2024/04/09 00:12:10 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] CUDA available: True numpy_random_seed: 779397422 GPU 0,1,2,3: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 9.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.5 - 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_61,code=sm_61;-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;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.5, CUDNN_VERSION=8.3.2, 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 -DEDGE_PROFILER_USE_KINETO -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-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=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.7.0 MMEngine: 0.8.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl', 'port': 29320} seed: 779397422 Distributed launcher: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2024/04/09 00:12:10 - mmengine - INFO - Config: default_scope = 'embodiedscan' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3), sampler_seed=dict(type='DistSamplerSeedHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl', port=29320)) log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = True n_points = 100000 backend_args = None metainfo = dict(classes='all') model = dict( type='SparseFeatureFusion3DGrounder', num_queries=256, voxel_size=0.01, data_preprocessor=dict( type='Det3DDataPreprocessor', mean=[ 123.675, 116.28, 103.53, ], std=[ 58.395, 57.12, 57.375, ], bgr_to_rgb=True, pad_size_divisor=32), backbone=dict( type='mmdet.ResNet', depth=50, base_channels=16, num_stages=4, out_indices=( 0, 1, 2, 3, ), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'), style='pytorch'), backbone_lidar=dict(type='MinkResNet', in_channels=3, depth=34), use_xyz_feat=True, neck_3d=dict( type='MinkNeck', num_classes=1, in_channels=[ 128, 256, 512, 1024, ], out_channels=256, voxel_size=0.01, pts_prune_threshold=1000), decoder=dict( num_layers=6, return_intermediate=True, layer_cfg=dict( self_attn_cfg=dict(embed_dims=256, num_heads=8, dropout=0.0), cross_attn_text_cfg=dict(embed_dims=256, num_heads=8, dropout=0.0), cross_attn_cfg=dict(embed_dims=256, num_heads=8, dropout=0.0), ffn_cfg=dict( embed_dims=256, feedforward_channels=2048, ffn_drop=0.0)), post_norm_cfg=None), bbox_head=dict( type='GroundingHead', num_classes=256, sync_cls_avg_factor=True, decouple_bbox_loss=True, decouple_groups=4, share_pred_layer=True, decouple_weights=[ 0.2, 0.2, 0.2, 0.4, ], contrastive_cfg=dict(max_text_len=256, log_scale='auto', bias=True), loss_cls=dict( type='mmdet.FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict( type='BBoxCDLoss', mode='l1', loss_weight=1.0, group='g8')), coord_type='DEPTH', train_cfg=dict( assigner=dict( type='HungarianAssigner3D', match_costs=[ dict(type='BinaryFocalLossCost', weight=1.0), dict(type='BBox3DL1Cost', weight=2.0), dict(type='IoU3DCost', weight=2.0), ])), test_cfg=None) dataset_type = 'MultiView3DGroundingDataset' data_root = 'data' train_pipeline = [ dict(type='LoadAnnotations3D'), dict( type='MultiViewPipeline', n_images=20, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict(type='AggregateMultiViewPoints', coord_type='DEPTH'), dict(type='PointSample', num_points=100000), dict( type='GlobalRotScaleTrans', rot_range=[ -0.087266, 0.087266, ], scale_ratio_range=[ 0.9, 1.1, ], translation_std=[ 0.1, 0.1, 0.1, ], shift_height=False), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ] test_pipeline = [ dict(type='LoadAnnotations3D'), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict(type='AggregateMultiViewPoints', coord_type='DEPTH'), dict(type='PointSample', num_points=100000), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ] train_dataloader = dict( batch_size=12, num_workers=12, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=1, dataset=dict( type='MultiView3DGroundingDataset', data_root='data', ann_file='embodiedscan_infos_train.pkl', vg_file='embodiedscan_train_vg_all.json', metainfo=dict(classes='all'), pipeline=[ dict(type='LoadAnnotations3D'), dict( type='MultiViewPipeline', n_images=20, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict( type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict(type='AggregateMultiViewPoints', coord_type='DEPTH'), dict(type='PointSample', num_points=100000), dict( type='GlobalRotScaleTrans', rot_range=[ -0.087266, 0.087266, ], scale_ratio_range=[ 0.9, 1.1, ], translation_std=[ 0.1, 0.1, 0.1, ], shift_height=False), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=False, filter_empty_gt=True, box_type_3d='Euler-Depth'))) val_dataloader = dict( batch_size=12, num_workers=12, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='MultiView3DGroundingDataset', data_root='data', ann_file='embodiedscan_infos_val.pkl', vg_file='embodiedscan_val_vg_all.json', metainfo=dict(classes='all'), pipeline=[ dict(type='LoadAnnotations3D'), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict(type='AggregateMultiViewPoints', coord_type='DEPTH'), dict(type='PointSample', num_points=100000), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth')) test_dataloader = dict( batch_size=12, num_workers=12, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='MultiView3DGroundingDataset', data_root='data', ann_file='embodiedscan_infos_test.pkl', vg_file='embodiedscan_test_vg_all.json', metainfo=dict(classes='all'), pipeline=[ dict(type='LoadAnnotations3D'), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict(type='AggregateMultiViewPoints', coord_type='DEPTH'), dict(type='PointSample', num_points=100000), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth')) val_evaluator = dict(type='GroundingMetric') test_evaluator = dict(type='GroundingMetric', format_only=True) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=12) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') lr = 0.0005 optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='AdamW', lr=0.0005, weight_decay=0.0005), paramwise_cfg=dict( custom_keys=dict( text_encoder=dict(lr_mult=0.0), decoder=dict(lr_mult=0.1, decay_mult=1.0))), clip_grad=dict(max_norm=10, norm_type=2)) param_scheduler = dict( type='MultiStepLR', begin=0, end=12, by_epoch=True, milestones=[ 8, 11, ], gamma=0.1) custom_hooks = [ dict(type='EmptyCacheHook', after_iter=True), ] find_unused_parameters = True launcher = 'slurm' work_dir = '/mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-grounding-complex-all' 2024/04/09 00:12:10 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "vis_backend" registry tree. As a workaround, the current "vis_backend" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:14:19 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "hook" registry tree. As a workaround, the current "hook" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:14:20 - 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 (NORMAL ) EmptyCacheHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train: (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2024/04/09 00:14:20 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "loop" registry tree. As a workaround, the current "loop" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:18:16 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:18:16 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optimizer wrapper constructor" registry tree. As a workaround, the current "optimizer wrapper constructor" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.word_embeddings.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.word_embeddings.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.word_embeddings.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.position_embeddings.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.position_embeddings.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.position_embeddings.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.token_type_embeddings.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.token_type_embeddings.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.token_type_embeddings.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.embeddings.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.0.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.1.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.2.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.3.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.4.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.5.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.6.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:16 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.7.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.8.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.9.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.10.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.query.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.key.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.self.value.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.attention.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.intermediate.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.encoder.layer.11.output.LayerNorm.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.weight:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.weight:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.bias:lr=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- text_encoder.pooler.dense.bias:lr_mult=0.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.0.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.1.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.2.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.3.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.4.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn_text.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.in_proj_bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.cross_attn.attn.out_proj.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.0.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.ffn.layers.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.2.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.norms.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.layers.5.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.self_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.0.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.1.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.weight:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.weight:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.weight:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.bias:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.bias:weight_decay=0.0005 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.bias:lr_mult=0.1 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.cross_posembed.position_embedding_head.3.bias:decay_mult=1.0 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.norm.weight:lr=5e-05 2024/04/09 00:18:17 - mmengine - INFO - paramwise_options -- decoder.norm.weight:weight_decay=0.0005 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.weight:lr_mult=0.1 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.weight:decay_mult=1.0 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.bias:lr=5e-05 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.bias:weight_decay=0.0005 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.bias:lr_mult=0.1 2024/04/09 00:18:18 - mmengine - INFO - paramwise_options -- decoder.norm.bias:decay_mult=1.0 2024/04/09 00:18:18 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optimizer" registry tree. As a workaround, the current "optimizer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:18:18 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optim_wrapper" registry tree. As a workaround, the current "optim_wrapper" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:18:18 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:19:13 - mmengine - WARNING - The prefix is not set in metric class GroundingMetric. 2024/04/09 00:19:14 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/09 00:19:14 - mmengine - INFO - load model from: torchvision://resnet50 2024/04/09 00:19:14 - mmengine - INFO - Loads checkpoint by torchvision backend from path: torchvision://resnet50 2024/04/09 00:19:21 - mmengine - WARNING - The model and loaded state dict do not match exactly size mismatch for conv1.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from checkpoint, the shape in current model is torch.Size([16, 3, 7, 7]). size mismatch for bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 16, 1, 1]). size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.0.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.0.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.0.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.0.downsample.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 64, 1, 1]). size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.1.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.1.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 64, 1, 1]). size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.2.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.2.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 64, 1, 1]). size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.0.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.0.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.0.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 64, 1, 1]). size mismatch for layer2.0.downsample.1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.1.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.1.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.2.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.2.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.3.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.3.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]). size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.0.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.0.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.0.weight: copying a param with shape torch.Size([1024, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 1, 1]). size mismatch for layer3.0.downsample.1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.1.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.1.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.2.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.2.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.3.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.3.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.4.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.4.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.5.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.5.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]). size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.0.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.0.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.0.weight: copying a param with shape torch.Size([2048, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 256, 1, 1]). size mismatch for layer4.0.downsample.1.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.1.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.1.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.2.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.2.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). unexpected key in source state_dict: fc.weight, fc.bias Name of parameter - Initialization information backbone.conv1.weight - torch.Size([16, 3, 7, 7]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.conv1.weight - torch.Size([16, 16, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.downsample.0.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.downsample.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.0.downsample.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.conv1.weight - torch.Size([16, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.1.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.conv1.weight - torch.Size([16, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer1.2.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.conv1.weight - torch.Size([32, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.downsample.0.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.downsample.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.0.downsample.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.1.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.2.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer2.3.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.conv1.weight - torch.Size([64, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.downsample.0.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.downsample.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.0.downsample.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.1.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.2.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.3.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.4.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer3.5.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.conv1.weight - torch.Size([128, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.downsample.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.0.downsample.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.conv1.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.1.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.conv1.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone.layer4.2.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.conv1.kernel - torch.Size([27, 3, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.norm1.weight - torch.Size([1, 64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.norm1.bias - torch.Size([1, 64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.0.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.0.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.downsample.0.kernel - torch.Size([1, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.0.downsample.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.0.downsample.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.1.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.1.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.1.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.1.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.1.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.1.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.2.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.2.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.2.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.2.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer1.2.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer1.2.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.conv1.kernel - torch.Size([27, 64, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.0.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.0.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.downsample.0.kernel - torch.Size([1, 64, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.0.downsample.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.0.downsample.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.1.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.1.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.1.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.1.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.1.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.1.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.2.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.2.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.2.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.2.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.2.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.2.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.3.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.3.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.3.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.3.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer2.3.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer2.3.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.conv1.kernel - torch.Size([27, 128, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.0.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.0.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.downsample.0.kernel - torch.Size([1, 128, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.0.downsample.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.0.downsample.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.1.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.1.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.1.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.1.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.1.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.1.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.2.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.2.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.2.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.2.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.2.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.2.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.3.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.3.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.3.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.3.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.3.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.3.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.4.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.4.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.4.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.4.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.4.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.4.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.5.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.5.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.5.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.5.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer3.5.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer3.5.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.conv1.kernel - torch.Size([27, 256, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.0.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.0.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.downsample.0.kernel - torch.Size([1, 256, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.0.downsample.1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.0.downsample.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.1.conv1.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.1.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.1.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.1.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.1.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.1.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.2.conv1.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.2.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.2.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.2.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_lidar.layer4.2.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder backbone_lidar.layer4.2.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_0.0.kernel - torch.Size([27, 128, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_0.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_0.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.0.kernel - torch.Size([8, 256, 128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.4.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_1.4.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_1.0.kernel - torch.Size([27, 256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_1.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_1.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.0.kernel - torch.Size([8, 512, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.3.kernel - torch.Size([27, 256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.4.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_2.4.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_2.0.kernel - torch.Size([27, 512, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_2.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_2.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.0.kernel - torch.Size([8, 1024, 512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.3.kernel - torch.Size([27, 512, 512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.4.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.up_block_3.4.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_3.0.kernel - torch.Size([27, 1024, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_3.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.out_block_3.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder neck_3d.conv_cls.kernel - torch.Size([256, 1]): Initialized by user-defined `init_weights` in MinkNeck neck_3d.conv_cls.bias - torch.Size([1, 1]): Initialized by user-defined `init_weights` in MinkNeck bbox_head.cls_branches.0.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder bbox_head.reg_branches.0.0.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder bbox_head.reg_branches.0.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder bbox_head.reg_branches.0.2.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder bbox_head.reg_branches.0.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder bbox_head.reg_branches.0.4.weight - torch.Size([9, 256]): Initialized by user-defined `init_weights` in GroundingHead bbox_head.reg_branches.0.4.bias - torch.Size([9]): Initialized by user-defined `init_weights` in GroundingHead text_encoder.embeddings.word_embeddings.weight - torch.Size([50265, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.embeddings.position_embeddings.weight - torch.Size([514, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.embeddings.token_type_embeddings.weight - torch.Size([1, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.embeddings.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.embeddings.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.0.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.1.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.2.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.3.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.4.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.5.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.6.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.7.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.8.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.9.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.10.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.query.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.query.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.key.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.key.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.value.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.self.value.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.output.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.attention.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.intermediate.dense.weight - torch.Size([3072, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.intermediate.dense.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.output.dense.weight - torch.Size([768, 3072]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.output.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.output.LayerNorm.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.encoder.layer.11.output.LayerNorm.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.pooler.dense.weight - torch.Size([768, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_encoder.pooler.dense.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.0.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.1.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.2.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.3.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.4.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn_text.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn_text.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn_text.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn_text.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn.attn.in_proj_weight - torch.Size([768, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn.attn.in_proj_bias - torch.Size([768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn.attn.out_proj.weight - torch.Size([256, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.cross_attn.attn.out_proj.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.ffn.layers.0.0.weight - torch.Size([2048, 256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.ffn.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.ffn.layers.1.weight - torch.Size([256, 2048]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.ffn.layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.norms.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.layers.5.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.0.weight - torch.Size([256, 9, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.self_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.0.weight - torch.Size([256, 3, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.3.weight - torch.Size([256, 256, 1]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.cross_posembed.position_embedding_head.3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.norm.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder decoder.norm.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_feat_map.weight - torch.Size([256, 768]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder text_feat_map.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of SparseFeatureFusion3DGrounder 2024/04/09 00:19:21 - mmengine - INFO - Auto resumed from the latest checkpoint /mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-grounding-complex-all/epoch_7.pth. 2024/04/09 00:19:27 - mmengine - INFO - Load checkpoint from /mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-grounding-complex-all/epoch_7.pth 2024/04/09 00:19:27 - mmengine - INFO - resumed epoch: 7, iter: 17997 2024/04/09 00:19:27 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2024/04/09 00:19:27 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2024/04/09 00:19:27 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-grounding-complex-all. 2024/04/09 00:20:48 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 00:23:20 - mmengine - INFO - Epoch(train) [8][ 50/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 16:35:34 time: 4.6650 data_time: 0.7316 memory: 28847 grad_norm: 23.4562 loss: 6.1448 loss_cls: 0.7511 loss_bbox: 0.2531 d0.loss_cls: 0.8330 d0.loss_bbox: 0.2656 d1.loss_cls: 0.7851 d1.loss_bbox: 0.2489 d2.loss_cls: 0.7586 d2.loss_bbox: 0.2491 d3.loss_cls: 0.7530 d3.loss_bbox: 0.2508 d4.loss_cls: 0.7482 d4.loss_bbox: 0.2482 2024/04/09 00:26:10 - mmengine - INFO - Epoch(train) [8][ 100/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 14:16:28 time: 3.3928 data_time: 0.1731 memory: 28313 grad_norm: 22.4232 loss: 6.2645 loss_cls: 0.7665 loss_bbox: 0.2549 d0.loss_cls: 0.8386 d0.loss_bbox: 0.2668 d1.loss_cls: 0.7964 d1.loss_bbox: 0.2592 d2.loss_cls: 0.7698 d2.loss_bbox: 0.2596 d3.loss_cls: 0.7663 d3.loss_bbox: 0.2591 d4.loss_cls: 0.7707 d4.loss_bbox: 0.2567 2024/04/09 00:28:59 - mmengine - INFO - Epoch(train) [8][ 150/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 13:27:56 time: 3.3890 data_time: 0.1747 memory: 28492 grad_norm: 22.4997 loss: 6.1214 loss_cls: 0.7486 loss_bbox: 0.2442 d0.loss_cls: 0.8461 d0.loss_bbox: 0.2584 d1.loss_cls: 0.7799 d1.loss_bbox: 0.2487 d2.loss_cls: 0.7650 d2.loss_bbox: 0.2410 d3.loss_cls: 0.7547 d3.loss_bbox: 0.2406 d4.loss_cls: 0.7547 d4.loss_bbox: 0.2395 2024/04/09 00:31:46 - mmengine - INFO - Epoch(train) [8][ 200/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:59:24 time: 3.3345 data_time: 0.1616 memory: 28211 grad_norm: 23.1599 loss: 6.3047 loss_cls: 0.7919 loss_bbox: 0.2328 d0.loss_cls: 0.8684 d0.loss_bbox: 0.2474 d1.loss_cls: 0.8317 d1.loss_bbox: 0.2364 d2.loss_cls: 0.8077 d2.loss_bbox: 0.2354 d3.loss_cls: 0.7978 d3.loss_bbox: 0.2304 d4.loss_cls: 0.7927 d4.loss_bbox: 0.2321 2024/04/09 00:34:58 - mmengine - INFO - Epoch(train) [8][ 250/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 13:02:11 time: 3.8351 data_time: 0.1852 memory: 28147 grad_norm: 22.4105 loss: 6.2753 loss_cls: 0.7751 loss_bbox: 0.2482 d0.loss_cls: 0.8566 d0.loss_bbox: 0.2574 d1.loss_cls: 0.8067 d1.loss_bbox: 0.2449 d2.loss_cls: 0.7918 d2.loss_bbox: 0.2433 d3.loss_cls: 0.7882 d3.loss_bbox: 0.2411 d4.loss_cls: 0.7771 d4.loss_bbox: 0.2449 2024/04/09 00:37:46 - mmengine - INFO - Epoch(train) [8][ 300/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:46:28 time: 3.3615 data_time: 0.2085 memory: 29044 grad_norm: 22.3721 loss: 6.2857 loss_cls: 0.7672 loss_bbox: 0.2464 d0.loss_cls: 0.8769 d0.loss_bbox: 0.2608 d1.loss_cls: 0.8099 d1.loss_bbox: 0.2481 d2.loss_cls: 0.7960 d2.loss_bbox: 0.2461 d3.loss_cls: 0.7834 d3.loss_bbox: 0.2409 d4.loss_cls: 0.7658 d4.loss_bbox: 0.2441 2024/04/09 00:40:36 - mmengine - INFO - Epoch(train) [8][ 350/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:35:38 time: 3.4013 data_time: 0.1839 memory: 29453 grad_norm: 22.7692 loss: 6.0850 loss_cls: 0.7490 loss_bbox: 0.2397 d0.loss_cls: 0.8308 d0.loss_bbox: 0.2521 d1.loss_cls: 0.7911 d1.loss_bbox: 0.2406 d2.loss_cls: 0.7693 d2.loss_bbox: 0.2357 d3.loss_cls: 0.7561 d3.loss_bbox: 0.2367 d4.loss_cls: 0.7469 d4.loss_bbox: 0.2371 2024/04/09 00:43:24 - mmengine - INFO - Epoch(train) [8][ 400/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:25:34 time: 3.3544 data_time: 0.1815 memory: 28151 grad_norm: 22.7912 loss: 6.2474 loss_cls: 0.8013 loss_bbox: 0.2249 d0.loss_cls: 0.8520 d0.loss_bbox: 0.2494 d1.loss_cls: 0.8199 d1.loss_bbox: 0.2360 d2.loss_cls: 0.7936 d2.loss_bbox: 0.2320 d3.loss_cls: 0.7871 d3.loss_bbox: 0.2326 d4.loss_cls: 0.7914 d4.loss_bbox: 0.2272 2024/04/09 00:46:14 - mmengine - INFO - Epoch(train) [8][ 450/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:18:21 time: 3.4079 data_time: 0.2063 memory: 29483 grad_norm: 22.4738 loss: 6.4078 loss_cls: 0.8046 loss_bbox: 0.2321 d0.loss_cls: 0.8758 d0.loss_bbox: 0.2526 d1.loss_cls: 0.8446 d1.loss_bbox: 0.2457 d2.loss_cls: 0.8288 d2.loss_bbox: 0.2380 d3.loss_cls: 0.8119 d3.loss_bbox: 0.2345 d4.loss_cls: 0.8057 d4.loss_bbox: 0.2334 2024/04/09 00:49:08 - mmengine - INFO - Epoch(train) [8][ 500/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:13:28 time: 3.4785 data_time: 0.1976 memory: 28761 grad_norm: 22.8420 loss: 6.2354 loss_cls: 0.7617 loss_bbox: 0.2525 d0.loss_cls: 0.8316 d0.loss_bbox: 0.2743 d1.loss_cls: 0.7938 d1.loss_bbox: 0.2595 d2.loss_cls: 0.7776 d2.loss_bbox: 0.2559 d3.loss_cls: 0.7650 d3.loss_bbox: 0.2530 d4.loss_cls: 0.7593 d4.loss_bbox: 0.2512 2024/04/09 00:52:00 - mmengine - INFO - Epoch(train) [8][ 550/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:08:08 time: 3.4352 data_time: 0.2193 memory: 29629 grad_norm: 22.8329 loss: 6.2342 loss_cls: 0.7770 loss_bbox: 0.2284 d0.loss_cls: 0.8681 d0.loss_bbox: 0.2517 d1.loss_cls: 0.8099 d1.loss_bbox: 0.2389 d2.loss_cls: 0.7953 d2.loss_bbox: 0.2321 d3.loss_cls: 0.7809 d3.loss_bbox: 0.2335 d4.loss_cls: 0.7887 d4.loss_bbox: 0.2297 2024/04/09 00:54:50 - mmengine - INFO - Epoch(train) [8][ 600/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 12:02:46 time: 3.4086 data_time: 0.2139 memory: 28229 grad_norm: 22.4831 loss: 6.1772 loss_cls: 0.7770 loss_bbox: 0.2260 d0.loss_cls: 0.8590 d0.loss_bbox: 0.2517 d1.loss_cls: 0.8106 d1.loss_bbox: 0.2288 d2.loss_cls: 0.7989 d2.loss_bbox: 0.2236 d3.loss_cls: 0.7797 d3.loss_bbox: 0.2271 d4.loss_cls: 0.7727 d4.loss_bbox: 0.2223 2024/04/09 00:57:41 - mmengine - INFO - Epoch(train) [8][ 650/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:57:50 time: 3.4121 data_time: 0.2062 memory: 28762 grad_norm: 22.5255 loss: 6.0473 loss_cls: 0.7369 loss_bbox: 0.2429 d0.loss_cls: 0.8309 d0.loss_bbox: 0.2585 d1.loss_cls: 0.7859 d1.loss_bbox: 0.2374 d2.loss_cls: 0.7526 d2.loss_bbox: 0.2397 d3.loss_cls: 0.7403 d3.loss_bbox: 0.2406 d4.loss_cls: 0.7417 d4.loss_bbox: 0.2398 2024/04/09 01:00:34 - mmengine - INFO - Epoch(train) [8][ 700/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:54:03 time: 3.4706 data_time: 0.1930 memory: 28974 grad_norm: 22.6887 loss: 6.3584 loss_cls: 0.7898 loss_bbox: 0.2454 d0.loss_cls: 0.8697 d0.loss_bbox: 0.2623 d1.loss_cls: 0.8310 d1.loss_bbox: 0.2465 d2.loss_cls: 0.8020 d2.loss_bbox: 0.2441 d3.loss_cls: 0.7864 d3.loss_bbox: 0.2437 d4.loss_cls: 0.7932 d4.loss_bbox: 0.2443 2024/04/09 01:03:16 - mmengine - INFO - Epoch(train) [8][ 750/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:47:11 time: 3.2330 data_time: 0.1899 memory: 28720 grad_norm: 23.4162 loss: 6.1864 loss_cls: 0.7714 loss_bbox: 0.2303 d0.loss_cls: 0.8564 d0.loss_bbox: 0.2523 d1.loss_cls: 0.8159 d1.loss_bbox: 0.2424 d2.loss_cls: 0.7857 d2.loss_bbox: 0.2351 d3.loss_cls: 0.7710 d3.loss_bbox: 0.2300 d4.loss_cls: 0.7655 d4.loss_bbox: 0.2304 2024/04/09 01:06:03 - mmengine - INFO - Epoch(train) [8][ 800/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:42:17 time: 3.3468 data_time: 0.1933 memory: 29449 grad_norm: 22.1874 loss: 6.2227 loss_cls: 0.7656 loss_bbox: 0.2478 d0.loss_cls: 0.8357 d0.loss_bbox: 0.2645 d1.loss_cls: 0.8007 d1.loss_bbox: 0.2538 d2.loss_cls: 0.7765 d2.loss_bbox: 0.2536 d3.loss_cls: 0.7695 d3.loss_bbox: 0.2493 d4.loss_cls: 0.7590 d4.loss_bbox: 0.2467 2024/04/09 01:08:43 - mmengine - INFO - Epoch(train) [8][ 850/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:35:43 time: 3.1854 data_time: 0.1856 memory: 28575 grad_norm: 22.8392 loss: 6.1113 loss_cls: 0.7456 loss_bbox: 0.2475 d0.loss_cls: 0.8231 d0.loss_bbox: 0.2622 d1.loss_cls: 0.7765 d1.loss_bbox: 0.2520 d2.loss_cls: 0.7651 d2.loss_bbox: 0.2488 d3.loss_cls: 0.7477 d3.loss_bbox: 0.2502 d4.loss_cls: 0.7438 d4.loss_bbox: 0.2490 2024/04/09 01:11:36 - mmengine - INFO - Epoch(train) [8][ 900/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:32:38 time: 3.4610 data_time: 0.2157 memory: 29012 grad_norm: 22.7148 loss: 6.2912 loss_cls: 0.7606 loss_bbox: 0.2572 d0.loss_cls: 0.8387 d0.loss_bbox: 0.2728 d1.loss_cls: 0.8045 d1.loss_bbox: 0.2665 d2.loss_cls: 0.7869 d2.loss_bbox: 0.2588 d3.loss_cls: 0.7710 d3.loss_bbox: 0.2567 d4.loss_cls: 0.7594 d4.loss_bbox: 0.2581 2024/04/09 01:14:42 - mmengine - INFO - Epoch(train) [8][ 950/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:32:15 time: 3.7170 data_time: 0.2006 memory: 28420 grad_norm: 22.1397 loss: 6.0763 loss_cls: 0.7375 loss_bbox: 0.2435 d0.loss_cls: 0.8164 d0.loss_bbox: 0.2581 d1.loss_cls: 0.7854 d1.loss_bbox: 0.2447 d2.loss_cls: 0.7556 d2.loss_bbox: 0.2409 d3.loss_cls: 0.7609 d3.loss_bbox: 0.2412 d4.loss_cls: 0.7499 d4.loss_bbox: 0.2423 2024/04/09 01:17:33 - mmengine - INFO - Epoch(train) [8][1000/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:28:48 time: 3.4331 data_time: 0.2213 memory: 28374 grad_norm: 23.0212 loss: 6.1819 loss_cls: 0.7601 loss_bbox: 0.2432 d0.loss_cls: 0.8384 d0.loss_bbox: 0.2646 d1.loss_cls: 0.7926 d1.loss_bbox: 0.2565 d2.loss_cls: 0.7648 d2.loss_bbox: 0.2491 d3.loss_cls: 0.7620 d3.loss_bbox: 0.2474 d4.loss_cls: 0.7513 d4.loss_bbox: 0.2521 2024/04/09 01:17:43 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 01:20:34 - mmengine - INFO - Epoch(train) [8][1050/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:27:11 time: 3.6238 data_time: 0.2123 memory: 28205 grad_norm: 22.6873 loss: 6.2621 loss_cls: 0.7749 loss_bbox: 0.2407 d0.loss_cls: 0.8631 d0.loss_bbox: 0.2590 d1.loss_cls: 0.8043 d1.loss_bbox: 0.2463 d2.loss_cls: 0.7838 d2.loss_bbox: 0.2442 d3.loss_cls: 0.7767 d3.loss_bbox: 0.2466 d4.loss_cls: 0.7797 d4.loss_bbox: 0.2429 2024/04/09 01:23:20 - mmengine - INFO - Epoch(train) [8][1100/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:22:41 time: 3.3150 data_time: 0.1969 memory: 28447 grad_norm: 22.1268 loss: 6.0473 loss_cls: 0.7464 loss_bbox: 0.2446 d0.loss_cls: 0.8200 d0.loss_bbox: 0.2527 d1.loss_cls: 0.7718 d1.loss_bbox: 0.2410 d2.loss_cls: 0.7528 d2.loss_bbox: 0.2425 d3.loss_cls: 0.7421 d3.loss_bbox: 0.2450 d4.loss_cls: 0.7425 d4.loss_bbox: 0.2457 2024/04/09 01:26:22 - mmengine - INFO - Epoch(train) [8][1150/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:21:02 time: 3.6313 data_time: 0.2126 memory: 28786 grad_norm: 21.3016 loss: 6.0013 loss_cls: 0.7333 loss_bbox: 0.2353 d0.loss_cls: 0.8243 d0.loss_bbox: 0.2652 d1.loss_cls: 0.7625 d1.loss_bbox: 0.2524 d2.loss_cls: 0.7508 d2.loss_bbox: 0.2361 d3.loss_cls: 0.7378 d3.loss_bbox: 0.2357 d4.loss_cls: 0.7297 d4.loss_bbox: 0.2381 2024/04/09 01:29:17 - mmengine - INFO - Epoch(train) [8][1200/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:18:13 time: 3.5027 data_time: 0.2073 memory: 28980 grad_norm: 22.7168 loss: 6.1561 loss_cls: 0.7651 loss_bbox: 0.2402 d0.loss_cls: 0.8488 d0.loss_bbox: 0.2515 d1.loss_cls: 0.8031 d1.loss_bbox: 0.2402 d2.loss_cls: 0.7743 d2.loss_bbox: 0.2383 d3.loss_cls: 0.7566 d3.loss_bbox: 0.2361 d4.loss_cls: 0.7632 d4.loss_bbox: 0.2387 2024/04/09 01:32:11 - mmengine - INFO - Epoch(train) [8][1250/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:15:19 time: 3.4928 data_time: 0.2487 memory: 29293 grad_norm: 22.9204 loss: 6.1578 loss_cls: 0.7604 loss_bbox: 0.2410 d0.loss_cls: 0.8508 d0.loss_bbox: 0.2549 d1.loss_cls: 0.8058 d1.loss_bbox: 0.2416 d2.loss_cls: 0.7730 d2.loss_bbox: 0.2374 d3.loss_cls: 0.7596 d3.loss_bbox: 0.2393 d4.loss_cls: 0.7530 d4.loss_bbox: 0.2409 2024/04/09 01:34:57 - mmengine - INFO - Epoch(train) [8][1300/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:11:02 time: 3.3069 data_time: 0.2019 memory: 28069 grad_norm: 22.9818 loss: 6.1492 loss_cls: 0.7449 loss_bbox: 0.2530 d0.loss_cls: 0.8212 d0.loss_bbox: 0.2671 d1.loss_cls: 0.7887 d1.loss_bbox: 0.2573 d2.loss_cls: 0.7610 d2.loss_bbox: 0.2516 d3.loss_cls: 0.7527 d3.loss_bbox: 0.2534 d4.loss_cls: 0.7482 d4.loss_bbox: 0.2502 2024/04/09 01:37:48 - mmengine - INFO - Epoch(train) [8][1350/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:07:42 time: 3.4239 data_time: 0.2134 memory: 28396 grad_norm: 21.4278 loss: 6.0795 loss_cls: 0.7444 loss_bbox: 0.2394 d0.loss_cls: 0.8288 d0.loss_bbox: 0.2538 d1.loss_cls: 0.7936 d1.loss_bbox: 0.2394 d2.loss_cls: 0.7637 d2.loss_bbox: 0.2350 d3.loss_cls: 0.7497 d3.loss_bbox: 0.2368 d4.loss_cls: 0.7538 d4.loss_bbox: 0.2411 2024/04/09 01:40:45 - mmengine - INFO - Epoch(train) [8][1400/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:05:11 time: 3.5380 data_time: 0.2063 memory: 28534 grad_norm: 21.9097 loss: 6.0429 loss_cls: 0.7284 loss_bbox: 0.2455 d0.loss_cls: 0.8197 d0.loss_bbox: 0.2631 d1.loss_cls: 0.7717 d1.loss_bbox: 0.2489 d2.loss_cls: 0.7519 d2.loss_bbox: 0.2463 d3.loss_cls: 0.7364 d3.loss_bbox: 0.2442 d4.loss_cls: 0.7426 d4.loss_bbox: 0.2441 2024/04/09 01:43:33 - mmengine - INFO - Epoch(train) [8][1450/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 11:01:26 time: 3.3553 data_time: 0.2081 memory: 28568 grad_norm: 21.7827 loss: 5.8625 loss_cls: 0.7237 loss_bbox: 0.2321 d0.loss_cls: 0.7941 d0.loss_bbox: 0.2397 d1.loss_cls: 0.7506 d1.loss_bbox: 0.2302 d2.loss_cls: 0.7353 d2.loss_bbox: 0.2281 d3.loss_cls: 0.7276 d3.loss_bbox: 0.2309 d4.loss_cls: 0.7429 d4.loss_bbox: 0.2274 2024/04/09 01:46:23 - mmengine - INFO - Epoch(train) [8][1500/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:58:04 time: 3.4061 data_time: 0.2059 memory: 28184 grad_norm: 23.4859 loss: 6.0032 loss_cls: 0.7494 loss_bbox: 0.2221 d0.loss_cls: 0.8263 d0.loss_bbox: 0.2412 d1.loss_cls: 0.7918 d1.loss_bbox: 0.2254 d2.loss_cls: 0.7711 d2.loss_bbox: 0.2248 d3.loss_cls: 0.7553 d3.loss_bbox: 0.2210 d4.loss_cls: 0.7550 d4.loss_bbox: 0.2197 2024/04/09 01:49:26 - mmengine - INFO - Epoch(train) [8][1550/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:56:19 time: 3.6657 data_time: 0.2133 memory: 28825 grad_norm: 23.4384 loss: 6.0301 loss_cls: 0.7422 loss_bbox: 0.2333 d0.loss_cls: 0.8403 d0.loss_bbox: 0.2454 d1.loss_cls: 0.7887 d1.loss_bbox: 0.2306 d2.loss_cls: 0.7649 d2.loss_bbox: 0.2298 d3.loss_cls: 0.7499 d3.loss_bbox: 0.2294 d4.loss_cls: 0.7470 d4.loss_bbox: 0.2287 2024/04/09 01:52:17 - mmengine - INFO - Epoch(train) [8][1600/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:53:00 time: 3.4125 data_time: 0.2538 memory: 28777 grad_norm: 23.1836 loss: 6.0828 loss_cls: 0.7449 loss_bbox: 0.2493 d0.loss_cls: 0.8108 d0.loss_bbox: 0.2645 d1.loss_cls: 0.7757 d1.loss_bbox: 0.2534 d2.loss_cls: 0.7622 d2.loss_bbox: 0.2557 d3.loss_cls: 0.7420 d3.loss_bbox: 0.2450 d4.loss_cls: 0.7385 d4.loss_bbox: 0.2410 2024/04/09 01:55:04 - mmengine - INFO - Epoch(train) [8][1650/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:49:19 time: 3.3440 data_time: 0.2322 memory: 29249 grad_norm: 21.6370 loss: 5.7996 loss_cls: 0.7175 loss_bbox: 0.2333 d0.loss_cls: 0.7917 d0.loss_bbox: 0.2420 d1.loss_cls: 0.7427 d1.loss_bbox: 0.2311 d2.loss_cls: 0.7180 d2.loss_bbox: 0.2292 d3.loss_cls: 0.7192 d3.loss_bbox: 0.2320 d4.loss_cls: 0.7130 d4.loss_bbox: 0.2300 2024/04/09 01:57:56 - mmengine - INFO - Epoch(train) [8][1700/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:46:15 time: 3.4449 data_time: 0.1934 memory: 28740 grad_norm: 23.8130 loss: 5.9267 loss_cls: 0.7266 loss_bbox: 0.2292 d0.loss_cls: 0.8138 d0.loss_bbox: 0.2479 d1.loss_cls: 0.7638 d1.loss_bbox: 0.2377 d2.loss_cls: 0.7466 d2.loss_bbox: 0.2317 d3.loss_cls: 0.7339 d3.loss_bbox: 0.2324 d4.loss_cls: 0.7317 d4.loss_bbox: 0.2313 2024/04/09 02:00:50 - mmengine - INFO - Epoch(train) [8][1750/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:43:23 time: 3.4811 data_time: 0.2423 memory: 28290 grad_norm: 23.0728 loss: 6.2765 loss_cls: 0.7614 loss_bbox: 0.2513 d0.loss_cls: 0.8632 d0.loss_bbox: 0.2668 d1.loss_cls: 0.8188 d1.loss_bbox: 0.2544 d2.loss_cls: 0.7828 d2.loss_bbox: 0.2513 d3.loss_cls: 0.7624 d3.loss_bbox: 0.2513 d4.loss_cls: 0.7651 d4.loss_bbox: 0.2478 2024/04/09 02:03:36 - mmengine - INFO - Epoch(train) [8][1800/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:39:39 time: 3.3125 data_time: 0.2037 memory: 29334 grad_norm: 22.0908 loss: 6.2491 loss_cls: 0.7741 loss_bbox: 0.2416 d0.loss_cls: 0.8443 d0.loss_bbox: 0.2623 d1.loss_cls: 0.8078 d1.loss_bbox: 0.2502 d2.loss_cls: 0.7879 d2.loss_bbox: 0.2449 d3.loss_cls: 0.7711 d3.loss_bbox: 0.2425 d4.loss_cls: 0.7755 d4.loss_bbox: 0.2469 2024/04/09 02:06:28 - mmengine - INFO - Epoch(train) [8][1850/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:36:35 time: 3.4383 data_time: 0.2215 memory: 28551 grad_norm: 22.7731 loss: 6.4385 loss_cls: 0.7866 loss_bbox: 0.2699 d0.loss_cls: 0.8521 d0.loss_bbox: 0.2771 d1.loss_cls: 0.8123 d1.loss_bbox: 0.2665 d2.loss_cls: 0.8013 d2.loss_bbox: 0.2611 d3.loss_cls: 0.7910 d3.loss_bbox: 0.2618 d4.loss_cls: 0.7930 d4.loss_bbox: 0.2659 2024/04/09 02:09:16 - mmengine - INFO - Epoch(train) [8][1900/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:33:09 time: 3.3574 data_time: 0.2265 memory: 29110 grad_norm: 21.8257 loss: 6.0551 loss_cls: 0.7363 loss_bbox: 0.2451 d0.loss_cls: 0.8207 d0.loss_bbox: 0.2549 d1.loss_cls: 0.7792 d1.loss_bbox: 0.2469 d2.loss_cls: 0.7544 d2.loss_bbox: 0.2486 d3.loss_cls: 0.7394 d3.loss_bbox: 0.2474 d4.loss_cls: 0.7399 d4.loss_bbox: 0.2423 2024/04/09 02:12:07 - mmengine - INFO - Epoch(train) [8][1950/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:30:03 time: 3.4219 data_time: 0.2248 memory: 28493 grad_norm: 23.4210 loss: 6.0164 loss_cls: 0.7447 loss_bbox: 0.2319 d0.loss_cls: 0.8231 d0.loss_bbox: 0.2507 d1.loss_cls: 0.7749 d1.loss_bbox: 0.2357 d2.loss_cls: 0.7617 d2.loss_bbox: 0.2314 d3.loss_cls: 0.7487 d3.loss_bbox: 0.2340 d4.loss_cls: 0.7431 d4.loss_bbox: 0.2363 2024/04/09 02:14:57 - mmengine - INFO - Epoch(train) [8][2000/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:26:51 time: 3.3990 data_time: 0.2321 memory: 28950 grad_norm: 22.1589 loss: 6.0409 loss_cls: 0.7715 loss_bbox: 0.2196 d0.loss_cls: 0.8380 d0.loss_bbox: 0.2307 d1.loss_cls: 0.7970 d1.loss_bbox: 0.2239 d2.loss_cls: 0.7766 d2.loss_bbox: 0.2217 d3.loss_cls: 0.7632 d3.loss_bbox: 0.2186 d4.loss_cls: 0.7622 d4.loss_bbox: 0.2178 2024/04/09 02:15:07 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 02:17:47 - mmengine - INFO - Epoch(train) [8][2050/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:23:39 time: 3.3954 data_time: 0.2344 memory: 29220 grad_norm: 22.7132 loss: 6.2676 loss_cls: 0.7632 loss_bbox: 0.2547 d0.loss_cls: 0.8457 d0.loss_bbox: 0.2848 d1.loss_cls: 0.7953 d1.loss_bbox: 0.2595 d2.loss_cls: 0.7745 d2.loss_bbox: 0.2517 d3.loss_cls: 0.7637 d3.loss_bbox: 0.2592 d4.loss_cls: 0.7567 d4.loss_bbox: 0.2585 2024/04/09 02:20:38 - mmengine - INFO - Epoch(train) [8][2100/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:20:36 time: 3.4241 data_time: 0.2082 memory: 28413 grad_norm: 22.3156 loss: 6.0579 loss_cls: 0.7327 loss_bbox: 0.2415 d0.loss_cls: 0.8342 d0.loss_bbox: 0.2513 d1.loss_cls: 0.7828 d1.loss_bbox: 0.2427 d2.loss_cls: 0.7664 d2.loss_bbox: 0.2396 d3.loss_cls: 0.7486 d3.loss_bbox: 0.2383 d4.loss_cls: 0.7406 d4.loss_bbox: 0.2391 2024/04/09 02:23:26 - mmengine - INFO - Epoch(train) [8][2150/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:17:20 time: 3.3672 data_time: 0.2135 memory: 28697 grad_norm: 22.9390 loss: 6.2100 loss_cls: 0.7594 loss_bbox: 0.2456 d0.loss_cls: 0.8345 d0.loss_bbox: 0.2628 d1.loss_cls: 0.7987 d1.loss_bbox: 0.2502 d2.loss_cls: 0.7745 d2.loss_bbox: 0.2518 d3.loss_cls: 0.7649 d3.loss_bbox: 0.2524 d4.loss_cls: 0.7676 d4.loss_bbox: 0.2477 2024/04/09 02:26:17 - mmengine - INFO - Epoch(train) [8][2200/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:14:15 time: 3.4129 data_time: 0.2298 memory: 28364 grad_norm: 22.9287 loss: 6.0149 loss_cls: 0.7251 loss_bbox: 0.2465 d0.loss_cls: 0.8223 d0.loss_bbox: 0.2637 d1.loss_cls: 0.7670 d1.loss_bbox: 0.2549 d2.loss_cls: 0.7423 d2.loss_bbox: 0.2501 d3.loss_cls: 0.7294 d3.loss_bbox: 0.2458 d4.loss_cls: 0.7214 d4.loss_bbox: 0.2464 2024/04/09 02:29:07 - mmengine - INFO - Epoch(train) [8][2250/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:11:07 time: 3.3948 data_time: 0.2353 memory: 27983 grad_norm: 21.7562 loss: 6.1238 loss_cls: 0.7526 loss_bbox: 0.2398 d0.loss_cls: 0.8308 d0.loss_bbox: 0.2628 d1.loss_cls: 0.7894 d1.loss_bbox: 0.2478 d2.loss_cls: 0.7669 d2.loss_bbox: 0.2443 d3.loss_cls: 0.7547 d3.loss_bbox: 0.2393 d4.loss_cls: 0.7557 d4.loss_bbox: 0.2396 2024/04/09 02:31:58 - mmengine - INFO - Epoch(train) [8][2300/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:08:07 time: 3.4251 data_time: 0.2228 memory: 28068 grad_norm: 22.2007 loss: 5.7987 loss_cls: 0.7074 loss_bbox: 0.2243 d0.loss_cls: 0.7961 d0.loss_bbox: 0.2386 d1.loss_cls: 0.7470 d1.loss_bbox: 0.2352 d2.loss_cls: 0.7317 d2.loss_bbox: 0.2309 d3.loss_cls: 0.7203 d3.loss_bbox: 0.2281 d4.loss_cls: 0.7113 d4.loss_bbox: 0.2279 2024/04/09 02:34:45 - mmengine - INFO - Epoch(train) [8][2350/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:04:46 time: 3.3320 data_time: 0.1974 memory: 28522 grad_norm: 22.7206 loss: 5.9661 loss_cls: 0.7303 loss_bbox: 0.2364 d0.loss_cls: 0.8071 d0.loss_bbox: 0.2559 d1.loss_cls: 0.7682 d1.loss_bbox: 0.2479 d2.loss_cls: 0.7530 d2.loss_bbox: 0.2344 d3.loss_cls: 0.7316 d3.loss_bbox: 0.2344 d4.loss_cls: 0.7336 d4.loss_bbox: 0.2333 2024/04/09 02:37:39 - mmengine - INFO - Epoch(train) [8][2400/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 10:02:00 time: 3.4834 data_time: 0.2205 memory: 28894 grad_norm: 22.2670 loss: 5.9493 loss_cls: 0.7270 loss_bbox: 0.2407 d0.loss_cls: 0.8051 d0.loss_bbox: 0.2491 d1.loss_cls: 0.7650 d1.loss_bbox: 0.2416 d2.loss_cls: 0.7476 d2.loss_bbox: 0.2388 d3.loss_cls: 0.7326 d3.loss_bbox: 0.2331 d4.loss_cls: 0.7326 d4.loss_bbox: 0.2358 2024/04/09 02:40:29 - mmengine - INFO - Epoch(train) [8][2450/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 9:58:57 time: 3.4091 data_time: 0.2284 memory: 28175 grad_norm: 21.1963 loss: 5.8275 loss_cls: 0.6956 loss_bbox: 0.2497 d0.loss_cls: 0.7722 d0.loss_bbox: 0.2623 d1.loss_cls: 0.7428 d1.loss_bbox: 0.2552 d2.loss_cls: 0.7126 d2.loss_bbox: 0.2468 d3.loss_cls: 0.7005 d3.loss_bbox: 0.2435 d4.loss_cls: 0.7016 d4.loss_bbox: 0.2447 2024/04/09 02:43:19 - mmengine - INFO - Epoch(train) [8][2500/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 9:55:52 time: 3.3933 data_time: 0.2001 memory: 29161 grad_norm: 22.1696 loss: 6.1130 loss_cls: 0.7478 loss_bbox: 0.2471 d0.loss_cls: 0.8358 d0.loss_bbox: 0.2609 d1.loss_cls: 0.7783 d1.loss_bbox: 0.2509 d2.loss_cls: 0.7561 d2.loss_bbox: 0.2465 d3.loss_cls: 0.7414 d3.loss_bbox: 0.2506 d4.loss_cls: 0.7469 d4.loss_bbox: 0.2508 2024/04/09 02:46:10 - mmengine - INFO - Epoch(train) [8][2550/2571] base_lr: 5.0000e-04 lr: 5.0000e-04 eta: 9:52:52 time: 3.4174 data_time: 0.1917 memory: 30032 grad_norm: 22.1207 loss: 6.2382 loss_cls: 0.7691 loss_bbox: 0.2388 d0.loss_cls: 0.8593 d0.loss_bbox: 0.2525 d1.loss_cls: 0.8122 d1.loss_bbox: 0.2449 d2.loss_cls: 0.7875 d2.loss_bbox: 0.2445 d3.loss_cls: 0.7788 d3.loss_bbox: 0.2381 d4.loss_cls: 0.7753 d4.loss_bbox: 0.2372 2024/04/09 02:47:07 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 02:47:07 - mmengine - INFO - Saving checkpoint at 8 epochs 2024/04/09 02:50:53 - mmengine - INFO - Epoch(train) [9][ 50/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:50:14 time: 4.1992 data_time: 0.6563 memory: 28985 grad_norm: 20.8449 loss: 5.7392 loss_cls: 0.7243 loss_bbox: 0.2054 d0.loss_cls: 0.7998 d0.loss_bbox: 0.2192 d1.loss_cls: 0.7625 d1.loss_bbox: 0.2068 d2.loss_cls: 0.7426 d2.loss_bbox: 0.2067 d3.loss_cls: 0.7299 d3.loss_bbox: 0.2020 d4.loss_cls: 0.7341 d4.loss_bbox: 0.2059 2024/04/09 02:53:42 - mmengine - INFO - Epoch(train) [9][ 100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:47:05 time: 3.3733 data_time: 0.2028 memory: 29156 grad_norm: 19.8811 loss: 5.8426 loss_cls: 0.7220 loss_bbox: 0.2253 d0.loss_cls: 0.8056 d0.loss_bbox: 0.2375 d1.loss_cls: 0.7607 d1.loss_bbox: 0.2229 d2.loss_cls: 0.7371 d2.loss_bbox: 0.2196 d3.loss_cls: 0.7411 d3.loss_bbox: 0.2218 d4.loss_cls: 0.7296 d4.loss_bbox: 0.2192 2024/04/09 02:56:34 - mmengine - INFO - Epoch(train) [9][ 150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:44:09 time: 3.4417 data_time: 0.1937 memory: 28637 grad_norm: 20.2651 loss: 6.0904 loss_cls: 0.7513 loss_bbox: 0.2343 d0.loss_cls: 0.8253 d0.loss_bbox: 0.2495 d1.loss_cls: 0.7952 d1.loss_bbox: 0.2420 d2.loss_cls: 0.7654 d2.loss_bbox: 0.2345 d3.loss_cls: 0.7586 d3.loss_bbox: 0.2386 d4.loss_cls: 0.7618 d4.loss_bbox: 0.2338 2024/04/09 02:59:25 - mmengine - INFO - Epoch(train) [9][ 200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:41:09 time: 3.4197 data_time: 0.2259 memory: 27882 grad_norm: 20.8295 loss: 5.7336 loss_cls: 0.7043 loss_bbox: 0.2169 d0.loss_cls: 0.8000 d0.loss_bbox: 0.2380 d1.loss_cls: 0.7491 d1.loss_bbox: 0.2241 d2.loss_cls: 0.7249 d2.loss_bbox: 0.2198 d3.loss_cls: 0.7159 d3.loss_bbox: 0.2167 d4.loss_cls: 0.7059 d4.loss_bbox: 0.2179 2024/04/09 03:02:17 - mmengine - INFO - Epoch(train) [9][ 250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:38:15 time: 3.4544 data_time: 0.2176 memory: 28478 grad_norm: 20.2778 loss: 5.7932 loss_cls: 0.7201 loss_bbox: 0.2224 d0.loss_cls: 0.8117 d0.loss_bbox: 0.2303 d1.loss_cls: 0.7568 d1.loss_bbox: 0.2229 d2.loss_cls: 0.7372 d2.loss_bbox: 0.2137 d3.loss_cls: 0.7268 d3.loss_bbox: 0.2125 d4.loss_cls: 0.7197 d4.loss_bbox: 0.2190 2024/04/09 03:05:08 - mmengine - INFO - Epoch(train) [9][ 300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:35:14 time: 3.4086 data_time: 0.2081 memory: 28314 grad_norm: 20.2730 loss: 5.6836 loss_cls: 0.7045 loss_bbox: 0.2074 d0.loss_cls: 0.8116 d0.loss_bbox: 0.2244 d1.loss_cls: 0.7569 d1.loss_bbox: 0.2090 d2.loss_cls: 0.7331 d2.loss_bbox: 0.2043 d3.loss_cls: 0.7174 d3.loss_bbox: 0.2048 d4.loss_cls: 0.7036 d4.loss_bbox: 0.2065 2024/04/09 03:08:01 - mmengine - INFO - Epoch(train) [9][ 350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:32:21 time: 3.4583 data_time: 0.1949 memory: 28747 grad_norm: 20.5431 loss: 5.8174 loss_cls: 0.7152 loss_bbox: 0.2219 d0.loss_cls: 0.8118 d0.loss_bbox: 0.2313 d1.loss_cls: 0.7626 d1.loss_bbox: 0.2229 d2.loss_cls: 0.7392 d2.loss_bbox: 0.2216 d3.loss_cls: 0.7277 d3.loss_bbox: 0.2198 d4.loss_cls: 0.7227 d4.loss_bbox: 0.2210 2024/04/09 03:10:55 - mmengine - INFO - Epoch(train) [9][ 400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:29:33 time: 3.4849 data_time: 0.2072 memory: 28453 grad_norm: 21.1359 loss: 5.7154 loss_cls: 0.7067 loss_bbox: 0.2191 d0.loss_cls: 0.7864 d0.loss_bbox: 0.2320 d1.loss_cls: 0.7391 d1.loss_bbox: 0.2222 d2.loss_cls: 0.7286 d2.loss_bbox: 0.2220 d3.loss_cls: 0.7145 d3.loss_bbox: 0.2189 d4.loss_cls: 0.7054 d4.loss_bbox: 0.2204 2024/04/09 03:12:43 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 03:13:44 - mmengine - INFO - Epoch(train) [9][ 450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:26:28 time: 3.3850 data_time: 0.1909 memory: 29223 grad_norm: 21.6385 loss: 5.8919 loss_cls: 0.7345 loss_bbox: 0.2233 d0.loss_cls: 0.8144 d0.loss_bbox: 0.2404 d1.loss_cls: 0.7688 d1.loss_bbox: 0.2221 d2.loss_cls: 0.7473 d2.loss_bbox: 0.2251 d3.loss_cls: 0.7387 d3.loss_bbox: 0.2196 d4.loss_cls: 0.7362 d4.loss_bbox: 0.2213 2024/04/09 03:16:38 - mmengine - INFO - Epoch(train) [9][ 500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:23:37 time: 3.4642 data_time: 0.2077 memory: 29188 grad_norm: 19.9971 loss: 5.6737 loss_cls: 0.7019 loss_bbox: 0.2105 d0.loss_cls: 0.7945 d0.loss_bbox: 0.2345 d1.loss_cls: 0.7577 d1.loss_bbox: 0.2133 d2.loss_cls: 0.7245 d2.loss_bbox: 0.2107 d3.loss_cls: 0.7058 d3.loss_bbox: 0.2130 d4.loss_cls: 0.6980 d4.loss_bbox: 0.2093 2024/04/09 03:19:40 - mmengine - INFO - Epoch(train) [9][ 550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:21:14 time: 3.6524 data_time: 0.2152 memory: 28296 grad_norm: 20.1535 loss: 5.8879 loss_cls: 0.7231 loss_bbox: 0.2297 d0.loss_cls: 0.8121 d0.loss_bbox: 0.2430 d1.loss_cls: 0.7705 d1.loss_bbox: 0.2281 d2.loss_cls: 0.7448 d2.loss_bbox: 0.2259 d3.loss_cls: 0.7268 d3.loss_bbox: 0.2277 d4.loss_cls: 0.7307 d4.loss_bbox: 0.2256 2024/04/09 03:22:31 - mmengine - INFO - Epoch(train) [9][ 600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:18:14 time: 3.4079 data_time: 0.2178 memory: 28700 grad_norm: 20.5590 loss: 5.8045 loss_cls: 0.7248 loss_bbox: 0.2154 d0.loss_cls: 0.8031 d0.loss_bbox: 0.2319 d1.loss_cls: 0.7527 d1.loss_bbox: 0.2279 d2.loss_cls: 0.7360 d2.loss_bbox: 0.2215 d3.loss_cls: 0.7258 d3.loss_bbox: 0.2237 d4.loss_cls: 0.7261 d4.loss_bbox: 0.2155 2024/04/09 03:25:21 - mmengine - INFO - Epoch(train) [9][ 650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:15:14 time: 3.4135 data_time: 0.1968 memory: 28586 grad_norm: 20.3967 loss: 5.7843 loss_cls: 0.7138 loss_bbox: 0.2280 d0.loss_cls: 0.7853 d0.loss_bbox: 0.2437 d1.loss_cls: 0.7448 d1.loss_bbox: 0.2316 d2.loss_cls: 0.7271 d2.loss_bbox: 0.2309 d3.loss_cls: 0.7100 d3.loss_bbox: 0.2249 d4.loss_cls: 0.7206 d4.loss_bbox: 0.2236 2024/04/09 03:28:12 - mmengine - INFO - Epoch(train) [9][ 700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:12:14 time: 3.4114 data_time: 0.1996 memory: 27640 grad_norm: 21.2017 loss: 5.7960 loss_cls: 0.7296 loss_bbox: 0.2064 d0.loss_cls: 0.8236 d0.loss_bbox: 0.2224 d1.loss_cls: 0.7576 d1.loss_bbox: 0.2156 d2.loss_cls: 0.7463 d2.loss_bbox: 0.2096 d3.loss_cls: 0.7377 d3.loss_bbox: 0.2087 d4.loss_cls: 0.7329 d4.loss_bbox: 0.2057 2024/04/09 03:31:06 - mmengine - INFO - Epoch(train) [9][ 750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:09:25 time: 3.4839 data_time: 0.2170 memory: 28963 grad_norm: 20.4402 loss: 5.9594 loss_cls: 0.7384 loss_bbox: 0.2186 d0.loss_cls: 0.8222 d0.loss_bbox: 0.2530 d1.loss_cls: 0.7863 d1.loss_bbox: 0.2367 d2.loss_cls: 0.7492 d2.loss_bbox: 0.2318 d3.loss_cls: 0.7369 d3.loss_bbox: 0.2262 d4.loss_cls: 0.7362 d4.loss_bbox: 0.2238 2024/04/09 03:33:56 - mmengine - INFO - Epoch(train) [9][ 800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:06:23 time: 3.3893 data_time: 0.2212 memory: 28978 grad_norm: 19.8538 loss: 5.5860 loss_cls: 0.6908 loss_bbox: 0.2143 d0.loss_cls: 0.7695 d0.loss_bbox: 0.2336 d1.loss_cls: 0.7266 d1.loss_bbox: 0.2187 d2.loss_cls: 0.7089 d2.loss_bbox: 0.2122 d3.loss_cls: 0.6979 d3.loss_bbox: 0.2105 d4.loss_cls: 0.6908 d4.loss_bbox: 0.2123 2024/04/09 03:36:51 - mmengine - INFO - Epoch(train) [9][ 850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:03:38 time: 3.5174 data_time: 0.2072 memory: 29137 grad_norm: 20.2591 loss: 5.7681 loss_cls: 0.7275 loss_bbox: 0.2059 d0.loss_cls: 0.8090 d0.loss_bbox: 0.2245 d1.loss_cls: 0.7576 d1.loss_bbox: 0.2087 d2.loss_cls: 0.7505 d2.loss_bbox: 0.2067 d3.loss_cls: 0.7355 d3.loss_bbox: 0.2061 d4.loss_cls: 0.7285 d4.loss_bbox: 0.2075 2024/04/09 03:39:42 - mmengine - INFO - Epoch(train) [9][ 900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 9:00:38 time: 3.4039 data_time: 0.2179 memory: 28351 grad_norm: 20.4214 loss: 5.9076 loss_cls: 0.7409 loss_bbox: 0.2118 d0.loss_cls: 0.8360 d0.loss_bbox: 0.2303 d1.loss_cls: 0.7825 d1.loss_bbox: 0.2186 d2.loss_cls: 0.7618 d2.loss_bbox: 0.2126 d3.loss_cls: 0.7456 d3.loss_bbox: 0.2096 d4.loss_cls: 0.7473 d4.loss_bbox: 0.2107 2024/04/09 03:42:32 - mmengine - INFO - Epoch(train) [9][ 950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:57:38 time: 3.4039 data_time: 0.2089 memory: 28320 grad_norm: 20.9453 loss: 5.8611 loss_cls: 0.7282 loss_bbox: 0.2205 d0.loss_cls: 0.8081 d0.loss_bbox: 0.2468 d1.loss_cls: 0.7541 d1.loss_bbox: 0.2332 d2.loss_cls: 0.7467 d2.loss_bbox: 0.2249 d3.loss_cls: 0.7268 d3.loss_bbox: 0.2237 d4.loss_cls: 0.7251 d4.loss_bbox: 0.2232 2024/04/09 03:45:23 - mmengine - INFO - Epoch(train) [9][1000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:54:42 time: 3.4276 data_time: 0.2116 memory: 28827 grad_norm: 19.9665 loss: 5.7557 loss_cls: 0.7039 loss_bbox: 0.2232 d0.loss_cls: 0.7979 d0.loss_bbox: 0.2371 d1.loss_cls: 0.7513 d1.loss_bbox: 0.2251 d2.loss_cls: 0.7261 d2.loss_bbox: 0.2220 d3.loss_cls: 0.7146 d3.loss_bbox: 0.2238 d4.loss_cls: 0.7083 d4.loss_bbox: 0.2225 2024/04/09 03:48:16 - mmengine - INFO - Epoch(train) [9][1050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:51:48 time: 3.4520 data_time: 0.2227 memory: 28932 grad_norm: 20.8568 loss: 5.5251 loss_cls: 0.6958 loss_bbox: 0.1962 d0.loss_cls: 0.7926 d0.loss_bbox: 0.2091 d1.loss_cls: 0.7375 d1.loss_bbox: 0.1968 d2.loss_cls: 0.7132 d2.loss_bbox: 0.1962 d3.loss_cls: 0.7013 d3.loss_bbox: 0.1941 d4.loss_cls: 0.7010 d4.loss_bbox: 0.1914 2024/04/09 03:51:09 - mmengine - INFO - Epoch(train) [9][1100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:48:57 time: 3.4678 data_time: 0.2484 memory: 28895 grad_norm: 19.8962 loss: 5.6649 loss_cls: 0.6980 loss_bbox: 0.2170 d0.loss_cls: 0.7861 d0.loss_bbox: 0.2319 d1.loss_cls: 0.7354 d1.loss_bbox: 0.2242 d2.loss_cls: 0.7170 d2.loss_bbox: 0.2187 d3.loss_cls: 0.7002 d3.loss_bbox: 0.2201 d4.loss_cls: 0.6973 d4.loss_bbox: 0.2189 2024/04/09 03:53:58 - mmengine - INFO - Epoch(train) [9][1150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:45:56 time: 3.3850 data_time: 0.2231 memory: 28461 grad_norm: 20.1066 loss: 6.0719 loss_cls: 0.7559 loss_bbox: 0.2211 d0.loss_cls: 0.8644 d0.loss_bbox: 0.2333 d1.loss_cls: 0.8073 d1.loss_bbox: 0.2236 d2.loss_cls: 0.7800 d2.loss_bbox: 0.2192 d3.loss_cls: 0.7649 d3.loss_bbox: 0.2240 d4.loss_cls: 0.7590 d4.loss_bbox: 0.2193 2024/04/09 03:56:50 - mmengine - INFO - Epoch(train) [9][1200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:43:00 time: 3.4333 data_time: 0.2202 memory: 28552 grad_norm: 20.3511 loss: 5.8626 loss_cls: 0.7329 loss_bbox: 0.2209 d0.loss_cls: 0.8058 d0.loss_bbox: 0.2415 d1.loss_cls: 0.7580 d1.loss_bbox: 0.2356 d2.loss_cls: 0.7345 d2.loss_bbox: 0.2312 d3.loss_cls: 0.7289 d3.loss_bbox: 0.2262 d4.loss_cls: 0.7253 d4.loss_bbox: 0.2219 2024/04/09 03:59:39 - mmengine - INFO - Epoch(train) [9][1250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:39:58 time: 3.3768 data_time: 0.2183 memory: 29608 grad_norm: 20.0660 loss: 5.5075 loss_cls: 0.6844 loss_bbox: 0.2039 d0.loss_cls: 0.7708 d0.loss_bbox: 0.2197 d1.loss_cls: 0.7255 d1.loss_bbox: 0.2099 d2.loss_cls: 0.7006 d2.loss_bbox: 0.2037 d3.loss_cls: 0.6908 d3.loss_bbox: 0.2047 d4.loss_cls: 0.6912 d4.loss_bbox: 0.2024 2024/04/09 04:02:26 - mmengine - INFO - Epoch(train) [9][1300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:36:53 time: 3.3424 data_time: 0.2559 memory: 29199 grad_norm: 20.1749 loss: 5.6281 loss_cls: 0.6903 loss_bbox: 0.2164 d0.loss_cls: 0.7869 d0.loss_bbox: 0.2304 d1.loss_cls: 0.7303 d1.loss_bbox: 0.2239 d2.loss_cls: 0.7081 d2.loss_bbox: 0.2206 d3.loss_cls: 0.6978 d3.loss_bbox: 0.2167 d4.loss_cls: 0.6937 d4.loss_bbox: 0.2129 2024/04/09 04:05:12 - mmengine - INFO - Epoch(train) [9][1350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:33:44 time: 3.3114 data_time: 0.2188 memory: 29001 grad_norm: 20.4981 loss: 6.0512 loss_cls: 0.7507 loss_bbox: 0.2311 d0.loss_cls: 0.8309 d0.loss_bbox: 0.2486 d1.loss_cls: 0.7900 d1.loss_bbox: 0.2373 d2.loss_cls: 0.7631 d2.loss_bbox: 0.2341 d3.loss_cls: 0.7558 d3.loss_bbox: 0.2318 d4.loss_cls: 0.7447 d4.loss_bbox: 0.2332 2024/04/09 04:07:58 - mmengine - INFO - Epoch(train) [9][1400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:30:37 time: 3.3221 data_time: 0.2020 memory: 28345 grad_norm: 20.4623 loss: 5.5806 loss_cls: 0.6889 loss_bbox: 0.2111 d0.loss_cls: 0.7796 d0.loss_bbox: 0.2284 d1.loss_cls: 0.7308 d1.loss_bbox: 0.2191 d2.loss_cls: 0.7112 d2.loss_bbox: 0.2125 d3.loss_cls: 0.6924 d3.loss_bbox: 0.2071 d4.loss_cls: 0.6919 d4.loss_bbox: 0.2077 2024/04/09 04:09:43 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 04:10:45 - mmengine - INFO - Epoch(train) [9][1450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:27:33 time: 3.3373 data_time: 0.2022 memory: 28262 grad_norm: 20.8571 loss: 5.4027 loss_cls: 0.6764 loss_bbox: 0.1969 d0.loss_cls: 0.7561 d0.loss_bbox: 0.2121 d1.loss_cls: 0.7032 d1.loss_bbox: 0.2029 d2.loss_cls: 0.6932 d2.loss_bbox: 0.2007 d3.loss_cls: 0.6845 d3.loss_bbox: 0.2001 d4.loss_cls: 0.6809 d4.loss_bbox: 0.1956 2024/04/09 04:13:35 - mmengine - INFO - Epoch(train) [9][1500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:24:36 time: 3.4047 data_time: 0.2162 memory: 28958 grad_norm: 20.0245 loss: 5.8085 loss_cls: 0.7284 loss_bbox: 0.2115 d0.loss_cls: 0.8031 d0.loss_bbox: 0.2408 d1.loss_cls: 0.7594 d1.loss_bbox: 0.2237 d2.loss_cls: 0.7425 d2.loss_bbox: 0.2179 d3.loss_cls: 0.7349 d3.loss_bbox: 0.2135 d4.loss_cls: 0.7218 d4.loss_bbox: 0.2109 2024/04/09 04:16:19 - mmengine - INFO - Epoch(train) [9][1550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:21:27 time: 3.2881 data_time: 0.2129 memory: 29238 grad_norm: 20.2162 loss: 5.7697 loss_cls: 0.7325 loss_bbox: 0.2048 d0.loss_cls: 0.8104 d0.loss_bbox: 0.2239 d1.loss_cls: 0.7569 d1.loss_bbox: 0.2120 d2.loss_cls: 0.7395 d2.loss_bbox: 0.2118 d3.loss_cls: 0.7368 d3.loss_bbox: 0.2017 d4.loss_cls: 0.7353 d4.loss_bbox: 0.2042 2024/04/09 04:19:07 - mmengine - INFO - Epoch(train) [9][1600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:18:25 time: 3.3584 data_time: 0.2194 memory: 28069 grad_norm: 20.3948 loss: 5.8853 loss_cls: 0.7297 loss_bbox: 0.2188 d0.loss_cls: 0.8353 d0.loss_bbox: 0.2282 d1.loss_cls: 0.7810 d1.loss_bbox: 0.2177 d2.loss_cls: 0.7490 d2.loss_bbox: 0.2213 d3.loss_cls: 0.7340 d3.loss_bbox: 0.2197 d4.loss_cls: 0.7306 d4.loss_bbox: 0.2200 2024/04/09 04:21:57 - mmengine - INFO - Epoch(train) [9][1650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:15:29 time: 3.4031 data_time: 0.2179 memory: 28560 grad_norm: 20.1239 loss: 5.6098 loss_cls: 0.6890 loss_bbox: 0.2106 d0.loss_cls: 0.7755 d0.loss_bbox: 0.2317 d1.loss_cls: 0.7305 d1.loss_bbox: 0.2234 d2.loss_cls: 0.7053 d2.loss_bbox: 0.2186 d3.loss_cls: 0.6987 d3.loss_bbox: 0.2178 d4.loss_cls: 0.6901 d4.loss_bbox: 0.2187 2024/04/09 04:24:42 - mmengine - INFO - Epoch(train) [9][1700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:12:23 time: 3.3008 data_time: 0.2313 memory: 27914 grad_norm: 19.9125 loss: 5.7328 loss_cls: 0.7189 loss_bbox: 0.2107 d0.loss_cls: 0.8011 d0.loss_bbox: 0.2304 d1.loss_cls: 0.7559 d1.loss_bbox: 0.2177 d2.loss_cls: 0.7260 d2.loss_bbox: 0.2127 d3.loss_cls: 0.7184 d3.loss_bbox: 0.2121 d4.loss_cls: 0.7162 d4.loss_bbox: 0.2129 2024/04/09 04:27:32 - mmengine - INFO - Epoch(train) [9][1750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:09:26 time: 3.3932 data_time: 0.2072 memory: 28031 grad_norm: 20.3776 loss: 5.7380 loss_cls: 0.7081 loss_bbox: 0.2184 d0.loss_cls: 0.7892 d0.loss_bbox: 0.2380 d1.loss_cls: 0.7533 d1.loss_bbox: 0.2223 d2.loss_cls: 0.7296 d2.loss_bbox: 0.2238 d3.loss_cls: 0.7123 d3.loss_bbox: 0.2177 d4.loss_cls: 0.7044 d4.loss_bbox: 0.2208 2024/04/09 04:30:28 - mmengine - INFO - Epoch(train) [9][1800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:06:42 time: 3.5257 data_time: 0.1981 memory: 28632 grad_norm: 20.3727 loss: 5.4607 loss_cls: 0.6769 loss_bbox: 0.2020 d0.loss_cls: 0.7573 d0.loss_bbox: 0.2227 d1.loss_cls: 0.7262 d1.loss_bbox: 0.2079 d2.loss_cls: 0.6988 d2.loss_bbox: 0.2038 d3.loss_cls: 0.6791 d3.loss_bbox: 0.2008 d4.loss_cls: 0.6817 d4.loss_bbox: 0.2035 2024/04/09 04:33:28 - mmengine - INFO - Epoch(train) [9][1850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:04:05 time: 3.6002 data_time: 0.2303 memory: 28837 grad_norm: 20.4382 loss: 5.7527 loss_cls: 0.7162 loss_bbox: 0.2134 d0.loss_cls: 0.8046 d0.loss_bbox: 0.2304 d1.loss_cls: 0.7572 d1.loss_bbox: 0.2244 d2.loss_cls: 0.7287 d2.loss_bbox: 0.2187 d3.loss_cls: 0.7179 d3.loss_bbox: 0.2145 d4.loss_cls: 0.7126 d4.loss_bbox: 0.2141 2024/04/09 04:36:18 - mmengine - INFO - Epoch(train) [9][1900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 8:01:07 time: 3.3892 data_time: 0.2253 memory: 28276 grad_norm: 19.6329 loss: 5.9453 loss_cls: 0.7383 loss_bbox: 0.2260 d0.loss_cls: 0.8274 d0.loss_bbox: 0.2358 d1.loss_cls: 0.7843 d1.loss_bbox: 0.2255 d2.loss_cls: 0.7611 d2.loss_bbox: 0.2206 d3.loss_cls: 0.7453 d3.loss_bbox: 0.2209 d4.loss_cls: 0.7324 d4.loss_bbox: 0.2277 2024/04/09 04:39:06 - mmengine - INFO - Epoch(train) [9][1950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:58:08 time: 3.3627 data_time: 0.2093 memory: 28360 grad_norm: 21.0936 loss: 5.8331 loss_cls: 0.7321 loss_bbox: 0.2162 d0.loss_cls: 0.8120 d0.loss_bbox: 0.2325 d1.loss_cls: 0.7657 d1.loss_bbox: 0.2229 d2.loss_cls: 0.7472 d2.loss_bbox: 0.2162 d3.loss_cls: 0.7344 d3.loss_bbox: 0.2162 d4.loss_cls: 0.7226 d4.loss_bbox: 0.2151 2024/04/09 04:41:57 - mmengine - INFO - Epoch(train) [9][2000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:55:13 time: 3.4128 data_time: 0.2223 memory: 29344 grad_norm: 19.5691 loss: 5.6895 loss_cls: 0.7094 loss_bbox: 0.2072 d0.loss_cls: 0.8200 d0.loss_bbox: 0.2229 d1.loss_cls: 0.7479 d1.loss_bbox: 0.2118 d2.loss_cls: 0.7276 d2.loss_bbox: 0.2083 d3.loss_cls: 0.7089 d3.loss_bbox: 0.2072 d4.loss_cls: 0.7093 d4.loss_bbox: 0.2089 2024/04/09 04:44:48 - mmengine - INFO - Epoch(train) [9][2050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:52:20 time: 3.4309 data_time: 0.1999 memory: 29379 grad_norm: 20.1619 loss: 5.9360 loss_cls: 0.7393 loss_bbox: 0.2269 d0.loss_cls: 0.8308 d0.loss_bbox: 0.2434 d1.loss_cls: 0.7705 d1.loss_bbox: 0.2283 d2.loss_cls: 0.7481 d2.loss_bbox: 0.2240 d3.loss_cls: 0.7411 d3.loss_bbox: 0.2249 d4.loss_cls: 0.7331 d4.loss_bbox: 0.2255 2024/04/09 04:47:45 - mmengine - INFO - Epoch(train) [9][2100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:49:36 time: 3.5288 data_time: 0.2115 memory: 28537 grad_norm: 20.7160 loss: 6.0538 loss_cls: 0.7645 loss_bbox: 0.2154 d0.loss_cls: 0.8530 d0.loss_bbox: 0.2370 d1.loss_cls: 0.8045 d1.loss_bbox: 0.2217 d2.loss_cls: 0.7782 d2.loss_bbox: 0.2145 d3.loss_cls: 0.7750 d3.loss_bbox: 0.2125 d4.loss_cls: 0.7648 d4.loss_bbox: 0.2128 2024/04/09 04:50:35 - mmengine - INFO - Epoch(train) [9][2150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:46:40 time: 3.4006 data_time: 0.2087 memory: 29581 grad_norm: 20.7677 loss: 5.8275 loss_cls: 0.7278 loss_bbox: 0.2174 d0.loss_cls: 0.8021 d0.loss_bbox: 0.2422 d1.loss_cls: 0.7686 d1.loss_bbox: 0.2191 d2.loss_cls: 0.7342 d2.loss_bbox: 0.2191 d3.loss_cls: 0.7327 d3.loss_bbox: 0.2202 d4.loss_cls: 0.7226 d4.loss_bbox: 0.2215 2024/04/09 04:53:20 - mmengine - INFO - Epoch(train) [9][2200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:43:36 time: 3.3034 data_time: 0.2221 memory: 28990 grad_norm: 20.7511 loss: 5.7312 loss_cls: 0.7193 loss_bbox: 0.2085 d0.loss_cls: 0.8137 d0.loss_bbox: 0.2207 d1.loss_cls: 0.7576 d1.loss_bbox: 0.2166 d2.loss_cls: 0.7262 d2.loss_bbox: 0.2175 d3.loss_cls: 0.7184 d3.loss_bbox: 0.2104 d4.loss_cls: 0.7113 d4.loss_bbox: 0.2109 2024/04/09 04:56:27 - mmengine - INFO - Epoch(train) [9][2250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:41:09 time: 3.7421 data_time: 0.1984 memory: 27876 grad_norm: 21.0631 loss: 5.7147 loss_cls: 0.7134 loss_bbox: 0.2157 d0.loss_cls: 0.7786 d0.loss_bbox: 0.2307 d1.loss_cls: 0.7475 d1.loss_bbox: 0.2211 d2.loss_cls: 0.7243 d2.loss_bbox: 0.2174 d3.loss_cls: 0.7188 d3.loss_bbox: 0.2221 d4.loss_cls: 0.7075 d4.loss_bbox: 0.2176 2024/04/09 04:59:21 - mmengine - INFO - Epoch(train) [9][2300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:38:20 time: 3.4826 data_time: 0.2017 memory: 28413 grad_norm: 19.7943 loss: 5.7115 loss_cls: 0.7102 loss_bbox: 0.2055 d0.loss_cls: 0.8169 d0.loss_bbox: 0.2275 d1.loss_cls: 0.7592 d1.loss_bbox: 0.2085 d2.loss_cls: 0.7339 d2.loss_bbox: 0.2062 d3.loss_cls: 0.7137 d3.loss_bbox: 0.2072 d4.loss_cls: 0.7175 d4.loss_bbox: 0.2054 2024/04/09 05:02:04 - mmengine - INFO - Epoch(train) [9][2350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:35:13 time: 3.2667 data_time: 0.2104 memory: 29871 grad_norm: 20.6405 loss: 5.6977 loss_cls: 0.7073 loss_bbox: 0.2134 d0.loss_cls: 0.7985 d0.loss_bbox: 0.2368 d1.loss_cls: 0.7466 d1.loss_bbox: 0.2184 d2.loss_cls: 0.7183 d2.loss_bbox: 0.2155 d3.loss_cls: 0.7102 d3.loss_bbox: 0.2133 d4.loss_cls: 0.7032 d4.loss_bbox: 0.2161 2024/04/09 05:04:43 - mmengine - INFO - Epoch(train) [9][2400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:31:59 time: 3.1622 data_time: 0.1829 memory: 28824 grad_norm: 20.1666 loss: 5.5906 loss_cls: 0.6867 loss_bbox: 0.2093 d0.loss_cls: 0.7822 d0.loss_bbox: 0.2306 d1.loss_cls: 0.7366 d1.loss_bbox: 0.2166 d2.loss_cls: 0.7101 d2.loss_bbox: 0.2110 d3.loss_cls: 0.6890 d3.loss_bbox: 0.2121 d4.loss_cls: 0.6957 d4.loss_bbox: 0.2106 2024/04/09 05:06:28 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 05:07:24 - mmengine - INFO - Epoch(train) [9][2450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:28:51 time: 3.2309 data_time: 0.2237 memory: 28053 grad_norm: 20.6121 loss: 5.6295 loss_cls: 0.7076 loss_bbox: 0.1986 d0.loss_cls: 0.7922 d0.loss_bbox: 0.2258 d1.loss_cls: 0.7570 d1.loss_bbox: 0.2058 d2.loss_cls: 0.7259 d2.loss_bbox: 0.2026 d3.loss_cls: 0.7104 d3.loss_bbox: 0.1971 d4.loss_cls: 0.7086 d4.loss_bbox: 0.1978 2024/04/09 05:10:02 - mmengine - INFO - Epoch(train) [9][2500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:25:37 time: 3.1544 data_time: 0.1962 memory: 28216 grad_norm: 20.5844 loss: 5.4668 loss_cls: 0.6927 loss_bbox: 0.1941 d0.loss_cls: 0.7632 d0.loss_bbox: 0.2136 d1.loss_cls: 0.7278 d1.loss_bbox: 0.2028 d2.loss_cls: 0.7069 d2.loss_bbox: 0.1976 d3.loss_cls: 0.6908 d3.loss_bbox: 0.1964 d4.loss_cls: 0.6859 d4.loss_bbox: 0.1950 2024/04/09 05:12:42 - mmengine - INFO - Epoch(train) [9][2550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:22:28 time: 3.2013 data_time: 0.1926 memory: 27961 grad_norm: 28.0982 loss: 5.6558 loss_cls: 0.6887 loss_bbox: 0.2219 d0.loss_cls: 0.7776 d0.loss_bbox: 0.2418 d1.loss_cls: 0.7318 d1.loss_bbox: 0.2291 d2.loss_cls: 0.7088 d2.loss_bbox: 0.2238 d3.loss_cls: 0.6921 d3.loss_bbox: 0.2230 d4.loss_cls: 0.6967 d4.loss_bbox: 0.2204 2024/04/09 05:13:38 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 05:13:38 - mmengine - INFO - Saving checkpoint at 9 epochs 2024/04/09 05:17:20 - mmengine - INFO - Epoch(train) [10][ 50/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:18:51 time: 4.1199 data_time: 0.8899 memory: 29237 grad_norm: 20.0029 loss: 5.6625 loss_cls: 0.6890 loss_bbox: 0.2164 d0.loss_cls: 0.7963 d0.loss_bbox: 0.2351 d1.loss_cls: 0.7467 d1.loss_bbox: 0.2224 d2.loss_cls: 0.7186 d2.loss_bbox: 0.2141 d3.loss_cls: 0.6989 d3.loss_bbox: 0.2137 d4.loss_cls: 0.6968 d4.loss_bbox: 0.2145 2024/04/09 05:19:58 - mmengine - INFO - Epoch(train) [10][ 100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:15:40 time: 3.1661 data_time: 0.2082 memory: 28103 grad_norm: 20.4870 loss: 5.5237 loss_cls: 0.6741 loss_bbox: 0.2098 d0.loss_cls: 0.7814 d0.loss_bbox: 0.2271 d1.loss_cls: 0.7230 d1.loss_bbox: 0.2173 d2.loss_cls: 0.6922 d2.loss_bbox: 0.2149 d3.loss_cls: 0.6865 d3.loss_bbox: 0.2063 d4.loss_cls: 0.6839 d4.loss_bbox: 0.2070 2024/04/09 05:22:38 - mmengine - INFO - Epoch(train) [10][ 150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:12:31 time: 3.1930 data_time: 0.2023 memory: 28922 grad_norm: 20.7282 loss: 5.7409 loss_cls: 0.6983 loss_bbox: 0.2278 d0.loss_cls: 0.7845 d0.loss_bbox: 0.2425 d1.loss_cls: 0.7378 d1.loss_bbox: 0.2348 d2.loss_cls: 0.7132 d2.loss_bbox: 0.2309 d3.loss_cls: 0.7125 d3.loss_bbox: 0.2320 d4.loss_cls: 0.6970 d4.loss_bbox: 0.2295 2024/04/09 05:25:16 - mmengine - INFO - Epoch(train) [10][ 200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:09:21 time: 3.1773 data_time: 0.2018 memory: 27973 grad_norm: 20.4702 loss: 5.6804 loss_cls: 0.6997 loss_bbox: 0.2089 d0.loss_cls: 0.7969 d0.loss_bbox: 0.2237 d1.loss_cls: 0.7599 d1.loss_bbox: 0.2127 d2.loss_cls: 0.7293 d2.loss_bbox: 0.2090 d3.loss_cls: 0.7164 d3.loss_bbox: 0.2058 d4.loss_cls: 0.7074 d4.loss_bbox: 0.2105 2024/04/09 05:27:57 - mmengine - INFO - Epoch(train) [10][ 250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:06:15 time: 3.2090 data_time: 0.1862 memory: 28169 grad_norm: 19.5586 loss: 5.6320 loss_cls: 0.6970 loss_bbox: 0.2127 d0.loss_cls: 0.7804 d0.loss_bbox: 0.2326 d1.loss_cls: 0.7330 d1.loss_bbox: 0.2228 d2.loss_cls: 0.7140 d2.loss_bbox: 0.2144 d3.loss_cls: 0.7047 d3.loss_bbox: 0.2137 d4.loss_cls: 0.6936 d4.loss_bbox: 0.2131 2024/04/09 05:30:41 - mmengine - INFO - Epoch(train) [10][ 300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:03:13 time: 3.2803 data_time: 0.1932 memory: 28465 grad_norm: 19.9360 loss: 5.5954 loss_cls: 0.6925 loss_bbox: 0.2080 d0.loss_cls: 0.7901 d0.loss_bbox: 0.2268 d1.loss_cls: 0.7378 d1.loss_bbox: 0.2134 d2.loss_cls: 0.7147 d2.loss_bbox: 0.2098 d3.loss_cls: 0.6966 d3.loss_bbox: 0.2075 d4.loss_cls: 0.6882 d4.loss_bbox: 0.2099 2024/04/09 05:33:20 - mmengine - INFO - Epoch(train) [10][ 350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 7:00:06 time: 3.1792 data_time: 0.1913 memory: 28856 grad_norm: 20.2875 loss: 5.7817 loss_cls: 0.7227 loss_bbox: 0.2130 d0.loss_cls: 0.7969 d0.loss_bbox: 0.2368 d1.loss_cls: 0.7599 d1.loss_bbox: 0.2149 d2.loss_cls: 0.7441 d2.loss_bbox: 0.2174 d3.loss_cls: 0.7256 d3.loss_bbox: 0.2169 d4.loss_cls: 0.7189 d4.loss_bbox: 0.2145 2024/04/09 05:36:05 - mmengine - INFO - Epoch(train) [10][ 400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:57:06 time: 3.2953 data_time: 0.1928 memory: 27879 grad_norm: 19.7528 loss: 5.5437 loss_cls: 0.6886 loss_bbox: 0.2117 d0.loss_cls: 0.7789 d0.loss_bbox: 0.2257 d1.loss_cls: 0.7215 d1.loss_bbox: 0.2140 d2.loss_cls: 0.6970 d2.loss_bbox: 0.2142 d3.loss_cls: 0.6878 d3.loss_bbox: 0.2109 d4.loss_cls: 0.6840 d4.loss_bbox: 0.2095 2024/04/09 05:38:45 - mmengine - INFO - Epoch(train) [10][ 450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:54:00 time: 3.1986 data_time: 0.2100 memory: 28908 grad_norm: 19.4668 loss: 5.5800 loss_cls: 0.6954 loss_bbox: 0.1997 d0.loss_cls: 0.7958 d0.loss_bbox: 0.2159 d1.loss_cls: 0.7377 d1.loss_bbox: 0.2063 d2.loss_cls: 0.7177 d2.loss_bbox: 0.2024 d3.loss_cls: 0.7077 d3.loss_bbox: 0.2007 d4.loss_cls: 0.7039 d4.loss_bbox: 0.1968 2024/04/09 05:41:29 - mmengine - INFO - Epoch(train) [10][ 500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:51:01 time: 3.2841 data_time: 0.2190 memory: 29075 grad_norm: 20.3059 loss: 5.6020 loss_cls: 0.6966 loss_bbox: 0.2068 d0.loss_cls: 0.7812 d0.loss_bbox: 0.2270 d1.loss_cls: 0.7351 d1.loss_bbox: 0.2170 d2.loss_cls: 0.7123 d2.loss_bbox: 0.2122 d3.loss_cls: 0.7018 d3.loss_bbox: 0.2090 d4.loss_cls: 0.6950 d4.loss_bbox: 0.2080 2024/04/09 05:44:06 - mmengine - INFO - Epoch(train) [10][ 550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:47:53 time: 3.1513 data_time: 0.2076 memory: 28628 grad_norm: 20.4537 loss: 5.7519 loss_cls: 0.7135 loss_bbox: 0.2186 d0.loss_cls: 0.7915 d0.loss_bbox: 0.2367 d1.loss_cls: 0.7432 d1.loss_bbox: 0.2219 d2.loss_cls: 0.7310 d2.loss_bbox: 0.2197 d3.loss_cls: 0.7243 d3.loss_bbox: 0.2155 d4.loss_cls: 0.7157 d4.loss_bbox: 0.2203 2024/04/09 05:46:46 - mmengine - INFO - Epoch(train) [10][ 600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:44:48 time: 3.1845 data_time: 0.1666 memory: 28813 grad_norm: 19.2565 loss: 5.7210 loss_cls: 0.7074 loss_bbox: 0.2191 d0.loss_cls: 0.7977 d0.loss_bbox: 0.2325 d1.loss_cls: 0.7443 d1.loss_bbox: 0.2237 d2.loss_cls: 0.7181 d2.loss_bbox: 0.2221 d3.loss_cls: 0.7084 d3.loss_bbox: 0.2214 d4.loss_cls: 0.7049 d4.loss_bbox: 0.2215 2024/04/09 05:49:24 - mmengine - INFO - Epoch(train) [10][ 650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:41:42 time: 3.1696 data_time: 0.2005 memory: 28638 grad_norm: 20.2211 loss: 5.5892 loss_cls: 0.6872 loss_bbox: 0.2124 d0.loss_cls: 0.7766 d0.loss_bbox: 0.2294 d1.loss_cls: 0.7274 d1.loss_bbox: 0.2156 d2.loss_cls: 0.7170 d2.loss_bbox: 0.2113 d3.loss_cls: 0.7005 d3.loss_bbox: 0.2103 d4.loss_cls: 0.6902 d4.loss_bbox: 0.2115 2024/04/09 05:52:05 - mmengine - INFO - Epoch(train) [10][ 700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:38:39 time: 3.2123 data_time: 0.2070 memory: 28654 grad_norm: 20.6504 loss: 5.6001 loss_cls: 0.6848 loss_bbox: 0.2209 d0.loss_cls: 0.7809 d0.loss_bbox: 0.2365 d1.loss_cls: 0.7270 d1.loss_bbox: 0.2239 d2.loss_cls: 0.6937 d2.loss_bbox: 0.2241 d3.loss_cls: 0.6796 d3.loss_bbox: 0.2251 d4.loss_cls: 0.6829 d4.loss_bbox: 0.2209 2024/04/09 05:54:43 - mmengine - INFO - Epoch(train) [10][ 750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:35:34 time: 3.1656 data_time: 0.1784 memory: 28910 grad_norm: 20.2513 loss: 5.5562 loss_cls: 0.6860 loss_bbox: 0.2154 d0.loss_cls: 0.7679 d0.loss_bbox: 0.2267 d1.loss_cls: 0.7216 d1.loss_bbox: 0.2187 d2.loss_cls: 0.6986 d2.loss_bbox: 0.2171 d3.loss_cls: 0.6842 d3.loss_bbox: 0.2161 d4.loss_cls: 0.6880 d4.loss_bbox: 0.2160 2024/04/09 05:57:26 - mmengine - INFO - Epoch(train) [10][ 800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:32:35 time: 3.2616 data_time: 0.1982 memory: 27468 grad_norm: 20.3254 loss: 5.7210 loss_cls: 0.7074 loss_bbox: 0.2194 d0.loss_cls: 0.7985 d0.loss_bbox: 0.2420 d1.loss_cls: 0.7474 d1.loss_bbox: 0.2213 d2.loss_cls: 0.7213 d2.loss_bbox: 0.2186 d3.loss_cls: 0.7093 d3.loss_bbox: 0.2149 d4.loss_cls: 0.7062 d4.loss_bbox: 0.2147 2024/04/09 06:00:07 - mmengine - INFO - Epoch(train) [10][ 850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:29:34 time: 3.2196 data_time: 0.2039 memory: 28412 grad_norm: 21.5284 loss: 5.8604 loss_cls: 0.7431 loss_bbox: 0.2042 d0.loss_cls: 0.8332 d0.loss_bbox: 0.2270 d1.loss_cls: 0.7917 d1.loss_bbox: 0.2086 d2.loss_cls: 0.7553 d2.loss_bbox: 0.2068 d3.loss_cls: 0.7471 d3.loss_bbox: 0.2008 d4.loss_cls: 0.7422 d4.loss_bbox: 0.2005 2024/04/09 06:00:45 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 06:02:47 - mmengine - INFO - Epoch(train) [10][ 900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:26:32 time: 3.1991 data_time: 0.1963 memory: 28295 grad_norm: 20.7191 loss: 5.6223 loss_cls: 0.6973 loss_bbox: 0.2177 d0.loss_cls: 0.7669 d0.loss_bbox: 0.2360 d1.loss_cls: 0.7318 d1.loss_bbox: 0.2175 d2.loss_cls: 0.7152 d2.loss_bbox: 0.2148 d3.loss_cls: 0.7021 d3.loss_bbox: 0.2091 d4.loss_cls: 0.6992 d4.loss_bbox: 0.2147 2024/04/09 06:05:29 - mmengine - INFO - Epoch(train) [10][ 950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:23:33 time: 3.2324 data_time: 0.1771 memory: 28514 grad_norm: 21.3347 loss: 5.5296 loss_cls: 0.6665 loss_bbox: 0.2212 d0.loss_cls: 0.7707 d0.loss_bbox: 0.2395 d1.loss_cls: 0.7089 d1.loss_bbox: 0.2270 d2.loss_cls: 0.6918 d2.loss_bbox: 0.2221 d3.loss_cls: 0.6664 d3.loss_bbox: 0.2241 d4.loss_cls: 0.6668 d4.loss_bbox: 0.2246 2024/04/09 06:08:09 - mmengine - INFO - Epoch(train) [10][1000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:20:31 time: 3.2022 data_time: 0.1948 memory: 28557 grad_norm: 21.9524 loss: 5.5745 loss_cls: 0.6905 loss_bbox: 0.2031 d0.loss_cls: 0.7843 d0.loss_bbox: 0.2219 d1.loss_cls: 0.7339 d1.loss_bbox: 0.2130 d2.loss_cls: 0.7098 d2.loss_bbox: 0.2089 d3.loss_cls: 0.6999 d3.loss_bbox: 0.2058 d4.loss_cls: 0.6997 d4.loss_bbox: 0.2038 2024/04/09 06:10:50 - mmengine - INFO - Epoch(train) [10][1050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:17:31 time: 3.2150 data_time: 0.1967 memory: 28730 grad_norm: 20.9626 loss: 5.6369 loss_cls: 0.6851 loss_bbox: 0.2114 d0.loss_cls: 0.7935 d0.loss_bbox: 0.2326 d1.loss_cls: 0.7460 d1.loss_bbox: 0.2172 d2.loss_cls: 0.7202 d2.loss_bbox: 0.2133 d3.loss_cls: 0.7032 d3.loss_bbox: 0.2080 d4.loss_cls: 0.6968 d4.loss_bbox: 0.2097 2024/04/09 06:13:26 - mmengine - INFO - Epoch(train) [10][1100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:14:27 time: 3.1275 data_time: 0.2019 memory: 27806 grad_norm: 20.6201 loss: 5.6100 loss_cls: 0.6997 loss_bbox: 0.2070 d0.loss_cls: 0.7920 d0.loss_bbox: 0.2305 d1.loss_cls: 0.7332 d1.loss_bbox: 0.2177 d2.loss_cls: 0.7114 d2.loss_bbox: 0.2123 d3.loss_cls: 0.6982 d3.loss_bbox: 0.2079 d4.loss_cls: 0.6959 d4.loss_bbox: 0.2043 2024/04/09 06:16:07 - mmengine - INFO - Epoch(train) [10][1150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:11:28 time: 3.2302 data_time: 0.2069 memory: 28143 grad_norm: 21.2419 loss: 5.6948 loss_cls: 0.7090 loss_bbox: 0.2110 d0.loss_cls: 0.8020 d0.loss_bbox: 0.2292 d1.loss_cls: 0.7447 d1.loss_bbox: 0.2181 d2.loss_cls: 0.7264 d2.loss_bbox: 0.2111 d3.loss_cls: 0.7116 d3.loss_bbox: 0.2097 d4.loss_cls: 0.7131 d4.loss_bbox: 0.2089 2024/04/09 06:18:46 - mmengine - INFO - Epoch(train) [10][1200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:08:27 time: 3.1678 data_time: 0.1807 memory: 28378 grad_norm: 20.9746 loss: 5.5698 loss_cls: 0.6842 loss_bbox: 0.2135 d0.loss_cls: 0.7728 d0.loss_bbox: 0.2302 d1.loss_cls: 0.7257 d1.loss_bbox: 0.2224 d2.loss_cls: 0.7054 d2.loss_bbox: 0.2175 d3.loss_cls: 0.6849 d3.loss_bbox: 0.2172 d4.loss_cls: 0.6781 d4.loss_bbox: 0.2181 2024/04/09 06:21:28 - mmengine - INFO - Epoch(train) [10][1250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:05:29 time: 3.2437 data_time: 0.1967 memory: 29078 grad_norm: 20.4158 loss: 5.3658 loss_cls: 0.6608 loss_bbox: 0.2055 d0.loss_cls: 0.7508 d0.loss_bbox: 0.2268 d1.loss_cls: 0.6915 d1.loss_bbox: 0.2131 d2.loss_cls: 0.6702 d2.loss_bbox: 0.2109 d3.loss_cls: 0.6635 d3.loss_bbox: 0.2089 d4.loss_cls: 0.6607 d4.loss_bbox: 0.2031 2024/04/09 06:24:08 - mmengine - INFO - Epoch(train) [10][1300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 6:02:31 time: 3.2072 data_time: 0.1913 memory: 28398 grad_norm: 20.5251 loss: 5.4762 loss_cls: 0.6757 loss_bbox: 0.1966 d0.loss_cls: 0.7916 d0.loss_bbox: 0.2105 d1.loss_cls: 0.7329 d1.loss_bbox: 0.2031 d2.loss_cls: 0.7120 d2.loss_bbox: 0.1977 d3.loss_cls: 0.6803 d3.loss_bbox: 0.1969 d4.loss_cls: 0.6836 d4.loss_bbox: 0.1954 2024/04/09 06:26:52 - mmengine - INFO - Epoch(train) [10][1350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:59:35 time: 3.2784 data_time: 0.1983 memory: 29018 grad_norm: 20.2920 loss: 5.6241 loss_cls: 0.6964 loss_bbox: 0.2065 d0.loss_cls: 0.7901 d0.loss_bbox: 0.2210 d1.loss_cls: 0.7473 d1.loss_bbox: 0.2106 d2.loss_cls: 0.7245 d2.loss_bbox: 0.2042 d3.loss_cls: 0.7106 d3.loss_bbox: 0.2103 d4.loss_cls: 0.6945 d4.loss_bbox: 0.2082 2024/04/09 06:29:30 - mmengine - INFO - Epoch(train) [10][1400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:56:35 time: 3.1579 data_time: 0.1890 memory: 28774 grad_norm: 20.1655 loss: 5.5668 loss_cls: 0.6937 loss_bbox: 0.2003 d0.loss_cls: 0.7806 d0.loss_bbox: 0.2290 d1.loss_cls: 0.7397 d1.loss_bbox: 0.2085 d2.loss_cls: 0.7172 d2.loss_bbox: 0.2044 d3.loss_cls: 0.6983 d3.loss_bbox: 0.2042 d4.loss_cls: 0.6905 d4.loss_bbox: 0.2004 2024/04/09 06:32:12 - mmengine - INFO - Epoch(train) [10][1450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:53:38 time: 3.2296 data_time: 0.2289 memory: 28271 grad_norm: 20.2178 loss: 5.6883 loss_cls: 0.7001 loss_bbox: 0.2167 d0.loss_cls: 0.7898 d0.loss_bbox: 0.2446 d1.loss_cls: 0.7310 d1.loss_bbox: 0.2313 d2.loss_cls: 0.7143 d2.loss_bbox: 0.2213 d3.loss_cls: 0.7040 d3.loss_bbox: 0.2179 d4.loss_cls: 0.7026 d4.loss_bbox: 0.2148 2024/04/09 06:34:49 - mmengine - INFO - Epoch(train) [10][1500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:50:37 time: 3.1517 data_time: 0.2048 memory: 28248 grad_norm: 20.8113 loss: 5.7471 loss_cls: 0.7232 loss_bbox: 0.2074 d0.loss_cls: 0.8115 d0.loss_bbox: 0.2300 d1.loss_cls: 0.7587 d1.loss_bbox: 0.2109 d2.loss_cls: 0.7311 d2.loss_bbox: 0.2108 d3.loss_cls: 0.7207 d3.loss_bbox: 0.2123 d4.loss_cls: 0.7253 d4.loss_bbox: 0.2052 2024/04/09 06:37:31 - mmengine - INFO - Epoch(train) [10][1550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:47:41 time: 3.2311 data_time: 0.1941 memory: 28866 grad_norm: 19.6663 loss: 5.5570 loss_cls: 0.6834 loss_bbox: 0.2156 d0.loss_cls: 0.7739 d0.loss_bbox: 0.2379 d1.loss_cls: 0.7164 d1.loss_bbox: 0.2230 d2.loss_cls: 0.6924 d2.loss_bbox: 0.2196 d3.loss_cls: 0.6840 d3.loss_bbox: 0.2161 d4.loss_cls: 0.6737 d4.loss_bbox: 0.2210 2024/04/09 06:40:10 - mmengine - INFO - Epoch(train) [10][1600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:44:43 time: 3.1868 data_time: 0.1987 memory: 29538 grad_norm: 20.0453 loss: 5.5840 loss_cls: 0.6932 loss_bbox: 0.2114 d0.loss_cls: 0.7752 d0.loss_bbox: 0.2208 d1.loss_cls: 0.7358 d1.loss_bbox: 0.2157 d2.loss_cls: 0.7079 d2.loss_bbox: 0.2139 d3.loss_cls: 0.6973 d3.loss_bbox: 0.2103 d4.loss_cls: 0.6905 d4.loss_bbox: 0.2119 2024/04/09 06:42:51 - mmengine - INFO - Epoch(train) [10][1650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:41:46 time: 3.2107 data_time: 0.2313 memory: 29561 grad_norm: 20.5882 loss: 5.4646 loss_cls: 0.6697 loss_bbox: 0.2130 d0.loss_cls: 0.7563 d0.loss_bbox: 0.2279 d1.loss_cls: 0.7104 d1.loss_bbox: 0.2181 d2.loss_cls: 0.6859 d2.loss_bbox: 0.2126 d3.loss_cls: 0.6740 d3.loss_bbox: 0.2101 d4.loss_cls: 0.6741 d4.loss_bbox: 0.2125 2024/04/09 06:45:28 - mmengine - INFO - Epoch(train) [10][1700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:38:46 time: 3.1498 data_time: 0.1946 memory: 28115 grad_norm: 19.7596 loss: 5.4547 loss_cls: 0.6686 loss_bbox: 0.2091 d0.loss_cls: 0.7641 d0.loss_bbox: 0.2304 d1.loss_cls: 0.7208 d1.loss_bbox: 0.2168 d2.loss_cls: 0.6839 d2.loss_bbox: 0.2095 d3.loss_cls: 0.6714 d3.loss_bbox: 0.2072 d4.loss_cls: 0.6626 d4.loss_bbox: 0.2102 2024/04/09 06:48:06 - mmengine - INFO - Epoch(train) [10][1750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:35:48 time: 3.1590 data_time: 0.1900 memory: 28280 grad_norm: 20.0973 loss: 5.6144 loss_cls: 0.7004 loss_bbox: 0.1980 d0.loss_cls: 0.7927 d0.loss_bbox: 0.2240 d1.loss_cls: 0.7572 d1.loss_bbox: 0.2031 d2.loss_cls: 0.7234 d2.loss_bbox: 0.2034 d3.loss_cls: 0.7092 d3.loss_bbox: 0.2014 d4.loss_cls: 0.7047 d4.loss_bbox: 0.1968 2024/04/09 06:50:47 - mmengine - INFO - Epoch(train) [10][1800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:32:52 time: 3.2099 data_time: 0.2116 memory: 29449 grad_norm: 20.2500 loss: 5.9141 loss_cls: 0.7254 loss_bbox: 0.2332 d0.loss_cls: 0.8141 d0.loss_bbox: 0.2479 d1.loss_cls: 0.7702 d1.loss_bbox: 0.2321 d2.loss_cls: 0.7465 d2.loss_bbox: 0.2285 d3.loss_cls: 0.7251 d3.loss_bbox: 0.2290 d4.loss_cls: 0.7318 d4.loss_bbox: 0.2304 2024/04/09 06:53:21 - mmengine - INFO - Epoch(train) [10][1850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:29:50 time: 3.0815 data_time: 0.1643 memory: 28808 grad_norm: 20.0906 loss: 5.5725 loss_cls: 0.6866 loss_bbox: 0.2097 d0.loss_cls: 0.7873 d0.loss_bbox: 0.2260 d1.loss_cls: 0.7300 d1.loss_bbox: 0.2118 d2.loss_cls: 0.7087 d2.loss_bbox: 0.2094 d3.loss_cls: 0.6882 d3.loss_bbox: 0.2085 d4.loss_cls: 0.6974 d4.loss_bbox: 0.2088 2024/04/09 06:53:55 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 06:56:01 - mmengine - INFO - Epoch(train) [10][1900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:26:55 time: 3.2088 data_time: 0.1772 memory: 28645 grad_norm: 20.0644 loss: 5.8431 loss_cls: 0.7262 loss_bbox: 0.2114 d0.loss_cls: 0.8232 d0.loss_bbox: 0.2387 d1.loss_cls: 0.7675 d1.loss_bbox: 0.2234 d2.loss_cls: 0.7420 d2.loss_bbox: 0.2222 d3.loss_cls: 0.7335 d3.loss_bbox: 0.2175 d4.loss_cls: 0.7236 d4.loss_bbox: 0.2139 2024/04/09 06:58:38 - mmengine - INFO - Epoch(train) [10][1950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:23:56 time: 3.1296 data_time: 0.1909 memory: 28448 grad_norm: 20.6816 loss: 5.5653 loss_cls: 0.6959 loss_bbox: 0.2022 d0.loss_cls: 0.7775 d0.loss_bbox: 0.2246 d1.loss_cls: 0.7320 d1.loss_bbox: 0.2134 d2.loss_cls: 0.7151 d2.loss_bbox: 0.2060 d3.loss_cls: 0.7010 d3.loss_bbox: 0.2054 d4.loss_cls: 0.6880 d4.loss_bbox: 0.2042 2024/04/09 07:01:17 - mmengine - INFO - Epoch(train) [10][2000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:21:00 time: 3.1931 data_time: 0.2065 memory: 28792 grad_norm: 20.1567 loss: 5.5822 loss_cls: 0.6902 loss_bbox: 0.2037 d0.loss_cls: 0.7757 d0.loss_bbox: 0.2276 d1.loss_cls: 0.7368 d1.loss_bbox: 0.2130 d2.loss_cls: 0.7149 d2.loss_bbox: 0.2117 d3.loss_cls: 0.6985 d3.loss_bbox: 0.2059 d4.loss_cls: 0.6956 d4.loss_bbox: 0.2087 2024/04/09 07:03:54 - mmengine - INFO - Epoch(train) [10][2050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:18:02 time: 3.1237 data_time: 0.1866 memory: 29396 grad_norm: 20.4418 loss: 5.3393 loss_cls: 0.6749 loss_bbox: 0.1882 d0.loss_cls: 0.7626 d0.loss_bbox: 0.2045 d1.loss_cls: 0.7064 d1.loss_bbox: 0.1982 d2.loss_cls: 0.6870 d2.loss_bbox: 0.1925 d3.loss_cls: 0.6761 d3.loss_bbox: 0.1876 d4.loss_cls: 0.6691 d4.loss_bbox: 0.1922 2024/04/09 07:06:35 - mmengine - INFO - Epoch(train) [10][2100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:15:08 time: 3.2358 data_time: 0.2000 memory: 28440 grad_norm: 20.0808 loss: 5.6531 loss_cls: 0.7021 loss_bbox: 0.2070 d0.loss_cls: 0.7996 d0.loss_bbox: 0.2296 d1.loss_cls: 0.7379 d1.loss_bbox: 0.2227 d2.loss_cls: 0.7165 d2.loss_bbox: 0.2138 d3.loss_cls: 0.7067 d3.loss_bbox: 0.2108 d4.loss_cls: 0.6999 d4.loss_bbox: 0.2064 2024/04/09 07:09:11 - mmengine - INFO - Epoch(train) [10][2150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:12:10 time: 3.1194 data_time: 0.1713 memory: 28681 grad_norm: 20.2045 loss: 5.3857 loss_cls: 0.6614 loss_bbox: 0.2092 d0.loss_cls: 0.7396 d0.loss_bbox: 0.2262 d1.loss_cls: 0.6998 d1.loss_bbox: 0.2142 d2.loss_cls: 0.6838 d2.loss_bbox: 0.2085 d3.loss_cls: 0.6661 d3.loss_bbox: 0.2074 d4.loss_cls: 0.6619 d4.loss_bbox: 0.2076 2024/04/09 07:11:55 - mmengine - INFO - Epoch(train) [10][2200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:09:18 time: 3.2745 data_time: 0.2366 memory: 29307 grad_norm: 19.8900 loss: 5.5928 loss_cls: 0.6947 loss_bbox: 0.2012 d0.loss_cls: 0.7877 d0.loss_bbox: 0.2293 d1.loss_cls: 0.7390 d1.loss_bbox: 0.2111 d2.loss_cls: 0.7142 d2.loss_bbox: 0.2096 d3.loss_cls: 0.6983 d3.loss_bbox: 0.2010 d4.loss_cls: 0.7050 d4.loss_bbox: 0.2017 2024/04/09 07:14:36 - mmengine - INFO - Epoch(train) [10][2250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:06:25 time: 3.2218 data_time: 0.2845 memory: 28623 grad_norm: 19.6120 loss: 5.5783 loss_cls: 0.6952 loss_bbox: 0.2134 d0.loss_cls: 0.7643 d0.loss_bbox: 0.2300 d1.loss_cls: 0.7220 d1.loss_bbox: 0.2206 d2.loss_cls: 0.7050 d2.loss_bbox: 0.2174 d3.loss_cls: 0.6907 d3.loss_bbox: 0.2192 d4.loss_cls: 0.6868 d4.loss_bbox: 0.2136 2024/04/09 07:17:15 - mmengine - INFO - Epoch(train) [10][2300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:03:30 time: 3.1794 data_time: 0.1744 memory: 28871 grad_norm: 20.2541 loss: 5.3470 loss_cls: 0.6511 loss_bbox: 0.2030 d0.loss_cls: 0.7491 d0.loss_bbox: 0.2180 d1.loss_cls: 0.7122 d1.loss_bbox: 0.2091 d2.loss_cls: 0.6730 d2.loss_bbox: 0.2053 d3.loss_cls: 0.6648 d3.loss_bbox: 0.2043 d4.loss_cls: 0.6509 d4.loss_bbox: 0.2061 2024/04/09 07:19:52 - mmengine - INFO - Epoch(train) [10][2350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 5:00:33 time: 3.1376 data_time: 0.1868 memory: 28635 grad_norm: 20.9881 loss: 5.6603 loss_cls: 0.6974 loss_bbox: 0.2135 d0.loss_cls: 0.7778 d0.loss_bbox: 0.2490 d1.loss_cls: 0.7264 d1.loss_bbox: 0.2257 d2.loss_cls: 0.7191 d2.loss_bbox: 0.2213 d3.loss_cls: 0.7024 d3.loss_bbox: 0.2140 d4.loss_cls: 0.7006 d4.loss_bbox: 0.2131 2024/04/09 07:22:32 - mmengine - INFO - Epoch(train) [10][2400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:57:39 time: 3.1961 data_time: 0.2257 memory: 28791 grad_norm: 28.4609 loss: 5.7816 loss_cls: 0.7237 loss_bbox: 0.2071 d0.loss_cls: 0.8127 d0.loss_bbox: 0.2245 d1.loss_cls: 0.7758 d1.loss_bbox: 0.2135 d2.loss_cls: 0.7413 d2.loss_bbox: 0.2109 d3.loss_cls: 0.7319 d3.loss_bbox: 0.2070 d4.loss_cls: 0.7276 d4.loss_bbox: 0.2055 2024/04/09 07:25:10 - mmengine - INFO - Epoch(train) [10][2450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:54:45 time: 3.1683 data_time: 0.2025 memory: 28828 grad_norm: 20.1333 loss: 5.5453 loss_cls: 0.6952 loss_bbox: 0.1970 d0.loss_cls: 0.7923 d0.loss_bbox: 0.2126 d1.loss_cls: 0.7380 d1.loss_bbox: 0.2036 d2.loss_cls: 0.7175 d2.loss_bbox: 0.1993 d3.loss_cls: 0.6985 d3.loss_bbox: 0.1983 d4.loss_cls: 0.6948 d4.loss_bbox: 0.1981 2024/04/09 07:27:51 - mmengine - INFO - Epoch(train) [10][2500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:51:51 time: 3.2102 data_time: 0.1977 memory: 28120 grad_norm: 20.9031 loss: 5.6614 loss_cls: 0.7032 loss_bbox: 0.2104 d0.loss_cls: 0.8050 d0.loss_bbox: 0.2224 d1.loss_cls: 0.7446 d1.loss_bbox: 0.2151 d2.loss_cls: 0.7161 d2.loss_bbox: 0.2119 d3.loss_cls: 0.7095 d3.loss_bbox: 0.2073 d4.loss_cls: 0.7077 d4.loss_bbox: 0.2081 2024/04/09 07:30:31 - mmengine - INFO - Epoch(train) [10][2550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:48:58 time: 3.1993 data_time: 0.1926 memory: 29005 grad_norm: 20.3424 loss: 5.8118 loss_cls: 0.7125 loss_bbox: 0.2171 d0.loss_cls: 0.8143 d0.loss_bbox: 0.2397 d1.loss_cls: 0.7696 d1.loss_bbox: 0.2217 d2.loss_cls: 0.7357 d2.loss_bbox: 0.2197 d3.loss_cls: 0.7268 d3.loss_bbox: 0.2212 d4.loss_cls: 0.7141 d4.loss_bbox: 0.2193 2024/04/09 07:31:28 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 07:31:28 - mmengine - INFO - Saving checkpoint at 10 epochs 2024/04/09 07:35:11 - mmengine - INFO - Epoch(train) [11][ 50/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:45:18 time: 4.1686 data_time: 0.6800 memory: 29865 grad_norm: 20.7613 loss: 5.7289 loss_cls: 0.7075 loss_bbox: 0.2151 d0.loss_cls: 0.7902 d0.loss_bbox: 0.2352 d1.loss_cls: 0.7573 d1.loss_bbox: 0.2248 d2.loss_cls: 0.7252 d2.loss_bbox: 0.2215 d3.loss_cls: 0.7112 d3.loss_bbox: 0.2142 d4.loss_cls: 0.7115 d4.loss_bbox: 0.2151 2024/04/09 07:37:50 - mmengine - INFO - Epoch(train) [11][ 100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:42:24 time: 3.1880 data_time: 0.1989 memory: 29692 grad_norm: 20.2302 loss: 5.5230 loss_cls: 0.6862 loss_bbox: 0.2006 d0.loss_cls: 0.7756 d0.loss_bbox: 0.2258 d1.loss_cls: 0.7304 d1.loss_bbox: 0.2119 d2.loss_cls: 0.7016 d2.loss_bbox: 0.2054 d3.loss_cls: 0.6947 d3.loss_bbox: 0.2029 d4.loss_cls: 0.6868 d4.loss_bbox: 0.2011 2024/04/09 07:40:30 - mmengine - INFO - Epoch(train) [11][ 150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:39:30 time: 3.1882 data_time: 0.2011 memory: 29106 grad_norm: 20.7578 loss: 5.4435 loss_cls: 0.6719 loss_bbox: 0.2016 d0.loss_cls: 0.7650 d0.loss_bbox: 0.2227 d1.loss_cls: 0.7109 d1.loss_bbox: 0.2084 d2.loss_cls: 0.6925 d2.loss_bbox: 0.2036 d3.loss_cls: 0.6798 d3.loss_bbox: 0.2038 d4.loss_cls: 0.6781 d4.loss_bbox: 0.2052 2024/04/09 07:43:05 - mmengine - INFO - Epoch(train) [11][ 200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:36:35 time: 3.1173 data_time: 0.1997 memory: 28399 grad_norm: 20.3945 loss: 5.6634 loss_cls: 0.6966 loss_bbox: 0.2104 d0.loss_cls: 0.7956 d0.loss_bbox: 0.2351 d1.loss_cls: 0.7480 d1.loss_bbox: 0.2225 d2.loss_cls: 0.7122 d2.loss_bbox: 0.2168 d3.loss_cls: 0.6951 d3.loss_bbox: 0.2148 d4.loss_cls: 0.7013 d4.loss_bbox: 0.2151 2024/04/09 07:45:45 - mmengine - INFO - Epoch(train) [11][ 250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:33:42 time: 3.1867 data_time: 0.1992 memory: 28559 grad_norm: 20.3678 loss: 5.3966 loss_cls: 0.6724 loss_bbox: 0.1906 d0.loss_cls: 0.7621 d0.loss_bbox: 0.2194 d1.loss_cls: 0.7140 d1.loss_bbox: 0.2059 d2.loss_cls: 0.6920 d2.loss_bbox: 0.1959 d3.loss_cls: 0.6787 d3.loss_bbox: 0.1939 d4.loss_cls: 0.6805 d4.loss_bbox: 0.1912 2024/04/09 07:47:50 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 07:48:23 - mmengine - INFO - Epoch(train) [11][ 300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:30:48 time: 3.1606 data_time: 0.1817 memory: 28713 grad_norm: 19.6126 loss: 5.6211 loss_cls: 0.7028 loss_bbox: 0.2050 d0.loss_cls: 0.7882 d0.loss_bbox: 0.2198 d1.loss_cls: 0.7449 d1.loss_bbox: 0.2069 d2.loss_cls: 0.7217 d2.loss_bbox: 0.2063 d3.loss_cls: 0.7146 d3.loss_bbox: 0.2037 d4.loss_cls: 0.7047 d4.loss_bbox: 0.2024 2024/04/09 07:50:59 - mmengine - INFO - Epoch(train) [11][ 350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:27:53 time: 3.1276 data_time: 0.2029 memory: 28989 grad_norm: 19.9132 loss: 5.6529 loss_cls: 0.6971 loss_bbox: 0.2180 d0.loss_cls: 0.7879 d0.loss_bbox: 0.2279 d1.loss_cls: 0.7423 d1.loss_bbox: 0.2190 d2.loss_cls: 0.7095 d2.loss_bbox: 0.2165 d3.loss_cls: 0.7006 d3.loss_bbox: 0.2204 d4.loss_cls: 0.6973 d4.loss_bbox: 0.2166 2024/04/09 07:53:33 - mmengine - INFO - Epoch(train) [11][ 400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:24:57 time: 3.0715 data_time: 0.1871 memory: 29519 grad_norm: 20.1905 loss: 5.6962 loss_cls: 0.7100 loss_bbox: 0.2078 d0.loss_cls: 0.8073 d0.loss_bbox: 0.2253 d1.loss_cls: 0.7640 d1.loss_bbox: 0.2114 d2.loss_cls: 0.7208 d2.loss_bbox: 0.2130 d3.loss_cls: 0.7130 d3.loss_bbox: 0.2073 d4.loss_cls: 0.7108 d4.loss_bbox: 0.2054 2024/04/09 07:56:12 - mmengine - INFO - Epoch(train) [11][ 450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:22:05 time: 3.1940 data_time: 0.1854 memory: 29120 grad_norm: 19.9079 loss: 5.4568 loss_cls: 0.6757 loss_bbox: 0.1986 d0.loss_cls: 0.7655 d0.loss_bbox: 0.2248 d1.loss_cls: 0.7215 d1.loss_bbox: 0.2061 d2.loss_cls: 0.6868 d2.loss_bbox: 0.2047 d3.loss_cls: 0.6861 d3.loss_bbox: 0.2026 d4.loss_cls: 0.6882 d4.loss_bbox: 0.1962 2024/04/09 07:58:51 - mmengine - INFO - Epoch(train) [11][ 500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:19:12 time: 3.1682 data_time: 0.2200 memory: 29026 grad_norm: 19.8613 loss: 5.3265 loss_cls: 0.6498 loss_bbox: 0.2031 d0.loss_cls: 0.7424 d0.loss_bbox: 0.2208 d1.loss_cls: 0.6946 d1.loss_bbox: 0.2150 d2.loss_cls: 0.6746 d2.loss_bbox: 0.2096 d3.loss_cls: 0.6535 d3.loss_bbox: 0.2064 d4.loss_cls: 0.6528 d4.loss_bbox: 0.2039 2024/04/09 08:01:31 - mmengine - INFO - Epoch(train) [11][ 550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:16:21 time: 3.1983 data_time: 0.1712 memory: 29103 grad_norm: 20.2125 loss: 5.4132 loss_cls: 0.6490 loss_bbox: 0.2081 d0.loss_cls: 0.7716 d0.loss_bbox: 0.2233 d1.loss_cls: 0.7234 d1.loss_bbox: 0.2099 d2.loss_cls: 0.6814 d2.loss_bbox: 0.2097 d3.loss_cls: 0.6686 d3.loss_bbox: 0.2064 d4.loss_cls: 0.6560 d4.loss_bbox: 0.2060 2024/04/09 08:04:07 - mmengine - INFO - Epoch(train) [11][ 600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:13:27 time: 3.1269 data_time: 0.1804 memory: 28164 grad_norm: 21.3988 loss: 5.5255 loss_cls: 0.6921 loss_bbox: 0.2023 d0.loss_cls: 0.7820 d0.loss_bbox: 0.2136 d1.loss_cls: 0.7308 d1.loss_bbox: 0.2082 d2.loss_cls: 0.7067 d2.loss_bbox: 0.2070 d3.loss_cls: 0.6919 d3.loss_bbox: 0.2045 d4.loss_cls: 0.6868 d4.loss_bbox: 0.1995 2024/04/09 08:06:44 - mmengine - INFO - Epoch(train) [11][ 650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:10:34 time: 3.1439 data_time: 0.2061 memory: 28066 grad_norm: 20.8355 loss: 5.5472 loss_cls: 0.6883 loss_bbox: 0.1985 d0.loss_cls: 0.7997 d0.loss_bbox: 0.2204 d1.loss_cls: 0.7478 d1.loss_bbox: 0.2075 d2.loss_cls: 0.7089 d2.loss_bbox: 0.2043 d3.loss_cls: 0.6843 d3.loss_bbox: 0.2011 d4.loss_cls: 0.6881 d4.loss_bbox: 0.1983 2024/04/09 08:09:20 - mmengine - INFO - Epoch(train) [11][ 700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:07:41 time: 3.1105 data_time: 0.1906 memory: 28539 grad_norm: 20.4243 loss: 5.4863 loss_cls: 0.6676 loss_bbox: 0.2166 d0.loss_cls: 0.7558 d0.loss_bbox: 0.2320 d1.loss_cls: 0.7154 d1.loss_bbox: 0.2167 d2.loss_cls: 0.6925 d2.loss_bbox: 0.2134 d3.loss_cls: 0.6757 d3.loss_bbox: 0.2135 d4.loss_cls: 0.6691 d4.loss_bbox: 0.2179 2024/04/09 08:11:58 - mmengine - INFO - Epoch(train) [11][ 750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:04:48 time: 3.1561 data_time: 0.1911 memory: 28291 grad_norm: 19.3599 loss: 5.5542 loss_cls: 0.6803 loss_bbox: 0.2109 d0.loss_cls: 0.7725 d0.loss_bbox: 0.2355 d1.loss_cls: 0.7239 d1.loss_bbox: 0.2221 d2.loss_cls: 0.6997 d2.loss_bbox: 0.2181 d3.loss_cls: 0.6854 d3.loss_bbox: 0.2137 d4.loss_cls: 0.6800 d4.loss_bbox: 0.2122 2024/04/09 08:14:33 - mmengine - INFO - Epoch(train) [11][ 800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 4:01:55 time: 3.0957 data_time: 0.1765 memory: 28114 grad_norm: 20.0108 loss: 5.5490 loss_cls: 0.7000 loss_bbox: 0.1934 d0.loss_cls: 0.7899 d0.loss_bbox: 0.2122 d1.loss_cls: 0.7398 d1.loss_bbox: 0.2045 d2.loss_cls: 0.7206 d2.loss_bbox: 0.1985 d3.loss_cls: 0.6987 d3.loss_bbox: 0.1959 d4.loss_cls: 0.6997 d4.loss_bbox: 0.1959 2024/04/09 08:17:12 - mmengine - INFO - Epoch(train) [11][ 850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:59:04 time: 3.1961 data_time: 0.1825 memory: 28770 grad_norm: 20.7722 loss: 5.6611 loss_cls: 0.7108 loss_bbox: 0.1993 d0.loss_cls: 0.8084 d0.loss_bbox: 0.2193 d1.loss_cls: 0.7564 d1.loss_bbox: 0.2051 d2.loss_cls: 0.7273 d2.loss_bbox: 0.2023 d3.loss_cls: 0.7231 d3.loss_bbox: 0.2032 d4.loss_cls: 0.7064 d4.loss_bbox: 0.1993 2024/04/09 08:19:49 - mmengine - INFO - Epoch(train) [11][ 900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:56:12 time: 3.1257 data_time: 0.1909 memory: 28338 grad_norm: 20.8516 loss: 5.3058 loss_cls: 0.6444 loss_bbox: 0.2002 d0.loss_cls: 0.7525 d0.loss_bbox: 0.2076 d1.loss_cls: 0.7030 d1.loss_bbox: 0.2040 d2.loss_cls: 0.6826 d2.loss_bbox: 0.1994 d3.loss_cls: 0.6604 d3.loss_bbox: 0.2006 d4.loss_cls: 0.6496 d4.loss_bbox: 0.2016 2024/04/09 08:22:32 - mmengine - INFO - Epoch(train) [11][ 950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:53:23 time: 3.2748 data_time: 0.2200 memory: 28393 grad_norm: 20.7304 loss: 5.4175 loss_cls: 0.6785 loss_bbox: 0.2024 d0.loss_cls: 0.7543 d0.loss_bbox: 0.2159 d1.loss_cls: 0.7121 d1.loss_bbox: 0.2071 d2.loss_cls: 0.6926 d2.loss_bbox: 0.2003 d3.loss_cls: 0.6760 d3.loss_bbox: 0.1983 d4.loss_cls: 0.6805 d4.loss_bbox: 0.1994 2024/04/09 08:25:06 - mmengine - INFO - Epoch(train) [11][1000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:50:30 time: 3.0734 data_time: 0.1893 memory: 27979 grad_norm: 20.8607 loss: 5.5391 loss_cls: 0.6869 loss_bbox: 0.1997 d0.loss_cls: 0.7809 d0.loss_bbox: 0.2196 d1.loss_cls: 0.7360 d1.loss_bbox: 0.2108 d2.loss_cls: 0.7117 d2.loss_bbox: 0.2028 d3.loss_cls: 0.7038 d3.loss_bbox: 0.1960 d4.loss_cls: 0.6896 d4.loss_bbox: 0.2013 2024/04/09 08:27:45 - mmengine - INFO - Epoch(train) [11][1050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:47:39 time: 3.1778 data_time: 0.1782 memory: 28305 grad_norm: 19.8541 loss: 5.6067 loss_cls: 0.6780 loss_bbox: 0.2214 d0.loss_cls: 0.7723 d0.loss_bbox: 0.2419 d1.loss_cls: 0.7249 d1.loss_bbox: 0.2289 d2.loss_cls: 0.7059 d2.loss_bbox: 0.2206 d3.loss_cls: 0.6861 d3.loss_bbox: 0.2211 d4.loss_cls: 0.6865 d4.loss_bbox: 0.2192 2024/04/09 08:30:23 - mmengine - INFO - Epoch(train) [11][1100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:44:48 time: 3.1711 data_time: 0.1932 memory: 28078 grad_norm: 20.5030 loss: 5.5102 loss_cls: 0.6903 loss_bbox: 0.2042 d0.loss_cls: 0.7661 d0.loss_bbox: 0.2241 d1.loss_cls: 0.7208 d1.loss_bbox: 0.2115 d2.loss_cls: 0.7032 d2.loss_bbox: 0.2069 d3.loss_cls: 0.6839 d3.loss_bbox: 0.2047 d4.loss_cls: 0.6868 d4.loss_bbox: 0.2078 2024/04/09 08:32:58 - mmengine - INFO - Epoch(train) [11][1150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:41:56 time: 3.0926 data_time: 0.1962 memory: 28026 grad_norm: 19.6074 loss: 5.5292 loss_cls: 0.7006 loss_bbox: 0.1949 d0.loss_cls: 0.7679 d0.loss_bbox: 0.2129 d1.loss_cls: 0.7380 d1.loss_bbox: 0.2048 d2.loss_cls: 0.7153 d2.loss_bbox: 0.1995 d3.loss_cls: 0.7097 d3.loss_bbox: 0.1916 d4.loss_cls: 0.6999 d4.loss_bbox: 0.1940 2024/04/09 08:35:35 - mmengine - INFO - Epoch(train) [11][1200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:39:04 time: 3.1292 data_time: 0.1765 memory: 28860 grad_norm: 20.2576 loss: 5.7275 loss_cls: 0.7157 loss_bbox: 0.2130 d0.loss_cls: 0.8148 d0.loss_bbox: 0.2173 d1.loss_cls: 0.7568 d1.loss_bbox: 0.2103 d2.loss_cls: 0.7399 d2.loss_bbox: 0.2116 d3.loss_cls: 0.7165 d3.loss_bbox: 0.2109 d4.loss_cls: 0.7088 d4.loss_bbox: 0.2119 2024/04/09 08:38:10 - mmengine - INFO - Epoch(train) [11][1250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:36:13 time: 3.1005 data_time: 0.1981 memory: 28531 grad_norm: 19.9954 loss: 5.4633 loss_cls: 0.6795 loss_bbox: 0.1984 d0.loss_cls: 0.7839 d0.loss_bbox: 0.2097 d1.loss_cls: 0.7252 d1.loss_bbox: 0.1984 d2.loss_cls: 0.7009 d2.loss_bbox: 0.1932 d3.loss_cls: 0.6914 d3.loss_bbox: 0.1955 d4.loss_cls: 0.6902 d4.loss_bbox: 0.1970 2024/04/09 08:40:13 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 08:40:49 - mmengine - INFO - Epoch(train) [11][1300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:33:23 time: 3.1804 data_time: 0.1974 memory: 28108 grad_norm: 19.6272 loss: 5.2802 loss_cls: 0.6587 loss_bbox: 0.1888 d0.loss_cls: 0.7469 d0.loss_bbox: 0.2055 d1.loss_cls: 0.7018 d1.loss_bbox: 0.1990 d2.loss_cls: 0.6772 d2.loss_bbox: 0.1914 d3.loss_cls: 0.6701 d3.loss_bbox: 0.1877 d4.loss_cls: 0.6657 d4.loss_bbox: 0.1875 2024/04/09 08:43:24 - mmengine - INFO - Epoch(train) [11][1350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:30:31 time: 3.1011 data_time: 0.1938 memory: 28380 grad_norm: 20.5243 loss: 5.7125 loss_cls: 0.7087 loss_bbox: 0.2132 d0.loss_cls: 0.8069 d0.loss_bbox: 0.2317 d1.loss_cls: 0.7405 d1.loss_bbox: 0.2230 d2.loss_cls: 0.7213 d2.loss_bbox: 0.2204 d3.loss_cls: 0.7070 d3.loss_bbox: 0.2155 d4.loss_cls: 0.7085 d4.loss_bbox: 0.2160 2024/04/09 08:46:03 - mmengine - INFO - Epoch(train) [11][1400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:27:42 time: 3.1845 data_time: 0.1982 memory: 29083 grad_norm: 20.0890 loss: 5.1857 loss_cls: 0.6265 loss_bbox: 0.2068 d0.loss_cls: 0.7203 d0.loss_bbox: 0.2187 d1.loss_cls: 0.6694 d1.loss_bbox: 0.2119 d2.loss_cls: 0.6402 d2.loss_bbox: 0.2075 d3.loss_cls: 0.6397 d3.loss_bbox: 0.2064 d4.loss_cls: 0.6323 d4.loss_bbox: 0.2059 2024/04/09 08:48:42 - mmengine - INFO - Epoch(train) [11][1450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:24:52 time: 3.1836 data_time: 0.1994 memory: 28985 grad_norm: 21.0582 loss: 5.4921 loss_cls: 0.6842 loss_bbox: 0.1978 d0.loss_cls: 0.7813 d0.loss_bbox: 0.2146 d1.loss_cls: 0.7301 d1.loss_bbox: 0.2046 d2.loss_cls: 0.7042 d2.loss_bbox: 0.2015 d3.loss_cls: 0.6908 d3.loss_bbox: 0.1985 d4.loss_cls: 0.6873 d4.loss_bbox: 0.1972 2024/04/09 08:51:22 - mmengine - INFO - Epoch(train) [11][1500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:22:03 time: 3.2059 data_time: 0.3223 memory: 29520 grad_norm: 21.1509 loss: 5.6604 loss_cls: 0.6921 loss_bbox: 0.2174 d0.loss_cls: 0.7776 d0.loss_bbox: 0.2505 d1.loss_cls: 0.7330 d1.loss_bbox: 0.2349 d2.loss_cls: 0.7122 d2.loss_bbox: 0.2222 d3.loss_cls: 0.6947 d3.loss_bbox: 0.2140 d4.loss_cls: 0.6935 d4.loss_bbox: 0.2182 2024/04/09 08:53:54 - mmengine - INFO - Epoch(train) [11][1550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:19:11 time: 3.0293 data_time: 0.1729 memory: 28444 grad_norm: 20.2267 loss: 5.5703 loss_cls: 0.6927 loss_bbox: 0.2054 d0.loss_cls: 0.7762 d0.loss_bbox: 0.2243 d1.loss_cls: 0.7319 d1.loss_bbox: 0.2113 d2.loss_cls: 0.7132 d2.loss_bbox: 0.2072 d3.loss_cls: 0.7004 d3.loss_bbox: 0.2026 d4.loss_cls: 0.7003 d4.loss_bbox: 0.2046 2024/04/09 08:56:31 - mmengine - INFO - Epoch(train) [11][1600/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:16:21 time: 3.1409 data_time: 0.1870 memory: 30004 grad_norm: 20.4919 loss: 5.5531 loss_cls: 0.6857 loss_bbox: 0.2118 d0.loss_cls: 0.7723 d0.loss_bbox: 0.2267 d1.loss_cls: 0.7293 d1.loss_bbox: 0.2190 d2.loss_cls: 0.6972 d2.loss_bbox: 0.2132 d3.loss_cls: 0.6872 d3.loss_bbox: 0.2116 d4.loss_cls: 0.6883 d4.loss_bbox: 0.2107 2024/04/09 08:59:03 - mmengine - INFO - Epoch(train) [11][1650/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:13:29 time: 3.0388 data_time: 0.1855 memory: 29004 grad_norm: 19.6497 loss: 5.4366 loss_cls: 0.6798 loss_bbox: 0.2044 d0.loss_cls: 0.7602 d0.loss_bbox: 0.2227 d1.loss_cls: 0.7158 d1.loss_bbox: 0.2069 d2.loss_cls: 0.6913 d2.loss_bbox: 0.2031 d3.loss_cls: 0.6743 d3.loss_bbox: 0.2042 d4.loss_cls: 0.6696 d4.loss_bbox: 0.2042 2024/04/09 09:01:40 - mmengine - INFO - Epoch(train) [11][1700/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:10:40 time: 3.1407 data_time: 0.1832 memory: 29918 grad_norm: 20.5256 loss: 5.4692 loss_cls: 0.6880 loss_bbox: 0.1932 d0.loss_cls: 0.7755 d0.loss_bbox: 0.2127 d1.loss_cls: 0.7276 d1.loss_bbox: 0.1981 d2.loss_cls: 0.7080 d2.loss_bbox: 0.1978 d3.loss_cls: 0.6949 d3.loss_bbox: 0.1921 d4.loss_cls: 0.6865 d4.loss_bbox: 0.1948 2024/04/09 09:04:33 - mmengine - INFO - Epoch(train) [11][1750/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:07:56 time: 3.4662 data_time: 0.1938 memory: 28749 grad_norm: 21.5469 loss: 5.6747 loss_cls: 0.7057 loss_bbox: 0.2113 d0.loss_cls: 0.7956 d0.loss_bbox: 0.2265 d1.loss_cls: 0.7539 d1.loss_bbox: 0.2180 d2.loss_cls: 0.7203 d2.loss_bbox: 0.2114 d3.loss_cls: 0.7019 d3.loss_bbox: 0.2126 d4.loss_cls: 0.7056 d4.loss_bbox: 0.2119 2024/04/09 09:07:09 - mmengine - INFO - Epoch(train) [11][1800/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:05:06 time: 3.1079 data_time: 0.2030 memory: 31576 grad_norm: 21.2655 loss: 5.4152 loss_cls: 0.6529 loss_bbox: 0.2220 d0.loss_cls: 0.7399 d0.loss_bbox: 0.2383 d1.loss_cls: 0.7021 d1.loss_bbox: 0.2244 d2.loss_cls: 0.6690 d2.loss_bbox: 0.2186 d3.loss_cls: 0.6552 d3.loss_bbox: 0.2198 d4.loss_cls: 0.6523 d4.loss_bbox: 0.2208 2024/04/09 09:09:41 - mmengine - INFO - Epoch(train) [11][1850/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 3:02:15 time: 3.0513 data_time: 0.1989 memory: 27834 grad_norm: 20.2607 loss: 5.6010 loss_cls: 0.7064 loss_bbox: 0.1941 d0.loss_cls: 0.8099 d0.loss_bbox: 0.2057 d1.loss_cls: 0.7459 d1.loss_bbox: 0.2037 d2.loss_cls: 0.7224 d2.loss_bbox: 0.1988 d3.loss_cls: 0.7118 d3.loss_bbox: 0.1959 d4.loss_cls: 0.7112 d4.loss_bbox: 0.1952 2024/04/09 09:12:19 - mmengine - INFO - Epoch(train) [11][1900/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:59:26 time: 3.1515 data_time: 0.2116 memory: 28751 grad_norm: 20.3313 loss: 5.5978 loss_cls: 0.6821 loss_bbox: 0.2192 d0.loss_cls: 0.7623 d0.loss_bbox: 0.2330 d1.loss_cls: 0.7363 d1.loss_bbox: 0.2249 d2.loss_cls: 0.7096 d2.loss_bbox: 0.2207 d3.loss_cls: 0.6862 d3.loss_bbox: 0.2195 d4.loss_cls: 0.6871 d4.loss_bbox: 0.2168 2024/04/09 09:14:56 - mmengine - INFO - Epoch(train) [11][1950/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:56:37 time: 3.1414 data_time: 0.2144 memory: 29253 grad_norm: 19.6718 loss: 5.5001 loss_cls: 0.6779 loss_bbox: 0.2058 d0.loss_cls: 0.7691 d0.loss_bbox: 0.2273 d1.loss_cls: 0.7262 d1.loss_bbox: 0.2138 d2.loss_cls: 0.6976 d2.loss_bbox: 0.2102 d3.loss_cls: 0.6849 d3.loss_bbox: 0.2082 d4.loss_cls: 0.6736 d4.loss_bbox: 0.2054 2024/04/09 09:17:32 - mmengine - INFO - Epoch(train) [11][2000/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:53:48 time: 3.1297 data_time: 0.1792 memory: 28598 grad_norm: 21.0678 loss: 5.5604 loss_cls: 0.6888 loss_bbox: 0.2022 d0.loss_cls: 0.7852 d0.loss_bbox: 0.2246 d1.loss_cls: 0.7328 d1.loss_bbox: 0.2130 d2.loss_cls: 0.7070 d2.loss_bbox: 0.2078 d3.loss_cls: 0.6950 d3.loss_bbox: 0.2072 d4.loss_cls: 0.6946 d4.loss_bbox: 0.2022 2024/04/09 09:20:05 - mmengine - INFO - Epoch(train) [11][2050/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:50:58 time: 3.0528 data_time: 0.2071 memory: 28326 grad_norm: 20.4919 loss: 5.3434 loss_cls: 0.6638 loss_bbox: 0.1944 d0.loss_cls: 0.7677 d0.loss_bbox: 0.2142 d1.loss_cls: 0.7019 d1.loss_bbox: 0.2019 d2.loss_cls: 0.6724 d2.loss_bbox: 0.1979 d3.loss_cls: 0.6734 d3.loss_bbox: 0.1956 d4.loss_cls: 0.6652 d4.loss_bbox: 0.1949 2024/04/09 09:22:42 - mmengine - INFO - Epoch(train) [11][2100/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:48:09 time: 3.1383 data_time: 0.1864 memory: 29197 grad_norm: 19.5659 loss: 5.5144 loss_cls: 0.6911 loss_bbox: 0.1961 d0.loss_cls: 0.7959 d0.loss_bbox: 0.2128 d1.loss_cls: 0.7362 d1.loss_bbox: 0.2016 d2.loss_cls: 0.7083 d2.loss_bbox: 0.1977 d3.loss_cls: 0.6903 d3.loss_bbox: 0.1968 d4.loss_cls: 0.6900 d4.loss_bbox: 0.1974 2024/04/09 09:25:18 - mmengine - INFO - Epoch(train) [11][2150/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:45:21 time: 3.1262 data_time: 0.2088 memory: 27955 grad_norm: 19.6268 loss: 5.3712 loss_cls: 0.6610 loss_bbox: 0.1999 d0.loss_cls: 0.7493 d0.loss_bbox: 0.2217 d1.loss_cls: 0.7049 d1.loss_bbox: 0.2053 d2.loss_cls: 0.6800 d2.loss_bbox: 0.2073 d3.loss_cls: 0.6674 d3.loss_bbox: 0.2034 d4.loss_cls: 0.6721 d4.loss_bbox: 0.1988 2024/04/09 09:27:52 - mmengine - INFO - Epoch(train) [11][2200/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:42:31 time: 3.0816 data_time: 0.1702 memory: 28159 grad_norm: 20.5042 loss: 5.6215 loss_cls: 0.7030 loss_bbox: 0.2030 d0.loss_cls: 0.7951 d0.loss_bbox: 0.2181 d1.loss_cls: 0.7355 d1.loss_bbox: 0.2122 d2.loss_cls: 0.7217 d2.loss_bbox: 0.2074 d3.loss_cls: 0.7122 d3.loss_bbox: 0.2034 d4.loss_cls: 0.7088 d4.loss_bbox: 0.2011 2024/04/09 09:30:27 - mmengine - INFO - Epoch(train) [11][2250/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:39:42 time: 3.0858 data_time: 0.2027 memory: 28061 grad_norm: 19.8106 loss: 5.4732 loss_cls: 0.6854 loss_bbox: 0.1987 d0.loss_cls: 0.7780 d0.loss_bbox: 0.2174 d1.loss_cls: 0.7175 d1.loss_bbox: 0.2055 d2.loss_cls: 0.6953 d2.loss_bbox: 0.2032 d3.loss_cls: 0.6864 d3.loss_bbox: 0.1985 d4.loss_cls: 0.6882 d4.loss_bbox: 0.1990 2024/04/09 09:32:31 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 09:33:02 - mmengine - INFO - Epoch(train) [11][2300/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:36:54 time: 3.1059 data_time: 0.2011 memory: 28322 grad_norm: 20.2436 loss: 5.4423 loss_cls: 0.6720 loss_bbox: 0.2060 d0.loss_cls: 0.7570 d0.loss_bbox: 0.2220 d1.loss_cls: 0.7087 d1.loss_bbox: 0.2119 d2.loss_cls: 0.6917 d2.loss_bbox: 0.2060 d3.loss_cls: 0.6808 d3.loss_bbox: 0.2059 d4.loss_cls: 0.6719 d4.loss_bbox: 0.2084 2024/04/09 09:35:41 - mmengine - INFO - Epoch(train) [11][2350/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:34:06 time: 3.1785 data_time: 0.2020 memory: 28709 grad_norm: 20.5869 loss: 5.3811 loss_cls: 0.6799 loss_bbox: 0.1878 d0.loss_cls: 0.7651 d0.loss_bbox: 0.2006 d1.loss_cls: 0.7252 d1.loss_bbox: 0.1922 d2.loss_cls: 0.6958 d2.loss_bbox: 0.1909 d3.loss_cls: 0.6887 d3.loss_bbox: 0.1895 d4.loss_cls: 0.6750 d4.loss_bbox: 0.1904 2024/04/09 09:38:10 - mmengine - INFO - Epoch(train) [11][2400/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:31:16 time: 2.9918 data_time: 0.1889 memory: 28186 grad_norm: 20.0851 loss: 5.5762 loss_cls: 0.7099 loss_bbox: 0.1893 d0.loss_cls: 0.7984 d0.loss_bbox: 0.2062 d1.loss_cls: 0.7585 d1.loss_bbox: 0.1928 d2.loss_cls: 0.7258 d2.loss_bbox: 0.1926 d3.loss_cls: 0.7137 d3.loss_bbox: 0.1904 d4.loss_cls: 0.7090 d4.loss_bbox: 0.1896 2024/04/09 09:40:45 - mmengine - INFO - Epoch(train) [11][2450/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:28:28 time: 3.0896 data_time: 0.1896 memory: 29102 grad_norm: 20.7571 loss: 5.3709 loss_cls: 0.6707 loss_bbox: 0.1949 d0.loss_cls: 0.7628 d0.loss_bbox: 0.2097 d1.loss_cls: 0.7116 d1.loss_bbox: 0.2002 d2.loss_cls: 0.6913 d2.loss_bbox: 0.1958 d3.loss_cls: 0.6770 d3.loss_bbox: 0.1927 d4.loss_cls: 0.6713 d4.loss_bbox: 0.1929 2024/04/09 09:43:15 - mmengine - INFO - Epoch(train) [11][2500/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:25:38 time: 3.0020 data_time: 0.1840 memory: 28789 grad_norm: 20.8227 loss: 5.2951 loss_cls: 0.6567 loss_bbox: 0.1888 d0.loss_cls: 0.7660 d0.loss_bbox: 0.2092 d1.loss_cls: 0.7084 d1.loss_bbox: 0.1919 d2.loss_cls: 0.6817 d2.loss_bbox: 0.1932 d3.loss_cls: 0.6622 d3.loss_bbox: 0.1935 d4.loss_cls: 0.6539 d4.loss_bbox: 0.1895 2024/04/09 09:45:57 - mmengine - INFO - Epoch(train) [11][2550/2571] base_lr: 5.0000e-05 lr: 5.0000e-05 eta: 2:22:52 time: 3.2449 data_time: 0.1710 memory: 28943 grad_norm: 19.9350 loss: 5.4705 loss_cls: 0.6788 loss_bbox: 0.2053 d0.loss_cls: 0.7765 d0.loss_bbox: 0.2250 d1.loss_cls: 0.7155 d1.loss_bbox: 0.2140 d2.loss_cls: 0.6926 d2.loss_bbox: 0.2062 d3.loss_cls: 0.6781 d3.loss_bbox: 0.2020 d4.loss_cls: 0.6726 d4.loss_bbox: 0.2041 2024/04/09 09:46:54 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 09:46:54 - mmengine - INFO - Saving checkpoint at 11 epochs 2024/04/09 09:50:27 - mmengine - INFO - Epoch(train) [12][ 50/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:19:03 time: 3.9809 data_time: 0.9587 memory: 29109 grad_norm: 20.3225 loss: 5.7846 loss_cls: 0.7117 loss_bbox: 0.2188 d0.loss_cls: 0.8131 d0.loss_bbox: 0.2394 d1.loss_cls: 0.7566 d1.loss_bbox: 0.2269 d2.loss_cls: 0.7319 d2.loss_bbox: 0.2197 d3.loss_cls: 0.7149 d3.loss_bbox: 0.2174 d4.loss_cls: 0.7154 d4.loss_bbox: 0.2189 2024/04/09 09:53:02 - mmengine - INFO - Epoch(train) [12][ 100/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:16:15 time: 3.1094 data_time: 0.1817 memory: 28286 grad_norm: 20.4039 loss: 5.6426 loss_cls: 0.6971 loss_bbox: 0.2161 d0.loss_cls: 0.7871 d0.loss_bbox: 0.2304 d1.loss_cls: 0.7321 d1.loss_bbox: 0.2186 d2.loss_cls: 0.7077 d2.loss_bbox: 0.2176 d3.loss_cls: 0.6986 d3.loss_bbox: 0.2164 d4.loss_cls: 0.7027 d4.loss_bbox: 0.2180 2024/04/09 09:55:38 - mmengine - INFO - Epoch(train) [12][ 150/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:13:27 time: 3.1053 data_time: 0.1822 memory: 28782 grad_norm: 19.8476 loss: 5.5901 loss_cls: 0.7071 loss_bbox: 0.1945 d0.loss_cls: 0.7941 d0.loss_bbox: 0.2143 d1.loss_cls: 0.7468 d1.loss_bbox: 0.2010 d2.loss_cls: 0.7211 d2.loss_bbox: 0.2007 d3.loss_cls: 0.7110 d3.loss_bbox: 0.1956 d4.loss_cls: 0.7116 d4.loss_bbox: 0.1922 2024/04/09 09:58:11 - mmengine - INFO - Epoch(train) [12][ 200/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:10:39 time: 3.0612 data_time: 0.1940 memory: 28074 grad_norm: 20.1693 loss: 5.4170 loss_cls: 0.6686 loss_bbox: 0.2034 d0.loss_cls: 0.7504 d0.loss_bbox: 0.2280 d1.loss_cls: 0.7062 d1.loss_bbox: 0.2167 d2.loss_cls: 0.6887 d2.loss_bbox: 0.2048 d3.loss_cls: 0.6749 d3.loss_bbox: 0.2023 d4.loss_cls: 0.6729 d4.loss_bbox: 0.2002 2024/04/09 10:00:55 - mmengine - INFO - Epoch(train) [12][ 250/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:07:53 time: 3.2952 data_time: 0.2136 memory: 28281 grad_norm: 19.9304 loss: 5.5384 loss_cls: 0.6923 loss_bbox: 0.2004 d0.loss_cls: 0.7907 d0.loss_bbox: 0.2179 d1.loss_cls: 0.7235 d1.loss_bbox: 0.2118 d2.loss_cls: 0.7040 d2.loss_bbox: 0.2075 d3.loss_cls: 0.6912 d3.loss_bbox: 0.2069 d4.loss_cls: 0.6905 d4.loss_bbox: 0.2017 2024/04/09 10:03:30 - mmengine - INFO - Epoch(train) [12][ 300/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:05:06 time: 3.0881 data_time: 0.1993 memory: 28397 grad_norm: 20.9995 loss: 5.4181 loss_cls: 0.6689 loss_bbox: 0.2037 d0.loss_cls: 0.7720 d0.loss_bbox: 0.2153 d1.loss_cls: 0.7067 d1.loss_bbox: 0.2094 d2.loss_cls: 0.6821 d2.loss_bbox: 0.2080 d3.loss_cls: 0.6708 d3.loss_bbox: 0.2024 d4.loss_cls: 0.6730 d4.loss_bbox: 0.2057 2024/04/09 10:06:02 - mmengine - INFO - Epoch(train) [12][ 350/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 2:02:18 time: 3.0467 data_time: 0.1917 memory: 28463 grad_norm: 19.6529 loss: 5.3914 loss_cls: 0.6670 loss_bbox: 0.2002 d0.loss_cls: 0.7479 d0.loss_bbox: 0.2221 d1.loss_cls: 0.7116 d1.loss_bbox: 0.2098 d2.loss_cls: 0.6919 d2.loss_bbox: 0.1995 d3.loss_cls: 0.6741 d3.loss_bbox: 0.2003 d4.loss_cls: 0.6689 d4.loss_bbox: 0.1980 2024/04/09 10:08:34 - mmengine - INFO - Epoch(train) [12][ 400/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:59:30 time: 3.0370 data_time: 0.1943 memory: 29308 grad_norm: 20.1583 loss: 5.3488 loss_cls: 0.6502 loss_bbox: 0.2107 d0.loss_cls: 0.7482 d0.loss_bbox: 0.2183 d1.loss_cls: 0.6901 d1.loss_bbox: 0.2139 d2.loss_cls: 0.6702 d2.loss_bbox: 0.2084 d3.loss_cls: 0.6656 d3.loss_bbox: 0.2089 d4.loss_cls: 0.6562 d4.loss_bbox: 0.2082 2024/04/09 10:11:07 - mmengine - INFO - Epoch(train) [12][ 450/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:56:42 time: 3.0554 data_time: 0.2030 memory: 28278 grad_norm: 19.9635 loss: 5.4925 loss_cls: 0.6936 loss_bbox: 0.1964 d0.loss_cls: 0.7878 d0.loss_bbox: 0.2083 d1.loss_cls: 0.7379 d1.loss_bbox: 0.1941 d2.loss_cls: 0.7093 d2.loss_bbox: 0.1967 d3.loss_cls: 0.6951 d3.loss_bbox: 0.1951 d4.loss_cls: 0.6839 d4.loss_bbox: 0.1942 2024/04/09 10:13:41 - mmengine - INFO - Epoch(train) [12][ 500/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:53:55 time: 3.0925 data_time: 0.2136 memory: 29684 grad_norm: 19.8088 loss: 5.7706 loss_cls: 0.7067 loss_bbox: 0.2146 d0.loss_cls: 0.8204 d0.loss_bbox: 0.2395 d1.loss_cls: 0.7659 d1.loss_bbox: 0.2189 d2.loss_cls: 0.7317 d2.loss_bbox: 0.2199 d3.loss_cls: 0.7196 d3.loss_bbox: 0.2132 d4.loss_cls: 0.7093 d4.loss_bbox: 0.2109 2024/04/09 10:16:32 - mmengine - INFO - Epoch(train) [12][ 550/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:51:11 time: 3.4204 data_time: 0.1882 memory: 28650 grad_norm: 19.6245 loss: 5.5533 loss_cls: 0.6868 loss_bbox: 0.2011 d0.loss_cls: 0.7817 d0.loss_bbox: 0.2210 d1.loss_cls: 0.7416 d1.loss_bbox: 0.2104 d2.loss_cls: 0.7140 d2.loss_bbox: 0.2079 d3.loss_cls: 0.6917 d3.loss_bbox: 0.2021 d4.loss_cls: 0.6921 d4.loss_bbox: 0.2028 2024/04/09 10:19:03 - mmengine - INFO - Epoch(train) [12][ 600/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:48:24 time: 3.0130 data_time: 0.2097 memory: 28452 grad_norm: 19.5238 loss: 5.4048 loss_cls: 0.6699 loss_bbox: 0.1982 d0.loss_cls: 0.7643 d0.loss_bbox: 0.2214 d1.loss_cls: 0.7011 d1.loss_bbox: 0.2113 d2.loss_cls: 0.6775 d2.loss_bbox: 0.2094 d3.loss_cls: 0.6783 d3.loss_bbox: 0.2021 d4.loss_cls: 0.6731 d4.loss_bbox: 0.1983 2024/04/09 10:21:43 - mmengine - INFO - Epoch(train) [12][ 650/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:45:38 time: 3.1974 data_time: 0.2051 memory: 29286 grad_norm: 20.1419 loss: 5.5858 loss_cls: 0.7052 loss_bbox: 0.1949 d0.loss_cls: 0.7873 d0.loss_bbox: 0.2296 d1.loss_cls: 0.7439 d1.loss_bbox: 0.2092 d2.loss_cls: 0.7194 d2.loss_bbox: 0.2014 d3.loss_cls: 0.7002 d3.loss_bbox: 0.1951 d4.loss_cls: 0.7054 d4.loss_bbox: 0.1941 2024/04/09 10:24:31 - mmengine - INFO - Epoch(train) [12][ 700/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:42:53 time: 3.3668 data_time: 0.5351 memory: 28881 grad_norm: 19.9976 loss: 5.4211 loss_cls: 0.6707 loss_bbox: 0.2045 d0.loss_cls: 0.7588 d0.loss_bbox: 0.2238 d1.loss_cls: 0.7079 d1.loss_bbox: 0.2105 d2.loss_cls: 0.6799 d2.loss_bbox: 0.2092 d3.loss_cls: 0.6740 d3.loss_bbox: 0.2056 d4.loss_cls: 0.6718 d4.loss_bbox: 0.2045 2024/04/09 10:25:30 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 10:27:12 - mmengine - INFO - Epoch(train) [12][ 750/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:40:08 time: 3.2101 data_time: 0.2897 memory: 28631 grad_norm: 20.4250 loss: 5.5159 loss_cls: 0.6944 loss_bbox: 0.2000 d0.loss_cls: 0.7797 d0.loss_bbox: 0.2194 d1.loss_cls: 0.7234 d1.loss_bbox: 0.2074 d2.loss_cls: 0.7029 d2.loss_bbox: 0.2038 d3.loss_cls: 0.6882 d3.loss_bbox: 0.2010 d4.loss_cls: 0.6970 d4.loss_bbox: 0.1986 2024/04/09 10:29:44 - mmengine - INFO - Epoch(train) [12][ 800/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:37:21 time: 3.0439 data_time: 0.1621 memory: 28559 grad_norm: 19.6533 loss: 5.7143 loss_cls: 0.7090 loss_bbox: 0.2077 d0.loss_cls: 0.8050 d0.loss_bbox: 0.2343 d1.loss_cls: 0.7654 d1.loss_bbox: 0.2177 d2.loss_cls: 0.7270 d2.loss_bbox: 0.2111 d3.loss_cls: 0.7122 d3.loss_bbox: 0.2069 d4.loss_cls: 0.7073 d4.loss_bbox: 0.2107 2024/04/09 10:32:20 - mmengine - INFO - Epoch(train) [12][ 850/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:34:34 time: 3.1263 data_time: 0.3006 memory: 28206 grad_norm: 20.5211 loss: 5.6587 loss_cls: 0.6987 loss_bbox: 0.2090 d0.loss_cls: 0.8031 d0.loss_bbox: 0.2215 d1.loss_cls: 0.7478 d1.loss_bbox: 0.2132 d2.loss_cls: 0.7265 d2.loss_bbox: 0.2105 d3.loss_cls: 0.7090 d3.loss_bbox: 0.2097 d4.loss_cls: 0.6984 d4.loss_bbox: 0.2112 2024/04/09 10:34:56 - mmengine - INFO - Epoch(train) [12][ 900/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:31:48 time: 3.1197 data_time: 0.2871 memory: 28676 grad_norm: 20.5583 loss: 5.5370 loss_cls: 0.6837 loss_bbox: 0.2000 d0.loss_cls: 0.7649 d0.loss_bbox: 0.2298 d1.loss_cls: 0.7325 d1.loss_bbox: 0.2160 d2.loss_cls: 0.7064 d2.loss_bbox: 0.2113 d3.loss_cls: 0.6924 d3.loss_bbox: 0.2087 d4.loss_cls: 0.6879 d4.loss_bbox: 0.2033 2024/04/09 10:37:35 - mmengine - INFO - Epoch(train) [12][ 950/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:29:02 time: 3.1735 data_time: 0.1795 memory: 28485 grad_norm: 20.9540 loss: 5.3966 loss_cls: 0.6765 loss_bbox: 0.1944 d0.loss_cls: 0.7691 d0.loss_bbox: 0.2059 d1.loss_cls: 0.7173 d1.loss_bbox: 0.1994 d2.loss_cls: 0.6959 d2.loss_bbox: 0.1998 d3.loss_cls: 0.6667 d3.loss_bbox: 0.1978 d4.loss_cls: 0.6764 d4.loss_bbox: 0.1973 2024/04/09 10:40:05 - mmengine - INFO - Epoch(train) [12][1000/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:26:15 time: 2.9971 data_time: 0.1852 memory: 28580 grad_norm: 20.4525 loss: 5.5208 loss_cls: 0.6926 loss_bbox: 0.2017 d0.loss_cls: 0.7869 d0.loss_bbox: 0.2180 d1.loss_cls: 0.7273 d1.loss_bbox: 0.2028 d2.loss_cls: 0.7059 d2.loss_bbox: 0.2022 d3.loss_cls: 0.6954 d3.loss_bbox: 0.1980 d4.loss_cls: 0.6904 d4.loss_bbox: 0.1997 2024/04/09 10:42:42 - mmengine - INFO - Epoch(train) [12][1050/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:23:30 time: 3.1496 data_time: 0.2050 memory: 28936 grad_norm: 19.2805 loss: 5.4905 loss_cls: 0.6901 loss_bbox: 0.2023 d0.loss_cls: 0.7669 d0.loss_bbox: 0.2197 d1.loss_cls: 0.7276 d1.loss_bbox: 0.2083 d2.loss_cls: 0.6938 d2.loss_bbox: 0.2060 d3.loss_cls: 0.6852 d3.loss_bbox: 0.2008 d4.loss_cls: 0.6880 d4.loss_bbox: 0.2019 2024/04/09 10:45:19 - mmengine - INFO - Epoch(train) [12][1100/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:20:44 time: 3.1235 data_time: 0.1874 memory: 28635 grad_norm: 19.4248 loss: 5.6019 loss_cls: 0.7017 loss_bbox: 0.2024 d0.loss_cls: 0.7842 d0.loss_bbox: 0.2214 d1.loss_cls: 0.7396 d1.loss_bbox: 0.2121 d2.loss_cls: 0.7210 d2.loss_bbox: 0.2052 d3.loss_cls: 0.7046 d3.loss_bbox: 0.2050 d4.loss_cls: 0.7014 d4.loss_bbox: 0.2032 2024/04/09 10:47:55 - mmengine - INFO - Epoch(train) [12][1150/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:17:58 time: 3.1334 data_time: 0.1795 memory: 28927 grad_norm: 19.7435 loss: 5.6099 loss_cls: 0.6985 loss_bbox: 0.2088 d0.loss_cls: 0.7988 d0.loss_bbox: 0.2239 d1.loss_cls: 0.7426 d1.loss_bbox: 0.2110 d2.loss_cls: 0.7167 d2.loss_bbox: 0.2062 d3.loss_cls: 0.6970 d3.loss_bbox: 0.2026 d4.loss_cls: 0.6989 d4.loss_bbox: 0.2049 2024/04/09 10:50:40 - mmengine - INFO - Epoch(train) [12][1200/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:15:14 time: 3.3021 data_time: 0.2088 memory: 28122 grad_norm: 20.3677 loss: 5.3655 loss_cls: 0.6569 loss_bbox: 0.1991 d0.loss_cls: 0.7667 d0.loss_bbox: 0.2151 d1.loss_cls: 0.7063 d1.loss_bbox: 0.2064 d2.loss_cls: 0.6836 d2.loss_bbox: 0.1997 d3.loss_cls: 0.6672 d3.loss_bbox: 0.1998 d4.loss_cls: 0.6674 d4.loss_bbox: 0.1975 2024/04/09 10:53:14 - mmengine - INFO - Epoch(train) [12][1250/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:12:28 time: 3.0769 data_time: 0.1797 memory: 29498 grad_norm: 19.8347 loss: 5.6903 loss_cls: 0.7064 loss_bbox: 0.2116 d0.loss_cls: 0.7977 d0.loss_bbox: 0.2317 d1.loss_cls: 0.7508 d1.loss_bbox: 0.2177 d2.loss_cls: 0.7261 d2.loss_bbox: 0.2105 d3.loss_cls: 0.7043 d3.loss_bbox: 0.2109 d4.loss_cls: 0.7089 d4.loss_bbox: 0.2138 2024/04/09 10:55:51 - mmengine - INFO - Epoch(train) [12][1300/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:09:42 time: 3.1278 data_time: 0.1925 memory: 29238 grad_norm: 19.5570 loss: 5.7158 loss_cls: 0.7072 loss_bbox: 0.2074 d0.loss_cls: 0.8160 d0.loss_bbox: 0.2262 d1.loss_cls: 0.7552 d1.loss_bbox: 0.2168 d2.loss_cls: 0.7381 d2.loss_bbox: 0.2124 d3.loss_cls: 0.7139 d3.loss_bbox: 0.2073 d4.loss_cls: 0.7075 d4.loss_bbox: 0.2080 2024/04/09 10:58:24 - mmengine - INFO - Epoch(train) [12][1350/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:06:57 time: 3.0775 data_time: 0.1743 memory: 30442 grad_norm: 20.4632 loss: 5.5152 loss_cls: 0.6854 loss_bbox: 0.2017 d0.loss_cls: 0.7727 d0.loss_bbox: 0.2325 d1.loss_cls: 0.7218 d1.loss_bbox: 0.2118 d2.loss_cls: 0.7035 d2.loss_bbox: 0.2082 d3.loss_cls: 0.6921 d3.loss_bbox: 0.2025 d4.loss_cls: 0.6805 d4.loss_bbox: 0.2023 2024/04/09 11:01:00 - mmengine - INFO - Epoch(train) [12][1400/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:04:11 time: 3.1099 data_time: 0.2031 memory: 28183 grad_norm: 20.5445 loss: 5.4747 loss_cls: 0.6987 loss_bbox: 0.1926 d0.loss_cls: 0.7689 d0.loss_bbox: 0.2081 d1.loss_cls: 0.7266 d1.loss_bbox: 0.2005 d2.loss_cls: 0.7083 d2.loss_bbox: 0.1963 d3.loss_cls: 0.6987 d3.loss_bbox: 0.1923 d4.loss_cls: 0.6895 d4.loss_bbox: 0.1940 2024/04/09 11:03:43 - mmengine - INFO - Epoch(train) [12][1450/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 1:01:27 time: 3.2648 data_time: 0.3795 memory: 27657 grad_norm: 20.3537 loss: 5.7329 loss_cls: 0.7203 loss_bbox: 0.1942 d0.loss_cls: 0.8285 d0.loss_bbox: 0.2234 d1.loss_cls: 0.7678 d1.loss_bbox: 0.2114 d2.loss_cls: 0.7480 d2.loss_bbox: 0.1983 d3.loss_cls: 0.7241 d3.loss_bbox: 0.1987 d4.loss_cls: 0.7215 d4.loss_bbox: 0.1965 2024/04/09 11:06:20 - mmengine - INFO - Epoch(train) [12][1500/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:58:42 time: 3.1359 data_time: 0.1713 memory: 29203 grad_norm: 20.1941 loss: 5.3670 loss_cls: 0.6524 loss_bbox: 0.2121 d0.loss_cls: 0.7382 d0.loss_bbox: 0.2274 d1.loss_cls: 0.6983 d1.loss_bbox: 0.2140 d2.loss_cls: 0.6761 d2.loss_bbox: 0.2124 d3.loss_cls: 0.6630 d3.loss_bbox: 0.2083 d4.loss_cls: 0.6537 d4.loss_bbox: 0.2110 2024/04/09 11:08:54 - mmengine - INFO - Epoch(train) [12][1550/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:55:56 time: 3.0780 data_time: 0.2134 memory: 29063 grad_norm: 20.7432 loss: 5.3807 loss_cls: 0.6691 loss_bbox: 0.1933 d0.loss_cls: 0.7876 d0.loss_bbox: 0.2068 d1.loss_cls: 0.7206 d1.loss_bbox: 0.1966 d2.loss_cls: 0.6927 d2.loss_bbox: 0.1955 d3.loss_cls: 0.6684 d3.loss_bbox: 0.1915 d4.loss_cls: 0.6661 d4.loss_bbox: 0.1925 2024/04/09 11:11:33 - mmengine - INFO - Epoch(train) [12][1600/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:53:11 time: 3.1750 data_time: 0.2373 memory: 29874 grad_norm: 19.7830 loss: 5.6851 loss_cls: 0.7146 loss_bbox: 0.2005 d0.loss_cls: 0.8055 d0.loss_bbox: 0.2337 d1.loss_cls: 0.7555 d1.loss_bbox: 0.2165 d2.loss_cls: 0.7234 d2.loss_bbox: 0.2091 d3.loss_cls: 0.7059 d3.loss_bbox: 0.2056 d4.loss_cls: 0.7087 d4.loss_bbox: 0.2061 2024/04/09 11:14:01 - mmengine - INFO - Epoch(train) [12][1650/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:50:26 time: 2.9702 data_time: 0.1587 memory: 28864 grad_norm: 19.8148 loss: 5.4192 loss_cls: 0.6790 loss_bbox: 0.1908 d0.loss_cls: 0.7766 d0.loss_bbox: 0.2150 d1.loss_cls: 0.7259 d1.loss_bbox: 0.1995 d2.loss_cls: 0.6959 d2.loss_bbox: 0.1928 d3.loss_cls: 0.6799 d3.loss_bbox: 0.1930 d4.loss_cls: 0.6792 d4.loss_bbox: 0.1918 2024/04/09 11:16:40 - mmengine - INFO - Epoch(train) [12][1700/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:47:41 time: 3.1674 data_time: 0.2542 memory: 28251 grad_norm: 19.7197 loss: 5.4098 loss_cls: 0.6718 loss_bbox: 0.2048 d0.loss_cls: 0.7622 d0.loss_bbox: 0.2214 d1.loss_cls: 0.7090 d1.loss_bbox: 0.2092 d2.loss_cls: 0.6834 d2.loss_bbox: 0.2069 d3.loss_cls: 0.6774 d3.loss_bbox: 0.2029 d4.loss_cls: 0.6580 d4.loss_bbox: 0.2026 2024/04/09 11:17:36 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 11:19:09 - mmengine - INFO - Epoch(train) [12][1750/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:44:56 time: 2.9982 data_time: 0.1882 memory: 28756 grad_norm: 20.3417 loss: 5.6468 loss_cls: 0.7023 loss_bbox: 0.2045 d0.loss_cls: 0.8172 d0.loss_bbox: 0.2149 d1.loss_cls: 0.7520 d1.loss_bbox: 0.2062 d2.loss_cls: 0.7258 d2.loss_bbox: 0.2068 d3.loss_cls: 0.7045 d3.loss_bbox: 0.2072 d4.loss_cls: 0.6989 d4.loss_bbox: 0.2066 2024/04/09 11:21:43 - mmengine - INFO - Epoch(train) [12][1800/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:42:11 time: 3.0657 data_time: 0.1789 memory: 29149 grad_norm: 19.7312 loss: 5.2697 loss_cls: 0.6487 loss_bbox: 0.2043 d0.loss_cls: 0.7441 d0.loss_bbox: 0.2210 d1.loss_cls: 0.6734 d1.loss_bbox: 0.2130 d2.loss_cls: 0.6578 d2.loss_bbox: 0.2058 d3.loss_cls: 0.6470 d3.loss_bbox: 0.2033 d4.loss_cls: 0.6488 d4.loss_bbox: 0.2028 2024/04/09 11:24:12 - mmengine - INFO - Epoch(train) [12][1850/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:39:26 time: 2.9796 data_time: 0.1679 memory: 29075 grad_norm: 19.6767 loss: 5.4211 loss_cls: 0.6804 loss_bbox: 0.2020 d0.loss_cls: 0.7506 d0.loss_bbox: 0.2228 d1.loss_cls: 0.7037 d1.loss_bbox: 0.2126 d2.loss_cls: 0.6887 d2.loss_bbox: 0.2048 d3.loss_cls: 0.6801 d3.loss_bbox: 0.2018 d4.loss_cls: 0.6731 d4.loss_bbox: 0.2006 2024/04/09 11:26:46 - mmengine - INFO - Epoch(train) [12][1900/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:36:41 time: 3.0927 data_time: 0.1879 memory: 28894 grad_norm: 20.3462 loss: 5.5400 loss_cls: 0.6869 loss_bbox: 0.2027 d0.loss_cls: 0.7681 d0.loss_bbox: 0.2289 d1.loss_cls: 0.7297 d1.loss_bbox: 0.2190 d2.loss_cls: 0.7055 d2.loss_bbox: 0.2109 d3.loss_cls: 0.6927 d3.loss_bbox: 0.2061 d4.loss_cls: 0.6844 d4.loss_bbox: 0.2051 2024/04/09 11:29:28 - mmengine - INFO - Epoch(train) [12][1950/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:33:57 time: 3.2397 data_time: 0.1900 memory: 28046 grad_norm: 20.4483 loss: 5.5029 loss_cls: 0.6858 loss_bbox: 0.1970 d0.loss_cls: 0.7895 d0.loss_bbox: 0.2136 d1.loss_cls: 0.7383 d1.loss_bbox: 0.2020 d2.loss_cls: 0.7085 d2.loss_bbox: 0.1966 d3.loss_cls: 0.6870 d3.loss_bbox: 0.1976 d4.loss_cls: 0.6918 d4.loss_bbox: 0.1952 2024/04/09 11:32:01 - mmengine - INFO - Epoch(train) [12][2000/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:31:12 time: 3.0600 data_time: 0.1847 memory: 29183 grad_norm: 19.7406 loss: 5.3671 loss_cls: 0.6557 loss_bbox: 0.2112 d0.loss_cls: 0.7550 d0.loss_bbox: 0.2348 d1.loss_cls: 0.6959 d1.loss_bbox: 0.2169 d2.loss_cls: 0.6667 d2.loss_bbox: 0.2074 d3.loss_cls: 0.6529 d3.loss_bbox: 0.2085 d4.loss_cls: 0.6544 d4.loss_bbox: 0.2077 2024/04/09 11:34:30 - mmengine - INFO - Epoch(train) [12][2050/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:28:28 time: 2.9709 data_time: 0.1659 memory: 28537 grad_norm: 20.5029 loss: 5.4761 loss_cls: 0.6696 loss_bbox: 0.2027 d0.loss_cls: 0.7820 d0.loss_bbox: 0.2230 d1.loss_cls: 0.7185 d1.loss_bbox: 0.2107 d2.loss_cls: 0.6903 d2.loss_bbox: 0.2094 d3.loss_cls: 0.6824 d3.loss_bbox: 0.2031 d4.loss_cls: 0.6794 d4.loss_bbox: 0.2051 2024/04/09 11:37:04 - mmengine - INFO - Epoch(train) [12][2100/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:25:44 time: 3.0860 data_time: 0.1821 memory: 29081 grad_norm: 19.8492 loss: 5.4586 loss_cls: 0.6810 loss_bbox: 0.1920 d0.loss_cls: 0.7798 d0.loss_bbox: 0.2116 d1.loss_cls: 0.7361 d1.loss_bbox: 0.1981 d2.loss_cls: 0.7060 d2.loss_bbox: 0.1945 d3.loss_cls: 0.6860 d3.loss_bbox: 0.1901 d4.loss_cls: 0.6892 d4.loss_bbox: 0.1943 2024/04/09 11:39:34 - mmengine - INFO - Epoch(train) [12][2150/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:22:59 time: 2.9983 data_time: 0.1951 memory: 28937 grad_norm: 20.3741 loss: 5.8246 loss_cls: 0.7325 loss_bbox: 0.2022 d0.loss_cls: 0.8294 d0.loss_bbox: 0.2280 d1.loss_cls: 0.7827 d1.loss_bbox: 0.2114 d2.loss_cls: 0.7511 d2.loss_bbox: 0.2095 d3.loss_cls: 0.7357 d3.loss_bbox: 0.2017 d4.loss_cls: 0.7401 d4.loss_bbox: 0.2004 2024/04/09 11:42:09 - mmengine - INFO - Epoch(train) [12][2200/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:20:15 time: 3.0936 data_time: 0.1981 memory: 28788 grad_norm: 19.4130 loss: 5.3340 loss_cls: 0.6747 loss_bbox: 0.1898 d0.loss_cls: 0.7499 d0.loss_bbox: 0.2122 d1.loss_cls: 0.7002 d1.loss_bbox: 0.1993 d2.loss_cls: 0.6878 d2.loss_bbox: 0.1937 d3.loss_cls: 0.6721 d3.loss_bbox: 0.1922 d4.loss_cls: 0.6735 d4.loss_bbox: 0.1887 2024/04/09 11:44:40 - mmengine - INFO - Epoch(train) [12][2250/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:17:31 time: 3.0200 data_time: 0.1810 memory: 29078 grad_norm: 20.0315 loss: 5.5044 loss_cls: 0.6684 loss_bbox: 0.2129 d0.loss_cls: 0.7734 d0.loss_bbox: 0.2329 d1.loss_cls: 0.7236 d1.loss_bbox: 0.2210 d2.loss_cls: 0.6832 d2.loss_bbox: 0.2168 d3.loss_cls: 0.6718 d3.loss_bbox: 0.2142 d4.loss_cls: 0.6708 d4.loss_bbox: 0.2155 2024/04/09 11:47:19 - mmengine - INFO - Epoch(train) [12][2300/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:14:47 time: 3.1841 data_time: 0.1742 memory: 29223 grad_norm: 20.5097 loss: 5.4181 loss_cls: 0.6669 loss_bbox: 0.2013 d0.loss_cls: 0.7619 d0.loss_bbox: 0.2291 d1.loss_cls: 0.7144 d1.loss_bbox: 0.2098 d2.loss_cls: 0.6887 d2.loss_bbox: 0.2049 d3.loss_cls: 0.6666 d3.loss_bbox: 0.2043 d4.loss_cls: 0.6682 d4.loss_bbox: 0.2022 2024/04/09 11:49:51 - mmengine - INFO - Epoch(train) [12][2350/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:12:03 time: 3.0472 data_time: 0.2011 memory: 28142 grad_norm: 19.8260 loss: 5.3831 loss_cls: 0.6763 loss_bbox: 0.1937 d0.loss_cls: 0.7590 d0.loss_bbox: 0.2126 d1.loss_cls: 0.7150 d1.loss_bbox: 0.2007 d2.loss_cls: 0.6857 d2.loss_bbox: 0.1976 d3.loss_cls: 0.6727 d3.loss_bbox: 0.1975 d4.loss_cls: 0.6788 d4.loss_bbox: 0.1935 2024/04/09 11:52:28 - mmengine - INFO - Epoch(train) [12][2400/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:09:19 time: 3.1375 data_time: 0.1943 memory: 29755 grad_norm: 20.4118 loss: 5.3691 loss_cls: 0.6479 loss_bbox: 0.2190 d0.loss_cls: 0.7387 d0.loss_bbox: 0.2332 d1.loss_cls: 0.6898 d1.loss_bbox: 0.2211 d2.loss_cls: 0.6637 d2.loss_bbox: 0.2203 d3.loss_cls: 0.6479 d3.loss_bbox: 0.2199 d4.loss_cls: 0.6478 d4.loss_bbox: 0.2199 2024/04/09 11:55:07 - mmengine - INFO - Epoch(train) [12][2450/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:06:36 time: 3.1819 data_time: 0.1869 memory: 29832 grad_norm: 19.7041 loss: 5.5236 loss_cls: 0.6841 loss_bbox: 0.2088 d0.loss_cls: 0.7732 d0.loss_bbox: 0.2221 d1.loss_cls: 0.7210 d1.loss_bbox: 0.2092 d2.loss_cls: 0.7061 d2.loss_bbox: 0.2096 d3.loss_cls: 0.6908 d3.loss_bbox: 0.2045 d4.loss_cls: 0.6887 d4.loss_bbox: 0.2054 2024/04/09 11:57:57 - mmengine - INFO - Epoch(train) [12][2500/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:03:52 time: 3.3830 data_time: 0.1852 memory: 28959 grad_norm: 20.0684 loss: 5.7665 loss_cls: 0.7042 loss_bbox: 0.2254 d0.loss_cls: 0.7987 d0.loss_bbox: 0.2405 d1.loss_cls: 0.7574 d1.loss_bbox: 0.2251 d2.loss_cls: 0.7336 d2.loss_bbox: 0.2255 d3.loss_cls: 0.7060 d3.loss_bbox: 0.2236 d4.loss_cls: 0.7044 d4.loss_bbox: 0.2220 2024/04/09 12:00:34 - mmengine - INFO - Epoch(train) [12][2550/2571] base_lr: 5.0000e-06 lr: 5.0000e-06 eta: 0:01:08 time: 3.1469 data_time: 0.2266 memory: 28384 grad_norm: 20.1472 loss: 5.4324 loss_cls: 0.6649 loss_bbox: 0.2045 d0.loss_cls: 0.7596 d0.loss_bbox: 0.2276 d1.loss_cls: 0.7050 d1.loss_bbox: 0.2205 d2.loss_cls: 0.6857 d2.loss_bbox: 0.2164 d3.loss_cls: 0.6705 d3.loss_bbox: 0.2073 d4.loss_cls: 0.6675 d4.loss_bbox: 0.2029 2024/04/09 12:01:31 - mmengine - INFO - Exp name: mv-grounding_8xb12_embodiedscan-vg-9dof_complex-all_20240409_001206 2024/04/09 12:01:31 - mmengine - INFO - Saving checkpoint at 12 epochs 2024/04/09 12:08:07 - mmengine - INFO - Epoch(val) [12][ 50/629] eta: 1:13:45 time: 7.6438 data_time: 6.8468 memory: 27875 2024/04/09 12:13:03 - mmengine - INFO - Epoch(val) [12][100/629] eta: 0:59:49 time: 5.9280 data_time: 5.1188 memory: 13559 2024/04/09 12:17:57 - mmengine - INFO - Epoch(val) [12][150/629] eta: 0:51:43 time: 5.8680 data_time: 5.0807 memory: 13547 2024/04/09 12:20:40 - mmengine - INFO - Epoch(val) [12][200/629] eta: 0:40:34 time: 3.2634 data_time: 2.4885 memory: 13552 2024/04/09 12:23:11 - mmengine - INFO - Epoch(val) [12][250/629] eta: 0:32:29 time: 3.0114 data_time: 2.2247 memory: 13582 2024/04/09 12:34:52 - mmengine - INFO - Epoch(val) [12][300/629] eta: 0:36:19 time: 14.0302 data_time: 13.2011 memory: 13862