_mask_dice: 2.2674 decode.d7.loss_cls_ce: 2.0847 decode.d7.loss_mask_ce: 1.0949 decode.d7.loss_mask_dice: 2.2547 2023/09/07 15:35:55 - mmengine - INFO - Iter(train) [20700/60000] base_lr: 6.5501e-05 lr: 6.5501e-05 eta: 10:45:03 time: 0.9839 data_time: 0.0215 memory: 29214 grad_norm: 19.8474 loss: 8.7327 decode.loss_cls_ce: 1.7358 decode.loss_mask_ce: 0.8780 decode.loss_mask_dice: 1.7511 decode.d7.loss_cls_ce: 1.7492 decode.d7.loss_mask_ce: 0.8732 decode.d7.loss_mask_dice: 1.7454 2023/09/07 15:36:44 - mmengine - INFO - Iter(train) [20750/60000] base_lr: 6.5418e-05 lr: 6.5418e-05 eta: 10:44:14 time: 0.9868 data_time: 0.0216 memory: 29255 grad_norm: 20.4916 loss: 6.6736 decode.loss_cls_ce: 1.3006 decode.loss_mask_ce: 0.7520 decode.loss_mask_dice: 1.2912 decode.d7.loss_cls_ce: 1.3038 decode.d7.loss_mask_ce: 0.7511 decode.d7.loss_mask_dice: 1.2749 2023/09/07 15:37:33 - mmengine - INFO - Iter(train) [20800/60000] base_lr: 6.5334e-05 lr: 6.5334e-05 eta: 10:43:24 time: 0.9840 data_time: 0.0216 memory: 29127 grad_norm: nan loss: 11.0236 decode.loss_cls_ce: 2.1738 decode.loss_mask_ce: 1.1448 decode.loss_mask_dice: 2.1755 decode.d7.loss_cls_ce: 2.2012 decode.d7.loss_mask_ce: 1.1636 decode.d7.loss_mask_dice: 2.1646 2023/09/07 15:38:22 - mmengine - INFO - Iter(train) [20850/60000] base_lr: 6.5251e-05 lr: 6.5251e-05 eta: 10:42:35 time: 0.9881 data_time: 0.0213 memory: 29320 grad_norm: 24.1006 loss: 8.3112 decode.loss_cls_ce: 1.6314 decode.loss_mask_ce: 0.8390 decode.loss_mask_dice: 1.6905 decode.d7.loss_cls_ce: 1.6448 decode.d7.loss_mask_ce: 0.8260 decode.d7.loss_mask_dice: 1.6794 2023/09/07 15:39:12 - mmengine - INFO - Iter(train) [20900/60000] base_lr: 6.5168e-05 lr: 6.5168e-05 eta: 10:41:46 time: 0.9879 data_time: 0.0217 memory: 29201 grad_norm: 21.8982 loss: 9.2150 decode.loss_cls_ce: 1.6717 decode.loss_mask_ce: 0.9793 decode.loss_mask_dice: 1.9404 decode.d7.loss_cls_ce: 1.7173 decode.d7.loss_mask_ce: 0.9812 decode.d7.loss_mask_dice: 1.9250 2023/09/07 15:40:01 - mmengine - INFO - Iter(train) [20950/60000] base_lr: 6.5084e-05 lr: 6.5084e-05 eta: 10:40:57 time: 0.9851 data_time: 0.0215 memory: 29229 grad_norm: 22.5147 loss: 9.0384 decode.loss_cls_ce: 1.6958 decode.loss_mask_ce: 0.9521 decode.loss_mask_dice: 1.8646 decode.d7.loss_cls_ce: 1.7024 decode.d7.loss_mask_ce: 0.9624 decode.d7.loss_mask_dice: 1.8610 2023/09/07 15:40:50 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 15:40:50 - mmengine - INFO - Iter(train) [21000/60000] base_lr: 6.5001e-05 lr: 6.5001e-05 eta: 10:40:08 time: 0.9839 data_time: 0.0216 memory: 29271 grad_norm: 19.8960 loss: 7.9064 decode.loss_cls_ce: 1.5771 decode.loss_mask_ce: 0.8192 decode.loss_mask_dice: 1.5264 decode.d7.loss_cls_ce: 1.6245 decode.d7.loss_mask_ce: 0.8188 decode.d7.loss_mask_dice: 1.5404 2023/09/07 15:41:39 - mmengine - INFO - Iter(train) [21050/60000] base_lr: 6.4918e-05 lr: 6.4918e-05 eta: 10:39:18 time: 0.9840 data_time: 0.0217 memory: 29357 grad_norm: 19.7821 loss: 9.7857 decode.loss_cls_ce: 2.0748 decode.loss_mask_ce: 0.8899 decode.loss_mask_dice: 1.9132 decode.d7.loss_cls_ce: 2.0933 decode.d7.loss_mask_ce: 0.8793 decode.d7.loss_mask_dice: 1.9352 2023/09/07 15:42:29 - mmengine - INFO - Iter(train) [21100/60000] base_lr: 6.4834e-05 lr: 6.4834e-05 eta: 10:38:29 time: 0.9869 data_time: 0.0215 memory: 29188 grad_norm: 20.0563 loss: 8.7226 decode.loss_cls_ce: 1.7459 decode.loss_mask_ce: 0.8806 decode.loss_mask_dice: 1.7464 decode.d7.loss_cls_ce: 1.7626 decode.d7.loss_mask_ce: 0.8671 decode.d7.loss_mask_dice: 1.7199 2023/09/07 15:43:18 - mmengine - INFO - Iter(train) [21150/60000] base_lr: 6.4751e-05 lr: 6.4751e-05 eta: 10:37:40 time: 0.9830 data_time: 0.0218 memory: 29210 grad_norm: 20.3530 loss: 9.3937 decode.loss_cls_ce: 1.8470 decode.loss_mask_ce: 0.8748 decode.loss_mask_dice: 1.9727 decode.d7.loss_cls_ce: 1.8512 decode.d7.loss_mask_ce: 0.8779 decode.d7.loss_mask_dice: 1.9700 2023/09/07 15:44:07 - mmengine - INFO - Iter(train) [21200/60000] base_lr: 6.4668e-05 lr: 6.4668e-05 eta: 10:36:51 time: 0.9867 data_time: 0.0216 memory: 29164 grad_norm: 20.9152 loss: 8.6946 decode.loss_cls_ce: 1.6021 decode.loss_mask_ce: 0.9395 decode.loss_mask_dice: 1.8033 decode.d7.loss_cls_ce: 1.6134 decode.d7.loss_mask_ce: 0.9301 decode.d7.loss_mask_dice: 1.8062 2023/09/07 15:44:56 - mmengine - INFO - Iter(train) [21250/60000] base_lr: 6.4584e-05 lr: 6.4584e-05 eta: 10:36:01 time: 0.9849 data_time: 0.0223 memory: 29203 grad_norm: 19.3518 loss: 7.9812 decode.loss_cls_ce: 1.6626 decode.loss_mask_ce: 0.8307 decode.loss_mask_dice: 1.5181 decode.d7.loss_cls_ce: 1.6352 decode.d7.loss_mask_ce: 0.8288 decode.d7.loss_mask_dice: 1.5058 2023/09/07 15:45:46 - mmengine - INFO - Iter(train) [21300/60000] base_lr: 6.4501e-05 lr: 6.4501e-05 eta: 10:35:12 time: 0.9858 data_time: 0.0219 memory: 29242 grad_norm: 19.5773 loss: 8.4122 decode.loss_cls_ce: 1.8444 decode.loss_mask_ce: 0.8292 decode.loss_mask_dice: 1.5099 decode.d7.loss_cls_ce: 1.8913 decode.d7.loss_mask_ce: 0.8226 decode.d7.loss_mask_dice: 1.5148 2023/09/07 15:46:35 - mmengine - INFO - Iter(train) [21350/60000] base_lr: 6.4418e-05 lr: 6.4418e-05 eta: 10:34:23 time: 0.9853 data_time: 0.0224 memory: 29092 grad_norm: 20.0872 loss: 8.7467 decode.loss_cls_ce: 1.7945 decode.loss_mask_ce: 0.9635 decode.loss_mask_dice: 1.6242 decode.d7.loss_cls_ce: 1.7480 decode.d7.loss_mask_ce: 0.9838 decode.d7.loss_mask_dice: 1.6326 2023/09/07 15:47:24 - mmengine - INFO - Iter(train) [21400/60000] base_lr: 6.4334e-05 lr: 6.4334e-05 eta: 10:33:34 time: 0.9860 data_time: 0.0217 memory: 29241 grad_norm: 20.7984 loss: 9.0112 decode.loss_cls_ce: 1.7480 decode.loss_mask_ce: 1.0110 decode.loss_mask_dice: 1.7497 decode.d7.loss_cls_ce: 1.7490 decode.d7.loss_mask_ce: 1.0113 decode.d7.loss_mask_dice: 1.7422 2023/09/07 15:48:14 - mmengine - INFO - Iter(train) [21450/60000] base_lr: 6.4251e-05 lr: 6.4251e-05 eta: 10:32:45 time: 0.9875 data_time: 0.0218 memory: 29168 grad_norm: 20.3971 loss: 8.9526 decode.loss_cls_ce: 1.7797 decode.loss_mask_ce: 0.8656 decode.loss_mask_dice: 1.8258 decode.d7.loss_cls_ce: 1.7864 decode.d7.loss_mask_ce: 0.8755 decode.d7.loss_mask_dice: 1.8196 2023/09/07 15:49:03 - mmengine - INFO - Iter(train) [21500/60000] base_lr: 6.4168e-05 lr: 6.4168e-05 eta: 10:31:55 time: 0.9843 data_time: 0.0212 memory: 29204 grad_norm: 20.5899 loss: 6.5969 decode.loss_cls_ce: 1.4704 decode.loss_mask_ce: 0.6500 decode.loss_mask_dice: 1.1708 decode.d7.loss_cls_ce: 1.4784 decode.d7.loss_mask_ce: 0.6452 decode.d7.loss_mask_dice: 1.1820 2023/09/07 15:49:52 - mmengine - INFO - Iter(train) [21550/60000] base_lr: 6.4084e-05 lr: 6.4084e-05 eta: 10:31:06 time: 0.9872 data_time: 0.0212 memory: 29319 grad_norm: 20.4217 loss: 7.9290 decode.loss_cls_ce: 1.5581 decode.loss_mask_ce: 0.8039 decode.loss_mask_dice: 1.6018 decode.d7.loss_cls_ce: 1.5662 decode.d7.loss_mask_ce: 0.8000 decode.d7.loss_mask_dice: 1.5990 2023/09/07 15:50:41 - mmengine - INFO - Iter(train) [21600/60000] base_lr: 6.4001e-05 lr: 6.4001e-05 eta: 10:30:17 time: 0.9863 data_time: 0.0220 memory: 29148 grad_norm: 22.5257 loss: 9.4411 decode.loss_cls_ce: 1.8933 decode.loss_mask_ce: 0.9428 decode.loss_mask_dice: 1.8987 decode.d7.loss_cls_ce: 1.8744 decode.d7.loss_mask_ce: 0.9410 decode.d7.loss_mask_dice: 1.8909 2023/09/07 15:51:31 - mmengine - INFO - Iter(train) [21650/60000] base_lr: 6.3918e-05 lr: 6.3918e-05 eta: 10:29:28 time: 0.9855 data_time: 0.0225 memory: 29203 grad_norm: 21.4717 loss: 9.0820 decode.loss_cls_ce: 1.9133 decode.loss_mask_ce: 0.8980 decode.loss_mask_dice: 1.7372 decode.d7.loss_cls_ce: 1.9234 decode.d7.loss_mask_ce: 0.8941 decode.d7.loss_mask_dice: 1.7158 2023/09/07 15:52:20 - mmengine - INFO - Iter(train) [21700/60000] base_lr: 6.3834e-05 lr: 6.3834e-05 eta: 10:28:39 time: 0.9871 data_time: 0.0217 memory: 29393 grad_norm: 20.3569 loss: 9.1423 decode.loss_cls_ce: 1.9291 decode.loss_mask_ce: 0.9452 decode.loss_mask_dice: 1.7085 decode.d7.loss_cls_ce: 1.9275 decode.d7.loss_mask_ce: 0.9321 decode.d7.loss_mask_dice: 1.6999 2023/09/07 15:53:09 - mmengine - INFO - Iter(train) [21750/60000] base_lr: 6.3751e-05 lr: 6.3751e-05 eta: 10:27:50 time: 0.9875 data_time: 0.0215 memory: 29205 grad_norm: 19.9405 loss: 8.9976 decode.loss_cls_ce: 1.7527 decode.loss_mask_ce: 0.9015 decode.loss_mask_dice: 1.8521 decode.d7.loss_cls_ce: 1.7366 decode.d7.loss_mask_ce: 0.9067 decode.d7.loss_mask_dice: 1.8480 2023/09/07 15:53:59 - mmengine - INFO - Iter(train) [21800/60000] base_lr: 6.3668e-05 lr: 6.3668e-05 eta: 10:27:00 time: 0.9876 data_time: 0.0217 memory: 29149 grad_norm: 19.8243 loss: 7.1601 decode.loss_cls_ce: 1.5314 decode.loss_mask_ce: 0.7481 decode.loss_mask_dice: 1.3092 decode.d7.loss_cls_ce: 1.5346 decode.d7.loss_mask_ce: 0.7511 decode.d7.loss_mask_dice: 1.2857 2023/09/07 15:54:48 - mmengine - INFO - Iter(train) [21850/60000] base_lr: 6.3584e-05 lr: 6.3584e-05 eta: 10:26:11 time: 0.9870 data_time: 0.0216 memory: 29254 grad_norm: 17.9783 loss: 9.6368 decode.loss_cls_ce: 1.8791 decode.loss_mask_ce: 0.9734 decode.loss_mask_dice: 1.9385 decode.d7.loss_cls_ce: 1.9213 decode.d7.loss_mask_ce: 0.9629 decode.d7.loss_mask_dice: 1.9617 2023/09/07 15:55:37 - mmengine - INFO - Iter(train) [21900/60000] base_lr: 6.3501e-05 lr: 6.3501e-05 eta: 10:25:22 time: 0.9842 data_time: 0.0217 memory: 29180 grad_norm: 19.5295 loss: 10.4275 decode.loss_cls_ce: 2.0754 decode.loss_mask_ce: 1.0234 decode.loss_mask_dice: 2.1231 decode.d7.loss_cls_ce: 2.1001 decode.d7.loss_mask_ce: 1.0179 decode.d7.loss_mask_dice: 2.0876 2023/09/07 15:56:26 - mmengine - INFO - Iter(train) [21950/60000] base_lr: 6.3418e-05 lr: 6.3418e-05 eta: 10:24:33 time: 0.9877 data_time: 0.0221 memory: 29167 grad_norm: 20.9615 loss: 8.6088 decode.loss_cls_ce: 1.8634 decode.loss_mask_ce: 0.8604 decode.loss_mask_dice: 1.5929 decode.d7.loss_cls_ce: 1.8239 decode.d7.loss_mask_ce: 0.8587 decode.d7.loss_mask_dice: 1.6095 2023/09/07 15:57:16 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 15:57:16 - mmengine - INFO - Iter(train) [22000/60000] base_lr: 6.3334e-05 lr: 6.3334e-05 eta: 10:23:44 time: 0.9873 data_time: 0.0213 memory: 29228 grad_norm: 17.8946 loss: 8.2332 decode.loss_cls_ce: 1.7623 decode.loss_mask_ce: 0.7590 decode.loss_mask_dice: 1.5979 decode.d7.loss_cls_ce: 1.7594 decode.d7.loss_mask_ce: 0.7524 decode.d7.loss_mask_dice: 1.6022 2023/09/07 15:58:05 - mmengine - INFO - Iter(train) [22050/60000] base_lr: 6.3251e-05 lr: 6.3251e-05 eta: 10:22:55 time: 0.9822 data_time: 0.0226 memory: 29206 grad_norm: 18.1052 loss: 7.8875 decode.loss_cls_ce: 1.5197 decode.loss_mask_ce: 0.8594 decode.loss_mask_dice: 1.5581 decode.d7.loss_cls_ce: 1.5164 decode.d7.loss_mask_ce: 0.8650 decode.d7.loss_mask_dice: 1.5690 2023/09/07 15:58:54 - mmengine - INFO - Iter(train) [22100/60000] base_lr: 6.3168e-05 lr: 6.3168e-05 eta: 10:22:05 time: 0.9862 data_time: 0.0223 memory: 29144 grad_norm: 19.9074 loss: 7.8253 decode.loss_cls_ce: 1.6605 decode.loss_mask_ce: 0.7798 decode.loss_mask_dice: 1.4566 decode.d7.loss_cls_ce: 1.6979 decode.d7.loss_mask_ce: 0.7720 decode.d7.loss_mask_dice: 1.4586 2023/09/07 15:59:44 - mmengine - INFO - Iter(train) [22150/60000] base_lr: 6.3084e-05 lr: 6.3084e-05 eta: 10:21:16 time: 0.9893 data_time: 0.0217 memory: 29155 grad_norm: 20.0313 loss: 9.5887 decode.loss_cls_ce: 1.9423 decode.loss_mask_ce: 0.8805 decode.loss_mask_dice: 1.9930 decode.d7.loss_cls_ce: 1.9150 decode.d7.loss_mask_ce: 0.8783 decode.d7.loss_mask_dice: 1.9796 2023/09/07 16:00:33 - mmengine - INFO - Iter(train) [22200/60000] base_lr: 6.3001e-05 lr: 6.3001e-05 eta: 10:20:27 time: 0.9862 data_time: 0.0215 memory: 29217 grad_norm: 20.1951 loss: 7.6500 decode.loss_cls_ce: 1.6684 decode.loss_mask_ce: 0.8546 decode.loss_mask_dice: 1.3046 decode.d7.loss_cls_ce: 1.6822 decode.d7.loss_mask_ce: 0.8501 decode.d7.loss_mask_dice: 1.2901 2023/09/07 16:01:22 - mmengine - INFO - Iter(train) [22250/60000] base_lr: 6.2918e-05 lr: 6.2918e-05 eta: 10:19:38 time: 0.9876 data_time: 0.0212 memory: 29187 grad_norm: 20.2946 loss: 6.9394 decode.loss_cls_ce: 1.4212 decode.loss_mask_ce: 0.7459 decode.loss_mask_dice: 1.3158 decode.d7.loss_cls_ce: 1.4032 decode.d7.loss_mask_ce: 0.7476 decode.d7.loss_mask_dice: 1.3057 2023/09/07 16:02:11 - mmengine - INFO - Iter(train) [22300/60000] base_lr: 6.2834e-05 lr: 6.2834e-05 eta: 10:18:49 time: 0.9856 data_time: 0.0224 memory: 29251 grad_norm: 19.4032 loss: 9.3682 decode.loss_cls_ce: 1.9107 decode.loss_mask_ce: 0.9593 decode.loss_mask_dice: 1.8065 decode.d7.loss_cls_ce: 1.9025 decode.d7.loss_mask_ce: 0.9724 decode.d7.loss_mask_dice: 1.8168 2023/09/07 16:03:01 - mmengine - INFO - Iter(train) [22350/60000] base_lr: 6.2751e-05 lr: 6.2751e-05 eta: 10:17:59 time: 0.9853 data_time: 0.0214 memory: 29204 grad_norm: 20.4712 loss: 9.1370 decode.loss_cls_ce: 2.0017 decode.loss_mask_ce: 0.9380 decode.loss_mask_dice: 1.6273 decode.d7.loss_cls_ce: 2.0283 decode.d7.loss_mask_ce: 0.9376 decode.d7.loss_mask_dice: 1.6041 2023/09/07 16:03:50 - mmengine - INFO - Iter(train) [22400/60000] base_lr: 6.2668e-05 lr: 6.2668e-05 eta: 10:17:10 time: 0.9855 data_time: 0.0215 memory: 29128 grad_norm: 20.5855 loss: 9.1367 decode.loss_cls_ce: 1.8220 decode.loss_mask_ce: 0.9340 decode.loss_mask_dice: 1.7855 decode.d7.loss_cls_ce: 1.8598 decode.d7.loss_mask_ce: 0.9340 decode.d7.loss_mask_dice: 1.8013 2023/09/07 16:04:39 - mmengine - INFO - Iter(train) [22450/60000] base_lr: 6.2584e-05 lr: 6.2584e-05 eta: 10:16:21 time: 0.9824 data_time: 0.0224 memory: 29187 grad_norm: 19.8539 loss: 8.3332 decode.loss_cls_ce: 1.7577 decode.loss_mask_ce: 0.8132 decode.loss_mask_dice: 1.5791 decode.d7.loss_cls_ce: 1.7605 decode.d7.loss_mask_ce: 0.8230 decode.d7.loss_mask_dice: 1.5996 2023/09/07 16:05:28 - mmengine - INFO - Iter(train) [22500/60000] base_lr: 6.2501e-05 lr: 6.2501e-05 eta: 10:15:32 time: 0.9853 data_time: 0.0207 memory: 29307 grad_norm: 20.3279 loss: 9.9042 decode.loss_cls_ce: 2.1366 decode.loss_mask_ce: 0.9518 decode.loss_mask_dice: 1.8801 decode.d7.loss_cls_ce: 2.1165 decode.d7.loss_mask_ce: 0.9383 decode.d7.loss_mask_dice: 1.8809 2023/09/07 16:06:18 - mmengine - INFO - Iter(train) [22550/60000] base_lr: 6.2418e-05 lr: 6.2418e-05 eta: 10:14:42 time: 0.9839 data_time: 0.0214 memory: 29140 grad_norm: 21.7287 loss: 8.2826 decode.loss_cls_ce: 1.5796 decode.loss_mask_ce: 0.8676 decode.loss_mask_dice: 1.6871 decode.d7.loss_cls_ce: 1.5847 decode.d7.loss_mask_ce: 0.8621 decode.d7.loss_mask_dice: 1.7015 2023/09/07 16:07:07 - mmengine - INFO - Iter(train) [22600/60000] base_lr: 6.2334e-05 lr: 6.2334e-05 eta: 10:13:53 time: 0.9866 data_time: 0.0206 memory: 29244 grad_norm: 20.0276 loss: 8.0170 decode.loss_cls_ce: 1.7544 decode.loss_mask_ce: 0.7719 decode.loss_mask_dice: 1.4800 decode.d7.loss_cls_ce: 1.7626 decode.d7.loss_mask_ce: 0.7743 decode.d7.loss_mask_dice: 1.4738 2023/09/07 16:07:56 - mmengine - INFO - Iter(train) [22650/60000] base_lr: 6.2251e-05 lr: 6.2251e-05 eta: 10:13:04 time: 0.9869 data_time: 0.0213 memory: 29177 grad_norm: 20.1902 loss: 8.2503 decode.loss_cls_ce: 1.7310 decode.loss_mask_ce: 0.8218 decode.loss_mask_dice: 1.5924 decode.d7.loss_cls_ce: 1.7154 decode.d7.loss_mask_ce: 0.8252 decode.d7.loss_mask_dice: 1.5644 2023/09/07 16:08:45 - mmengine - INFO - Iter(train) [22700/60000] base_lr: 6.2168e-05 lr: 6.2168e-05 eta: 10:12:15 time: 0.9884 data_time: 0.0215 memory: 29188 grad_norm: 22.1013 loss: 8.4388 decode.loss_cls_ce: 1.8884 decode.loss_mask_ce: 0.8156 decode.loss_mask_dice: 1.5094 decode.d7.loss_cls_ce: 1.8829 decode.d7.loss_mask_ce: 0.8214 decode.d7.loss_mask_dice: 1.5212 2023/09/07 16:09:35 - mmengine - INFO - Iter(train) [22750/60000] base_lr: 6.2084e-05 lr: 6.2084e-05 eta: 10:11:25 time: 0.9846 data_time: 0.0217 memory: 29214 grad_norm: 21.5128 loss: 8.0629 decode.loss_cls_ce: 1.6555 decode.loss_mask_ce: 0.8835 decode.loss_mask_dice: 1.5116 decode.d7.loss_cls_ce: 1.6351 decode.d7.loss_mask_ce: 0.8808 decode.d7.loss_mask_dice: 1.4964 2023/09/07 16:10:24 - mmengine - INFO - Iter(train) [22800/60000] base_lr: 6.2001e-05 lr: 6.2001e-05 eta: 10:10:36 time: 0.9852 data_time: 0.0214 memory: 29253 grad_norm: 19.8653 loss: 9.4393 decode.loss_cls_ce: 1.9223 decode.loss_mask_ce: 0.9273 decode.loss_mask_dice: 1.8722 decode.d7.loss_cls_ce: 1.9202 decode.d7.loss_mask_ce: 0.9204 decode.d7.loss_mask_dice: 1.8770 2023/09/07 16:11:13 - mmengine - INFO - Iter(train) [22850/60000] base_lr: 6.1918e-05 lr: 6.1918e-05 eta: 10:09:47 time: 0.9848 data_time: 0.0218 memory: 29176 grad_norm: 20.2418 loss: 7.9052 decode.loss_cls_ce: 1.5038 decode.loss_mask_ce: 0.9141 decode.loss_mask_dice: 1.5389 decode.d7.loss_cls_ce: 1.4706 decode.d7.loss_mask_ce: 0.9278 decode.d7.loss_mask_dice: 1.5500 2023/09/07 16:12:03 - mmengine - INFO - Iter(train) [22900/60000] base_lr: 6.1834e-05 lr: 6.1834e-05 eta: 10:08:58 time: 0.9860 data_time: 0.0223 memory: 29328 grad_norm: 20.4194 loss: 10.4704 decode.loss_cls_ce: 2.1565 decode.loss_mask_ce: 0.9148 decode.loss_mask_dice: 2.1640 decode.d7.loss_cls_ce: 2.1765 decode.d7.loss_mask_ce: 0.9169 decode.d7.loss_mask_dice: 2.1417 2023/09/07 16:12:52 - mmengine - INFO - Iter(train) [22950/60000] base_lr: 6.1751e-05 lr: 6.1751e-05 eta: 10:08:09 time: 0.9859 data_time: 0.0222 memory: 29188 grad_norm: 20.6180 loss: 8.5001 decode.loss_cls_ce: 1.8071 decode.loss_mask_ce: 0.8192 decode.loss_mask_dice: 1.6394 decode.d7.loss_cls_ce: 1.7894 decode.d7.loss_mask_ce: 0.8125 decode.d7.loss_mask_dice: 1.6325 2023/09/07 16:13:41 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 16:13:41 - mmengine - INFO - Iter(train) [23000/60000] base_lr: 6.1668e-05 lr: 6.1668e-05 eta: 10:07:19 time: 0.9840 data_time: 0.0221 memory: 29195 grad_norm: 22.1695 loss: 7.9021 decode.loss_cls_ce: 1.7832 decode.loss_mask_ce: 0.6946 decode.loss_mask_dice: 1.4720 decode.d7.loss_cls_ce: 1.7724 decode.d7.loss_mask_ce: 0.6885 decode.d7.loss_mask_dice: 1.4913 2023/09/07 16:14:30 - mmengine - INFO - Iter(train) [23050/60000] base_lr: 6.1584e-05 lr: 6.1584e-05 eta: 10:06:30 time: 0.9855 data_time: 0.0223 memory: 29126 grad_norm: 18.6244 loss: 8.1357 decode.loss_cls_ce: 1.6765 decode.loss_mask_ce: 0.7858 decode.loss_mask_dice: 1.6021 decode.d7.loss_cls_ce: 1.6863 decode.d7.loss_mask_ce: 0.7939 decode.d7.loss_mask_dice: 1.5910 2023/09/07 16:15:20 - mmengine - INFO - Iter(train) [23100/60000] base_lr: 6.1501e-05 lr: 6.1501e-05 eta: 10:05:41 time: 0.9891 data_time: 0.0214 memory: 29212 grad_norm: 21.4360 loss: 8.2501 decode.loss_cls_ce: 1.5521 decode.loss_mask_ce: 0.9175 decode.loss_mask_dice: 1.6426 decode.d7.loss_cls_ce: 1.5953 decode.d7.loss_mask_ce: 0.9091 decode.d7.loss_mask_dice: 1.6334 2023/09/07 16:16:09 - mmengine - INFO - Iter(train) [23150/60000] base_lr: 6.1418e-05 lr: 6.1418e-05 eta: 10:04:52 time: 0.9846 data_time: 0.0217 memory: 29218 grad_norm: 18.5687 loss: 10.0676 decode.loss_cls_ce: 2.0483 decode.loss_mask_ce: 0.9474 decode.loss_mask_dice: 2.0007 decode.d7.loss_cls_ce: 2.0679 decode.d7.loss_mask_ce: 0.9620 decode.d7.loss_mask_dice: 2.0414 2023/09/07 16:16:58 - mmengine - INFO - Iter(train) [23200/60000] base_lr: 6.1334e-05 lr: 6.1334e-05 eta: 10:04:03 time: 0.9851 data_time: 0.0214 memory: 29126 grad_norm: 23.0729 loss: 7.0615 decode.loss_cls_ce: 1.3444 decode.loss_mask_ce: 0.7469 decode.loss_mask_dice: 1.4146 decode.d7.loss_cls_ce: 1.3551 decode.d7.loss_mask_ce: 0.7608 decode.d7.loss_mask_dice: 1.4397 2023/09/07 16:17:47 - mmengine - INFO - Iter(train) [23250/60000] base_lr: 6.1251e-05 lr: 6.1251e-05 eta: 10:03:13 time: 0.9842 data_time: 0.0227 memory: 29241 grad_norm: 18.0944 loss: 7.3945 decode.loss_cls_ce: 1.4513 decode.loss_mask_ce: 0.7163 decode.loss_mask_dice: 1.5167 decode.d7.loss_cls_ce: 1.4602 decode.d7.loss_mask_ce: 0.7149 decode.d7.loss_mask_dice: 1.5350 2023/09/07 16:18:37 - mmengine - INFO - Iter(train) [23300/60000] base_lr: 6.1168e-05 lr: 6.1168e-05 eta: 10:02:24 time: 0.9849 data_time: 0.0215 memory: 29344 grad_norm: 19.9257 loss: 7.5232 decode.loss_cls_ce: 1.6609 decode.loss_mask_ce: 0.6853 decode.loss_mask_dice: 1.4086 decode.d7.loss_cls_ce: 1.6859 decode.d7.loss_mask_ce: 0.6766 decode.d7.loss_mask_dice: 1.4059 2023/09/07 16:19:26 - mmengine - INFO - Iter(train) [23350/60000] base_lr: 6.1084e-05 lr: 6.1084e-05 eta: 10:01:35 time: 0.9831 data_time: 0.0219 memory: 29256 grad_norm: 20.1019 loss: 8.9250 decode.loss_cls_ce: 1.7446 decode.loss_mask_ce: 0.9355 decode.loss_mask_dice: 1.7814 decode.d7.loss_cls_ce: 1.7429 decode.d7.loss_mask_ce: 0.9411 decode.d7.loss_mask_dice: 1.7795 2023/09/07 16:20:15 - mmengine - INFO - Iter(train) [23400/60000] base_lr: 6.1001e-05 lr: 6.1001e-05 eta: 10:00:46 time: 0.9832 data_time: 0.0223 memory: 29217 grad_norm: 16.8778 loss: 8.3236 decode.loss_cls_ce: 1.5635 decode.loss_mask_ce: 0.8379 decode.loss_mask_dice: 1.7531 decode.d7.loss_cls_ce: 1.5743 decode.d7.loss_mask_ce: 0.8412 decode.d7.loss_mask_dice: 1.7538 2023/09/07 16:21:04 - mmengine - INFO - Iter(train) [23450/60000] base_lr: 6.0918e-05 lr: 6.0918e-05 eta: 9:59:56 time: 0.9834 data_time: 0.0222 memory: 29294 grad_norm: 18.3848 loss: 7.8983 decode.loss_cls_ce: 1.6810 decode.loss_mask_ce: 0.8461 decode.loss_mask_dice: 1.4235 decode.d7.loss_cls_ce: 1.6632 decode.d7.loss_mask_ce: 0.8590 decode.d7.loss_mask_dice: 1.4256 2023/09/07 16:21:54 - mmengine - INFO - Iter(train) [23500/60000] base_lr: 6.0834e-05 lr: 6.0834e-05 eta: 9:59:07 time: 0.9832 data_time: 0.0216 memory: 29320 grad_norm: 24.2228 loss: 8.6036 decode.loss_cls_ce: 1.6060 decode.loss_mask_ce: 0.9638 decode.loss_mask_dice: 1.7342 decode.d7.loss_cls_ce: 1.5813 decode.d7.loss_mask_ce: 0.9759 decode.d7.loss_mask_dice: 1.7423 2023/09/07 16:22:43 - mmengine - INFO - Iter(train) [23550/60000] base_lr: 6.0751e-05 lr: 6.0751e-05 eta: 9:58:18 time: 0.9877 data_time: 0.0220 memory: 29176 grad_norm: 22.4955 loss: 7.2373 decode.loss_cls_ce: 1.5232 decode.loss_mask_ce: 0.6277 decode.loss_mask_dice: 1.4546 decode.d7.loss_cls_ce: 1.5584 decode.d7.loss_mask_ce: 0.6307 decode.d7.loss_mask_dice: 1.4426 2023/09/07 16:23:32 - mmengine - INFO - Iter(train) [23600/60000] base_lr: 6.0668e-05 lr: 6.0668e-05 eta: 9:57:29 time: 0.9861 data_time: 0.0221 memory: 29081 grad_norm: 24.0522 loss: 9.6898 decode.loss_cls_ce: 2.0511 decode.loss_mask_ce: 0.9473 decode.loss_mask_dice: 1.8210 decode.d7.loss_cls_ce: 2.0671 decode.d7.loss_mask_ce: 0.9687 decode.d7.loss_mask_dice: 1.8347 2023/09/07 16:24:21 - mmengine - INFO - Iter(train) [23650/60000] base_lr: 6.0584e-05 lr: 6.0584e-05 eta: 9:56:39 time: 0.9864 data_time: 0.0223 memory: 29202 grad_norm: 22.7754 loss: 10.4816 decode.loss_cls_ce: 2.2523 decode.loss_mask_ce: 0.9261 decode.loss_mask_dice: 2.0589 decode.d7.loss_cls_ce: 2.2218 decode.d7.loss_mask_ce: 0.9307 decode.d7.loss_mask_dice: 2.0919 2023/09/07 16:25:11 - mmengine - INFO - Iter(train) [23700/60000] base_lr: 6.0501e-05 lr: 6.0501e-05 eta: 9:55:50 time: 0.9859 data_time: 0.0224 memory: 29195 grad_norm: 21.2911 loss: 7.2270 decode.loss_cls_ce: 1.5041 decode.loss_mask_ce: 0.7347 decode.loss_mask_dice: 1.3677 decode.d7.loss_cls_ce: 1.5045 decode.d7.loss_mask_ce: 0.7435 decode.d7.loss_mask_dice: 1.3725 2023/09/07 16:26:00 - mmengine - INFO - Iter(train) [23750/60000] base_lr: 6.0418e-05 lr: 6.0418e-05 eta: 9:55:01 time: 0.9856 data_time: 0.0218 memory: 29101 grad_norm: 18.4738 loss: 7.2229 decode.loss_cls_ce: 1.3888 decode.loss_mask_ce: 0.8000 decode.loss_mask_dice: 1.4215 decode.d7.loss_cls_ce: 1.4215 decode.d7.loss_mask_ce: 0.7885 decode.d7.loss_mask_dice: 1.4026 2023/09/07 16:26:49 - mmengine - INFO - Iter(train) [23800/60000] base_lr: 6.0334e-05 lr: 6.0334e-05 eta: 9:54:12 time: 0.9848 data_time: 0.0218 memory: 29154 grad_norm: 22.3154 loss: 7.9722 decode.loss_cls_ce: 1.4957 decode.loss_mask_ce: 0.8972 decode.loss_mask_dice: 1.5994 decode.d7.loss_cls_ce: 1.4656 decode.d7.loss_mask_ce: 0.9001 decode.d7.loss_mask_dice: 1.6143 2023/09/07 16:27:39 - mmengine - INFO - Iter(train) [23850/60000] base_lr: 6.0251e-05 lr: 6.0251e-05 eta: 9:53:23 time: 0.9851 data_time: 0.0220 memory: 29176 grad_norm: 19.3958 loss: 7.7155 decode.loss_cls_ce: 1.6016 decode.loss_mask_ce: 0.7877 decode.loss_mask_dice: 1.4633 decode.d7.loss_cls_ce: 1.6084 decode.d7.loss_mask_ce: 0.7837 decode.d7.loss_mask_dice: 1.4707 2023/09/07 16:28:28 - mmengine - INFO - Iter(train) [23900/60000] base_lr: 6.0168e-05 lr: 6.0168e-05 eta: 9:52:33 time: 0.9856 data_time: 0.0225 memory: 29188 grad_norm: 20.1280 loss: 9.2568 decode.loss_cls_ce: 1.8531 decode.loss_mask_ce: 0.9895 decode.loss_mask_dice: 1.8102 decode.d7.loss_cls_ce: 1.8373 decode.d7.loss_mask_ce: 0.9650 decode.d7.loss_mask_dice: 1.8017 2023/09/07 16:29:17 - mmengine - INFO - Iter(train) [23950/60000] base_lr: 6.0084e-05 lr: 6.0084e-05 eta: 9:51:44 time: 0.9907 data_time: 0.0216 memory: 29256 grad_norm: 22.1665 loss: 7.8343 decode.loss_cls_ce: 1.6237 decode.loss_mask_ce: 0.7965 decode.loss_mask_dice: 1.4764 decode.d7.loss_cls_ce: 1.6390 decode.d7.loss_mask_ce: 0.8088 decode.d7.loss_mask_dice: 1.4898 2023/09/07 16:30:06 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 16:30:06 - mmengine - INFO - Iter(train) [24000/60000] base_lr: 6.0001e-05 lr: 6.0001e-05 eta: 9:50:55 time: 0.9833 data_time: 0.0228 memory: 29191 grad_norm: 19.7015 loss: 7.8858 decode.loss_cls_ce: 1.7038 decode.loss_mask_ce: 0.7333 decode.loss_mask_dice: 1.5124 decode.d7.loss_cls_ce: 1.6943 decode.d7.loss_mask_ce: 0.7289 decode.d7.loss_mask_dice: 1.5130 2023/09/07 16:30:56 - mmengine - INFO - Iter(train) [24050/60000] base_lr: 5.9918e-05 lr: 5.9918e-05 eta: 9:50:06 time: 0.9863 data_time: 0.0217 memory: 29162 grad_norm: 20.7008 loss: 7.7220 decode.loss_cls_ce: 1.5566 decode.loss_mask_ce: 0.7777 decode.loss_mask_dice: 1.5103 decode.d7.loss_cls_ce: 1.5953 decode.d7.loss_mask_ce: 0.7794 decode.d7.loss_mask_dice: 1.5027 2023/09/07 16:31:45 - mmengine - INFO - Iter(train) [24100/60000] base_lr: 5.9834e-05 lr: 5.9834e-05 eta: 9:49:17 time: 0.9859 data_time: 0.0227 memory: 29140 grad_norm: 20.5835 loss: 7.7284 decode.loss_cls_ce: 1.6564 decode.loss_mask_ce: 0.7985 decode.loss_mask_dice: 1.3934 decode.d7.loss_cls_ce: 1.6707 decode.d7.loss_mask_ce: 0.8134 decode.d7.loss_mask_dice: 1.3960 2023/09/07 16:32:34 - mmengine - INFO - Iter(train) [24150/60000] base_lr: 5.9751e-05 lr: 5.9751e-05 eta: 9:48:27 time: 0.9848 data_time: 0.0225 memory: 29170 grad_norm: 21.0059 loss: 7.7099 decode.loss_cls_ce: 1.4817 decode.loss_mask_ce: 0.7575 decode.loss_mask_dice: 1.6081 decode.d7.loss_cls_ce: 1.5042 decode.d7.loss_mask_ce: 0.7516 decode.d7.loss_mask_dice: 1.6068 2023/09/07 16:33:24 - mmengine - INFO - Iter(train) [24200/60000] base_lr: 5.9668e-05 lr: 5.9668e-05 eta: 9:47:38 time: 0.9884 data_time: 0.0213 memory: 29116 grad_norm: 20.4729 loss: 8.1305 decode.loss_cls_ce: 1.7148 decode.loss_mask_ce: 0.7604 decode.loss_mask_dice: 1.5925 decode.d7.loss_cls_ce: 1.7128 decode.d7.loss_mask_ce: 0.7677 decode.d7.loss_mask_dice: 1.5823 2023/09/07 16:34:13 - mmengine - INFO - Iter(train) [24250/60000] base_lr: 5.9584e-05 lr: 5.9584e-05 eta: 9:46:49 time: 0.9867 data_time: 0.0216 memory: 29316 grad_norm: 17.9987 loss: 8.9747 decode.loss_cls_ce: 1.8282 decode.loss_mask_ce: 0.8790 decode.loss_mask_dice: 1.7757 decode.d7.loss_cls_ce: 1.8269 decode.d7.loss_mask_ce: 0.8812 decode.d7.loss_mask_dice: 1.7837 2023/09/07 16:35:02 - mmengine - INFO - Iter(train) [24300/60000] base_lr: 5.9501e-05 lr: 5.9501e-05 eta: 9:46:00 time: 0.9881 data_time: 0.0212 memory: 29195 grad_norm: 20.3810 loss: 7.8652 decode.loss_cls_ce: 1.5747 decode.loss_mask_ce: 0.8580 decode.loss_mask_dice: 1.4764 decode.d7.loss_cls_ce: 1.6055 decode.d7.loss_mask_ce: 0.8519 decode.d7.loss_mask_dice: 1.4986 2023/09/07 16:35:51 - mmengine - INFO - Iter(train) [24350/60000] base_lr: 5.9418e-05 lr: 5.9418e-05 eta: 9:45:10 time: 0.9816 data_time: 0.0215 memory: 29232 grad_norm: 20.5712 loss: 8.5787 decode.loss_cls_ce: 1.8703 decode.loss_mask_ce: 0.8200 decode.loss_mask_dice: 1.5838 decode.d7.loss_cls_ce: 1.9177 decode.d7.loss_mask_ce: 0.8093 decode.d7.loss_mask_dice: 1.5777 2023/09/07 16:36:41 - mmengine - INFO - Iter(train) [24400/60000] base_lr: 5.9334e-05 lr: 5.9334e-05 eta: 9:44:21 time: 0.9859 data_time: 0.0215 memory: 29255 grad_norm: 22.3619 loss: 7.4975 decode.loss_cls_ce: 1.5875 decode.loss_mask_ce: 0.7368 decode.loss_mask_dice: 1.4206 decode.d7.loss_cls_ce: 1.5928 decode.d7.loss_mask_ce: 0.7353 decode.d7.loss_mask_dice: 1.4244 2023/09/07 16:37:30 - mmengine - INFO - Iter(train) [24450/60000] base_lr: 5.9251e-05 lr: 5.9251e-05 eta: 9:43:32 time: 0.9875 data_time: 0.0221 memory: 29162 grad_norm: 20.8108 loss: 7.5887 decode.loss_cls_ce: 1.6746 decode.loss_mask_ce: 0.8381 decode.loss_mask_dice: 1.2890 decode.d7.loss_cls_ce: 1.6533 decode.d7.loss_mask_ce: 0.8376 decode.d7.loss_mask_dice: 1.2961 2023/09/07 16:38:19 - mmengine - INFO - Iter(train) [24500/60000] base_lr: 5.9168e-05 lr: 5.9168e-05 eta: 9:42:43 time: 0.9860 data_time: 0.0213 memory: 29188 grad_norm: 24.0571 loss: 8.9668 decode.loss_cls_ce: 1.8186 decode.loss_mask_ce: 0.9396 decode.loss_mask_dice: 1.7309 decode.d7.loss_cls_ce: 1.8216 decode.d7.loss_mask_ce: 0.9251 decode.d7.loss_mask_dice: 1.7309 2023/09/07 16:39:08 - mmengine - INFO - Iter(train) [24550/60000] base_lr: 5.9084e-05 lr: 5.9084e-05 eta: 9:41:54 time: 0.9836 data_time: 0.0219 memory: 29153 grad_norm: 19.6180 loss: 8.2202 decode.loss_cls_ce: 1.7514 decode.loss_mask_ce: 0.8705 decode.loss_mask_dice: 1.5085 decode.d7.loss_cls_ce: 1.7266 decode.d7.loss_mask_ce: 0.8601 decode.d7.loss_mask_dice: 1.5030 2023/09/07 16:39:58 - mmengine - INFO - Iter(train) [24600/60000] base_lr: 5.9001e-05 lr: 5.9001e-05 eta: 9:41:04 time: 0.9858 data_time: 0.0218 memory: 29330 grad_norm: 19.5896 loss: 7.6670 decode.loss_cls_ce: 1.6560 decode.loss_mask_ce: 0.7905 decode.loss_mask_dice: 1.3701 decode.d7.loss_cls_ce: 1.6860 decode.d7.loss_mask_ce: 0.7905 decode.d7.loss_mask_dice: 1.3739 2023/09/07 16:40:47 - mmengine - INFO - Iter(train) [24650/60000] base_lr: 5.8918e-05 lr: 5.8918e-05 eta: 9:40:15 time: 0.9846 data_time: 0.0217 memory: 29174 grad_norm: 19.7550 loss: 9.8932 decode.loss_cls_ce: 1.8949 decode.loss_mask_ce: 0.9711 decode.loss_mask_dice: 2.0823 decode.d7.loss_cls_ce: 1.8760 decode.d7.loss_mask_ce: 0.9679 decode.d7.loss_mask_dice: 2.1011 2023/09/07 16:41:36 - mmengine - INFO - Iter(train) [24700/60000] base_lr: 5.8834e-05 lr: 5.8834e-05 eta: 9:39:26 time: 0.9880 data_time: 0.0218 memory: 29152 grad_norm: 21.2704 loss: 7.9758 decode.loss_cls_ce: 1.5977 decode.loss_mask_ce: 0.9145 decode.loss_mask_dice: 1.4635 decode.d7.loss_cls_ce: 1.5981 decode.d7.loss_mask_ce: 0.9266 decode.d7.loss_mask_dice: 1.4754 2023/09/07 16:42:26 - mmengine - INFO - Iter(train) [24750/60000] base_lr: 5.8751e-05 lr: 5.8751e-05 eta: 9:38:37 time: 0.9847 data_time: 0.0226 memory: 29232 grad_norm: 20.8232 loss: 8.6364 decode.loss_cls_ce: 1.8721 decode.loss_mask_ce: 0.8124 decode.loss_mask_dice: 1.6261 decode.d7.loss_cls_ce: 1.8933 decode.d7.loss_mask_ce: 0.8153 decode.d7.loss_mask_dice: 1.6172 2023/09/07 16:43:15 - mmengine - INFO - Iter(train) [24800/60000] base_lr: 5.8668e-05 lr: 5.8668e-05 eta: 9:37:48 time: 0.9845 data_time: 0.0224 memory: 29205 grad_norm: 19.4191 loss: 9.7073 decode.loss_cls_ce: 2.1151 decode.loss_mask_ce: 0.8659 decode.loss_mask_dice: 1.8870 decode.d7.loss_cls_ce: 2.0855 decode.d7.loss_mask_ce: 0.8739 decode.d7.loss_mask_dice: 1.8798 2023/09/07 16:44:04 - mmengine - INFO - Iter(train) [24850/60000] base_lr: 5.8584e-05 lr: 5.8584e-05 eta: 9:36:58 time: 0.9855 data_time: 0.0222 memory: 29289 grad_norm: 19.8863 loss: 9.1028 decode.loss_cls_ce: 1.9211 decode.loss_mask_ce: 0.8560 decode.loss_mask_dice: 1.7851 decode.d7.loss_cls_ce: 1.9175 decode.d7.loss_mask_ce: 0.8612 decode.d7.loss_mask_dice: 1.7619 2023/09/07 16:44:53 - mmengine - INFO - Iter(train) [24900/60000] base_lr: 5.8501e-05 lr: 5.8501e-05 eta: 9:36:09 time: 0.9864 data_time: 0.0221 memory: 29188 grad_norm: 18.2394 loss: 8.0985 decode.loss_cls_ce: 1.7446 decode.loss_mask_ce: 0.7914 decode.loss_mask_dice: 1.5137 decode.d7.loss_cls_ce: 1.7554 decode.d7.loss_mask_ce: 0.7859 decode.d7.loss_mask_dice: 1.5075 2023/09/07 16:45:43 - mmengine - INFO - Iter(train) [24950/60000] base_lr: 5.8418e-05 lr: 5.8418e-05 eta: 9:35:20 time: 0.9869 data_time: 0.0216 memory: 29143 grad_norm: 18.8656 loss: 7.6783 decode.loss_cls_ce: 1.6412 decode.loss_mask_ce: 0.7457 decode.loss_mask_dice: 1.4589 decode.d7.loss_cls_ce: 1.6454 decode.d7.loss_mask_ce: 0.7307 decode.d7.loss_mask_dice: 1.4563 2023/09/07 16:46:32 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 16:46:32 - mmengine - INFO - Iter(train) [25000/60000] base_lr: 5.8334e-05 lr: 5.8334e-05 eta: 9:34:31 time: 0.9844 data_time: 0.0221 memory: 29237 grad_norm: 20.0057 loss: 8.2378 decode.loss_cls_ce: 1.7098 decode.loss_mask_ce: 0.7954 decode.loss_mask_dice: 1.6091 decode.d7.loss_cls_ce: 1.7182 decode.d7.loss_mask_ce: 0.8003 decode.d7.loss_mask_dice: 1.6050 2023/09/07 16:47:21 - mmengine - INFO - Iter(train) [25050/60000] base_lr: 5.8251e-05 lr: 5.8251e-05 eta: 9:33:42 time: 0.9861 data_time: 0.0217 memory: 29099 grad_norm: 18.7500 loss: 7.4322 decode.loss_cls_ce: 1.5184 decode.loss_mask_ce: 0.8343 decode.loss_mask_dice: 1.3714 decode.d7.loss_cls_ce: 1.5013 decode.d7.loss_mask_ce: 0.8406 decode.d7.loss_mask_dice: 1.3663 2023/09/07 16:48:11 - mmengine - INFO - Iter(train) [25100/60000] base_lr: 5.8168e-05 lr: 5.8168e-05 eta: 9:32:52 time: 0.9882 data_time: 0.0224 memory: 29230 grad_norm: 20.0677 loss: 8.7263 decode.loss_cls_ce: 1.7190 decode.loss_mask_ce: 0.9231 decode.loss_mask_dice: 1.7145 decode.d7.loss_cls_ce: 1.7352 decode.d7.loss_mask_ce: 0.9246 decode.d7.loss_mask_dice: 1.7099 2023/09/07 16:49:00 - mmengine - INFO - Iter(train) [25150/60000] base_lr: 5.8084e-05 lr: 5.8084e-05 eta: 9:32:03 time: 0.9883 data_time: 0.0208 memory: 29229 grad_norm: 18.0035 loss: 8.1684 decode.loss_cls_ce: 1.6722 decode.loss_mask_ce: 0.8194 decode.loss_mask_dice: 1.5930 decode.d7.loss_cls_ce: 1.6675 decode.d7.loss_mask_ce: 0.8133 decode.d7.loss_mask_dice: 1.6029 2023/09/07 16:49:49 - mmengine - INFO - Iter(train) [25200/60000] base_lr: 5.8001e-05 lr: 5.8001e-05 eta: 9:31:14 time: 0.9855 data_time: 0.0222 memory: 29226 grad_norm: 21.4807 loss: 8.6285 decode.loss_cls_ce: 1.8115 decode.loss_mask_ce: 0.8217 decode.loss_mask_dice: 1.6807 decode.d7.loss_cls_ce: 1.7804 decode.d7.loss_mask_ce: 0.8370 decode.d7.loss_mask_dice: 1.6972 2023/09/07 16:50:38 - mmengine - INFO - Iter(train) [25250/60000] base_lr: 5.7918e-05 lr: 5.7918e-05 eta: 9:30:25 time: 0.9848 data_time: 0.0217 memory: 29151 grad_norm: 21.0447 loss: 7.0539 decode.loss_cls_ce: 1.4244 decode.loss_mask_ce: 0.7538 decode.loss_mask_dice: 1.3480 decode.d7.loss_cls_ce: 1.4201 decode.d7.loss_mask_ce: 0.7533 decode.d7.loss_mask_dice: 1.3542 2023/09/07 16:51:28 - mmengine - INFO - Iter(train) [25300/60000] base_lr: 5.7834e-05 lr: 5.7834e-05 eta: 9:29:36 time: 0.9852 data_time: 0.0223 memory: 29281 grad_norm: 24.5690 loss: 7.3525 decode.loss_cls_ce: 1.5963 decode.loss_mask_ce: 0.7162 decode.loss_mask_dice: 1.3537 decode.d7.loss_cls_ce: 1.6285 decode.d7.loss_mask_ce: 0.7081 decode.d7.loss_mask_dice: 1.3496 2023/09/07 16:52:17 - mmengine - INFO - Iter(train) [25350/60000] base_lr: 5.7751e-05 lr: 5.7751e-05 eta: 9:28:46 time: 0.9852 data_time: 0.0218 memory: 29140 grad_norm: 21.0996 loss: 7.4761 decode.loss_cls_ce: 1.5310 decode.loss_mask_ce: 0.7567 decode.loss_mask_dice: 1.4534 decode.d7.loss_cls_ce: 1.5305 decode.d7.loss_mask_ce: 0.7621 decode.d7.loss_mask_dice: 1.4424 2023/09/07 16:53:06 - mmengine - INFO - Iter(train) [25400/60000] base_lr: 5.7668e-05 lr: 5.7668e-05 eta: 9:27:57 time: 0.9869 data_time: 0.0216 memory: 29141 grad_norm: 18.7424 loss: 8.0495 decode.loss_cls_ce: 1.6962 decode.loss_mask_ce: 0.8693 decode.loss_mask_dice: 1.4679 decode.d7.loss_cls_ce: 1.6737 decode.d7.loss_mask_ce: 0.8783 decode.d7.loss_mask_dice: 1.4641 2023/09/07 16:53:56 - mmengine - INFO - Iter(train) [25450/60000] base_lr: 5.7584e-05 lr: 5.7584e-05 eta: 9:27:08 time: 0.9856 data_time: 0.0221 memory: 29189 grad_norm: 19.8176 loss: 9.3144 decode.loss_cls_ce: 1.8855 decode.loss_mask_ce: 0.8686 decode.loss_mask_dice: 1.8945 decode.d7.loss_cls_ce: 1.9091 decode.d7.loss_mask_ce: 0.8626 decode.d7.loss_mask_dice: 1.8941 2023/09/07 16:54:45 - mmengine - INFO - Iter(train) [25500/60000] base_lr: 5.7501e-05 lr: 5.7501e-05 eta: 9:26:19 time: 0.9854 data_time: 0.0225 memory: 29211 grad_norm: 20.6631 loss: 7.6072 decode.loss_cls_ce: 1.7099 decode.loss_mask_ce: 0.7579 decode.loss_mask_dice: 1.3454 decode.d7.loss_cls_ce: 1.6989 decode.d7.loss_mask_ce: 0.7533 decode.d7.loss_mask_dice: 1.3419 2023/09/07 16:55:34 - mmengine - INFO - Iter(train) [25550/60000] base_lr: 5.7418e-05 lr: 5.7418e-05 eta: 9:25:30 time: 0.9852 data_time: 0.0219 memory: 29293 grad_norm: 18.2395 loss: 9.0155 decode.loss_cls_ce: 1.8830 decode.loss_mask_ce: 0.9354 decode.loss_mask_dice: 1.7060 decode.d7.loss_cls_ce: 1.8782 decode.d7.loss_mask_ce: 0.9236 decode.d7.loss_mask_dice: 1.6893 2023/09/07 16:56:24 - mmengine - INFO - Iter(train) [25600/60000] base_lr: 5.7334e-05 lr: 5.7334e-05 eta: 9:24:41 time: 0.9841 data_time: 0.0221 memory: 29140 grad_norm: 20.3261 loss: 8.4543 decode.loss_cls_ce: 1.7195 decode.loss_mask_ce: 0.8526 decode.loss_mask_dice: 1.6504 decode.d7.loss_cls_ce: 1.7173 decode.d7.loss_mask_ce: 0.8607 decode.d7.loss_mask_dice: 1.6538 2023/09/07 16:57:13 - mmengine - INFO - Iter(train) [25650/60000] base_lr: 5.7251e-05 lr: 5.7251e-05 eta: 9:23:52 time: 0.9877 data_time: 0.0219 memory: 29117 grad_norm: 19.2182 loss: 8.6119 decode.loss_cls_ce: 1.8255 decode.loss_mask_ce: 0.7805 decode.loss_mask_dice: 1.6982 decode.d7.loss_cls_ce: 1.8342 decode.d7.loss_mask_ce: 0.7811 decode.d7.loss_mask_dice: 1.6925 2023/09/07 16:58:02 - mmengine - INFO - Iter(train) [25700/60000] base_lr: 5.7168e-05 lr: 5.7168e-05 eta: 9:23:02 time: 0.9882 data_time: 0.0222 memory: 29176 grad_norm: 22.2998 loss: 7.1958 decode.loss_cls_ce: 1.4204 decode.loss_mask_ce: 0.8264 decode.loss_mask_dice: 1.3638 decode.d7.loss_cls_ce: 1.4065 decode.d7.loss_mask_ce: 0.8270 decode.d7.loss_mask_dice: 1.3518 2023/09/07 16:58:52 - mmengine - INFO - Iter(train) [25750/60000] base_lr: 5.7084e-05 lr: 5.7084e-05 eta: 9:22:13 time: 0.9855 data_time: 0.0220 memory: 29203 grad_norm: 21.2903 loss: 8.8953 decode.loss_cls_ce: 1.7047 decode.loss_mask_ce: 0.8794 decode.loss_mask_dice: 1.8654 decode.d7.loss_cls_ce: 1.7083 decode.d7.loss_mask_ce: 0.8810 decode.d7.loss_mask_dice: 1.8565 2023/09/07 16:59:41 - mmengine - INFO - Iter(train) [25800/60000] base_lr: 5.7001e-05 lr: 5.7001e-05 eta: 9:21:24 time: 0.9856 data_time: 0.0214 memory: 29205 grad_norm: 21.2459 loss: 8.9504 decode.loss_cls_ce: 1.9491 decode.loss_mask_ce: 0.8158 decode.loss_mask_dice: 1.7085 decode.d7.loss_cls_ce: 1.9317 decode.d7.loss_mask_ce: 0.8252 decode.d7.loss_mask_dice: 1.7201 2023/09/07 17:00:30 - mmengine - INFO - Iter(train) [25850/60000] base_lr: 5.6918e-05 lr: 5.6918e-05 eta: 9:20:35 time: 0.9838 data_time: 0.0218 memory: 29148 grad_norm: 18.4184 loss: 9.9603 decode.loss_cls_ce: 2.0569 decode.loss_mask_ce: 0.9535 decode.loss_mask_dice: 1.9593 decode.d7.loss_cls_ce: 2.0722 decode.d7.loss_mask_ce: 0.9726 decode.d7.loss_mask_dice: 1.9459 2023/09/07 17:01:19 - mmengine - INFO - Iter(train) [25900/60000] base_lr: 5.6834e-05 lr: 5.6834e-05 eta: 9:19:46 time: 0.9842 data_time: 0.0216 memory: 29138 grad_norm: 19.8969 loss: 7.2086 decode.loss_cls_ce: 1.4292 decode.loss_mask_ce: 0.8314 decode.loss_mask_dice: 1.3460 decode.d7.loss_cls_ce: 1.4230 decode.d7.loss_mask_ce: 0.8337 decode.d7.loss_mask_dice: 1.3453 2023/09/07 17:02:09 - mmengine - INFO - Iter(train) [25950/60000] base_lr: 5.6751e-05 lr: 5.6751e-05 eta: 9:18:56 time: 0.9863 data_time: 0.0216 memory: 29201 grad_norm: 21.2476 loss: 9.0250 decode.loss_cls_ce: 1.8380 decode.loss_mask_ce: 0.9255 decode.loss_mask_dice: 1.7468 decode.d7.loss_cls_ce: 1.8583 decode.d7.loss_mask_ce: 0.9100 decode.d7.loss_mask_dice: 1.7465 2023/09/07 17:02:58 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 17:02:58 - mmengine - INFO - Iter(train) [26000/60000] base_lr: 5.6668e-05 lr: 5.6668e-05 eta: 9:18:07 time: 0.9857 data_time: 0.0225 memory: 29382 grad_norm: 20.3181 loss: 8.5949 decode.loss_cls_ce: 1.7239 decode.loss_mask_ce: 0.8883 decode.loss_mask_dice: 1.6749 decode.d7.loss_cls_ce: 1.7557 decode.d7.loss_mask_ce: 0.8706 decode.d7.loss_mask_dice: 1.6816 2023/09/07 17:03:47 - mmengine - INFO - Iter(train) [26050/60000] base_lr: 5.6584e-05 lr: 5.6584e-05 eta: 9:17:18 time: 0.9874 data_time: 0.0210 memory: 29262 grad_norm: 18.5662 loss: 7.9061 decode.loss_cls_ce: 1.6288 decode.loss_mask_ce: 0.6836 decode.loss_mask_dice: 1.6638 decode.d7.loss_cls_ce: 1.6103 decode.d7.loss_mask_ce: 0.6785 decode.d7.loss_mask_dice: 1.6411 2023/09/07 17:04:37 - mmengine - INFO - Iter(train) [26100/60000] base_lr: 5.6501e-05 lr: 5.6501e-05 eta: 9:16:29 time: 0.9864 data_time: 0.0220 memory: 29114 grad_norm: 23.7462 loss: 7.9045 decode.loss_cls_ce: 1.6401 decode.loss_mask_ce: 0.8350 decode.loss_mask_dice: 1.4643 decode.d7.loss_cls_ce: 1.6508 decode.d7.loss_mask_ce: 0.8381 decode.d7.loss_mask_dice: 1.4762 2023/09/07 17:05:26 - mmengine - INFO - Iter(train) [26150/60000] base_lr: 5.6418e-05 lr: 5.6418e-05 eta: 9:15:39 time: 0.9844 data_time: 0.0214 memory: 29125 grad_norm: 21.0805 loss: 7.4296 decode.loss_cls_ce: 1.4087 decode.loss_mask_ce: 0.8887 decode.loss_mask_dice: 1.4103 decode.d7.loss_cls_ce: 1.4352 decode.d7.loss_mask_ce: 0.8874 decode.d7.loss_mask_dice: 1.3992 2023/09/07 17:06:15 - mmengine - INFO - Iter(train) [26200/60000] base_lr: 5.6334e-05 lr: 5.6334e-05 eta: 9:14:50 time: 0.9856 data_time: 0.0220 memory: 29153 grad_norm: 21.9652 loss: 9.8122 decode.loss_cls_ce: 1.9208 decode.loss_mask_ce: 0.9649 decode.loss_mask_dice: 2.0283 decode.d7.loss_cls_ce: 1.9298 decode.d7.loss_mask_ce: 0.9611 decode.d7.loss_mask_dice: 2.0072 2023/09/07 17:07:05 - mmengine - INFO - Iter(train) [26250/60000] base_lr: 5.6251e-05 lr: 5.6251e-05 eta: 9:14:01 time: 0.9878 data_time: 0.0215 memory: 29109 grad_norm: 18.9851 loss: 8.2506 decode.loss_cls_ce: 1.7687 decode.loss_mask_ce: 0.7515 decode.loss_mask_dice: 1.6040 decode.d7.loss_cls_ce: 1.7531 decode.d7.loss_mask_ce: 0.7561 decode.d7.loss_mask_dice: 1.6171 2023/09/07 17:07:54 - mmengine - INFO - Iter(train) [26300/60000] base_lr: 5.6168e-05 lr: 5.6168e-05 eta: 9:13:12 time: 0.9860 data_time: 0.0216 memory: 29217 grad_norm: 20.4600 loss: 8.0392 decode.loss_cls_ce: 1.5731 decode.loss_mask_ce: 0.8607 decode.loss_mask_dice: 1.6038 decode.d7.loss_cls_ce: 1.5314 decode.d7.loss_mask_ce: 0.8584 decode.d7.loss_mask_dice: 1.6119 2023/09/07 17:08:43 - mmengine - INFO - Iter(train) [26350/60000] base_lr: 5.6084e-05 lr: 5.6084e-05 eta: 9:12:23 time: 0.9863 data_time: 0.0215 memory: 29394 grad_norm: 18.0612 loss: 8.5404 decode.loss_cls_ce: 1.8175 decode.loss_mask_ce: 0.7615 decode.loss_mask_dice: 1.6946 decode.d7.loss_cls_ce: 1.8027 decode.d7.loss_mask_ce: 0.7628 decode.d7.loss_mask_dice: 1.7014 2023/09/07 17:09:32 - mmengine - INFO - Iter(train) [26400/60000] base_lr: 5.6001e-05 lr: 5.6001e-05 eta: 9:11:34 time: 0.9854 data_time: 0.0215 memory: 29265 grad_norm: 19.3176 loss: 9.2196 decode.loss_cls_ce: 1.8179 decode.loss_mask_ce: 0.9583 decode.loss_mask_dice: 1.8369 decode.d7.loss_cls_ce: 1.8133 decode.d7.loss_mask_ce: 0.9640 decode.d7.loss_mask_dice: 1.8292 2023/09/07 17:10:22 - mmengine - INFO - Iter(train) [26450/60000] base_lr: 5.5918e-05 lr: 5.5918e-05 eta: 9:10:44 time: 0.9873 data_time: 0.0219 memory: 29188 grad_norm: 18.9512 loss: 8.5773 decode.loss_cls_ce: 1.7913 decode.loss_mask_ce: 0.8795 decode.loss_mask_dice: 1.6597 decode.d7.loss_cls_ce: 1.7056 decode.d7.loss_mask_ce: 0.8890 decode.d7.loss_mask_dice: 1.6522 2023/09/07 17:11:11 - mmengine - INFO - Iter(train) [26500/60000] base_lr: 5.5834e-05 lr: 5.5834e-05 eta: 9:09:55 time: 0.9857 data_time: 0.0218 memory: 29216 grad_norm: 21.1684 loss: 10.6809 decode.loss_cls_ce: 2.1514 decode.loss_mask_ce: 1.0251 decode.loss_mask_dice: 2.1472 decode.d7.loss_cls_ce: 2.1772 decode.d7.loss_mask_ce: 1.0317 decode.d7.loss_mask_dice: 2.1482 2023/09/07 17:12:00 - mmengine - INFO - Iter(train) [26550/60000] base_lr: 5.5751e-05 lr: 5.5751e-05 eta: 9:09:06 time: 0.9846 data_time: 0.0210 memory: 29224 grad_norm: 22.8078 loss: 8.5228 decode.loss_cls_ce: 1.6871 decode.loss_mask_ce: 0.9024 decode.loss_mask_dice: 1.6808 decode.d7.loss_cls_ce: 1.6630 decode.d7.loss_mask_ce: 0.9089 decode.d7.loss_mask_dice: 1.6807 2023/09/07 17:12:50 - mmengine - INFO - Iter(train) [26600/60000] base_lr: 5.5668e-05 lr: 5.5668e-05 eta: 9:08:17 time: 0.9869 data_time: 0.0222 memory: 29228 grad_norm: 22.3191 loss: 9.8365 decode.loss_cls_ce: 2.1241 decode.loss_mask_ce: 0.9282 decode.loss_mask_dice: 1.8555 decode.d7.loss_cls_ce: 2.1488 decode.d7.loss_mask_ce: 0.9200 decode.d7.loss_mask_dice: 1.8599 2023/09/07 17:13:39 - mmengine - INFO - Iter(train) [26650/60000] base_lr: 5.5584e-05 lr: 5.5584e-05 eta: 9:07:28 time: 0.9874 data_time: 0.0216 memory: 29318 grad_norm: 19.9833 loss: 8.4947 decode.loss_cls_ce: 1.6578 decode.loss_mask_ce: 0.8755 decode.loss_mask_dice: 1.7095 decode.d7.loss_cls_ce: 1.6415 decode.d7.loss_mask_ce: 0.8888 decode.d7.loss_mask_dice: 1.7216 2023/09/07 17:14:28 - mmengine - INFO - Iter(train) [26700/60000] base_lr: 5.5501e-05 lr: 5.5501e-05 eta: 9:06:39 time: 0.9877 data_time: 0.0216 memory: 29215 grad_norm: 22.2085 loss: 10.2238 decode.loss_cls_ce: 2.0114 decode.loss_mask_ce: 1.0349 decode.loss_mask_dice: 2.0533 decode.d7.loss_cls_ce: 2.0315 decode.d7.loss_mask_ce: 1.0410 decode.d7.loss_mask_dice: 2.0517 2023/09/07 17:15:18 - mmengine - INFO - Iter(train) [26750/60000] base_lr: 5.5418e-05 lr: 5.5418e-05 eta: 9:05:49 time: 0.9875 data_time: 0.0214 memory: 29218 grad_norm: 18.1343 loss: 8.4898 decode.loss_cls_ce: 1.7350 decode.loss_mask_ce: 0.7793 decode.loss_mask_dice: 1.7282 decode.d7.loss_cls_ce: 1.7318 decode.d7.loss_mask_ce: 0.7862 decode.d7.loss_mask_dice: 1.7294 2023/09/07 17:16:07 - mmengine - INFO - Iter(train) [26800/60000] base_lr: 5.5334e-05 lr: 5.5334e-05 eta: 9:05:00 time: 0.9870 data_time: 0.0215 memory: 29175 grad_norm: 19.2046 loss: 8.4535 decode.loss_cls_ce: 1.8611 decode.loss_mask_ce: 0.7788 decode.loss_mask_dice: 1.5973 decode.d7.loss_cls_ce: 1.8209 decode.d7.loss_mask_ce: 0.7839 decode.d7.loss_mask_dice: 1.6115 2023/09/07 17:16:56 - mmengine - INFO - Iter(train) [26850/60000] base_lr: 5.5251e-05 lr: 5.5251e-05 eta: 9:04:11 time: 0.9850 data_time: 0.0219 memory: 29214 grad_norm: 20.7896 loss: 8.8379 decode.loss_cls_ce: 1.7911 decode.loss_mask_ce: 0.8461 decode.loss_mask_dice: 1.7643 decode.d7.loss_cls_ce: 1.8301 decode.d7.loss_mask_ce: 0.8425 decode.d7.loss_mask_dice: 1.7638 2023/09/07 17:17:46 - mmengine - INFO - Iter(train) [26900/60000] base_lr: 5.5168e-05 lr: 5.5168e-05 eta: 9:03:22 time: 0.9856 data_time: 0.0214 memory: 29203 grad_norm: 19.1611 loss: 7.7638 decode.loss_cls_ce: 1.5919 decode.loss_mask_ce: 0.7235 decode.loss_mask_dice: 1.5871 decode.d7.loss_cls_ce: 1.5403 decode.d7.loss_mask_ce: 0.7286 decode.d7.loss_mask_dice: 1.5925 2023/09/07 17:18:35 - mmengine - INFO - Iter(train) [26950/60000] base_lr: 5.5084e-05 lr: 5.5084e-05 eta: 9:02:33 time: 0.9834 data_time: 0.0226 memory: 29122 grad_norm: 22.1917 loss: 8.5934 decode.loss_cls_ce: 1.8094 decode.loss_mask_ce: 0.8292 decode.loss_mask_dice: 1.6640 decode.d7.loss_cls_ce: 1.8254 decode.d7.loss_mask_ce: 0.8247 decode.d7.loss_mask_dice: 1.6406 2023/09/07 17:19:24 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 17:19:24 - mmengine - INFO - Iter(train) [27000/60000] base_lr: 5.5001e-05 lr: 5.5001e-05 eta: 9:01:44 time: 0.9870 data_time: 0.0216 memory: 29152 grad_norm: 21.0989 loss: 8.6616 decode.loss_cls_ce: 1.8330 decode.loss_mask_ce: 0.7925 decode.loss_mask_dice: 1.7246 decode.d7.loss_cls_ce: 1.7743 decode.d7.loss_mask_ce: 0.7995 decode.d7.loss_mask_dice: 1.7378 2023/09/07 17:20:14 - mmengine - INFO - Iter(train) [27050/60000] base_lr: 5.4918e-05 lr: 5.4918e-05 eta: 9:00:54 time: 0.9864 data_time: 0.0224 memory: 29191 grad_norm: 19.5769 loss: 8.4303 decode.loss_cls_ce: 1.6878 decode.loss_mask_ce: 0.8580 decode.loss_mask_dice: 1.6684 decode.d7.loss_cls_ce: 1.6669 decode.d7.loss_mask_ce: 0.8630 decode.d7.loss_mask_dice: 1.6862 2023/09/07 17:21:03 - mmengine - INFO - Iter(train) [27100/60000] base_lr: 5.4834e-05 lr: 5.4834e-05 eta: 9:00:05 time: 0.9842 data_time: 0.0221 memory: 29180 grad_norm: 17.8711 loss: 8.6320 decode.loss_cls_ce: 1.6947 decode.loss_mask_ce: 0.8431 decode.loss_mask_dice: 1.7651 decode.d7.loss_cls_ce: 1.7052 decode.d7.loss_mask_ce: 0.8399 decode.d7.loss_mask_dice: 1.7840 2023/09/07 17:21:52 - mmengine - INFO - Iter(train) [27150/60000] base_lr: 5.4751e-05 lr: 5.4751e-05 eta: 8:59:16 time: 0.9863 data_time: 0.0217 memory: 29191 grad_norm: 17.0668 loss: 8.2758 decode.loss_cls_ce: 1.6282 decode.loss_mask_ce: 0.9426 decode.loss_mask_dice: 1.5743 decode.d7.loss_cls_ce: 1.6190 decode.d7.loss_mask_ce: 0.9434 decode.d7.loss_mask_dice: 1.5684 2023/09/07 17:22:42 - mmengine - INFO - Iter(train) [27200/60000] base_lr: 5.4668e-05 lr: 5.4668e-05 eta: 8:58:27 time: 0.9868 data_time: 0.0218 memory: 29163 grad_norm: 19.2080 loss: 8.2251 decode.loss_cls_ce: 1.6957 decode.loss_mask_ce: 0.8156 decode.loss_mask_dice: 1.6053 decode.d7.loss_cls_ce: 1.6707 decode.d7.loss_mask_ce: 0.8303 decode.d7.loss_mask_dice: 1.6076 2023/09/07 17:23:31 - mmengine - INFO - Iter(train) [27250/60000] base_lr: 5.4584e-05 lr: 5.4584e-05 eta: 8:57:38 time: 0.9875 data_time: 0.0214 memory: 29168 grad_norm: 19.5937 loss: 8.6912 decode.loss_cls_ce: 1.8824 decode.loss_mask_ce: 0.7622 decode.loss_mask_dice: 1.6873 decode.d7.loss_cls_ce: 1.9011 decode.d7.loss_mask_ce: 0.7634 decode.d7.loss_mask_dice: 1.6949 2023/09/07 17:24:20 - mmengine - INFO - Iter(train) [27300/60000] base_lr: 5.4501e-05 lr: 5.4501e-05 eta: 8:56:49 time: 0.9884 data_time: 0.0208 memory: 29180 grad_norm: 19.1091 loss: 8.0445 decode.loss_cls_ce: 1.6833 decode.loss_mask_ce: 0.7353 decode.loss_mask_dice: 1.6151 decode.d7.loss_cls_ce: 1.6543 decode.d7.loss_mask_ce: 0.7408 decode.d7.loss_mask_dice: 1.6157 2023/09/07 17:25:10 - mmengine - INFO - Iter(train) [27350/60000] base_lr: 5.4418e-05 lr: 5.4418e-05 eta: 8:55:59 time: 0.9878 data_time: 0.0215 memory: 29187 grad_norm: 20.0057 loss: 8.5979 decode.loss_cls_ce: 1.7870 decode.loss_mask_ce: 0.8916 decode.loss_mask_dice: 1.6184 decode.d7.loss_cls_ce: 1.8085 decode.d7.loss_mask_ce: 0.8892 decode.d7.loss_mask_dice: 1.6032 2023/09/07 17:25:59 - mmengine - INFO - Iter(train) [27400/60000] base_lr: 5.4334e-05 lr: 5.4334e-05 eta: 8:55:10 time: 0.9870 data_time: 0.0215 memory: 29155 grad_norm: 18.7738 loss: 9.6584 decode.loss_cls_ce: 1.8745 decode.loss_mask_ce: 0.9329 decode.loss_mask_dice: 2.0227 decode.d7.loss_cls_ce: 1.8912 decode.d7.loss_mask_ce: 0.9196 decode.d7.loss_mask_dice: 2.0175 2023/09/07 17:26:48 - mmengine - INFO - Iter(train) [27450/60000] base_lr: 5.4251e-05 lr: 5.4251e-05 eta: 8:54:21 time: 0.9867 data_time: 0.0221 memory: 29152 grad_norm: 17.5889 loss: 8.2724 decode.loss_cls_ce: 1.7001 decode.loss_mask_ce: 0.8428 decode.loss_mask_dice: 1.5804 decode.d7.loss_cls_ce: 1.6954 decode.d7.loss_mask_ce: 0.8503 decode.d7.loss_mask_dice: 1.6032 2023/09/07 17:27:37 - mmengine - INFO - Iter(train) [27500/60000] base_lr: 5.4168e-05 lr: 5.4168e-05 eta: 8:53:32 time: 0.9850 data_time: 0.0220 memory: 29335 grad_norm: 22.1274 loss: 8.2949 decode.loss_cls_ce: 1.5825 decode.loss_mask_ce: 0.8839 decode.loss_mask_dice: 1.6712 decode.d7.loss_cls_ce: 1.5976 decode.d7.loss_mask_ce: 0.8790 decode.d7.loss_mask_dice: 1.6806 2023/09/07 17:28:27 - mmengine - INFO - Iter(train) [27550/60000] base_lr: 5.4084e-05 lr: 5.4084e-05 eta: 8:52:43 time: 0.9862 data_time: 0.0223 memory: 29162 grad_norm: 20.6936 loss: 8.5159 decode.loss_cls_ce: 1.7892 decode.loss_mask_ce: 0.8794 decode.loss_mask_dice: 1.6102 decode.d7.loss_cls_ce: 1.7560 decode.d7.loss_mask_ce: 0.8733 decode.d7.loss_mask_dice: 1.6078 2023/09/07 17:29:16 - mmengine - INFO - Iter(train) [27600/60000] base_lr: 5.4001e-05 lr: 5.4001e-05 eta: 8:51:53 time: 0.9863 data_time: 0.0212 memory: 29220 grad_norm: 20.4385 loss: 8.8945 decode.loss_cls_ce: 1.7249 decode.loss_mask_ce: 0.9464 decode.loss_mask_dice: 1.7935 decode.d7.loss_cls_ce: 1.7141 decode.d7.loss_mask_ce: 0.9190 decode.d7.loss_mask_dice: 1.7966 2023/09/07 17:30:05 - mmengine - INFO - Iter(train) [27650/60000] base_lr: 5.3918e-05 lr: 5.3918e-05 eta: 8:51:04 time: 0.9838 data_time: 0.0210 memory: 29327 grad_norm: 20.9136 loss: 9.6145 decode.loss_cls_ce: 1.8991 decode.loss_mask_ce: 0.8494 decode.loss_mask_dice: 2.0595 decode.d7.loss_cls_ce: 1.8898 decode.d7.loss_mask_ce: 0.8614 decode.d7.loss_mask_dice: 2.0551 2023/09/07 17:30:55 - mmengine - INFO - Iter(train) [27700/60000] base_lr: 5.3834e-05 lr: 5.3834e-05 eta: 8:50:15 time: 0.9852 data_time: 0.0227 memory: 29176 grad_norm: 22.1775 loss: 7.4247 decode.loss_cls_ce: 1.5704 decode.loss_mask_ce: 0.7710 decode.loss_mask_dice: 1.3653 decode.d7.loss_cls_ce: 1.5834 decode.d7.loss_mask_ce: 0.7754 decode.d7.loss_mask_dice: 1.3591 2023/09/07 17:31:44 - mmengine - INFO - Iter(train) [27750/60000] base_lr: 5.3751e-05 lr: 5.3751e-05 eta: 8:49:26 time: 0.9870 data_time: 0.0225 memory: 29292 grad_norm: 19.0007 loss: 8.9864 decode.loss_cls_ce: 1.7051 decode.loss_mask_ce: 0.9057 decode.loss_mask_dice: 1.8630 decode.d7.loss_cls_ce: 1.7288 decode.d7.loss_mask_ce: 0.9142 decode.d7.loss_mask_dice: 1.8697 2023/09/07 17:32:33 - mmengine - INFO - Iter(train) [27800/60000] base_lr: 5.3668e-05 lr: 5.3668e-05 eta: 8:48:36 time: 0.9867 data_time: 0.0218 memory: 29115 grad_norm: 19.2334 loss: 8.8450 decode.loss_cls_ce: 1.9597 decode.loss_mask_ce: 0.8129 decode.loss_mask_dice: 1.6738 decode.d7.loss_cls_ce: 1.9235 decode.d7.loss_mask_ce: 0.8030 decode.d7.loss_mask_dice: 1.6720 2023/09/07 17:33:22 - mmengine - INFO - Iter(train) [27850/60000] base_lr: 5.3584e-05 lr: 5.3584e-05 eta: 8:47:47 time: 0.9866 data_time: 0.0218 memory: 29191 grad_norm: 17.3043 loss: 7.6625 decode.loss_cls_ce: 1.6763 decode.loss_mask_ce: 0.7847 decode.loss_mask_dice: 1.3651 decode.d7.loss_cls_ce: 1.6519 decode.d7.loss_mask_ce: 0.7994 decode.d7.loss_mask_dice: 1.3852 2023/09/07 17:34:12 - mmengine - INFO - Iter(train) [27900/60000] base_lr: 5.3501e-05 lr: 5.3501e-05 eta: 8:46:58 time: 0.9835 data_time: 0.0221 memory: 29168 grad_norm: 18.5672 loss: 6.7025 decode.loss_cls_ce: 1.3182 decode.loss_mask_ce: 0.6812 decode.loss_mask_dice: 1.3554 decode.d7.loss_cls_ce: 1.3181 decode.d7.loss_mask_ce: 0.6762 decode.d7.loss_mask_dice: 1.3534 2023/09/07 17:35:01 - mmengine - INFO - Iter(train) [27950/60000] base_lr: 5.3418e-05 lr: 5.3418e-05 eta: 8:46:09 time: 0.9856 data_time: 0.0214 memory: 29233 grad_norm: 19.9474 loss: 7.0981 decode.loss_cls_ce: 1.3229 decode.loss_mask_ce: 0.7887 decode.loss_mask_dice: 1.4169 decode.d7.loss_cls_ce: 1.3507 decode.d7.loss_mask_ce: 0.7963 decode.d7.loss_mask_dice: 1.4225 2023/09/07 17:35:50 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 17:35:50 - mmengine - INFO - Iter(train) [28000/60000] base_lr: 5.3334e-05 lr: 5.3334e-05 eta: 8:45:19 time: 0.9864 data_time: 0.0222 memory: 29174 grad_norm: 19.6651 loss: 7.6958 decode.loss_cls_ce: 1.5613 decode.loss_mask_ce: 0.8496 decode.loss_mask_dice: 1.4274 decode.d7.loss_cls_ce: 1.5935 decode.d7.loss_mask_ce: 0.8409 decode.d7.loss_mask_dice: 1.4231 2023/09/07 17:36:40 - mmengine - INFO - Iter(train) [28050/60000] base_lr: 5.3251e-05 lr: 5.3251e-05 eta: 8:44:30 time: 0.9846 data_time: 0.0223 memory: 29282 grad_norm: 19.4358 loss: 8.4840 decode.loss_cls_ce: 1.7936 decode.loss_mask_ce: 0.8343 decode.loss_mask_dice: 1.6233 decode.d7.loss_cls_ce: 1.7687 decode.d7.loss_mask_ce: 0.8389 decode.d7.loss_mask_dice: 1.6253 2023/09/07 17:37:29 - mmengine - INFO - Iter(train) [28100/60000] base_lr: 5.3168e-05 lr: 5.3168e-05 eta: 8:43:41 time: 0.9858 data_time: 0.0214 memory: 29270 grad_norm: 19.0622 loss: 9.5476 decode.loss_cls_ce: 1.8467 decode.loss_mask_ce: 0.9405 decode.loss_mask_dice: 1.9965 decode.d7.loss_cls_ce: 1.8650 decode.d7.loss_mask_ce: 0.9351 decode.d7.loss_mask_dice: 1.9639 2023/09/07 17:38:18 - mmengine - INFO - Iter(train) [28150/60000] base_lr: 5.3084e-05 lr: 5.3084e-05 eta: 8:42:52 time: 0.9870 data_time: 0.0215 memory: 29085 grad_norm: 18.7550 loss: 8.4480 decode.loss_cls_ce: 1.7540 decode.loss_mask_ce: 0.8321 decode.loss_mask_dice: 1.6410 decode.d7.loss_cls_ce: 1.7485 decode.d7.loss_mask_ce: 0.8328 decode.d7.loss_mask_dice: 1.6396 2023/09/07 17:39:08 - mmengine - INFO - Iter(train) [28200/60000] base_lr: 5.3001e-05 lr: 5.3001e-05 eta: 8:42:03 time: 0.9868 data_time: 0.0216 memory: 29203 grad_norm: 21.3240 loss: 8.9696 decode.loss_cls_ce: 1.8705 decode.loss_mask_ce: 0.8606 decode.loss_mask_dice: 1.7882 decode.d7.loss_cls_ce: 1.8153 decode.d7.loss_mask_ce: 0.8651 decode.d7.loss_mask_dice: 1.7700 2023/09/07 17:39:57 - mmengine - INFO - Iter(train) [28250/60000] base_lr: 5.2918e-05 lr: 5.2918e-05 eta: 8:41:14 time: 0.9837 data_time: 0.0219 memory: 29118 grad_norm: 19.6433 loss: 8.1546 decode.loss_cls_ce: 1.6100 decode.loss_mask_ce: 0.9012 decode.loss_mask_dice: 1.5726 decode.d7.loss_cls_ce: 1.6061 decode.d7.loss_mask_ce: 0.8999 decode.d7.loss_mask_dice: 1.5649 2023/09/07 17:40:46 - mmengine - INFO - Iter(train) [28300/60000] base_lr: 5.2834e-05 lr: 5.2834e-05 eta: 8:40:24 time: 0.9863 data_time: 0.0212 memory: 29195 grad_norm: 18.5206 loss: 7.5388 decode.loss_cls_ce: 1.5575 decode.loss_mask_ce: 0.7628 decode.loss_mask_dice: 1.4706 decode.d7.loss_cls_ce: 1.5106 decode.d7.loss_mask_ce: 0.7665 decode.d7.loss_mask_dice: 1.4707 2023/09/07 17:41:35 - mmengine - INFO - Iter(train) [28350/60000] base_lr: 5.2751e-05 lr: 5.2751e-05 eta: 8:39:35 time: 0.9897 data_time: 0.0211 memory: 29346 grad_norm: 19.1876 loss: 9.4960 decode.loss_cls_ce: 1.8478 decode.loss_mask_ce: 0.9678 decode.loss_mask_dice: 1.9404 decode.d7.loss_cls_ce: 1.8273 decode.d7.loss_mask_ce: 0.9684 decode.d7.loss_mask_dice: 1.9442 2023/09/07 17:42:25 - mmengine - INFO - Iter(train) [28400/60000] base_lr: 5.2668e-05 lr: 5.2668e-05 eta: 8:38:46 time: 0.9828 data_time: 0.0227 memory: 29153 grad_norm: 20.0935 loss: 8.6727 decode.loss_cls_ce: 1.7189 decode.loss_mask_ce: 0.8644 decode.loss_mask_dice: 1.7470 decode.d7.loss_cls_ce: 1.7039 decode.d7.loss_mask_ce: 0.8740 decode.d7.loss_mask_dice: 1.7644 2023/09/07 17:43:14 - mmengine - INFO - Iter(train) [28450/60000] base_lr: 5.2584e-05 lr: 5.2584e-05 eta: 8:37:57 time: 0.9868 data_time: 0.0220 memory: 29215 grad_norm: 18.9718 loss: 7.2994 decode.loss_cls_ce: 1.4612 decode.loss_mask_ce: 0.8133 decode.loss_mask_dice: 1.3549 decode.d7.loss_cls_ce: 1.4891 decode.d7.loss_mask_ce: 0.8143 decode.d7.loss_mask_dice: 1.3667 2023/09/07 17:44:03 - mmengine - INFO - Iter(train) [28500/60000] base_lr: 5.2501e-05 lr: 5.2501e-05 eta: 8:37:07 time: 0.9853 data_time: 0.0215 memory: 29143 grad_norm: 18.0678 loss: 8.6900 decode.loss_cls_ce: 1.8733 decode.loss_mask_ce: 0.7857 decode.loss_mask_dice: 1.7005 decode.d7.loss_cls_ce: 1.8383 decode.d7.loss_mask_ce: 0.7877 decode.d7.loss_mask_dice: 1.7044 2023/09/07 17:44:53 - mmengine - INFO - Iter(train) [28550/60000] base_lr: 5.2418e-05 lr: 5.2418e-05 eta: 8:36:18 time: 0.9828 data_time: 0.0218 memory: 29254 grad_norm: 18.6223 loss: 8.6185 decode.loss_cls_ce: 1.6889 decode.loss_mask_ce: 0.8931 decode.loss_mask_dice: 1.7179 decode.d7.loss_cls_ce: 1.7398 decode.d7.loss_mask_ce: 0.8589 decode.d7.loss_mask_dice: 1.7199 2023/09/07 17:45:42 - mmengine - INFO - Iter(train) [28600/60000] base_lr: 5.2334e-05 lr: 5.2334e-05 eta: 8:35:29 time: 0.9874 data_time: 0.0217 memory: 29278 grad_norm: 19.4465 loss: 8.3213 decode.loss_cls_ce: 1.6961 decode.loss_mask_ce: 0.8735 decode.loss_mask_dice: 1.5864 decode.d7.loss_cls_ce: 1.7244 decode.d7.loss_mask_ce: 0.8695 decode.d7.loss_mask_dice: 1.5714 2023/09/07 17:46:31 - mmengine - INFO - Iter(train) [28650/60000] base_lr: 5.2251e-05 lr: 5.2251e-05 eta: 8:34:40 time: 0.9865 data_time: 0.0219 memory: 29193 grad_norm: 22.1350 loss: 8.8076 decode.loss_cls_ce: 1.7665 decode.loss_mask_ce: 0.9482 decode.loss_mask_dice: 1.6897 decode.d7.loss_cls_ce: 1.7563 decode.d7.loss_mask_ce: 0.9498 decode.d7.loss_mask_dice: 1.6971 2023/09/07 17:47:20 - mmengine - INFO - Iter(train) [28700/60000] base_lr: 5.2168e-05 lr: 5.2168e-05 eta: 8:33:50 time: 0.9851 data_time: 0.0215 memory: 29140 grad_norm: 21.5379 loss: 8.2226 decode.loss_cls_ce: 1.7347 decode.loss_mask_ce: 0.7278 decode.loss_mask_dice: 1.6257 decode.d7.loss_cls_ce: 1.7743 decode.d7.loss_mask_ce: 0.7249 decode.d7.loss_mask_dice: 1.6352 2023/09/07 17:48:10 - mmengine - INFO - Iter(train) [28750/60000] base_lr: 5.2084e-05 lr: 5.2084e-05 eta: 8:33:01 time: 0.9863 data_time: 0.0212 memory: 29395 grad_norm: 20.1868 loss: 9.4245 decode.loss_cls_ce: 1.8674 decode.loss_mask_ce: 0.8979 decode.loss_mask_dice: 1.9398 decode.d7.loss_cls_ce: 1.8909 decode.d7.loss_mask_ce: 0.8840 decode.d7.loss_mask_dice: 1.9444 2023/09/07 17:48:59 - mmengine - INFO - Iter(train) [28800/60000] base_lr: 5.2001e-05 lr: 5.2001e-05 eta: 8:32:12 time: 0.9830 data_time: 0.0220 memory: 29333 grad_norm: 19.1453 loss: 6.8941 decode.loss_cls_ce: 1.3323 decode.loss_mask_ce: 0.7499 decode.loss_mask_dice: 1.3803 decode.d7.loss_cls_ce: 1.2980 decode.d7.loss_mask_ce: 0.7527 decode.d7.loss_mask_dice: 1.3809 2023/09/07 17:49:48 - mmengine - INFO - Iter(train) [28850/60000] base_lr: 5.1918e-05 lr: 5.1918e-05 eta: 8:31:23 time: 0.9865 data_time: 0.0218 memory: 29213 grad_norm: 18.4726 loss: 8.3493 decode.loss_cls_ce: 1.7075 decode.loss_mask_ce: 0.8815 decode.loss_mask_dice: 1.5804 decode.d7.loss_cls_ce: 1.6917 decode.d7.loss_mask_ce: 0.8940 decode.d7.loss_mask_dice: 1.5944 2023/09/07 17:50:38 - mmengine - INFO - Iter(train) [28900/60000] base_lr: 5.1834e-05 lr: 5.1834e-05 eta: 8:30:34 time: 0.9834 data_time: 0.0220 memory: 29154 grad_norm: 18.0239 loss: 8.2249 decode.loss_cls_ce: 1.7401 decode.loss_mask_ce: 0.8834 decode.loss_mask_dice: 1.4957 decode.d7.loss_cls_ce: 1.7046 decode.d7.loss_mask_ce: 0.8966 decode.d7.loss_mask_dice: 1.5044 2023/09/07 17:51:27 - mmengine - INFO - Iter(train) [28950/60000] base_lr: 5.1751e-05 lr: 5.1751e-05 eta: 8:29:44 time: 0.9852 data_time: 0.0219 memory: 29390 grad_norm: 19.3593 loss: 9.4859 decode.loss_cls_ce: 1.9672 decode.loss_mask_ce: 0.7659 decode.loss_mask_dice: 2.0385 decode.d7.loss_cls_ce: 1.9292 decode.d7.loss_mask_ce: 0.7626 decode.d7.loss_mask_dice: 2.0226 2023/09/07 17:52:16 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 17:52:16 - mmengine - INFO - Iter(train) [29000/60000] base_lr: 5.1668e-05 lr: 5.1668e-05 eta: 8:28:55 time: 0.9864 data_time: 0.0223 memory: 29432 grad_norm: 18.5074 loss: 8.6744 decode.loss_cls_ce: 1.6629 decode.loss_mask_ce: 0.9854 decode.loss_mask_dice: 1.6910 decode.d7.loss_cls_ce: 1.6556 decode.d7.loss_mask_ce: 0.9920 decode.d7.loss_mask_dice: 1.6876 2023/09/07 17:53:06 - mmengine - INFO - Iter(train) [29050/60000] base_lr: 5.1584e-05 lr: 5.1584e-05 eta: 8:28:06 time: 0.9859 data_time: 0.0224 memory: 29122 grad_norm: 21.9061 loss: 7.4003 decode.loss_cls_ce: 1.4648 decode.loss_mask_ce: 0.7464 decode.loss_mask_dice: 1.4718 decode.d7.loss_cls_ce: 1.4847 decode.d7.loss_mask_ce: 0.7455 decode.d7.loss_mask_dice: 1.4871 2023/09/07 17:53:55 - mmengine - INFO - Iter(train) [29100/60000] base_lr: 5.1501e-05 lr: 5.1501e-05 eta: 8:27:17 time: 0.9830 data_time: 0.0215 memory: 29268 grad_norm: 19.4246 loss: 8.4590 decode.loss_cls_ce: 1.7829 decode.loss_mask_ce: 0.8172 decode.loss_mask_dice: 1.6525 decode.d7.loss_cls_ce: 1.7408 decode.d7.loss_mask_ce: 0.8203 decode.d7.loss_mask_dice: 1.6454 2023/09/07 17:54:44 - mmengine - INFO - Iter(train) [29150/60000] base_lr: 5.1418e-05 lr: 5.1418e-05 eta: 8:26:28 time: 0.9860 data_time: 0.0223 memory: 29115 grad_norm: 20.1383 loss: 7.8529 decode.loss_cls_ce: 1.6392 decode.loss_mask_ce: 0.7909 decode.loss_mask_dice: 1.5079 decode.d7.loss_cls_ce: 1.6262 decode.d7.loss_mask_ce: 0.7992 decode.d7.loss_mask_dice: 1.4895 2023/09/07 17:55:33 - mmengine - INFO - Iter(train) [29200/60000] base_lr: 5.1334e-05 lr: 5.1334e-05 eta: 8:25:38 time: 0.9864 data_time: 0.0222 memory: 29227 grad_norm: 19.3021 loss: 8.3227 decode.loss_cls_ce: 1.6690 decode.loss_mask_ce: 0.8240 decode.loss_mask_dice: 1.6680 decode.d7.loss_cls_ce: 1.6860 decode.d7.loss_mask_ce: 0.8153 decode.d7.loss_mask_dice: 1.6604 2023/09/07 17:56:23 - mmengine - INFO - Iter(train) [29250/60000] base_lr: 5.1251e-05 lr: 5.1251e-05 eta: 8:24:49 time: 0.9850 data_time: 0.0222 memory: 29330 grad_norm: 20.6736 loss: 7.6009 decode.loss_cls_ce: 1.4577 decode.loss_mask_ce: 0.7793 decode.loss_mask_dice: 1.5521 decode.d7.loss_cls_ce: 1.4745 decode.d7.loss_mask_ce: 0.7824 decode.d7.loss_mask_dice: 1.5549 2023/09/07 17:57:12 - mmengine - INFO - Iter(train) [29300/60000] base_lr: 5.1168e-05 lr: 5.1168e-05 eta: 8:24:00 time: 0.9851 data_time: 0.0218 memory: 29188 grad_norm: 20.0106 loss: 8.5661 decode.loss_cls_ce: 1.7734 decode.loss_mask_ce: 0.8094 decode.loss_mask_dice: 1.7197 decode.d7.loss_cls_ce: 1.7530 decode.d7.loss_mask_ce: 0.8107 decode.d7.loss_mask_dice: 1.6999 2023/09/07 17:58:01 - mmengine - INFO - Iter(train) [29350/60000] base_lr: 5.1084e-05 lr: 5.1084e-05 eta: 8:23:11 time: 0.9858 data_time: 0.0215 memory: 29101 grad_norm: 19.7433 loss: 8.7979 decode.loss_cls_ce: 1.7748 decode.loss_mask_ce: 0.8877 decode.loss_mask_dice: 1.7008 decode.d7.loss_cls_ce: 1.8333 decode.d7.loss_mask_ce: 0.8823 decode.d7.loss_mask_dice: 1.7189 2023/09/07 17:58:51 - mmengine - INFO - Iter(train) [29400/60000] base_lr: 5.1001e-05 lr: 5.1001e-05 eta: 8:22:22 time: 0.9842 data_time: 0.0223 memory: 29252 grad_norm: 18.6460 loss: 7.9958 decode.loss_cls_ce: 1.5436 decode.loss_mask_ce: 0.7955 decode.loss_mask_dice: 1.6417 decode.d7.loss_cls_ce: 1.5943 decode.d7.loss_mask_ce: 0.7973 decode.d7.loss_mask_dice: 1.6233 2023/09/07 17:59:40 - mmengine - INFO - Iter(train) [29450/60000] base_lr: 5.0918e-05 lr: 5.0918e-05 eta: 8:21:32 time: 0.9848 data_time: 0.0222 memory: 29165 grad_norm: 18.5898 loss: 8.4645 decode.loss_cls_ce: 1.7078 decode.loss_mask_ce: 0.8947 decode.loss_mask_dice: 1.6380 decode.d7.loss_cls_ce: 1.7064 decode.d7.loss_mask_ce: 0.8963 decode.d7.loss_mask_dice: 1.6213 2023/09/07 18:00:29 - mmengine - INFO - Iter(train) [29500/60000] base_lr: 5.0834e-05 lr: 5.0834e-05 eta: 8:20:43 time: 0.9851 data_time: 0.0220 memory: 29225 grad_norm: 21.4893 loss: 8.2538 decode.loss_cls_ce: 1.7709 decode.loss_mask_ce: 0.8185 decode.loss_mask_dice: 1.5436 decode.d7.loss_cls_ce: 1.7752 decode.d7.loss_mask_ce: 0.8135 decode.d7.loss_mask_dice: 1.5321 2023/09/07 18:01:18 - mmengine - INFO - Iter(train) [29550/60000] base_lr: 5.0751e-05 lr: 5.0751e-05 eta: 8:19:54 time: 0.9859 data_time: 0.0217 memory: 29165 grad_norm: 20.3154 loss: 7.2697 decode.loss_cls_ce: 1.3985 decode.loss_mask_ce: 0.7827 decode.loss_mask_dice: 1.4660 decode.d7.loss_cls_ce: 1.3962 decode.d7.loss_mask_ce: 0.7707 decode.d7.loss_mask_dice: 1.4557 2023/09/07 18:01:40 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 18:02:08 - mmengine - INFO - Iter(train) [29600/60000] base_lr: 5.0668e-05 lr: 5.0668e-05 eta: 8:19:05 time: 0.9850 data_time: 0.0222 memory: 29256 grad_norm: 20.6606 loss: 9.3824 decode.loss_cls_ce: 1.8814 decode.loss_mask_ce: 0.9519 decode.loss_mask_dice: 1.8636 decode.d7.loss_cls_ce: 1.8622 decode.d7.loss_mask_ce: 0.9566 decode.d7.loss_mask_dice: 1.8666 2023/09/07 18:02:57 - mmengine - INFO - Iter(train) [29650/60000] base_lr: 5.0584e-05 lr: 5.0584e-05 eta: 8:18:15 time: 0.9867 data_time: 0.0223 memory: 29180 grad_norm: 19.4582 loss: 8.3732 decode.loss_cls_ce: 1.6874 decode.loss_mask_ce: 0.8102 decode.loss_mask_dice: 1.6642 decode.d7.loss_cls_ce: 1.7168 decode.d7.loss_mask_ce: 0.8179 decode.d7.loss_mask_dice: 1.6766 2023/09/07 18:03:46 - mmengine - INFO - Iter(train) [29700/60000] base_lr: 5.0501e-05 lr: 5.0501e-05 eta: 8:17:26 time: 0.9884 data_time: 0.0221 memory: 29168 grad_norm: 24.3380 loss: 7.8932 decode.loss_cls_ce: 1.6161 decode.loss_mask_ce: 0.7941 decode.loss_mask_dice: 1.5412 decode.d7.loss_cls_ce: 1.6004 decode.d7.loss_mask_ce: 0.7943 decode.d7.loss_mask_dice: 1.5471 2023/09/07 18:04:36 - mmengine - INFO - Iter(train) [29750/60000] base_lr: 5.0418e-05 lr: 5.0418e-05 eta: 8:16:37 time: 0.9840 data_time: 0.0218 memory: 29200 grad_norm: 18.5484 loss: 7.8101 decode.loss_cls_ce: 1.5879 decode.loss_mask_ce: 0.8197 decode.loss_mask_dice: 1.4788 decode.d7.loss_cls_ce: 1.6313 decode.d7.loss_mask_ce: 0.8129 decode.d7.loss_mask_dice: 1.4794 2023/09/07 18:05:25 - mmengine - INFO - Iter(train) [29800/60000] base_lr: 5.0334e-05 lr: 5.0334e-05 eta: 8:15:48 time: 0.9869 data_time: 0.0214 memory: 29100 grad_norm: 21.6213 loss: 6.7735 decode.loss_cls_ce: 1.4238 decode.loss_mask_ce: 0.7911 decode.loss_mask_dice: 1.1626 decode.d7.loss_cls_ce: 1.4400 decode.d7.loss_mask_ce: 0.7779 decode.d7.loss_mask_dice: 1.1781 2023/09/07 18:06:14 - mmengine - INFO - Iter(train) [29850/60000] base_lr: 5.0251e-05 lr: 5.0251e-05 eta: 8:14:59 time: 0.9832 data_time: 0.0219 memory: 29232 grad_norm: 21.4675 loss: 7.8603 decode.loss_cls_ce: 1.5558 decode.loss_mask_ce: 0.8402 decode.loss_mask_dice: 1.5216 decode.d7.loss_cls_ce: 1.5774 decode.d7.loss_mask_ce: 0.8402 decode.d7.loss_mask_dice: 1.5251 2023/09/07 18:07:04 - mmengine - INFO - Iter(train) [29900/60000] base_lr: 5.0168e-05 lr: 5.0168e-05 eta: 8:14:09 time: 0.9840 data_time: 0.0221 memory: 29125 grad_norm: 20.9633 loss: 7.5308 decode.loss_cls_ce: 1.5344 decode.loss_mask_ce: 0.7659 decode.loss_mask_dice: 1.4586 decode.d7.loss_cls_ce: 1.5687 decode.d7.loss_mask_ce: 0.7609 decode.d7.loss_mask_dice: 1.4422 2023/09/07 18:07:53 - mmengine - INFO - Iter(train) [29950/60000] base_lr: 5.0084e-05 lr: 5.0084e-05 eta: 8:13:20 time: 0.9875 data_time: 0.0224 memory: 29269 grad_norm: 18.2825 loss: 7.2630 decode.loss_cls_ce: 1.4356 decode.loss_mask_ce: 0.8262 decode.loss_mask_dice: 1.3523 decode.d7.loss_cls_ce: 1.4387 decode.d7.loss_mask_ce: 0.8409 decode.d7.loss_mask_dice: 1.3693 2023/09/07 18:08:42 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 18:08:42 - mmengine - INFO - Iter(train) [30000/60000] base_lr: 5.0001e-05 lr: 5.0001e-05 eta: 8:12:31 time: 0.9873 data_time: 0.0222 memory: 29264 grad_norm: 20.7193 loss: 8.8427 decode.loss_cls_ce: 1.7941 decode.loss_mask_ce: 0.8147 decode.loss_mask_dice: 1.8009 decode.d7.loss_cls_ce: 1.8160 decode.d7.loss_mask_ce: 0.8107 decode.d7.loss_mask_dice: 1.8064 2023/09/07 18:08:42 - mmengine - INFO - Saving checkpoint at 30000 iterations 2023/09/07 18:09:39 - mmengine - INFO - Iter(train) [30050/60000] base_lr: 4.9917e-05 lr: 4.9917e-05 eta: 8:11:49 time: 0.9881 data_time: 0.0218 memory: 29163 grad_norm: 20.0121 loss: 8.4571 decode.loss_cls_ce: 1.8012 decode.loss_mask_ce: 0.8504 decode.loss_mask_dice: 1.6018 decode.d7.loss_cls_ce: 1.7439 decode.d7.loss_mask_ce: 0.8472 decode.d7.loss_mask_dice: 1.6126 2023/09/07 18:10:28 - mmengine - INFO - Iter(train) [30100/60000] base_lr: 4.9834e-05 lr: 4.9834e-05 eta: 8:11:00 time: 0.9837 data_time: 0.0219 memory: 29240 grad_norm: 20.0449 loss: 8.6387 decode.loss_cls_ce: 1.5548 decode.loss_mask_ce: 0.9140 decode.loss_mask_dice: 1.8534 decode.d7.loss_cls_ce: 1.5317 decode.d7.loss_mask_ce: 0.9226 decode.d7.loss_mask_dice: 1.8623 2023/09/07 18:11:17 - mmengine - INFO - Iter(train) [30150/60000] base_lr: 4.9751e-05 lr: 4.9751e-05 eta: 8:10:10 time: 0.9861 data_time: 0.0222 memory: 29204 grad_norm: 19.2814 loss: 8.1755 decode.loss_cls_ce: 1.6146 decode.loss_mask_ce: 0.9074 decode.loss_mask_dice: 1.5703 decode.d7.loss_cls_ce: 1.6247 decode.d7.loss_mask_ce: 0.8978 decode.d7.loss_mask_dice: 1.5606 2023/09/07 18:12:07 - mmengine - INFO - Iter(train) [30200/60000] base_lr: 4.9667e-05 lr: 4.9667e-05 eta: 8:09:21 time: 0.9844 data_time: 0.0227 memory: 29214 grad_norm: 20.0706 loss: 8.8693 decode.loss_cls_ce: 1.7885 decode.loss_mask_ce: 0.9592 decode.loss_mask_dice: 1.6795 decode.d7.loss_cls_ce: 1.7940 decode.d7.loss_mask_ce: 0.9581 decode.d7.loss_mask_dice: 1.6900 2023/09/07 18:12:56 - mmengine - INFO - Iter(train) [30250/60000] base_lr: 4.9584e-05 lr: 4.9584e-05 eta: 8:08:32 time: 0.9883 data_time: 0.0223 memory: 29161 grad_norm: 19.3011 loss: 8.9223 decode.loss_cls_ce: 1.8031 decode.loss_mask_ce: 0.9186 decode.loss_mask_dice: 1.7615 decode.d7.loss_cls_ce: 1.7931 decode.d7.loss_mask_ce: 0.9101 decode.d7.loss_mask_dice: 1.7359 2023/09/07 18:13:45 - mmengine - INFO - Iter(train) [30300/60000] base_lr: 4.9501e-05 lr: 4.9501e-05 eta: 8:07:43 time: 0.9848 data_time: 0.0223 memory: 29216 grad_norm: 20.1151 loss: 7.9734 decode.loss_cls_ce: 1.5471 decode.loss_mask_ce: 0.8603 decode.loss_mask_dice: 1.5610 decode.d7.loss_cls_ce: 1.5758 decode.d7.loss_mask_ce: 0.8758 decode.d7.loss_mask_dice: 1.5533 2023/09/07 18:14:35 - mmengine - INFO - Iter(train) [30350/60000] base_lr: 4.9417e-05 lr: 4.9417e-05 eta: 8:06:54 time: 0.9872 data_time: 0.0217 memory: 29162 grad_norm: 20.1906 loss: 7.8661 decode.loss_cls_ce: 1.6436 decode.loss_mask_ce: 0.7860 decode.loss_mask_dice: 1.5071 decode.d7.loss_cls_ce: 1.6216 decode.d7.loss_mask_ce: 0.8023 decode.d7.loss_mask_dice: 1.5055 2023/09/07 18:15:24 - mmengine - INFO - Iter(train) [30400/60000] base_lr: 4.9334e-05 lr: 4.9334e-05 eta: 8:06:04 time: 0.9845 data_time: 0.0224 memory: 29208 grad_norm: 20.3549 loss: 7.6410 decode.loss_cls_ce: 1.4941 decode.loss_mask_ce: 0.8327 decode.loss_mask_dice: 1.4882 decode.d7.loss_cls_ce: 1.5000 decode.d7.loss_mask_ce: 0.8461 decode.d7.loss_mask_dice: 1.4799 2023/09/07 18:16:13 - mmengine - INFO - Iter(train) [30450/60000] base_lr: 4.9251e-05 lr: 4.9251e-05 eta: 8:05:15 time: 0.9880 data_time: 0.0221 memory: 29226 grad_norm: 20.2655 loss: 9.5574 decode.loss_cls_ce: 1.8694 decode.loss_mask_ce: 0.9414 decode.loss_mask_dice: 1.9700 decode.d7.loss_cls_ce: 1.8417 decode.d7.loss_mask_ce: 0.9436 decode.d7.loss_mask_dice: 1.9914 2023/09/07 18:17:03 - mmengine - INFO - Iter(train) [30500/60000] base_lr: 4.9167e-05 lr: 4.9167e-05 eta: 8:04:26 time: 0.9869 data_time: 0.0244 memory: 29192 grad_norm: 27.3870 loss: 9.6329 decode.loss_cls_ce: 1.8466 decode.loss_mask_ce: 0.9437 decode.loss_mask_dice: 2.0055 decode.d7.loss_cls_ce: 1.8688 decode.d7.loss_mask_ce: 0.9533 decode.d7.loss_mask_dice: 2.0150 2023/09/07 18:17:52 - mmengine - INFO - Iter(train) [30550/60000] base_lr: 4.9084e-05 lr: 4.9084e-05 eta: 8:03:37 time: 0.9866 data_time: 0.0220 memory: 29182 grad_norm: 22.6308 loss: 7.4014 decode.loss_cls_ce: 1.5989 decode.loss_mask_ce: 0.6944 decode.loss_mask_dice: 1.3963 decode.d7.loss_cls_ce: 1.6343 decode.d7.loss_mask_ce: 0.6848 decode.d7.loss_mask_dice: 1.3927 2023/09/07 18:18:41 - mmengine - INFO - Iter(train) [30600/60000] base_lr: 4.9001e-05 lr: 4.9001e-05 eta: 8:02:48 time: 0.9887 data_time: 0.0216 memory: 29193 grad_norm: 20.7664 loss: 8.2152 decode.loss_cls_ce: 1.5735 decode.loss_mask_ce: 0.8932 decode.loss_mask_dice: 1.6322 decode.d7.loss_cls_ce: 1.5807 decode.d7.loss_mask_ce: 0.8874 decode.d7.loss_mask_dice: 1.6481 2023/09/07 18:19:31 - mmengine - INFO - Iter(train) [30650/60000] base_lr: 4.8917e-05 lr: 4.8917e-05 eta: 8:01:58 time: 0.9890 data_time: 0.0217 memory: 29216 grad_norm: 21.4533 loss: 9.1935 decode.loss_cls_ce: 1.8417 decode.loss_mask_ce: 0.8694 decode.loss_mask_dice: 1.8996 decode.d7.loss_cls_ce: 1.8281 decode.d7.loss_mask_ce: 0.8614 decode.d7.loss_mask_dice: 1.8934 2023/09/07 18:20:20 - mmengine - INFO - Iter(train) [30700/60000] base_lr: 4.8834e-05 lr: 4.8834e-05 eta: 8:01:09 time: 0.9916 data_time: 0.0214 memory: 29204 grad_norm: 17.7241 loss: 7.7408 decode.loss_cls_ce: 1.5678 decode.loss_mask_ce: 0.7524 decode.loss_mask_dice: 1.5422 decode.d7.loss_cls_ce: 1.5650 decode.d7.loss_mask_ce: 0.7555 decode.d7.loss_mask_dice: 1.5579 2023/09/07 18:21:10 - mmengine - INFO - Iter(train) [30750/60000] base_lr: 4.8751e-05 lr: 4.8751e-05 eta: 8:00:20 time: 0.9887 data_time: 0.0212 memory: 29233 grad_norm: 18.1932 loss: 9.2132 decode.loss_cls_ce: 1.8051 decode.loss_mask_ce: 0.8390 decode.loss_mask_dice: 1.9557 decode.d7.loss_cls_ce: 1.8201 decode.d7.loss_mask_ce: 0.8362 decode.d7.loss_mask_dice: 1.9572 2023/09/07 18:21:59 - mmengine - INFO - Iter(train) [30800/60000] base_lr: 4.8667e-05 lr: 4.8667e-05 eta: 7:59:31 time: 0.9904 data_time: 0.0211 memory: 29167 grad_norm: 18.1497 loss: 8.1359 decode.loss_cls_ce: 1.5738 decode.loss_mask_ce: 0.8809 decode.loss_mask_dice: 1.6066 decode.d7.loss_cls_ce: 1.5997 decode.d7.loss_mask_ce: 0.8688 decode.d7.loss_mask_dice: 1.6062 2023/09/07 18:22:49 - mmengine - INFO - Iter(train) [30850/60000] base_lr: 4.8584e-05 lr: 4.8584e-05 eta: 7:58:42 time: 0.9915 data_time: 0.0216 memory: 29244 grad_norm: 19.1957 loss: 8.3103 decode.loss_cls_ce: 1.7033 decode.loss_mask_ce: 0.8425 decode.loss_mask_dice: 1.6107 decode.d7.loss_cls_ce: 1.6905 decode.d7.loss_mask_ce: 0.8530 decode.d7.loss_mask_dice: 1.6104 2023/09/07 18:23:38 - mmengine - INFO - Iter(train) [30900/60000] base_lr: 4.8501e-05 lr: 4.8501e-05 eta: 7:57:53 time: 0.9866 data_time: 0.0218 memory: 29218 grad_norm: 19.2581 loss: 8.6193 decode.loss_cls_ce: 1.7231 decode.loss_mask_ce: 0.9037 decode.loss_mask_dice: 1.6938 decode.d7.loss_cls_ce: 1.7106 decode.d7.loss_mask_ce: 0.9015 decode.d7.loss_mask_dice: 1.6866 2023/09/07 18:24:28 - mmengine - INFO - Iter(train) [30950/60000] base_lr: 4.8417e-05 lr: 4.8417e-05 eta: 7:57:04 time: 0.9901 data_time: 0.0218 memory: 29232 grad_norm: 19.1513 loss: 8.3397 decode.loss_cls_ce: 1.6834 decode.loss_mask_ce: 0.8405 decode.loss_mask_dice: 1.6432 decode.d7.loss_cls_ce: 1.6958 decode.d7.loss_mask_ce: 0.8509 decode.d7.loss_mask_dice: 1.6259 2023/09/07 18:25:17 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 18:25:17 - mmengine - INFO - Iter(train) [31000/60000] base_lr: 4.8334e-05 lr: 4.8334e-05 eta: 7:56:15 time: 0.9876 data_time: 0.0215 memory: 29223 grad_norm: 20.5566 loss: 7.8026 decode.loss_cls_ce: 1.6316 decode.loss_mask_ce: 0.8217 decode.loss_mask_dice: 1.4549 decode.d7.loss_cls_ce: 1.5988 decode.d7.loss_mask_ce: 0.8275 decode.d7.loss_mask_dice: 1.4680 2023/09/07 18:26:07 - mmengine - INFO - Iter(train) [31050/60000] base_lr: 4.8251e-05 lr: 4.8251e-05 eta: 7:55:26 time: 0.9898 data_time: 0.0217 memory: 29095 grad_norm: 18.7706 loss: 8.2613 decode.loss_cls_ce: 1.6305 decode.loss_mask_ce: 0.8679 decode.loss_mask_dice: 1.6454 decode.d7.loss_cls_ce: 1.6253 decode.d7.loss_mask_ce: 0.8655 decode.d7.loss_mask_dice: 1.6267 2023/09/07 18:26:56 - mmengine - INFO - Iter(train) [31100/60000] base_lr: 4.8167e-05 lr: 4.8167e-05 eta: 7:54:37 time: 0.9862 data_time: 0.0220 memory: 29255 grad_norm: 18.4848 loss: 8.5593 decode.loss_cls_ce: 1.6556 decode.loss_mask_ce: 0.9167 decode.loss_mask_dice: 1.7226 decode.d7.loss_cls_ce: 1.6526 decode.d7.loss_mask_ce: 0.9067 decode.d7.loss_mask_dice: 1.7050 2023/09/07 18:27:45 - mmengine - INFO - Iter(train) [31150/60000] base_lr: 4.8084e-05 lr: 4.8084e-05 eta: 7:53:47 time: 0.9878 data_time: 0.0223 memory: 29320 grad_norm: 17.4870 loss: 7.3656 decode.loss_cls_ce: 1.4181 decode.loss_mask_ce: 0.7954 decode.loss_mask_dice: 1.4735 decode.d7.loss_cls_ce: 1.4138 decode.d7.loss_mask_ce: 0.7897 decode.d7.loss_mask_dice: 1.4751 2023/09/07 18:28:35 - mmengine - INFO - Iter(train) [31200/60000] base_lr: 4.8001e-05 lr: 4.8001e-05 eta: 7:52:58 time: 0.9889 data_time: 0.0222 memory: 29126 grad_norm: 19.9273 loss: 7.7944 decode.loss_cls_ce: 1.6545 decode.loss_mask_ce: 0.8082 decode.loss_mask_dice: 1.4303 decode.d7.loss_cls_ce: 1.6737 decode.d7.loss_mask_ce: 0.7977 decode.d7.loss_mask_dice: 1.4301 2023/09/07 18:29:24 - mmengine - INFO - Iter(train) [31250/60000] base_lr: 4.7917e-05 lr: 4.7917e-05 eta: 7:52:09 time: 0.9905 data_time: 0.0212 memory: 29201 grad_norm: 17.9052 loss: 8.0956 decode.loss_cls_ce: 1.6658 decode.loss_mask_ce: 0.8475 decode.loss_mask_dice: 1.5386 decode.d7.loss_cls_ce: 1.6628 decode.d7.loss_mask_ce: 0.8465 decode.d7.loss_mask_dice: 1.5343 2023/09/07 18:30:14 - mmengine - INFO - Iter(train) [31300/60000] base_lr: 4.7834e-05 lr: 4.7834e-05 eta: 7:51:20 time: 0.9881 data_time: 0.0218 memory: 29320 grad_norm: 18.1056 loss: 8.0542 decode.loss_cls_ce: 1.6067 decode.loss_mask_ce: 0.8265 decode.loss_mask_dice: 1.6091 decode.d7.loss_cls_ce: 1.5662 decode.d7.loss_mask_ce: 0.8337 decode.d7.loss_mask_dice: 1.6120 2023/09/07 18:31:03 - mmengine - INFO - Iter(train) [31350/60000] base_lr: 4.7751e-05 lr: 4.7751e-05 eta: 7:50:31 time: 0.9895 data_time: 0.0220 memory: 29216 grad_norm: 22.1907 loss: 8.1193 decode.loss_cls_ce: 1.5335 decode.loss_mask_ce: 0.9874 decode.loss_mask_dice: 1.5443 decode.d7.loss_cls_ce: 1.4955 decode.d7.loss_mask_ce: 0.9894 decode.d7.loss_mask_dice: 1.5692 2023/09/07 18:31:53 - mmengine - INFO - Iter(train) [31400/60000] base_lr: 4.7667e-05 lr: 4.7667e-05 eta: 7:49:42 time: 0.9894 data_time: 0.0215 memory: 29201 grad_norm: 18.2658 loss: 7.1164 decode.loss_cls_ce: 1.4078 decode.loss_mask_ce: 0.7516 decode.loss_mask_dice: 1.4142 decode.d7.loss_cls_ce: 1.3646 decode.d7.loss_mask_ce: 0.7496 decode.d7.loss_mask_dice: 1.4287 2023/09/07 18:32:42 - mmengine - INFO - Iter(train) [31450/60000] base_lr: 4.7584e-05 lr: 4.7584e-05 eta: 7:48:53 time: 0.9887 data_time: 0.0216 memory: 29163 grad_norm: 18.5956 loss: 8.0488 decode.loss_cls_ce: 1.5394 decode.loss_mask_ce: 0.8706 decode.loss_mask_dice: 1.6070 decode.d7.loss_cls_ce: 1.5366 decode.d7.loss_mask_ce: 0.8721 decode.d7.loss_mask_dice: 1.6230 2023/09/07 18:33:32 - mmengine - INFO - Iter(train) [31500/60000] base_lr: 4.7501e-05 lr: 4.7501e-05 eta: 7:48:04 time: 0.9893 data_time: 0.0220 memory: 29152 grad_norm: 18.5874 loss: 7.1914 decode.loss_cls_ce: 1.4617 decode.loss_mask_ce: 0.7995 decode.loss_mask_dice: 1.3310 decode.d7.loss_cls_ce: 1.4694 decode.d7.loss_mask_ce: 0.7989 decode.d7.loss_mask_dice: 1.3309 2023/09/07 18:34:21 - mmengine - INFO - Iter(train) [31550/60000] base_lr: 4.7417e-05 lr: 4.7417e-05 eta: 7:47:15 time: 0.9885 data_time: 0.0210 memory: 29188 grad_norm: 18.3552 loss: 8.2448 decode.loss_cls_ce: 1.6953 decode.loss_mask_ce: 0.7440 decode.loss_mask_dice: 1.7107 decode.d7.loss_cls_ce: 1.6608 decode.d7.loss_mask_ce: 0.7410 decode.d7.loss_mask_dice: 1.6929 2023/09/07 18:35:11 - mmengine - INFO - Iter(train) [31600/60000] base_lr: 4.7334e-05 lr: 4.7334e-05 eta: 7:46:26 time: 0.9896 data_time: 0.0225 memory: 29189 grad_norm: 20.3142 loss: 7.2263 decode.loss_cls_ce: 1.3954 decode.loss_mask_ce: 0.8285 decode.loss_mask_dice: 1.3713 decode.d7.loss_cls_ce: 1.4094 decode.d7.loss_mask_ce: 0.8449 decode.d7.loss_mask_dice: 1.3767 2023/09/07 18:36:00 - mmengine - INFO - Iter(train) [31650/60000] base_lr: 4.7251e-05 lr: 4.7251e-05 eta: 7:45:36 time: 0.9888 data_time: 0.0213 memory: 29251 grad_norm: 18.4104 loss: 8.6733 decode.loss_cls_ce: 1.7984 decode.loss_mask_ce: 0.8661 decode.loss_mask_dice: 1.6856 decode.d7.loss_cls_ce: 1.8293 decode.d7.loss_mask_ce: 0.8349 decode.d7.loss_mask_dice: 1.6590 2023/09/07 18:36:50 - mmengine - INFO - Iter(train) [31700/60000] base_lr: 4.7167e-05 lr: 4.7167e-05 eta: 7:44:47 time: 0.9893 data_time: 0.0220 memory: 29233 grad_norm: 22.5895 loss: 8.8392 decode.loss_cls_ce: 1.7520 decode.loss_mask_ce: 0.9192 decode.loss_mask_dice: 1.7229 decode.d7.loss_cls_ce: 1.7869 decode.d7.loss_mask_ce: 0.9240 decode.d7.loss_mask_dice: 1.7342 2023/09/07 18:37:39 - mmengine - INFO - Iter(train) [31750/60000] base_lr: 4.7084e-05 lr: 4.7084e-05 eta: 7:43:58 time: 0.9889 data_time: 0.0217 memory: 29239 grad_norm: 18.8422 loss: 8.7788 decode.loss_cls_ce: 1.7764 decode.loss_mask_ce: 0.8895 decode.loss_mask_dice: 1.7064 decode.d7.loss_cls_ce: 1.7829 decode.d7.loss_mask_ce: 0.9062 decode.d7.loss_mask_dice: 1.7174 2023/09/07 18:38:28 - mmengine - INFO - Iter(train) [31800/60000] base_lr: 4.7001e-05 lr: 4.7001e-05 eta: 7:43:09 time: 0.9875 data_time: 0.0212 memory: 29126 grad_norm: 16.3781 loss: 8.8921 decode.loss_cls_ce: 1.8552 decode.loss_mask_ce: 0.8494 decode.loss_mask_dice: 1.7519 decode.d7.loss_cls_ce: 1.8317 decode.d7.loss_mask_ce: 0.8417 decode.d7.loss_mask_dice: 1.7621 2023/09/07 18:39:18 - mmengine - INFO - Iter(train) [31850/60000] base_lr: 4.6917e-05 lr: 4.6917e-05 eta: 7:42:20 time: 0.9917 data_time: 0.0219 memory: 29183 grad_norm: 18.5197 loss: 7.8933 decode.loss_cls_ce: 1.6620 decode.loss_mask_ce: 0.7652 decode.loss_mask_dice: 1.5062 decode.d7.loss_cls_ce: 1.7189 decode.d7.loss_mask_ce: 0.7499 decode.d7.loss_mask_dice: 1.4910 2023/09/07 18:40:07 - mmengine - INFO - Iter(train) [31900/60000] base_lr: 4.6834e-05 lr: 4.6834e-05 eta: 7:41:31 time: 0.9896 data_time: 0.0214 memory: 29164 grad_norm: 23.5325 loss: 7.5948 decode.loss_cls_ce: 1.5821 decode.loss_mask_ce: 0.7968 decode.loss_mask_dice: 1.4228 decode.d7.loss_cls_ce: 1.5511 decode.d7.loss_mask_ce: 0.8132 decode.d7.loss_mask_dice: 1.4288 2023/09/07 18:40:57 - mmengine - INFO - Iter(train) [31950/60000] base_lr: 4.6751e-05 lr: 4.6751e-05 eta: 7:40:42 time: 0.9876 data_time: 0.0222 memory: 29192 grad_norm: 22.2742 loss: 7.1841 decode.loss_cls_ce: 1.3986 decode.loss_mask_ce: 0.8075 decode.loss_mask_dice: 1.3903 decode.d7.loss_cls_ce: 1.3717 decode.d7.loss_mask_ce: 0.8100 decode.d7.loss_mask_dice: 1.4058 2023/09/07 18:41:46 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 18:41:46 - mmengine - INFO - Iter(train) [32000/60000] base_lr: 4.6667e-05 lr: 4.6667e-05 eta: 7:39:52 time: 0.9863 data_time: 0.0214 memory: 29276 grad_norm: 18.7376 loss: 8.2284 decode.loss_cls_ce: 1.5461 decode.loss_mask_ce: 0.8009 decode.loss_mask_dice: 1.7480 decode.d7.loss_cls_ce: 1.5775 decode.d7.loss_mask_ce: 0.8021 decode.d7.loss_mask_dice: 1.7539 2023/09/07 18:42:36 - mmengine - INFO - Iter(train) [32050/60000] base_lr: 4.6584e-05 lr: 4.6584e-05 eta: 7:39:03 time: 0.9850 data_time: 0.0216 memory: 29238 grad_norm: 18.1248 loss: 8.0704 decode.loss_cls_ce: 1.5619 decode.loss_mask_ce: 0.7727 decode.loss_mask_dice: 1.7085 decode.d7.loss_cls_ce: 1.5703 decode.d7.loss_mask_ce: 0.7742 decode.d7.loss_mask_dice: 1.6827 2023/09/07 18:43:25 - mmengine - INFO - Iter(train) [32100/60000] base_lr: 4.6501e-05 lr: 4.6501e-05 eta: 7:38:14 time: 0.9855 data_time: 0.0218 memory: 29132 grad_norm: 18.0475 loss: 7.5243 decode.loss_cls_ce: 1.5936 decode.loss_mask_ce: 0.7469 decode.loss_mask_dice: 1.4205 decode.d7.loss_cls_ce: 1.5879 decode.d7.loss_mask_ce: 0.7555 decode.d7.loss_mask_dice: 1.4200 2023/09/07 18:44:14 - mmengine - INFO - Iter(train) [32150/60000] base_lr: 4.6417e-05 lr: 4.6417e-05 eta: 7:37:25 time: 0.9851 data_time: 0.0222 memory: 29227 grad_norm: 19.7474 loss: 8.9928 decode.loss_cls_ce: 1.6743 decode.loss_mask_ce: 0.9228 decode.loss_mask_dice: 1.9108 decode.d7.loss_cls_ce: 1.7024 decode.d7.loss_mask_ce: 0.9228 decode.d7.loss_mask_dice: 1.8595 2023/09/07 18:45:04 - mmengine - INFO - Iter(train) [32200/60000] base_lr: 4.6334e-05 lr: 4.6334e-05 eta: 7:36:36 time: 0.9867 data_time: 0.0205 memory: 29142 grad_norm: 18.6648 loss: 9.7659 decode.loss_cls_ce: 2.0563 decode.loss_mask_ce: 0.9116 decode.loss_mask_dice: 1.9165 decode.d7.loss_cls_ce: 2.0398 decode.d7.loss_mask_ce: 0.9270 decode.d7.loss_mask_dice: 1.9148 2023/09/07 18:45:53 - mmengine - INFO - Iter(train) [32250/60000] base_lr: 4.6251e-05 lr: 4.6251e-05 eta: 7:35:46 time: 0.9863 data_time: 0.0203 memory: 29243 grad_norm: 18.3469 loss: 8.0473 decode.loss_cls_ce: 1.6382 decode.loss_mask_ce: 0.8892 decode.loss_mask_dice: 1.4981 decode.d7.loss_cls_ce: 1.6290 decode.d7.loss_mask_ce: 0.8936 decode.d7.loss_mask_dice: 1.4991 2023/09/07 18:46:42 - mmengine - INFO - Iter(train) [32300/60000] base_lr: 4.6167e-05 lr: 4.6167e-05 eta: 7:34:57 time: 0.9876 data_time: 0.0223 memory: 29229 grad_norm: 18.6195 loss: 7.1832 decode.loss_cls_ce: 1.5132 decode.loss_mask_ce: 0.7209 decode.loss_mask_dice: 1.3657 decode.d7.loss_cls_ce: 1.5075 decode.d7.loss_mask_ce: 0.7255 decode.d7.loss_mask_dice: 1.3504 2023/09/07 18:47:32 - mmengine - INFO - Iter(train) [32350/60000] base_lr: 4.6084e-05 lr: 4.6084e-05 eta: 7:34:08 time: 0.9852 data_time: 0.0216 memory: 29256 grad_norm: 19.4173 loss: 7.6608 decode.loss_cls_ce: 1.4678 decode.loss_mask_ce: 0.8227 decode.loss_mask_dice: 1.5347 decode.d7.loss_cls_ce: 1.5082 decode.d7.loss_mask_ce: 0.8182 decode.d7.loss_mask_dice: 1.5093 2023/09/07 18:48:21 - mmengine - INFO - Iter(train) [32400/60000] base_lr: 4.6001e-05 lr: 4.6001e-05 eta: 7:33:19 time: 0.9899 data_time: 0.0219 memory: 29332 grad_norm: 21.0778 loss: 8.4372 decode.loss_cls_ce: 1.8610 decode.loss_mask_ce: 0.7774 decode.loss_mask_dice: 1.5917 decode.d7.loss_cls_ce: 1.8162 decode.d7.loss_mask_ce: 0.7819 decode.d7.loss_mask_dice: 1.6091 2023/09/07 18:49:11 - mmengine - INFO - Iter(train) [32450/60000] base_lr: 4.5917e-05 lr: 4.5917e-05 eta: 7:32:30 time: 0.9885 data_time: 0.0218 memory: 29140 grad_norm: 18.9792 loss: 8.5084 decode.loss_cls_ce: 1.8615 decode.loss_mask_ce: 0.7747 decode.loss_mask_dice: 1.6074 decode.d7.loss_cls_ce: 1.8933 decode.d7.loss_mask_ce: 0.7646 decode.d7.loss_mask_dice: 1.6069 2023/09/07 18:50:00 - mmengine - INFO - Iter(train) [32500/60000] base_lr: 4.5834e-05 lr: 4.5834e-05 eta: 7:31:41 time: 0.9890 data_time: 0.0217 memory: 29217 grad_norm: 17.9418 loss: 9.0105 decode.loss_cls_ce: 1.7259 decode.loss_mask_ce: 0.9399 decode.loss_mask_dice: 1.8380 decode.d7.loss_cls_ce: 1.6938 decode.d7.loss_mask_ce: 0.9635 decode.d7.loss_mask_dice: 1.8494 2023/09/07 18:50:50 - mmengine - INFO - Iter(train) [32550/60000] base_lr: 4.5751e-05 lr: 4.5751e-05 eta: 7:30:51 time: 0.9885 data_time: 0.0222 memory: 29173 grad_norm: 18.0842 loss: 7.8475 decode.loss_cls_ce: 1.7572 decode.loss_mask_ce: 0.7440 decode.loss_mask_dice: 1.4277 decode.d7.loss_cls_ce: 1.7491 decode.d7.loss_mask_ce: 0.7372 decode.d7.loss_mask_dice: 1.4324 2023/09/07 18:51:39 - mmengine - INFO - Iter(train) [32600/60000] base_lr: 4.5667e-05 lr: 4.5667e-05 eta: 7:30:02 time: 0.9911 data_time: 0.0219 memory: 29306 grad_norm: 19.0865 loss: 9.2649 decode.loss_cls_ce: 1.7252 decode.loss_mask_ce: 0.9064 decode.loss_mask_dice: 1.9825 decode.d7.loss_cls_ce: 1.7364 decode.d7.loss_mask_ce: 0.9043 decode.d7.loss_mask_dice: 2.0100 2023/09/07 18:52:28 - mmengine - INFO - Iter(train) [32650/60000] base_lr: 4.5584e-05 lr: 4.5584e-05 eta: 7:29:13 time: 0.9891 data_time: 0.0224 memory: 29240 grad_norm: 18.9913 loss: 9.4603 decode.loss_cls_ce: 1.8388 decode.loss_mask_ce: 1.0235 decode.loss_mask_dice: 1.8561 decode.d7.loss_cls_ce: 1.8403 decode.d7.loss_mask_ce: 1.0293 decode.d7.loss_mask_dice: 1.8723 2023/09/07 18:53:18 - mmengine - INFO - Iter(train) [32700/60000] base_lr: 4.5501e-05 lr: 4.5501e-05 eta: 7:28:24 time: 0.9877 data_time: 0.0221 memory: 29191 grad_norm: 19.4982 loss: 8.5323 decode.loss_cls_ce: 1.8309 decode.loss_mask_ce: 0.8613 decode.loss_mask_dice: 1.5679 decode.d7.loss_cls_ce: 1.8522 decode.d7.loss_mask_ce: 0.8490 decode.d7.loss_mask_dice: 1.5710 2023/09/07 18:54:07 - mmengine - INFO - Iter(train) [32750/60000] base_lr: 4.5417e-05 lr: 4.5417e-05 eta: 7:27:35 time: 0.9891 data_time: 0.0222 memory: 29189 grad_norm: 19.0770 loss: 8.6645 decode.loss_cls_ce: 1.7070 decode.loss_mask_ce: 0.9065 decode.loss_mask_dice: 1.7176 decode.d7.loss_cls_ce: 1.6922 decode.d7.loss_mask_ce: 0.9117 decode.d7.loss_mask_dice: 1.7294 2023/09/07 18:54:57 - mmengine - INFO - Iter(train) [32800/60000] base_lr: 4.5334e-05 lr: 4.5334e-05 eta: 7:26:46 time: 0.9895 data_time: 0.0218 memory: 29169 grad_norm: 18.0341 loss: 8.9487 decode.loss_cls_ce: 1.7531 decode.loss_mask_ce: 0.8854 decode.loss_mask_dice: 1.8391 decode.d7.loss_cls_ce: 1.7635 decode.d7.loss_mask_ce: 0.8756 decode.d7.loss_mask_dice: 1.8320 2023/09/07 18:55:46 - mmengine - INFO - Iter(train) [32850/60000] base_lr: 4.5251e-05 lr: 4.5251e-05 eta: 7:25:57 time: 0.9874 data_time: 0.0216 memory: 29210 grad_norm: 18.4638 loss: 8.0245 decode.loss_cls_ce: 1.7257 decode.loss_mask_ce: 0.7942 decode.loss_mask_dice: 1.4907 decode.d7.loss_cls_ce: 1.7368 decode.d7.loss_mask_ce: 0.8152 decode.d7.loss_mask_dice: 1.4619 2023/09/07 18:56:36 - mmengine - INFO - Iter(train) [32900/60000] base_lr: 4.5167e-05 lr: 4.5167e-05 eta: 7:25:08 time: 0.9881 data_time: 0.0218 memory: 29187 grad_norm: 18.0638 loss: 7.9915 decode.loss_cls_ce: 1.6450 decode.loss_mask_ce: 0.7490 decode.loss_mask_dice: 1.6024 decode.d7.loss_cls_ce: 1.6223 decode.d7.loss_mask_ce: 0.7554 decode.d7.loss_mask_dice: 1.6173 2023/09/07 18:57:25 - mmengine - INFO - Iter(train) [32950/60000] base_lr: 4.5084e-05 lr: 4.5084e-05 eta: 7:24:18 time: 0.9897 data_time: 0.0217 memory: 29194 grad_norm: 17.7406 loss: 8.2503 decode.loss_cls_ce: 1.7133 decode.loss_mask_ce: 0.8074 decode.loss_mask_dice: 1.6038 decode.d7.loss_cls_ce: 1.7263 decode.d7.loss_mask_ce: 0.7935 decode.d7.loss_mask_dice: 1.6060 2023/09/07 18:58:15 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 18:58:15 - mmengine - INFO - Iter(train) [33000/60000] base_lr: 4.5001e-05 lr: 4.5001e-05 eta: 7:23:29 time: 0.9900 data_time: 0.0224 memory: 29202 grad_norm: 18.4079 loss: 8.3930 decode.loss_cls_ce: 1.7484 decode.loss_mask_ce: 0.8643 decode.loss_mask_dice: 1.5915 decode.d7.loss_cls_ce: 1.7274 decode.d7.loss_mask_ce: 0.8702 decode.d7.loss_mask_dice: 1.5912 2023/09/07 18:59:04 - mmengine - INFO - Iter(train) [33050/60000] base_lr: 4.4917e-05 lr: 4.4917e-05 eta: 7:22:40 time: 0.9879 data_time: 0.0217 memory: 29372 grad_norm: 17.9686 loss: 9.8850 decode.loss_cls_ce: 1.9150 decode.loss_mask_ce: 0.9393 decode.loss_mask_dice: 2.0928 decode.d7.loss_cls_ce: 1.8706 decode.d7.loss_mask_ce: 0.9499 decode.d7.loss_mask_dice: 2.1175 2023/09/07 18:59:54 - mmengine - INFO - Iter(train) [33100/60000] base_lr: 4.4834e-05 lr: 4.4834e-05 eta: 7:21:51 time: 0.9882 data_time: 0.0215 memory: 29215 grad_norm: 21.4313 loss: 8.4893 decode.loss_cls_ce: 1.7301 decode.loss_mask_ce: 0.9022 decode.loss_mask_dice: 1.5949 decode.d7.loss_cls_ce: 1.7656 decode.d7.loss_mask_ce: 0.8947 decode.d7.loss_mask_dice: 1.6018 2023/09/07 19:00:43 - mmengine - INFO - Iter(train) [33150/60000] base_lr: 4.4751e-05 lr: 4.4751e-05 eta: 7:21:02 time: 0.9904 data_time: 0.0218 memory: 29177 grad_norm: 20.2763 loss: 8.0713 decode.loss_cls_ce: 1.6298 decode.loss_mask_ce: 0.8220 decode.loss_mask_dice: 1.5771 decode.d7.loss_cls_ce: 1.6409 decode.d7.loss_mask_ce: 0.8257 decode.d7.loss_mask_dice: 1.5758 2023/09/07 19:01:33 - mmengine - INFO - Iter(train) [33200/60000] base_lr: 4.4667e-05 lr: 4.4667e-05 eta: 7:20:13 time: 0.9889 data_time: 0.0221 memory: 29205 grad_norm: 17.9567 loss: 7.1660 decode.loss_cls_ce: 1.4829 decode.loss_mask_ce: 0.7130 decode.loss_mask_dice: 1.3816 decode.d7.loss_cls_ce: 1.5090 decode.d7.loss_mask_ce: 0.7090 decode.d7.loss_mask_dice: 1.3706 2023/09/07 19:02:22 - mmengine - INFO - Iter(train) [33250/60000] base_lr: 4.4584e-05 lr: 4.4584e-05 eta: 7:19:24 time: 0.9891 data_time: 0.0216 memory: 29264 grad_norm: 19.7757 loss: 9.6332 decode.loss_cls_ce: 1.8498 decode.loss_mask_ce: 0.8985 decode.loss_mask_dice: 2.0540 decode.d7.loss_cls_ce: 1.8732 decode.d7.loss_mask_ce: 0.9064 decode.d7.loss_mask_dice: 2.0513 2023/09/07 19:03:12 - mmengine - INFO - Iter(train) [33300/60000] base_lr: 4.4501e-05 lr: 4.4501e-05 eta: 7:18:35 time: 0.9906 data_time: 0.0218 memory: 29189 grad_norm: 20.6326 loss: 9.1316 decode.loss_cls_ce: 1.8386 decode.loss_mask_ce: 0.9401 decode.loss_mask_dice: 1.7890 decode.d7.loss_cls_ce: 1.8471 decode.d7.loss_mask_ce: 0.9331 decode.d7.loss_mask_dice: 1.7837 2023/09/07 19:04:01 - mmengine - INFO - Iter(train) [33350/60000] base_lr: 4.4417e-05 lr: 4.4417e-05 eta: 7:17:45 time: 0.9889 data_time: 0.0212 memory: 29230 grad_norm: 18.2334 loss: 7.9592 decode.loss_cls_ce: 1.7681 decode.loss_mask_ce: 0.7242 decode.loss_mask_dice: 1.4782 decode.d7.loss_cls_ce: 1.7901 decode.d7.loss_mask_ce: 0.7284 decode.d7.loss_mask_dice: 1.4703 2023/09/07 19:04:50 - mmengine - INFO - Iter(train) [33400/60000] base_lr: 4.4334e-05 lr: 4.4334e-05 eta: 7:16:56 time: 0.9881 data_time: 0.0218 memory: 29295 grad_norm: 20.9724 loss: 8.2792 decode.loss_cls_ce: 1.7109 decode.loss_mask_ce: 0.7695 decode.loss_mask_dice: 1.6526 decode.d7.loss_cls_ce: 1.7202 decode.d7.loss_mask_ce: 0.7658 decode.d7.loss_mask_dice: 1.6601 2023/09/07 19:05:40 - mmengine - INFO - Iter(train) [33450/60000] base_lr: 4.4251e-05 lr: 4.4251e-05 eta: 7:16:07 time: 0.9897 data_time: 0.0223 memory: 29151 grad_norm: 20.0658 loss: 8.8123 decode.loss_cls_ce: 1.7468 decode.loss_mask_ce: 0.9168 decode.loss_mask_dice: 1.7378 decode.d7.loss_cls_ce: 1.7481 decode.d7.loss_mask_ce: 0.9200 decode.d7.loss_mask_dice: 1.7427 2023/09/07 19:06:29 - mmengine - INFO - Iter(train) [33500/60000] base_lr: 4.4167e-05 lr: 4.4167e-05 eta: 7:15:18 time: 0.9901 data_time: 0.0225 memory: 29128 grad_norm: 20.7517 loss: 6.6018 decode.loss_cls_ce: 1.2568 decode.loss_mask_ce: 0.7659 decode.loss_mask_dice: 1.2625 decode.d7.loss_cls_ce: 1.2784 decode.d7.loss_mask_ce: 0.7721 decode.d7.loss_mask_dice: 1.2662 2023/09/07 19:07:19 - mmengine - INFO - Iter(train) [33550/60000] base_lr: 4.4084e-05 lr: 4.4084e-05 eta: 7:14:29 time: 0.9898 data_time: 0.0223 memory: 29207 grad_norm: 21.3829 loss: 8.4994 decode.loss_cls_ce: 1.7838 decode.loss_mask_ce: 0.7732 decode.loss_mask_dice: 1.6742 decode.d7.loss_cls_ce: 1.7914 decode.d7.loss_mask_ce: 0.7778 decode.d7.loss_mask_dice: 1.6989 2023/09/07 19:08:08 - mmengine - INFO - Iter(train) [33600/60000] base_lr: 4.4001e-05 lr: 4.4001e-05 eta: 7:13:40 time: 0.9904 data_time: 0.0215 memory: 29345 grad_norm: 18.2887 loss: 6.8166 decode.loss_cls_ce: 1.3318 decode.loss_mask_ce: 0.6667 decode.loss_mask_dice: 1.3847 decode.d7.loss_cls_ce: 1.3522 decode.d7.loss_mask_ce: 0.6755 decode.d7.loss_mask_dice: 1.4057 2023/09/07 19:08:58 - mmengine - INFO - Iter(train) [33650/60000] base_lr: 4.3917e-05 lr: 4.3917e-05 eta: 7:12:51 time: 0.9889 data_time: 0.0218 memory: 29162 grad_norm: 17.8765 loss: 8.8106 decode.loss_cls_ce: 1.6547 decode.loss_mask_ce: 0.9536 decode.loss_mask_dice: 1.7812 decode.d7.loss_cls_ce: 1.6757 decode.d7.loss_mask_ce: 0.9509 decode.d7.loss_mask_dice: 1.7944 2023/09/07 19:09:47 - mmengine - INFO - Iter(train) [33700/60000] base_lr: 4.3834e-05 lr: 4.3834e-05 eta: 7:12:01 time: 0.9895 data_time: 0.0218 memory: 29198 grad_norm: 18.8878 loss: 7.1796 decode.loss_cls_ce: 1.6265 decode.loss_mask_ce: 0.6948 decode.loss_mask_dice: 1.2590 decode.d7.loss_cls_ce: 1.6510 decode.d7.loss_mask_ce: 0.6898 decode.d7.loss_mask_dice: 1.2584 2023/09/07 19:10:37 - mmengine - INFO - Iter(train) [33750/60000] base_lr: 4.3751e-05 lr: 4.3751e-05 eta: 7:11:12 time: 0.9890 data_time: 0.0216 memory: 29200 grad_norm: 17.3428 loss: 8.9726 decode.loss_cls_ce: 1.7662 decode.loss_mask_ce: 0.9659 decode.loss_mask_dice: 1.7566 decode.d7.loss_cls_ce: 1.7576 decode.d7.loss_mask_ce: 0.9702 decode.d7.loss_mask_dice: 1.7560 2023/09/07 19:11:26 - mmengine - INFO - Iter(train) [33800/60000] base_lr: 4.3667e-05 lr: 4.3667e-05 eta: 7:10:23 time: 0.9877 data_time: 0.0234 memory: 29127 grad_norm: 24.4008 loss: 9.1972 decode.loss_cls_ce: 1.7319 decode.loss_mask_ce: 0.9151 decode.loss_mask_dice: 1.9479 decode.d7.loss_cls_ce: 1.7269 decode.d7.loss_mask_ce: 0.9161 decode.d7.loss_mask_dice: 1.9593 2023/09/07 19:12:16 - mmengine - INFO - Iter(train) [33850/60000] base_lr: 4.3584e-05 lr: 4.3584e-05 eta: 7:09:34 time: 0.9895 data_time: 0.0222 memory: 29138 grad_norm: 19.7951 loss: 8.1901 decode.loss_cls_ce: 1.6480 decode.loss_mask_ce: 0.8910 decode.loss_mask_dice: 1.5478 decode.d7.loss_cls_ce: 1.6528 decode.d7.loss_mask_ce: 0.8899 decode.d7.loss_mask_dice: 1.5606 2023/09/07 19:13:05 - mmengine - INFO - Iter(train) [33900/60000] base_lr: 4.3501e-05 lr: 4.3501e-05 eta: 7:08:45 time: 0.9900 data_time: 0.0213 memory: 29255 grad_norm: 19.5160 loss: 8.0788 decode.loss_cls_ce: 1.7433 decode.loss_mask_ce: 0.8131 decode.loss_mask_dice: 1.4805 decode.d7.loss_cls_ce: 1.7572 decode.d7.loss_mask_ce: 0.7919 decode.d7.loss_mask_dice: 1.4928 2023/09/07 19:13:55 - mmengine - INFO - Iter(train) [33950/60000] base_lr: 4.3417e-05 lr: 4.3417e-05 eta: 7:07:56 time: 0.9883 data_time: 0.0227 memory: 29255 grad_norm: 19.3223 loss: 7.5511 decode.loss_cls_ce: 1.5587 decode.loss_mask_ce: 0.7401 decode.loss_mask_dice: 1.4673 decode.d7.loss_cls_ce: 1.5630 decode.d7.loss_mask_ce: 0.7354 decode.d7.loss_mask_dice: 1.4865 2023/09/07 19:14:44 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 19:14:44 - mmengine - INFO - Iter(train) [34000/60000] base_lr: 4.3334e-05 lr: 4.3334e-05 eta: 7:07:07 time: 0.9894 data_time: 0.0219 memory: 29127 grad_norm: 21.0273 loss: 8.7005 decode.loss_cls_ce: 1.6588 decode.loss_mask_ce: 0.8379 decode.loss_mask_dice: 1.8496 decode.d7.loss_cls_ce: 1.6689 decode.d7.loss_mask_ce: 0.8344 decode.d7.loss_mask_dice: 1.8510 2023/09/07 19:15:34 - mmengine - INFO - Iter(train) [34050/60000] base_lr: 4.3251e-05 lr: 4.3251e-05 eta: 7:06:17 time: 0.9909 data_time: 0.0213 memory: 29180 grad_norm: 17.7424 loss: 8.6591 decode.loss_cls_ce: 1.7052 decode.loss_mask_ce: 0.8848 decode.loss_mask_dice: 1.7420 decode.d7.loss_cls_ce: 1.6835 decode.d7.loss_mask_ce: 0.8810 decode.d7.loss_mask_dice: 1.7625 2023/09/07 19:16:23 - mmengine - INFO - Iter(train) [34100/60000] base_lr: 4.3167e-05 lr: 4.3167e-05 eta: 7:05:28 time: 0.9891 data_time: 0.0214 memory: 29162 grad_norm: 18.4166 loss: 7.4638 decode.loss_cls_ce: 1.5745 decode.loss_mask_ce: 0.7936 decode.loss_mask_dice: 1.3466 decode.d7.loss_cls_ce: 1.6019 decode.d7.loss_mask_ce: 0.7933 decode.d7.loss_mask_dice: 1.3538 2023/09/07 19:17:13 - mmengine - INFO - Iter(train) [34150/60000] base_lr: 4.3084e-05 lr: 4.3084e-05 eta: 7:04:39 time: 0.9904 data_time: 0.0225 memory: 29231 grad_norm: 21.4886 loss: 8.6506 decode.loss_cls_ce: 1.6183 decode.loss_mask_ce: 0.9535 decode.loss_mask_dice: 1.7573 decode.d7.loss_cls_ce: 1.6210 decode.d7.loss_mask_ce: 0.9505 decode.d7.loss_mask_dice: 1.7500 2023/09/07 19:18:02 - mmengine - INFO - Iter(train) [34200/60000] base_lr: 4.3001e-05 lr: 4.3001e-05 eta: 7:03:50 time: 0.9898 data_time: 0.0219 memory: 29115 grad_norm: 24.5225 loss: 6.9877 decode.loss_cls_ce: 1.4656 decode.loss_mask_ce: 0.7135 decode.loss_mask_dice: 1.3262 decode.d7.loss_cls_ce: 1.4463 decode.d7.loss_mask_ce: 0.7160 decode.d7.loss_mask_dice: 1.3201 2023/09/07 19:18:52 - mmengine - INFO - Iter(train) [34250/60000] base_lr: 4.2917e-05 lr: 4.2917e-05 eta: 7:03:01 time: 0.9892 data_time: 0.0217 memory: 29150 grad_norm: 19.0143 loss: 8.9047 decode.loss_cls_ce: 1.7801 decode.loss_mask_ce: 0.9267 decode.loss_mask_dice: 1.7241 decode.d7.loss_cls_ce: 1.8245 decode.d7.loss_mask_ce: 0.9095 decode.d7.loss_mask_dice: 1.7399 2023/09/07 19:19:41 - mmengine - INFO - Iter(train) [34300/60000] base_lr: 4.2834e-05 lr: 4.2834e-05 eta: 7:02:12 time: 0.9879 data_time: 0.0221 memory: 29433 grad_norm: 20.9715 loss: 7.3919 decode.loss_cls_ce: 1.4596 decode.loss_mask_ce: 0.8242 decode.loss_mask_dice: 1.3920 decode.d7.loss_cls_ce: 1.5076 decode.d7.loss_mask_ce: 0.8193 decode.d7.loss_mask_dice: 1.3891 2023/09/07 19:20:30 - mmengine - INFO - Iter(train) [34350/60000] base_lr: 4.2751e-05 lr: 4.2751e-05 eta: 7:01:22 time: 0.9890 data_time: 0.0219 memory: 29357 grad_norm: 18.3837 loss: 7.2112 decode.loss_cls_ce: 1.4556 decode.loss_mask_ce: 0.7434 decode.loss_mask_dice: 1.3850 decode.d7.loss_cls_ce: 1.4918 decode.d7.loss_mask_ce: 0.7533 decode.d7.loss_mask_dice: 1.3822 2023/09/07 19:21:20 - mmengine - INFO - Iter(train) [34400/60000] base_lr: 4.2667e-05 lr: 4.2667e-05 eta: 7:00:33 time: 0.9910 data_time: 0.0224 memory: 29190 grad_norm: 18.2212 loss: 8.1335 decode.loss_cls_ce: 1.8035 decode.loss_mask_ce: 0.8069 decode.loss_mask_dice: 1.4443 decode.d7.loss_cls_ce: 1.8103 decode.d7.loss_mask_ce: 0.8068 decode.d7.loss_mask_dice: 1.4616 2023/09/07 19:22:09 - mmengine - INFO - Iter(train) [34450/60000] base_lr: 4.2584e-05 lr: 4.2584e-05 eta: 6:59:44 time: 0.9904 data_time: 0.0221 memory: 29340 grad_norm: 17.8999 loss: 7.8678 decode.loss_cls_ce: 1.6256 decode.loss_mask_ce: 0.8031 decode.loss_mask_dice: 1.5015 decode.d7.loss_cls_ce: 1.6105 decode.d7.loss_mask_ce: 0.8137 decode.d7.loss_mask_dice: 1.5134 2023/09/07 19:22:59 - mmengine - INFO - Iter(train) [34500/60000] base_lr: 4.2501e-05 lr: 4.2501e-05 eta: 6:58:55 time: 0.9902 data_time: 0.0213 memory: 29190 grad_norm: 18.1763 loss: 7.7812 decode.loss_cls_ce: 1.6686 decode.loss_mask_ce: 0.7500 decode.loss_mask_dice: 1.4785 decode.d7.loss_cls_ce: 1.6713 decode.d7.loss_mask_ce: 0.7387 decode.d7.loss_mask_dice: 1.4742 2023/09/07 19:23:48 - mmengine - INFO - Iter(train) [34550/60000] base_lr: 4.2417e-05 lr: 4.2417e-05 eta: 6:58:06 time: 0.9893 data_time: 0.0220 memory: 29229 grad_norm: 19.1210 loss: 9.4182 decode.loss_cls_ce: 1.8981 decode.loss_mask_ce: 0.8711 decode.loss_mask_dice: 1.9260 decode.d7.loss_cls_ce: 1.9057 decode.d7.loss_mask_ce: 0.8623 decode.d7.loss_mask_dice: 1.9550 2023/09/07 19:24:38 - mmengine - INFO - Iter(train) [34600/60000] base_lr: 4.2334e-05 lr: 4.2334e-05 eta: 6:57:17 time: 0.9905 data_time: 0.0218 memory: 29167 grad_norm: 18.6439 loss: 8.7577 decode.loss_cls_ce: 1.9750 decode.loss_mask_ce: 0.7775 decode.loss_mask_dice: 1.6186 decode.d7.loss_cls_ce: 1.9854 decode.d7.loss_mask_ce: 0.7865 decode.d7.loss_mask_dice: 1.6147 2023/09/07 19:25:27 - mmengine - INFO - Iter(train) [34650/60000] base_lr: 4.2251e-05 lr: 4.2251e-05 eta: 6:56:28 time: 0.9901 data_time: 0.0219 memory: 29255 grad_norm: 20.1453 loss: 7.7414 decode.loss_cls_ce: 1.5327 decode.loss_mask_ce: 0.8038 decode.loss_mask_dice: 1.5345 decode.d7.loss_cls_ce: 1.5339 decode.d7.loss_mask_ce: 0.8047 decode.d7.loss_mask_dice: 1.5318 2023/09/07 19:26:17 - mmengine - INFO - Iter(train) [34700/60000] base_lr: 4.2167e-05 lr: 4.2167e-05 eta: 6:55:38 time: 0.9882 data_time: 0.0223 memory: 29190 grad_norm: 18.9970 loss: 7.7875 decode.loss_cls_ce: 1.6882 decode.loss_mask_ce: 0.7340 decode.loss_mask_dice: 1.4637 decode.d7.loss_cls_ce: 1.7048 decode.d7.loss_mask_ce: 0.7326 decode.d7.loss_mask_dice: 1.4642 2023/09/07 19:27:06 - mmengine - INFO - Iter(train) [34750/60000] base_lr: 4.2084e-05 lr: 4.2084e-05 eta: 6:54:49 time: 0.9874 data_time: 0.0223 memory: 29181 grad_norm: 19.7575 loss: 8.9484 decode.loss_cls_ce: 1.6234 decode.loss_mask_ce: 0.9678 decode.loss_mask_dice: 1.8598 decode.d7.loss_cls_ce: 1.6602 decode.d7.loss_mask_ce: 0.9669 decode.d7.loss_mask_dice: 1.8702 2023/09/07 19:27:56 - mmengine - INFO - Iter(train) [34800/60000] base_lr: 4.2001e-05 lr: 4.2001e-05 eta: 6:54:00 time: 0.9905 data_time: 0.0220 memory: 29195 grad_norm: 19.1806 loss: 7.7635 decode.loss_cls_ce: 1.7168 decode.loss_mask_ce: 0.7143 decode.loss_mask_dice: 1.4500 decode.d7.loss_cls_ce: 1.7115 decode.d7.loss_mask_ce: 0.7304 decode.d7.loss_mask_dice: 1.4405 2023/09/07 19:28:45 - mmengine - INFO - Iter(train) [34850/60000] base_lr: 4.1917e-05 lr: 4.1917e-05 eta: 6:53:11 time: 0.9866 data_time: 0.0222 memory: 29175 grad_norm: nan loss: 7.7877 decode.loss_cls_ce: 1.7427 decode.loss_mask_ce: 0.7782 decode.loss_mask_dice: 1.3829 decode.d7.loss_cls_ce: 1.7358 decode.d7.loss_mask_ce: 0.7741 decode.d7.loss_mask_dice: 1.3740 2023/09/07 19:29:35 - mmengine - INFO - Iter(train) [34900/60000] base_lr: 4.1834e-05 lr: 4.1834e-05 eta: 6:52:22 time: 0.9876 data_time: 0.0223 memory: 29189 grad_norm: 19.6007 loss: 8.4925 decode.loss_cls_ce: 1.5912 decode.loss_mask_ce: 0.8650 decode.loss_mask_dice: 1.7732 decode.d7.loss_cls_ce: 1.6297 decode.d7.loss_mask_ce: 0.8572 decode.d7.loss_mask_dice: 1.7761 2023/09/07 19:30:24 - mmengine - INFO - Iter(train) [34950/60000] base_lr: 4.1751e-05 lr: 4.1751e-05 eta: 6:51:33 time: 0.9908 data_time: 0.0218 memory: 29240 grad_norm: 18.3944 loss: 7.9496 decode.loss_cls_ce: 1.6119 decode.loss_mask_ce: 0.9183 decode.loss_mask_dice: 1.4352 decode.d7.loss_cls_ce: 1.6211 decode.d7.loss_mask_ce: 0.9166 decode.d7.loss_mask_dice: 1.4464 2023/09/07 19:31:14 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 19:31:14 - mmengine - INFO - Iter(train) [35000/60000] base_lr: 4.1667e-05 lr: 4.1667e-05 eta: 6:50:43 time: 0.9882 data_time: 0.0227 memory: 29226 grad_norm: 21.9912 loss: 9.0434 decode.loss_cls_ce: 1.8638 decode.loss_mask_ce: 0.8824 decode.loss_mask_dice: 1.7916 decode.d7.loss_cls_ce: 1.8212 decode.d7.loss_mask_ce: 0.8908 decode.d7.loss_mask_dice: 1.7937 2023/09/07 19:32:03 - mmengine - INFO - Iter(train) [35050/60000] base_lr: 4.1584e-05 lr: 4.1584e-05 eta: 6:49:54 time: 0.9883 data_time: 0.0219 memory: 29231 grad_norm: 18.6331 loss: 7.5181 decode.loss_cls_ce: 1.6327 decode.loss_mask_ce: 0.7341 decode.loss_mask_dice: 1.4085 decode.d7.loss_cls_ce: 1.5994 decode.d7.loss_mask_ce: 0.7421 decode.d7.loss_mask_dice: 1.4012 2023/09/07 19:32:53 - mmengine - INFO - Iter(train) [35100/60000] base_lr: 4.1501e-05 lr: 4.1501e-05 eta: 6:49:05 time: 0.9883 data_time: 0.0221 memory: 29318 grad_norm: 18.0412 loss: 8.8867 decode.loss_cls_ce: 1.7458 decode.loss_mask_ce: 0.8762 decode.loss_mask_dice: 1.8597 decode.d7.loss_cls_ce: 1.6526 decode.d7.loss_mask_ce: 0.8798 decode.d7.loss_mask_dice: 1.8726 2023/09/07 19:33:42 - mmengine - INFO - Iter(train) [35150/60000] base_lr: 4.1417e-05 lr: 4.1417e-05 eta: 6:48:16 time: 0.9882 data_time: 0.0221 memory: 29356 grad_norm: 18.7633 loss: 7.1439 decode.loss_cls_ce: 1.4672 decode.loss_mask_ce: 0.7623 decode.loss_mask_dice: 1.3383 decode.d7.loss_cls_ce: 1.4770 decode.d7.loss_mask_ce: 0.7668 decode.d7.loss_mask_dice: 1.3323 2023/09/07 19:34:31 - mmengine - INFO - Iter(train) [35200/60000] base_lr: 4.1334e-05 lr: 4.1334e-05 eta: 6:47:27 time: 0.9867 data_time: 0.0226 memory: 29225 grad_norm: 20.2169 loss: 7.3134 decode.loss_cls_ce: 1.5874 decode.loss_mask_ce: 0.7743 decode.loss_mask_dice: 1.2949 decode.d7.loss_cls_ce: 1.5649 decode.d7.loss_mask_ce: 0.7834 decode.d7.loss_mask_dice: 1.3086 2023/09/07 19:35:21 - mmengine - INFO - Iter(train) [35250/60000] base_lr: 4.1251e-05 lr: 4.1251e-05 eta: 6:46:37 time: 0.9893 data_time: 0.0219 memory: 29174 grad_norm: 18.9568 loss: 7.3586 decode.loss_cls_ce: 1.4654 decode.loss_mask_ce: 0.7450 decode.loss_mask_dice: 1.4691 decode.d7.loss_cls_ce: 1.4681 decode.d7.loss_mask_ce: 0.7437 decode.d7.loss_mask_dice: 1.4674 2023/09/07 19:36:10 - mmengine - INFO - Iter(train) [35300/60000] base_lr: 4.1167e-05 lr: 4.1167e-05 eta: 6:45:48 time: 0.9890 data_time: 0.0220 memory: 29204 grad_norm: 27.1137 loss: 8.6290 decode.loss_cls_ce: 1.7524 decode.loss_mask_ce: 0.9017 decode.loss_mask_dice: 1.6592 decode.d7.loss_cls_ce: 1.7418 decode.d7.loss_mask_ce: 0.9110 decode.d7.loss_mask_dice: 1.6629 2023/09/07 19:37:00 - mmengine - INFO - Iter(train) [35350/60000] base_lr: 4.1084e-05 lr: 4.1084e-05 eta: 6:44:59 time: 0.9902 data_time: 0.0224 memory: 29189 grad_norm: 21.8566 loss: 7.5691 decode.loss_cls_ce: 1.5725 decode.loss_mask_ce: 0.7674 decode.loss_mask_dice: 1.4437 decode.d7.loss_cls_ce: 1.5721 decode.d7.loss_mask_ce: 0.7611 decode.d7.loss_mask_dice: 1.4523 2023/09/07 19:37:49 - mmengine - INFO - Iter(train) [35400/60000] base_lr: 4.1001e-05 lr: 4.1001e-05 eta: 6:44:10 time: 0.9896 data_time: 0.0218 memory: 29255 grad_norm: 19.3812 loss: 7.8608 decode.loss_cls_ce: 1.6929 decode.loss_mask_ce: 0.7680 decode.loss_mask_dice: 1.4768 decode.d7.loss_cls_ce: 1.6974 decode.d7.loss_mask_ce: 0.7742 decode.d7.loss_mask_dice: 1.4515 2023/09/07 19:38:39 - mmengine - INFO - Iter(train) [35450/60000] base_lr: 4.0917e-05 lr: 4.0917e-05 eta: 6:43:21 time: 0.9891 data_time: 0.0219 memory: 29130 grad_norm: 18.5458 loss: 8.6756 decode.loss_cls_ce: 1.7575 decode.loss_mask_ce: 0.8591 decode.loss_mask_dice: 1.7194 decode.d7.loss_cls_ce: 1.7659 decode.d7.loss_mask_ce: 0.8683 decode.d7.loss_mask_dice: 1.7055 2023/09/07 19:39:28 - mmengine - INFO - Iter(train) [35500/60000] base_lr: 4.0834e-05 lr: 4.0834e-05 eta: 6:42:32 time: 0.9888 data_time: 0.0223 memory: 29251 grad_norm: 20.4384 loss: 6.9870 decode.loss_cls_ce: 1.4331 decode.loss_mask_ce: 0.6601 decode.loss_mask_dice: 1.4037 decode.d7.loss_cls_ce: 1.4563 decode.d7.loss_mask_ce: 0.6632 decode.d7.loss_mask_dice: 1.3706 2023/09/07 19:40:18 - mmengine - INFO - Iter(train) [35550/60000] base_lr: 4.0751e-05 lr: 4.0751e-05 eta: 6:41:43 time: 0.9914 data_time: 0.0224 memory: 29253 grad_norm: 23.0890 loss: 8.1117 decode.loss_cls_ce: 1.6058 decode.loss_mask_ce: 0.8461 decode.loss_mask_dice: 1.6107 decode.d7.loss_cls_ce: 1.6138 decode.d7.loss_mask_ce: 0.8336 decode.d7.loss_mask_dice: 1.6018 2023/09/07 19:41:07 - mmengine - INFO - Iter(train) [35600/60000] base_lr: 4.0667e-05 lr: 4.0667e-05 eta: 6:40:53 time: 0.9902 data_time: 0.0226 memory: 29137 grad_norm: 18.7886 loss: 7.8842 decode.loss_cls_ce: 1.6317 decode.loss_mask_ce: 0.8525 decode.loss_mask_dice: 1.4418 decode.d7.loss_cls_ce: 1.6802 decode.d7.loss_mask_ce: 0.8383 decode.d7.loss_mask_dice: 1.4397 2023/09/07 19:41:57 - mmengine - INFO - Iter(train) [35650/60000] base_lr: 4.0584e-05 lr: 4.0584e-05 eta: 6:40:04 time: 0.9888 data_time: 0.0225 memory: 29161 grad_norm: 24.7283 loss: 8.2262 decode.loss_cls_ce: 1.7082 decode.loss_mask_ce: 0.8509 decode.loss_mask_dice: 1.5648 decode.d7.loss_cls_ce: 1.7134 decode.d7.loss_mask_ce: 0.8436 decode.d7.loss_mask_dice: 1.5453 2023/09/07 19:42:46 - mmengine - INFO - Iter(train) [35700/60000] base_lr: 4.0501e-05 lr: 4.0501e-05 eta: 6:39:15 time: 0.9912 data_time: 0.0227 memory: 29227 grad_norm: 22.1920 loss: 7.6672 decode.loss_cls_ce: 1.4103 decode.loss_mask_ce: 0.8454 decode.loss_mask_dice: 1.5663 decode.d7.loss_cls_ce: 1.4669 decode.d7.loss_mask_ce: 0.8253 decode.d7.loss_mask_dice: 1.5531 2023/09/07 19:43:36 - mmengine - INFO - Iter(train) [35750/60000] base_lr: 4.0417e-05 lr: 4.0417e-05 eta: 6:38:26 time: 0.9883 data_time: 0.0220 memory: 29231 grad_norm: 16.8728 loss: 8.1826 decode.loss_cls_ce: 1.7332 decode.loss_mask_ce: 0.8090 decode.loss_mask_dice: 1.5766 decode.d7.loss_cls_ce: 1.6933 decode.d7.loss_mask_ce: 0.8151 decode.d7.loss_mask_dice: 1.5555 2023/09/07 19:44:25 - mmengine - INFO - Iter(train) [35800/60000] base_lr: 4.0334e-05 lr: 4.0334e-05 eta: 6:37:37 time: 0.9889 data_time: 0.0216 memory: 29140 grad_norm: 18.2510 loss: 8.4091 decode.loss_cls_ce: 1.5227 decode.loss_mask_ce: 0.8987 decode.loss_mask_dice: 1.7744 decode.d7.loss_cls_ce: 1.5637 decode.d7.loss_mask_ce: 0.8936 decode.d7.loss_mask_dice: 1.7560 2023/09/07 19:45:15 - mmengine - INFO - Iter(train) [35850/60000] base_lr: 4.0251e-05 lr: 4.0251e-05 eta: 6:36:47 time: 0.9890 data_time: 0.0232 memory: 29191 grad_norm: 18.5735 loss: 7.8892 decode.loss_cls_ce: 1.6462 decode.loss_mask_ce: 0.8128 decode.loss_mask_dice: 1.4773 decode.d7.loss_cls_ce: 1.6739 decode.d7.loss_mask_ce: 0.8044 decode.d7.loss_mask_dice: 1.4747 2023/09/07 19:46:04 - mmengine - INFO - Iter(train) [35900/60000] base_lr: 4.0167e-05 lr: 4.0167e-05 eta: 6:35:58 time: 0.9909 data_time: 0.0221 memory: 29163 grad_norm: 17.1946 loss: 6.7788 decode.loss_cls_ce: 1.4131 decode.loss_mask_ce: 0.7151 decode.loss_mask_dice: 1.2787 decode.d7.loss_cls_ce: 1.3988 decode.d7.loss_mask_ce: 0.7189 decode.d7.loss_mask_dice: 1.2543 2023/09/07 19:46:54 - mmengine - INFO - Iter(train) [35950/60000] base_lr: 4.0084e-05 lr: 4.0084e-05 eta: 6:35:09 time: 0.9889 data_time: 0.0221 memory: 29195 grad_norm: 18.9168 loss: 8.7905 decode.loss_cls_ce: 1.9323 decode.loss_mask_ce: 0.8242 decode.loss_mask_dice: 1.6388 decode.d7.loss_cls_ce: 1.9349 decode.d7.loss_mask_ce: 0.8299 decode.d7.loss_mask_dice: 1.6304 2023/09/07 19:47:43 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 19:47:43 - mmengine - INFO - Iter(train) [36000/60000] base_lr: 4.0001e-05 lr: 4.0001e-05 eta: 6:34:20 time: 0.9893 data_time: 0.0219 memory: 29217 grad_norm: 18.1623 loss: 7.8306 decode.loss_cls_ce: 1.5648 decode.loss_mask_ce: 0.8001 decode.loss_mask_dice: 1.5400 decode.d7.loss_cls_ce: 1.5659 decode.d7.loss_mask_ce: 0.8074 decode.d7.loss_mask_dice: 1.5523 2023/09/07 19:48:33 - mmengine - INFO - Iter(train) [36050/60000] base_lr: 3.9917e-05 lr: 3.9917e-05 eta: 6:33:31 time: 0.9882 data_time: 0.0218 memory: 29257 grad_norm: 17.2366 loss: 8.2127 decode.loss_cls_ce: 1.6690 decode.loss_mask_ce: 0.7575 decode.loss_mask_dice: 1.6668 decode.d7.loss_cls_ce: 1.6875 decode.d7.loss_mask_ce: 0.7707 decode.d7.loss_mask_dice: 1.6612 2023/09/07 19:49:22 - mmengine - INFO - Iter(train) [36100/60000] base_lr: 3.9834e-05 lr: 3.9834e-05 eta: 6:32:42 time: 0.9883 data_time: 0.0223 memory: 29150 grad_norm: 16.9067 loss: 8.5625 decode.loss_cls_ce: 1.7909 decode.loss_mask_ce: 0.8639 decode.loss_mask_dice: 1.6141 decode.d7.loss_cls_ce: 1.8136 decode.d7.loss_mask_ce: 0.8550 decode.d7.loss_mask_dice: 1.6251 2023/09/07 19:50:12 - mmengine - INFO - Iter(train) [36150/60000] base_lr: 3.9751e-05 lr: 3.9751e-05 eta: 6:31:52 time: 0.9868 data_time: 0.0217 memory: 29154 grad_norm: 17.8448 loss: 7.3705 decode.loss_cls_ce: 1.4499 decode.loss_mask_ce: 0.7592 decode.loss_mask_dice: 1.5004 decode.d7.loss_cls_ce: 1.4579 decode.d7.loss_mask_ce: 0.7500 decode.d7.loss_mask_dice: 1.4531 2023/09/07 19:51:01 - mmengine - INFO - Iter(train) [36200/60000] base_lr: 3.9667e-05 lr: 3.9667e-05 eta: 6:31:03 time: 0.9889 data_time: 0.0215 memory: 29264 grad_norm: 17.8307 loss: 7.3747 decode.loss_cls_ce: 1.3915 decode.loss_mask_ce: 0.8309 decode.loss_mask_dice: 1.4536 decode.d7.loss_cls_ce: 1.4173 decode.d7.loss_mask_ce: 0.8096 decode.d7.loss_mask_dice: 1.4716 2023/09/07 19:51:51 - mmengine - INFO - Iter(train) [36250/60000] base_lr: 3.9584e-05 lr: 3.9584e-05 eta: 6:30:14 time: 0.9875 data_time: 0.0229 memory: 29174 grad_norm: 17.1850 loss: 9.4046 decode.loss_cls_ce: 1.8876 decode.loss_mask_ce: 0.8653 decode.loss_mask_dice: 1.9661 decode.d7.loss_cls_ce: 1.8569 decode.d7.loss_mask_ce: 0.8716 decode.d7.loss_mask_dice: 1.9572 2023/09/07 19:52:40 - mmengine - INFO - Iter(train) [36300/60000] base_lr: 3.9501e-05 lr: 3.9501e-05 eta: 6:29:25 time: 0.9865 data_time: 0.0223 memory: 29146 grad_norm: 20.4146 loss: 7.9755 decode.loss_cls_ce: 1.5790 decode.loss_mask_ce: 0.9175 decode.loss_mask_dice: 1.4813 decode.d7.loss_cls_ce: 1.6198 decode.d7.loss_mask_ce: 0.9083 decode.d7.loss_mask_dice: 1.4695 2023/09/07 19:53:29 - mmengine - INFO - Iter(train) [36350/60000] base_lr: 3.9417e-05 lr: 3.9417e-05 eta: 6:28:36 time: 0.9889 data_time: 0.0220 memory: 29252 grad_norm: 17.6079 loss: 9.7949 decode.loss_cls_ce: 2.1873 decode.loss_mask_ce: 0.8752 decode.loss_mask_dice: 1.8230 decode.d7.loss_cls_ce: 2.2124 decode.d7.loss_mask_ce: 0.8682 decode.d7.loss_mask_dice: 1.8287 2023/09/07 19:54:19 - mmengine - INFO - Iter(train) [36400/60000] base_lr: 3.9334e-05 lr: 3.9334e-05 eta: 6:27:46 time: 0.9882 data_time: 0.0221 memory: 29231 grad_norm: 18.5909 loss: 8.3958 decode.loss_cls_ce: 1.7708 decode.loss_mask_ce: 0.7977 decode.loss_mask_dice: 1.6190 decode.d7.loss_cls_ce: 1.8151 decode.d7.loss_mask_ce: 0.8014 decode.d7.loss_mask_dice: 1.5918 2023/09/07 19:55:08 - mmengine - INFO - Iter(train) [36450/60000] base_lr: 3.9251e-05 lr: 3.9251e-05 eta: 6:26:57 time: 0.9850 data_time: 0.0221 memory: 29142 grad_norm: 19.3028 loss: 8.0232 decode.loss_cls_ce: 1.8087 decode.loss_mask_ce: 0.7396 decode.loss_mask_dice: 1.4507 decode.d7.loss_cls_ce: 1.8476 decode.d7.loss_mask_ce: 0.7303 decode.d7.loss_mask_dice: 1.4463 2023/09/07 19:55:57 - mmengine - INFO - Iter(train) [36500/60000] base_lr: 3.9167e-05 lr: 3.9167e-05 eta: 6:26:08 time: 0.9867 data_time: 0.0225 memory: 29191 grad_norm: 18.9143 loss: 8.0193 decode.loss_cls_ce: 1.6901 decode.loss_mask_ce: 0.8267 decode.loss_mask_dice: 1.4766 decode.d7.loss_cls_ce: 1.7207 decode.d7.loss_mask_ce: 0.8268 decode.d7.loss_mask_dice: 1.4785 2023/09/07 19:56:47 - mmengine - INFO - Iter(train) [36550/60000] base_lr: 3.9084e-05 lr: 3.9084e-05 eta: 6:25:19 time: 0.9879 data_time: 0.0225 memory: 29242 grad_norm: 16.9453 loss: 7.6215 decode.loss_cls_ce: 1.5580 decode.loss_mask_ce: 0.7948 decode.loss_mask_dice: 1.4515 decode.d7.loss_cls_ce: 1.5342 decode.d7.loss_mask_ce: 0.8097 decode.d7.loss_mask_dice: 1.4734 2023/09/07 19:57:36 - mmengine - INFO - Iter(train) [36600/60000] base_lr: 3.9001e-05 lr: 3.9001e-05 eta: 6:24:29 time: 0.9916 data_time: 0.0219 memory: 29188 grad_norm: 18.0329 loss: 8.2948 decode.loss_cls_ce: 1.7025 decode.loss_mask_ce: 0.7786 decode.loss_mask_dice: 1.6471 decode.d7.loss_cls_ce: 1.7292 decode.d7.loss_mask_ce: 0.7780 decode.d7.loss_mask_dice: 1.6593 2023/09/07 19:58:26 - mmengine - INFO - Iter(train) [36650/60000] base_lr: 3.8917e-05 lr: 3.8917e-05 eta: 6:23:40 time: 0.9910 data_time: 0.0222 memory: 29294 grad_norm: 22.7441 loss: 9.9674 decode.loss_cls_ce: 2.0688 decode.loss_mask_ce: 1.0056 decode.loss_mask_dice: 1.9196 decode.d7.loss_cls_ce: 2.0506 decode.d7.loss_mask_ce: 1.0139 decode.d7.loss_mask_dice: 1.9088 2023/09/07 19:59:15 - mmengine - INFO - Iter(train) [36700/60000] base_lr: 3.8834e-05 lr: 3.8834e-05 eta: 6:22:51 time: 0.9891 data_time: 0.0222 memory: 29304 grad_norm: 19.3577 loss: 8.8743 decode.loss_cls_ce: 1.7019 decode.loss_mask_ce: 0.9052 decode.loss_mask_dice: 1.8360 decode.d7.loss_cls_ce: 1.6541 decode.d7.loss_mask_ce: 0.9108 decode.d7.loss_mask_dice: 1.8663 2023/09/07 20:00:05 - mmengine - INFO - Iter(train) [36750/60000] base_lr: 3.8751e-05 lr: 3.8751e-05 eta: 6:22:02 time: 0.9918 data_time: 0.0218 memory: 29229 grad_norm: 20.2299 loss: 7.1288 decode.loss_cls_ce: 1.3988 decode.loss_mask_ce: 0.7477 decode.loss_mask_dice: 1.4179 decode.d7.loss_cls_ce: 1.4235 decode.d7.loss_mask_ce: 0.7474 decode.d7.loss_mask_dice: 1.3934 2023/09/07 20:00:54 - mmengine - INFO - Iter(train) [36800/60000] base_lr: 3.8667e-05 lr: 3.8667e-05 eta: 6:21:13 time: 0.9910 data_time: 0.0230 memory: 29265 grad_norm: 18.2677 loss: 7.4832 decode.loss_cls_ce: 1.3786 decode.loss_mask_ce: 0.8011 decode.loss_mask_dice: 1.5437 decode.d7.loss_cls_ce: 1.3814 decode.d7.loss_mask_ce: 0.8065 decode.d7.loss_mask_dice: 1.5720 2023/09/07 20:01:44 - mmengine - INFO - Iter(train) [36850/60000] base_lr: 3.8584e-05 lr: 3.8584e-05 eta: 6:20:24 time: 0.9909 data_time: 0.0221 memory: 29186 grad_norm: 17.7738 loss: 8.8569 decode.loss_cls_ce: 1.7431 decode.loss_mask_ce: 0.8602 decode.loss_mask_dice: 1.8182 decode.d7.loss_cls_ce: 1.7118 decode.d7.loss_mask_ce: 0.8741 decode.d7.loss_mask_dice: 1.8495 2023/09/07 20:02:33 - mmengine - INFO - Iter(train) [36900/60000] base_lr: 3.8501e-05 lr: 3.8501e-05 eta: 6:19:34 time: 0.9878 data_time: 0.0224 memory: 29283 grad_norm: 24.9757 loss: 7.8808 decode.loss_cls_ce: 1.4772 decode.loss_mask_ce: 0.9360 decode.loss_mask_dice: 1.5247 decode.d7.loss_cls_ce: 1.5362 decode.d7.loss_mask_ce: 0.9170 decode.d7.loss_mask_dice: 1.4898 2023/09/07 20:03:23 - mmengine - INFO - Iter(train) [36950/60000] base_lr: 3.8417e-05 lr: 3.8417e-05 eta: 6:18:45 time: 0.9878 data_time: 0.0222 memory: 29226 grad_norm: 20.3229 loss: 8.5788 decode.loss_cls_ce: 1.7449 decode.loss_mask_ce: 0.8716 decode.loss_mask_dice: 1.6641 decode.d7.loss_cls_ce: 1.7468 decode.d7.loss_mask_ce: 0.8855 decode.d7.loss_mask_dice: 1.6660 2023/09/07 20:04:12 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 20:04:12 - mmengine - INFO - Iter(train) [37000/60000] base_lr: 3.8334e-05 lr: 3.8334e-05 eta: 6:17:56 time: 0.9919 data_time: 0.0217 memory: 29176 grad_norm: 17.2772 loss: 7.7507 decode.loss_cls_ce: 1.6306 decode.loss_mask_ce: 0.7405 decode.loss_mask_dice: 1.5159 decode.d7.loss_cls_ce: 1.6159 decode.d7.loss_mask_ce: 0.7440 decode.d7.loss_mask_dice: 1.5038 2023/09/07 20:05:02 - mmengine - INFO - Iter(train) [37050/60000] base_lr: 3.8251e-05 lr: 3.8251e-05 eta: 6:17:07 time: 0.9902 data_time: 0.0217 memory: 29225 grad_norm: 18.1542 loss: 7.1029 decode.loss_cls_ce: 1.5241 decode.loss_mask_ce: 0.7228 decode.loss_mask_dice: 1.3034 decode.d7.loss_cls_ce: 1.5207 decode.d7.loss_mask_ce: 0.7220 decode.d7.loss_mask_dice: 1.3099 2023/09/07 20:05:51 - mmengine - INFO - Iter(train) [37100/60000] base_lr: 3.8167e-05 lr: 3.8167e-05 eta: 6:16:18 time: 0.9897 data_time: 0.0226 memory: 29137 grad_norm: 21.6866 loss: 7.5754 decode.loss_cls_ce: 1.3686 decode.loss_mask_ce: 0.8484 decode.loss_mask_dice: 1.5579 decode.d7.loss_cls_ce: 1.3809 decode.d7.loss_mask_ce: 0.8475 decode.d7.loss_mask_dice: 1.5720 2023/09/07 20:06:41 - mmengine - INFO - Iter(train) [37150/60000] base_lr: 3.8084e-05 lr: 3.8084e-05 eta: 6:15:28 time: 0.9901 data_time: 0.0221 memory: 29153 grad_norm: 19.7972 loss: 8.5638 decode.loss_cls_ce: 1.6987 decode.loss_mask_ce: 0.8645 decode.loss_mask_dice: 1.7296 decode.d7.loss_cls_ce: 1.6565 decode.d7.loss_mask_ce: 0.8601 decode.d7.loss_mask_dice: 1.7544 2023/09/07 20:07:30 - mmengine - INFO - Iter(train) [37200/60000] base_lr: 3.8001e-05 lr: 3.8001e-05 eta: 6:14:39 time: 0.9883 data_time: 0.0225 memory: 29258 grad_norm: 22.4095 loss: 7.7569 decode.loss_cls_ce: 1.5982 decode.loss_mask_ce: 0.7986 decode.loss_mask_dice: 1.4807 decode.d7.loss_cls_ce: 1.5977 decode.d7.loss_mask_ce: 0.8006 decode.d7.loss_mask_dice: 1.4811 2023/09/07 20:08:20 - mmengine - INFO - Iter(train) [37250/60000] base_lr: 3.7917e-05 lr: 3.7917e-05 eta: 6:13:50 time: 0.9895 data_time: 0.0220 memory: 29154 grad_norm: 17.9526 loss: 7.3310 decode.loss_cls_ce: 1.4705 decode.loss_mask_ce: 0.7713 decode.loss_mask_dice: 1.4429 decode.d7.loss_cls_ce: 1.4252 decode.d7.loss_mask_ce: 0.7740 decode.d7.loss_mask_dice: 1.4471 2023/09/07 20:09:09 - mmengine - INFO - Iter(train) [37300/60000] base_lr: 3.7834e-05 lr: 3.7834e-05 eta: 6:13:01 time: 0.9926 data_time: 0.0219 memory: 29114 grad_norm: 22.4186 loss: 8.0808 decode.loss_cls_ce: 1.6632 decode.loss_mask_ce: 0.9059 decode.loss_mask_dice: 1.4628 decode.d7.loss_cls_ce: 1.6664 decode.d7.loss_mask_ce: 0.9255 decode.d7.loss_mask_dice: 1.4571 2023/09/07 20:09:59 - mmengine - INFO - Iter(train) [37350/60000] base_lr: 3.7751e-05 lr: 3.7751e-05 eta: 6:12:12 time: 0.9882 data_time: 0.0220 memory: 29179 grad_norm: 16.9834 loss: 6.1372 decode.loss_cls_ce: 1.2464 decode.loss_mask_ce: 0.6904 decode.loss_mask_dice: 1.1414 decode.d7.loss_cls_ce: 1.2346 decode.d7.loss_mask_ce: 0.6854 decode.d7.loss_mask_dice: 1.1389 2023/09/07 20:10:48 - mmengine - INFO - Iter(train) [37400/60000] base_lr: 3.7667e-05 lr: 3.7667e-05 eta: 6:11:22 time: 0.9870 data_time: 0.0224 memory: 29175 grad_norm: 19.1715 loss: 8.2181 decode.loss_cls_ce: 1.5708 decode.loss_mask_ce: 0.8813 decode.loss_mask_dice: 1.6557 decode.d7.loss_cls_ce: 1.5830 decode.d7.loss_mask_ce: 0.8827 decode.d7.loss_mask_dice: 1.6445 2023/09/07 20:11:38 - mmengine - INFO - Iter(train) [37450/60000] base_lr: 3.7584e-05 lr: 3.7584e-05 eta: 6:10:33 time: 0.9895 data_time: 0.0221 memory: 29149 grad_norm: 19.0000 loss: 8.1165 decode.loss_cls_ce: 1.7044 decode.loss_mask_ce: 0.8112 decode.loss_mask_dice: 1.5374 decode.d7.loss_cls_ce: 1.6983 decode.d7.loss_mask_ce: 0.8141 decode.d7.loss_mask_dice: 1.5511 2023/09/07 20:12:27 - mmengine - INFO - Iter(train) [37500/60000] base_lr: 3.7501e-05 lr: 3.7501e-05 eta: 6:09:44 time: 0.9919 data_time: 0.0218 memory: 29345 grad_norm: 18.3969 loss: 7.2821 decode.loss_cls_ce: 1.4829 decode.loss_mask_ce: 0.7672 decode.loss_mask_dice: 1.3752 decode.d7.loss_cls_ce: 1.5261 decode.d7.loss_mask_ce: 0.7810 decode.d7.loss_mask_dice: 1.3496 2023/09/07 20:13:17 - mmengine - INFO - Iter(train) [37550/60000] base_lr: 3.7417e-05 lr: 3.7417e-05 eta: 6:08:55 time: 0.9903 data_time: 0.0224 memory: 29180 grad_norm: 21.2185 loss: 7.1884 decode.loss_cls_ce: 1.4255 decode.loss_mask_ce: 0.7958 decode.loss_mask_dice: 1.3482 decode.d7.loss_cls_ce: 1.4632 decode.d7.loss_mask_ce: 0.7938 decode.d7.loss_mask_dice: 1.3619 2023/09/07 20:14:06 - mmengine - INFO - Iter(train) [37600/60000] base_lr: 3.7334e-05 lr: 3.7334e-05 eta: 6:08:06 time: 0.9909 data_time: 0.0224 memory: 29161 grad_norm: 16.6237 loss: 9.8508 decode.loss_cls_ce: 1.9435 decode.loss_mask_ce: 1.0184 decode.loss_mask_dice: 1.9539 decode.d7.loss_cls_ce: 1.9907 decode.d7.loss_mask_ce: 1.0179 decode.d7.loss_mask_dice: 1.9265 2023/09/07 20:14:56 - mmengine - INFO - Iter(train) [37650/60000] base_lr: 3.7251e-05 lr: 3.7251e-05 eta: 6:07:16 time: 0.9890 data_time: 0.0219 memory: 29163 grad_norm: 17.3229 loss: 8.1266 decode.loss_cls_ce: 1.6205 decode.loss_mask_ce: 0.8065 decode.loss_mask_dice: 1.5970 decode.d7.loss_cls_ce: 1.6739 decode.d7.loss_mask_ce: 0.8082 decode.d7.loss_mask_dice: 1.6205 2023/09/07 20:15:45 - mmengine - INFO - Iter(train) [37700/60000] base_lr: 3.7167e-05 lr: 3.7167e-05 eta: 6:06:27 time: 0.9924 data_time: 0.0218 memory: 29165 grad_norm: 20.7876 loss: 6.9487 decode.loss_cls_ce: 1.5558 decode.loss_mask_ce: 0.7511 decode.loss_mask_dice: 1.1770 decode.d7.loss_cls_ce: 1.5137 decode.d7.loss_mask_ce: 0.7675 decode.d7.loss_mask_dice: 1.1837 2023/09/07 20:16:35 - mmengine - INFO - Iter(train) [37750/60000] base_lr: 3.7084e-05 lr: 3.7084e-05 eta: 6:05:38 time: 0.9904 data_time: 0.0231 memory: 29168 grad_norm: 19.1303 loss: 7.8759 decode.loss_cls_ce: 1.6145 decode.loss_mask_ce: 0.8253 decode.loss_mask_dice: 1.4979 decode.d7.loss_cls_ce: 1.6247 decode.d7.loss_mask_ce: 0.8254 decode.d7.loss_mask_dice: 1.4881 2023/09/07 20:17:24 - mmengine - INFO - Iter(train) [37800/60000] base_lr: 3.7001e-05 lr: 3.7001e-05 eta: 6:04:49 time: 0.9893 data_time: 0.0211 memory: 29206 grad_norm: 19.7291 loss: 9.3377 decode.loss_cls_ce: 1.8383 decode.loss_mask_ce: 0.9304 decode.loss_mask_dice: 1.8855 decode.d7.loss_cls_ce: 1.8545 decode.d7.loss_mask_ce: 0.9196 decode.d7.loss_mask_dice: 1.9094 2023/09/07 20:18:14 - mmengine - INFO - Iter(train) [37850/60000] base_lr: 3.6917e-05 lr: 3.6917e-05 eta: 6:04:00 time: 0.9926 data_time: 0.0228 memory: 29189 grad_norm: 17.5863 loss: 8.9675 decode.loss_cls_ce: 1.6934 decode.loss_mask_ce: 0.9825 decode.loss_mask_dice: 1.8102 decode.d7.loss_cls_ce: 1.6920 decode.d7.loss_mask_ce: 0.9716 decode.d7.loss_mask_dice: 1.8178 2023/09/07 20:19:03 - mmengine - INFO - Iter(train) [37900/60000] base_lr: 3.6834e-05 lr: 3.6834e-05 eta: 6:03:11 time: 0.9918 data_time: 0.0221 memory: 29266 grad_norm: 16.5623 loss: 8.5326 decode.loss_cls_ce: 1.6874 decode.loss_mask_ce: 0.8915 decode.loss_mask_dice: 1.6814 decode.d7.loss_cls_ce: 1.7517 decode.d7.loss_mask_ce: 0.8753 decode.d7.loss_mask_dice: 1.6452 2023/09/07 20:19:53 - mmengine - INFO - Iter(train) [37950/60000] base_lr: 3.6751e-05 lr: 3.6751e-05 eta: 6:02:21 time: 0.9880 data_time: 0.0220 memory: 29266 grad_norm: 17.3429 loss: 7.8192 decode.loss_cls_ce: 1.5182 decode.loss_mask_ce: 0.8250 decode.loss_mask_dice: 1.5689 decode.d7.loss_cls_ce: 1.5423 decode.d7.loss_mask_ce: 0.8259 decode.d7.loss_mask_dice: 1.5390 2023/09/07 20:20:42 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 20:20:42 - mmengine - INFO - Iter(train) [38000/60000] base_lr: 3.6667e-05 lr: 3.6667e-05 eta: 6:01:32 time: 0.9891 data_time: 0.0228 memory: 29225 grad_norm: 19.6213 loss: 7.4800 decode.loss_cls_ce: 1.4970 decode.loss_mask_ce: 0.7973 decode.loss_mask_dice: 1.4521 decode.d7.loss_cls_ce: 1.4901 decode.d7.loss_mask_ce: 0.7822 decode.d7.loss_mask_dice: 1.4612 2023/09/07 20:21:32 - mmengine - INFO - Iter(train) [38050/60000] base_lr: 3.6584e-05 lr: 3.6584e-05 eta: 6:00:43 time: 0.9896 data_time: 0.0224 memory: 29293 grad_norm: 19.1154 loss: 8.0572 decode.loss_cls_ce: 1.6881 decode.loss_mask_ce: 0.8059 decode.loss_mask_dice: 1.5336 decode.d7.loss_cls_ce: 1.6928 decode.d7.loss_mask_ce: 0.8059 decode.d7.loss_mask_dice: 1.5307 2023/09/07 20:22:21 - mmengine - INFO - Iter(train) [38100/60000] base_lr: 3.6501e-05 lr: 3.6501e-05 eta: 5:59:54 time: 0.9903 data_time: 0.0227 memory: 29129 grad_norm: 21.1652 loss: 7.8034 decode.loss_cls_ce: 1.5365 decode.loss_mask_ce: 0.8911 decode.loss_mask_dice: 1.4709 decode.d7.loss_cls_ce: 1.5258 decode.d7.loss_mask_ce: 0.9086 decode.d7.loss_mask_dice: 1.4706 2023/09/07 20:23:11 - mmengine - INFO - Iter(train) [38150/60000] base_lr: 3.6417e-05 lr: 3.6417e-05 eta: 5:59:05 time: 0.9865 data_time: 0.0231 memory: 29241 grad_norm: 21.4656 loss: 7.7888 decode.loss_cls_ce: 1.6337 decode.loss_mask_ce: 0.7774 decode.loss_mask_dice: 1.4551 decode.d7.loss_cls_ce: 1.6546 decode.d7.loss_mask_ce: 0.8004 decode.d7.loss_mask_dice: 1.4675 2023/09/07 20:24:00 - mmengine - INFO - Iter(train) [38200/60000] base_lr: 3.6334e-05 lr: 3.6334e-05 eta: 5:58:15 time: 0.9892 data_time: 0.0225 memory: 29142 grad_norm: 19.4393 loss: 7.3327 decode.loss_cls_ce: 1.3483 decode.loss_mask_ce: 0.7740 decode.loss_mask_dice: 1.5380 decode.d7.loss_cls_ce: 1.3684 decode.d7.loss_mask_ce: 0.7769 decode.d7.loss_mask_dice: 1.5271 2023/09/07 20:24:50 - mmengine - INFO - Iter(train) [38250/60000] base_lr: 3.6251e-05 lr: 3.6251e-05 eta: 5:57:26 time: 0.9893 data_time: 0.0226 memory: 29231 grad_norm: 18.8608 loss: 7.8484 decode.loss_cls_ce: 1.5298 decode.loss_mask_ce: 0.7436 decode.loss_mask_dice: 1.6405 decode.d7.loss_cls_ce: 1.5670 decode.d7.loss_mask_ce: 0.7479 decode.d7.loss_mask_dice: 1.6196 2023/09/07 20:25:39 - mmengine - INFO - Iter(train) [38300/60000] base_lr: 3.6167e-05 lr: 3.6167e-05 eta: 5:56:37 time: 0.9916 data_time: 0.0223 memory: 29204 grad_norm: 21.6583 loss: 7.8780 decode.loss_cls_ce: 1.6496 decode.loss_mask_ce: 0.8168 decode.loss_mask_dice: 1.4693 decode.d7.loss_cls_ce: 1.6551 decode.d7.loss_mask_ce: 0.8112 decode.d7.loss_mask_dice: 1.4760 2023/09/07 20:26:29 - mmengine - INFO - Iter(train) [38350/60000] base_lr: 3.6084e-05 lr: 3.6084e-05 eta: 5:55:48 time: 0.9928 data_time: 0.0218 memory: 29208 grad_norm: 18.7751 loss: 7.2960 decode.loss_cls_ce: 1.4349 decode.loss_mask_ce: 0.7595 decode.loss_mask_dice: 1.4305 decode.d7.loss_cls_ce: 1.4772 decode.d7.loss_mask_ce: 0.7691 decode.d7.loss_mask_dice: 1.4248 2023/09/07 20:27:18 - mmengine - INFO - Iter(train) [38400/60000] base_lr: 3.6001e-05 lr: 3.6001e-05 eta: 5:54:58 time: 0.9871 data_time: 0.0220 memory: 29141 grad_norm: 17.7636 loss: 8.1826 decode.loss_cls_ce: 1.6337 decode.loss_mask_ce: 0.8900 decode.loss_mask_dice: 1.5937 decode.d7.loss_cls_ce: 1.6054 decode.d7.loss_mask_ce: 0.8730 decode.d7.loss_mask_dice: 1.5867 2023/09/07 20:28:08 - mmengine - INFO - Iter(train) [38450/60000] base_lr: 3.5917e-05 lr: 3.5917e-05 eta: 5:54:09 time: 0.9887 data_time: 0.0224 memory: 29100 grad_norm: 19.6141 loss: 7.8347 decode.loss_cls_ce: 1.5898 decode.loss_mask_ce: 0.8090 decode.loss_mask_dice: 1.5105 decode.d7.loss_cls_ce: 1.5896 decode.d7.loss_mask_ce: 0.8144 decode.d7.loss_mask_dice: 1.5215 2023/09/07 20:28:57 - mmengine - INFO - Iter(train) [38500/60000] base_lr: 3.5834e-05 lr: 3.5834e-05 eta: 5:53:20 time: 0.9891 data_time: 0.0230 memory: 29150 grad_norm: 20.4660 loss: 8.7401 decode.loss_cls_ce: 1.8061 decode.loss_mask_ce: 0.8956 decode.loss_mask_dice: 1.6782 decode.d7.loss_cls_ce: 1.7633 decode.d7.loss_mask_ce: 0.8935 decode.d7.loss_mask_dice: 1.7034 2023/09/07 20:29:47 - mmengine - INFO - Iter(train) [38550/60000] base_lr: 3.5751e-05 lr: 3.5751e-05 eta: 5:52:31 time: 0.9884 data_time: 0.0221 memory: 29202 grad_norm: 19.9124 loss: 6.5884 decode.loss_cls_ce: 1.2699 decode.loss_mask_ce: 0.7603 decode.loss_mask_dice: 1.2571 decode.d7.loss_cls_ce: 1.2895 decode.d7.loss_mask_ce: 0.7522 decode.d7.loss_mask_dice: 1.2593 2023/09/07 20:30:36 - mmengine - INFO - Iter(train) [38600/60000] base_lr: 3.5667e-05 lr: 3.5667e-05 eta: 5:51:42 time: 0.9901 data_time: 0.0225 memory: 29155 grad_norm: 18.5599 loss: 8.6318 decode.loss_cls_ce: 1.6155 decode.loss_mask_ce: 0.8539 decode.loss_mask_dice: 1.8359 decode.d7.loss_cls_ce: 1.6019 decode.d7.loss_mask_ce: 0.8664 decode.d7.loss_mask_dice: 1.8583 2023/09/07 20:31:25 - mmengine - INFO - Iter(train) [38650/60000] base_lr: 3.5584e-05 lr: 3.5584e-05 eta: 5:50:52 time: 0.9907 data_time: 0.0227 memory: 29218 grad_norm: 18.7535 loss: 6.3771 decode.loss_cls_ce: 1.3974 decode.loss_mask_ce: 0.6632 decode.loss_mask_dice: 1.1102 decode.d7.loss_cls_ce: 1.4279 decode.d7.loss_mask_ce: 0.6775 decode.d7.loss_mask_dice: 1.1008 2023/09/07 20:32:15 - mmengine - INFO - Iter(train) [38700/60000] base_lr: 3.5501e-05 lr: 3.5501e-05 eta: 5:50:03 time: 0.9912 data_time: 0.0220 memory: 29100 grad_norm: 21.2348 loss: 7.3017 decode.loss_cls_ce: 1.5848 decode.loss_mask_ce: 0.6854 decode.loss_mask_dice: 1.3640 decode.d7.loss_cls_ce: 1.6197 decode.d7.loss_mask_ce: 0.6822 decode.d7.loss_mask_dice: 1.3655 2023/09/07 20:33:05 - mmengine - INFO - Iter(train) [38750/60000] base_lr: 3.5417e-05 lr: 3.5417e-05 eta: 5:49:14 time: 0.9925 data_time: 0.0224 memory: 29189 grad_norm: 22.8199 loss: 9.1176 decode.loss_cls_ce: 1.8179 decode.loss_mask_ce: 0.8866 decode.loss_mask_dice: 1.8653 decode.d7.loss_cls_ce: 1.8214 decode.d7.loss_mask_ce: 0.8777 decode.d7.loss_mask_dice: 1.8488 2023/09/07 20:33:54 - mmengine - INFO - Iter(train) [38800/60000] base_lr: 3.5334e-05 lr: 3.5334e-05 eta: 5:48:25 time: 0.9877 data_time: 0.0219 memory: 29228 grad_norm: 18.0383 loss: 7.9578 decode.loss_cls_ce: 1.4448 decode.loss_mask_ce: 0.8911 decode.loss_mask_dice: 1.6405 decode.d7.loss_cls_ce: 1.4156 decode.d7.loss_mask_ce: 0.9030 decode.d7.loss_mask_dice: 1.6628 2023/09/07 20:34:44 - mmengine - INFO - Iter(train) [38850/60000] base_lr: 3.5251e-05 lr: 3.5251e-05 eta: 5:47:36 time: 0.9884 data_time: 0.0231 memory: 29315 grad_norm: 19.5512 loss: 9.3813 decode.loss_cls_ce: 1.8498 decode.loss_mask_ce: 0.9638 decode.loss_mask_dice: 1.8906 decode.d7.loss_cls_ce: 1.8318 decode.d7.loss_mask_ce: 0.9564 decode.d7.loss_mask_dice: 1.8889 2023/09/07 20:35:33 - mmengine - INFO - Iter(train) [38900/60000] base_lr: 3.5167e-05 lr: 3.5167e-05 eta: 5:46:46 time: 0.9872 data_time: 0.0222 memory: 29092 grad_norm: 17.4995 loss: 7.1215 decode.loss_cls_ce: 1.3930 decode.loss_mask_ce: 0.7251 decode.loss_mask_dice: 1.4266 decode.d7.loss_cls_ce: 1.4226 decode.d7.loss_mask_ce: 0.7155 decode.d7.loss_mask_dice: 1.4387 2023/09/07 20:36:23 - mmengine - INFO - Iter(train) [38950/60000] base_lr: 3.5084e-05 lr: 3.5084e-05 eta: 5:45:57 time: 0.9911 data_time: 0.0221 memory: 29139 grad_norm: 21.3210 loss: 9.0251 decode.loss_cls_ce: 1.8560 decode.loss_mask_ce: 0.9069 decode.loss_mask_dice: 1.7376 decode.d7.loss_cls_ce: 1.8847 decode.d7.loss_mask_ce: 0.9074 decode.d7.loss_mask_dice: 1.7325 2023/09/07 20:37:12 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 20:37:12 - mmengine - INFO - Iter(train) [39000/60000] base_lr: 3.5001e-05 lr: 3.5001e-05 eta: 5:45:08 time: 0.9864 data_time: 0.0228 memory: 29155 grad_norm: 17.7828 loss: 8.7423 decode.loss_cls_ce: 1.8390 decode.loss_mask_ce: 0.8238 decode.loss_mask_dice: 1.7155 decode.d7.loss_cls_ce: 1.8322 decode.d7.loss_mask_ce: 0.8169 decode.d7.loss_mask_dice: 1.7149 2023/09/07 20:38:02 - mmengine - INFO - Iter(train) [39050/60000] base_lr: 3.4917e-05 lr: 3.4917e-05 eta: 5:44:19 time: 0.9868 data_time: 0.0228 memory: 29177 grad_norm: 20.6262 loss: 8.2733 decode.loss_cls_ce: 1.6041 decode.loss_mask_ce: 0.9131 decode.loss_mask_dice: 1.6066 decode.d7.loss_cls_ce: 1.6309 decode.d7.loss_mask_ce: 0.9184 decode.d7.loss_mask_dice: 1.6002 2023/09/07 20:38:51 - mmengine - INFO - Iter(train) [39100/60000] base_lr: 3.4834e-05 lr: 3.4834e-05 eta: 5:43:30 time: 0.9879 data_time: 0.0219 memory: 29165 grad_norm: 18.6772 loss: 8.2195 decode.loss_cls_ce: 1.6354 decode.loss_mask_ce: 0.8065 decode.loss_mask_dice: 1.6537 decode.d7.loss_cls_ce: 1.6776 decode.d7.loss_mask_ce: 0.7928 decode.d7.loss_mask_dice: 1.6536 2023/09/07 20:39:40 - mmengine - INFO - Iter(train) [39150/60000] base_lr: 3.4751e-05 lr: 3.4751e-05 eta: 5:42:40 time: 0.9882 data_time: 0.0227 memory: 29164 grad_norm: 19.4119 loss: 8.8564 decode.loss_cls_ce: 1.8164 decode.loss_mask_ce: 0.8604 decode.loss_mask_dice: 1.7661 decode.d7.loss_cls_ce: 1.8215 decode.d7.loss_mask_ce: 0.8554 decode.d7.loss_mask_dice: 1.7366 2023/09/07 20:40:30 - mmengine - INFO - Iter(train) [39200/60000] base_lr: 3.4667e-05 lr: 3.4667e-05 eta: 5:41:51 time: 0.9903 data_time: 0.0237 memory: 29252 grad_norm: 20.7565 loss: 7.1787 decode.loss_cls_ce: 1.3890 decode.loss_mask_ce: 0.7538 decode.loss_mask_dice: 1.4394 decode.d7.loss_cls_ce: 1.3899 decode.d7.loss_mask_ce: 0.7605 decode.d7.loss_mask_dice: 1.4460 2023/09/07 20:41:19 - mmengine - INFO - Iter(train) [39250/60000] base_lr: 3.4584e-05 lr: 3.4584e-05 eta: 5:41:02 time: 0.9883 data_time: 0.0228 memory: 29243 grad_norm: 18.6856 loss: 8.9026 decode.loss_cls_ce: 1.7376 decode.loss_mask_ce: 0.8157 decode.loss_mask_dice: 1.8754 decode.d7.loss_cls_ce: 1.7750 decode.d7.loss_mask_ce: 0.8194 decode.d7.loss_mask_dice: 1.8794 2023/09/07 20:42:09 - mmengine - INFO - Iter(train) [39300/60000] base_lr: 3.4501e-05 lr: 3.4501e-05 eta: 5:40:13 time: 0.9894 data_time: 0.0230 memory: 29141 grad_norm: 17.9305 loss: 7.2607 decode.loss_cls_ce: 1.4126 decode.loss_mask_ce: 0.7520 decode.loss_mask_dice: 1.4642 decode.d7.loss_cls_ce: 1.4039 decode.d7.loss_mask_ce: 0.7520 decode.d7.loss_mask_dice: 1.4760 2023/09/07 20:42:58 - mmengine - INFO - Iter(train) [39350/60000] base_lr: 3.4417e-05 lr: 3.4417e-05 eta: 5:39:23 time: 0.9888 data_time: 0.0232 memory: 29130 grad_norm: 17.7665 loss: 7.8776 decode.loss_cls_ce: 1.7237 decode.loss_mask_ce: 0.7444 decode.loss_mask_dice: 1.4733 decode.d7.loss_cls_ce: 1.7363 decode.d7.loss_mask_ce: 0.7339 decode.d7.loss_mask_dice: 1.4660 2023/09/07 20:43:48 - mmengine - INFO - Iter(train) [39400/60000] base_lr: 3.4334e-05 lr: 3.4334e-05 eta: 5:38:34 time: 0.9902 data_time: 0.0225 memory: 29231 grad_norm: 19.8155 loss: 8.4989 decode.loss_cls_ce: 1.7701 decode.loss_mask_ce: 0.8605 decode.loss_mask_dice: 1.6129 decode.d7.loss_cls_ce: 1.7595 decode.d7.loss_mask_ce: 0.8648 decode.d7.loss_mask_dice: 1.6311 2023/09/07 20:44:37 - mmengine - INFO - Iter(train) [39450/60000] base_lr: 3.4251e-05 lr: 3.4251e-05 eta: 5:37:45 time: 0.9863 data_time: 0.0229 memory: 29137 grad_norm: 19.8003 loss: 8.9748 decode.loss_cls_ce: 1.5678 decode.loss_mask_ce: 0.9806 decode.loss_mask_dice: 1.9307 decode.d7.loss_cls_ce: 1.5751 decode.d7.loss_mask_ce: 0.9825 decode.d7.loss_mask_dice: 1.9381 2023/09/07 20:45:26 - mmengine - INFO - Iter(train) [39500/60000] base_lr: 3.4167e-05 lr: 3.4167e-05 eta: 5:36:56 time: 0.9894 data_time: 0.0222 memory: 29215 grad_norm: 19.3670 loss: 9.0021 decode.loss_cls_ce: 1.7446 decode.loss_mask_ce: 0.9062 decode.loss_mask_dice: 1.8440 decode.d7.loss_cls_ce: 1.7320 decode.d7.loss_mask_ce: 0.9175 decode.d7.loss_mask_dice: 1.8576 2023/09/07 20:46:16 - mmengine - INFO - Iter(train) [39550/60000] base_lr: 3.4084e-05 lr: 3.4084e-05 eta: 5:36:06 time: 0.9880 data_time: 0.0229 memory: 29216 grad_norm: 17.9986 loss: 6.9717 decode.loss_cls_ce: 1.4357 decode.loss_mask_ce: 0.6749 decode.loss_mask_dice: 1.3733 decode.d7.loss_cls_ce: 1.4371 decode.d7.loss_mask_ce: 0.6699 decode.d7.loss_mask_dice: 1.3806 2023/09/07 20:47:05 - mmengine - INFO - Iter(train) [39600/60000] base_lr: 3.4001e-05 lr: 3.4001e-05 eta: 5:35:17 time: 0.9887 data_time: 0.0226 memory: 29216 grad_norm: 19.5800 loss: 7.6675 decode.loss_cls_ce: 1.4739 decode.loss_mask_ce: 0.7857 decode.loss_mask_dice: 1.5742 decode.d7.loss_cls_ce: 1.4845 decode.d7.loss_mask_ce: 0.7796 decode.d7.loss_mask_dice: 1.5695 2023/09/07 20:47:55 - mmengine - INFO - Iter(train) [39650/60000] base_lr: 3.3917e-05 lr: 3.3917e-05 eta: 5:34:28 time: 0.9871 data_time: 0.0226 memory: 29240 grad_norm: 18.4799 loss: 9.3439 decode.loss_cls_ce: 1.8894 decode.loss_mask_ce: 0.9439 decode.loss_mask_dice: 1.8234 decode.d7.loss_cls_ce: 1.9453 decode.d7.loss_mask_ce: 0.9315 decode.d7.loss_mask_dice: 1.8105 2023/09/07 20:48:44 - mmengine - INFO - Iter(train) [39700/60000] base_lr: 3.3834e-05 lr: 3.3834e-05 eta: 5:33:39 time: 0.9893 data_time: 0.0225 memory: 29202 grad_norm: 17.9208 loss: 7.1294 decode.loss_cls_ce: 1.4413 decode.loss_mask_ce: 0.7428 decode.loss_mask_dice: 1.3923 decode.d7.loss_cls_ce: 1.4475 decode.d7.loss_mask_ce: 0.7376 decode.d7.loss_mask_dice: 1.3679 2023/09/07 20:49:34 - mmengine - INFO - Iter(train) [39750/60000] base_lr: 3.3751e-05 lr: 3.3751e-05 eta: 5:32:49 time: 0.9885 data_time: 0.0235 memory: 29115 grad_norm: 20.8678 loss: 7.6991 decode.loss_cls_ce: 1.5667 decode.loss_mask_ce: 0.8106 decode.loss_mask_dice: 1.4430 decode.d7.loss_cls_ce: 1.6293 decode.d7.loss_mask_ce: 0.8012 decode.d7.loss_mask_dice: 1.4483 2023/09/07 20:50:23 - mmengine - INFO - Iter(train) [39800/60000] base_lr: 3.3667e-05 lr: 3.3667e-05 eta: 5:32:00 time: 0.9938 data_time: 0.0222 memory: 29154 grad_norm: 19.6683 loss: 7.2539 decode.loss_cls_ce: 1.5639 decode.loss_mask_ce: 0.7748 decode.loss_mask_dice: 1.2985 decode.d7.loss_cls_ce: 1.5444 decode.d7.loss_mask_ce: 0.7811 decode.d7.loss_mask_dice: 1.2912 2023/09/07 20:51:13 - mmengine - INFO - Iter(train) [39850/60000] base_lr: 3.3584e-05 lr: 3.3584e-05 eta: 5:31:11 time: 0.9851 data_time: 0.0221 memory: 29137 grad_norm: 29.2433 loss: 7.6011 decode.loss_cls_ce: 1.5254 decode.loss_mask_ce: 0.7660 decode.loss_mask_dice: 1.5090 decode.d7.loss_cls_ce: 1.5379 decode.d7.loss_mask_ce: 0.7649 decode.d7.loss_mask_dice: 1.4977 2023/09/07 20:52:02 - mmengine - INFO - Iter(train) [39900/60000] base_lr: 3.3501e-05 lr: 3.3501e-05 eta: 5:30:22 time: 0.9855 data_time: 0.0229 memory: 29135 grad_norm: 17.9061 loss: 7.0064 decode.loss_cls_ce: 1.4643 decode.loss_mask_ce: 0.7328 decode.loss_mask_dice: 1.3097 decode.d7.loss_cls_ce: 1.4475 decode.d7.loss_mask_ce: 0.7298 decode.d7.loss_mask_dice: 1.3223 2023/09/07 20:52:51 - mmengine - INFO - Iter(train) [39950/60000] base_lr: 3.3417e-05 lr: 3.3417e-05 eta: 5:29:32 time: 0.9883 data_time: 0.0223 memory: 29198 grad_norm: 17.6054 loss: 8.2715 decode.loss_cls_ce: 1.7501 decode.loss_mask_ce: 0.7691 decode.loss_mask_dice: 1.5972 decode.d7.loss_cls_ce: 1.7825 decode.d7.loss_mask_ce: 0.7682 decode.d7.loss_mask_dice: 1.6044 2023/09/07 20:53:41 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 20:53:41 - mmengine - INFO - Iter(train) [40000/60000] base_lr: 3.3334e-05 lr: 3.3334e-05 eta: 5:28:43 time: 0.9888 data_time: 0.0223 memory: 29101 grad_norm: 18.5422 loss: 8.0333 decode.loss_cls_ce: 1.7163 decode.loss_mask_ce: 0.7489 decode.loss_mask_dice: 1.5301 decode.d7.loss_cls_ce: 1.7437 decode.d7.loss_mask_ce: 0.7761 decode.d7.loss_mask_dice: 1.5181 2023/09/07 20:53:41 - mmengine - INFO - Saving checkpoint at 40000 iterations 2023/09/07 20:54:38 - mmengine - INFO - Iter(train) [40050/60000] base_lr: 3.3251e-05 lr: 3.3251e-05 eta: 5:27:57 time: 0.9876 data_time: 0.0223 memory: 29242 grad_norm: 19.4597 loss: 8.7703 decode.loss_cls_ce: 1.7903 decode.loss_mask_ce: 0.8261 decode.loss_mask_dice: 1.7757 decode.d7.loss_cls_ce: 1.8039 decode.d7.loss_mask_ce: 0.8185 decode.d7.loss_mask_dice: 1.7557 2023/09/07 20:55:27 - mmengine - INFO - Iter(train) [40100/60000] base_lr: 3.3167e-05 lr: 3.3167e-05 eta: 5:27:08 time: 0.9865 data_time: 0.0223 memory: 29217 grad_norm: 19.2269 loss: 6.5253 decode.loss_cls_ce: 1.1795 decode.loss_mask_ce: 0.8015 decode.loss_mask_dice: 1.2523 decode.d7.loss_cls_ce: 1.2302 decode.d7.loss_mask_ce: 0.8036 decode.d7.loss_mask_dice: 1.2581 2023/09/07 20:56:16 - mmengine - INFO - Iter(train) [40150/60000] base_lr: 3.3084e-05 lr: 3.3084e-05 eta: 5:26:19 time: 0.9907 data_time: 0.0226 memory: 29241 grad_norm: 18.2203 loss: 7.7553 decode.loss_cls_ce: 1.5415 decode.loss_mask_ce: 0.8704 decode.loss_mask_dice: 1.4988 decode.d7.loss_cls_ce: 1.5033 decode.d7.loss_mask_ce: 0.8650 decode.d7.loss_mask_dice: 1.4762 2023/09/07 20:57:06 - mmengine - INFO - Iter(train) [40200/60000] base_lr: 3.3001e-05 lr: 3.3001e-05 eta: 5:25:30 time: 0.9911 data_time: 0.0227 memory: 29126 grad_norm: 20.7597 loss: 7.1497 decode.loss_cls_ce: 1.4493 decode.loss_mask_ce: 0.7916 decode.loss_mask_dice: 1.3406 decode.d7.loss_cls_ce: 1.4298 decode.d7.loss_mask_ce: 0.8048 decode.d7.loss_mask_dice: 1.3337 2023/09/07 20:57:55 - mmengine - INFO - Iter(train) [40250/60000] base_lr: 3.2917e-05 lr: 3.2917e-05 eta: 5:24:40 time: 0.9876 data_time: 0.0226 memory: 29395 grad_norm: 22.4190 loss: 7.3659 decode.loss_cls_ce: 1.5393 decode.loss_mask_ce: 0.7797 decode.loss_mask_dice: 1.3410 decode.d7.loss_cls_ce: 1.5557 decode.d7.loss_mask_ce: 0.7854 decode.d7.loss_mask_dice: 1.3648 2023/09/07 20:58:45 - mmengine - INFO - Iter(train) [40300/60000] base_lr: 3.2834e-05 lr: 3.2834e-05 eta: 5:23:51 time: 0.9924 data_time: 0.0222 memory: 29134 grad_norm: 20.5922 loss: 8.0493 decode.loss_cls_ce: 1.6161 decode.loss_mask_ce: 0.8073 decode.loss_mask_dice: 1.6011 decode.d7.loss_cls_ce: 1.6035 decode.d7.loss_mask_ce: 0.8084 decode.d7.loss_mask_dice: 1.6128 2023/09/07 20:59:34 - mmengine - INFO - Iter(train) [40350/60000] base_lr: 3.2751e-05 lr: 3.2751e-05 eta: 5:23:02 time: 0.9878 data_time: 0.0222 memory: 29155 grad_norm: 18.0082 loss: 6.9074 decode.loss_cls_ce: 1.4254 decode.loss_mask_ce: 0.7217 decode.loss_mask_dice: 1.2981 decode.d7.loss_cls_ce: 1.4481 decode.d7.loss_mask_ce: 0.7252 decode.d7.loss_mask_dice: 1.2889 2023/09/07 21:00:24 - mmengine - INFO - Iter(train) [40400/60000] base_lr: 3.2667e-05 lr: 3.2667e-05 eta: 5:22:13 time: 0.9941 data_time: 0.0229 memory: 29180 grad_norm: 19.6097 loss: 7.6362 decode.loss_cls_ce: 1.6092 decode.loss_mask_ce: 0.7737 decode.loss_mask_dice: 1.4542 decode.d7.loss_cls_ce: 1.6079 decode.d7.loss_mask_ce: 0.7638 decode.d7.loss_mask_dice: 1.4274 2023/09/07 21:01:13 - mmengine - INFO - Iter(train) [40450/60000] base_lr: 3.2584e-05 lr: 3.2584e-05 eta: 5:21:23 time: 0.9906 data_time: 0.0220 memory: 29267 grad_norm: 20.3298 loss: 8.5712 decode.loss_cls_ce: 1.9136 decode.loss_mask_ce: 0.8160 decode.loss_mask_dice: 1.5526 decode.d7.loss_cls_ce: 1.9218 decode.d7.loss_mask_ce: 0.8172 decode.d7.loss_mask_dice: 1.5499 2023/09/07 21:02:03 - mmengine - INFO - Iter(train) [40500/60000] base_lr: 3.2501e-05 lr: 3.2501e-05 eta: 5:20:34 time: 0.9885 data_time: 0.0224 memory: 29230 grad_norm: 21.0086 loss: 9.3594 decode.loss_cls_ce: 1.8553 decode.loss_mask_ce: 0.8875 decode.loss_mask_dice: 1.9352 decode.d7.loss_cls_ce: 1.8734 decode.d7.loss_mask_ce: 0.8845 decode.d7.loss_mask_dice: 1.9235 2023/09/07 21:02:52 - mmengine - INFO - Iter(train) [40550/60000] base_lr: 3.2417e-05 lr: 3.2417e-05 eta: 5:19:45 time: 0.9886 data_time: 0.0230 memory: 29425 grad_norm: 17.9649 loss: 8.9376 decode.loss_cls_ce: 1.7810 decode.loss_mask_ce: 0.7812 decode.loss_mask_dice: 1.9241 decode.d7.loss_cls_ce: 1.7303 decode.d7.loss_mask_ce: 0.7810 decode.d7.loss_mask_dice: 1.9400 2023/09/07 21:03:42 - mmengine - INFO - Iter(train) [40600/60000] base_lr: 3.2334e-05 lr: 3.2334e-05 eta: 5:18:56 time: 0.9879 data_time: 0.0229 memory: 29096 grad_norm: 18.1250 loss: 7.9930 decode.loss_cls_ce: 1.6497 decode.loss_mask_ce: 0.6992 decode.loss_mask_dice: 1.6370 decode.d7.loss_cls_ce: 1.6536 decode.d7.loss_mask_ce: 0.6991 decode.d7.loss_mask_dice: 1.6545 2023/09/07 21:04:31 - mmengine - INFO - Iter(train) [40650/60000] base_lr: 3.2251e-05 lr: 3.2251e-05 eta: 5:18:06 time: 0.9878 data_time: 0.0227 memory: 29126 grad_norm: 18.0990 loss: 7.3756 decode.loss_cls_ce: 1.4125 decode.loss_mask_ce: 0.7598 decode.loss_mask_dice: 1.4943 decode.d7.loss_cls_ce: 1.4315 decode.d7.loss_mask_ce: 0.7653 decode.d7.loss_mask_dice: 1.5123 2023/09/07 21:05:20 - mmengine - INFO - Iter(train) [40700/60000] base_lr: 3.2167e-05 lr: 3.2167e-05 eta: 5:17:17 time: 0.9881 data_time: 0.0237 memory: 29250 grad_norm: 17.1050 loss: 9.1919 decode.loss_cls_ce: 1.8649 decode.loss_mask_ce: 0.9321 decode.loss_mask_dice: 1.7802 decode.d7.loss_cls_ce: 1.8663 decode.d7.loss_mask_ce: 0.9327 decode.d7.loss_mask_dice: 1.8157 2023/09/07 21:06:10 - mmengine - INFO - Iter(train) [40750/60000] base_lr: 3.2084e-05 lr: 3.2084e-05 eta: 5:16:28 time: 0.9912 data_time: 0.0228 memory: 29265 grad_norm: 17.9086 loss: 7.4459 decode.loss_cls_ce: 1.5243 decode.loss_mask_ce: 0.7356 decode.loss_mask_dice: 1.4534 decode.d7.loss_cls_ce: 1.5204 decode.d7.loss_mask_ce: 0.7502 decode.d7.loss_mask_dice: 1.4620 2023/09/07 21:06:59 - mmengine - INFO - Iter(train) [40800/60000] base_lr: 3.2001e-05 lr: 3.2001e-05 eta: 5:15:39 time: 0.9891 data_time: 0.0232 memory: 29280 grad_norm: 19.3623 loss: 8.5895 decode.loss_cls_ce: 1.6816 decode.loss_mask_ce: 0.9079 decode.loss_mask_dice: 1.7228 decode.d7.loss_cls_ce: 1.6894 decode.d7.loss_mask_ce: 0.8850 decode.d7.loss_mask_dice: 1.7028 2023/09/07 21:07:49 - mmengine - INFO - Iter(train) [40850/60000] base_lr: 3.1917e-05 lr: 3.1917e-05 eta: 5:14:49 time: 0.9861 data_time: 0.0234 memory: 29141 grad_norm: 20.5331 loss: 7.2245 decode.loss_cls_ce: 1.4412 decode.loss_mask_ce: 0.8258 decode.loss_mask_dice: 1.3453 decode.d7.loss_cls_ce: 1.4427 decode.d7.loss_mask_ce: 0.8306 decode.d7.loss_mask_dice: 1.3389 2023/09/07 21:08:38 - mmengine - INFO - Iter(train) [40900/60000] base_lr: 3.1834e-05 lr: 3.1834e-05 eta: 5:14:00 time: 0.9875 data_time: 0.0226 memory: 29154 grad_norm: 22.7782 loss: 9.6310 decode.loss_cls_ce: 1.9134 decode.loss_mask_ce: 0.9215 decode.loss_mask_dice: 1.9584 decode.d7.loss_cls_ce: 1.9470 decode.d7.loss_mask_ce: 0.9254 decode.d7.loss_mask_dice: 1.9654 2023/09/07 21:09:28 - mmengine - INFO - Iter(train) [40950/60000] base_lr: 3.1751e-05 lr: 3.1751e-05 eta: 5:13:11 time: 0.9875 data_time: 0.0227 memory: 29140 grad_norm: 20.4398 loss: 8.6179 decode.loss_cls_ce: 1.6834 decode.loss_mask_ce: 0.8793 decode.loss_mask_dice: 1.7539 decode.d7.loss_cls_ce: 1.6238 decode.d7.loss_mask_ce: 0.8979 decode.d7.loss_mask_dice: 1.7795 2023/09/07 21:10:17 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 21:10:17 - mmengine - INFO - Iter(train) [41000/60000] base_lr: 3.1667e-05 lr: 3.1667e-05 eta: 5:12:21 time: 0.9869 data_time: 0.0228 memory: 29202 grad_norm: 18.6241 loss: 8.7194 decode.loss_cls_ce: 1.7399 decode.loss_mask_ce: 0.8390 decode.loss_mask_dice: 1.7631 decode.d7.loss_cls_ce: 1.7153 decode.d7.loss_mask_ce: 0.8513 decode.d7.loss_mask_dice: 1.8109 2023/09/07 21:11:07 - mmengine - INFO - Iter(train) [41050/60000] base_lr: 3.1584e-05 lr: 3.1584e-05 eta: 5:11:32 time: 0.9867 data_time: 0.0222 memory: 29230 grad_norm: 18.7204 loss: 9.0257 decode.loss_cls_ce: 1.7409 decode.loss_mask_ce: 0.9815 decode.loss_mask_dice: 1.7866 decode.d7.loss_cls_ce: 1.7346 decode.d7.loss_mask_ce: 0.9897 decode.d7.loss_mask_dice: 1.7924 2023/09/07 21:11:56 - mmengine - INFO - Iter(train) [41100/60000] base_lr: 3.1501e-05 lr: 3.1501e-05 eta: 5:10:43 time: 0.9873 data_time: 0.0220 memory: 29115 grad_norm: 21.0098 loss: 8.2918 decode.loss_cls_ce: 1.8344 decode.loss_mask_ce: 0.6866 decode.loss_mask_dice: 1.6269 decode.d7.loss_cls_ce: 1.8526 decode.d7.loss_mask_ce: 0.6737 decode.d7.loss_mask_dice: 1.6176 2023/09/07 21:12:45 - mmengine - INFO - Iter(train) [41150/60000] base_lr: 3.1417e-05 lr: 3.1417e-05 eta: 5:09:54 time: 0.9870 data_time: 0.0223 memory: 29163 grad_norm: 22.3138 loss: 8.3242 decode.loss_cls_ce: 1.6405 decode.loss_mask_ce: 0.8947 decode.loss_mask_dice: 1.6182 decode.d7.loss_cls_ce: 1.6629 decode.d7.loss_mask_ce: 0.8835 decode.d7.loss_mask_dice: 1.6244 2023/09/07 21:13:35 - mmengine - INFO - Iter(train) [41200/60000] base_lr: 3.1334e-05 lr: 3.1334e-05 eta: 5:09:04 time: 0.9883 data_time: 0.0226 memory: 29268 grad_norm: 18.5142 loss: 7.8651 decode.loss_cls_ce: 1.7362 decode.loss_mask_ce: 0.6993 decode.loss_mask_dice: 1.4923 decode.d7.loss_cls_ce: 1.7280 decode.d7.loss_mask_ce: 0.7117 decode.d7.loss_mask_dice: 1.4976 2023/09/07 21:14:24 - mmengine - INFO - Iter(train) [41250/60000] base_lr: 3.1251e-05 lr: 3.1251e-05 eta: 5:08:15 time: 0.9882 data_time: 0.0229 memory: 29218 grad_norm: 20.0947 loss: 7.9589 decode.loss_cls_ce: 1.6927 decode.loss_mask_ce: 0.7293 decode.loss_mask_dice: 1.5394 decode.d7.loss_cls_ce: 1.7400 decode.d7.loss_mask_ce: 0.7264 decode.d7.loss_mask_dice: 1.5312 2023/09/07 21:15:14 - mmengine - INFO - Iter(train) [41300/60000] base_lr: 3.1167e-05 lr: 3.1167e-05 eta: 5:07:26 time: 0.9871 data_time: 0.0225 memory: 29140 grad_norm: 20.3579 loss: 8.7242 decode.loss_cls_ce: 1.7521 decode.loss_mask_ce: 0.7631 decode.loss_mask_dice: 1.8393 decode.d7.loss_cls_ce: 1.7818 decode.d7.loss_mask_ce: 0.7505 decode.d7.loss_mask_dice: 1.8374 2023/09/07 21:16:03 - mmengine - INFO - Iter(train) [41350/60000] base_lr: 3.1084e-05 lr: 3.1084e-05 eta: 5:06:36 time: 0.9872 data_time: 0.0224 memory: 29286 grad_norm: 17.3778 loss: 10.7365 decode.loss_cls_ce: 1.8604 decode.loss_mask_ce: 1.0986 decode.loss_mask_dice: 2.4094 decode.d7.loss_cls_ce: 1.8748 decode.d7.loss_mask_ce: 1.0842 decode.d7.loss_mask_dice: 2.4089 2023/09/07 21:16:52 - mmengine - INFO - Iter(train) [41400/60000] base_lr: 3.1001e-05 lr: 3.1001e-05 eta: 5:05:47 time: 0.9864 data_time: 0.0234 memory: 29213 grad_norm: 18.8096 loss: 7.8067 decode.loss_cls_ce: 1.6566 decode.loss_mask_ce: 0.8237 decode.loss_mask_dice: 1.3917 decode.d7.loss_cls_ce: 1.7008 decode.d7.loss_mask_ce: 0.8214 decode.d7.loss_mask_dice: 1.4125 2023/09/07 21:17:42 - mmengine - INFO - Iter(train) [41450/60000] base_lr: 3.0917e-05 lr: 3.0917e-05 eta: 5:04:58 time: 0.9883 data_time: 0.0230 memory: 29238 grad_norm: 17.8528 loss: 7.7847 decode.loss_cls_ce: 1.6326 decode.loss_mask_ce: 0.8944 decode.loss_mask_dice: 1.3731 decode.d7.loss_cls_ce: 1.6085 decode.d7.loss_mask_ce: 0.8908 decode.d7.loss_mask_dice: 1.3853 2023/09/07 21:18:31 - mmengine - INFO - Iter(train) [41500/60000] base_lr: 3.0834e-05 lr: 3.0834e-05 eta: 5:04:09 time: 0.9868 data_time: 0.0232 memory: 29202 grad_norm: 21.4545 loss: 7.8515 decode.loss_cls_ce: 1.6024 decode.loss_mask_ce: 0.8225 decode.loss_mask_dice: 1.4771 decode.d7.loss_cls_ce: 1.6325 decode.d7.loss_mask_ce: 0.8251 decode.d7.loss_mask_dice: 1.4920 2023/09/07 21:19:21 - mmengine - INFO - Iter(train) [41550/60000] base_lr: 3.0751e-05 lr: 3.0751e-05 eta: 5:03:19 time: 0.9853 data_time: 0.0224 memory: 29269 grad_norm: 16.8990 loss: 7.5898 decode.loss_cls_ce: 1.5160 decode.loss_mask_ce: 0.8341 decode.loss_mask_dice: 1.4284 decode.d7.loss_cls_ce: 1.5523 decode.d7.loss_mask_ce: 0.8210 decode.d7.loss_mask_dice: 1.4379 2023/09/07 21:20:10 - mmengine - INFO - Iter(train) [41600/60000] base_lr: 3.0667e-05 lr: 3.0667e-05 eta: 5:02:30 time: 0.9882 data_time: 0.0224 memory: 29152 grad_norm: 19.6690 loss: 8.1014 decode.loss_cls_ce: 1.5311 decode.loss_mask_ce: 0.8865 decode.loss_mask_dice: 1.6297 decode.d7.loss_cls_ce: 1.5310 decode.d7.loss_mask_ce: 0.8906 decode.d7.loss_mask_dice: 1.6324 2023/09/07 21:20:59 - mmengine - INFO - Iter(train) [41650/60000] base_lr: 3.0584e-05 lr: 3.0584e-05 eta: 5:01:41 time: 0.9880 data_time: 0.0223 memory: 29216 grad_norm: 19.0076 loss: 7.2618 decode.loss_cls_ce: 1.4388 decode.loss_mask_ce: 0.8091 decode.loss_mask_dice: 1.4031 decode.d7.loss_cls_ce: 1.4043 decode.d7.loss_mask_ce: 0.8018 decode.d7.loss_mask_dice: 1.4047 2023/09/07 21:21:49 - mmengine - INFO - Iter(train) [41700/60000] base_lr: 3.0501e-05 lr: 3.0501e-05 eta: 5:00:51 time: 0.9881 data_time: 0.0219 memory: 29136 grad_norm: 18.5778 loss: 7.8140 decode.loss_cls_ce: 1.4376 decode.loss_mask_ce: 0.8138 decode.loss_mask_dice: 1.6304 decode.d7.loss_cls_ce: 1.4974 decode.d7.loss_mask_ce: 0.7989 decode.d7.loss_mask_dice: 1.6358 2023/09/07 21:22:38 - mmengine - INFO - Iter(train) [41750/60000] base_lr: 3.0417e-05 lr: 3.0417e-05 eta: 5:00:02 time: 0.9893 data_time: 0.0230 memory: 29191 grad_norm: 19.2029 loss: 10.1172 decode.loss_cls_ce: 2.0440 decode.loss_mask_ce: 0.9066 decode.loss_mask_dice: 2.1217 decode.d7.loss_cls_ce: 2.0505 decode.d7.loss_mask_ce: 0.9047 decode.d7.loss_mask_dice: 2.0898 2023/09/07 21:23:28 - mmengine - INFO - Iter(train) [41800/60000] base_lr: 3.0334e-05 lr: 3.0334e-05 eta: 4:59:13 time: 0.9878 data_time: 0.0222 memory: 29257 grad_norm: 17.3295 loss: 9.0414 decode.loss_cls_ce: 1.8191 decode.loss_mask_ce: 0.9647 decode.loss_mask_dice: 1.7182 decode.d7.loss_cls_ce: 1.8861 decode.d7.loss_mask_ce: 0.9617 decode.d7.loss_mask_dice: 1.6916 2023/09/07 21:24:17 - mmengine - INFO - Iter(train) [41850/60000] base_lr: 3.0251e-05 lr: 3.0251e-05 eta: 4:58:24 time: 0.9868 data_time: 0.0221 memory: 29203 grad_norm: 17.2790 loss: 7.4538 decode.loss_cls_ce: 1.5424 decode.loss_mask_ce: 0.6880 decode.loss_mask_dice: 1.5010 decode.d7.loss_cls_ce: 1.5529 decode.d7.loss_mask_ce: 0.6892 decode.d7.loss_mask_dice: 1.4803 2023/09/07 21:25:07 - mmengine - INFO - Iter(train) [41900/60000] base_lr: 3.0167e-05 lr: 3.0167e-05 eta: 4:57:34 time: 0.9880 data_time: 0.0219 memory: 29274 grad_norm: 17.6860 loss: 6.4666 decode.loss_cls_ce: 1.2229 decode.loss_mask_ce: 0.7323 decode.loss_mask_dice: 1.2536 decode.d7.loss_cls_ce: 1.2655 decode.d7.loss_mask_ce: 0.7411 decode.d7.loss_mask_dice: 1.2512 2023/09/07 21:25:56 - mmengine - INFO - Iter(train) [41950/60000] base_lr: 3.0084e-05 lr: 3.0084e-05 eta: 4:56:45 time: 0.9873 data_time: 0.0226 memory: 29275 grad_norm: 17.7937 loss: 9.1016 decode.loss_cls_ce: 1.8541 decode.loss_mask_ce: 0.9786 decode.loss_mask_dice: 1.7380 decode.d7.loss_cls_ce: 1.8346 decode.d7.loss_mask_ce: 0.9789 decode.d7.loss_mask_dice: 1.7172 2023/09/07 21:26:46 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 21:26:46 - mmengine - INFO - Iter(train) [42000/60000] base_lr: 3.0001e-05 lr: 3.0001e-05 eta: 4:55:56 time: 0.9913 data_time: 0.0225 memory: 29202 grad_norm: 17.4672 loss: 9.0542 decode.loss_cls_ce: 1.8112 decode.loss_mask_ce: 0.9550 decode.loss_mask_dice: 1.7570 decode.d7.loss_cls_ce: 1.8330 decode.d7.loss_mask_ce: 0.9595 decode.d7.loss_mask_dice: 1.7384 2023/09/07 21:27:35 - mmengine - INFO - Iter(train) [42050/60000] base_lr: 2.9917e-05 lr: 2.9917e-05 eta: 4:55:06 time: 0.9875 data_time: 0.0230 memory: 29212 grad_norm: 18.9121 loss: 7.3913 decode.loss_cls_ce: 1.4906 decode.loss_mask_ce: 0.7617 decode.loss_mask_dice: 1.4307 decode.d7.loss_cls_ce: 1.5149 decode.d7.loss_mask_ce: 0.7616 decode.d7.loss_mask_dice: 1.4318 2023/09/07 21:28:25 - mmengine - INFO - Iter(train) [42100/60000] base_lr: 2.9834e-05 lr: 2.9834e-05 eta: 4:54:17 time: 0.9878 data_time: 0.0226 memory: 29191 grad_norm: 16.9853 loss: 8.5435 decode.loss_cls_ce: 1.6745 decode.loss_mask_ce: 0.8856 decode.loss_mask_dice: 1.6893 decode.d7.loss_cls_ce: 1.6910 decode.d7.loss_mask_ce: 0.8875 decode.d7.loss_mask_dice: 1.7156 2023/09/07 21:29:14 - mmengine - INFO - Iter(train) [42150/60000] base_lr: 2.9750e-05 lr: 2.9750e-05 eta: 4:53:28 time: 0.9895 data_time: 0.0233 memory: 29282 grad_norm: 18.5060 loss: 8.2457 decode.loss_cls_ce: 1.6273 decode.loss_mask_ce: 0.8189 decode.loss_mask_dice: 1.6662 decode.d7.loss_cls_ce: 1.6440 decode.d7.loss_mask_ce: 0.8180 decode.d7.loss_mask_dice: 1.6714 2023/09/07 21:30:04 - mmengine - INFO - Iter(train) [42200/60000] base_lr: 2.9667e-05 lr: 2.9667e-05 eta: 4:52:39 time: 0.9908 data_time: 0.0222 memory: 29095 grad_norm: 17.2015 loss: 7.8844 decode.loss_cls_ce: 1.5671 decode.loss_mask_ce: 0.8454 decode.loss_mask_dice: 1.5200 decode.d7.loss_cls_ce: 1.5761 decode.d7.loss_mask_ce: 0.8568 decode.d7.loss_mask_dice: 1.5189 2023/09/07 21:30:53 - mmengine - INFO - Iter(train) [42250/60000] base_lr: 2.9584e-05 lr: 2.9584e-05 eta: 4:51:49 time: 0.9891 data_time: 0.0233 memory: 29162 grad_norm: 20.1409 loss: 8.8382 decode.loss_cls_ce: 1.7874 decode.loss_mask_ce: 0.8212 decode.loss_mask_dice: 1.7898 decode.d7.loss_cls_ce: 1.8329 decode.d7.loss_mask_ce: 0.8269 decode.d7.loss_mask_dice: 1.7800 2023/09/07 21:31:42 - mmengine - INFO - Iter(train) [42300/60000] base_lr: 2.9500e-05 lr: 2.9500e-05 eta: 4:51:00 time: 0.9876 data_time: 0.0235 memory: 29177 grad_norm: 20.2392 loss: 8.7080 decode.loss_cls_ce: 1.5827 decode.loss_mask_ce: 0.9976 decode.loss_mask_dice: 1.7787 decode.d7.loss_cls_ce: 1.6044 decode.d7.loss_mask_ce: 0.9924 decode.d7.loss_mask_dice: 1.7523 2023/09/07 21:32:32 - mmengine - INFO - Iter(train) [42350/60000] base_lr: 2.9417e-05 lr: 2.9417e-05 eta: 4:50:11 time: 0.9932 data_time: 0.0255 memory: 29243 grad_norm: 19.4318 loss: 8.1487 decode.loss_cls_ce: 1.6312 decode.loss_mask_ce: 0.8180 decode.loss_mask_dice: 1.6415 decode.d7.loss_cls_ce: 1.5720 decode.d7.loss_mask_ce: 0.8363 decode.d7.loss_mask_dice: 1.6497 2023/09/07 21:33:21 - mmengine - INFO - Iter(train) [42400/60000] base_lr: 2.9334e-05 lr: 2.9334e-05 eta: 4:49:22 time: 0.9891 data_time: 0.0223 memory: 29149 grad_norm: 20.9774 loss: 8.3857 decode.loss_cls_ce: 1.7367 decode.loss_mask_ce: 0.8698 decode.loss_mask_dice: 1.5839 decode.d7.loss_cls_ce: 1.7492 decode.d7.loss_mask_ce: 0.8663 decode.d7.loss_mask_dice: 1.5798 2023/09/07 21:34:11 - mmengine - INFO - Iter(train) [42450/60000] base_lr: 2.9250e-05 lr: 2.9250e-05 eta: 4:48:32 time: 0.9934 data_time: 0.0225 memory: 29204 grad_norm: 19.5292 loss: 8.5362 decode.loss_cls_ce: 1.8204 decode.loss_mask_ce: 0.7988 decode.loss_mask_dice: 1.6310 decode.d7.loss_cls_ce: 1.8540 decode.d7.loss_mask_ce: 0.8053 decode.d7.loss_mask_dice: 1.6267 2023/09/07 21:35:00 - mmengine - INFO - Iter(train) [42500/60000] base_lr: 2.9167e-05 lr: 2.9167e-05 eta: 4:47:43 time: 0.9927 data_time: 0.0228 memory: 29473 grad_norm: 18.0805 loss: 8.2546 decode.loss_cls_ce: 1.6155 decode.loss_mask_ce: 0.8270 decode.loss_mask_dice: 1.6721 decode.d7.loss_cls_ce: 1.6409 decode.d7.loss_mask_ce: 0.8189 decode.d7.loss_mask_dice: 1.6802 2023/09/07 21:35:50 - mmengine - INFO - Iter(train) [42550/60000] base_lr: 2.9084e-05 lr: 2.9084e-05 eta: 4:46:54 time: 0.9884 data_time: 0.0232 memory: 29249 grad_norm: 18.2245 loss: 8.9515 decode.loss_cls_ce: 1.7790 decode.loss_mask_ce: 0.9466 decode.loss_mask_dice: 1.7505 decode.d7.loss_cls_ce: 1.7383 decode.d7.loss_mask_ce: 0.9527 decode.d7.loss_mask_dice: 1.7844 2023/09/07 21:36:39 - mmengine - INFO - Iter(train) [42600/60000] base_lr: 2.9000e-05 lr: 2.9000e-05 eta: 4:46:05 time: 0.9901 data_time: 0.0226 memory: 29302 grad_norm: 20.2333 loss: 8.3340 decode.loss_cls_ce: 1.4865 decode.loss_mask_ce: 0.9237 decode.loss_mask_dice: 1.7297 decode.d7.loss_cls_ce: 1.5135 decode.d7.loss_mask_ce: 0.9254 decode.d7.loss_mask_dice: 1.7551 2023/09/07 21:37:29 - mmengine - INFO - Iter(train) [42650/60000] base_lr: 2.8917e-05 lr: 2.8917e-05 eta: 4:45:15 time: 0.9889 data_time: 0.0221 memory: 29201 grad_norm: 22.3791 loss: 6.9254 decode.loss_cls_ce: 1.5813 decode.loss_mask_ce: 0.6658 decode.loss_mask_dice: 1.2212 decode.d7.loss_cls_ce: 1.5480 decode.d7.loss_mask_ce: 0.6753 decode.d7.loss_mask_dice: 1.2338 2023/09/07 21:38:18 - mmengine - INFO - Iter(train) [42700/60000] base_lr: 2.8834e-05 lr: 2.8834e-05 eta: 4:44:26 time: 0.9847 data_time: 0.0225 memory: 29327 grad_norm: 18.0303 loss: 9.0765 decode.loss_cls_ce: 1.7394 decode.loss_mask_ce: 0.9366 decode.loss_mask_dice: 1.8862 decode.d7.loss_cls_ce: 1.7230 decode.d7.loss_mask_ce: 0.9290 decode.d7.loss_mask_dice: 1.8624 2023/09/07 21:39:08 - mmengine - INFO - Iter(train) [42750/60000] base_lr: 2.8750e-05 lr: 2.8750e-05 eta: 4:43:37 time: 0.9867 data_time: 0.0224 memory: 29140 grad_norm: 19.1363 loss: 7.6906 decode.loss_cls_ce: 1.5569 decode.loss_mask_ce: 0.7746 decode.loss_mask_dice: 1.4835 decode.d7.loss_cls_ce: 1.5589 decode.d7.loss_mask_ce: 0.7983 decode.d7.loss_mask_dice: 1.5185 2023/09/07 21:39:57 - mmengine - INFO - Iter(train) [42800/60000] base_lr: 2.8667e-05 lr: 2.8667e-05 eta: 4:42:47 time: 0.9900 data_time: 0.0227 memory: 29189 grad_norm: 18.1490 loss: 7.0832 decode.loss_cls_ce: 1.3825 decode.loss_mask_ce: 0.7352 decode.loss_mask_dice: 1.4105 decode.d7.loss_cls_ce: 1.4328 decode.d7.loss_mask_ce: 0.7325 decode.d7.loss_mask_dice: 1.3897 2023/09/07 21:40:46 - mmengine - INFO - Iter(train) [42850/60000] base_lr: 2.8584e-05 lr: 2.8584e-05 eta: 4:41:58 time: 0.9866 data_time: 0.0233 memory: 29216 grad_norm: 20.5071 loss: 7.0736 decode.loss_cls_ce: 1.3784 decode.loss_mask_ce: 0.7262 decode.loss_mask_dice: 1.4308 decode.d7.loss_cls_ce: 1.3744 decode.d7.loss_mask_ce: 0.7415 decode.d7.loss_mask_dice: 1.4222 2023/09/07 21:41:36 - mmengine - INFO - Iter(train) [42900/60000] base_lr: 2.8500e-05 lr: 2.8500e-05 eta: 4:41:09 time: 0.9881 data_time: 0.0224 memory: 29217 grad_norm: 18.7552 loss: 8.1373 decode.loss_cls_ce: 1.6375 decode.loss_mask_ce: 0.8150 decode.loss_mask_dice: 1.6132 decode.d7.loss_cls_ce: 1.6111 decode.d7.loss_mask_ce: 0.8329 decode.d7.loss_mask_dice: 1.6276 2023/09/07 21:42:25 - mmengine - INFO - Iter(train) [42950/60000] base_lr: 2.8417e-05 lr: 2.8417e-05 eta: 4:40:20 time: 0.9893 data_time: 0.0224 memory: 29203 grad_norm: 23.4851 loss: 9.1140 decode.loss_cls_ce: 1.6754 decode.loss_mask_ce: 1.0096 decode.loss_mask_dice: 1.8775 decode.d7.loss_cls_ce: 1.6386 decode.d7.loss_mask_ce: 1.0338 decode.d7.loss_mask_dice: 1.8791 2023/09/07 21:43:15 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 21:43:15 - mmengine - INFO - Iter(train) [43000/60000] base_lr: 2.8334e-05 lr: 2.8334e-05 eta: 4:39:30 time: 0.9902 data_time: 0.0229 memory: 29288 grad_norm: 18.4616 loss: 8.3111 decode.loss_cls_ce: 1.6451 decode.loss_mask_ce: 0.7959 decode.loss_mask_dice: 1.6738 decode.d7.loss_cls_ce: 1.7010 decode.d7.loss_mask_ce: 0.8086 decode.d7.loss_mask_dice: 1.6868 2023/09/07 21:44:04 - mmengine - INFO - Iter(train) [43050/60000] base_lr: 2.8250e-05 lr: 2.8250e-05 eta: 4:38:41 time: 0.9871 data_time: 0.0226 memory: 29153 grad_norm: 16.7483 loss: 7.4126 decode.loss_cls_ce: 1.4921 decode.loss_mask_ce: 0.7256 decode.loss_mask_dice: 1.4960 decode.d7.loss_cls_ce: 1.4871 decode.d7.loss_mask_ce: 0.7182 decode.d7.loss_mask_dice: 1.4936 2023/09/07 21:44:54 - mmengine - INFO - Iter(train) [43100/60000] base_lr: 2.8167e-05 lr: 2.8167e-05 eta: 4:37:52 time: 0.9938 data_time: 0.0228 memory: 29320 grad_norm: 16.9187 loss: 7.5705 decode.loss_cls_ce: 1.4873 decode.loss_mask_ce: 0.7854 decode.loss_mask_dice: 1.4937 decode.d7.loss_cls_ce: 1.5403 decode.d7.loss_mask_ce: 0.7849 decode.d7.loss_mask_dice: 1.4789 2023/09/07 21:45:43 - mmengine - INFO - Iter(train) [43150/60000] base_lr: 2.8084e-05 lr: 2.8084e-05 eta: 4:37:02 time: 0.9892 data_time: 0.0227 memory: 29189 grad_norm: 17.8020 loss: 7.7680 decode.loss_cls_ce: 1.5473 decode.loss_mask_ce: 0.8300 decode.loss_mask_dice: 1.4778 decode.d7.loss_cls_ce: 1.5944 decode.d7.loss_mask_ce: 0.8226 decode.d7.loss_mask_dice: 1.4958 2023/09/07 21:46:33 - mmengine - INFO - Iter(train) [43200/60000] base_lr: 2.8000e-05 lr: 2.8000e-05 eta: 4:36:13 time: 0.9900 data_time: 0.0227 memory: 29142 grad_norm: 20.5997 loss: 7.0926 decode.loss_cls_ce: 1.4519 decode.loss_mask_ce: 0.7371 decode.loss_mask_dice: 1.3491 decode.d7.loss_cls_ce: 1.4514 decode.d7.loss_mask_ce: 0.7419 decode.d7.loss_mask_dice: 1.3611 2023/09/07 21:47:22 - mmengine - INFO - Iter(train) [43250/60000] base_lr: 2.7917e-05 lr: 2.7917e-05 eta: 4:35:24 time: 0.9873 data_time: 0.0236 memory: 29203 grad_norm: 20.9067 loss: 9.4354 decode.loss_cls_ce: 1.7477 decode.loss_mask_ce: 0.9440 decode.loss_mask_dice: 2.0373 decode.d7.loss_cls_ce: 1.7278 decode.d7.loss_mask_ce: 0.9490 decode.d7.loss_mask_dice: 2.0298 2023/09/07 21:48:12 - mmengine - INFO - Iter(train) [43300/60000] base_lr: 2.7834e-05 lr: 2.7834e-05 eta: 4:34:35 time: 0.9888 data_time: 0.0230 memory: 29277 grad_norm: 16.5280 loss: 8.2161 decode.loss_cls_ce: 1.4355 decode.loss_mask_ce: 0.9984 decode.loss_mask_dice: 1.6527 decode.d7.loss_cls_ce: 1.4366 decode.d7.loss_mask_ce: 1.0309 decode.d7.loss_mask_dice: 1.6621 2023/09/07 21:49:01 - mmengine - INFO - Iter(train) [43350/60000] base_lr: 2.7750e-05 lr: 2.7750e-05 eta: 4:33:45 time: 0.9892 data_time: 0.0222 memory: 29155 grad_norm: 19.2030 loss: 8.3964 decode.loss_cls_ce: 1.7209 decode.loss_mask_ce: 0.8147 decode.loss_mask_dice: 1.6782 decode.d7.loss_cls_ce: 1.6832 decode.d7.loss_mask_ce: 0.8181 decode.d7.loss_mask_dice: 1.6813 2023/09/07 21:49:51 - mmengine - INFO - Iter(train) [43400/60000] base_lr: 2.7667e-05 lr: 2.7667e-05 eta: 4:32:56 time: 0.9903 data_time: 0.0235 memory: 29125 grad_norm: 17.1270 loss: 6.6217 decode.loss_cls_ce: 1.4476 decode.loss_mask_ce: 0.7005 decode.loss_mask_dice: 1.1547 decode.d7.loss_cls_ce: 1.4658 decode.d7.loss_mask_ce: 0.6945 decode.d7.loss_mask_dice: 1.1586 2023/09/07 21:50:40 - mmengine - INFO - Iter(train) [43450/60000] base_lr: 2.7584e-05 lr: 2.7584e-05 eta: 4:32:07 time: 0.9924 data_time: 0.0220 memory: 29306 grad_norm: 18.2121 loss: 7.7247 decode.loss_cls_ce: 1.4255 decode.loss_mask_ce: 0.8446 decode.loss_mask_dice: 1.5953 decode.d7.loss_cls_ce: 1.4265 decode.d7.loss_mask_ce: 0.8414 decode.d7.loss_mask_dice: 1.5914 2023/09/07 21:51:30 - mmengine - INFO - Iter(train) [43500/60000] base_lr: 2.7500e-05 lr: 2.7500e-05 eta: 4:31:17 time: 0.9860 data_time: 0.0225 memory: 29182 grad_norm: 19.1905 loss: 8.2262 decode.loss_cls_ce: 1.6514 decode.loss_mask_ce: 0.8645 decode.loss_mask_dice: 1.5892 decode.d7.loss_cls_ce: 1.6636 decode.d7.loss_mask_ce: 0.8712 decode.d7.loss_mask_dice: 1.5861 2023/09/07 21:52:19 - mmengine - INFO - Iter(train) [43550/60000] base_lr: 2.7417e-05 lr: 2.7417e-05 eta: 4:30:28 time: 0.9908 data_time: 0.0224 memory: 29166 grad_norm: 19.2421 loss: 8.4606 decode.loss_cls_ce: 1.7811 decode.loss_mask_ce: 0.8239 decode.loss_mask_dice: 1.6358 decode.d7.loss_cls_ce: 1.7821 decode.d7.loss_mask_ce: 0.8181 decode.d7.loss_mask_dice: 1.6194 2023/09/07 21:53:08 - mmengine - INFO - Iter(train) [43600/60000] base_lr: 2.7334e-05 lr: 2.7334e-05 eta: 4:29:39 time: 0.9861 data_time: 0.0233 memory: 29245 grad_norm: 18.6538 loss: 8.3430 decode.loss_cls_ce: 1.6200 decode.loss_mask_ce: 0.9319 decode.loss_mask_dice: 1.6161 decode.d7.loss_cls_ce: 1.6063 decode.d7.loss_mask_ce: 0.9519 decode.d7.loss_mask_dice: 1.6168 2023/09/07 21:53:58 - mmengine - INFO - Iter(train) [43650/60000] base_lr: 2.7250e-05 lr: 2.7250e-05 eta: 4:28:50 time: 0.9897 data_time: 0.0234 memory: 29269 grad_norm: 18.4249 loss: 7.5467 decode.loss_cls_ce: 1.4592 decode.loss_mask_ce: 0.8228 decode.loss_mask_dice: 1.4722 decode.d7.loss_cls_ce: 1.5188 decode.d7.loss_mask_ce: 0.8218 decode.d7.loss_mask_dice: 1.4519 2023/09/07 21:54:47 - mmengine - INFO - Iter(train) [43700/60000] base_lr: 2.7167e-05 lr: 2.7167e-05 eta: 4:28:00 time: 0.9896 data_time: 0.0229 memory: 29179 grad_norm: 20.4534 loss: 7.4870 decode.loss_cls_ce: 1.5618 decode.loss_mask_ce: 0.7755 decode.loss_mask_dice: 1.3941 decode.d7.loss_cls_ce: 1.5960 decode.d7.loss_mask_ce: 0.7691 decode.d7.loss_mask_dice: 1.3904 2023/09/07 21:55:37 - mmengine - INFO - Iter(train) [43750/60000] base_lr: 2.7084e-05 lr: 2.7084e-05 eta: 4:27:11 time: 0.9885 data_time: 0.0228 memory: 29358 grad_norm: 17.4504 loss: 8.7203 decode.loss_cls_ce: 1.8036 decode.loss_mask_ce: 0.9748 decode.loss_mask_dice: 1.6089 decode.d7.loss_cls_ce: 1.7653 decode.d7.loss_mask_ce: 0.9654 decode.d7.loss_mask_dice: 1.6021 2023/09/07 21:56:26 - mmengine - INFO - Iter(train) [43800/60000] base_lr: 2.7000e-05 lr: 2.7000e-05 eta: 4:26:22 time: 0.9885 data_time: 0.0237 memory: 29179 grad_norm: 19.5900 loss: 7.5634 decode.loss_cls_ce: 1.5726 decode.loss_mask_ce: 0.7696 decode.loss_mask_dice: 1.4200 decode.d7.loss_cls_ce: 1.6048 decode.d7.loss_mask_ce: 0.7600 decode.d7.loss_mask_dice: 1.4364 2023/09/07 21:57:16 - mmengine - INFO - Iter(train) [43850/60000] base_lr: 2.6917e-05 lr: 2.6917e-05 eta: 4:25:32 time: 0.9879 data_time: 0.0236 memory: 29148 grad_norm: 19.3012 loss: 8.2163 decode.loss_cls_ce: 1.6108 decode.loss_mask_ce: 0.7751 decode.loss_mask_dice: 1.7246 decode.d7.loss_cls_ce: 1.6022 decode.d7.loss_mask_ce: 0.7902 decode.d7.loss_mask_dice: 1.7134 2023/09/07 21:58:05 - mmengine - INFO - Iter(train) [43900/60000] base_lr: 2.6834e-05 lr: 2.6834e-05 eta: 4:24:43 time: 0.9903 data_time: 0.0228 memory: 29294 grad_norm: 17.5991 loss: 8.0259 decode.loss_cls_ce: 1.5988 decode.loss_mask_ce: 0.8058 decode.loss_mask_dice: 1.5957 decode.d7.loss_cls_ce: 1.6400 decode.d7.loss_mask_ce: 0.8184 decode.d7.loss_mask_dice: 1.5671 2023/09/07 21:58:55 - mmengine - INFO - Iter(train) [43950/60000] base_lr: 2.6750e-05 lr: 2.6750e-05 eta: 4:23:54 time: 0.9897 data_time: 0.0225 memory: 29245 grad_norm: 17.9873 loss: 8.6059 decode.loss_cls_ce: 1.7592 decode.loss_mask_ce: 0.8166 decode.loss_mask_dice: 1.7185 decode.d7.loss_cls_ce: 1.7675 decode.d7.loss_mask_ce: 0.8231 decode.d7.loss_mask_dice: 1.7209 2023/09/07 21:59:44 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 21:59:44 - mmengine - INFO - Iter(train) [44000/60000] base_lr: 2.6667e-05 lr: 2.6667e-05 eta: 4:23:05 time: 0.9939 data_time: 0.0231 memory: 29178 grad_norm: 24.5808 loss: 8.5115 decode.loss_cls_ce: 1.7581 decode.loss_mask_ce: 0.8188 decode.loss_mask_dice: 1.6827 decode.d7.loss_cls_ce: 1.7654 decode.d7.loss_mask_ce: 0.8047 decode.d7.loss_mask_dice: 1.6817 2023/09/07 22:00:34 - mmengine - INFO - Iter(train) [44050/60000] base_lr: 2.6584e-05 lr: 2.6584e-05 eta: 4:22:15 time: 0.9898 data_time: 0.0228 memory: 29095 grad_norm: 19.7058 loss: 6.7538 decode.loss_cls_ce: 1.3460 decode.loss_mask_ce: 0.7376 decode.loss_mask_dice: 1.2871 decode.d7.loss_cls_ce: 1.3748 decode.d7.loss_mask_ce: 0.7288 decode.d7.loss_mask_dice: 1.2796 2023/09/07 22:01:23 - mmengine - INFO - Iter(train) [44100/60000] base_lr: 2.6500e-05 lr: 2.6500e-05 eta: 4:21:26 time: 0.9874 data_time: 0.0225 memory: 29094 grad_norm: 18.6406 loss: 7.5691 decode.loss_cls_ce: 1.6220 decode.loss_mask_ce: 0.7934 decode.loss_mask_dice: 1.3675 decode.d7.loss_cls_ce: 1.6266 decode.d7.loss_mask_ce: 0.8000 decode.d7.loss_mask_dice: 1.3596 2023/09/07 22:02:13 - mmengine - INFO - Iter(train) [44150/60000] base_lr: 2.6417e-05 lr: 2.6417e-05 eta: 4:20:37 time: 0.9916 data_time: 0.0224 memory: 29241 grad_norm: 17.9993 loss: 7.5936 decode.loss_cls_ce: 1.5352 decode.loss_mask_ce: 0.7522 decode.loss_mask_dice: 1.5076 decode.d7.loss_cls_ce: 1.5455 decode.d7.loss_mask_ce: 0.7481 decode.d7.loss_mask_dice: 1.5050 2023/09/07 22:03:02 - mmengine - INFO - Iter(train) [44200/60000] base_lr: 2.6334e-05 lr: 2.6334e-05 eta: 4:19:47 time: 0.9892 data_time: 0.0224 memory: 29114 grad_norm: 17.2683 loss: 7.9449 decode.loss_cls_ce: 1.5444 decode.loss_mask_ce: 0.7640 decode.loss_mask_dice: 1.6521 decode.d7.loss_cls_ce: 1.5583 decode.d7.loss_mask_ce: 0.7797 decode.d7.loss_mask_dice: 1.6464 2023/09/07 22:03:52 - mmengine - INFO - Iter(train) [44250/60000] base_lr: 2.6250e-05 lr: 2.6250e-05 eta: 4:18:58 time: 0.9903 data_time: 0.0221 memory: 29255 grad_norm: 18.6830 loss: 8.5174 decode.loss_cls_ce: 1.6631 decode.loss_mask_ce: 0.8334 decode.loss_mask_dice: 1.7474 decode.d7.loss_cls_ce: 1.7084 decode.d7.loss_mask_ce: 0.8245 decode.d7.loss_mask_dice: 1.7406 2023/09/07 22:04:41 - mmengine - INFO - Iter(train) [44300/60000] base_lr: 2.6167e-05 lr: 2.6167e-05 eta: 4:18:09 time: 0.9879 data_time: 0.0235 memory: 29265 grad_norm: 17.2036 loss: 7.9690 decode.loss_cls_ce: 1.6723 decode.loss_mask_ce: 0.7468 decode.loss_mask_dice: 1.5510 decode.d7.loss_cls_ce: 1.6867 decode.d7.loss_mask_ce: 0.7502 decode.d7.loss_mask_dice: 1.5620 2023/09/07 22:05:31 - mmengine - INFO - Iter(train) [44350/60000] base_lr: 2.6084e-05 lr: 2.6084e-05 eta: 4:17:20 time: 0.9895 data_time: 0.0236 memory: 29191 grad_norm: 18.1328 loss: 8.0298 decode.loss_cls_ce: 1.6161 decode.loss_mask_ce: 0.8224 decode.loss_mask_dice: 1.5743 decode.d7.loss_cls_ce: 1.6513 decode.d7.loss_mask_ce: 0.8027 decode.d7.loss_mask_dice: 1.5631 2023/09/07 22:06:20 - mmengine - INFO - Iter(train) [44400/60000] base_lr: 2.6000e-05 lr: 2.6000e-05 eta: 4:16:30 time: 0.9914 data_time: 0.0227 memory: 29213 grad_norm: 18.0385 loss: 7.6869 decode.loss_cls_ce: 1.5496 decode.loss_mask_ce: 0.7353 decode.loss_mask_dice: 1.5398 decode.d7.loss_cls_ce: 1.5774 decode.d7.loss_mask_ce: 0.7351 decode.d7.loss_mask_dice: 1.5498 2023/09/07 22:07:10 - mmengine - INFO - Iter(train) [44450/60000] base_lr: 2.5917e-05 lr: 2.5917e-05 eta: 4:15:41 time: 0.9879 data_time: 0.0232 memory: 29115 grad_norm: 20.1921 loss: 8.1758 decode.loss_cls_ce: 1.5511 decode.loss_mask_ce: 0.8248 decode.loss_mask_dice: 1.7021 decode.d7.loss_cls_ce: 1.5733 decode.d7.loss_mask_ce: 0.8231 decode.d7.loss_mask_dice: 1.7014 2023/09/07 22:07:59 - mmengine - INFO - Iter(train) [44500/60000] base_lr: 2.5834e-05 lr: 2.5834e-05 eta: 4:14:52 time: 0.9893 data_time: 0.0233 memory: 29214 grad_norm: 16.9846 loss: 8.1680 decode.loss_cls_ce: 1.4678 decode.loss_mask_ce: 0.8735 decode.loss_mask_dice: 1.7296 decode.d7.loss_cls_ce: 1.4800 decode.d7.loss_mask_ce: 0.8839 decode.d7.loss_mask_dice: 1.7333 2023/09/07 22:08:48 - mmengine - INFO - Iter(train) [44550/60000] base_lr: 2.5750e-05 lr: 2.5750e-05 eta: 4:14:02 time: 0.9877 data_time: 0.0226 memory: 29231 grad_norm: 19.0427 loss: 8.2548 decode.loss_cls_ce: 1.5976 decode.loss_mask_ce: 0.8966 decode.loss_mask_dice: 1.6097 decode.d7.loss_cls_ce: 1.6167 decode.d7.loss_mask_ce: 0.9300 decode.d7.loss_mask_dice: 1.6042 2023/09/07 22:09:38 - mmengine - INFO - Iter(train) [44600/60000] base_lr: 2.5667e-05 lr: 2.5667e-05 eta: 4:13:13 time: 0.9897 data_time: 0.0228 memory: 29144 grad_norm: 19.3157 loss: 7.8512 decode.loss_cls_ce: 1.6160 decode.loss_mask_ce: 0.7859 decode.loss_mask_dice: 1.5093 decode.d7.loss_cls_ce: 1.6396 decode.d7.loss_mask_ce: 0.7915 decode.d7.loss_mask_dice: 1.5088 2023/09/07 22:10:27 - mmengine - INFO - Iter(train) [44650/60000] base_lr: 2.5584e-05 lr: 2.5584e-05 eta: 4:12:24 time: 0.9905 data_time: 0.0222 memory: 29154 grad_norm: 20.0301 loss: 7.5036 decode.loss_cls_ce: 1.5849 decode.loss_mask_ce: 0.6774 decode.loss_mask_dice: 1.4816 decode.d7.loss_cls_ce: 1.6244 decode.d7.loss_mask_ce: 0.6712 decode.d7.loss_mask_dice: 1.4642 2023/09/07 22:11:17 - mmengine - INFO - Iter(train) [44700/60000] base_lr: 2.5500e-05 lr: 2.5500e-05 eta: 4:11:35 time: 0.9886 data_time: 0.0221 memory: 29132 grad_norm: 22.0225 loss: 7.8441 decode.loss_cls_ce: 1.6691 decode.loss_mask_ce: 0.7892 decode.loss_mask_dice: 1.4360 decode.d7.loss_cls_ce: 1.7124 decode.d7.loss_mask_ce: 0.7857 decode.d7.loss_mask_dice: 1.4517 2023/09/07 22:12:06 - mmengine - INFO - Iter(train) [44750/60000] base_lr: 2.5417e-05 lr: 2.5417e-05 eta: 4:10:45 time: 0.9923 data_time: 0.0232 memory: 29175 grad_norm: 18.9807 loss: 8.3361 decode.loss_cls_ce: 1.6951 decode.loss_mask_ce: 0.8316 decode.loss_mask_dice: 1.6379 decode.d7.loss_cls_ce: 1.6998 decode.d7.loss_mask_ce: 0.8279 decode.d7.loss_mask_dice: 1.6438 2023/09/07 22:12:56 - mmengine - INFO - Iter(train) [44800/60000] base_lr: 2.5334e-05 lr: 2.5334e-05 eta: 4:09:56 time: 0.9871 data_time: 0.0227 memory: 29109 grad_norm: 17.6394 loss: 6.8604 decode.loss_cls_ce: 1.2844 decode.loss_mask_ce: 0.7439 decode.loss_mask_dice: 1.3754 decode.d7.loss_cls_ce: 1.3161 decode.d7.loss_mask_ce: 0.7506 decode.d7.loss_mask_dice: 1.3900 2023/09/07 22:13:45 - mmengine - INFO - Iter(train) [44850/60000] base_lr: 2.5250e-05 lr: 2.5250e-05 eta: 4:09:07 time: 0.9878 data_time: 0.0225 memory: 29306 grad_norm: 16.1098 loss: 8.4956 decode.loss_cls_ce: 1.6712 decode.loss_mask_ce: 0.8293 decode.loss_mask_dice: 1.7345 decode.d7.loss_cls_ce: 1.6822 decode.d7.loss_mask_ce: 0.8297 decode.d7.loss_mask_dice: 1.7487 2023/09/07 22:14:35 - mmengine - INFO - Iter(train) [44900/60000] base_lr: 2.5167e-05 lr: 2.5167e-05 eta: 4:08:17 time: 0.9873 data_time: 0.0226 memory: 29205 grad_norm: 19.4845 loss: 7.8029 decode.loss_cls_ce: 1.6419 decode.loss_mask_ce: 0.8285 decode.loss_mask_dice: 1.4368 decode.d7.loss_cls_ce: 1.6283 decode.d7.loss_mask_ce: 0.8207 decode.d7.loss_mask_dice: 1.4468 2023/09/07 22:15:24 - mmengine - INFO - Iter(train) [44950/60000] base_lr: 2.5084e-05 lr: 2.5084e-05 eta: 4:07:28 time: 0.9866 data_time: 0.0228 memory: 29295 grad_norm: 18.2443 loss: 8.1373 decode.loss_cls_ce: 1.7018 decode.loss_mask_ce: 0.7549 decode.loss_mask_dice: 1.5872 decode.d7.loss_cls_ce: 1.7484 decode.d7.loss_mask_ce: 0.7537 decode.d7.loss_mask_dice: 1.5913 2023/09/07 22:16:13 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 22:16:13 - mmengine - INFO - Iter(train) [45000/60000] base_lr: 2.5000e-05 lr: 2.5000e-05 eta: 4:06:39 time: 0.9893 data_time: 0.0233 memory: 29194 grad_norm: 19.9160 loss: 9.0083 decode.loss_cls_ce: 1.8589 decode.loss_mask_ce: 0.8255 decode.loss_mask_dice: 1.8122 decode.d7.loss_cls_ce: 1.8914 decode.d7.loss_mask_ce: 0.8167 decode.d7.loss_mask_dice: 1.8036 2023/09/07 22:17:03 - mmengine - INFO - Iter(train) [45050/60000] base_lr: 2.4917e-05 lr: 2.4917e-05 eta: 4:05:50 time: 0.9897 data_time: 0.0225 memory: 29206 grad_norm: 17.9629 loss: 8.4153 decode.loss_cls_ce: 1.6182 decode.loss_mask_ce: 0.8926 decode.loss_mask_dice: 1.6883 decode.d7.loss_cls_ce: 1.6535 decode.d7.loss_mask_ce: 0.8832 decode.d7.loss_mask_dice: 1.6795 2023/09/07 22:17:53 - mmengine - INFO - Iter(train) [45100/60000] base_lr: 2.4834e-05 lr: 2.4834e-05 eta: 4:05:00 time: 0.9886 data_time: 0.0226 memory: 29316 grad_norm: 20.1221 loss: 7.2641 decode.loss_cls_ce: 1.5972 decode.loss_mask_ce: 0.7117 decode.loss_mask_dice: 1.3215 decode.d7.loss_cls_ce: 1.5978 decode.d7.loss_mask_ce: 0.7104 decode.d7.loss_mask_dice: 1.3254 2023/09/07 22:18:42 - mmengine - INFO - Iter(train) [45150/60000] base_lr: 2.4750e-05 lr: 2.4750e-05 eta: 4:04:11 time: 0.9879 data_time: 0.0226 memory: 29213 grad_norm: 20.7614 loss: 7.3500 decode.loss_cls_ce: 1.4278 decode.loss_mask_ce: 0.8080 decode.loss_mask_dice: 1.4324 decode.d7.loss_cls_ce: 1.4280 decode.d7.loss_mask_ce: 0.8098 decode.d7.loss_mask_dice: 1.4440 2023/09/07 22:19:32 - mmengine - INFO - Iter(train) [45200/60000] base_lr: 2.4667e-05 lr: 2.4667e-05 eta: 4:03:22 time: 0.9866 data_time: 0.0222 memory: 29191 grad_norm: 24.3546 loss: 8.5575 decode.loss_cls_ce: 1.7965 decode.loss_mask_ce: 0.8372 decode.loss_mask_dice: 1.6466 decode.d7.loss_cls_ce: 1.8344 decode.d7.loss_mask_ce: 0.8139 decode.d7.loss_mask_dice: 1.6288 2023/09/07 22:20:21 - mmengine - INFO - Iter(train) [45250/60000] base_lr: 2.4584e-05 lr: 2.4584e-05 eta: 4:02:32 time: 0.9913 data_time: 0.0225 memory: 29307 grad_norm: 17.8907 loss: 6.3657 decode.loss_cls_ce: 1.2405 decode.loss_mask_ce: 0.6618 decode.loss_mask_dice: 1.2829 decode.d7.loss_cls_ce: 1.2872 decode.d7.loss_mask_ce: 0.6582 decode.d7.loss_mask_dice: 1.2352 2023/09/07 22:21:10 - mmengine - INFO - Iter(train) [45300/60000] base_lr: 2.4500e-05 lr: 2.4500e-05 eta: 4:01:43 time: 0.9912 data_time: 0.0223 memory: 29252 grad_norm: 18.1231 loss: 8.2914 decode.loss_cls_ce: 1.7495 decode.loss_mask_ce: 0.7794 decode.loss_mask_dice: 1.6249 decode.d7.loss_cls_ce: 1.7176 decode.d7.loss_mask_ce: 0.7937 decode.d7.loss_mask_dice: 1.6264 2023/09/07 22:22:00 - mmengine - INFO - Iter(train) [45350/60000] base_lr: 2.4417e-05 lr: 2.4417e-05 eta: 4:00:54 time: 0.9899 data_time: 0.0234 memory: 29255 grad_norm: 17.3678 loss: 7.3922 decode.loss_cls_ce: 1.4187 decode.loss_mask_ce: 0.7805 decode.loss_mask_dice: 1.4792 decode.d7.loss_cls_ce: 1.4470 decode.d7.loss_mask_ce: 0.7852 decode.d7.loss_mask_dice: 1.4815 2023/09/07 22:22:49 - mmengine - INFO - Iter(train) [45400/60000] base_lr: 2.4334e-05 lr: 2.4334e-05 eta: 4:00:05 time: 0.9934 data_time: 0.0225 memory: 29254 grad_norm: 19.0335 loss: 9.3993 decode.loss_cls_ce: 1.8488 decode.loss_mask_ce: 0.9325 decode.loss_mask_dice: 1.9357 decode.d7.loss_cls_ce: 1.8686 decode.d7.loss_mask_ce: 0.9043 decode.d7.loss_mask_dice: 1.9094 2023/09/07 22:23:39 - mmengine - INFO - Iter(train) [45450/60000] base_lr: 2.4250e-05 lr: 2.4250e-05 eta: 3:59:15 time: 0.9911 data_time: 0.0223 memory: 29191 grad_norm: 19.4593 loss: 8.0736 decode.loss_cls_ce: 1.4405 decode.loss_mask_ce: 0.8677 decode.loss_mask_dice: 1.7447 decode.d7.loss_cls_ce: 1.4202 decode.d7.loss_mask_ce: 0.8611 decode.d7.loss_mask_dice: 1.7394 2023/09/07 22:24:28 - mmengine - INFO - Iter(train) [45500/60000] base_lr: 2.4167e-05 lr: 2.4167e-05 eta: 3:58:26 time: 0.9900 data_time: 0.0228 memory: 29142 grad_norm: 17.0795 loss: 7.5797 decode.loss_cls_ce: 1.5422 decode.loss_mask_ce: 0.8049 decode.loss_mask_dice: 1.4259 decode.d7.loss_cls_ce: 1.5733 decode.d7.loss_mask_ce: 0.8037 decode.d7.loss_mask_dice: 1.4296 2023/09/07 22:25:18 - mmengine - INFO - Iter(train) [45550/60000] base_lr: 2.4084e-05 lr: 2.4084e-05 eta: 3:57:37 time: 0.9894 data_time: 0.0224 memory: 29104 grad_norm: 20.3820 loss: 7.2140 decode.loss_cls_ce: 1.4079 decode.loss_mask_ce: 0.7586 decode.loss_mask_dice: 1.4387 decode.d7.loss_cls_ce: 1.4011 decode.d7.loss_mask_ce: 0.7709 decode.d7.loss_mask_dice: 1.4368 2023/09/07 22:26:07 - mmengine - INFO - Iter(train) [45600/60000] base_lr: 2.4000e-05 lr: 2.4000e-05 eta: 3:56:47 time: 0.9930 data_time: 0.0221 memory: 29330 grad_norm: 19.9194 loss: 8.1430 decode.loss_cls_ce: 1.6009 decode.loss_mask_ce: 0.8440 decode.loss_mask_dice: 1.6207 decode.d7.loss_cls_ce: 1.6029 decode.d7.loss_mask_ce: 0.8432 decode.d7.loss_mask_dice: 1.6313 2023/09/07 22:26:57 - mmengine - INFO - Iter(train) [45650/60000] base_lr: 2.3917e-05 lr: 2.3917e-05 eta: 3:55:58 time: 0.9909 data_time: 0.0228 memory: 29121 grad_norm: 19.6971 loss: 7.9459 decode.loss_cls_ce: 1.5882 decode.loss_mask_ce: 0.7871 decode.loss_mask_dice: 1.6067 decode.d7.loss_cls_ce: 1.5938 decode.d7.loss_mask_ce: 0.7814 decode.d7.loss_mask_dice: 1.5887 2023/09/07 22:27:46 - mmengine - INFO - Iter(train) [45700/60000] base_lr: 2.3834e-05 lr: 2.3834e-05 eta: 3:55:09 time: 0.9889 data_time: 0.0224 memory: 29224 grad_norm: 17.8839 loss: 9.2969 decode.loss_cls_ce: 1.7860 decode.loss_mask_ce: 0.9157 decode.loss_mask_dice: 1.9539 decode.d7.loss_cls_ce: 1.8024 decode.d7.loss_mask_ce: 0.9039 decode.d7.loss_mask_dice: 1.9350 2023/09/07 22:28:36 - mmengine - INFO - Iter(train) [45750/60000] base_lr: 2.3750e-05 lr: 2.3750e-05 eta: 3:54:19 time: 0.9872 data_time: 0.0224 memory: 29191 grad_norm: 17.8499 loss: 7.4950 decode.loss_cls_ce: 1.4237 decode.loss_mask_ce: 0.8160 decode.loss_mask_dice: 1.4851 decode.d7.loss_cls_ce: 1.5028 decode.d7.loss_mask_ce: 0.7965 decode.d7.loss_mask_dice: 1.4708 2023/09/07 22:29:25 - mmengine - INFO - Iter(train) [45800/60000] base_lr: 2.3667e-05 lr: 2.3667e-05 eta: 3:53:30 time: 0.9919 data_time: 0.0246 memory: 29128 grad_norm: 17.1229 loss: 8.0351 decode.loss_cls_ce: 1.6427 decode.loss_mask_ce: 0.7337 decode.loss_mask_dice: 1.6375 decode.d7.loss_cls_ce: 1.6592 decode.d7.loss_mask_ce: 0.7351 decode.d7.loss_mask_dice: 1.6270 2023/09/07 22:30:15 - mmengine - INFO - Iter(train) [45850/60000] base_lr: 2.3584e-05 lr: 2.3584e-05 eta: 3:52:41 time: 0.9943 data_time: 0.0227 memory: 29098 grad_norm: 18.5663 loss: 7.5611 decode.loss_cls_ce: 1.5131 decode.loss_mask_ce: 0.7571 decode.loss_mask_dice: 1.4712 decode.d7.loss_cls_ce: 1.5592 decode.d7.loss_mask_ce: 0.7652 decode.d7.loss_mask_dice: 1.4954 2023/09/07 22:31:04 - mmengine - INFO - Iter(train) [45900/60000] base_lr: 2.3500e-05 lr: 2.3500e-05 eta: 3:51:52 time: 0.9952 data_time: 0.0229 memory: 29108 grad_norm: 21.8960 loss: 7.0670 decode.loss_cls_ce: 1.4085 decode.loss_mask_ce: 0.7820 decode.loss_mask_dice: 1.3157 decode.d7.loss_cls_ce: 1.4440 decode.d7.loss_mask_ce: 0.7821 decode.d7.loss_mask_dice: 1.3346 2023/09/07 22:31:54 - mmengine - INFO - Iter(train) [45950/60000] base_lr: 2.3417e-05 lr: 2.3417e-05 eta: 3:51:02 time: 0.9874 data_time: 0.0228 memory: 29204 grad_norm: 20.3576 loss: 8.5664 decode.loss_cls_ce: 1.7406 decode.loss_mask_ce: 0.8445 decode.loss_mask_dice: 1.6695 decode.d7.loss_cls_ce: 1.7662 decode.d7.loss_mask_ce: 0.8455 decode.d7.loss_mask_dice: 1.7000 2023/09/07 22:32:43 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 22:32:43 - mmengine - INFO - Iter(train) [46000/60000] base_lr: 2.3334e-05 lr: 2.3334e-05 eta: 3:50:13 time: 0.9890 data_time: 0.0221 memory: 29228 grad_norm: 19.4174 loss: 9.3332 decode.loss_cls_ce: 1.8476 decode.loss_mask_ce: 0.9386 decode.loss_mask_dice: 1.8652 decode.d7.loss_cls_ce: 1.8857 decode.d7.loss_mask_ce: 0.9341 decode.d7.loss_mask_dice: 1.8620 2023/09/07 22:33:33 - mmengine - INFO - Iter(train) [46050/60000] base_lr: 2.3250e-05 lr: 2.3250e-05 eta: 3:49:24 time: 0.9870 data_time: 0.0221 memory: 29230 grad_norm: 20.2489 loss: 7.9160 decode.loss_cls_ce: 1.6839 decode.loss_mask_ce: 0.7351 decode.loss_mask_dice: 1.5247 decode.d7.loss_cls_ce: 1.6813 decode.d7.loss_mask_ce: 0.7573 decode.d7.loss_mask_dice: 1.5338 2023/09/07 22:34:22 - mmengine - INFO - Iter(train) [46100/60000] base_lr: 2.3167e-05 lr: 2.3167e-05 eta: 3:48:34 time: 0.9956 data_time: 0.0225 memory: 29207 grad_norm: 20.0569 loss: 8.3233 decode.loss_cls_ce: 1.6607 decode.loss_mask_ce: 0.8310 decode.loss_mask_dice: 1.6635 decode.d7.loss_cls_ce: 1.6824 decode.d7.loss_mask_ce: 0.8269 decode.d7.loss_mask_dice: 1.6588 2023/09/07 22:35:12 - mmengine - INFO - Iter(train) [46150/60000] base_lr: 2.3084e-05 lr: 2.3084e-05 eta: 3:47:45 time: 0.9870 data_time: 0.0231 memory: 29150 grad_norm: 17.7275 loss: 8.4855 decode.loss_cls_ce: 1.5916 decode.loss_mask_ce: 0.9532 decode.loss_mask_dice: 1.7195 decode.d7.loss_cls_ce: 1.5348 decode.d7.loss_mask_ce: 0.9506 decode.d7.loss_mask_dice: 1.7357 2023/09/07 22:36:01 - mmengine - INFO - Iter(train) [46200/60000] base_lr: 2.3000e-05 lr: 2.3000e-05 eta: 3:46:56 time: 0.9875 data_time: 0.0230 memory: 29225 grad_norm: 18.5239 loss: 7.5703 decode.loss_cls_ce: 1.4584 decode.loss_mask_ce: 0.8438 decode.loss_mask_dice: 1.4749 decode.d7.loss_cls_ce: 1.4504 decode.d7.loss_mask_ce: 0.8499 decode.d7.loss_mask_dice: 1.4930 2023/09/07 22:36:51 - mmengine - INFO - Iter(train) [46250/60000] base_lr: 2.2917e-05 lr: 2.2917e-05 eta: 3:46:07 time: 0.9928 data_time: 0.0227 memory: 29167 grad_norm: 19.1665 loss: 7.7902 decode.loss_cls_ce: 1.4137 decode.loss_mask_ce: 0.8709 decode.loss_mask_dice: 1.5698 decode.d7.loss_cls_ce: 1.5024 decode.d7.loss_mask_ce: 0.8632 decode.d7.loss_mask_dice: 1.5702 2023/09/07 22:37:40 - mmengine - INFO - Iter(train) [46300/60000] base_lr: 2.2834e-05 lr: 2.2834e-05 eta: 3:45:17 time: 0.9954 data_time: 0.0220 memory: 29227 grad_norm: 18.3856 loss: 7.9158 decode.loss_cls_ce: 1.4169 decode.loss_mask_ce: 0.8519 decode.loss_mask_dice: 1.6659 decode.d7.loss_cls_ce: 1.4463 decode.d7.loss_mask_ce: 0.8732 decode.d7.loss_mask_dice: 1.6616 2023/09/07 22:38:30 - mmengine - INFO - Iter(train) [46350/60000] base_lr: 2.2750e-05 lr: 2.2750e-05 eta: 3:44:28 time: 0.9897 data_time: 0.0223 memory: 29128 grad_norm: 18.2687 loss: 6.9760 decode.loss_cls_ce: 1.4053 decode.loss_mask_ce: 0.7833 decode.loss_mask_dice: 1.2910 decode.d7.loss_cls_ce: 1.4331 decode.d7.loss_mask_ce: 0.7782 decode.d7.loss_mask_dice: 1.2853 2023/09/07 22:39:19 - mmengine - INFO - Iter(train) [46400/60000] base_lr: 2.2667e-05 lr: 2.2667e-05 eta: 3:43:39 time: 0.9887 data_time: 0.0223 memory: 29183 grad_norm: 18.2262 loss: 7.7513 decode.loss_cls_ce: 1.6342 decode.loss_mask_ce: 0.7843 decode.loss_mask_dice: 1.4464 decode.d7.loss_cls_ce: 1.6502 decode.d7.loss_mask_ce: 0.7888 decode.d7.loss_mask_dice: 1.4474 2023/09/07 22:40:09 - mmengine - INFO - Iter(train) [46450/60000] base_lr: 2.2584e-05 lr: 2.2584e-05 eta: 3:42:49 time: 0.9929 data_time: 0.0221 memory: 29254 grad_norm: 19.3785 loss: 8.2167 decode.loss_cls_ce: 1.5782 decode.loss_mask_ce: 0.8704 decode.loss_mask_dice: 1.6547 decode.d7.loss_cls_ce: 1.5642 decode.d7.loss_mask_ce: 0.8808 decode.d7.loss_mask_dice: 1.6683 2023/09/07 22:40:59 - mmengine - INFO - Iter(train) [46500/60000] base_lr: 2.2500e-05 lr: 2.2500e-05 eta: 3:42:00 time: 0.9899 data_time: 0.0227 memory: 29405 grad_norm: 16.6732 loss: 7.0173 decode.loss_cls_ce: 1.4631 decode.loss_mask_ce: 0.6778 decode.loss_mask_dice: 1.3571 decode.d7.loss_cls_ce: 1.4804 decode.d7.loss_mask_ce: 0.6687 decode.d7.loss_mask_dice: 1.3703 2023/09/07 22:41:48 - mmengine - INFO - Iter(train) [46550/60000] base_lr: 2.2417e-05 lr: 2.2417e-05 eta: 3:41:11 time: 0.9907 data_time: 0.0228 memory: 29188 grad_norm: 22.0976 loss: 6.9719 decode.loss_cls_ce: 1.3880 decode.loss_mask_ce: 0.7154 decode.loss_mask_dice: 1.3652 decode.d7.loss_cls_ce: 1.4260 decode.d7.loss_mask_ce: 0.7272 decode.d7.loss_mask_dice: 1.3501 2023/09/07 22:42:38 - mmengine - INFO - Iter(train) [46600/60000] base_lr: 2.2334e-05 lr: 2.2334e-05 eta: 3:40:22 time: 0.9876 data_time: 0.0228 memory: 29292 grad_norm: 17.3385 loss: 8.1589 decode.loss_cls_ce: 1.6722 decode.loss_mask_ce: 0.8460 decode.loss_mask_dice: 1.5619 decode.d7.loss_cls_ce: 1.6548 decode.d7.loss_mask_ce: 0.8674 decode.d7.loss_mask_dice: 1.5566 2023/09/07 22:43:27 - mmengine - INFO - Iter(train) [46650/60000] base_lr: 2.2250e-05 lr: 2.2250e-05 eta: 3:39:32 time: 0.9948 data_time: 0.0228 memory: 29178 grad_norm: 17.9798 loss: 8.0260 decode.loss_cls_ce: 1.5822 decode.loss_mask_ce: 0.8390 decode.loss_mask_dice: 1.5935 decode.d7.loss_cls_ce: 1.6119 decode.d7.loss_mask_ce: 0.8324 decode.d7.loss_mask_dice: 1.5669 2023/09/07 22:44:17 - mmengine - INFO - Iter(train) [46700/60000] base_lr: 2.2167e-05 lr: 2.2167e-05 eta: 3:38:43 time: 0.9906 data_time: 0.0223 memory: 29202 grad_norm: 17.2297 loss: 8.3663 decode.loss_cls_ce: 1.7862 decode.loss_mask_ce: 0.8279 decode.loss_mask_dice: 1.5373 decode.d7.loss_cls_ce: 1.8219 decode.d7.loss_mask_ce: 0.8297 decode.d7.loss_mask_dice: 1.5631 2023/09/07 22:45:06 - mmengine - INFO - Iter(train) [46750/60000] base_lr: 2.2084e-05 lr: 2.2084e-05 eta: 3:37:54 time: 0.9880 data_time: 0.0236 memory: 29162 grad_norm: 17.2248 loss: 8.6835 decode.loss_cls_ce: 1.7240 decode.loss_mask_ce: 0.9215 decode.loss_mask_dice: 1.6786 decode.d7.loss_cls_ce: 1.7164 decode.d7.loss_mask_ce: 0.9379 decode.d7.loss_mask_dice: 1.7050 2023/09/07 22:45:56 - mmengine - INFO - Iter(train) [46800/60000] base_lr: 2.2000e-05 lr: 2.2000e-05 eta: 3:37:04 time: 0.9919 data_time: 0.0223 memory: 29290 grad_norm: 17.9687 loss: 7.5486 decode.loss_cls_ce: 1.4399 decode.loss_mask_ce: 0.8235 decode.loss_mask_dice: 1.5050 decode.d7.loss_cls_ce: 1.4480 decode.d7.loss_mask_ce: 0.8227 decode.d7.loss_mask_dice: 1.5095 2023/09/07 22:46:45 - mmengine - INFO - Iter(train) [46850/60000] base_lr: 2.1917e-05 lr: 2.1917e-05 eta: 3:36:15 time: 0.9881 data_time: 0.0229 memory: 29126 grad_norm: 19.3731 loss: 7.8403 decode.loss_cls_ce: 1.6812 decode.loss_mask_ce: 0.7153 decode.loss_mask_dice: 1.5049 decode.d7.loss_cls_ce: 1.7206 decode.d7.loss_mask_ce: 0.7163 decode.d7.loss_mask_dice: 1.5020 2023/09/07 22:47:35 - mmengine - INFO - Iter(train) [46900/60000] base_lr: 2.1834e-05 lr: 2.1834e-05 eta: 3:35:26 time: 0.9891 data_time: 0.0226 memory: 29183 grad_norm: 16.5464 loss: 6.5377 decode.loss_cls_ce: 1.5283 decode.loss_mask_ce: 0.6301 decode.loss_mask_dice: 1.0944 decode.d7.loss_cls_ce: 1.5432 decode.d7.loss_mask_ce: 0.6466 decode.d7.loss_mask_dice: 1.0950 2023/09/07 22:48:24 - mmengine - INFO - Iter(train) [46950/60000] base_lr: 2.1750e-05 lr: 2.1750e-05 eta: 3:34:37 time: 0.9859 data_time: 0.0225 memory: 29189 grad_norm: 18.3412 loss: 8.8702 decode.loss_cls_ce: 1.7841 decode.loss_mask_ce: 0.9074 decode.loss_mask_dice: 1.7107 decode.d7.loss_cls_ce: 1.8428 decode.d7.loss_mask_ce: 0.9192 decode.d7.loss_mask_dice: 1.7060 2023/09/07 22:49:13 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 22:49:13 - mmengine - INFO - Iter(train) [47000/60000] base_lr: 2.1667e-05 lr: 2.1667e-05 eta: 3:33:47 time: 0.9861 data_time: 0.0223 memory: 29203 grad_norm: 17.2692 loss: 8.3820 decode.loss_cls_ce: 1.5681 decode.loss_mask_ce: 0.8780 decode.loss_mask_dice: 1.7363 decode.d7.loss_cls_ce: 1.5875 decode.d7.loss_mask_ce: 0.8803 decode.d7.loss_mask_dice: 1.7319 2023/09/07 22:50:03 - mmengine - INFO - Iter(train) [47050/60000] base_lr: 2.1584e-05 lr: 2.1584e-05 eta: 3:32:58 time: 0.9918 data_time: 0.0221 memory: 29246 grad_norm: 16.2009 loss: 7.0694 decode.loss_cls_ce: 1.2925 decode.loss_mask_ce: 0.7664 decode.loss_mask_dice: 1.4689 decode.d7.loss_cls_ce: 1.2954 decode.d7.loss_mask_ce: 0.7679 decode.d7.loss_mask_dice: 1.4783 2023/09/07 22:50:52 - mmengine - INFO - Iter(train) [47100/60000] base_lr: 2.1500e-05 lr: 2.1500e-05 eta: 3:32:09 time: 0.9881 data_time: 0.0226 memory: 29241 grad_norm: 21.0996 loss: 8.7576 decode.loss_cls_ce: 1.8857 decode.loss_mask_ce: 0.8657 decode.loss_mask_dice: 1.6237 decode.d7.loss_cls_ce: 1.8872 decode.d7.loss_mask_ce: 0.8640 decode.d7.loss_mask_dice: 1.6314 2023/09/07 22:51:42 - mmengine - INFO - Iter(train) [47150/60000] base_lr: 2.1417e-05 lr: 2.1417e-05 eta: 3:31:19 time: 0.9886 data_time: 0.0227 memory: 29225 grad_norm: 18.1562 loss: 8.8135 decode.loss_cls_ce: 1.6970 decode.loss_mask_ce: 0.9440 decode.loss_mask_dice: 1.7650 decode.d7.loss_cls_ce: 1.7197 decode.d7.loss_mask_ce: 0.9282 decode.d7.loss_mask_dice: 1.7596 2023/09/07 22:52:31 - mmengine - INFO - Iter(train) [47200/60000] base_lr: 2.1334e-05 lr: 2.1334e-05 eta: 3:30:30 time: 0.9899 data_time: 0.0226 memory: 29239 grad_norm: 18.7471 loss: 7.5364 decode.loss_cls_ce: 1.5915 decode.loss_mask_ce: 0.7711 decode.loss_mask_dice: 1.4090 decode.d7.loss_cls_ce: 1.5869 decode.d7.loss_mask_ce: 0.7752 decode.d7.loss_mask_dice: 1.4028 2023/09/07 22:53:21 - mmengine - INFO - Iter(train) [47250/60000] base_lr: 2.1250e-05 lr: 2.1250e-05 eta: 3:29:41 time: 0.9887 data_time: 0.0227 memory: 29228 grad_norm: 17.1461 loss: 7.6349 decode.loss_cls_ce: 1.3956 decode.loss_mask_ce: 0.7986 decode.loss_mask_dice: 1.5903 decode.d7.loss_cls_ce: 1.4527 decode.d7.loss_mask_ce: 0.7911 decode.d7.loss_mask_dice: 1.6066 2023/09/07 22:54:10 - mmengine - INFO - Iter(train) [47300/60000] base_lr: 2.1167e-05 lr: 2.1167e-05 eta: 3:28:51 time: 0.9858 data_time: 0.0225 memory: 29094 grad_norm: 19.5628 loss: 6.9702 decode.loss_cls_ce: 1.4192 decode.loss_mask_ce: 0.8512 decode.loss_mask_dice: 1.2201 decode.d7.loss_cls_ce: 1.4152 decode.d7.loss_mask_ce: 0.8622 decode.d7.loss_mask_dice: 1.2023 2023/09/07 22:55:00 - mmengine - INFO - Iter(train) [47350/60000] base_lr: 2.1084e-05 lr: 2.1084e-05 eta: 3:28:02 time: 0.9897 data_time: 0.0222 memory: 29205 grad_norm: 21.7313 loss: 7.8725 decode.loss_cls_ce: 1.7006 decode.loss_mask_ce: 0.7630 decode.loss_mask_dice: 1.4639 decode.d7.loss_cls_ce: 1.7257 decode.d7.loss_mask_ce: 0.7698 decode.d7.loss_mask_dice: 1.4495 2023/09/07 22:55:49 - mmengine - INFO - Iter(train) [47400/60000] base_lr: 2.1000e-05 lr: 2.1000e-05 eta: 3:27:13 time: 0.9876 data_time: 0.0226 memory: 29216 grad_norm: 19.3949 loss: 7.2287 decode.loss_cls_ce: 1.5373 decode.loss_mask_ce: 0.7404 decode.loss_mask_dice: 1.3363 decode.d7.loss_cls_ce: 1.5376 decode.d7.loss_mask_ce: 0.7493 decode.d7.loss_mask_dice: 1.3278 2023/09/07 22:56:38 - mmengine - INFO - Iter(train) [47450/60000] base_lr: 2.0917e-05 lr: 2.0917e-05 eta: 3:26:23 time: 0.9889 data_time: 0.0218 memory: 29202 grad_norm: 18.0348 loss: 8.3518 decode.loss_cls_ce: 1.6885 decode.loss_mask_ce: 0.7629 decode.loss_mask_dice: 1.7017 decode.d7.loss_cls_ce: 1.7526 decode.d7.loss_mask_ce: 0.7596 decode.d7.loss_mask_dice: 1.6865 2023/09/07 22:57:28 - mmengine - INFO - Iter(train) [47500/60000] base_lr: 2.0834e-05 lr: 2.0834e-05 eta: 3:25:34 time: 0.9890 data_time: 0.0224 memory: 29150 grad_norm: 18.5703 loss: 7.3649 decode.loss_cls_ce: 1.4884 decode.loss_mask_ce: 0.7223 decode.loss_mask_dice: 1.4448 decode.d7.loss_cls_ce: 1.5358 decode.d7.loss_mask_ce: 0.7182 decode.d7.loss_mask_dice: 1.4554 2023/09/07 22:58:17 - mmengine - INFO - Iter(train) [47550/60000] base_lr: 2.0750e-05 lr: 2.0750e-05 eta: 3:24:45 time: 0.9891 data_time: 0.0232 memory: 29154 grad_norm: 21.5229 loss: 7.5031 decode.loss_cls_ce: 1.5091 decode.loss_mask_ce: 0.7443 decode.loss_mask_dice: 1.4690 decode.d7.loss_cls_ce: 1.5403 decode.d7.loss_mask_ce: 0.7531 decode.d7.loss_mask_dice: 1.4873 2023/09/07 22:59:07 - mmengine - INFO - Iter(train) [47600/60000] base_lr: 2.0667e-05 lr: 2.0667e-05 eta: 3:23:55 time: 0.9905 data_time: 0.0229 memory: 29228 grad_norm: 25.4666 loss: 8.3060 decode.loss_cls_ce: 1.7612 decode.loss_mask_ce: 0.8465 decode.loss_mask_dice: 1.5493 decode.d7.loss_cls_ce: 1.7693 decode.d7.loss_mask_ce: 0.8336 decode.d7.loss_mask_dice: 1.5461 2023/09/07 22:59:56 - mmengine - INFO - Iter(train) [47650/60000] base_lr: 2.0584e-05 lr: 2.0584e-05 eta: 3:23:06 time: 0.9913 data_time: 0.0223 memory: 29203 grad_norm: 16.4953 loss: 8.8214 decode.loss_cls_ce: 1.8652 decode.loss_mask_ce: 0.8397 decode.loss_mask_dice: 1.6902 decode.d7.loss_cls_ce: 1.8808 decode.d7.loss_mask_ce: 0.8495 decode.d7.loss_mask_dice: 1.6960 2023/09/07 23:00:46 - mmengine - INFO - Iter(train) [47700/60000] base_lr: 2.0500e-05 lr: 2.0500e-05 eta: 3:22:17 time: 0.9894 data_time: 0.0226 memory: 29408 grad_norm: 22.2629 loss: 8.6721 decode.loss_cls_ce: 1.8538 decode.loss_mask_ce: 0.7998 decode.loss_mask_dice: 1.6777 decode.d7.loss_cls_ce: 1.8556 decode.d7.loss_mask_ce: 0.8139 decode.d7.loss_mask_dice: 1.6713 2023/09/07 23:01:35 - mmengine - INFO - Iter(train) [47750/60000] base_lr: 2.0417e-05 lr: 2.0417e-05 eta: 3:21:28 time: 0.9884 data_time: 0.0220 memory: 29191 grad_norm: 17.4949 loss: 8.2052 decode.loss_cls_ce: 1.6312 decode.loss_mask_ce: 0.7906 decode.loss_mask_dice: 1.6695 decode.d7.loss_cls_ce: 1.6496 decode.d7.loss_mask_ce: 0.7913 decode.d7.loss_mask_dice: 1.6730 2023/09/07 23:02:25 - mmengine - INFO - Iter(train) [47800/60000] base_lr: 2.0334e-05 lr: 2.0334e-05 eta: 3:20:38 time: 0.9918 data_time: 0.0224 memory: 29163 grad_norm: 19.9736 loss: 6.4006 decode.loss_cls_ce: 1.2692 decode.loss_mask_ce: 0.7473 decode.loss_mask_dice: 1.1684 decode.d7.loss_cls_ce: 1.2982 decode.d7.loss_mask_ce: 0.7490 decode.d7.loss_mask_dice: 1.1685 2023/09/07 23:03:14 - mmengine - INFO - Iter(train) [47850/60000] base_lr: 2.0250e-05 lr: 2.0250e-05 eta: 3:19:49 time: 0.9947 data_time: 0.0224 memory: 29152 grad_norm: 17.7379 loss: 8.1987 decode.loss_cls_ce: 1.6508 decode.loss_mask_ce: 0.8588 decode.loss_mask_dice: 1.5707 decode.d7.loss_cls_ce: 1.6583 decode.d7.loss_mask_ce: 0.8685 decode.d7.loss_mask_dice: 1.5917 2023/09/07 23:04:04 - mmengine - INFO - Iter(train) [47900/60000] base_lr: 2.0167e-05 lr: 2.0167e-05 eta: 3:19:00 time: 0.9874 data_time: 0.0224 memory: 29164 grad_norm: 16.9392 loss: 7.4340 decode.loss_cls_ce: 1.5848 decode.loss_mask_ce: 0.8038 decode.loss_mask_dice: 1.3274 decode.d7.loss_cls_ce: 1.5797 decode.d7.loss_mask_ce: 0.7985 decode.d7.loss_mask_dice: 1.3397 2023/09/07 23:04:53 - mmengine - INFO - Iter(train) [47950/60000] base_lr: 2.0084e-05 lr: 2.0084e-05 eta: 3:18:10 time: 0.9901 data_time: 0.0220 memory: 29188 grad_norm: 19.1284 loss: 7.9730 decode.loss_cls_ce: 1.6294 decode.loss_mask_ce: 0.8039 decode.loss_mask_dice: 1.5272 decode.d7.loss_cls_ce: 1.6711 decode.d7.loss_mask_ce: 0.8116 decode.d7.loss_mask_dice: 1.5298 2023/09/07 23:05:43 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 23:05:43 - mmengine - INFO - Iter(train) [48000/60000] base_lr: 2.0000e-05 lr: 2.0000e-05 eta: 3:17:21 time: 0.9900 data_time: 0.0223 memory: 29148 grad_norm: 18.6850 loss: 7.2750 decode.loss_cls_ce: 1.3462 decode.loss_mask_ce: 0.7864 decode.loss_mask_dice: 1.4845 decode.d7.loss_cls_ce: 1.4230 decode.d7.loss_mask_ce: 0.7596 decode.d7.loss_mask_dice: 1.4753 2023/09/07 23:06:32 - mmengine - INFO - Iter(train) [48050/60000] base_lr: 1.9917e-05 lr: 1.9917e-05 eta: 3:16:32 time: 0.9903 data_time: 0.0242 memory: 29225 grad_norm: 17.9930 loss: 8.7341 decode.loss_cls_ce: 1.6466 decode.loss_mask_ce: 0.8551 decode.loss_mask_dice: 1.8367 decode.d7.loss_cls_ce: 1.7096 decode.d7.loss_mask_ce: 0.8481 decode.d7.loss_mask_dice: 1.8380 2023/09/07 23:07:22 - mmengine - INFO - Iter(train) [48100/60000] base_lr: 1.9834e-05 lr: 1.9834e-05 eta: 3:15:42 time: 0.9884 data_time: 0.0229 memory: 29205 grad_norm: 18.7079 loss: 7.4766 decode.loss_cls_ce: 1.5632 decode.loss_mask_ce: 0.7128 decode.loss_mask_dice: 1.4403 decode.d7.loss_cls_ce: 1.5967 decode.d7.loss_mask_ce: 0.7284 decode.d7.loss_mask_dice: 1.4352 2023/09/07 23:08:11 - mmengine - INFO - Iter(train) [48150/60000] base_lr: 1.9750e-05 lr: 1.9750e-05 eta: 3:14:53 time: 0.9894 data_time: 0.0227 memory: 29179 grad_norm: 18.1547 loss: 9.1642 decode.loss_cls_ce: 1.7923 decode.loss_mask_ce: 0.9162 decode.loss_mask_dice: 1.8557 decode.d7.loss_cls_ce: 1.8200 decode.d7.loss_mask_ce: 0.9272 decode.d7.loss_mask_dice: 1.8527 2023/09/07 23:09:01 - mmengine - INFO - Iter(train) [48200/60000] base_lr: 1.9667e-05 lr: 1.9667e-05 eta: 3:14:04 time: 0.9913 data_time: 0.0222 memory: 29141 grad_norm: 18.2767 loss: 8.0945 decode.loss_cls_ce: 1.6823 decode.loss_mask_ce: 0.7384 decode.loss_mask_dice: 1.6261 decode.d7.loss_cls_ce: 1.6692 decode.d7.loss_mask_ce: 0.7463 decode.d7.loss_mask_dice: 1.6322 2023/09/07 23:09:50 - mmengine - INFO - Iter(train) [48250/60000] base_lr: 1.9584e-05 lr: 1.9584e-05 eta: 3:13:14 time: 0.9878 data_time: 0.0225 memory: 29343 grad_norm: 18.4433 loss: 8.6219 decode.loss_cls_ce: 1.7348 decode.loss_mask_ce: 0.8489 decode.loss_mask_dice: 1.7300 decode.d7.loss_cls_ce: 1.7329 decode.d7.loss_mask_ce: 0.8416 decode.d7.loss_mask_dice: 1.7336 2023/09/07 23:10:40 - mmengine - INFO - Iter(train) [48300/60000] base_lr: 1.9500e-05 lr: 1.9500e-05 eta: 3:12:25 time: 0.9896 data_time: 0.0232 memory: 29279 grad_norm: 18.5175 loss: 8.1685 decode.loss_cls_ce: 1.6938 decode.loss_mask_ce: 0.8006 decode.loss_mask_dice: 1.5838 decode.d7.loss_cls_ce: 1.7178 decode.d7.loss_mask_ce: 0.7949 decode.d7.loss_mask_dice: 1.5776 2023/09/07 23:11:29 - mmengine - INFO - Iter(train) [48350/60000] base_lr: 1.9417e-05 lr: 1.9417e-05 eta: 3:11:36 time: 0.9904 data_time: 0.0234 memory: 29283 grad_norm: 19.0244 loss: 8.3405 decode.loss_cls_ce: 1.5038 decode.loss_mask_ce: 0.8386 decode.loss_mask_dice: 1.8132 decode.d7.loss_cls_ce: 1.5242 decode.d7.loss_mask_ce: 0.8396 decode.d7.loss_mask_dice: 1.8210 2023/09/07 23:12:19 - mmengine - INFO - Iter(train) [48400/60000] base_lr: 1.9334e-05 lr: 1.9334e-05 eta: 3:10:47 time: 0.9902 data_time: 0.0228 memory: 29254 grad_norm: 17.9135 loss: 7.6050 decode.loss_cls_ce: 1.6604 decode.loss_mask_ce: 0.7463 decode.loss_mask_dice: 1.3885 decode.d7.loss_cls_ce: 1.6554 decode.d7.loss_mask_ce: 0.7579 decode.d7.loss_mask_dice: 1.3965 2023/09/07 23:13:08 - mmengine - INFO - Iter(train) [48450/60000] base_lr: 1.9250e-05 lr: 1.9250e-05 eta: 3:09:57 time: 0.9894 data_time: 0.0222 memory: 29241 grad_norm: 16.7073 loss: 8.2390 decode.loss_cls_ce: 1.6107 decode.loss_mask_ce: 0.7453 decode.loss_mask_dice: 1.7237 decode.d7.loss_cls_ce: 1.6186 decode.d7.loss_mask_ce: 0.7682 decode.d7.loss_mask_dice: 1.7725 2023/09/07 23:13:58 - mmengine - INFO - Iter(train) [48500/60000] base_lr: 1.9167e-05 lr: 1.9167e-05 eta: 3:09:08 time: 0.9935 data_time: 0.0223 memory: 29219 grad_norm: 18.2535 loss: 7.6236 decode.loss_cls_ce: 1.4677 decode.loss_mask_ce: 0.8323 decode.loss_mask_dice: 1.5218 decode.d7.loss_cls_ce: 1.4445 decode.d7.loss_mask_ce: 0.8191 decode.d7.loss_mask_dice: 1.5382 2023/09/07 23:14:47 - mmengine - INFO - Iter(train) [48550/60000] base_lr: 1.9084e-05 lr: 1.9084e-05 eta: 3:08:19 time: 0.9898 data_time: 0.0224 memory: 29119 grad_norm: 19.9175 loss: 7.1130 decode.loss_cls_ce: 1.3850 decode.loss_mask_ce: 0.6856 decode.loss_mask_dice: 1.4837 decode.d7.loss_cls_ce: 1.3971 decode.d7.loss_mask_ce: 0.6872 decode.d7.loss_mask_dice: 1.4744 2023/09/07 23:15:37 - mmengine - INFO - Iter(train) [48600/60000] base_lr: 1.9000e-05 lr: 1.9000e-05 eta: 3:07:29 time: 0.9880 data_time: 0.0228 memory: 29099 grad_norm: 17.5092 loss: 8.3918 decode.loss_cls_ce: 1.5879 decode.loss_mask_ce: 0.8328 decode.loss_mask_dice: 1.7585 decode.d7.loss_cls_ce: 1.6084 decode.d7.loss_mask_ce: 0.8361 decode.d7.loss_mask_dice: 1.7680 2023/09/07 23:16:26 - mmengine - INFO - Iter(train) [48650/60000] base_lr: 1.8917e-05 lr: 1.8917e-05 eta: 3:06:40 time: 0.9868 data_time: 0.0226 memory: 29253 grad_norm: 18.0696 loss: 8.1817 decode.loss_cls_ce: 1.5826 decode.loss_mask_ce: 0.8422 decode.loss_mask_dice: 1.6733 decode.d7.loss_cls_ce: 1.5968 decode.d7.loss_mask_ce: 0.8373 decode.d7.loss_mask_dice: 1.6496 2023/09/07 23:17:15 - mmengine - INFO - Iter(train) [48700/60000] base_lr: 1.8834e-05 lr: 1.8834e-05 eta: 3:05:51 time: 0.9865 data_time: 0.0224 memory: 29211 grad_norm: 17.0523 loss: 8.7555 decode.loss_cls_ce: 1.8400 decode.loss_mask_ce: 0.7769 decode.loss_mask_dice: 1.7474 decode.d7.loss_cls_ce: 1.8916 decode.d7.loss_mask_ce: 0.7672 decode.d7.loss_mask_dice: 1.7323 2023/09/07 23:18:05 - mmengine - INFO - Iter(train) [48750/60000] base_lr: 1.8750e-05 lr: 1.8750e-05 eta: 3:05:01 time: 0.9878 data_time: 0.0226 memory: 29150 grad_norm: 18.1873 loss: 8.6894 decode.loss_cls_ce: 1.7019 decode.loss_mask_ce: 0.8244 decode.loss_mask_dice: 1.8246 decode.d7.loss_cls_ce: 1.7133 decode.d7.loss_mask_ce: 0.8132 decode.d7.loss_mask_dice: 1.8119 2023/09/07 23:18:54 - mmengine - INFO - Iter(train) [48800/60000] base_lr: 1.8667e-05 lr: 1.8667e-05 eta: 3:04:12 time: 0.9878 data_time: 0.0229 memory: 29151 grad_norm: 18.6227 loss: 7.5157 decode.loss_cls_ce: 1.5980 decode.loss_mask_ce: 0.7205 decode.loss_mask_dice: 1.4218 decode.d7.loss_cls_ce: 1.6043 decode.d7.loss_mask_ce: 0.7419 decode.d7.loss_mask_dice: 1.4292 2023/09/07 23:19:44 - mmengine - INFO - Iter(train) [48850/60000] base_lr: 1.8584e-05 lr: 1.8584e-05 eta: 3:03:23 time: 0.9890 data_time: 0.0229 memory: 29149 grad_norm: 17.9345 loss: 6.8727 decode.loss_cls_ce: 1.3751 decode.loss_mask_ce: 0.7499 decode.loss_mask_dice: 1.3133 decode.d7.loss_cls_ce: 1.3649 decode.d7.loss_mask_ce: 0.7511 decode.d7.loss_mask_dice: 1.3186 2023/09/07 23:20:33 - mmengine - INFO - Iter(train) [48900/60000] base_lr: 1.8500e-05 lr: 1.8500e-05 eta: 3:02:33 time: 0.9921 data_time: 0.0223 memory: 29203 grad_norm: 18.5488 loss: 8.8377 decode.loss_cls_ce: 1.7648 decode.loss_mask_ce: 0.7618 decode.loss_mask_dice: 1.8978 decode.d7.loss_cls_ce: 1.7183 decode.d7.loss_mask_ce: 0.7767 decode.d7.loss_mask_dice: 1.9183 2023/09/07 23:21:23 - mmengine - INFO - Iter(train) [48950/60000] base_lr: 1.8417e-05 lr: 1.8417e-05 eta: 3:01:44 time: 0.9884 data_time: 0.0227 memory: 29228 grad_norm: 18.0534 loss: 7.2965 decode.loss_cls_ce: 1.4817 decode.loss_mask_ce: 0.7737 decode.loss_mask_dice: 1.4044 decode.d7.loss_cls_ce: 1.4588 decode.d7.loss_mask_ce: 0.7822 decode.d7.loss_mask_dice: 1.3958 2023/09/07 23:22:12 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 23:22:12 - mmengine - INFO - Iter(train) [49000/60000] base_lr: 1.8334e-05 lr: 1.8334e-05 eta: 3:00:55 time: 0.9902 data_time: 0.0228 memory: 29162 grad_norm: 17.7026 loss: 8.9315 decode.loss_cls_ce: 1.9531 decode.loss_mask_ce: 0.9516 decode.loss_mask_dice: 1.5925 decode.d7.loss_cls_ce: 1.9153 decode.d7.loss_mask_ce: 0.9413 decode.d7.loss_mask_dice: 1.5777 2023/09/07 23:23:02 - mmengine - INFO - Iter(train) [49050/60000] base_lr: 1.8250e-05 lr: 1.8250e-05 eta: 3:00:05 time: 0.9882 data_time: 0.0225 memory: 29258 grad_norm: 18.0712 loss: 6.6620 decode.loss_cls_ce: 1.2767 decode.loss_mask_ce: 0.7643 decode.loss_mask_dice: 1.2797 decode.d7.loss_cls_ce: 1.2914 decode.d7.loss_mask_ce: 0.7764 decode.d7.loss_mask_dice: 1.2735 2023/09/07 23:23:51 - mmengine - INFO - Iter(train) [49100/60000] base_lr: 1.8167e-05 lr: 1.8167e-05 eta: 2:59:16 time: 0.9903 data_time: 0.0231 memory: 29226 grad_norm: 18.1232 loss: 6.5053 decode.loss_cls_ce: 1.3030 decode.loss_mask_ce: 0.6032 decode.loss_mask_dice: 1.3200 decode.d7.loss_cls_ce: 1.3350 decode.d7.loss_mask_ce: 0.6122 decode.d7.loss_mask_dice: 1.3319 2023/09/07 23:24:41 - mmengine - INFO - Iter(train) [49150/60000] base_lr: 1.8084e-05 lr: 1.8084e-05 eta: 2:58:27 time: 0.9893 data_time: 0.0230 memory: 29181 grad_norm: 23.7575 loss: 9.0164 decode.loss_cls_ce: 1.6798 decode.loss_mask_ce: 0.9769 decode.loss_mask_dice: 1.8414 decode.d7.loss_cls_ce: 1.7066 decode.d7.loss_mask_ce: 0.9716 decode.d7.loss_mask_dice: 1.8401 2023/09/07 23:25:30 - mmengine - INFO - Iter(train) [49200/60000] base_lr: 1.8000e-05 lr: 1.8000e-05 eta: 2:57:37 time: 0.9879 data_time: 0.0226 memory: 29254 grad_norm: 19.6863 loss: 7.8688 decode.loss_cls_ce: 1.6047 decode.loss_mask_ce: 0.8129 decode.loss_mask_dice: 1.5030 decode.d7.loss_cls_ce: 1.6068 decode.d7.loss_mask_ce: 0.8254 decode.d7.loss_mask_dice: 1.5160 2023/09/07 23:26:20 - mmengine - INFO - Iter(train) [49250/60000] base_lr: 1.7917e-05 lr: 1.7917e-05 eta: 2:56:48 time: 0.9916 data_time: 0.0225 memory: 29126 grad_norm: 18.6563 loss: 8.5380 decode.loss_cls_ce: 1.5995 decode.loss_mask_ce: 0.8487 decode.loss_mask_dice: 1.7965 decode.d7.loss_cls_ce: 1.6172 decode.d7.loss_mask_ce: 0.8423 decode.d7.loss_mask_dice: 1.8338 2023/09/07 23:27:09 - mmengine - INFO - Iter(train) [49300/60000] base_lr: 1.7834e-05 lr: 1.7834e-05 eta: 2:55:59 time: 0.9869 data_time: 0.0234 memory: 29165 grad_norm: 18.6375 loss: 8.1294 decode.loss_cls_ce: 1.6237 decode.loss_mask_ce: 0.8121 decode.loss_mask_dice: 1.5996 decode.d7.loss_cls_ce: 1.6921 decode.d7.loss_mask_ce: 0.7972 decode.d7.loss_mask_dice: 1.6047 2023/09/07 23:27:59 - mmengine - INFO - Iter(train) [49350/60000] base_lr: 1.7750e-05 lr: 1.7750e-05 eta: 2:55:10 time: 0.9863 data_time: 0.0227 memory: 29253 grad_norm: 17.1097 loss: 7.6081 decode.loss_cls_ce: 1.4633 decode.loss_mask_ce: 0.9081 decode.loss_mask_dice: 1.4237 decode.d7.loss_cls_ce: 1.4722 decode.d7.loss_mask_ce: 0.9132 decode.d7.loss_mask_dice: 1.4276 2023/09/07 23:28:48 - mmengine - INFO - Iter(train) [49400/60000] base_lr: 1.7667e-05 lr: 1.7667e-05 eta: 2:54:20 time: 0.9913 data_time: 0.0236 memory: 29154 grad_norm: 19.2264 loss: 8.8987 decode.loss_cls_ce: 1.6429 decode.loss_mask_ce: 0.9492 decode.loss_mask_dice: 1.8414 decode.d7.loss_cls_ce: 1.6884 decode.d7.loss_mask_ce: 0.9494 decode.d7.loss_mask_dice: 1.8273 2023/09/07 23:29:38 - mmengine - INFO - Iter(train) [49450/60000] base_lr: 1.7584e-05 lr: 1.7584e-05 eta: 2:53:31 time: 0.9882 data_time: 0.0228 memory: 29204 grad_norm: 18.7142 loss: 7.7510 decode.loss_cls_ce: 1.5808 decode.loss_mask_ce: 0.7896 decode.loss_mask_dice: 1.5105 decode.d7.loss_cls_ce: 1.6145 decode.d7.loss_mask_ce: 0.7522 decode.d7.loss_mask_dice: 1.5034 2023/09/07 23:30:27 - mmengine - INFO - Iter(train) [49500/60000] base_lr: 1.7500e-05 lr: 1.7500e-05 eta: 2:52:42 time: 0.9913 data_time: 0.0221 memory: 29074 grad_norm: 18.0593 loss: 8.3861 decode.loss_cls_ce: 1.7672 decode.loss_mask_ce: 0.8728 decode.loss_mask_dice: 1.5730 decode.d7.loss_cls_ce: 1.7524 decode.d7.loss_mask_ce: 0.8565 decode.d7.loss_mask_dice: 1.5642 2023/09/07 23:31:17 - mmengine - INFO - Iter(train) [49550/60000] base_lr: 1.7417e-05 lr: 1.7417e-05 eta: 2:51:52 time: 0.9874 data_time: 0.0232 memory: 29142 grad_norm: 21.5341 loss: 8.6775 decode.loss_cls_ce: 1.6522 decode.loss_mask_ce: 0.9522 decode.loss_mask_dice: 1.7159 decode.d7.loss_cls_ce: 1.7024 decode.d7.loss_mask_ce: 0.9432 decode.d7.loss_mask_dice: 1.7116 2023/09/07 23:32:06 - mmengine - INFO - Iter(train) [49600/60000] base_lr: 1.7334e-05 lr: 1.7334e-05 eta: 2:51:03 time: 0.9920 data_time: 0.0225 memory: 29245 grad_norm: 17.8288 loss: 7.7863 decode.loss_cls_ce: 1.4974 decode.loss_mask_ce: 0.9489 decode.loss_mask_dice: 1.4321 decode.d7.loss_cls_ce: 1.5375 decode.d7.loss_mask_ce: 0.9373 decode.d7.loss_mask_dice: 1.4331 2023/09/07 23:32:56 - mmengine - INFO - Iter(train) [49650/60000] base_lr: 1.7250e-05 lr: 1.7250e-05 eta: 2:50:14 time: 0.9891 data_time: 0.0228 memory: 29216 grad_norm: 18.7527 loss: 8.9846 decode.loss_cls_ce: 1.7187 decode.loss_mask_ce: 0.8497 decode.loss_mask_dice: 1.8730 decode.d7.loss_cls_ce: 1.7820 decode.d7.loss_mask_ce: 0.8620 decode.d7.loss_mask_dice: 1.8992 2023/09/07 23:33:45 - mmengine - INFO - Iter(train) [49700/60000] base_lr: 1.7167e-05 lr: 1.7167e-05 eta: 2:49:24 time: 0.9893 data_time: 0.0233 memory: 29176 grad_norm: 18.9148 loss: 8.8765 decode.loss_cls_ce: 1.7307 decode.loss_mask_ce: 0.8660 decode.loss_mask_dice: 1.8245 decode.d7.loss_cls_ce: 1.7596 decode.d7.loss_mask_ce: 0.8833 decode.d7.loss_mask_dice: 1.8124 2023/09/07 23:34:35 - mmengine - INFO - Iter(train) [49750/60000] base_lr: 1.7084e-05 lr: 1.7084e-05 eta: 2:48:35 time: 0.9908 data_time: 0.0235 memory: 29118 grad_norm: 22.9162 loss: 7.3727 decode.loss_cls_ce: 1.4286 decode.loss_mask_ce: 0.7594 decode.loss_mask_dice: 1.4880 decode.d7.loss_cls_ce: 1.4594 decode.d7.loss_mask_ce: 0.7589 decode.d7.loss_mask_dice: 1.4785 2023/09/07 23:35:24 - mmengine - INFO - Iter(train) [49800/60000] base_lr: 1.7000e-05 lr: 1.7000e-05 eta: 2:47:46 time: 0.9868 data_time: 0.0230 memory: 29323 grad_norm: 20.0215 loss: 6.9320 decode.loss_cls_ce: 1.3673 decode.loss_mask_ce: 0.7745 decode.loss_mask_dice: 1.3408 decode.d7.loss_cls_ce: 1.3406 decode.d7.loss_mask_ce: 0.7780 decode.d7.loss_mask_dice: 1.3308 2023/09/07 23:36:14 - mmengine - INFO - Iter(train) [49850/60000] base_lr: 1.6917e-05 lr: 1.6917e-05 eta: 2:46:56 time: 0.9893 data_time: 0.0224 memory: 29218 grad_norm: 18.7722 loss: 10.1881 decode.loss_cls_ce: 2.0565 decode.loss_mask_ce: 0.9976 decode.loss_mask_dice: 2.0127 decode.d7.loss_cls_ce: 2.0939 decode.d7.loss_mask_ce: 1.0085 decode.d7.loss_mask_dice: 2.0189 2023/09/07 23:37:03 - mmengine - INFO - Iter(train) [49900/60000] base_lr: 1.6834e-05 lr: 1.6834e-05 eta: 2:46:07 time: 0.9914 data_time: 0.0231 memory: 29244 grad_norm: 17.4595 loss: 6.9899 decode.loss_cls_ce: 1.5397 decode.loss_mask_ce: 0.6347 decode.loss_mask_dice: 1.3146 decode.d7.loss_cls_ce: 1.5427 decode.d7.loss_mask_ce: 0.6371 decode.d7.loss_mask_dice: 1.3211 2023/09/07 23:37:53 - mmengine - INFO - Iter(train) [49950/60000] base_lr: 1.6750e-05 lr: 1.6750e-05 eta: 2:45:18 time: 0.9865 data_time: 0.0230 memory: 29217 grad_norm: 18.1342 loss: 7.1060 decode.loss_cls_ce: 1.5068 decode.loss_mask_ce: 0.6745 decode.loss_mask_dice: 1.3704 decode.d7.loss_cls_ce: 1.5084 decode.d7.loss_mask_ce: 0.6664 decode.d7.loss_mask_dice: 1.3795 2023/09/07 23:38:42 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 23:38:42 - mmengine - INFO - Iter(train) [50000/60000] base_lr: 1.6667e-05 lr: 1.6667e-05 eta: 2:44:28 time: 0.9879 data_time: 0.0222 memory: 29163 grad_norm: 16.8232 loss: 7.8711 decode.loss_cls_ce: 1.6671 decode.loss_mask_ce: 0.7530 decode.loss_mask_dice: 1.5144 decode.d7.loss_cls_ce: 1.6502 decode.d7.loss_mask_ce: 0.7685 decode.d7.loss_mask_dice: 1.5180 2023/09/07 23:38:42 - mmengine - INFO - Saving checkpoint at 50000 iterations 2023/09/07 23:39:39 - mmengine - INFO - Iter(train) [50050/60000] base_lr: 1.6584e-05 lr: 1.6584e-05 eta: 2:43:40 time: 0.9909 data_time: 0.0228 memory: 29183 grad_norm: 18.2297 loss: 8.8285 decode.loss_cls_ce: 1.8136 decode.loss_mask_ce: 0.8560 decode.loss_mask_dice: 1.7494 decode.d7.loss_cls_ce: 1.8111 decode.d7.loss_mask_ce: 0.8585 decode.d7.loss_mask_dice: 1.7399 2023/09/07 23:40:28 - mmengine - INFO - Iter(train) [50100/60000] base_lr: 1.6500e-05 lr: 1.6500e-05 eta: 2:42:51 time: 0.9867 data_time: 0.0231 memory: 29242 grad_norm: 22.8068 loss: 8.0447 decode.loss_cls_ce: 1.6083 decode.loss_mask_ce: 0.7935 decode.loss_mask_dice: 1.6116 decode.d7.loss_cls_ce: 1.6093 decode.d7.loss_mask_ce: 0.7972 decode.d7.loss_mask_dice: 1.6248 2023/09/07 23:41:18 - mmengine - INFO - Iter(train) [50150/60000] base_lr: 1.6417e-05 lr: 1.6417e-05 eta: 2:42:02 time: 0.9891 data_time: 0.0231 memory: 29202 grad_norm: 17.9642 loss: 7.9000 decode.loss_cls_ce: 1.5918 decode.loss_mask_ce: 0.8166 decode.loss_mask_dice: 1.5245 decode.d7.loss_cls_ce: 1.6246 decode.d7.loss_mask_ce: 0.8131 decode.d7.loss_mask_dice: 1.5296 2023/09/07 23:42:07 - mmengine - INFO - Iter(train) [50200/60000] base_lr: 1.6334e-05 lr: 1.6334e-05 eta: 2:41:12 time: 0.9873 data_time: 0.0237 memory: 29129 grad_norm: 18.6219 loss: 7.0188 decode.loss_cls_ce: 1.4288 decode.loss_mask_ce: 0.7523 decode.loss_mask_dice: 1.3101 decode.d7.loss_cls_ce: 1.4632 decode.d7.loss_mask_ce: 0.7582 decode.d7.loss_mask_dice: 1.3063 2023/09/07 23:42:56 - mmengine - INFO - Iter(train) [50250/60000] base_lr: 1.6250e-05 lr: 1.6250e-05 eta: 2:40:23 time: 0.9866 data_time: 0.0229 memory: 29216 grad_norm: 18.2045 loss: 8.2142 decode.loss_cls_ce: 1.6240 decode.loss_mask_ce: 0.8859 decode.loss_mask_dice: 1.6052 decode.d7.loss_cls_ce: 1.6488 decode.d7.loss_mask_ce: 0.8774 decode.d7.loss_mask_dice: 1.5728 2023/09/07 23:43:46 - mmengine - INFO - Iter(train) [50300/60000] base_lr: 1.6167e-05 lr: 1.6167e-05 eta: 2:39:34 time: 0.9867 data_time: 0.0229 memory: 29149 grad_norm: 18.2480 loss: 7.3775 decode.loss_cls_ce: 1.4489 decode.loss_mask_ce: 0.7531 decode.loss_mask_dice: 1.5033 decode.d7.loss_cls_ce: 1.4292 decode.d7.loss_mask_ce: 0.7520 decode.d7.loss_mask_dice: 1.4912 2023/09/07 23:44:35 - mmengine - INFO - Iter(train) [50350/60000] base_lr: 1.6084e-05 lr: 1.6084e-05 eta: 2:38:44 time: 0.9868 data_time: 0.0230 memory: 29382 grad_norm: 19.1921 loss: 9.2327 decode.loss_cls_ce: 1.8317 decode.loss_mask_ce: 0.9296 decode.loss_mask_dice: 1.8196 decode.d7.loss_cls_ce: 1.9155 decode.d7.loss_mask_ce: 0.9086 decode.d7.loss_mask_dice: 1.8279 2023/09/07 23:45:25 - mmengine - INFO - Iter(train) [50400/60000] base_lr: 1.6000e-05 lr: 1.6000e-05 eta: 2:37:55 time: 0.9887 data_time: 0.0230 memory: 29292 grad_norm: 16.5500 loss: 7.1785 decode.loss_cls_ce: 1.4017 decode.loss_mask_ce: 0.8570 decode.loss_mask_dice: 1.3310 decode.d7.loss_cls_ce: 1.4233 decode.d7.loss_mask_ce: 0.8428 decode.d7.loss_mask_dice: 1.3226 2023/09/07 23:46:14 - mmengine - INFO - Iter(train) [50450/60000] base_lr: 1.5917e-05 lr: 1.5917e-05 eta: 2:37:06 time: 0.9892 data_time: 0.0230 memory: 29266 grad_norm: 18.1106 loss: 7.1724 decode.loss_cls_ce: 1.3497 decode.loss_mask_ce: 0.7538 decode.loss_mask_dice: 1.4695 decode.d7.loss_cls_ce: 1.3831 decode.d7.loss_mask_ce: 0.7454 decode.d7.loss_mask_dice: 1.4709 2023/09/07 23:47:04 - mmengine - INFO - Iter(train) [50500/60000] base_lr: 1.5834e-05 lr: 1.5834e-05 eta: 2:36:16 time: 0.9910 data_time: 0.0231 memory: 29175 grad_norm: 18.2146 loss: 8.9662 decode.loss_cls_ce: 1.8176 decode.loss_mask_ce: 0.9117 decode.loss_mask_dice: 1.7473 decode.d7.loss_cls_ce: 1.7957 decode.d7.loss_mask_ce: 0.9128 decode.d7.loss_mask_dice: 1.7811 2023/09/07 23:47:53 - mmengine - INFO - Iter(train) [50550/60000] base_lr: 1.5750e-05 lr: 1.5750e-05 eta: 2:35:27 time: 0.9881 data_time: 0.0226 memory: 29141 grad_norm: 19.2310 loss: 7.6476 decode.loss_cls_ce: 1.5631 decode.loss_mask_ce: 0.7765 decode.loss_mask_dice: 1.4754 decode.d7.loss_cls_ce: 1.5789 decode.d7.loss_mask_ce: 0.7780 decode.d7.loss_mask_dice: 1.4757 2023/09/07 23:48:43 - mmengine - INFO - Iter(train) [50600/60000] base_lr: 1.5667e-05 lr: 1.5667e-05 eta: 2:34:38 time: 0.9921 data_time: 0.0229 memory: 29229 grad_norm: 17.3174 loss: 8.2322 decode.loss_cls_ce: 1.6765 decode.loss_mask_ce: 0.8092 decode.loss_mask_dice: 1.6254 decode.d7.loss_cls_ce: 1.6719 decode.d7.loss_mask_ce: 0.8164 decode.d7.loss_mask_dice: 1.6328 2023/09/07 23:49:32 - mmengine - INFO - Iter(train) [50650/60000] base_lr: 1.5584e-05 lr: 1.5584e-05 eta: 2:33:48 time: 0.9940 data_time: 0.0230 memory: 29203 grad_norm: 17.7519 loss: 8.2315 decode.loss_cls_ce: 1.5650 decode.loss_mask_ce: 0.9169 decode.loss_mask_dice: 1.6263 decode.d7.loss_cls_ce: 1.5787 decode.d7.loss_mask_ce: 0.9128 decode.d7.loss_mask_dice: 1.6318 2023/09/07 23:50:22 - mmengine - INFO - Iter(train) [50700/60000] base_lr: 1.5500e-05 lr: 1.5500e-05 eta: 2:32:59 time: 0.9928 data_time: 0.0226 memory: 29228 grad_norm: 20.1585 loss: 8.0899 decode.loss_cls_ce: 1.6301 decode.loss_mask_ce: 0.8619 decode.loss_mask_dice: 1.5426 decode.d7.loss_cls_ce: 1.6341 decode.d7.loss_mask_ce: 0.8704 decode.d7.loss_mask_dice: 1.5509 2023/09/07 23:51:11 - mmengine - INFO - Iter(train) [50750/60000] base_lr: 1.5417e-05 lr: 1.5417e-05 eta: 2:32:10 time: 0.9915 data_time: 0.0227 memory: 29229 grad_norm: 18.1071 loss: 7.9675 decode.loss_cls_ce: 1.5006 decode.loss_mask_ce: 0.8382 decode.loss_mask_dice: 1.6077 decode.d7.loss_cls_ce: 1.5494 decode.d7.loss_mask_ce: 0.8419 decode.d7.loss_mask_dice: 1.6297 2023/09/07 23:52:01 - mmengine - INFO - Iter(train) [50800/60000] base_lr: 1.5334e-05 lr: 1.5334e-05 eta: 2:31:21 time: 0.9894 data_time: 0.0226 memory: 29166 grad_norm: 21.4735 loss: 8.6912 decode.loss_cls_ce: 1.6651 decode.loss_mask_ce: 0.8730 decode.loss_mask_dice: 1.8099 decode.d7.loss_cls_ce: 1.6522 decode.d7.loss_mask_ce: 0.8718 decode.d7.loss_mask_dice: 1.8193 2023/09/07 23:52:50 - mmengine - INFO - Iter(train) [50850/60000] base_lr: 1.5250e-05 lr: 1.5250e-05 eta: 2:30:31 time: 0.9882 data_time: 0.0225 memory: 29162 grad_norm: 18.4267 loss: 8.1709 decode.loss_cls_ce: 1.6811 decode.loss_mask_ce: 0.8264 decode.loss_mask_dice: 1.5669 decode.d7.loss_cls_ce: 1.7051 decode.d7.loss_mask_ce: 0.8328 decode.d7.loss_mask_dice: 1.5586 2023/09/07 23:53:40 - mmengine - INFO - Iter(train) [50900/60000] base_lr: 1.5167e-05 lr: 1.5167e-05 eta: 2:29:42 time: 0.9935 data_time: 0.0228 memory: 29107 grad_norm: 18.4755 loss: 7.8598 decode.loss_cls_ce: 1.5417 decode.loss_mask_ce: 0.8456 decode.loss_mask_dice: 1.5374 decode.d7.loss_cls_ce: 1.5351 decode.d7.loss_mask_ce: 0.8572 decode.d7.loss_mask_dice: 1.5429 2023/09/07 23:54:30 - mmengine - INFO - Iter(train) [50950/60000] base_lr: 1.5084e-05 lr: 1.5084e-05 eta: 2:28:53 time: 0.9942 data_time: 0.0236 memory: 29175 grad_norm: 16.6878 loss: 7.1821 decode.loss_cls_ce: 1.4343 decode.loss_mask_ce: 0.7965 decode.loss_mask_dice: 1.3243 decode.d7.loss_cls_ce: 1.4970 decode.d7.loss_mask_ce: 0.7906 decode.d7.loss_mask_dice: 1.3395 2023/09/07 23:55:19 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/07 23:55:19 - mmengine - INFO - Iter(train) [51000/60000] base_lr: 1.5000e-05 lr: 1.5000e-05 eta: 2:28:03 time: 0.9926 data_time: 0.0226 memory: 29181 grad_norm: 18.6219 loss: 7.5050 decode.loss_cls_ce: 1.4820 decode.loss_mask_ce: 0.7355 decode.loss_mask_dice: 1.5109 decode.d7.loss_cls_ce: 1.5536 decode.d7.loss_mask_ce: 0.7309 decode.d7.loss_mask_dice: 1.4921 2023/09/07 23:56:09 - mmengine - INFO - Iter(train) [51050/60000] base_lr: 1.4917e-05 lr: 1.4917e-05 eta: 2:27:14 time: 0.9914 data_time: 0.0228 memory: 29228 grad_norm: 20.3107 loss: 7.5346 decode.loss_cls_ce: 1.4929 decode.loss_mask_ce: 0.7892 decode.loss_mask_dice: 1.4989 decode.d7.loss_cls_ce: 1.4667 decode.d7.loss_mask_ce: 0.7918 decode.d7.loss_mask_dice: 1.4951 2023/09/07 23:56:59 - mmengine - INFO - Iter(train) [51100/60000] base_lr: 1.4834e-05 lr: 1.4834e-05 eta: 2:26:25 time: 0.9926 data_time: 0.0235 memory: 29357 grad_norm: 17.8022 loss: 9.9244 decode.loss_cls_ce: 2.0801 decode.loss_mask_ce: 1.0087 decode.loss_mask_dice: 1.8801 decode.d7.loss_cls_ce: 2.0688 decode.d7.loss_mask_ce: 0.9982 decode.d7.loss_mask_dice: 1.8884 2023/09/07 23:57:48 - mmengine - INFO - Iter(train) [51150/60000] base_lr: 1.4750e-05 lr: 1.4750e-05 eta: 2:25:35 time: 0.9926 data_time: 0.0236 memory: 29048 grad_norm: 20.4455 loss: 5.9231 decode.loss_cls_ce: 1.1382 decode.loss_mask_ce: 0.6430 decode.loss_mask_dice: 1.1621 decode.d7.loss_cls_ce: 1.1814 decode.d7.loss_mask_ce: 0.6263 decode.d7.loss_mask_dice: 1.1721 2023/09/07 23:58:38 - mmengine - INFO - Iter(train) [51200/60000] base_lr: 1.4667e-05 lr: 1.4667e-05 eta: 2:24:46 time: 0.9920 data_time: 0.0230 memory: 29241 grad_norm: 16.8372 loss: 9.1786 decode.loss_cls_ce: 1.8599 decode.loss_mask_ce: 0.9098 decode.loss_mask_dice: 1.8225 decode.d7.loss_cls_ce: 1.8676 decode.d7.loss_mask_ce: 0.9078 decode.d7.loss_mask_dice: 1.8109 2023/09/07 23:59:27 - mmengine - INFO - Iter(train) [51250/60000] base_lr: 1.4584e-05 lr: 1.4584e-05 eta: 2:23:57 time: 0.9913 data_time: 0.0220 memory: 29174 grad_norm: 20.2303 loss: 8.3267 decode.loss_cls_ce: 1.7198 decode.loss_mask_ce: 0.8616 decode.loss_mask_dice: 1.5694 decode.d7.loss_cls_ce: 1.7375 decode.d7.loss_mask_ce: 0.8746 decode.d7.loss_mask_dice: 1.5637 2023/09/08 00:00:17 - mmengine - INFO - Iter(train) [51300/60000] base_lr: 1.4500e-05 lr: 1.4500e-05 eta: 2:23:07 time: 0.9921 data_time: 0.0231 memory: 29190 grad_norm: 21.5252 loss: 8.0682 decode.loss_cls_ce: 1.6974 decode.loss_mask_ce: 0.8122 decode.loss_mask_dice: 1.5017 decode.d7.loss_cls_ce: 1.6964 decode.d7.loss_mask_ce: 0.8214 decode.d7.loss_mask_dice: 1.5390 2023/09/08 00:01:07 - mmengine - INFO - Iter(train) [51350/60000] base_lr: 1.4417e-05 lr: 1.4417e-05 eta: 2:22:18 time: 0.9909 data_time: 0.0226 memory: 29293 grad_norm: 17.8230 loss: 8.6072 decode.loss_cls_ce: 1.6786 decode.loss_mask_ce: 0.9107 decode.loss_mask_dice: 1.6903 decode.d7.loss_cls_ce: 1.7419 decode.d7.loss_mask_ce: 0.9058 decode.d7.loss_mask_dice: 1.6799 2023/09/08 00:01:56 - mmengine - INFO - Iter(train) [51400/60000] base_lr: 1.4334e-05 lr: 1.4334e-05 eta: 2:21:29 time: 0.9913 data_time: 0.0232 memory: 29148 grad_norm: 17.4264 loss: 8.5386 decode.loss_cls_ce: 1.6498 decode.loss_mask_ce: 0.9203 decode.loss_mask_dice: 1.6844 decode.d7.loss_cls_ce: 1.6527 decode.d7.loss_mask_ce: 0.9303 decode.d7.loss_mask_dice: 1.7010 2023/09/08 00:02:46 - mmengine - INFO - Iter(train) [51450/60000] base_lr: 1.4250e-05 lr: 1.4250e-05 eta: 2:20:39 time: 0.9899 data_time: 0.0225 memory: 29150 grad_norm: 17.9604 loss: 8.6203 decode.loss_cls_ce: 1.5490 decode.loss_mask_ce: 1.0310 decode.loss_mask_dice: 1.7210 decode.d7.loss_cls_ce: 1.5276 decode.d7.loss_mask_ce: 1.0539 decode.d7.loss_mask_dice: 1.7377 2023/09/08 00:03:35 - mmengine - INFO - Iter(train) [51500/60000] base_lr: 1.4167e-05 lr: 1.4167e-05 eta: 2:19:50 time: 0.9904 data_time: 0.0232 memory: 29175 grad_norm: 18.3098 loss: 8.7300 decode.loss_cls_ce: 1.7928 decode.loss_mask_ce: 0.8113 decode.loss_mask_dice: 1.7784 decode.d7.loss_cls_ce: 1.7534 decode.d7.loss_mask_ce: 0.8113 decode.d7.loss_mask_dice: 1.7829 2023/09/08 00:04:25 - mmengine - INFO - Iter(train) [51550/60000] base_lr: 1.4084e-05 lr: 1.4084e-05 eta: 2:19:01 time: 0.9923 data_time: 0.0228 memory: 29112 grad_norm: 19.3688 loss: 8.4952 decode.loss_cls_ce: 1.6557 decode.loss_mask_ce: 0.8789 decode.loss_mask_dice: 1.6925 decode.d7.loss_cls_ce: 1.7043 decode.d7.loss_mask_ce: 0.8754 decode.d7.loss_mask_dice: 1.6885 2023/09/08 00:05:15 - mmengine - INFO - Iter(train) [51600/60000] base_lr: 1.4000e-05 lr: 1.4000e-05 eta: 2:18:11 time: 0.9905 data_time: 0.0229 memory: 29283 grad_norm: 19.1010 loss: 8.5862 decode.loss_cls_ce: 1.5479 decode.loss_mask_ce: 0.8774 decode.loss_mask_dice: 1.8575 decode.d7.loss_cls_ce: 1.5669 decode.d7.loss_mask_ce: 0.8741 decode.d7.loss_mask_dice: 1.8624 2023/09/08 00:06:04 - mmengine - INFO - Iter(train) [51650/60000] base_lr: 1.3917e-05 lr: 1.3917e-05 eta: 2:17:22 time: 0.9937 data_time: 0.0226 memory: 29208 grad_norm: 19.2586 loss: 6.4257 decode.loss_cls_ce: 1.1698 decode.loss_mask_ce: 0.7645 decode.loss_mask_dice: 1.2674 decode.d7.loss_cls_ce: 1.1955 decode.d7.loss_mask_ce: 0.7652 decode.d7.loss_mask_dice: 1.2633 2023/09/08 00:06:54 - mmengine - INFO - Iter(train) [51700/60000] base_lr: 1.3834e-05 lr: 1.3834e-05 eta: 2:16:33 time: 0.9931 data_time: 0.0227 memory: 29203 grad_norm: 22.2452 loss: 9.2790 decode.loss_cls_ce: 1.9474 decode.loss_mask_ce: 0.8948 decode.loss_mask_dice: 1.7879 decode.d7.loss_cls_ce: 1.9732 decode.d7.loss_mask_ce: 0.9065 decode.d7.loss_mask_dice: 1.7691 2023/09/08 00:07:44 - mmengine - INFO - Iter(train) [51750/60000] base_lr: 1.3750e-05 lr: 1.3750e-05 eta: 2:15:44 time: 0.9919 data_time: 0.0238 memory: 29204 grad_norm: 18.0240 loss: 8.0892 decode.loss_cls_ce: 1.6731 decode.loss_mask_ce: 0.8561 decode.loss_mask_dice: 1.4986 decode.d7.loss_cls_ce: 1.6589 decode.d7.loss_mask_ce: 0.8628 decode.d7.loss_mask_dice: 1.5397 2023/09/08 00:08:33 - mmengine - INFO - Iter(train) [51800/60000] base_lr: 1.3667e-05 lr: 1.3667e-05 eta: 2:14:54 time: 0.9922 data_time: 0.0237 memory: 29329 grad_norm: 17.3076 loss: 7.2626 decode.loss_cls_ce: 1.4277 decode.loss_mask_ce: 0.8061 decode.loss_mask_dice: 1.3857 decode.d7.loss_cls_ce: 1.4175 decode.d7.loss_mask_ce: 0.8203 decode.d7.loss_mask_dice: 1.4053 2023/09/08 00:09:23 - mmengine - INFO - Iter(train) [51850/60000] base_lr: 1.3584e-05 lr: 1.3584e-05 eta: 2:14:05 time: 0.9946 data_time: 0.0230 memory: 29200 grad_norm: 17.6013 loss: 8.7752 decode.loss_cls_ce: 1.6784 decode.loss_mask_ce: 0.9396 decode.loss_mask_dice: 1.7623 decode.d7.loss_cls_ce: 1.7063 decode.d7.loss_mask_ce: 0.9333 decode.d7.loss_mask_dice: 1.7552 2023/09/08 00:10:12 - mmengine - INFO - Iter(train) [51900/60000] base_lr: 1.3500e-05 lr: 1.3500e-05 eta: 2:13:16 time: 0.9912 data_time: 0.0229 memory: 29225 grad_norm: 18.4533 loss: 8.5354 decode.loss_cls_ce: 1.7203 decode.loss_mask_ce: 0.9666 decode.loss_mask_dice: 1.5802 decode.d7.loss_cls_ce: 1.7249 decode.d7.loss_mask_ce: 0.9732 decode.d7.loss_mask_dice: 1.5702 2023/09/08 00:11:02 - mmengine - INFO - Iter(train) [51950/60000] base_lr: 1.3417e-05 lr: 1.3417e-05 eta: 2:12:26 time: 0.9904 data_time: 0.0224 memory: 29332 grad_norm: 17.8877 loss: 9.3040 decode.loss_cls_ce: 1.8080 decode.loss_mask_ce: 0.9185 decode.loss_mask_dice: 1.9037 decode.d7.loss_cls_ce: 1.8378 decode.d7.loss_mask_ce: 0.9274 decode.d7.loss_mask_dice: 1.9086 2023/09/08 00:11:52 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 00:11:52 - mmengine - INFO - Iter(train) [52000/60000] base_lr: 1.3334e-05 lr: 1.3334e-05 eta: 2:11:37 time: 0.9923 data_time: 0.0222 memory: 29273 grad_norm: 19.5062 loss: 7.6384 decode.loss_cls_ce: 1.4406 decode.loss_mask_ce: 0.8649 decode.loss_mask_dice: 1.4839 decode.d7.loss_cls_ce: 1.5427 decode.d7.loss_mask_ce: 0.8392 decode.d7.loss_mask_dice: 1.4671 2023/09/08 00:12:41 - mmengine - INFO - Iter(train) [52050/60000] base_lr: 1.3250e-05 lr: 1.3250e-05 eta: 2:10:48 time: 0.9914 data_time: 0.0227 memory: 29276 grad_norm: 16.3501 loss: 6.4158 decode.loss_cls_ce: 1.2417 decode.loss_mask_ce: 0.7831 decode.loss_mask_dice: 1.2085 decode.d7.loss_cls_ce: 1.2271 decode.d7.loss_mask_ce: 0.7419 decode.d7.loss_mask_dice: 1.2135 2023/09/08 00:13:31 - mmengine - INFO - Iter(train) [52100/60000] base_lr: 1.3167e-05 lr: 1.3167e-05 eta: 2:09:58 time: 0.9909 data_time: 0.0231 memory: 29139 grad_norm: 18.6749 loss: 7.5202 decode.loss_cls_ce: 1.4175 decode.loss_mask_ce: 0.8647 decode.loss_mask_dice: 1.4496 decode.d7.loss_cls_ce: 1.4576 decode.d7.loss_mask_ce: 0.8923 decode.d7.loss_mask_dice: 1.4385 2023/09/08 00:14:21 - mmengine - INFO - Iter(train) [52150/60000] base_lr: 1.3084e-05 lr: 1.3084e-05 eta: 2:09:09 time: 0.9913 data_time: 0.0228 memory: 29229 grad_norm: 17.2818 loss: 8.5899 decode.loss_cls_ce: 1.7066 decode.loss_mask_ce: 0.8777 decode.loss_mask_dice: 1.6938 decode.d7.loss_cls_ce: 1.7474 decode.d7.loss_mask_ce: 0.8737 decode.d7.loss_mask_dice: 1.6907 2023/09/08 00:15:10 - mmengine - INFO - Iter(train) [52200/60000] base_lr: 1.3000e-05 lr: 1.3000e-05 eta: 2:08:20 time: 0.9921 data_time: 0.0228 memory: 29178 grad_norm: 17.3464 loss: 7.2058 decode.loss_cls_ce: 1.4422 decode.loss_mask_ce: 0.7301 decode.loss_mask_dice: 1.4346 decode.d7.loss_cls_ce: 1.4456 decode.d7.loss_mask_ce: 0.7252 decode.d7.loss_mask_dice: 1.4281 2023/09/08 00:16:00 - mmengine - INFO - Iter(train) [52250/60000] base_lr: 1.2917e-05 lr: 1.2917e-05 eta: 2:07:30 time: 0.9944 data_time: 0.0227 memory: 29174 grad_norm: 19.0382 loss: 7.3514 decode.loss_cls_ce: 1.4432 decode.loss_mask_ce: 0.7682 decode.loss_mask_dice: 1.4480 decode.d7.loss_cls_ce: 1.4888 decode.d7.loss_mask_ce: 0.7688 decode.d7.loss_mask_dice: 1.4344 2023/09/08 00:16:49 - mmengine - INFO - Iter(train) [52300/60000] base_lr: 1.2834e-05 lr: 1.2834e-05 eta: 2:06:41 time: 0.9923 data_time: 0.0225 memory: 29149 grad_norm: 19.1899 loss: 8.7983 decode.loss_cls_ce: 1.6813 decode.loss_mask_ce: 0.9025 decode.loss_mask_dice: 1.7970 decode.d7.loss_cls_ce: 1.7051 decode.d7.loss_mask_ce: 0.9208 decode.d7.loss_mask_dice: 1.7916 2023/09/08 00:17:39 - mmengine - INFO - Iter(train) [52350/60000] base_lr: 1.2750e-05 lr: 1.2750e-05 eta: 2:05:52 time: 0.9940 data_time: 0.0227 memory: 29319 grad_norm: 18.4813 loss: 7.9947 decode.loss_cls_ce: 1.5827 decode.loss_mask_ce: 0.7716 decode.loss_mask_dice: 1.6511 decode.d7.loss_cls_ce: 1.5618 decode.d7.loss_mask_ce: 0.7847 decode.d7.loss_mask_dice: 1.6427 2023/09/08 00:18:29 - mmengine - INFO - Iter(train) [52400/60000] base_lr: 1.2667e-05 lr: 1.2667e-05 eta: 2:05:02 time: 0.9910 data_time: 0.0225 memory: 29113 grad_norm: 19.4031 loss: 6.9933 decode.loss_cls_ce: 1.5620 decode.loss_mask_ce: 0.7226 decode.loss_mask_dice: 1.2105 decode.d7.loss_cls_ce: 1.5787 decode.d7.loss_mask_ce: 0.6990 decode.d7.loss_mask_dice: 1.2207 2023/09/08 00:19:18 - mmengine - INFO - Iter(train) [52450/60000] base_lr: 1.2584e-05 lr: 1.2584e-05 eta: 2:04:13 time: 0.9951 data_time: 0.0226 memory: 29252 grad_norm: 18.2574 loss: 7.5303 decode.loss_cls_ce: 1.4726 decode.loss_mask_ce: 0.7965 decode.loss_mask_dice: 1.4825 decode.d7.loss_cls_ce: 1.4974 decode.d7.loss_mask_ce: 0.7938 decode.d7.loss_mask_dice: 1.4875 2023/09/08 00:20:08 - mmengine - INFO - Iter(train) [52500/60000] base_lr: 1.2500e-05 lr: 1.2500e-05 eta: 2:03:24 time: 0.9908 data_time: 0.0228 memory: 29357 grad_norm: 17.9033 loss: 7.7601 decode.loss_cls_ce: 1.4771 decode.loss_mask_ce: 0.7195 decode.loss_mask_dice: 1.6637 decode.d7.loss_cls_ce: 1.5274 decode.d7.loss_mask_ce: 0.7094 decode.d7.loss_mask_dice: 1.6630 2023/09/08 00:20:58 - mmengine - INFO - Iter(train) [52550/60000] base_lr: 1.2417e-05 lr: 1.2417e-05 eta: 2:02:34 time: 0.9909 data_time: 0.0228 memory: 29140 grad_norm: 16.2468 loss: 7.0725 decode.loss_cls_ce: 1.3969 decode.loss_mask_ce: 0.7887 decode.loss_mask_dice: 1.3423 decode.d7.loss_cls_ce: 1.3995 decode.d7.loss_mask_ce: 0.8002 decode.d7.loss_mask_dice: 1.3449 2023/09/08 00:21:47 - mmengine - INFO - Iter(train) [52600/60000] base_lr: 1.2334e-05 lr: 1.2334e-05 eta: 2:01:45 time: 0.9908 data_time: 0.0223 memory: 29163 grad_norm: 18.6091 loss: 8.2687 decode.loss_cls_ce: 1.6295 decode.loss_mask_ce: 0.8137 decode.loss_mask_dice: 1.6925 decode.d7.loss_cls_ce: 1.6269 decode.d7.loss_mask_ce: 0.8146 decode.d7.loss_mask_dice: 1.6915 2023/09/08 00:22:37 - mmengine - INFO - Iter(train) [52650/60000] base_lr: 1.2250e-05 lr: 1.2250e-05 eta: 2:00:56 time: 0.9930 data_time: 0.0226 memory: 29205 grad_norm: 17.8248 loss: 8.3240 decode.loss_cls_ce: 1.6222 decode.loss_mask_ce: 0.8279 decode.loss_mask_dice: 1.6718 decode.d7.loss_cls_ce: 1.6649 decode.d7.loss_mask_ce: 0.8308 decode.d7.loss_mask_dice: 1.7064 2023/09/08 00:23:26 - mmengine - INFO - Iter(train) [52700/60000] base_lr: 1.2167e-05 lr: 1.2167e-05 eta: 2:00:06 time: 0.9937 data_time: 0.0229 memory: 29397 grad_norm: 19.1670 loss: 8.5059 decode.loss_cls_ce: 1.4903 decode.loss_mask_ce: 0.8363 decode.loss_mask_dice: 1.9009 decode.d7.loss_cls_ce: 1.5423 decode.d7.loss_mask_ce: 0.8424 decode.d7.loss_mask_dice: 1.8937 2023/09/08 00:24:16 - mmengine - INFO - Iter(train) [52750/60000] base_lr: 1.2084e-05 lr: 1.2084e-05 eta: 1:59:17 time: 0.9944 data_time: 0.0233 memory: 29161 grad_norm: 18.9910 loss: 7.5893 decode.loss_cls_ce: 1.5762 decode.loss_mask_ce: 0.7671 decode.loss_mask_dice: 1.4534 decode.d7.loss_cls_ce: 1.5922 decode.d7.loss_mask_ce: 0.7533 decode.d7.loss_mask_dice: 1.4470 2023/09/08 00:25:06 - mmengine - INFO - Iter(train) [52800/60000] base_lr: 1.2000e-05 lr: 1.2000e-05 eta: 1:58:28 time: 0.9924 data_time: 0.0224 memory: 29168 grad_norm: 20.8686 loss: 6.6322 decode.loss_cls_ce: 1.2837 decode.loss_mask_ce: 0.6973 decode.loss_mask_dice: 1.3448 decode.d7.loss_cls_ce: 1.3286 decode.d7.loss_mask_ce: 0.6827 decode.d7.loss_mask_dice: 1.2951 2023/09/08 00:25:55 - mmengine - INFO - Iter(train) [52850/60000] base_lr: 1.1917e-05 lr: 1.1917e-05 eta: 1:57:38 time: 0.9922 data_time: 0.0225 memory: 29188 grad_norm: 21.0863 loss: 7.2777 decode.loss_cls_ce: 1.5002 decode.loss_mask_ce: 0.7979 decode.loss_mask_dice: 1.3187 decode.d7.loss_cls_ce: 1.5402 decode.d7.loss_mask_ce: 0.7954 decode.d7.loss_mask_dice: 1.3252 2023/09/08 00:26:45 - mmengine - INFO - Iter(train) [52900/60000] base_lr: 1.1834e-05 lr: 1.1834e-05 eta: 1:56:49 time: 0.9929 data_time: 0.0225 memory: 29176 grad_norm: 17.9571 loss: 6.4926 decode.loss_cls_ce: 1.2835 decode.loss_mask_ce: 0.7190 decode.loss_mask_dice: 1.2277 decode.d7.loss_cls_ce: 1.3359 decode.d7.loss_mask_ce: 0.7139 decode.d7.loss_mask_dice: 1.2127 2023/09/08 00:27:35 - mmengine - INFO - Iter(train) [52950/60000] base_lr: 1.1750e-05 lr: 1.1750e-05 eta: 1:56:00 time: 0.9933 data_time: 0.0224 memory: 29242 grad_norm: 16.9066 loss: 6.9653 decode.loss_cls_ce: 1.2379 decode.loss_mask_ce: 0.7713 decode.loss_mask_dice: 1.4590 decode.d7.loss_cls_ce: 1.2658 decode.d7.loss_mask_ce: 0.7761 decode.d7.loss_mask_dice: 1.4552 2023/09/08 00:28:24 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 00:28:24 - mmengine - INFO - Iter(train) [53000/60000] base_lr: 1.1667e-05 lr: 1.1667e-05 eta: 1:55:10 time: 0.9947 data_time: 0.0231 memory: 29193 grad_norm: 18.0329 loss: 7.6254 decode.loss_cls_ce: 1.4804 decode.loss_mask_ce: 0.8038 decode.loss_mask_dice: 1.5478 decode.d7.loss_cls_ce: 1.4484 decode.d7.loss_mask_ce: 0.8025 decode.d7.loss_mask_dice: 1.5426 2023/09/08 00:29:14 - mmengine - INFO - Iter(train) [53050/60000] base_lr: 1.1584e-05 lr: 1.1584e-05 eta: 1:54:21 time: 0.9938 data_time: 0.0226 memory: 29267 grad_norm: 24.0286 loss: 7.5204 decode.loss_cls_ce: 1.4515 decode.loss_mask_ce: 0.8514 decode.loss_mask_dice: 1.4512 decode.d7.loss_cls_ce: 1.4477 decode.d7.loss_mask_ce: 0.8654 decode.d7.loss_mask_dice: 1.4532 2023/09/08 00:30:03 - mmengine - INFO - Iter(train) [53100/60000] base_lr: 1.1500e-05 lr: 1.1500e-05 eta: 1:53:32 time: 0.9930 data_time: 0.0225 memory: 29252 grad_norm: 18.9775 loss: 9.1964 decode.loss_cls_ce: 1.8120 decode.loss_mask_ce: 0.9061 decode.loss_mask_dice: 1.8823 decode.d7.loss_cls_ce: 1.8052 decode.d7.loss_mask_ce: 0.9228 decode.d7.loss_mask_dice: 1.8679 2023/09/08 00:30:53 - mmengine - INFO - Iter(train) [53150/60000] base_lr: 1.1417e-05 lr: 1.1417e-05 eta: 1:52:42 time: 0.9929 data_time: 0.0231 memory: 29231 grad_norm: 22.3178 loss: 8.2577 decode.loss_cls_ce: 1.7652 decode.loss_mask_ce: 0.8388 decode.loss_mask_dice: 1.4955 decode.d7.loss_cls_ce: 1.8037 decode.d7.loss_mask_ce: 0.8433 decode.d7.loss_mask_dice: 1.5113 2023/09/08 00:31:43 - mmengine - INFO - Iter(train) [53200/60000] base_lr: 1.1334e-05 lr: 1.1334e-05 eta: 1:51:53 time: 0.9907 data_time: 0.0225 memory: 29177 grad_norm: 18.4704 loss: 7.5764 decode.loss_cls_ce: 1.6237 decode.loss_mask_ce: 0.7388 decode.loss_mask_dice: 1.4364 decode.d7.loss_cls_ce: 1.6058 decode.d7.loss_mask_ce: 0.7380 decode.d7.loss_mask_dice: 1.4337 2023/09/08 00:32:32 - mmengine - INFO - Iter(train) [53250/60000] base_lr: 1.1250e-05 lr: 1.1250e-05 eta: 1:51:04 time: 0.9907 data_time: 0.0225 memory: 29240 grad_norm: 18.3271 loss: 7.1313 decode.loss_cls_ce: 1.6340 decode.loss_mask_ce: 0.7105 decode.loss_mask_dice: 1.2250 decode.d7.loss_cls_ce: 1.6312 decode.d7.loss_mask_ce: 0.7201 decode.d7.loss_mask_dice: 1.2104 2023/09/08 00:33:22 - mmengine - INFO - Iter(train) [53300/60000] base_lr: 1.1167e-05 lr: 1.1167e-05 eta: 1:50:14 time: 0.9917 data_time: 0.0235 memory: 29254 grad_norm: 19.3822 loss: 6.9150 decode.loss_cls_ce: 1.3360 decode.loss_mask_ce: 0.6595 decode.loss_mask_dice: 1.4482 decode.d7.loss_cls_ce: 1.3420 decode.d7.loss_mask_ce: 0.6634 decode.d7.loss_mask_dice: 1.4661 2023/09/08 00:34:11 - mmengine - INFO - Iter(train) [53350/60000] base_lr: 1.1084e-05 lr: 1.1084e-05 eta: 1:49:25 time: 0.9922 data_time: 0.0223 memory: 29266 grad_norm: 18.9842 loss: 7.6915 decode.loss_cls_ce: 1.4766 decode.loss_mask_ce: 0.7615 decode.loss_mask_dice: 1.6136 decode.d7.loss_cls_ce: 1.4641 decode.d7.loss_mask_ce: 0.7637 decode.d7.loss_mask_dice: 1.6121 2023/09/08 00:35:01 - mmengine - INFO - Iter(train) [53400/60000] base_lr: 1.1000e-05 lr: 1.1000e-05 eta: 1:48:36 time: 0.9919 data_time: 0.0231 memory: 29099 grad_norm: 25.0876 loss: 8.0284 decode.loss_cls_ce: 1.4685 decode.loss_mask_ce: 0.9155 decode.loss_mask_dice: 1.6068 decode.d7.loss_cls_ce: 1.5042 decode.d7.loss_mask_ce: 0.9146 decode.d7.loss_mask_dice: 1.6189 2023/09/08 00:35:51 - mmengine - INFO - Iter(train) [53450/60000] base_lr: 1.0917e-05 lr: 1.0917e-05 eta: 1:47:46 time: 0.9920 data_time: 0.0227 memory: 29212 grad_norm: 19.1597 loss: 7.5064 decode.loss_cls_ce: 1.4979 decode.loss_mask_ce: 0.7695 decode.loss_mask_dice: 1.4886 decode.d7.loss_cls_ce: 1.4719 decode.d7.loss_mask_ce: 0.7746 decode.d7.loss_mask_dice: 1.5040 2023/09/08 00:36:40 - mmengine - INFO - Iter(train) [53500/60000] base_lr: 1.0834e-05 lr: 1.0834e-05 eta: 1:46:57 time: 0.9918 data_time: 0.0218 memory: 29215 grad_norm: 17.5241 loss: 8.4036 decode.loss_cls_ce: 1.7108 decode.loss_mask_ce: 0.8096 decode.loss_mask_dice: 1.6632 decode.d7.loss_cls_ce: 1.7381 decode.d7.loss_mask_ce: 0.8181 decode.d7.loss_mask_dice: 1.6637 2023/09/08 00:37:30 - mmengine - INFO - Iter(train) [53550/60000] base_lr: 1.0750e-05 lr: 1.0750e-05 eta: 1:46:08 time: 0.9919 data_time: 0.0230 memory: 29253 grad_norm: 17.7705 loss: 7.5844 decode.loss_cls_ce: 1.5615 decode.loss_mask_ce: 0.8301 decode.loss_mask_dice: 1.4001 decode.d7.loss_cls_ce: 1.5952 decode.d7.loss_mask_ce: 0.8073 decode.d7.loss_mask_dice: 1.3902 2023/09/08 00:38:20 - mmengine - INFO - Iter(train) [53600/60000] base_lr: 1.0667e-05 lr: 1.0667e-05 eta: 1:45:18 time: 0.9928 data_time: 0.0231 memory: 29232 grad_norm: 19.7895 loss: 8.1496 decode.loss_cls_ce: 1.4141 decode.loss_mask_ce: 0.9238 decode.loss_mask_dice: 1.7155 decode.d7.loss_cls_ce: 1.4132 decode.d7.loss_mask_ce: 0.9516 decode.d7.loss_mask_dice: 1.7313 2023/09/08 00:39:09 - mmengine - INFO - Iter(train) [53650/60000] base_lr: 1.0584e-05 lr: 1.0584e-05 eta: 1:44:29 time: 0.9913 data_time: 0.0229 memory: 29225 grad_norm: 18.3944 loss: 7.6671 decode.loss_cls_ce: 1.6513 decode.loss_mask_ce: 0.7430 decode.loss_mask_dice: 1.4680 decode.d7.loss_cls_ce: 1.6520 decode.d7.loss_mask_ce: 0.7111 decode.d7.loss_mask_dice: 1.4417 2023/09/08 00:39:59 - mmengine - INFO - Iter(train) [53700/60000] base_lr: 1.0500e-05 lr: 1.0500e-05 eta: 1:43:40 time: 0.9913 data_time: 0.0220 memory: 29244 grad_norm: 17.9651 loss: 7.3000 decode.loss_cls_ce: 1.5662 decode.loss_mask_ce: 0.7158 decode.loss_mask_dice: 1.3488 decode.d7.loss_cls_ce: 1.5845 decode.d7.loss_mask_ce: 0.7271 decode.d7.loss_mask_dice: 1.3575 2023/09/08 00:40:49 - mmengine - INFO - Iter(train) [53750/60000] base_lr: 1.0417e-05 lr: 1.0417e-05 eta: 1:42:50 time: 0.9949 data_time: 0.0222 memory: 29166 grad_norm: 19.8748 loss: 7.3572 decode.loss_cls_ce: 1.4496 decode.loss_mask_ce: 0.7634 decode.loss_mask_dice: 1.4536 decode.d7.loss_cls_ce: 1.4889 decode.d7.loss_mask_ce: 0.7364 decode.d7.loss_mask_dice: 1.4653 2023/09/08 00:41:38 - mmengine - INFO - Iter(train) [53800/60000] base_lr: 1.0334e-05 lr: 1.0334e-05 eta: 1:42:01 time: 0.9923 data_time: 0.0228 memory: 29315 grad_norm: 17.2736 loss: 7.9266 decode.loss_cls_ce: 1.5268 decode.loss_mask_ce: 0.8055 decode.loss_mask_dice: 1.6048 decode.d7.loss_cls_ce: 1.5751 decode.d7.loss_mask_ce: 0.8126 decode.d7.loss_mask_dice: 1.6018 2023/09/08 00:42:28 - mmengine - INFO - Iter(train) [53850/60000] base_lr: 1.0250e-05 lr: 1.0250e-05 eta: 1:41:12 time: 0.9911 data_time: 0.0226 memory: 29175 grad_norm: 17.6375 loss: 8.3401 decode.loss_cls_ce: 1.7598 decode.loss_mask_ce: 0.7836 decode.loss_mask_dice: 1.6232 decode.d7.loss_cls_ce: 1.7852 decode.d7.loss_mask_ce: 0.7794 decode.d7.loss_mask_dice: 1.6089 2023/09/08 00:43:17 - mmengine - INFO - Iter(train) [53900/60000] base_lr: 1.0167e-05 lr: 1.0167e-05 eta: 1:40:22 time: 0.9896 data_time: 0.0232 memory: 29591 grad_norm: 17.4061 loss: 8.7343 decode.loss_cls_ce: 1.6409 decode.loss_mask_ce: 0.9988 decode.loss_mask_dice: 1.7070 decode.d7.loss_cls_ce: 1.6843 decode.d7.loss_mask_ce: 0.9995 decode.d7.loss_mask_dice: 1.7037 2023/09/08 00:44:07 - mmengine - INFO - Iter(train) [53950/60000] base_lr: 1.0084e-05 lr: 1.0084e-05 eta: 1:39:33 time: 0.9932 data_time: 0.0230 memory: 29202 grad_norm: 18.9708 loss: 7.6019 decode.loss_cls_ce: 1.4639 decode.loss_mask_ce: 0.7937 decode.loss_mask_dice: 1.5361 decode.d7.loss_cls_ce: 1.4728 decode.d7.loss_mask_ce: 0.7901 decode.d7.loss_mask_dice: 1.5453 2023/09/08 00:44:57 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 00:44:57 - mmengine - INFO - Iter(train) [54000/60000] base_lr: 1.0000e-05 lr: 1.0000e-05 eta: 1:38:44 time: 0.9931 data_time: 0.0225 memory: 29040 grad_norm: 20.7317 loss: 6.9640 decode.loss_cls_ce: 1.4953 decode.loss_mask_ce: 0.6908 decode.loss_mask_dice: 1.3053 decode.d7.loss_cls_ce: 1.4765 decode.d7.loss_mask_ce: 0.6903 decode.d7.loss_mask_dice: 1.3059 2023/09/08 00:45:46 - mmengine - INFO - Iter(train) [54050/60000] base_lr: 9.9168e-06 lr: 9.9168e-06 eta: 1:37:54 time: 0.9900 data_time: 0.0237 memory: 29213 grad_norm: 22.0078 loss: 6.2448 decode.loss_cls_ce: 1.2744 decode.loss_mask_ce: 0.6591 decode.loss_mask_dice: 1.1780 decode.d7.loss_cls_ce: 1.3100 decode.d7.loss_mask_ce: 0.6594 decode.d7.loss_mask_dice: 1.1639 2023/09/08 00:46:36 - mmengine - INFO - Iter(train) [54100/60000] base_lr: 9.8335e-06 lr: 9.8335e-06 eta: 1:37:05 time: 0.9913 data_time: 0.0235 memory: 29155 grad_norm: 17.3821 loss: 8.7330 decode.loss_cls_ce: 1.5176 decode.loss_mask_ce: 0.9647 decode.loss_mask_dice: 1.8469 decode.d7.loss_cls_ce: 1.5949 decode.d7.loss_mask_ce: 0.9657 decode.d7.loss_mask_dice: 1.8432 2023/09/08 00:47:26 - mmengine - INFO - Iter(train) [54150/60000] base_lr: 9.7502e-06 lr: 9.7502e-06 eta: 1:36:16 time: 0.9928 data_time: 0.0226 memory: 29199 grad_norm: 16.7639 loss: 8.0845 decode.loss_cls_ce: 1.6064 decode.loss_mask_ce: 0.7941 decode.loss_mask_dice: 1.6594 decode.d7.loss_cls_ce: 1.5837 decode.d7.loss_mask_ce: 0.7844 decode.d7.loss_mask_dice: 1.6565 2023/09/08 00:48:15 - mmengine - INFO - Iter(train) [54200/60000] base_lr: 9.6668e-06 lr: 9.6668e-06 eta: 1:35:26 time: 0.9916 data_time: 0.0235 memory: 29268 grad_norm: 17.6061 loss: 10.0213 decode.loss_cls_ce: 1.9326 decode.loss_mask_ce: 1.0264 decode.loss_mask_dice: 2.0197 decode.d7.loss_cls_ce: 1.9587 decode.d7.loss_mask_ce: 1.0399 decode.d7.loss_mask_dice: 2.0441 2023/09/08 00:49:05 - mmengine - INFO - Iter(train) [54250/60000] base_lr: 9.5835e-06 lr: 9.5835e-06 eta: 1:34:37 time: 0.9927 data_time: 0.0230 memory: 29227 grad_norm: 18.6100 loss: 7.5425 decode.loss_cls_ce: 1.5503 decode.loss_mask_ce: 0.8044 decode.loss_mask_dice: 1.3931 decode.d7.loss_cls_ce: 1.5607 decode.d7.loss_mask_ce: 0.8229 decode.d7.loss_mask_dice: 1.4112 2023/09/08 00:49:54 - mmengine - INFO - Iter(train) [54300/60000] base_lr: 9.5002e-06 lr: 9.5002e-06 eta: 1:33:48 time: 0.9917 data_time: 0.0220 memory: 29165 grad_norm: 18.5949 loss: 6.0343 decode.loss_cls_ce: 1.2641 decode.loss_mask_ce: 0.6340 decode.loss_mask_dice: 1.1263 decode.d7.loss_cls_ce: 1.2840 decode.d7.loss_mask_ce: 0.6255 decode.d7.loss_mask_dice: 1.1005 2023/09/08 00:50:44 - mmengine - INFO - Iter(train) [54350/60000] base_lr: 9.4168e-06 lr: 9.4168e-06 eta: 1:32:58 time: 0.9902 data_time: 0.0227 memory: 29208 grad_norm: 18.2411 loss: 8.0218 decode.loss_cls_ce: 1.6037 decode.loss_mask_ce: 0.8344 decode.loss_mask_dice: 1.5513 decode.d7.loss_cls_ce: 1.6243 decode.d7.loss_mask_ce: 0.8474 decode.d7.loss_mask_dice: 1.5607 2023/09/08 00:51:34 - mmengine - INFO - Iter(train) [54400/60000] base_lr: 9.3335e-06 lr: 9.3335e-06 eta: 1:32:09 time: 0.9909 data_time: 0.0232 memory: 29241 grad_norm: 18.6747 loss: 7.3431 decode.loss_cls_ce: 1.5038 decode.loss_mask_ce: 0.7154 decode.loss_mask_dice: 1.4499 decode.d7.loss_cls_ce: 1.5406 decode.d7.loss_mask_ce: 0.6921 decode.d7.loss_mask_dice: 1.4414 2023/09/08 00:52:23 - mmengine - INFO - Iter(train) [54450/60000] base_lr: 9.2502e-06 lr: 9.2502e-06 eta: 1:31:20 time: 0.9934 data_time: 0.0232 memory: 29162 grad_norm: 18.7165 loss: 8.2626 decode.loss_cls_ce: 1.5957 decode.loss_mask_ce: 0.8862 decode.loss_mask_dice: 1.6534 decode.d7.loss_cls_ce: 1.6011 decode.d7.loss_mask_ce: 0.8729 decode.d7.loss_mask_dice: 1.6532 2023/09/08 00:53:13 - mmengine - INFO - Iter(train) [54500/60000] base_lr: 9.1668e-06 lr: 9.1668e-06 eta: 1:30:30 time: 0.9905 data_time: 0.0229 memory: 29116 grad_norm: 18.4621 loss: 7.6573 decode.loss_cls_ce: 1.5661 decode.loss_mask_ce: 0.8035 decode.loss_mask_dice: 1.4581 decode.d7.loss_cls_ce: 1.5573 decode.d7.loss_mask_ce: 0.8080 decode.d7.loss_mask_dice: 1.4643 2023/09/08 00:54:03 - mmengine - INFO - Iter(train) [54550/60000] base_lr: 9.0835e-06 lr: 9.0835e-06 eta: 1:29:41 time: 0.9933 data_time: 0.0226 memory: 29204 grad_norm: 19.7640 loss: 8.7224 decode.loss_cls_ce: 1.5801 decode.loss_mask_ce: 0.9252 decode.loss_mask_dice: 1.8515 decode.d7.loss_cls_ce: 1.5648 decode.d7.loss_mask_ce: 0.9290 decode.d7.loss_mask_dice: 1.8718 2023/09/08 00:54:52 - mmengine - INFO - Iter(train) [54600/60000] base_lr: 9.0002e-06 lr: 9.0002e-06 eta: 1:28:52 time: 0.9928 data_time: 0.0229 memory: 29214 grad_norm: 19.6609 loss: 7.3493 decode.loss_cls_ce: 1.5167 decode.loss_mask_ce: 0.7907 decode.loss_mask_dice: 1.3890 decode.d7.loss_cls_ce: 1.4791 decode.d7.loss_mask_ce: 0.7885 decode.d7.loss_mask_dice: 1.3853 2023/09/08 00:55:42 - mmengine - INFO - Iter(train) [54650/60000] base_lr: 8.9168e-06 lr: 8.9168e-06 eta: 1:28:02 time: 0.9932 data_time: 0.0223 memory: 29154 grad_norm: 19.1575 loss: 8.6881 decode.loss_cls_ce: 1.7414 decode.loss_mask_ce: 0.7712 decode.loss_mask_dice: 1.8101 decode.d7.loss_cls_ce: 1.7929 decode.d7.loss_mask_ce: 0.7670 decode.d7.loss_mask_dice: 1.8054 2023/09/08 00:56:32 - mmengine - INFO - Iter(train) [54700/60000] base_lr: 8.8335e-06 lr: 8.8335e-06 eta: 1:27:13 time: 0.9918 data_time: 0.0223 memory: 29344 grad_norm: 17.1811 loss: 8.5745 decode.loss_cls_ce: 1.6550 decode.loss_mask_ce: 0.8179 decode.loss_mask_dice: 1.7996 decode.d7.loss_cls_ce: 1.6816 decode.d7.loss_mask_ce: 0.8217 decode.d7.loss_mask_dice: 1.7988 2023/09/08 00:57:21 - mmengine - INFO - Iter(train) [54750/60000] base_lr: 8.7501e-06 lr: 8.7501e-06 eta: 1:26:23 time: 0.9923 data_time: 0.0222 memory: 29269 grad_norm: 16.8672 loss: 6.1672 decode.loss_cls_ce: 1.3087 decode.loss_mask_ce: 0.6686 decode.loss_mask_dice: 1.0696 decode.d7.loss_cls_ce: 1.3203 decode.d7.loss_mask_ce: 0.6880 decode.d7.loss_mask_dice: 1.1121 2023/09/08 00:58:11 - mmengine - INFO - Iter(train) [54800/60000] base_lr: 8.6668e-06 lr: 8.6668e-06 eta: 1:25:34 time: 0.9922 data_time: 0.0228 memory: 29185 grad_norm: 17.4904 loss: 6.9316 decode.loss_cls_ce: 1.4281 decode.loss_mask_ce: 0.6781 decode.loss_mask_dice: 1.3369 decode.d7.loss_cls_ce: 1.4504 decode.d7.loss_mask_ce: 0.6858 decode.d7.loss_mask_dice: 1.3523 2023/09/08 00:59:00 - mmengine - INFO - Iter(train) [54850/60000] base_lr: 8.5835e-06 lr: 8.5835e-06 eta: 1:24:45 time: 0.9930 data_time: 0.0225 memory: 29188 grad_norm: 18.3319 loss: 8.8425 decode.loss_cls_ce: 1.5847 decode.loss_mask_ce: 0.9820 decode.loss_mask_dice: 1.8439 decode.d7.loss_cls_ce: 1.6000 decode.d7.loss_mask_ce: 0.9937 decode.d7.loss_mask_dice: 1.8382 2023/09/08 00:59:50 - mmengine - INFO - Iter(train) [54900/60000] base_lr: 8.5001e-06 lr: 8.5001e-06 eta: 1:23:55 time: 0.9939 data_time: 0.0226 memory: 29122 grad_norm: 17.2971 loss: 8.6175 decode.loss_cls_ce: 1.7919 decode.loss_mask_ce: 0.8759 decode.loss_mask_dice: 1.6437 decode.d7.loss_cls_ce: 1.7829 decode.d7.loss_mask_ce: 0.8731 decode.d7.loss_mask_dice: 1.6501 2023/09/08 01:00:40 - mmengine - INFO - Iter(train) [54950/60000] base_lr: 8.4168e-06 lr: 8.4168e-06 eta: 1:23:06 time: 0.9936 data_time: 0.0235 memory: 29110 grad_norm: 22.6019 loss: 7.7965 decode.loss_cls_ce: 1.4583 decode.loss_mask_ce: 0.8780 decode.loss_mask_dice: 1.5310 decode.d7.loss_cls_ce: 1.4880 decode.d7.loss_mask_ce: 0.8883 decode.d7.loss_mask_dice: 1.5528 2023/09/08 01:01:29 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 01:01:29 - mmengine - INFO - Iter(train) [55000/60000] base_lr: 8.3335e-06 lr: 8.3335e-06 eta: 1:22:17 time: 0.9927 data_time: 0.0225 memory: 29058 grad_norm: 17.0056 loss: 7.6383 decode.loss_cls_ce: 1.4534 decode.loss_mask_ce: 0.8602 decode.loss_mask_dice: 1.5096 decode.d7.loss_cls_ce: 1.4393 decode.d7.loss_mask_ce: 0.8557 decode.d7.loss_mask_dice: 1.5200 2023/09/08 01:01:43 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:02:37 time: 0.2171 data_time: 0.0019 memory: 10245 2023/09/08 01:01:53 - mmengine - INFO - Iter(val) [100/625] eta: 0:02:02 time: 0.1703 data_time: 0.0020 memory: 10250 2023/09/08 01:02:01 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:40 time: 0.1744 data_time: 0.0020 memory: 9835 2023/09/08 01:02:10 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:27 time: 0.1957 data_time: 0.0019 memory: 10240 2023/09/08 01:02:20 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:15 time: 0.1647 data_time: 0.0018 memory: 9842 2023/09/08 01:02:28 - mmengine - INFO - Iter(val) [300/625] eta: 0:01:04 time: 0.1848 data_time: 0.0019 memory: 10247 2023/09/08 01:02:37 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:53 time: 0.1780 data_time: 0.0020 memory: 2646 2023/09/08 01:02:46 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:43 time: 0.1853 data_time: 0.0019 memory: 10237 2023/09/08 01:02:55 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:33 time: 0.1657 data_time: 0.0020 memory: 4607 2023/09/08 01:03:04 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:23 time: 0.1652 data_time: 0.0020 memory: 10262 2023/09/08 01:03:13 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:14 time: 0.1629 data_time: 0.0020 memory: 10248 2023/09/08 01:03:22 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1617 data_time: 0.0020 memory: 10260 2023/09/08 01:03:30 - mmengine - INFO - per class results: 2023/09/08 01:03:30 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.8 | 92.93 | | bicycle | 66.48 | 81.44 | | car | 64.22 | 86.31 | | motorcycle | 84.32 | 92.3 | | airplane | 81.52 | 91.93 | | bus | 82.65 | 93.79 | | train | 81.52 | 95.62 | | truck | 63.85 | 76.14 | | boat | 62.21 | 87.47 | | traffic light | 65.57 | 85.44 | | fire hydrant | 81.39 | 89.59 | | stop sign | 91.98 | 97.23 | | parking meter | 74.61 | 84.03 | | bench | 56.92 | 74.07 | | bird | 72.92 | 87.15 | | cat | 81.75 | 88.27 | | dog | 70.02 | 76.1 | | horse | 83.38 | 92.77 | | sheep | 86.61 | 93.8 | | cow | 84.01 | 90.25 | | elephant | 91.35 | 95.73 | | bear | 90.87 | 94.35 | | zebra | 90.24 | 95.3 | | giraffe | 84.51 | 91.74 | | backpack | 29.06 | 69.37 | | umbrella | 81.12 | 88.31 | | handbag | 36.45 | 53.38 | | tie | 10.23 | 17.08 | | suitcase | 69.3 | 83.29 | | frisbee | 71.71 | 86.51 | | skis | 39.32 | 63.42 | | snowboard | 64.7 | 75.47 | | sports ball | 54.48 | 78.42 | | kite | 62.26 | 74.11 | | baseball bat | 46.67 | 69.23 | | baseball glove | 66.09 | 87.65 | | skateboard | 71.08 | 88.41 | | surfboard | 80.43 | 89.74 | | tennis racket | 69.41 | 84.66 | | bottle | 48.32 | 67.95 | | wine glass | 47.83 | 70.75 | | cup | 44.08 | 62.36 | | fork | 40.85 | 56.24 | | knife | 27.4 | 37.06 | | spoon | 40.97 | 55.95 | | bowl | 38.17 | 51.52 | | banana | 64.38 | 90.14 | | apple | 48.13 | 58.07 | | sandwich | 49.34 | 61.97 | | orange | 67.58 | 72.04 | | broccoli | 52.09 | 66.79 | | carrot | 54.23 | 70.87 | | hot dog | 54.07 | 64.25 | | pizza | 68.27 | 79.79 | | donut | 73.91 | 88.49 | | cake | 71.1 | 85.61 | | chair | 47.63 | 72.47 | | couch | 57.41 | 76.62 | | potted plant | 33.2 | 49.58 | | bed | 65.19 | 85.09 | | dining table | 44.65 | 71.28 | | toilet | 78.22 | 93.47 | | tv | 70.86 | 82.47 | | laptop | 73.88 | 89.1 | | mouse | 67.82 | 78.13 | | remote | 59.55 | 71.57 | | keyboard | 61.88 | 72.91 | | cell phone | 68.6 | 89.36 | | microwave | 67.04 | 79.6 | | oven | 55.22 | 79.26 | | toaster | 65.91 | 90.54 | | sink | 48.32 | 81.78 | | refrigerator | 76.93 | 91.49 | | book | 48.43 | 62.01 | | clock | 71.33 | 79.19 | | vase | 53.32 | 83.63 | | scissors | 76.95 | 90.69 | | teddy bear | 78.07 | 87.77 | | hair drier | 42.03 | 56.61 | | toothbrush | 31.27 | 81.23 | | banner | 29.5 | 63.77 | | blanket | 20.56 | 26.62 | | branch | 4.44 | 5.69 | | bridge | 32.9 | 51.41 | | building-other | 51.98 | 70.16 | | bush | 32.33 | 47.97 | | cabinet | 50.61 | 70.87 | | cage | 10.23 | 14.81 | | cardboard | 37.39 | 56.74 | | carpet | 49.78 | 73.95 | | ceiling-other | 62.1 | 78.87 | | ceiling-tile | 26.83 | 28.63 | | cloth | 0.68 | 1.2 | | clothes | 18.6 | 27.68 | | clouds | 47.8 | 65.24 | | counter | 24.24 | 52.13 | | cupboard | 0.0 | 0.01 | | curtain | 63.41 | 79.93 | | desk-stuff | 36.0 | 54.14 | | dirt | 38.91 | 55.86 | | door-stuff | 40.24 | 60.91 | | fence | 34.42 | 66.31 | | floor-marble | 9.33 | 11.78 | | floor-other | 21.59 | 32.1 | | floor-stone | 5.25 | 6.58 | | floor-tile | 55.05 | 64.97 | | floor-wood | 62.81 | 78.51 | | flower | 39.31 | 58.87 | | fog | 11.32 | 12.89 | | food-other | 29.65 | 50.16 | | fruit | 31.6 | 61.35 | | furniture-other | 12.1 | 17.22 | | grass | 67.83 | 80.58 | | gravel | 25.9 | 41.3 | | ground-other | 1.89 | 2.75 | | hill | 13.88 | 22.11 | | house | 25.21 | 30.92 | | leaves | 25.11 | 31.98 | | light | 36.85 | 53.46 | | mat | 4.41 | 9.86 | | metal | 29.94 | 40.85 | | mirror-stuff | 54.91 | 78.86 | | moss | 0.0 | 0.0 | | mountain | 54.46 | 75.1 | | mud | 13.09 | 18.49 | | napkin | 9.93 | 14.34 | | net | 34.58 | 66.25 | | paper | 28.74 | 41.45 | | pavement | 52.02 | 71.58 | | pillow | 7.24 | 11.63 | | plant-other | 19.12 | 33.21 | | plastic | 16.91 | 22.68 | | platform | 24.05 | 36.02 | | playingfield | 70.9 | 92.76 | | railing | 6.79 | 16.57 | | railroad | 57.15 | 76.17 | | river | 41.36 | 63.86 | | road | 66.52 | 79.82 | | rock | 45.29 | 70.53 | | roof | 20.39 | 31.18 | | rug | 28.32 | 36.47 | | salad | 9.95 | 14.63 | | sand | 61.38 | 69.89 | | sea | 85.59 | 91.03 | | shelf | 24.43 | 34.12 | | sky-other | 70.32 | 84.34 | | skyscraper | 36.43 | 53.69 | | snow | 87.37 | 95.27 | | solid-other | 0.0 | 0.0 | | stairs | 24.21 | 55.03 | | stone | 0.01 | 0.02 | | straw | 19.3 | 23.21 | | structural-other | 0.08 | 0.09 | | table | 18.02 | 24.82 | | tent | 7.47 | 11.64 | | textile-other | 7.03 | 8.38 | | towel | 32.32 | 40.24 | | tree | 71.75 | 84.55 | | vegetable | 36.99 | 50.6 | | wall-brick | 41.91 | 52.25 | | wall-concrete | 49.69 | 62.07 | | wall-other | 16.31 | 36.52 | | wall-panel | 0.69 | 0.71 | | wall-stone | 25.38 | 33.84 | | wall-tile | 64.38 | 80.52 | | wall-wood | 35.07 | 49.98 | | water-other | 22.4 | 34.92 | | waterdrops | 0.48 | 0.83 | | window-blind | 50.32 | 64.23 | | window-other | 43.59 | 71.63 | | wood | 22.81 | 32.9 | +------------------+-------+-------+ 2023/09/08 01:03:31 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.6800 mIoU: 46.2300 mAcc: 59.8700 data_time: 0.0032 time: 0.1864 2023/09/08 01:03:38 - mmengine - INFO - The best checkpoint with 46.2300 mIoU at 55000 iter is saved to best_mIoU_iter_55000.pth. 2023/09/08 01:04:34 - mmengine - INFO - Iter(train) [55050/60000] base_lr: 8.2501e-06 lr: 8.2501e-06 eta: 1:21:29 time: 0.9903 data_time: 0.0235 memory: 29198 grad_norm: 17.8173 loss: 7.2960 decode.loss_cls_ce: 1.6224 decode.loss_mask_ce: 0.6647 decode.loss_mask_dice: 1.3448 decode.d7.loss_cls_ce: 1.5989 decode.d7.loss_mask_ce: 0.6731 decode.d7.loss_mask_dice: 1.3921 2023/09/08 01:05:24 - mmengine - INFO - Iter(train) [55100/60000] base_lr: 8.1668e-06 lr: 8.1668e-06 eta: 1:20:40 time: 0.9927 data_time: 0.0231 memory: 29177 grad_norm: 21.2991 loss: 7.7925 decode.loss_cls_ce: 1.6050 decode.loss_mask_ce: 0.7857 decode.loss_mask_dice: 1.4743 decode.d7.loss_cls_ce: 1.6505 decode.d7.loss_mask_ce: 0.7916 decode.d7.loss_mask_dice: 1.4853 2023/09/08 01:06:14 - mmengine - INFO - Iter(train) [55150/60000] base_lr: 8.0835e-06 lr: 8.0835e-06 eta: 1:19:50 time: 0.9903 data_time: 0.0230 memory: 29098 grad_norm: 16.6409 loss: 7.6622 decode.loss_cls_ce: 1.5145 decode.loss_mask_ce: 0.8401 decode.loss_mask_dice: 1.4784 decode.d7.loss_cls_ce: 1.5165 decode.d7.loss_mask_ce: 0.8430 decode.d7.loss_mask_dice: 1.4696 2023/09/08 01:07:03 - mmengine - INFO - Iter(train) [55200/60000] base_lr: 8.0001e-06 lr: 8.0001e-06 eta: 1:19:01 time: 0.9912 data_time: 0.0237 memory: 29276 grad_norm: 17.4806 loss: 7.1613 decode.loss_cls_ce: 1.4099 decode.loss_mask_ce: 0.8309 decode.loss_mask_dice: 1.3124 decode.d7.loss_cls_ce: 1.4459 decode.d7.loss_mask_ce: 0.8353 decode.d7.loss_mask_dice: 1.3269 2023/09/08 01:07:53 - mmengine - INFO - Iter(train) [55250/60000] base_lr: 7.9168e-06 lr: 7.9168e-06 eta: 1:18:12 time: 0.9930 data_time: 0.0231 memory: 29186 grad_norm: 17.8221 loss: 7.5963 decode.loss_cls_ce: 1.4522 decode.loss_mask_ce: 0.8084 decode.loss_mask_dice: 1.5102 decode.d7.loss_cls_ce: 1.5048 decode.d7.loss_mask_ce: 0.8037 decode.d7.loss_mask_dice: 1.5169 2023/09/08 01:08:43 - mmengine - INFO - Iter(train) [55300/60000] base_lr: 7.8335e-06 lr: 7.8335e-06 eta: 1:17:22 time: 0.9913 data_time: 0.0237 memory: 29251 grad_norm: 19.8301 loss: 7.4459 decode.loss_cls_ce: 1.4465 decode.loss_mask_ce: 0.7572 decode.loss_mask_dice: 1.4962 decode.d7.loss_cls_ce: 1.4720 decode.d7.loss_mask_ce: 0.7657 decode.d7.loss_mask_dice: 1.5084 2023/09/08 01:09:32 - mmengine - INFO - Iter(train) [55350/60000] base_lr: 7.7501e-06 lr: 7.7501e-06 eta: 1:16:33 time: 0.9895 data_time: 0.0239 memory: 29353 grad_norm: 20.2500 loss: 9.2185 decode.loss_cls_ce: 1.5591 decode.loss_mask_ce: 0.9787 decode.loss_mask_dice: 2.0582 decode.d7.loss_cls_ce: 1.6348 decode.d7.loss_mask_ce: 0.9537 decode.d7.loss_mask_dice: 2.0340 2023/09/08 01:10:22 - mmengine - INFO - Iter(train) [55400/60000] base_lr: 7.6668e-06 lr: 7.6668e-06 eta: 1:15:43 time: 0.9882 data_time: 0.0237 memory: 29086 grad_norm: 17.5922 loss: 6.1269 decode.loss_cls_ce: 1.1173 decode.loss_mask_ce: 0.6675 decode.loss_mask_dice: 1.2610 decode.d7.loss_cls_ce: 1.1337 decode.d7.loss_mask_ce: 0.6740 decode.d7.loss_mask_dice: 1.2734 2023/09/08 01:11:11 - mmengine - INFO - Iter(train) [55450/60000] base_lr: 7.5835e-06 lr: 7.5835e-06 eta: 1:14:54 time: 0.9897 data_time: 0.0236 memory: 29252 grad_norm: 18.8775 loss: 8.5038 decode.loss_cls_ce: 1.5161 decode.loss_mask_ce: 0.9576 decode.loss_mask_dice: 1.7632 decode.d7.loss_cls_ce: 1.5389 decode.d7.loss_mask_ce: 0.9584 decode.d7.loss_mask_dice: 1.7697 2023/09/08 01:12:01 - mmengine - INFO - Iter(train) [55500/60000] base_lr: 7.5001e-06 lr: 7.5001e-06 eta: 1:14:05 time: 0.9915 data_time: 0.0238 memory: 29209 grad_norm: 18.6389 loss: 6.6709 decode.loss_cls_ce: 1.3347 decode.loss_mask_ce: 0.6978 decode.loss_mask_dice: 1.2988 decode.d7.loss_cls_ce: 1.3367 decode.d7.loss_mask_ce: 0.7029 decode.d7.loss_mask_dice: 1.2999 2023/09/08 01:12:09 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1603 data_time: 0.0019 memory: 2646 2023/09/08 01:12:18 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1663 data_time: 0.0018 memory: 2757 2023/09/08 01:12:26 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1728 data_time: 0.0019 memory: 2646 2023/09/08 01:12:34 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1740 data_time: 0.0020 memory: 2601 2023/09/08 01:12:44 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:04 time: 0.1618 data_time: 0.0020 memory: 4253 2023/09/08 01:12:52 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1706 data_time: 0.0020 memory: 2677 2023/09/08 01:13:00 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1762 data_time: 0.0020 memory: 2646 2023/09/08 01:13:09 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1724 data_time: 0.0022 memory: 2646 2023/09/08 01:13:18 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1644 data_time: 0.0020 memory: 4605 2023/09/08 01:13:27 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1683 data_time: 0.0022 memory: 2981 2023/09/08 01:13:35 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1607 data_time: 0.0019 memory: 2705 2023/09/08 01:13:43 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1605 data_time: 0.0020 memory: 2923 2023/09/08 01:13:52 - mmengine - INFO - per class results: 2023/09/08 01:13:52 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.82 | 92.76 | | bicycle | 66.78 | 81.27 | | car | 64.06 | 86.4 | | motorcycle | 84.53 | 92.0 | | airplane | 79.75 | 91.97 | | bus | 82.92 | 93.7 | | train | 81.01 | 95.58 | | truck | 63.54 | 75.56 | | boat | 61.54 | 87.28 | | traffic light | 64.88 | 85.53 | | fire hydrant | 81.14 | 89.08 | | stop sign | 92.08 | 97.25 | | parking meter | 74.51 | 83.51 | | bench | 57.0 | 72.8 | | bird | 73.98 | 87.24 | | cat | 82.15 | 88.98 | | dog | 70.18 | 76.33 | | horse | 83.31 | 92.57 | | sheep | 86.56 | 93.87 | | cow | 84.15 | 90.15 | | elephant | 91.31 | 95.73 | | bear | 91.13 | 94.83 | | zebra | 90.27 | 95.22 | | giraffe | 84.56 | 91.61 | | backpack | 29.27 | 70.2 | | umbrella | 81.22 | 88.34 | | handbag | 37.0 | 55.14 | | tie | 9.98 | 17.44 | | suitcase | 69.15 | 82.77 | | frisbee | 71.92 | 87.38 | | skis | 39.67 | 63.56 | | snowboard | 63.87 | 75.39 | | sports ball | 51.27 | 77.85 | | kite | 61.37 | 73.62 | | baseball bat | 46.37 | 69.69 | | baseball glove | 65.27 | 88.07 | | skateboard | 68.0 | 88.48 | | surfboard | 80.64 | 90.01 | | tennis racket | 69.95 | 84.56 | | bottle | 48.22 | 66.76 | | wine glass | 49.09 | 71.04 | | cup | 43.87 | 62.57 | | fork | 39.36 | 54.97 | | knife | 24.39 | 33.15 | | spoon | 41.17 | 57.49 | | bowl | 38.09 | 51.2 | | banana | 64.4 | 90.67 | | apple | 47.0 | 56.92 | | sandwich | 48.34 | 60.61 | | orange | 66.38 | 70.27 | | broccoli | 53.8 | 67.16 | | carrot | 52.89 | 67.85 | | hot dog | 53.39 | 63.18 | | pizza | 67.05 | 77.73 | | donut | 75.41 | 89.71 | | cake | 71.28 | 84.87 | | chair | 48.02 | 72.54 | | couch | 57.21 | 75.34 | | potted plant | 32.66 | 48.23 | | bed | 66.05 | 85.18 | | dining table | 44.46 | 72.2 | | toilet | 78.96 | 93.16 | | tv | 70.58 | 82.35 | | laptop | 73.52 | 88.61 | | mouse | 69.26 | 78.82 | | remote | 58.96 | 72.08 | | keyboard | 62.37 | 73.61 | | cell phone | 68.27 | 89.58 | | microwave | 67.1 | 79.05 | | oven | 55.42 | 79.98 | | toaster | 66.22 | 90.73 | | sink | 47.87 | 81.98 | | refrigerator | 78.08 | 91.82 | | book | 50.22 | 63.64 | | clock | 71.05 | 79.2 | | vase | 54.21 | 83.05 | | scissors | 77.07 | 91.0 | | teddy bear | 77.95 | 87.46 | | hair drier | 41.92 | 57.23 | | toothbrush | 32.25 | 81.82 | | banner | 29.68 | 64.26 | | blanket | 18.46 | 24.0 | | branch | 4.5 | 5.6 | | bridge | 32.69 | 52.04 | | building-other | 51.58 | 70.53 | | bush | 31.89 | 47.86 | | cabinet | 50.82 | 71.22 | | cage | 10.23 | 14.91 | | cardboard | 37.26 | 56.11 | | carpet | 49.45 | 72.58 | | ceiling-other | 61.94 | 78.65 | | ceiling-tile | 26.93 | 28.63 | | cloth | 0.63 | 1.15 | | clothes | 19.07 | 28.8 | | clouds | 48.16 | 65.06 | | counter | 24.25 | 52.53 | | cupboard | 0.0 | 0.0 | | curtain | 64.44 | 80.38 | | desk-stuff | 36.22 | 54.87 | | dirt | 38.93 | 55.06 | | door-stuff | 40.6 | 61.94 | | fence | 33.98 | 65.07 | | floor-marble | 8.97 | 11.23 | | floor-other | 21.91 | 33.52 | | floor-stone | 2.83 | 3.51 | | floor-tile | 55.9 | 63.9 | | floor-wood | 63.08 | 78.39 | | flower | 39.78 | 60.69 | | fog | 11.61 | 13.34 | | food-other | 29.54 | 48.09 | | fruit | 31.27 | 61.95 | | furniture-other | 12.72 | 18.36 | | grass | 68.09 | 80.85 | | gravel | 25.82 | 38.88 | | ground-other | 4.64 | 7.34 | | hill | 14.47 | 23.24 | | house | 25.72 | 31.63 | | leaves | 25.84 | 33.31 | | light | 37.08 | 52.64 | | mat | 5.41 | 8.31 | | metal | 29.92 | 40.0 | | mirror-stuff | 54.64 | 78.71 | | moss | 0.0 | 0.0 | | mountain | 54.25 | 75.11 | | mud | 15.63 | 18.3 | | napkin | 10.21 | 14.58 | | net | 35.97 | 66.15 | | paper | 29.05 | 41.11 | | pavement | 51.36 | 71.14 | | pillow | 9.71 | 15.49 | | plant-other | 19.2 | 32.5 | | plastic | 17.27 | 22.76 | | platform | 23.58 | 36.61 | | playingfield | 71.05 | 93.59 | | railing | 6.62 | 16.18 | | railroad | 57.79 | 76.63 | | river | 40.78 | 64.38 | | road | 66.11 | 79.95 | | rock | 44.69 | 68.87 | | roof | 20.27 | 29.78 | | rug | 29.01 | 37.08 | | salad | 1.34 | 1.89 | | sand | 60.62 | 68.63 | | sea | 85.47 | 91.01 | | shelf | 24.83 | 34.85 | | sky-other | 70.34 | 84.55 | | skyscraper | 35.37 | 53.8 | | snow | 87.37 | 95.16 | | solid-other | 0.0 | 0.0 | | stairs | 23.25 | 52.58 | | stone | 0.01 | 0.02 | | straw | 19.25 | 22.95 | | structural-other | 0.08 | 0.09 | | table | 19.97 | 28.31 | | tent | 7.52 | 11.75 | | textile-other | 6.51 | 7.83 | | towel | 31.55 | 39.69 | | tree | 71.94 | 84.35 | | vegetable | 39.24 | 51.28 | | wall-brick | 42.03 | 53.47 | | wall-concrete | 47.81 | 58.94 | | wall-other | 16.55 | 38.59 | | wall-panel | 0.6 | 0.61 | | wall-stone | 25.55 | 34.05 | | wall-tile | 65.35 | 82.01 | | wall-wood | 35.04 | 50.23 | | water-other | 22.3 | 33.84 | | waterdrops | 0.33 | 0.56 | | window-blind | 51.9 | 63.15 | | window-other | 43.94 | 71.41 | | wood | 22.56 | 31.98 | +------------------+-------+-------+ 2023/09/08 01:13:52 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.6000 mIoU: 46.1900 mAcc: 59.7400 data_time: 0.0021 time: 0.1708 2023/09/08 01:14:42 - mmengine - INFO - Iter(train) [55550/60000] base_lr: 7.4168e-06 lr: 7.4168e-06 eta: 1:13:16 time: 0.9925 data_time: 0.0233 memory: 29123 grad_norm: 16.4499 loss: 7.2351 decode.loss_cls_ce: 1.4911 decode.loss_mask_ce: 0.6862 decode.loss_mask_dice: 1.4388 decode.d7.loss_cls_ce: 1.4910 decode.d7.loss_mask_ce: 0.6955 decode.d7.loss_mask_dice: 1.4325 2023/09/08 01:15:32 - mmengine - INFO - Iter(train) [55600/60000] base_lr: 7.3335e-06 lr: 7.3335e-06 eta: 1:12:26 time: 0.9918 data_time: 0.0228 memory: 29162 grad_norm: 18.2628 loss: 6.7392 decode.loss_cls_ce: 1.3525 decode.loss_mask_ce: 0.6891 decode.loss_mask_dice: 1.3334 decode.d7.loss_cls_ce: 1.3771 decode.d7.loss_mask_ce: 0.6801 decode.d7.loss_mask_dice: 1.3070 2023/09/08 01:16:21 - mmengine - INFO - Iter(train) [55650/60000] base_lr: 7.2501e-06 lr: 7.2501e-06 eta: 1:11:37 time: 0.9899 data_time: 0.0229 memory: 29276 grad_norm: 15.9839 loss: 7.9638 decode.loss_cls_ce: 1.5620 decode.loss_mask_ce: 0.7617 decode.loss_mask_dice: 1.6527 decode.d7.loss_cls_ce: 1.5813 decode.d7.loss_mask_ce: 0.7568 decode.d7.loss_mask_dice: 1.6493 2023/09/08 01:17:11 - mmengine - INFO - Iter(train) [55700/60000] base_lr: 7.1668e-06 lr: 7.1668e-06 eta: 1:10:48 time: 0.9918 data_time: 0.0236 memory: 29189 grad_norm: 19.0521 loss: 7.2492 decode.loss_cls_ce: 1.3512 decode.loss_mask_ce: 0.7705 decode.loss_mask_dice: 1.5100 decode.d7.loss_cls_ce: 1.3722 decode.d7.loss_mask_ce: 0.7678 decode.d7.loss_mask_dice: 1.4774 2023/09/08 01:18:01 - mmengine - INFO - Iter(train) [55750/60000] base_lr: 7.0835e-06 lr: 7.0835e-06 eta: 1:09:58 time: 0.9943 data_time: 0.0232 memory: 29177 grad_norm: 18.6152 loss: 9.1761 decode.loss_cls_ce: 1.6845 decode.loss_mask_ce: 0.9024 decode.loss_mask_dice: 1.9677 decode.d7.loss_cls_ce: 1.7166 decode.d7.loss_mask_ce: 0.9064 decode.d7.loss_mask_dice: 1.9985 2023/09/08 01:18:50 - mmengine - INFO - Iter(train) [55800/60000] base_lr: 7.0001e-06 lr: 7.0001e-06 eta: 1:09:09 time: 0.9921 data_time: 0.0229 memory: 29230 grad_norm: 17.1135 loss: 8.9925 decode.loss_cls_ce: 1.5853 decode.loss_mask_ce: 0.9556 decode.loss_mask_dice: 1.9238 decode.d7.loss_cls_ce: 1.6528 decode.d7.loss_mask_ce: 0.9302 decode.d7.loss_mask_dice: 1.9449 2023/09/08 01:19:40 - mmengine - INFO - Iter(train) [55850/60000] base_lr: 6.9168e-06 lr: 6.9168e-06 eta: 1:08:19 time: 0.9941 data_time: 0.0237 memory: 29152 grad_norm: 18.6758 loss: 6.5563 decode.loss_cls_ce: 1.2915 decode.loss_mask_ce: 0.6357 decode.loss_mask_dice: 1.3390 decode.d7.loss_cls_ce: 1.3015 decode.d7.loss_mask_ce: 0.6450 decode.d7.loss_mask_dice: 1.3436 2023/09/08 01:20:29 - mmengine - INFO - Iter(train) [55900/60000] base_lr: 6.8334e-06 lr: 6.8334e-06 eta: 1:07:30 time: 0.9912 data_time: 0.0231 memory: 29136 grad_norm: 17.9997 loss: 6.0664 decode.loss_cls_ce: 1.1792 decode.loss_mask_ce: 0.7390 decode.loss_mask_dice: 1.1156 decode.d7.loss_cls_ce: 1.1806 decode.d7.loss_mask_ce: 0.7477 decode.d7.loss_mask_dice: 1.1043 2023/09/08 01:21:19 - mmengine - INFO - Iter(train) [55950/60000] base_lr: 6.7501e-06 lr: 6.7501e-06 eta: 1:06:41 time: 0.9904 data_time: 0.0236 memory: 29290 grad_norm: 19.1090 loss: 8.4296 decode.loss_cls_ce: 1.7380 decode.loss_mask_ce: 0.8768 decode.loss_mask_dice: 1.6067 decode.d7.loss_cls_ce: 1.7474 decode.d7.loss_mask_ce: 0.8785 decode.d7.loss_mask_dice: 1.5822 2023/09/08 01:22:09 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 01:22:09 - mmengine - INFO - Iter(train) [56000/60000] base_lr: 6.6668e-06 lr: 6.6668e-06 eta: 1:05:51 time: 0.9914 data_time: 0.0242 memory: 29257 grad_norm: 18.8264 loss: 7.4219 decode.loss_cls_ce: 1.4519 decode.loss_mask_ce: 0.8381 decode.loss_mask_dice: 1.3959 decode.d7.loss_cls_ce: 1.4829 decode.d7.loss_mask_ce: 0.8437 decode.d7.loss_mask_dice: 1.4094 2023/09/08 01:22:17 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1612 data_time: 0.0019 memory: 2646 2023/09/08 01:22:26 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1670 data_time: 0.0019 memory: 2757 2023/09/08 01:22:34 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1733 data_time: 0.0020 memory: 2646 2023/09/08 01:22:43 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1730 data_time: 0.0020 memory: 2600 2023/09/08 01:22:51 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1637 data_time: 0.0019 memory: 4253 2023/09/08 01:23:00 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1704 data_time: 0.0019 memory: 2676 2023/09/08 01:23:08 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1763 data_time: 0.0020 memory: 2646 2023/09/08 01:23:17 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1727 data_time: 0.0020 memory: 2646 2023/09/08 01:23:25 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1651 data_time: 0.0020 memory: 4605 2023/09/08 01:23:34 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1638 data_time: 0.0023 memory: 2980 2023/09/08 01:23:42 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1609 data_time: 0.0020 memory: 2705 2023/09/08 01:23:51 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1614 data_time: 0.0020 memory: 2921 2023/09/08 01:23:59 - mmengine - INFO - per class results: 2023/09/08 01:23:59 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.78 | 92.84 | | bicycle | 67.46 | 82.04 | | car | 64.09 | 86.15 | | motorcycle | 84.73 | 91.88 | | airplane | 81.46 | 91.67 | | bus | 83.28 | 93.61 | | train | 81.12 | 95.29 | | truck | 63.69 | 75.66 | | boat | 61.42 | 87.25 | | traffic light | 64.37 | 84.91 | | fire hydrant | 81.2 | 89.2 | | stop sign | 92.06 | 97.19 | | parking meter | 74.37 | 83.27 | | bench | 56.68 | 73.71 | | bird | 75.08 | 87.44 | | cat | 82.49 | 89.19 | | dog | 69.85 | 75.68 | | horse | 83.42 | 92.23 | | sheep | 86.6 | 93.65 | | cow | 84.13 | 89.96 | | elephant | 91.14 | 95.56 | | bear | 90.82 | 94.52 | | zebra | 90.23 | 94.96 | | giraffe | 84.48 | 91.36 | | backpack | 29.65 | 67.44 | | umbrella | 80.82 | 88.09 | | handbag | 35.87 | 54.37 | | tie | 10.25 | 16.64 | | suitcase | 69.36 | 82.95 | | frisbee | 72.2 | 86.8 | | skis | 39.28 | 62.13 | | snowboard | 63.29 | 73.71 | | sports ball | 55.54 | 77.87 | | kite | 61.3 | 73.73 | | baseball bat | 46.78 | 69.39 | | baseball glove | 64.95 | 87.7 | | skateboard | 68.12 | 87.95 | | surfboard | 80.8 | 89.73 | | tennis racket | 73.82 | 84.24 | | bottle | 47.96 | 66.31 | | wine glass | 47.53 | 70.66 | | cup | 44.36 | 63.91 | | fork | 41.34 | 58.76 | | knife | 26.18 | 35.49 | | spoon | 40.51 | 56.53 | | bowl | 38.96 | 53.13 | | banana | 62.85 | 88.57 | | apple | 47.02 | 57.83 | | sandwich | 48.72 | 61.84 | | orange | 65.08 | 68.9 | | broccoli | 52.51 | 67.33 | | carrot | 53.65 | 68.95 | | hot dog | 53.48 | 63.35 | | pizza | 69.3 | 81.16 | | donut | 73.56 | 88.06 | | cake | 70.91 | 85.14 | | chair | 47.56 | 71.57 | | couch | 57.1 | 75.91 | | potted plant | 34.04 | 48.87 | | bed | 65.14 | 84.94 | | dining table | 44.72 | 70.62 | | toilet | 79.18 | 93.23 | | tv | 70.97 | 82.63 | | laptop | 73.75 | 88.79 | | mouse | 69.4 | 79.08 | | remote | 57.68 | 70.14 | | keyboard | 62.59 | 73.76 | | cell phone | 68.22 | 89.3 | | microwave | 67.11 | 79.28 | | oven | 55.45 | 79.33 | | toaster | 68.22 | 90.86 | | sink | 48.41 | 83.39 | | refrigerator | 77.63 | 91.92 | | book | 49.93 | 63.76 | | clock | 70.66 | 79.3 | | vase | 53.64 | 82.79 | | scissors | 76.56 | 90.29 | | teddy bear | 78.15 | 87.85 | | hair drier | 41.36 | 56.62 | | toothbrush | 33.18 | 81.28 | | banner | 28.71 | 61.2 | | blanket | 17.89 | 22.93 | | branch | 4.73 | 5.84 | | bridge | 33.07 | 52.36 | | building-other | 52.29 | 70.14 | | bush | 31.56 | 46.92 | | cabinet | 50.78 | 70.37 | | cage | 10.09 | 14.34 | | cardboard | 37.27 | 56.6 | | carpet | 49.57 | 74.07 | | ceiling-other | 62.27 | 79.77 | | ceiling-tile | 26.81 | 28.64 | | cloth | 0.71 | 1.3 | | clothes | 18.54 | 27.04 | | clouds | 48.22 | 66.24 | | counter | 24.63 | 50.76 | | cupboard | 0.01 | 0.02 | | curtain | 63.77 | 79.64 | | desk-stuff | 36.44 | 54.98 | | dirt | 38.98 | 56.0 | | door-stuff | 40.05 | 62.74 | | fence | 34.97 | 67.38 | | floor-marble | 9.16 | 11.5 | | floor-other | 21.32 | 31.86 | | floor-stone | 2.87 | 3.61 | | floor-tile | 55.74 | 65.05 | | floor-wood | 63.8 | 78.77 | | flower | 41.75 | 63.63 | | fog | 11.3 | 12.83 | | food-other | 29.92 | 51.2 | | fruit | 30.62 | 62.37 | | furniture-other | 13.18 | 19.02 | | grass | 67.96 | 80.46 | | gravel | 25.59 | 40.31 | | ground-other | 2.98 | 4.48 | | hill | 13.57 | 20.99 | | house | 24.76 | 29.59 | | leaves | 25.5 | 32.85 | | light | 37.59 | 52.51 | | mat | 4.0 | 8.75 | | metal | 30.25 | 41.65 | | mirror-stuff | 54.59 | 79.0 | | moss | 0.0 | 0.0 | | mountain | 54.69 | 74.2 | | mud | 13.11 | 18.67 | | napkin | 10.18 | 14.68 | | net | 36.12 | 66.68 | | paper | 28.76 | 41.63 | | pavement | 50.95 | 71.85 | | pillow | 8.57 | 13.54 | | plant-other | 19.35 | 31.9 | | plastic | 16.5 | 21.98 | | platform | 24.2 | 37.02 | | playingfield | 70.8 | 93.59 | | railing | 6.69 | 17.01 | | railroad | 57.12 | 76.78 | | river | 40.57 | 62.84 | | road | 65.12 | 77.83 | | rock | 45.44 | 70.8 | | roof | 21.36 | 31.67 | | rug | 28.9 | 36.77 | | salad | 9.0 | 12.67 | | sand | 61.66 | 70.16 | | sea | 85.39 | 90.88 | | shelf | 24.61 | 34.78 | | sky-other | 70.7 | 84.74 | | skyscraper | 35.44 | 50.47 | | snow | 88.72 | 95.5 | | solid-other | 0.0 | 0.0 | | stairs | 24.49 | 56.64 | | stone | 0.03 | 0.03 | | straw | 19.35 | 23.27 | | structural-other | 0.07 | 0.08 | | table | 18.7 | 26.08 | | tent | 7.48 | 11.67 | | textile-other | 7.34 | 8.85 | | towel | 31.28 | 38.84 | | tree | 71.91 | 84.97 | | vegetable | 37.84 | 50.48 | | wall-brick | 42.61 | 53.61 | | wall-concrete | 49.62 | 62.27 | | wall-other | 16.76 | 37.19 | | wall-panel | 0.62 | 0.63 | | wall-stone | 24.84 | 33.37 | | wall-tile | 64.37 | 81.05 | | wall-wood | 35.46 | 50.4 | | water-other | 22.65 | 35.19 | | waterdrops | 1.96 | 3.24 | | window-blind | 51.7 | 62.74 | | window-other | 44.27 | 72.45 | | wood | 22.94 | 32.78 | +------------------+-------+-------+ 2023/09/08 01:23:59 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.7700 mIoU: 46.2800 mAcc: 59.8100 data_time: 0.0021 time: 0.1702 2023/09/08 01:24:00 - mmengine - INFO - The previous best checkpoint /home/caoanqi/mmsegmentation/train_l14_60k/best_mIoU_iter_55000.pth is removed 2023/09/08 01:24:07 - mmengine - INFO - The best checkpoint with 46.2800 mIoU at 56000 iter is saved to best_mIoU_iter_56000.pth. 2023/09/08 01:25:03 - mmengine - INFO - Iter(train) [56050/60000] base_lr: 6.5834e-06 lr: 6.5834e-06 eta: 1:05:03 time: 0.9895 data_time: 0.0251 memory: 29114 grad_norm: 17.3767 loss: 7.0252 decode.loss_cls_ce: 1.3650 decode.loss_mask_ce: 0.7739 decode.loss_mask_dice: 1.3571 decode.d7.loss_cls_ce: 1.4091 decode.d7.loss_mask_ce: 0.7649 decode.d7.loss_mask_dice: 1.3553 2023/09/08 01:25:53 - mmengine - INFO - Iter(train) [56100/60000] base_lr: 6.5001e-06 lr: 6.5001e-06 eta: 1:04:14 time: 0.9901 data_time: 0.0231 memory: 29187 grad_norm: 19.2186 loss: 8.0347 decode.loss_cls_ce: 1.6129 decode.loss_mask_ce: 0.7973 decode.loss_mask_dice: 1.5901 decode.d7.loss_cls_ce: 1.6202 decode.d7.loss_mask_ce: 0.8012 decode.d7.loss_mask_dice: 1.6130 2023/09/08 01:26:43 - mmengine - INFO - Iter(train) [56150/60000] base_lr: 6.4168e-06 lr: 6.4168e-06 eta: 1:03:24 time: 0.9919 data_time: 0.0236 memory: 29292 grad_norm: 17.7499 loss: 7.3728 decode.loss_cls_ce: 1.4077 decode.loss_mask_ce: 0.7750 decode.loss_mask_dice: 1.4966 decode.d7.loss_cls_ce: 1.4379 decode.d7.loss_mask_ce: 0.7675 decode.d7.loss_mask_dice: 1.4882 2023/09/08 01:27:32 - mmengine - INFO - Iter(train) [56200/60000] base_lr: 6.3334e-06 lr: 6.3334e-06 eta: 1:02:35 time: 0.9925 data_time: 0.0236 memory: 29329 grad_norm: 18.8804 loss: 7.2105 decode.loss_cls_ce: 1.3937 decode.loss_mask_ce: 0.7539 decode.loss_mask_dice: 1.4392 decode.d7.loss_cls_ce: 1.4055 decode.d7.loss_mask_ce: 0.7599 decode.d7.loss_mask_dice: 1.4583 2023/09/08 01:28:22 - mmengine - INFO - Iter(train) [56250/60000] base_lr: 6.2501e-06 lr: 6.2501e-06 eta: 1:01:46 time: 0.9915 data_time: 0.0233 memory: 29141 grad_norm: 16.7496 loss: 7.7869 decode.loss_cls_ce: 1.6076 decode.loss_mask_ce: 0.7578 decode.loss_mask_dice: 1.5128 decode.d7.loss_cls_ce: 1.6356 decode.d7.loss_mask_ce: 0.7627 decode.d7.loss_mask_dice: 1.5104 2023/09/08 01:29:11 - mmengine - INFO - Iter(train) [56300/60000] base_lr: 6.1668e-06 lr: 6.1668e-06 eta: 1:00:56 time: 0.9913 data_time: 0.0234 memory: 29186 grad_norm: 18.5670 loss: 6.9364 decode.loss_cls_ce: 1.4199 decode.loss_mask_ce: 0.7088 decode.loss_mask_dice: 1.3277 decode.d7.loss_cls_ce: 1.4535 decode.d7.loss_mask_ce: 0.7095 decode.d7.loss_mask_dice: 1.3170 2023/09/08 01:30:01 - mmengine - INFO - Iter(train) [56350/60000] base_lr: 6.0834e-06 lr: 6.0834e-06 eta: 1:00:07 time: 0.9943 data_time: 0.0240 memory: 29129 grad_norm: 21.1953 loss: 7.1431 decode.loss_cls_ce: 1.2932 decode.loss_mask_ce: 0.9095 decode.loss_mask_dice: 1.3601 decode.d7.loss_cls_ce: 1.3284 decode.d7.loss_mask_ce: 0.9048 decode.d7.loss_mask_dice: 1.3470 2023/09/08 01:30:51 - mmengine - INFO - Iter(train) [56400/60000] base_lr: 6.0001e-06 lr: 6.0001e-06 eta: 0:59:17 time: 0.9924 data_time: 0.0233 memory: 29196 grad_norm: 19.1433 loss: 7.7082 decode.loss_cls_ce: 1.5867 decode.loss_mask_ce: 0.8085 decode.loss_mask_dice: 1.4391 decode.d7.loss_cls_ce: 1.6080 decode.d7.loss_mask_ce: 0.8135 decode.d7.loss_mask_dice: 1.4523 2023/09/08 01:31:40 - mmengine - INFO - Iter(train) [56450/60000] base_lr: 5.9168e-06 lr: 5.9168e-06 eta: 0:58:28 time: 0.9921 data_time: 0.0230 memory: 29326 grad_norm: 19.0393 loss: 7.7544 decode.loss_cls_ce: 1.4584 decode.loss_mask_ce: 0.8538 decode.loss_mask_dice: 1.5587 decode.d7.loss_cls_ce: 1.5111 decode.d7.loss_mask_ce: 0.8463 decode.d7.loss_mask_dice: 1.5261 2023/09/08 01:32:30 - mmengine - INFO - Iter(train) [56500/60000] base_lr: 5.8334e-06 lr: 5.8334e-06 eta: 0:57:39 time: 0.9929 data_time: 0.0256 memory: 29328 grad_norm: 16.9329 loss: 8.7130 decode.loss_cls_ce: 1.6493 decode.loss_mask_ce: 0.9837 decode.loss_mask_dice: 1.7124 decode.d7.loss_cls_ce: 1.6783 decode.d7.loss_mask_ce: 0.9746 decode.d7.loss_mask_dice: 1.7147 2023/09/08 01:32:38 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1613 data_time: 0.0020 memory: 2646 2023/09/08 01:32:47 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1669 data_time: 0.0020 memory: 2757 2023/09/08 01:32:55 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1725 data_time: 0.0019 memory: 2646 2023/09/08 01:33:04 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1720 data_time: 0.0019 memory: 2600 2023/09/08 01:33:12 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1620 data_time: 0.0020 memory: 4253 2023/09/08 01:33:21 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:54 time: 0.1691 data_time: 0.0022 memory: 2676 2023/09/08 01:33:29 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1755 data_time: 0.0019 memory: 2646 2023/09/08 01:33:38 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1719 data_time: 0.0021 memory: 2646 2023/09/08 01:33:47 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1651 data_time: 0.0021 memory: 4605 2023/09/08 01:33:55 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1655 data_time: 0.0021 memory: 2980 2023/09/08 01:34:04 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1610 data_time: 0.0020 memory: 2705 2023/09/08 01:34:12 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1610 data_time: 0.0021 memory: 2921 2023/09/08 01:34:21 - mmengine - INFO - per class results: 2023/09/08 01:34:21 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.78 | 92.45 | | bicycle | 66.45 | 81.09 | | car | 64.13 | 86.96 | | motorcycle | 84.55 | 92.03 | | airplane | 81.56 | 91.99 | | bus | 82.76 | 93.82 | | train | 80.94 | 95.42 | | truck | 64.25 | 76.23 | | boat | 61.76 | 87.32 | | traffic light | 65.4 | 85.67 | | fire hydrant | 81.37 | 89.48 | | stop sign | 91.94 | 97.48 | | parking meter | 73.4 | 83.99 | | bench | 56.79 | 73.22 | | bird | 73.65 | 87.96 | | cat | 82.46 | 88.9 | | dog | 69.69 | 76.0 | | horse | 83.47 | 92.5 | | sheep | 86.49 | 93.84 | | cow | 84.35 | 90.2 | | elephant | 91.32 | 95.74 | | bear | 90.74 | 94.37 | | zebra | 90.03 | 95.23 | | giraffe | 84.56 | 91.82 | | backpack | 29.43 | 69.15 | | umbrella | 81.39 | 88.7 | | handbag | 36.34 | 55.45 | | tie | 10.34 | 17.52 | | suitcase | 68.68 | 83.23 | | frisbee | 67.03 | 87.57 | | skis | 39.33 | 63.2 | | snowboard | 63.96 | 75.41 | | sports ball | 54.7 | 78.91 | | kite | 61.86 | 74.55 | | baseball bat | 47.0 | 69.92 | | baseball glove | 64.88 | 88.34 | | skateboard | 66.03 | 88.67 | | surfboard | 80.61 | 89.82 | | tennis racket | 74.99 | 84.73 | | bottle | 47.04 | 65.24 | | wine glass | 49.03 | 69.56 | | cup | 43.26 | 60.83 | | fork | 38.98 | 53.6 | | knife | 28.44 | 38.05 | | spoon | 39.31 | 54.5 | | bowl | 38.87 | 52.81 | | banana | 63.83 | 90.1 | | apple | 46.62 | 57.34 | | sandwich | 47.78 | 59.5 | | orange | 67.99 | 72.01 | | broccoli | 51.68 | 66.5 | | carrot | 51.26 | 66.68 | | hot dog | 53.95 | 64.08 | | pizza | 67.43 | 78.45 | | donut | 73.65 | 87.77 | | cake | 69.19 | 82.79 | | chair | 47.8 | 71.97 | | couch | 57.43 | 75.36 | | potted plant | 33.23 | 49.35 | | bed | 65.27 | 85.15 | | dining table | 44.62 | 72.65 | | toilet | 78.37 | 93.27 | | tv | 70.63 | 82.77 | | laptop | 73.08 | 87.85 | | mouse | 68.19 | 78.77 | | remote | 58.76 | 71.32 | | keyboard | 62.28 | 74.28 | | cell phone | 68.0 | 89.48 | | microwave | 67.12 | 79.53 | | oven | 54.87 | 79.29 | | toaster | 66.9 | 90.81 | | sink | 47.53 | 82.61 | | refrigerator | 77.1 | 91.73 | | book | 49.41 | 62.32 | | clock | 70.91 | 79.58 | | vase | 53.3 | 83.51 | | scissors | 77.15 | 91.07 | | teddy bear | 78.25 | 87.81 | | hair drier | 42.24 | 57.7 | | toothbrush | 31.96 | 82.02 | | banner | 29.4 | 63.06 | | blanket | 17.66 | 22.92 | | branch | 4.74 | 5.89 | | bridge | 32.64 | 51.65 | | building-other | 51.75 | 70.51 | | bush | 32.1 | 46.66 | | cabinet | 50.54 | 69.83 | | cage | 9.95 | 13.8 | | cardboard | 36.5 | 55.5 | | carpet | 50.26 | 73.83 | | ceiling-other | 61.59 | 78.47 | | ceiling-tile | 26.82 | 28.62 | | cloth | 0.76 | 1.32 | | clothes | 18.57 | 28.25 | | clouds | 47.87 | 66.95 | | counter | 25.44 | 51.75 | | cupboard | 0.0 | 0.0 | | curtain | 63.32 | 78.58 | | desk-stuff | 35.87 | 54.07 | | dirt | 39.07 | 55.42 | | door-stuff | 39.85 | 61.2 | | fence | 35.41 | 67.15 | | floor-marble | 6.03 | 7.53 | | floor-other | 20.98 | 32.14 | | floor-stone | 2.89 | 3.5 | | floor-tile | 56.02 | 64.36 | | floor-wood | 64.57 | 78.8 | | flower | 40.96 | 61.27 | | fog | 11.67 | 13.51 | | food-other | 28.21 | 46.67 | | fruit | 31.13 | 62.78 | | furniture-other | 12.76 | 18.44 | | grass | 67.47 | 79.97 | | gravel | 26.35 | 42.32 | | ground-other | 2.59 | 3.94 | | hill | 14.14 | 21.93 | | house | 25.43 | 30.27 | | leaves | 25.78 | 33.19 | | light | 37.02 | 53.39 | | mat | 3.9 | 8.43 | | metal | 29.88 | 40.51 | | mirror-stuff | 55.87 | 78.7 | | moss | 0.0 | 0.0 | | mountain | 53.91 | 74.35 | | mud | 13.64 | 18.75 | | napkin | 10.3 | 14.72 | | net | 36.26 | 66.3 | | paper | 28.5 | 41.47 | | pavement | 51.2 | 71.64 | | pillow | 10.33 | 16.03 | | plant-other | 19.04 | 32.65 | | plastic | 16.85 | 22.42 | | platform | 24.32 | 36.74 | | playingfield | 69.64 | 93.71 | | railing | 7.07 | 17.19 | | railroad | 57.42 | 75.9 | | river | 41.4 | 63.9 | | road | 66.13 | 79.32 | | rock | 46.44 | 72.4 | | roof | 20.96 | 31.09 | | rug | 28.87 | 36.94 | | salad | 3.45 | 5.02 | | sand | 61.67 | 70.05 | | sea | 85.59 | 91.04 | | shelf | 24.9 | 34.56 | | sky-other | 70.39 | 83.69 | | skyscraper | 31.8 | 46.53 | | snow | 88.58 | 95.46 | | solid-other | 0.0 | 0.0 | | stairs | 24.37 | 56.09 | | stone | 0.01 | 0.02 | | straw | 19.38 | 23.25 | | structural-other | 0.08 | 0.09 | | table | 17.8 | 24.57 | | tent | 7.45 | 11.61 | | textile-other | 7.23 | 8.88 | | towel | 31.33 | 38.84 | | tree | 72.02 | 84.87 | | vegetable | 36.91 | 49.89 | | wall-brick | 42.59 | 53.83 | | wall-concrete | 48.29 | 60.18 | | wall-other | 16.46 | 38.14 | | wall-panel | 0.63 | 0.64 | | wall-stone | 25.42 | 34.09 | | wall-tile | 64.44 | 80.8 | | wall-wood | 34.82 | 50.11 | | water-other | 23.23 | 36.14 | | waterdrops | 2.81 | 4.92 | | window-blind | 50.47 | 62.25 | | window-other | 43.04 | 71.14 | | wood | 22.86 | 32.85 | +------------------+-------+-------+ 2023/09/08 01:34:21 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.5400 mIoU: 46.0900 mAcc: 59.7100 data_time: 0.0021 time: 0.1702 2023/09/08 01:35:11 - mmengine - INFO - Iter(train) [56550/60000] base_lr: 5.7501e-06 lr: 5.7501e-06 eta: 0:56:49 time: 0.9921 data_time: 0.0236 memory: 29201 grad_norm: 17.5514 loss: 6.4806 decode.loss_cls_ce: 1.2464 decode.loss_mask_ce: 0.7474 decode.loss_mask_dice: 1.2306 decode.d7.loss_cls_ce: 1.2839 decode.d7.loss_mask_ce: 0.7491 decode.d7.loss_mask_dice: 1.2233 2023/09/08 01:36:00 - mmengine - INFO - Iter(train) [56600/60000] base_lr: 5.6668e-06 lr: 5.6668e-06 eta: 0:56:00 time: 0.9925 data_time: 0.0238 memory: 29226 grad_norm: 16.8485 loss: 8.7593 decode.loss_cls_ce: 1.7192 decode.loss_mask_ce: 0.8842 decode.loss_mask_dice: 1.7673 decode.d7.loss_cls_ce: 1.6976 decode.d7.loss_mask_ce: 0.9099 decode.d7.loss_mask_dice: 1.7810 2023/09/08 01:36:50 - mmengine - INFO - Iter(train) [56650/60000] base_lr: 5.5834e-06 lr: 5.5834e-06 eta: 0:55:11 time: 0.9920 data_time: 0.0231 memory: 29140 grad_norm: 18.2598 loss: 8.6372 decode.loss_cls_ce: 1.7031 decode.loss_mask_ce: 0.8167 decode.loss_mask_dice: 1.7877 decode.d7.loss_cls_ce: 1.7365 decode.d7.loss_mask_ce: 0.8129 decode.d7.loss_mask_dice: 1.7804 2023/09/08 01:37:40 - mmengine - INFO - Iter(train) [56700/60000] base_lr: 5.5001e-06 lr: 5.5001e-06 eta: 0:54:21 time: 0.9923 data_time: 0.0230 memory: 29174 grad_norm: 20.7910 loss: 5.4548 decode.loss_cls_ce: 1.1311 decode.loss_mask_ce: 0.5565 decode.loss_mask_dice: 1.0269 decode.d7.loss_cls_ce: 1.1165 decode.d7.loss_mask_ce: 0.5615 decode.d7.loss_mask_dice: 1.0624 2023/09/08 01:38:29 - mmengine - INFO - Iter(train) [56750/60000] base_lr: 5.4168e-06 lr: 5.4168e-06 eta: 0:53:32 time: 0.9904 data_time: 0.0233 memory: 29097 grad_norm: 18.9713 loss: 7.6530 decode.loss_cls_ce: 1.6074 decode.loss_mask_ce: 0.7599 decode.loss_mask_dice: 1.4782 decode.d7.loss_cls_ce: 1.5772 decode.d7.loss_mask_ce: 0.7629 decode.d7.loss_mask_dice: 1.4675 2023/09/08 01:39:19 - mmengine - INFO - Iter(train) [56800/60000] base_lr: 5.3334e-06 lr: 5.3334e-06 eta: 0:52:42 time: 0.9941 data_time: 0.0236 memory: 29250 grad_norm: 19.8604 loss: 9.2693 decode.loss_cls_ce: 1.9570 decode.loss_mask_ce: 0.8391 decode.loss_mask_dice: 1.8301 decode.d7.loss_cls_ce: 1.9712 decode.d7.loss_mask_ce: 0.8402 decode.d7.loss_mask_dice: 1.8318 2023/09/08 01:40:09 - mmengine - INFO - Iter(train) [56850/60000] base_lr: 5.2501e-06 lr: 5.2501e-06 eta: 0:51:53 time: 0.9950 data_time: 0.0265 memory: 29175 grad_norm: 17.6141 loss: 6.9042 decode.loss_cls_ce: 1.3484 decode.loss_mask_ce: 0.7218 decode.loss_mask_dice: 1.3701 decode.d7.loss_cls_ce: 1.3752 decode.d7.loss_mask_ce: 0.7235 decode.d7.loss_mask_dice: 1.3652 2023/09/08 01:40:58 - mmengine - INFO - Iter(train) [56900/60000] base_lr: 5.1668e-06 lr: 5.1668e-06 eta: 0:51:04 time: 0.9931 data_time: 0.0232 memory: 29160 grad_norm: 18.0392 loss: 7.6542 decode.loss_cls_ce: 1.3232 decode.loss_mask_ce: 0.9291 decode.loss_mask_dice: 1.5647 decode.d7.loss_cls_ce: 1.3052 decode.d7.loss_mask_ce: 0.9464 decode.d7.loss_mask_dice: 1.5856 2023/09/08 01:41:48 - mmengine - INFO - Iter(train) [56950/60000] base_lr: 5.0834e-06 lr: 5.0834e-06 eta: 0:50:14 time: 0.9929 data_time: 0.0232 memory: 29317 grad_norm: 18.4413 loss: 8.1747 decode.loss_cls_ce: 1.4727 decode.loss_mask_ce: 0.8357 decode.loss_mask_dice: 1.7753 decode.d7.loss_cls_ce: 1.5191 decode.d7.loss_mask_ce: 0.8376 decode.d7.loss_mask_dice: 1.7343 2023/09/08 01:42:38 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 01:42:38 - mmengine - INFO - Iter(train) [57000/60000] base_lr: 5.0001e-06 lr: 5.0001e-06 eta: 0:49:25 time: 0.9924 data_time: 0.0242 memory: 29182 grad_norm: 18.9923 loss: 8.4718 decode.loss_cls_ce: 1.6352 decode.loss_mask_ce: 0.8941 decode.loss_mask_dice: 1.6875 decode.d7.loss_cls_ce: 1.6729 decode.d7.loss_mask_ce: 0.8830 decode.d7.loss_mask_dice: 1.6990 2023/09/08 01:42:46 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1610 data_time: 0.0020 memory: 2646 2023/09/08 01:42:55 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1673 data_time: 0.0021 memory: 2757 2023/09/08 01:43:03 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1738 data_time: 0.0020 memory: 2646 2023/09/08 01:43:12 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1730 data_time: 0.0019 memory: 2600 2023/09/08 01:43:20 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1625 data_time: 0.0019 memory: 4253 2023/09/08 01:43:29 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1700 data_time: 0.0020 memory: 2676 2023/09/08 01:43:37 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1768 data_time: 0.0020 memory: 2646 2023/09/08 01:43:46 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1712 data_time: 0.0019 memory: 2646 2023/09/08 01:43:55 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1661 data_time: 0.0021 memory: 4605 2023/09/08 01:44:03 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1643 data_time: 0.0021 memory: 2980 2023/09/08 01:44:12 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1608 data_time: 0.0019 memory: 2705 2023/09/08 01:44:20 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1619 data_time: 0.0021 memory: 2921 2023/09/08 01:44:29 - mmengine - INFO - per class results: 2023/09/08 01:44:29 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.74 | 92.56 | | bicycle | 66.82 | 81.37 | | car | 64.37 | 86.9 | | motorcycle | 84.45 | 91.97 | | airplane | 81.5 | 91.92 | | bus | 82.19 | 93.8 | | train | 80.31 | 95.52 | | truck | 64.04 | 76.15 | | boat | 61.95 | 87.22 | | traffic light | 65.14 | 85.1 | | fire hydrant | 81.29 | 89.55 | | stop sign | 91.92 | 97.3 | | parking meter | 73.45 | 83.83 | | bench | 57.92 | 73.99 | | bird | 73.89 | 87.57 | | cat | 80.83 | 86.98 | | dog | 69.2 | 74.73 | | horse | 83.39 | 92.49 | | sheep | 86.59 | 93.78 | | cow | 84.34 | 90.15 | | elephant | 91.32 | 95.62 | | bear | 91.05 | 94.58 | | zebra | 90.88 | 95.22 | | giraffe | 84.54 | 91.81 | | backpack | 28.8 | 67.71 | | umbrella | 81.44 | 88.49 | | handbag | 36.24 | 55.09 | | tie | 10.17 | 16.98 | | suitcase | 68.04 | 83.52 | | frisbee | 70.32 | 88.17 | | skis | 39.13 | 63.53 | | snowboard | 64.64 | 75.8 | | sports ball | 53.7 | 78.84 | | kite | 62.22 | 74.4 | | baseball bat | 46.45 | 69.92 | | baseball glove | 64.97 | 87.98 | | skateboard | 65.18 | 88.47 | | surfboard | 80.62 | 89.86 | | tennis racket | 75.69 | 84.69 | | bottle | 47.34 | 66.11 | | wine glass | 48.08 | 70.48 | | cup | 44.42 | 63.7 | | fork | 41.85 | 58.61 | | knife | 27.69 | 37.73 | | spoon | 39.5 | 55.06 | | bowl | 38.9 | 53.74 | | banana | 64.19 | 89.74 | | apple | 46.44 | 56.3 | | sandwich | 50.56 | 63.03 | | orange | 65.28 | 68.97 | | broccoli | 50.74 | 65.05 | | carrot | 51.24 | 65.25 | | hot dog | 53.66 | 63.48 | | pizza | 67.02 | 78.67 | | donut | 73.48 | 87.46 | | cake | 71.61 | 85.3 | | chair | 48.25 | 72.88 | | couch | 56.24 | 75.76 | | potted plant | 33.03 | 48.91 | | bed | 65.22 | 84.77 | | dining table | 44.74 | 70.7 | | toilet | 78.1 | 93.26 | | tv | 70.24 | 82.8 | | laptop | 72.56 | 87.63 | | mouse | 68.68 | 79.3 | | remote | 53.07 | 70.26 | | keyboard | 62.24 | 74.08 | | cell phone | 69.24 | 89.43 | | microwave | 67.05 | 79.22 | | oven | 51.03 | 76.09 | | toaster | 37.98 | 90.75 | | sink | 47.15 | 83.2 | | refrigerator | 76.64 | 92.38 | | book | 48.7 | 62.73 | | clock | 68.51 | 78.99 | | vase | 52.98 | 83.63 | | scissors | 76.8 | 90.8 | | teddy bear | 77.64 | 86.92 | | hair drier | 46.82 | 54.07 | | toothbrush | 32.56 | 81.63 | | banner | 28.54 | 62.63 | | blanket | 17.9 | 23.49 | | branch | 4.16 | 5.22 | | bridge | 33.5 | 53.33 | | building-other | 51.81 | 69.53 | | bush | 32.08 | 48.15 | | cabinet | 50.28 | 70.31 | | cage | 10.05 | 14.0 | | cardboard | 37.56 | 57.26 | | carpet | 50.8 | 75.28 | | ceiling-other | 60.62 | 77.17 | | ceiling-tile | 26.77 | 28.6 | | cloth | 0.67 | 1.18 | | clothes | 18.63 | 28.79 | | clouds | 47.88 | 67.83 | | counter | 24.08 | 51.13 | | cupboard | 0.0 | 0.0 | | curtain | 63.2 | 80.45 | | desk-stuff | 35.63 | 53.8 | | dirt | 38.74 | 55.49 | | door-stuff | 40.2 | 63.13 | | fence | 35.09 | 67.15 | | floor-marble | 8.98 | 11.27 | | floor-other | 20.9 | 32.22 | | floor-stone | 2.71 | 3.36 | | floor-tile | 55.44 | 64.42 | | floor-wood | 64.26 | 78.76 | | flower | 40.42 | 59.71 | | fog | 11.4 | 13.99 | | food-other | 28.45 | 47.59 | | fruit | 31.43 | 63.76 | | furniture-other | 12.58 | 18.05 | | grass | 67.71 | 80.58 | | gravel | 25.53 | 40.16 | | ground-other | 3.76 | 5.55 | | hill | 14.75 | 23.58 | | house | 25.0 | 29.35 | | leaves | 23.1 | 29.49 | | light | 36.97 | 53.14 | | mat | 4.58 | 10.25 | | metal | 29.4 | 39.22 | | mirror-stuff | 54.39 | 79.63 | | moss | 0.0 | 0.0 | | mountain | 55.01 | 74.86 | | mud | 10.2 | 14.33 | | napkin | 10.74 | 15.48 | | net | 34.7 | 66.56 | | paper | 28.44 | 41.62 | | pavement | 51.87 | 71.21 | | pillow | 7.3 | 11.99 | | plant-other | 18.84 | 32.49 | | plastic | 16.98 | 22.7 | | platform | 24.17 | 36.27 | | playingfield | 69.93 | 93.05 | | railing | 7.43 | 18.68 | | railroad | 58.19 | 76.55 | | river | 39.4 | 60.84 | | road | 66.36 | 80.22 | | rock | 46.53 | 72.07 | | roof | 20.68 | 32.4 | | rug | 29.76 | 36.54 | | salad | 6.27 | 8.98 | | sand | 61.54 | 70.0 | | sea | 85.5 | 90.97 | | shelf | 24.8 | 35.26 | | sky-other | 69.73 | 82.38 | | skyscraper | 32.89 | 49.81 | | snow | 88.71 | 95.24 | | solid-other | 0.0 | 0.0 | | stairs | 24.18 | 56.84 | | stone | 0.23 | 0.27 | | straw | 19.38 | 23.16 | | structural-other | 0.1 | 0.11 | | table | 18.97 | 26.9 | | tent | 7.48 | 11.97 | | textile-other | 6.79 | 8.25 | | towel | 31.49 | 39.05 | | tree | 71.78 | 84.63 | | vegetable | 37.45 | 49.63 | | wall-brick | 43.16 | 54.71 | | wall-concrete | 47.51 | 58.45 | | wall-other | 16.5 | 38.2 | | wall-panel | 0.76 | 0.78 | | wall-stone | 25.65 | 34.62 | | wall-tile | 64.38 | 81.52 | | wall-wood | 35.43 | 50.96 | | water-other | 22.48 | 35.74 | | waterdrops | 2.33 | 4.44 | | window-blind | 48.72 | 62.83 | | window-other | 42.52 | 72.29 | | wood | 23.73 | 33.47 | +------------------+-------+-------+ 2023/09/08 01:44:29 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.4000 mIoU: 45.8400 mAcc: 59.7600 data_time: 0.0021 time: 0.1704 2023/09/08 01:45:19 - mmengine - INFO - Iter(train) [57050/60000] base_lr: 4.9167e-06 lr: 4.9167e-06 eta: 0:48:36 time: 0.9921 data_time: 0.0231 memory: 29173 grad_norm: 16.7064 loss: 8.3407 decode.loss_cls_ce: 1.6708 decode.loss_mask_ce: 0.8034 decode.loss_mask_dice: 1.7018 decode.d7.loss_cls_ce: 1.6586 decode.d7.loss_mask_ce: 0.8135 decode.d7.loss_mask_dice: 1.6926 2023/09/08 01:46:08 - mmengine - INFO - Iter(train) [57100/60000] base_lr: 4.8334e-06 lr: 4.8334e-06 eta: 0:47:46 time: 0.9908 data_time: 0.0234 memory: 29193 grad_norm: 18.3793 loss: 7.8356 decode.loss_cls_ce: 1.5712 decode.loss_mask_ce: 0.7689 decode.loss_mask_dice: 1.6087 decode.d7.loss_cls_ce: 1.5199 decode.d7.loss_mask_ce: 0.7681 decode.d7.loss_mask_dice: 1.5989 2023/09/08 01:46:58 - mmengine - INFO - Iter(train) [57150/60000] base_lr: 4.7501e-06 lr: 4.7501e-06 eta: 0:46:57 time: 0.9909 data_time: 0.0238 memory: 29173 grad_norm: 19.2928 loss: 7.9917 decode.loss_cls_ce: 1.5468 decode.loss_mask_ce: 0.8572 decode.loss_mask_dice: 1.5975 decode.d7.loss_cls_ce: 1.5744 decode.d7.loss_mask_ce: 0.8385 decode.d7.loss_mask_dice: 1.5773 2023/09/08 01:47:47 - mmengine - INFO - Iter(train) [57200/60000] base_lr: 4.6667e-06 lr: 4.6667e-06 eta: 0:46:07 time: 0.9925 data_time: 0.0235 memory: 29232 grad_norm: 19.8185 loss: 7.7549 decode.loss_cls_ce: 1.5946 decode.loss_mask_ce: 0.8910 decode.loss_mask_dice: 1.3828 decode.d7.loss_cls_ce: 1.6313 decode.d7.loss_mask_ce: 0.8716 decode.d7.loss_mask_dice: 1.3837 2023/09/08 01:48:37 - mmengine - INFO - Iter(train) [57250/60000] base_lr: 4.5834e-06 lr: 4.5834e-06 eta: 0:45:18 time: 0.9932 data_time: 0.0231 memory: 29111 grad_norm: 19.0540 loss: 8.0277 decode.loss_cls_ce: 1.7499 decode.loss_mask_ce: 0.7637 decode.loss_mask_dice: 1.5062 decode.d7.loss_cls_ce: 1.7024 decode.d7.loss_mask_ce: 0.7728 decode.d7.loss_mask_dice: 1.5327 2023/09/08 01:49:27 - mmengine - INFO - Iter(train) [57300/60000] base_lr: 4.5001e-06 lr: 4.5001e-06 eta: 0:44:29 time: 0.9916 data_time: 0.0231 memory: 29218 grad_norm: 18.8980 loss: 8.0117 decode.loss_cls_ce: 1.5785 decode.loss_mask_ce: 0.7911 decode.loss_mask_dice: 1.6143 decode.d7.loss_cls_ce: 1.6466 decode.d7.loss_mask_ce: 0.7829 decode.d7.loss_mask_dice: 1.5982 2023/09/08 01:50:16 - mmengine - INFO - Iter(train) [57350/60000] base_lr: 4.4167e-06 lr: 4.4167e-06 eta: 0:43:39 time: 0.9941 data_time: 0.0226 memory: 29154 grad_norm: 16.3988 loss: 7.4577 decode.loss_cls_ce: 1.4719 decode.loss_mask_ce: 0.6832 decode.loss_mask_dice: 1.5654 decode.d7.loss_cls_ce: 1.4888 decode.d7.loss_mask_ce: 0.6805 decode.d7.loss_mask_dice: 1.5679 2023/09/08 01:51:06 - mmengine - INFO - Iter(train) [57400/60000] base_lr: 4.3334e-06 lr: 4.3334e-06 eta: 0:42:50 time: 0.9916 data_time: 0.0232 memory: 29189 grad_norm: 17.0845 loss: 7.1744 decode.loss_cls_ce: 1.3391 decode.loss_mask_ce: 0.7483 decode.loss_mask_dice: 1.4819 decode.d7.loss_cls_ce: 1.3558 decode.d7.loss_mask_ce: 0.7706 decode.d7.loss_mask_dice: 1.4787 2023/09/08 01:51:56 - mmengine - INFO - Iter(train) [57450/60000] base_lr: 4.2501e-06 lr: 4.2501e-06 eta: 0:42:00 time: 0.9932 data_time: 0.0230 memory: 29269 grad_norm: 17.2631 loss: 7.7031 decode.loss_cls_ce: 1.5895 decode.loss_mask_ce: 0.7171 decode.loss_mask_dice: 1.5438 decode.d7.loss_cls_ce: 1.5787 decode.d7.loss_mask_ce: 0.7262 decode.d7.loss_mask_dice: 1.5479 2023/09/08 01:52:46 - mmengine - INFO - Iter(train) [57500/60000] base_lr: 4.1667e-06 lr: 4.1667e-06 eta: 0:41:11 time: 0.9947 data_time: 0.0231 memory: 29123 grad_norm: 18.4686 loss: 9.0765 decode.loss_cls_ce: 1.9327 decode.loss_mask_ce: 0.7375 decode.loss_mask_dice: 1.8748 decode.d7.loss_cls_ce: 1.9180 decode.d7.loss_mask_ce: 0.7402 decode.d7.loss_mask_dice: 1.8734 2023/09/08 01:52:54 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1614 data_time: 0.0020 memory: 2646 2023/09/08 01:53:03 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1668 data_time: 0.0019 memory: 2757 2023/09/08 01:53:11 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1731 data_time: 0.0021 memory: 2646 2023/09/08 01:53:19 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1725 data_time: 0.0019 memory: 2600 2023/09/08 01:53:28 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1614 data_time: 0.0018 memory: 4253 2023/09/08 01:53:36 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:54 time: 0.1698 data_time: 0.0020 memory: 2676 2023/09/08 01:53:45 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1771 data_time: 0.0023 memory: 2646 2023/09/08 01:53:53 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1732 data_time: 0.0020 memory: 2646 2023/09/08 01:54:02 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1647 data_time: 0.0019 memory: 4605 2023/09/08 01:54:11 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1670 data_time: 0.0019 memory: 2980 2023/09/08 01:54:19 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1612 data_time: 0.0020 memory: 2705 2023/09/08 01:54:28 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1612 data_time: 0.0020 memory: 2921 2023/09/08 01:54:36 - mmengine - INFO - per class results: 2023/09/08 01:54:36 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.74 | 92.71 | | bicycle | 66.84 | 81.27 | | car | 63.85 | 86.31 | | motorcycle | 84.53 | 92.11 | | airplane | 82.94 | 91.95 | | bus | 82.62 | 93.78 | | train | 80.99 | 95.46 | | truck | 63.91 | 75.93 | | boat | 62.17 | 87.3 | | traffic light | 65.06 | 85.5 | | fire hydrant | 81.26 | 89.48 | | stop sign | 91.83 | 97.35 | | parking meter | 73.59 | 84.28 | | bench | 56.83 | 73.92 | | bird | 74.73 | 87.81 | | cat | 82.03 | 89.02 | | dog | 69.66 | 75.61 | | horse | 83.4 | 92.57 | | sheep | 86.58 | 93.87 | | cow | 84.77 | 90.23 | | elephant | 91.12 | 95.67 | | bear | 91.27 | 94.67 | | zebra | 90.7 | 95.29 | | giraffe | 84.57 | 91.83 | | backpack | 29.06 | 69.21 | | umbrella | 79.29 | 88.45 | | handbag | 36.54 | 54.41 | | tie | 9.84 | 17.46 | | suitcase | 68.5 | 83.16 | | frisbee | 70.56 | 87.77 | | skis | 38.31 | 64.68 | | snowboard | 64.77 | 76.28 | | sports ball | 54.53 | 79.96 | | kite | 61.9 | 74.3 | | baseball bat | 46.16 | 70.75 | | baseball glove | 64.97 | 87.82 | | skateboard | 66.54 | 88.73 | | surfboard | 80.58 | 90.28 | | tennis racket | 75.78 | 85.66 | | bottle | 46.71 | 65.53 | | wine glass | 48.46 | 70.78 | | cup | 43.69 | 62.03 | | fork | 40.07 | 56.98 | | knife | 28.54 | 38.45 | | spoon | 41.1 | 56.99 | | bowl | 38.64 | 52.72 | | banana | 63.8 | 90.01 | | apple | 47.76 | 59.32 | | sandwich | 48.29 | 61.43 | | orange | 68.06 | 72.86 | | broccoli | 52.17 | 67.92 | | carrot | 53.26 | 69.87 | | hot dog | 52.57 | 62.11 | | pizza | 69.03 | 80.4 | | donut | 75.22 | 89.65 | | cake | 71.43 | 85.37 | | chair | 47.42 | 71.76 | | couch | 56.71 | 75.2 | | potted plant | 33.1 | 49.22 | | bed | 65.18 | 85.06 | | dining table | 44.49 | 71.55 | | toilet | 78.05 | 93.46 | | tv | 70.58 | 82.87 | | laptop | 72.67 | 87.79 | | mouse | 68.56 | 79.42 | | remote | 58.86 | 72.15 | | keyboard | 61.72 | 74.01 | | cell phone | 67.81 | 89.45 | | microwave | 67.1 | 79.5 | | oven | 54.13 | 78.22 | | toaster | 64.51 | 90.87 | | sink | 48.63 | 82.95 | | refrigerator | 76.83 | 91.97 | | book | 49.95 | 63.89 | | clock | 70.09 | 79.46 | | vase | 53.33 | 83.13 | | scissors | 76.93 | 91.25 | | teddy bear | 78.18 | 87.8 | | hair drier | 45.35 | 57.94 | | toothbrush | 32.63 | 82.03 | | banner | 29.53 | 64.84 | | blanket | 16.66 | 21.32 | | branch | 4.91 | 6.14 | | bridge | 33.15 | 51.9 | | building-other | 52.17 | 70.39 | | bush | 31.88 | 48.81 | | cabinet | 50.59 | 70.26 | | cage | 9.44 | 13.2 | | cardboard | 37.1 | 55.47 | | carpet | 49.7 | 73.83 | | ceiling-other | 61.48 | 79.1 | | ceiling-tile | 26.8 | 28.63 | | cloth | 0.75 | 1.33 | | clothes | 18.56 | 28.34 | | clouds | 47.34 | 65.0 | | counter | 24.8 | 51.82 | | cupboard | 0.0 | 0.0 | | curtain | 62.18 | 78.99 | | desk-stuff | 35.84 | 53.78 | | dirt | 39.54 | 56.89 | | door-stuff | 39.27 | 60.53 | | fence | 35.37 | 67.41 | | floor-marble | 9.32 | 11.24 | | floor-other | 20.94 | 32.09 | | floor-stone | 2.84 | 3.51 | | floor-tile | 56.2 | 65.31 | | floor-wood | 64.48 | 78.63 | | flower | 41.16 | 61.63 | | fog | 10.77 | 12.45 | | food-other | 28.67 | 46.67 | | fruit | 31.64 | 62.61 | | furniture-other | 12.41 | 17.65 | | grass | 68.08 | 80.96 | | gravel | 26.41 | 39.98 | | ground-other | 2.19 | 3.28 | | hill | 14.85 | 22.82 | | house | 25.2 | 29.93 | | leaves | 25.28 | 32.62 | | light | 37.29 | 54.14 | | mat | 3.0 | 6.61 | | metal | 29.87 | 40.36 | | mirror-stuff | 55.65 | 78.83 | | moss | 0.0 | 0.0 | | mountain | 55.52 | 73.95 | | mud | 10.69 | 14.88 | | napkin | 9.91 | 13.97 | | net | 36.31 | 66.74 | | paper | 28.49 | 41.49 | | pavement | 51.01 | 70.54 | | pillow | 8.56 | 14.16 | | plant-other | 19.11 | 31.95 | | plastic | 16.51 | 21.71 | | platform | 24.12 | 36.32 | | playingfield | 70.91 | 93.61 | | railing | 6.82 | 16.92 | | railroad | 57.92 | 76.82 | | river | 41.89 | 64.62 | | road | 65.54 | 79.99 | | rock | 45.91 | 70.68 | | roof | 21.38 | 31.09 | | rug | 28.6 | 36.66 | | salad | 8.48 | 11.6 | | sand | 61.91 | 69.83 | | sea | 85.65 | 90.97 | | shelf | 25.2 | 35.4 | | sky-other | 70.7 | 84.65 | | skyscraper | 34.12 | 49.57 | | snow | 88.88 | 95.46 | | solid-other | 0.0 | 0.0 | | stairs | 24.48 | 55.42 | | stone | 0.17 | 0.22 | | straw | 19.3 | 23.07 | | structural-other | 0.09 | 0.1 | | table | 18.3 | 25.79 | | tent | 7.83 | 11.69 | | textile-other | 7.15 | 8.76 | | towel | 30.59 | 38.71 | | tree | 71.89 | 84.53 | | vegetable | 37.28 | 50.36 | | wall-brick | 42.83 | 53.98 | | wall-concrete | 49.62 | 61.85 | | wall-other | 16.91 | 37.92 | | wall-panel | 0.65 | 0.67 | | wall-stone | 25.41 | 33.96 | | wall-tile | 64.93 | 81.83 | | wall-wood | 35.32 | 50.15 | | water-other | 24.59 | 37.7 | | waterdrops | 3.34 | 5.4 | | window-blind | 50.57 | 62.59 | | window-other | 43.47 | 72.22 | | wood | 23.08 | 32.58 | +------------------+-------+-------+ 2023/09/08 01:54:36 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.7200 mIoU: 46.2300 mAcc: 59.9300 data_time: 0.0021 time: 0.1703 2023/09/08 01:55:26 - mmengine - INFO - Iter(train) [57550/60000] base_lr: 4.0834e-06 lr: 4.0834e-06 eta: 0:40:22 time: 0.9940 data_time: 0.0239 memory: 29231 grad_norm: 19.1362 loss: 7.7728 decode.loss_cls_ce: 1.4147 decode.loss_mask_ce: 0.8852 decode.loss_mask_dice: 1.5575 decode.d7.loss_cls_ce: 1.4583 decode.d7.loss_mask_ce: 0.8904 decode.d7.loss_mask_dice: 1.5667 2023/09/08 01:56:16 - mmengine - INFO - Iter(train) [57600/60000] base_lr: 4.0001e-06 lr: 4.0001e-06 eta: 0:39:32 time: 0.9943 data_time: 0.0239 memory: 29135 grad_norm: 18.6583 loss: 8.1344 decode.loss_cls_ce: 1.5229 decode.loss_mask_ce: 0.8770 decode.loss_mask_dice: 1.6498 decode.d7.loss_cls_ce: 1.5212 decode.d7.loss_mask_ce: 0.8774 decode.d7.loss_mask_dice: 1.6861 2023/09/08 01:57:05 - mmengine - INFO - Iter(train) [57650/60000] base_lr: 3.9167e-06 lr: 3.9167e-06 eta: 0:38:43 time: 0.9927 data_time: 0.0236 memory: 29194 grad_norm: 17.5618 loss: 6.9633 decode.loss_cls_ce: 1.4172 decode.loss_mask_ce: 0.7521 decode.loss_mask_dice: 1.3212 decode.d7.loss_cls_ce: 1.4112 decode.d7.loss_mask_ce: 0.7456 decode.d7.loss_mask_dice: 1.3159 2023/09/08 01:57:55 - mmengine - INFO - Iter(train) [57700/60000] base_lr: 3.8334e-06 lr: 3.8334e-06 eta: 0:37:53 time: 0.9926 data_time: 0.0233 memory: 29173 grad_norm: 17.6415 loss: 7.9738 decode.loss_cls_ce: 1.6853 decode.loss_mask_ce: 0.8347 decode.loss_mask_dice: 1.4486 decode.d7.loss_cls_ce: 1.7187 decode.d7.loss_mask_ce: 0.8290 decode.d7.loss_mask_dice: 1.4576 2023/09/08 01:58:45 - mmengine - INFO - Iter(train) [57750/60000] base_lr: 3.7501e-06 lr: 3.7501e-06 eta: 0:37:04 time: 0.9915 data_time: 0.0229 memory: 29212 grad_norm: 18.6589 loss: 7.2501 decode.loss_cls_ce: 1.4071 decode.loss_mask_ce: 0.7237 decode.loss_mask_dice: 1.4703 decode.d7.loss_cls_ce: 1.4652 decode.d7.loss_mask_ce: 0.7205 decode.d7.loss_mask_dice: 1.4633 2023/09/08 01:59:34 - mmengine - INFO - Iter(train) [57800/60000] base_lr: 3.6667e-06 lr: 3.6667e-06 eta: 0:36:15 time: 0.9922 data_time: 0.0239 memory: 29136 grad_norm: 17.8957 loss: 7.4103 decode.loss_cls_ce: 1.5177 decode.loss_mask_ce: 0.8266 decode.loss_mask_dice: 1.3662 decode.d7.loss_cls_ce: 1.5266 decode.d7.loss_mask_ce: 0.8283 decode.d7.loss_mask_dice: 1.3450 2023/09/08 02:00:24 - mmengine - INFO - Iter(train) [57850/60000] base_lr: 3.5834e-06 lr: 3.5834e-06 eta: 0:35:25 time: 0.9935 data_time: 0.0241 memory: 29230 grad_norm: 19.4993 loss: 8.8970 decode.loss_cls_ce: 1.6873 decode.loss_mask_ce: 0.8815 decode.loss_mask_dice: 1.8528 decode.d7.loss_cls_ce: 1.7681 decode.d7.loss_mask_ce: 0.8734 decode.d7.loss_mask_dice: 1.8339 2023/09/08 02:01:13 - mmengine - INFO - Iter(train) [57900/60000] base_lr: 3.5001e-06 lr: 3.5001e-06 eta: 0:34:36 time: 0.9915 data_time: 0.0230 memory: 29151 grad_norm: 18.9897 loss: 9.9974 decode.loss_cls_ce: 1.9027 decode.loss_mask_ce: 0.9798 decode.loss_mask_dice: 2.0938 decode.d7.loss_cls_ce: 1.9094 decode.d7.loss_mask_ce: 0.9845 decode.d7.loss_mask_dice: 2.1273 2023/09/08 02:02:03 - mmengine - INFO - Iter(train) [57950/60000] base_lr: 3.4167e-06 lr: 3.4167e-06 eta: 0:33:46 time: 0.9936 data_time: 0.0242 memory: 29136 grad_norm: 17.4721 loss: 7.3270 decode.loss_cls_ce: 1.6532 decode.loss_mask_ce: 0.7859 decode.loss_mask_dice: 1.2465 decode.d7.loss_cls_ce: 1.6290 decode.d7.loss_mask_ce: 0.7700 decode.d7.loss_mask_dice: 1.2424 2023/09/08 02:02:53 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 02:02:53 - mmengine - INFO - Iter(train) [58000/60000] base_lr: 3.3334e-06 lr: 3.3334e-06 eta: 0:32:57 time: 0.9930 data_time: 0.0234 memory: 29136 grad_norm: 23.4552 loss: 7.9914 decode.loss_cls_ce: 1.5647 decode.loss_mask_ce: 0.8479 decode.loss_mask_dice: 1.5564 decode.d7.loss_cls_ce: 1.5741 decode.d7.loss_mask_ce: 0.8537 decode.d7.loss_mask_dice: 1.5945 2023/09/08 02:03:01 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1614 data_time: 0.0021 memory: 2646 2023/09/08 02:03:10 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1662 data_time: 0.0019 memory: 2757 2023/09/08 02:03:18 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1724 data_time: 0.0020 memory: 2646 2023/09/08 02:03:27 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1734 data_time: 0.0020 memory: 2600 2023/09/08 02:03:35 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1635 data_time: 0.0020 memory: 4253 2023/09/08 02:03:44 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1701 data_time: 0.0019 memory: 2676 2023/09/08 02:03:52 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1770 data_time: 0.0021 memory: 2646 2023/09/08 02:04:01 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1722 data_time: 0.0021 memory: 2646 2023/09/08 02:04:10 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1650 data_time: 0.0021 memory: 4605 2023/09/08 02:04:18 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1647 data_time: 0.0020 memory: 2980 2023/09/08 02:04:27 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1607 data_time: 0.0019 memory: 2705 2023/09/08 02:04:35 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1622 data_time: 0.0021 memory: 2921 2023/09/08 02:04:43 - mmengine - INFO - per class results: 2023/09/08 02:04:44 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.77 | 92.59 | | bicycle | 67.51 | 82.06 | | car | 63.93 | 86.46 | | motorcycle | 84.63 | 91.91 | | airplane | 81.45 | 91.7 | | bus | 82.54 | 93.75 | | train | 80.98 | 95.38 | | truck | 64.1 | 76.11 | | boat | 62.29 | 87.04 | | traffic light | 65.46 | 85.14 | | fire hydrant | 81.31 | 89.33 | | stop sign | 92.0 | 97.31 | | parking meter | 74.02 | 84.03 | | bench | 57.24 | 73.83 | | bird | 74.06 | 87.7 | | cat | 82.19 | 88.98 | | dog | 69.54 | 75.27 | | horse | 83.43 | 92.27 | | sheep | 86.59 | 93.67 | | cow | 84.71 | 89.99 | | elephant | 91.23 | 95.5 | | bear | 91.03 | 94.4 | | zebra | 90.65 | 95.06 | | giraffe | 84.53 | 91.57 | | backpack | 29.47 | 69.18 | | umbrella | 81.21 | 88.52 | | handbag | 36.63 | 54.8 | | tie | 10.06 | 16.59 | | suitcase | 68.63 | 83.07 | | frisbee | 68.66 | 86.89 | | skis | 38.64 | 62.01 | | snowboard | 63.77 | 74.71 | | sports ball | 54.45 | 79.34 | | kite | 61.9 | 74.21 | | baseball bat | 46.37 | 69.84 | | baseball glove | 65.68 | 87.27 | | skateboard | 65.02 | 87.95 | | surfboard | 80.92 | 89.69 | | tennis racket | 75.81 | 84.44 | | bottle | 47.49 | 66.48 | | wine glass | 48.27 | 71.13 | | cup | 44.6 | 64.19 | | fork | 40.63 | 56.32 | | knife | 27.7 | 37.35 | | spoon | 39.86 | 55.16 | | bowl | 38.59 | 53.58 | | banana | 63.95 | 89.58 | | apple | 47.51 | 58.83 | | sandwich | 47.47 | 59.72 | | orange | 66.1 | 70.13 | | broccoli | 51.62 | 66.63 | | carrot | 52.21 | 67.33 | | hot dog | 51.95 | 61.15 | | pizza | 67.89 | 79.91 | | donut | 75.44 | 89.6 | | cake | 71.71 | 85.12 | | chair | 47.72 | 72.01 | | couch | 56.52 | 75.02 | | potted plant | 33.63 | 48.97 | | bed | 64.78 | 84.71 | | dining table | 44.22 | 70.35 | | toilet | 78.18 | 93.34 | | tv | 70.05 | 82.8 | | laptop | 72.84 | 87.61 | | mouse | 67.86 | 79.03 | | remote | 59.18 | 71.4 | | keyboard | 61.53 | 74.12 | | cell phone | 68.06 | 89.1 | | microwave | 66.97 | 79.3 | | oven | 55.04 | 79.41 | | toaster | 67.36 | 90.44 | | sink | 47.45 | 83.06 | | refrigerator | 77.0 | 92.27 | | book | 49.04 | 63.04 | | clock | 70.83 | 79.31 | | vase | 53.33 | 83.46 | | scissors | 77.55 | 91.81 | | teddy bear | 77.71 | 87.06 | | hair drier | 46.34 | 56.7 | | toothbrush | 32.7 | 81.26 | | banner | 28.89 | 63.35 | | blanket | 17.86 | 23.5 | | branch | 5.08 | 6.45 | | bridge | 32.34 | 51.72 | | building-other | 51.79 | 70.72 | | bush | 31.7 | 47.97 | | cabinet | 50.56 | 70.08 | | cage | 9.43 | 13.18 | | cardboard | 37.54 | 56.23 | | carpet | 48.64 | 72.48 | | ceiling-other | 61.49 | 77.93 | | ceiling-tile | 26.79 | 28.62 | | cloth | 0.71 | 1.31 | | clothes | 18.76 | 28.86 | | clouds | 47.31 | 66.39 | | counter | 24.95 | 51.37 | | cupboard | 0.0 | 0.01 | | curtain | 63.18 | 79.6 | | desk-stuff | 34.73 | 51.84 | | dirt | 38.71 | 56.1 | | door-stuff | 40.26 | 62.02 | | fence | 35.32 | 67.88 | | floor-marble | 9.2 | 11.3 | | floor-other | 21.0 | 32.38 | | floor-stone | 2.95 | 3.6 | | floor-tile | 56.28 | 65.83 | | floor-wood | 64.24 | 78.85 | | flower | 40.72 | 60.83 | | fog | 11.43 | 13.57 | | food-other | 29.0 | 47.42 | | fruit | 30.97 | 63.14 | | furniture-other | 12.47 | 17.85 | | grass | 67.94 | 81.0 | | gravel | 26.06 | 40.09 | | ground-other | 2.23 | 3.31 | | hill | 13.93 | 21.96 | | house | 25.48 | 30.41 | | leaves | 24.92 | 32.24 | | light | 37.22 | 53.76 | | mat | 3.11 | 6.87 | | metal | 29.87 | 40.45 | | mirror-stuff | 55.07 | 79.07 | | moss | 0.0 | 0.0 | | mountain | 55.03 | 74.84 | | mud | 12.93 | 18.18 | | napkin | 9.89 | 14.3 | | net | 35.95 | 66.82 | | paper | 28.36 | 41.29 | | pavement | 51.6 | 71.74 | | pillow | 8.19 | 13.24 | | plant-other | 18.79 | 32.4 | | plastic | 16.36 | 21.61 | | platform | 24.06 | 36.25 | | playingfield | 70.41 | 92.78 | | railing | 6.71 | 16.3 | | railroad | 57.22 | 76.51 | | river | 40.4 | 62.42 | | road | 66.01 | 79.57 | | rock | 46.04 | 70.8 | | roof | 21.09 | 30.42 | | rug | 28.85 | 37.12 | | salad | 9.05 | 12.91 | | sand | 60.98 | 69.12 | | sea | 85.47 | 91.07 | | shelf | 25.54 | 36.08 | | sky-other | 69.82 | 83.0 | | skyscraper | 32.4 | 47.27 | | snow | 88.2 | 95.68 | | solid-other | 0.0 | 0.0 | | stairs | 24.73 | 58.0 | | stone | 0.01 | 0.02 | | straw | 19.42 | 23.29 | | structural-other | 0.09 | 0.1 | | table | 18.49 | 26.51 | | tent | 7.37 | 11.54 | | textile-other | 7.47 | 9.09 | | towel | 31.25 | 38.73 | | tree | 71.86 | 84.2 | | vegetable | 37.31 | 50.84 | | wall-brick | 42.22 | 53.33 | | wall-concrete | 45.99 | 56.54 | | wall-other | 16.25 | 38.85 | | wall-panel | 0.74 | 0.76 | | wall-stone | 25.63 | 34.57 | | wall-tile | 64.75 | 81.78 | | wall-wood | 35.48 | 50.4 | | water-other | 22.98 | 36.1 | | waterdrops | 3.01 | 5.19 | | window-blind | 49.38 | 62.31 | | window-other | 42.96 | 71.27 | | wood | 23.15 | 32.92 | +------------------+-------+-------+ 2023/09/08 02:04:44 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.3500 mIoU: 46.1300 mAcc: 59.7500 data_time: 0.0021 time: 0.1704 2023/09/08 02:05:33 - mmengine - INFO - Iter(train) [58050/60000] base_lr: 3.2501e-06 lr: 3.2501e-06 eta: 0:32:08 time: 0.9936 data_time: 0.0232 memory: 29584 grad_norm: 22.2398 loss: 9.4234 decode.loss_cls_ce: 1.8737 decode.loss_mask_ce: 0.8523 decode.loss_mask_dice: 1.9629 decode.d7.loss_cls_ce: 1.8948 decode.d7.loss_mask_ce: 0.8493 decode.d7.loss_mask_dice: 1.9904 2023/09/08 02:06:23 - mmengine - INFO - Iter(train) [58100/60000] base_lr: 3.1667e-06 lr: 3.1667e-06 eta: 0:31:18 time: 0.9931 data_time: 0.0236 memory: 29180 grad_norm: 18.5481 loss: 7.5023 decode.loss_cls_ce: 1.4898 decode.loss_mask_ce: 0.7583 decode.loss_mask_dice: 1.4793 decode.d7.loss_cls_ce: 1.5071 decode.d7.loss_mask_ce: 0.7656 decode.d7.loss_mask_dice: 1.5023 2023/09/08 02:07:13 - mmengine - INFO - Iter(train) [58150/60000] base_lr: 3.0834e-06 lr: 3.0834e-06 eta: 0:30:29 time: 0.9910 data_time: 0.0234 memory: 29284 grad_norm: 18.7146 loss: 8.5024 decode.loss_cls_ce: 1.6255 decode.loss_mask_ce: 0.8844 decode.loss_mask_dice: 1.7199 decode.d7.loss_cls_ce: 1.6325 decode.d7.loss_mask_ce: 0.8960 decode.d7.loss_mask_dice: 1.7442 2023/09/08 02:08:02 - mmengine - INFO - Iter(train) [58200/60000] base_lr: 3.0001e-06 lr: 3.0001e-06 eta: 0:29:39 time: 0.9909 data_time: 0.0245 memory: 29164 grad_norm: 18.4865 loss: 8.1428 decode.loss_cls_ce: 1.4748 decode.loss_mask_ce: 0.9657 decode.loss_mask_dice: 1.6047 decode.d7.loss_cls_ce: 1.5175 decode.d7.loss_mask_ce: 0.9845 decode.d7.loss_mask_dice: 1.5956 2023/09/08 02:08:52 - mmengine - INFO - Iter(train) [58250/60000] base_lr: 2.9167e-06 lr: 2.9167e-06 eta: 0:28:50 time: 0.9921 data_time: 0.0232 memory: 29251 grad_norm: 16.3227 loss: 8.0034 decode.loss_cls_ce: 1.6370 decode.loss_mask_ce: 0.8284 decode.loss_mask_dice: 1.5501 decode.d7.loss_cls_ce: 1.6129 decode.d7.loss_mask_ce: 0.8330 decode.d7.loss_mask_dice: 1.5419 2023/09/08 02:09:42 - mmengine - INFO - Iter(train) [58300/60000] base_lr: 2.8334e-06 lr: 2.8334e-06 eta: 0:28:00 time: 0.9942 data_time: 0.0240 memory: 29171 grad_norm: 19.1963 loss: 7.8197 decode.loss_cls_ce: 1.5500 decode.loss_mask_ce: 0.8117 decode.loss_mask_dice: 1.5406 decode.d7.loss_cls_ce: 1.5630 decode.d7.loss_mask_ce: 0.8084 decode.d7.loss_mask_dice: 1.5460 2023/09/08 02:10:31 - mmengine - INFO - Iter(train) [58350/60000] base_lr: 2.7500e-06 lr: 2.7500e-06 eta: 0:27:11 time: 0.9906 data_time: 0.0236 memory: 29176 grad_norm: 19.8762 loss: 7.8941 decode.loss_cls_ce: 1.5656 decode.loss_mask_ce: 0.8393 decode.loss_mask_dice: 1.5384 decode.d7.loss_cls_ce: 1.5610 decode.d7.loss_mask_ce: 0.8342 decode.d7.loss_mask_dice: 1.5555 2023/09/08 02:11:21 - mmengine - INFO - Iter(train) [58400/60000] base_lr: 2.6667e-06 lr: 2.6667e-06 eta: 0:26:22 time: 0.9923 data_time: 0.0237 memory: 29381 grad_norm: 17.0238 loss: 8.9751 decode.loss_cls_ce: 1.5997 decode.loss_mask_ce: 0.9959 decode.loss_mask_dice: 1.8749 decode.d7.loss_cls_ce: 1.6719 decode.d7.loss_mask_ce: 0.9829 decode.d7.loss_mask_dice: 1.8498 2023/09/08 02:12:11 - mmengine - INFO - Iter(train) [58450/60000] base_lr: 2.5834e-06 lr: 2.5834e-06 eta: 0:25:32 time: 0.9918 data_time: 0.0232 memory: 29229 grad_norm: 18.0793 loss: 6.1986 decode.loss_cls_ce: 1.2633 decode.loss_mask_ce: 0.7021 decode.loss_mask_dice: 1.1339 decode.d7.loss_cls_ce: 1.2680 decode.d7.loss_mask_ce: 0.7039 decode.d7.loss_mask_dice: 1.1275 2023/09/08 02:13:00 - mmengine - INFO - Iter(train) [58500/60000] base_lr: 2.5000e-06 lr: 2.5000e-06 eta: 0:24:43 time: 0.9912 data_time: 0.0241 memory: 29138 grad_norm: 17.7221 loss: 6.9478 decode.loss_cls_ce: 1.5292 decode.loss_mask_ce: 0.6992 decode.loss_mask_dice: 1.2279 decode.d7.loss_cls_ce: 1.5664 decode.d7.loss_mask_ce: 0.6929 decode.d7.loss_mask_dice: 1.2321 2023/09/08 02:13:09 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1612 data_time: 0.0019 memory: 2646 2023/09/08 02:13:17 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1667 data_time: 0.0021 memory: 2757 2023/09/08 02:13:26 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1736 data_time: 0.0020 memory: 2646 2023/09/08 02:13:34 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1735 data_time: 0.0019 memory: 2600 2023/09/08 02:13:43 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1636 data_time: 0.0019 memory: 4253 2023/09/08 02:13:51 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1698 data_time: 0.0020 memory: 2676 2023/09/08 02:14:00 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1769 data_time: 0.0021 memory: 2646 2023/09/08 02:14:08 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1717 data_time: 0.0019 memory: 2646 2023/09/08 02:14:17 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1661 data_time: 0.0021 memory: 4605 2023/09/08 02:14:26 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1640 data_time: 0.0019 memory: 2980 2023/09/08 02:14:34 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1623 data_time: 0.0020 memory: 2705 2023/09/08 02:14:43 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1621 data_time: 0.0020 memory: 2921 2023/09/08 02:14:51 - mmengine - INFO - per class results: 2023/09/08 02:14:51 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.73 | 92.61 | | bicycle | 67.47 | 82.03 | | car | 63.93 | 86.28 | | motorcycle | 84.62 | 92.0 | | airplane | 80.97 | 91.76 | | bus | 82.16 | 93.67 | | train | 80.6 | 95.37 | | truck | 64.11 | 76.23 | | boat | 61.87 | 87.26 | | traffic light | 65.6 | 84.83 | | fire hydrant | 81.22 | 89.38 | | stop sign | 92.02 | 97.25 | | parking meter | 73.4 | 83.84 | | bench | 57.04 | 73.97 | | bird | 74.2 | 86.99 | | cat | 82.34 | 89.06 | | dog | 69.42 | 75.2 | | horse | 83.48 | 92.41 | | sheep | 86.62 | 93.64 | | cow | 84.66 | 90.01 | | elephant | 91.28 | 95.58 | | bear | 91.11 | 94.7 | | zebra | 90.9 | 95.1 | | giraffe | 84.55 | 91.63 | | backpack | 29.49 | 69.01 | | umbrella | 81.12 | 88.44 | | handbag | 36.54 | 55.14 | | tie | 10.03 | 16.94 | | suitcase | 68.59 | 82.96 | | frisbee | 66.48 | 86.83 | | skis | 38.78 | 62.59 | | snowboard | 63.34 | 74.09 | | sports ball | 53.89 | 78.84 | | kite | 61.74 | 74.11 | | baseball bat | 46.23 | 69.72 | | baseball glove | 65.42 | 87.41 | | skateboard | 62.33 | 88.15 | | surfboard | 80.78 | 89.51 | | tennis racket | 75.23 | 84.29 | | bottle | 47.5 | 64.94 | | wine glass | 48.76 | 69.9 | | cup | 44.43 | 62.24 | | fork | 40.35 | 55.51 | | knife | 26.67 | 35.79 | | spoon | 40.94 | 55.28 | | bowl | 38.29 | 52.94 | | banana | 64.8 | 89.97 | | apple | 46.7 | 57.54 | | sandwich | 46.25 | 58.0 | | orange | 66.93 | 71.05 | | broccoli | 52.84 | 67.17 | | carrot | 50.66 | 64.82 | | hot dog | 52.67 | 62.04 | | pizza | 66.1 | 76.92 | | donut | 75.75 | 90.07 | | cake | 71.38 | 84.71 | | chair | 47.58 | 71.89 | | couch | 56.82 | 75.23 | | potted plant | 33.34 | 48.88 | | bed | 64.91 | 84.43 | | dining table | 44.45 | 72.39 | | toilet | 78.43 | 93.28 | | tv | 69.91 | 82.67 | | laptop | 72.63 | 87.08 | | mouse | 68.18 | 78.93 | | remote | 59.26 | 71.47 | | keyboard | 61.64 | 73.96 | | cell phone | 68.5 | 89.16 | | microwave | 67.18 | 79.26 | | oven | 54.46 | 79.78 | | toaster | 68.69 | 90.62 | | sink | 47.15 | 83.16 | | refrigerator | 77.01 | 92.13 | | book | 49.25 | 62.77 | | clock | 70.08 | 78.82 | | vase | 53.75 | 83.35 | | scissors | 77.05 | 91.0 | | teddy bear | 77.94 | 87.22 | | hair drier | 39.73 | 57.01 | | toothbrush | 32.34 | 81.38 | | banner | 29.57 | 63.19 | | blanket | 17.67 | 23.01 | | branch | 5.18 | 6.5 | | bridge | 32.21 | 52.02 | | building-other | 51.72 | 70.54 | | bush | 31.88 | 47.77 | | cabinet | 50.61 | 70.25 | | cage | 9.5 | 13.44 | | cardboard | 37.65 | 56.22 | | carpet | 49.68 | 73.83 | | ceiling-other | 61.27 | 78.39 | | ceiling-tile | 26.77 | 28.63 | | cloth | 0.68 | 1.25 | | clothes | 18.58 | 28.26 | | clouds | 47.49 | 65.96 | | counter | 24.62 | 50.69 | | cupboard | 0.01 | 0.01 | | curtain | 63.57 | 80.11 | | desk-stuff | 36.16 | 54.46 | | dirt | 38.66 | 55.95 | | door-stuff | 40.15 | 62.41 | | fence | 35.14 | 67.51 | | floor-marble | 9.61 | 11.7 | | floor-other | 20.71 | 31.64 | | floor-stone | 2.97 | 3.55 | | floor-tile | 57.37 | 66.79 | | floor-wood | 64.64 | 78.86 | | flower | 40.37 | 60.33 | | fog | 11.5 | 13.9 | | food-other | 28.12 | 44.99 | | fruit | 31.4 | 63.05 | | furniture-other | 12.49 | 17.91 | | grass | 68.11 | 80.98 | | gravel | 25.65 | 40.03 | | ground-other | 1.95 | 2.87 | | hill | 13.9 | 22.11 | | house | 25.64 | 30.71 | | leaves | 24.23 | 31.23 | | light | 37.22 | 53.12 | | mat | 4.05 | 8.94 | | metal | 29.88 | 40.34 | | mirror-stuff | 54.81 | 78.86 | | moss | 0.0 | 0.0 | | mountain | 54.73 | 74.96 | | mud | 13.23 | 18.55 | | napkin | 9.72 | 13.68 | | net | 36.14 | 66.93 | | paper | 27.99 | 40.61 | | pavement | 51.62 | 71.24 | | pillow | 8.53 | 14.05 | | plant-other | 18.81 | 32.48 | | plastic | 16.67 | 21.93 | | platform | 23.92 | 35.86 | | playingfield | 70.88 | 93.04 | | railing | 6.84 | 16.43 | | railroad | 57.16 | 76.36 | | river | 40.38 | 62.51 | | road | 65.85 | 79.47 | | rock | 45.19 | 69.82 | | roof | 20.79 | 30.89 | | rug | 28.68 | 36.78 | | salad | 7.96 | 11.33 | | sand | 61.89 | 69.87 | | sea | 85.48 | 91.09 | | shelf | 25.56 | 36.37 | | sky-other | 70.13 | 83.53 | | skyscraper | 35.52 | 52.65 | | snow | 88.25 | 95.27 | | solid-other | 0.0 | 0.0 | | stairs | 25.19 | 59.27 | | stone | 0.01 | 0.02 | | straw | 19.34 | 23.18 | | structural-other | 0.09 | 0.1 | | table | 18.19 | 25.27 | | tent | 7.38 | 11.75 | | textile-other | 7.43 | 9.06 | | towel | 30.32 | 38.23 | | tree | 71.91 | 84.44 | | vegetable | 37.95 | 51.27 | | wall-brick | 42.27 | 53.79 | | wall-concrete | 48.51 | 59.93 | | wall-other | 16.6 | 37.69 | | wall-panel | 0.75 | 0.78 | | wall-stone | 25.53 | 34.39 | | wall-tile | 64.67 | 82.29 | | wall-wood | 35.94 | 51.71 | | water-other | 23.39 | 36.47 | | waterdrops | 3.12 | 5.49 | | window-blind | 49.11 | 62.45 | | window-other | 42.79 | 71.49 | | wood | 23.02 | 32.83 | +------------------+-------+-------+ 2023/09/08 02:14:51 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.5400 mIoU: 46.0800 mAcc: 59.7300 data_time: 0.0022 time: 0.1704 2023/09/08 02:15:41 - mmengine - INFO - Iter(train) [58550/60000] base_lr: 2.4167e-06 lr: 2.4167e-06 eta: 0:23:53 time: 0.9944 data_time: 0.0243 memory: 29268 grad_norm: 19.4048 loss: 7.5185 decode.loss_cls_ce: 1.6026 decode.loss_mask_ce: 0.8322 decode.loss_mask_dice: 1.3447 decode.d7.loss_cls_ce: 1.5545 decode.d7.loss_mask_ce: 0.8479 decode.d7.loss_mask_dice: 1.3366 2023/09/08 02:16:30 - mmengine - INFO - Iter(train) [58600/60000] base_lr: 2.3334e-06 lr: 2.3334e-06 eta: 0:23:04 time: 0.9928 data_time: 0.0241 memory: 29167 grad_norm: 19.4222 loss: 7.6376 decode.loss_cls_ce: 1.5994 decode.loss_mask_ce: 0.8072 decode.loss_mask_dice: 1.3920 decode.d7.loss_cls_ce: 1.6240 decode.d7.loss_mask_ce: 0.8021 decode.d7.loss_mask_dice: 1.4129 2023/09/08 02:17:20 - mmengine - INFO - Iter(train) [58650/60000] base_lr: 2.2500e-06 lr: 2.2500e-06 eta: 0:22:14 time: 0.9945 data_time: 0.0241 memory: 29269 grad_norm: 19.6292 loss: 9.4241 decode.loss_cls_ce: 1.7783 decode.loss_mask_ce: 0.9523 decode.loss_mask_dice: 1.9598 decode.d7.loss_cls_ce: 1.7925 decode.d7.loss_mask_ce: 0.9484 decode.d7.loss_mask_dice: 1.9929 2023/09/08 02:18:10 - mmengine - INFO - Iter(train) [58700/60000] base_lr: 2.1667e-06 lr: 2.1667e-06 eta: 0:21:25 time: 0.9939 data_time: 0.0230 memory: 29315 grad_norm: 17.7067 loss: 8.3422 decode.loss_cls_ce: 1.6389 decode.loss_mask_ce: 0.7940 decode.loss_mask_dice: 1.7088 decode.d7.loss_cls_ce: 1.7057 decode.d7.loss_mask_ce: 0.7934 decode.d7.loss_mask_dice: 1.7013 2023/09/08 02:19:00 - mmengine - INFO - Iter(train) [58750/60000] base_lr: 2.0834e-06 lr: 2.0834e-06 eta: 0:20:36 time: 0.9923 data_time: 0.0239 memory: 29307 grad_norm: 17.6572 loss: 7.4010 decode.loss_cls_ce: 1.5850 decode.loss_mask_ce: 0.7671 decode.loss_mask_dice: 1.3327 decode.d7.loss_cls_ce: 1.6329 decode.d7.loss_mask_ce: 0.7757 decode.d7.loss_mask_dice: 1.3075 2023/09/08 02:19:49 - mmengine - INFO - Iter(train) [58800/60000] base_lr: 2.0000e-06 lr: 2.0000e-06 eta: 0:19:46 time: 0.9932 data_time: 0.0234 memory: 29215 grad_norm: 19.0058 loss: 6.3323 decode.loss_cls_ce: 1.3491 decode.loss_mask_ce: 0.6182 decode.loss_mask_dice: 1.2097 decode.d7.loss_cls_ce: 1.3473 decode.d7.loss_mask_ce: 0.6168 decode.d7.loss_mask_dice: 1.1913 2023/09/08 02:20:39 - mmengine - INFO - Iter(train) [58850/60000] base_lr: 1.9167e-06 lr: 1.9167e-06 eta: 0:18:57 time: 0.9929 data_time: 0.0235 memory: 29190 grad_norm: 19.1461 loss: 6.4578 decode.loss_cls_ce: 1.3029 decode.loss_mask_ce: 0.7011 decode.loss_mask_dice: 1.2077 decode.d7.loss_cls_ce: 1.3206 decode.d7.loss_mask_ce: 0.7111 decode.d7.loss_mask_dice: 1.2145 2023/09/08 02:21:28 - mmengine - INFO - Iter(train) [58900/60000] base_lr: 1.8334e-06 lr: 1.8334e-06 eta: 0:18:07 time: 0.9955 data_time: 0.0235 memory: 29084 grad_norm: 18.2891 loss: 6.9300 decode.loss_cls_ce: 1.5223 decode.loss_mask_ce: 0.6371 decode.loss_mask_dice: 1.3166 decode.d7.loss_cls_ce: 1.5355 decode.d7.loss_mask_ce: 0.6228 decode.d7.loss_mask_dice: 1.2958 2023/09/08 02:22:18 - mmengine - INFO - Iter(train) [58950/60000] base_lr: 1.7500e-06 lr: 1.7500e-06 eta: 0:17:18 time: 0.9929 data_time: 0.0236 memory: 29290 grad_norm: 16.7013 loss: 8.0594 decode.loss_cls_ce: 1.5193 decode.loss_mask_ce: 0.8359 decode.loss_mask_dice: 1.6554 decode.d7.loss_cls_ce: 1.5289 decode.d7.loss_mask_ce: 0.8522 decode.d7.loss_mask_dice: 1.6678 2023/09/08 02:23:08 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 02:23:08 - mmengine - INFO - Iter(train) [59000/60000] base_lr: 1.6667e-06 lr: 1.6667e-06 eta: 0:16:28 time: 0.9940 data_time: 0.0233 memory: 29200 grad_norm: 19.3326 loss: 8.9782 decode.loss_cls_ce: 1.8670 decode.loss_mask_ce: 0.8631 decode.loss_mask_dice: 1.7481 decode.d7.loss_cls_ce: 1.9298 decode.d7.loss_mask_ce: 0.8563 decode.d7.loss_mask_dice: 1.7138 2023/09/08 02:23:16 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1609 data_time: 0.0019 memory: 2646 2023/09/08 02:23:25 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1668 data_time: 0.0020 memory: 2757 2023/09/08 02:23:33 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1723 data_time: 0.0019 memory: 2646 2023/09/08 02:23:42 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1729 data_time: 0.0020 memory: 2600 2023/09/08 02:23:50 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1637 data_time: 0.0021 memory: 4253 2023/09/08 02:23:59 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1698 data_time: 0.0019 memory: 2676 2023/09/08 02:24:07 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1773 data_time: 0.0025 memory: 2646 2023/09/08 02:24:16 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1736 data_time: 0.0023 memory: 2646 2023/09/08 02:24:25 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1659 data_time: 0.0021 memory: 4605 2023/09/08 02:24:33 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1643 data_time: 0.0020 memory: 2980 2023/09/08 02:24:42 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1618 data_time: 0.0021 memory: 2705 2023/09/08 02:24:50 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1620 data_time: 0.0020 memory: 2921 2023/09/08 02:24:58 - mmengine - INFO - per class results: 2023/09/08 02:24:58 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.76 | 92.63 | | bicycle | 66.62 | 81.32 | | car | 63.85 | 86.35 | | motorcycle | 84.65 | 92.09 | | airplane | 81.51 | 91.89 | | bus | 82.72 | 93.76 | | train | 80.82 | 95.45 | | truck | 64.11 | 76.23 | | boat | 61.92 | 87.28 | | traffic light | 65.51 | 85.06 | | fire hydrant | 81.26 | 89.45 | | stop sign | 92.06 | 97.35 | | parking meter | 74.69 | 85.74 | | bench | 57.08 | 74.02 | | bird | 73.64 | 87.46 | | cat | 82.32 | 89.34 | | dog | 70.5 | 76.42 | | horse | 83.47 | 92.43 | | sheep | 86.62 | 93.71 | | cow | 84.57 | 90.1 | | elephant | 91.32 | 95.69 | | bear | 91.0 | 94.55 | | zebra | 90.92 | 95.2 | | giraffe | 84.58 | 91.81 | | backpack | 29.4 | 68.8 | | umbrella | 81.25 | 88.68 | | handbag | 36.67 | 54.99 | | tie | 10.59 | 16.81 | | suitcase | 69.27 | 82.95 | | frisbee | 69.81 | 87.29 | | skis | 39.14 | 62.89 | | snowboard | 63.05 | 73.85 | | sports ball | 53.84 | 78.37 | | kite | 61.72 | 74.36 | | baseball bat | 46.43 | 69.83 | | baseball glove | 65.31 | 87.43 | | skateboard | 66.2 | 88.18 | | surfboard | 80.81 | 89.65 | | tennis racket | 74.77 | 84.43 | | bottle | 47.63 | 65.82 | | wine glass | 48.79 | 70.1 | | cup | 44.64 | 63.24 | | fork | 41.41 | 57.33 | | knife | 28.04 | 37.89 | | spoon | 41.27 | 56.36 | | bowl | 38.52 | 52.42 | | banana | 64.82 | 90.51 | | apple | 48.85 | 60.48 | | sandwich | 46.99 | 59.27 | | orange | 68.39 | 72.48 | | broccoli | 53.0 | 68.39 | | carrot | 52.38 | 67.8 | | hot dog | 53.84 | 63.69 | | pizza | 66.99 | 78.13 | | donut | 74.94 | 89.45 | | cake | 71.51 | 85.02 | | chair | 47.71 | 71.96 | | couch | 57.2 | 75.55 | | potted plant | 33.58 | 49.22 | | bed | 65.71 | 84.89 | | dining table | 44.39 | 71.38 | | toilet | 78.9 | 93.34 | | tv | 70.04 | 82.95 | | laptop | 72.81 | 87.61 | | mouse | 67.92 | 78.96 | | remote | 60.15 | 72.78 | | keyboard | 62.12 | 74.38 | | cell phone | 68.3 | 89.09 | | microwave | 67.42 | 79.52 | | oven | 55.15 | 80.12 | | toaster | 67.56 | 90.66 | | sink | 46.96 | 83.02 | | refrigerator | 77.28 | 92.26 | | book | 49.3 | 63.63 | | clock | 70.35 | 79.17 | | vase | 54.13 | 83.48 | | scissors | 77.73 | 91.99 | | teddy bear | 78.22 | 87.75 | | hair drier | 40.02 | 57.04 | | toothbrush | 32.19 | 81.35 | | banner | 28.96 | 63.69 | | blanket | 17.88 | 23.03 | | branch | 5.26 | 6.56 | | bridge | 32.41 | 51.92 | | building-other | 52.03 | 70.91 | | bush | 31.76 | 46.92 | | cabinet | 50.59 | 70.05 | | cage | 9.51 | 13.54 | | cardboard | 37.67 | 57.39 | | carpet | 49.79 | 73.76 | | ceiling-other | 61.38 | 78.3 | | ceiling-tile | 26.73 | 28.63 | | cloth | 0.68 | 1.23 | | clothes | 18.75 | 28.71 | | clouds | 47.34 | 64.85 | | counter | 24.69 | 50.62 | | cupboard | 0.0 | 0.01 | | curtain | 63.85 | 80.6 | | desk-stuff | 36.06 | 54.12 | | dirt | 38.37 | 55.75 | | door-stuff | 40.16 | 62.98 | | fence | 35.06 | 67.05 | | floor-marble | 9.72 | 11.81 | | floor-other | 20.83 | 31.81 | | floor-stone | 3.02 | 3.65 | | floor-tile | 56.73 | 66.21 | | floor-wood | 64.44 | 78.78 | | flower | 40.67 | 61.38 | | fog | 11.72 | 13.7 | | food-other | 28.99 | 46.44 | | fruit | 31.4 | 62.45 | | furniture-other | 12.5 | 17.96 | | grass | 67.96 | 80.73 | | gravel | 25.7 | 40.25 | | ground-other | 1.81 | 2.65 | | hill | 13.79 | 21.64 | | house | 25.19 | 30.02 | | leaves | 24.71 | 31.76 | | light | 37.03 | 53.78 | | mat | 3.71 | 8.36 | | metal | 29.92 | 40.24 | | mirror-stuff | 54.86 | 79.26 | | moss | 0.0 | 0.0 | | mountain | 54.94 | 74.41 | | mud | 13.41 | 18.86 | | napkin | 10.28 | 14.76 | | net | 35.98 | 66.55 | | paper | 28.21 | 41.71 | | pavement | 51.42 | 71.54 | | pillow | 8.93 | 14.8 | | plant-other | 18.81 | 32.34 | | plastic | 17.23 | 22.81 | | platform | 24.09 | 36.22 | | playingfield | 70.55 | 92.87 | | railing | 6.77 | 16.5 | | railroad | 57.13 | 76.22 | | river | 40.51 | 62.51 | | road | 65.9 | 79.27 | | rock | 45.14 | 69.71 | | roof | 21.0 | 31.01 | | rug | 29.08 | 37.25 | | salad | 8.23 | 11.57 | | sand | 60.96 | 69.16 | | sea | 85.5 | 91.03 | | shelf | 25.25 | 35.97 | | sky-other | 70.45 | 84.38 | | skyscraper | 34.48 | 49.73 | | snow | 88.86 | 95.52 | | solid-other | 0.0 | 0.0 | | stairs | 24.84 | 59.27 | | stone | 0.04 | 0.05 | | straw | 19.32 | 23.11 | | structural-other | 0.09 | 0.1 | | table | 18.39 | 25.92 | | tent | 7.73 | 12.11 | | textile-other | 7.58 | 9.22 | | towel | 31.26 | 39.29 | | tree | 72.08 | 84.84 | | vegetable | 37.57 | 50.87 | | wall-brick | 42.25 | 53.69 | | wall-concrete | 48.88 | 60.28 | | wall-other | 16.8 | 37.72 | | wall-panel | 0.72 | 0.74 | | wall-stone | 25.92 | 34.94 | | wall-tile | 64.66 | 82.04 | | wall-wood | 35.89 | 51.31 | | water-other | 23.08 | 36.21 | | waterdrops | 3.12 | 5.25 | | window-blind | 48.88 | 62.34 | | window-other | 42.89 | 72.3 | | wood | 22.9 | 32.4 | +------------------+-------+-------+ 2023/09/08 02:24:59 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.6400 mIoU: 46.2500 mAcc: 59.9300 data_time: 0.0021 time: 0.1704 2023/09/08 02:25:48 - mmengine - INFO - Iter(train) [59050/60000] base_lr: 1.5834e-06 lr: 1.5834e-06 eta: 0:15:39 time: 0.9938 data_time: 0.0235 memory: 29145 grad_norm: 17.2715 loss: 6.9095 decode.loss_cls_ce: 1.3928 decode.loss_mask_ce: 0.7684 decode.loss_mask_dice: 1.3163 decode.d7.loss_cls_ce: 1.3670 decode.d7.loss_mask_ce: 0.7772 decode.d7.loss_mask_dice: 1.2877 2023/09/08 02:26:38 - mmengine - INFO - Iter(train) [59100/60000] base_lr: 1.5000e-06 lr: 1.5000e-06 eta: 0:14:50 time: 0.9944 data_time: 0.0235 memory: 29319 grad_norm: 17.6316 loss: 6.4312 decode.loss_cls_ce: 1.2844 decode.loss_mask_ce: 0.6976 decode.loss_mask_dice: 1.2507 decode.d7.loss_cls_ce: 1.2589 decode.d7.loss_mask_ce: 0.6951 decode.d7.loss_mask_dice: 1.2446 2023/09/08 02:27:28 - mmengine - INFO - Iter(train) [59150/60000] base_lr: 1.4167e-06 lr: 1.4167e-06 eta: 0:14:00 time: 0.9920 data_time: 0.0240 memory: 29204 grad_norm: 20.2795 loss: 7.7161 decode.loss_cls_ce: 1.5737 decode.loss_mask_ce: 0.7901 decode.loss_mask_dice: 1.4638 decode.d7.loss_cls_ce: 1.6270 decode.d7.loss_mask_ce: 0.7992 decode.d7.loss_mask_dice: 1.4623 2023/09/08 02:28:17 - mmengine - INFO - Iter(train) [59200/60000] base_lr: 1.3334e-06 lr: 1.3334e-06 eta: 0:13:11 time: 0.9938 data_time: 0.0237 memory: 29199 grad_norm: 17.5687 loss: 7.7322 decode.loss_cls_ce: 1.6300 decode.loss_mask_ce: 0.8019 decode.loss_mask_dice: 1.4418 decode.d7.loss_cls_ce: 1.5985 decode.d7.loss_mask_ce: 0.8057 decode.d7.loss_mask_dice: 1.4543 2023/09/08 02:29:07 - mmengine - INFO - Iter(train) [59250/60000] base_lr: 1.2500e-06 lr: 1.2500e-06 eta: 0:12:21 time: 0.9933 data_time: 0.0240 memory: 29164 grad_norm: 18.1148 loss: 7.7744 decode.loss_cls_ce: 1.7397 decode.loss_mask_ce: 0.7468 decode.loss_mask_dice: 1.4019 decode.d7.loss_cls_ce: 1.7330 decode.d7.loss_mask_ce: 0.7461 decode.d7.loss_mask_dice: 1.4068 2023/09/08 02:29:57 - mmengine - INFO - Iter(train) [59300/60000] base_lr: 1.1667e-06 lr: 1.1667e-06 eta: 0:11:32 time: 0.9952 data_time: 0.0233 memory: 29137 grad_norm: 17.5713 loss: 8.1774 decode.loss_cls_ce: 1.5350 decode.loss_mask_ce: 0.7887 decode.loss_mask_dice: 1.7505 decode.d7.loss_cls_ce: 1.5680 decode.d7.loss_mask_ce: 0.7933 decode.d7.loss_mask_dice: 1.7418 2023/09/08 02:30:46 - mmengine - INFO - Iter(train) [59350/60000] base_lr: 1.0834e-06 lr: 1.0834e-06 eta: 0:10:42 time: 0.9917 data_time: 0.0234 memory: 29163 grad_norm: 19.3765 loss: 7.6199 decode.loss_cls_ce: 1.5093 decode.loss_mask_ce: 0.7191 decode.loss_mask_dice: 1.5633 decode.d7.loss_cls_ce: 1.5112 decode.d7.loss_mask_ce: 0.7381 decode.d7.loss_mask_dice: 1.5789 2023/09/08 02:31:36 - mmengine - INFO - Iter(train) [59400/60000] base_lr: 1.0000e-06 lr: 1.0000e-06 eta: 0:09:53 time: 0.9936 data_time: 0.0237 memory: 29327 grad_norm: 20.4223 loss: 9.5896 decode.loss_cls_ce: 1.7664 decode.loss_mask_ce: 0.9504 decode.loss_mask_dice: 2.0546 decode.d7.loss_cls_ce: 1.7840 decode.d7.loss_mask_ce: 0.9633 decode.d7.loss_mask_dice: 2.0708 2023/09/08 02:32:26 - mmengine - INFO - Iter(train) [59450/60000] base_lr: 9.1668e-07 lr: 9.1668e-07 eta: 0:09:03 time: 0.9936 data_time: 0.0232 memory: 29269 grad_norm: 17.7011 loss: 8.4535 decode.loss_cls_ce: 1.7345 decode.loss_mask_ce: 0.8274 decode.loss_mask_dice: 1.6653 decode.d7.loss_cls_ce: 1.7194 decode.d7.loss_mask_ce: 0.8411 decode.d7.loss_mask_dice: 1.6658 2023/09/08 02:33:15 - mmengine - INFO - Iter(train) [59500/60000] base_lr: 8.3335e-07 lr: 8.3335e-07 eta: 0:08:14 time: 0.9929 data_time: 0.0238 memory: 29228 grad_norm: 20.9038 loss: 6.6996 decode.loss_cls_ce: 1.3529 decode.loss_mask_ce: 0.7098 decode.loss_mask_dice: 1.2589 decode.d7.loss_cls_ce: 1.3980 decode.d7.loss_mask_ce: 0.7140 decode.d7.loss_mask_dice: 1.2658 2023/09/08 02:33:24 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1618 data_time: 0.0023 memory: 2646 2023/09/08 02:33:32 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1695 data_time: 0.0020 memory: 2757 2023/09/08 02:33:41 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1754 data_time: 0.0023 memory: 2646 2023/09/08 02:33:49 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:12 time: 0.1739 data_time: 0.0019 memory: 2600 2023/09/08 02:33:58 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1635 data_time: 0.0022 memory: 4253 2023/09/08 02:34:06 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1690 data_time: 0.0020 memory: 2676 2023/09/08 02:34:15 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1757 data_time: 0.0019 memory: 2646 2023/09/08 02:34:23 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1724 data_time: 0.0020 memory: 2646 2023/09/08 02:34:32 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1638 data_time: 0.0019 memory: 4605 2023/09/08 02:34:41 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1667 data_time: 0.0020 memory: 2980 2023/09/08 02:34:49 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1615 data_time: 0.0020 memory: 2705 2023/09/08 02:34:58 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1619 data_time: 0.0020 memory: 2921 2023/09/08 02:35:06 - mmengine - INFO - per class results: 2023/09/08 02:35:06 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.76 | 92.59 | | bicycle | 66.74 | 81.49 | | car | 63.85 | 86.31 | | motorcycle | 84.63 | 92.11 | | airplane | 81.37 | 91.82 | | bus | 82.79 | 93.75 | | train | 80.93 | 95.48 | | truck | 64.08 | 76.25 | | boat | 61.79 | 87.22 | | traffic light | 65.54 | 85.07 | | fire hydrant | 81.25 | 89.41 | | stop sign | 92.1 | 97.32 | | parking meter | 73.24 | 83.81 | | bench | 57.2 | 74.03 | | bird | 73.87 | 87.17 | | cat | 82.21 | 89.1 | | dog | 70.1 | 75.97 | | horse | 83.49 | 92.44 | | sheep | 86.62 | 93.7 | | cow | 84.67 | 90.06 | | elephant | 91.28 | 95.6 | | bear | 90.98 | 94.55 | | zebra | 90.84 | 95.15 | | giraffe | 84.57 | 91.71 | | backpack | 29.54 | 67.97 | | umbrella | 81.25 | 88.63 | | handbag | 36.32 | 55.15 | | tie | 10.45 | 17.0 | | suitcase | 69.11 | 82.9 | | frisbee | 69.74 | 87.35 | | skis | 39.39 | 63.67 | | snowboard | 63.12 | 74.17 | | sports ball | 53.92 | 78.82 | | kite | 61.79 | 74.3 | | baseball bat | 46.32 | 69.79 | | baseball glove | 65.41 | 87.69 | | skateboard | 66.88 | 88.39 | | surfboard | 80.8 | 89.74 | | tennis racket | 75.04 | 84.65 | | bottle | 47.31 | 65.53 | | wine glass | 48.52 | 69.84 | | cup | 44.49 | 63.35 | | fork | 40.93 | 56.87 | | knife | 28.34 | 38.38 | | spoon | 41.09 | 56.39 | | bowl | 38.77 | 53.04 | | banana | 64.85 | 90.51 | | apple | 48.68 | 60.18 | | sandwich | 47.18 | 59.32 | | orange | 67.83 | 71.93 | | broccoli | 52.66 | 67.57 | | carrot | 51.82 | 67.06 | | hot dog | 53.54 | 63.28 | | pizza | 68.07 | 79.5 | | donut | 75.1 | 89.51 | | cake | 71.85 | 85.09 | | chair | 47.69 | 72.0 | | couch | 56.81 | 75.37 | | potted plant | 33.6 | 49.23 | | bed | 65.33 | 85.01 | | dining table | 44.91 | 72.19 | | toilet | 78.97 | 93.32 | | tv | 70.11 | 82.82 | | laptop | 72.99 | 87.72 | | mouse | 67.9 | 79.07 | | remote | 60.04 | 72.62 | | keyboard | 61.96 | 74.16 | | cell phone | 68.39 | 89.22 | | microwave | 67.23 | 79.33 | | oven | 55.16 | 80.12 | | toaster | 66.71 | 90.75 | | sink | 47.36 | 83.27 | | refrigerator | 77.38 | 92.23 | | book | 49.36 | 63.69 | | clock | 70.69 | 79.24 | | vase | 53.89 | 83.43 | | scissors | 77.7 | 92.03 | | teddy bear | 78.12 | 87.54 | | hair drier | 40.63 | 57.03 | | toothbrush | 32.43 | 81.49 | | banner | 29.15 | 63.67 | | blanket | 17.56 | 22.43 | | branch | 5.28 | 6.61 | | bridge | 32.63 | 52.1 | | building-other | 51.95 | 70.59 | | bush | 31.91 | 47.81 | | cabinet | 50.57 | 70.03 | | cage | 9.44 | 13.38 | | cardboard | 37.69 | 57.33 | | carpet | 49.87 | 73.8 | | ceiling-other | 61.98 | 78.77 | | ceiling-tile | 26.74 | 28.63 | | cloth | 0.7 | 1.26 | | clothes | 18.87 | 29.0 | | clouds | 47.5 | 66.43 | | counter | 24.94 | 51.01 | | cupboard | 0.0 | 0.01 | | curtain | 63.74 | 80.14 | | desk-stuff | 36.02 | 53.71 | | dirt | 39.46 | 57.39 | | door-stuff | 40.01 | 62.92 | | fence | 35.18 | 67.39 | | floor-marble | 9.3 | 11.27 | | floor-other | 20.95 | 32.22 | | floor-stone | 2.9 | 3.52 | | floor-tile | 56.74 | 66.17 | | floor-wood | 64.42 | 78.76 | | flower | 40.46 | 60.9 | | fog | 11.74 | 13.73 | | food-other | 28.7 | 45.95 | | fruit | 31.36 | 62.43 | | furniture-other | 12.48 | 17.95 | | grass | 68.0 | 80.97 | | gravel | 26.37 | 40.1 | | ground-other | 2.44 | 3.61 | | hill | 13.96 | 21.87 | | house | 25.38 | 30.26 | | leaves | 24.78 | 31.86 | | light | 37.05 | 53.87 | | mat | 3.43 | 7.55 | | metal | 29.83 | 40.13 | | mirror-stuff | 55.21 | 79.05 | | moss | 0.0 | 0.0 | | mountain | 54.96 | 74.87 | | mud | 13.31 | 18.51 | | napkin | 10.04 | 14.29 | | net | 35.98 | 66.28 | | paper | 28.2 | 41.55 | | pavement | 51.34 | 71.01 | | pillow | 7.73 | 12.65 | | plant-other | 18.8 | 32.26 | | plastic | 16.86 | 22.33 | | platform | 23.98 | 36.1 | | playingfield | 70.78 | 92.81 | | railing | 6.85 | 16.43 | | railroad | 57.39 | 76.34 | | river | 41.25 | 63.6 | | road | 65.91 | 79.67 | | rock | 45.11 | 69.88 | | roof | 23.37 | 34.35 | | rug | 29.07 | 37.27 | | salad | 7.67 | 10.8 | | sand | 61.31 | 68.93 | | sea | 85.51 | 91.05 | | shelf | 25.23 | 35.55 | | sky-other | 70.28 | 83.64 | | skyscraper | 33.81 | 49.73 | | snow | 88.62 | 95.38 | | solid-other | 0.0 | 0.0 | | stairs | 25.06 | 59.24 | | stone | 0.01 | 0.02 | | straw | 19.33 | 23.08 | | structural-other | 0.08 | 0.09 | | table | 18.46 | 25.76 | | tent | 7.75 | 12.12 | | textile-other | 7.68 | 9.36 | | towel | 30.65 | 38.37 | | tree | 72.02 | 84.53 | | vegetable | 37.19 | 50.44 | | wall-brick | 42.32 | 53.74 | | wall-concrete | 48.72 | 60.36 | | wall-other | 16.77 | 37.75 | | wall-panel | 0.78 | 0.8 | | wall-stone | 25.88 | 34.77 | | wall-tile | 64.66 | 82.0 | | wall-wood | 35.54 | 51.11 | | water-other | 23.36 | 36.07 | | waterdrops | 3.11 | 5.3 | | window-blind | 49.04 | 62.31 | | window-other | 43.0 | 72.01 | | wood | 22.7 | 32.26 | +------------------+-------+-------+ 2023/09/08 02:35:06 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.6600 mIoU: 46.2500 mAcc: 59.9200 data_time: 0.0021 time: 0.1704 2023/09/08 02:35:56 - mmengine - INFO - Iter(train) [59550/60000] base_lr: 7.5001e-07 lr: 7.5001e-07 eta: 0:07:25 time: 0.9904 data_time: 0.0236 memory: 29160 grad_norm: 18.5179 loss: 6.6784 decode.loss_cls_ce: 1.4108 decode.loss_mask_ce: 0.7010 decode.loss_mask_dice: 1.2147 decode.d7.loss_cls_ce: 1.4463 decode.d7.loss_mask_ce: 0.7062 decode.d7.loss_mask_dice: 1.1995 2023/09/08 02:36:45 - mmengine - INFO - Iter(train) [59600/60000] base_lr: 6.6668e-07 lr: 6.6668e-07 eta: 0:06:35 time: 0.9931 data_time: 0.0233 memory: 29151 grad_norm: 17.3126 loss: 8.1041 decode.loss_cls_ce: 1.4633 decode.loss_mask_ce: 0.8821 decode.loss_mask_dice: 1.6880 decode.d7.loss_cls_ce: 1.5053 decode.d7.loss_mask_ce: 0.8772 decode.d7.loss_mask_dice: 1.6883 2023/09/08 02:37:35 - mmengine - INFO - Iter(train) [59650/60000] base_lr: 5.8334e-07 lr: 5.8334e-07 eta: 0:05:46 time: 0.9950 data_time: 0.0233 memory: 29329 grad_norm: 19.3781 loss: 7.1800 decode.loss_cls_ce: 1.4655 decode.loss_mask_ce: 0.7805 decode.loss_mask_dice: 1.3277 decode.d7.loss_cls_ce: 1.5255 decode.d7.loss_mask_ce: 0.7814 decode.d7.loss_mask_dice: 1.2994 2023/09/08 02:38:25 - mmengine - INFO - Iter(train) [59700/60000] base_lr: 5.0001e-07 lr: 5.0001e-07 eta: 0:04:56 time: 0.9934 data_time: 0.0236 memory: 29244 grad_norm: 20.7479 loss: 8.3082 decode.loss_cls_ce: 1.5711 decode.loss_mask_ce: 0.8191 decode.loss_mask_dice: 1.7569 decode.d7.loss_cls_ce: 1.5918 decode.d7.loss_mask_ce: 0.8196 decode.d7.loss_mask_dice: 1.7497 2023/09/08 02:39:14 - mmengine - INFO - Iter(train) [59750/60000] base_lr: 4.1667e-07 lr: 4.1667e-07 eta: 0:04:07 time: 0.9932 data_time: 0.0231 memory: 29244 grad_norm: 17.7139 loss: 8.4315 decode.loss_cls_ce: 1.5914 decode.loss_mask_ce: 0.8665 decode.loss_mask_dice: 1.7345 decode.d7.loss_cls_ce: 1.6346 decode.d7.loss_mask_ce: 0.8504 decode.d7.loss_mask_dice: 1.7540 2023/09/08 02:40:04 - mmengine - INFO - Iter(train) [59800/60000] base_lr: 3.3334e-07 lr: 3.3334e-07 eta: 0:03:17 time: 0.9937 data_time: 0.0236 memory: 29157 grad_norm: 17.8568 loss: 9.2859 decode.loss_cls_ce: 1.8884 decode.loss_mask_ce: 0.8937 decode.loss_mask_dice: 1.8351 decode.d7.loss_cls_ce: 1.8921 decode.d7.loss_mask_ce: 0.9082 decode.d7.loss_mask_dice: 1.8685 2023/09/08 02:40:54 - mmengine - INFO - Iter(train) [59850/60000] base_lr: 2.5000e-07 lr: 2.5000e-07 eta: 0:02:28 time: 0.9930 data_time: 0.0238 memory: 29204 grad_norm: 18.2606 loss: 8.1336 decode.loss_cls_ce: 1.5767 decode.loss_mask_ce: 0.8259 decode.loss_mask_dice: 1.6714 decode.d7.loss_cls_ce: 1.5492 decode.d7.loss_mask_ce: 0.8233 decode.d7.loss_mask_dice: 1.6871 2023/09/08 02:41:43 - mmengine - INFO - Iter(train) [59900/60000] base_lr: 1.6667e-07 lr: 1.6667e-07 eta: 0:01:38 time: 0.9939 data_time: 0.0243 memory: 29270 grad_norm: 20.2860 loss: 8.6568 decode.loss_cls_ce: 1.6805 decode.loss_mask_ce: 0.8916 decode.loss_mask_dice: 1.7700 decode.d7.loss_cls_ce: 1.6370 decode.d7.loss_mask_ce: 0.9016 decode.d7.loss_mask_dice: 1.7761 2023/09/08 02:42:33 - mmengine - INFO - Iter(train) [59950/60000] base_lr: 8.3335e-08 lr: 8.3335e-08 eta: 0:00:49 time: 0.9934 data_time: 0.0238 memory: 29229 grad_norm: 17.4719 loss: 8.5926 decode.loss_cls_ce: 1.5367 decode.loss_mask_ce: 0.9579 decode.loss_mask_dice: 1.7733 decode.d7.loss_cls_ce: 1.5955 decode.d7.loss_mask_ce: 0.9470 decode.d7.loss_mask_dice: 1.7822 2023/09/08 02:43:23 - mmengine - INFO - Exp name: san-vit-l14_coco-stuff164k-640x640_20230907_095536 2023/09/08 02:43:23 - mmengine - INFO - Iter(train) [60000/60000] base_lr: 0.0000e+00 lr: 0.0000e+00 eta: 0:00:00 time: 0.9917 data_time: 0.0231 memory: 29160 grad_norm: 18.7276 loss: 8.0145 decode.loss_cls_ce: 1.5904 decode.loss_mask_ce: 0.8248 decode.loss_mask_dice: 1.5603 decode.d7.loss_cls_ce: 1.6336 decode.d7.loss_mask_ce: 0.8267 decode.d7.loss_mask_dice: 1.5787 2023/09/08 02:43:23 - mmengine - INFO - Saving checkpoint at 60000 iterations 2023/09/08 02:43:38 - mmengine - INFO - Iter(val) [ 50/625] eta: 0:01:37 time: 0.1612 data_time: 0.0021 memory: 2646 2023/09/08 02:43:47 - mmengine - INFO - Iter(val) [100/625] eta: 0:01:29 time: 0.1670 data_time: 0.0019 memory: 2757 2023/09/08 02:43:55 - mmengine - INFO - Iter(val) [150/625] eta: 0:01:20 time: 0.1737 data_time: 0.0020 memory: 2646 2023/09/08 02:44:03 - mmengine - INFO - Iter(val) [200/625] eta: 0:01:11 time: 0.1731 data_time: 0.0021 memory: 2600 2023/09/08 02:44:12 - mmengine - INFO - Iter(val) [250/625] eta: 0:01:03 time: 0.1620 data_time: 0.0020 memory: 4253 2023/09/08 02:44:20 - mmengine - INFO - Iter(val) [300/625] eta: 0:00:55 time: 0.1713 data_time: 0.0021 memory: 2676 2023/09/08 02:44:29 - mmengine - INFO - Iter(val) [350/625] eta: 0:00:46 time: 0.1750 data_time: 0.0020 memory: 2646 2023/09/08 02:44:37 - mmengine - INFO - Iter(val) [400/625] eta: 0:00:38 time: 0.1716 data_time: 0.0021 memory: 2646 2023/09/08 02:44:46 - mmengine - INFO - Iter(val) [450/625] eta: 0:00:29 time: 0.1642 data_time: 0.0018 memory: 4605 2023/09/08 02:44:55 - mmengine - INFO - Iter(val) [500/625] eta: 0:00:21 time: 0.1649 data_time: 0.0020 memory: 2980 2023/09/08 02:45:03 - mmengine - INFO - Iter(val) [550/625] eta: 0:00:12 time: 0.1643 data_time: 0.0024 memory: 2705 2023/09/08 02:45:12 - mmengine - INFO - Iter(val) [600/625] eta: 0:00:04 time: 0.1608 data_time: 0.0022 memory: 2921 2023/09/08 02:45:18 - mmengine - INFO - per class results: 2023/09/08 02:45:18 - mmengine - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.76 | 92.63 | | bicycle | 66.75 | 81.45 | | car | 63.84 | 86.32 | | motorcycle | 84.61 | 92.09 | | airplane | 81.36 | 91.84 | | bus | 82.83 | 93.74 | | train | 80.98 | 95.48 | | truck | 64.07 | 76.28 | | boat | 61.76 | 87.24 | | traffic light | 65.55 | 84.96 | | fire hydrant | 81.25 | 89.43 | | stop sign | 92.13 | 97.3 | | parking meter | 73.16 | 83.8 | | bench | 57.23 | 74.06 | | bird | 73.97 | 87.15 | | cat | 82.21 | 89.09 | | dog | 70.0 | 75.9 | | horse | 83.49 | 92.47 | | sheep | 86.62 | 93.74 | | cow | 84.6 | 90.1 | | elephant | 91.29 | 95.62 | | bear | 90.97 | 94.58 | | zebra | 90.84 | 95.18 | | giraffe | 84.57 | 91.73 | | backpack | 29.64 | 68.18 | | umbrella | 81.24 | 88.65 | | handbag | 36.34 | 55.2 | | tie | 10.47 | 16.91 | | suitcase | 69.06 | 82.89 | | frisbee | 70.66 | 87.34 | | skis | 39.46 | 63.59 | | snowboard | 63.14 | 74.16 | | sports ball | 53.35 | 78.73 | | kite | 61.73 | 74.25 | | baseball bat | 46.41 | 69.75 | | baseball glove | 65.25 | 87.63 | | skateboard | 66.74 | 88.34 | | surfboard | 80.8 | 89.73 | | tennis racket | 74.95 | 84.57 | | bottle | 47.3 | 65.45 | | wine glass | 48.48 | 69.72 | | cup | 44.52 | 63.51 | | fork | 40.84 | 56.65 | | knife | 28.12 | 38.02 | | spoon | 41.19 | 56.57 | | bowl | 38.81 | 53.0 | | banana | 64.83 | 90.43 | | apple | 48.69 | 60.26 | | sandwich | 47.03 | 59.15 | | orange | 67.77 | 71.86 | | broccoli | 52.84 | 67.68 | | carrot | 51.98 | 67.11 | | hot dog | 53.4 | 63.1 | | pizza | 67.28 | 78.61 | | donut | 75.28 | 89.83 | | cake | 71.79 | 85.1 | | chair | 47.63 | 72.17 | | couch | 56.82 | 75.4 | | potted plant | 33.58 | 49.25 | | bed | 65.22 | 85.02 | | dining table | 44.75 | 72.08 | | toilet | 78.64 | 93.34 | | tv | 70.08 | 82.81 | | laptop | 72.94 | 87.72 | | mouse | 67.82 | 79.01 | | remote | 59.84 | 72.36 | | keyboard | 61.91 | 73.94 | | cell phone | 68.46 | 89.2 | | microwave | 67.2 | 79.34 | | oven | 55.23 | 80.14 | | toaster | 67.43 | 90.8 | | sink | 47.29 | 83.47 | | refrigerator | 77.35 | 92.27 | | book | 49.26 | 63.6 | | clock | 70.88 | 79.65 | | vase | 54.08 | 83.4 | | scissors | 77.75 | 92.04 | | teddy bear | 78.14 | 87.57 | | hair drier | 40.59 | 56.94 | | toothbrush | 32.48 | 81.43 | | banner | 29.04 | 63.48 | | blanket | 17.83 | 22.81 | | branch | 5.3 | 6.65 | | bridge | 32.69 | 52.19 | | building-other | 51.9 | 70.62 | | bush | 31.9 | 47.89 | | cabinet | 50.62 | 70.06 | | cage | 9.53 | 13.52 | | cardboard | 37.61 | 57.22 | | carpet | 49.89 | 73.69 | | ceiling-other | 61.81 | 78.62 | | ceiling-tile | 26.75 | 28.63 | | cloth | 0.7 | 1.26 | | clothes | 18.95 | 29.12 | | clouds | 47.47 | 66.02 | | counter | 24.95 | 50.92 | | cupboard | 0.0 | 0.01 | | curtain | 63.53 | 79.74 | | desk-stuff | 36.23 | 54.08 | | dirt | 39.27 | 57.04 | | door-stuff | 40.02 | 63.07 | | fence | 35.04 | 67.21 | | floor-marble | 9.29 | 11.25 | | floor-other | 20.92 | 32.17 | | floor-stone | 2.9 | 3.52 | | floor-tile | 56.89 | 66.15 | | floor-wood | 64.38 | 78.72 | | flower | 40.63 | 61.45 | | fog | 11.78 | 13.79 | | food-other | 29.0 | 46.59 | | fruit | 31.29 | 62.58 | | furniture-other | 12.52 | 18.0 | | grass | 68.05 | 80.87 | | gravel | 26.28 | 39.92 | | ground-other | 2.41 | 3.54 | | hill | 13.88 | 21.77 | | house | 25.46 | 30.4 | | leaves | 24.93 | 32.04 | | light | 37.06 | 53.81 | | mat | 3.61 | 7.93 | | metal | 29.83 | 40.22 | | mirror-stuff | 55.16 | 79.12 | | moss | 0.0 | 0.0 | | mountain | 54.93 | 74.97 | | mud | 13.39 | 18.58 | | napkin | 10.11 | 14.4 | | net | 35.86 | 66.33 | | paper | 28.13 | 41.41 | | pavement | 51.37 | 71.04 | | pillow | 7.7 | 12.6 | | plant-other | 18.85 | 32.33 | | plastic | 16.79 | 22.16 | | platform | 23.99 | 36.11 | | playingfield | 70.92 | 92.95 | | railing | 6.88 | 16.55 | | railroad | 57.36 | 76.31 | | river | 41.21 | 63.58 | | road | 65.92 | 79.61 | | rock | 45.08 | 69.91 | | roof | 22.95 | 33.98 | | rug | 29.08 | 37.23 | | salad | 7.84 | 10.95 | | sand | 61.21 | 69.09 | | sea | 85.51 | 91.05 | | shelf | 25.18 | 35.59 | | sky-other | 70.35 | 83.88 | | skyscraper | 33.86 | 50.05 | | snow | 88.64 | 95.37 | | solid-other | 0.0 | 0.0 | | stairs | 24.97 | 59.27 | | stone | 0.02 | 0.02 | | straw | 19.31 | 23.07 | | structural-other | 0.08 | 0.09 | | table | 18.47 | 25.75 | | tent | 7.75 | 12.13 | | textile-other | 7.64 | 9.29 | | towel | 30.68 | 38.52 | | tree | 72.02 | 84.53 | | vegetable | 37.49 | 50.82 | | wall-brick | 42.05 | 53.27 | | wall-concrete | 49.01 | 60.78 | | wall-other | 16.81 | 37.51 | | wall-panel | 0.75 | 0.78 | | wall-stone | 25.86 | 34.79 | | wall-tile | 64.77 | 81.95 | | wall-wood | 35.69 | 50.93 | | water-other | 23.4 | 36.07 | | waterdrops | 3.12 | 5.31 | | window-blind | 49.02 | 62.45 | | window-other | 43.0 | 72.09 | | wood | 22.71 | 32.3 | +------------------+-------+-------+ 2023/09/08 02:45:18 - mmengine - INFO - Iter(val) [625/625] aAcc: 69.6800 mIoU: 46.2600 mAcc: 59.9200 data_time: 0.0021 time: 0.1702