2023/06/04 01:55:25 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.9 (main, Mar 8 2023, 10:47:38) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1786672076 GPU 0,1,2,3: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.6 NVCC: Cuda compilation tools, release 11.6, V11.6.124 GCC: gcc (GCC) 7.5.0 PyTorch: 1.13.1 PyTorch compiling details: PyTorch built with: - GCC 9.3 - 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 v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.6 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_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 (built against CUDA 11.5) - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.14.1 OpenCV: 4.7.0 MMEngine: 0.7.3 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None deterministic: False Distributed launcher: slurm Distributed training: True GPU number: 4 ------------------------------------------------------------ 2023/06/04 01:55:29 - mmengine - INFO - Config: optim_wrapper = dict( optimizer=dict( type='AdamW', lr=0.0001, weight_decay=0.3, _scope_='mmpretrain'), paramwise_cfg=dict( custom_keys=dict({ '.cls_token': dict(decay_mult=0.0), '.pos_embed': dict(decay_mult=0.0) })), type='AmpOptimWrapper', dtype='bfloat16', clip_grad=None) param_scheduler = [ dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=False, begin=0) ] train_cfg = dict(by_epoch=True, max_epochs=10, val_interval=1) val_cfg = dict() test_cfg = dict() auto_scale_lr = dict(base_batch_size=4096) model = dict( type='ImageClassifier', backbone=dict( frozen_stages=24, type='VisionTransformer', arch='l', img_size=224, patch_size=14, drop_rate=0.1, pre_norm=True, init_cfg=dict( type='Pretrained', checkpoint='ckpt/openclip-ViT-L-14.pth', prefix='backbone')), head=dict( type='LinearClsHead', num_classes=2, in_channels=1024, loss=dict(type='CrossEntropyLoss', loss_weight=1.0), init_cfg=None), init_cfg=dict( type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0), train_cfg=None) dataset_type = 'CustomDataset' data_preprocessor = dict( num_classes=2, mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) bgr_mean = [103.53, 116.28, 123.675] bgr_std = [57.375, 57.12, 58.395] train_pipeline = [ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='ResizeEdge', scale=256, edge='short', backend='pillow', interpolation='bicubic'), dict(type='CenterCrop', crop_size=224), dict(type='PackInputs') ] train_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stablediffusionV2-1-dpmsolver-25-1m.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/cc1m.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=True)) val_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV2-1-dpmsolver-25-1w.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=False)) val_evaluator = [ dict(type='Accuracy', topk=1), dict(type='SingleLabelMetric', average=None) ] test_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV2-1-dpmsolver-25-1w.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=False)) test_evaluator = [ dict(type='Accuracy', topk=1), dict(type='SingleLabelMetric', average=None) ] custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')] default_scope = 'mmpretrain' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='VisualizationHook', enable=True)) env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='UniversalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ]) log_level = 'INFO' load_from = None resume = False randomness = dict(seed=None, deterministic=False) launcher = 'slurm' work_dir = 'workdir/clip_large_pretrain_4x256_sdv2_lr1e-4' 2023/06/04 01:55:42 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (ABOVE_NORMAL) EMAHook (BELOW_NORMAL) LoggerHook -------------------- after_load_checkpoint: (ABOVE_NORMAL) EMAHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_save_checkpoint: (ABOVE_NORMAL) EMAHook -------------------- after_train: (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (ABOVE_NORMAL) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2023/06/04 01:56:02 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth Name of parameter - Initialization information backbone.cls_token - torch.Size([1, 1, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.pos_embed - torch.Size([1, 257, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.patch_embed.projection.weight - torch.Size([1024, 3, 14, 14]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.0.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.1.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.2.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.3.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.4.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.5.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.6.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.7.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.8.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.9.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.10.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.11.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.12.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.13.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.14.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.15.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.16.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.17.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.18.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.19.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.20.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.21.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.22.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.attn.qkv.weight - torch.Size([3072, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.attn.qkv.bias - torch.Size([3072]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.attn.proj.weight - torch.Size([1024, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.attn.proj.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ln2.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ln2.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ffn.layers.0.0.weight - torch.Size([4096, 1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ffn.layers.0.0.bias - torch.Size([4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ffn.layers.1.weight - torch.Size([1024, 4096]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.layers.23.ffn.layers.1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.pre_norm.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.pre_norm.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.ln1.weight - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth backbone.ln1.bias - torch.Size([1024]): PretrainedInit: load from ckpt/openclip-ViT-L-14.pth head.fc.weight - torch.Size([2, 1024]): TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 head.fc.bias - torch.Size([2]): TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 2023/06/04 01:56:04 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/06/04 01:56:04 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/06/04 01:56:04 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/luzeyu/workspace/fakebench/mmpretrain/workdir/clip_large_pretrain_4x256_sdv2_lr1e-4. 2023/06/04 01:57:13 - mmengine - INFO - Epoch(train) [1][ 100/3907] lr: 9.9999e-05 eta: 7:28:30 time: 0.6303 data_time: 0.0016 memory: 44120 loss: 0.6511 2023/06/04 01:58:16 - mmengine - INFO - Epoch(train) [1][ 200/3907] lr: 9.9994e-05 eta: 7:07:38 time: 0.6300 data_time: 0.0014 memory: 44120 loss: 0.5780 2023/06/04 01:59:19 - mmengine - INFO - Epoch(train) [1][ 300/3907] lr: 9.9987e-05 eta: 7:00:24 time: 0.6316 data_time: 0.0015 memory: 44120 loss: 0.5506 2023/06/04 02:00:23 - mmengine - INFO - Epoch(train) [1][ 400/3907] lr: 9.9977e-05 eta: 6:56:19 time: 0.6333 data_time: 0.0023 memory: 44120 loss: 0.5344 2023/06/04 02:01:26 - mmengine - INFO - Epoch(train) [1][ 500/3907] lr: 9.9964e-05 eta: 6:53:23 time: 0.6302 data_time: 0.0016 memory: 44120 loss: 0.5074 2023/06/04 02:02:29 - mmengine - INFO - Epoch(train) [1][ 600/3907] lr: 9.9948e-05 eta: 6:50:56 time: 0.6301 data_time: 0.0016 memory: 44120 loss: 0.4990 2023/06/04 02:03:32 - mmengine - INFO - Epoch(train) [1][ 700/3907] lr: 9.9929e-05 eta: 6:48:55 time: 0.6292 data_time: 0.0017 memory: 44120 loss: 0.5029 2023/06/04 02:04:35 - mmengine - INFO - Epoch(train) [1][ 800/3907] lr: 9.9907e-05 eta: 6:47:23 time: 0.6300 data_time: 0.0017 memory: 44120 loss: 0.4679 2023/06/04 02:05:38 - mmengine - INFO - Epoch(train) [1][ 900/3907] lr: 9.9882e-05 eta: 6:45:44 time: 0.6295 data_time: 0.0016 memory: 44120 loss: 0.4867 2023/06/04 02:06:41 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:06:41 - mmengine - INFO - Epoch(train) [1][1000/3907] lr: 9.9855e-05 eta: 6:44:12 time: 0.6297 data_time: 0.0015 memory: 44120 loss: 0.4594 2023/06/04 02:07:44 - mmengine - INFO - Epoch(train) [1][1100/3907] lr: 9.9824e-05 eta: 6:42:46 time: 0.6294 data_time: 0.0014 memory: 44120 loss: 0.4504 2023/06/04 02:08:47 - mmengine - INFO - Epoch(train) [1][1200/3907] lr: 9.9791e-05 eta: 6:41:22 time: 0.6302 data_time: 0.0015 memory: 44120 loss: 0.4513 2023/06/04 02:09:51 - mmengine - INFO - Epoch(train) [1][1300/3907] lr: 9.9755e-05 eta: 6:40:08 time: 0.6316 data_time: 0.0016 memory: 44120 loss: 0.4558 2023/06/04 02:10:54 - mmengine - INFO - Epoch(train) [1][1400/3907] lr: 9.9716e-05 eta: 6:38:50 time: 0.6292 data_time: 0.0015 memory: 44120 loss: 0.4728 2023/06/04 02:11:57 - mmengine - INFO - Epoch(train) [1][1500/3907] lr: 9.9674e-05 eta: 6:37:34 time: 0.6303 data_time: 0.0015 memory: 44120 loss: 0.4441 2023/06/04 02:13:00 - mmengine - INFO - Epoch(train) [1][1600/3907] lr: 9.9629e-05 eta: 6:36:20 time: 0.6305 data_time: 0.0016 memory: 44120 loss: 0.4235 2023/06/04 02:14:03 - mmengine - INFO - Epoch(train) [1][1700/3907] lr: 9.9581e-05 eta: 6:35:08 time: 0.6309 data_time: 0.0019 memory: 44120 loss: 0.4789 2023/06/04 02:15:06 - mmengine - INFO - Epoch(train) [1][1800/3907] lr: 9.9530e-05 eta: 6:33:56 time: 0.6308 data_time: 0.0021 memory: 44120 loss: 0.4395 2023/06/04 02:16:09 - mmengine - INFO - Epoch(train) [1][1900/3907] lr: 9.9476e-05 eta: 6:32:48 time: 0.6321 data_time: 0.0018 memory: 44120 loss: 0.4206 2023/06/04 02:17:12 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:17:12 - mmengine - INFO - Epoch(train) [1][2000/3907] lr: 9.9420e-05 eta: 6:31:39 time: 0.6313 data_time: 0.0016 memory: 44120 loss: 0.4306 2023/06/04 02:18:15 - mmengine - INFO - Epoch(train) [1][2100/3907] lr: 9.9361e-05 eta: 6:30:33 time: 0.6312 data_time: 0.0021 memory: 44120 loss: 0.4273 2023/06/04 02:19:18 - mmengine - INFO - Epoch(train) [1][2200/3907] lr: 9.9298e-05 eta: 6:29:25 time: 0.6324 data_time: 0.0017 memory: 44120 loss: 0.4137 2023/06/04 02:20:22 - mmengine - INFO - Epoch(train) [1][2300/3907] lr: 9.9233e-05 eta: 6:28:19 time: 0.6327 data_time: 0.0017 memory: 44120 loss: 0.4193 2023/06/04 02:21:25 - mmengine - INFO - Epoch(train) [1][2400/3907] lr: 9.9165e-05 eta: 6:27:12 time: 0.6312 data_time: 0.0016 memory: 44120 loss: 0.4384 2023/06/04 02:22:28 - mmengine - INFO - Epoch(train) [1][2500/3907] lr: 9.9095e-05 eta: 6:26:06 time: 0.6320 data_time: 0.0014 memory: 44120 loss: 0.4090 2023/06/04 02:23:31 - mmengine - INFO - Epoch(train) [1][2600/3907] lr: 9.9021e-05 eta: 6:24:59 time: 0.6303 data_time: 0.0017 memory: 44120 loss: 0.4292 2023/06/04 02:24:34 - mmengine - INFO - Epoch(train) [1][2700/3907] lr: 9.8944e-05 eta: 6:23:52 time: 0.6296 data_time: 0.0016 memory: 44120 loss: 0.4141 2023/06/04 02:25:37 - mmengine - INFO - Epoch(train) [1][2800/3907] lr: 9.8865e-05 eta: 6:22:47 time: 0.6308 data_time: 0.0016 memory: 44120 loss: 0.3893 2023/06/04 02:26:40 - mmengine - INFO - Epoch(train) [1][2900/3907] lr: 9.8783e-05 eta: 6:21:40 time: 0.6292 data_time: 0.0014 memory: 44120 loss: 0.3932 2023/06/04 02:27:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:27:44 - mmengine - INFO - Epoch(train) [1][3000/3907] lr: 9.8698e-05 eta: 6:20:35 time: 0.6313 data_time: 0.0021 memory: 44120 loss: 0.3949 2023/06/04 02:28:47 - mmengine - INFO - Epoch(train) [1][3100/3907] lr: 9.8610e-05 eta: 6:19:29 time: 0.6303 data_time: 0.0016 memory: 44120 loss: 0.3614 2023/06/04 02:29:50 - mmengine - INFO - Epoch(train) [1][3200/3907] lr: 9.8519e-05 eta: 6:18:24 time: 0.6316 data_time: 0.0016 memory: 44120 loss: 0.4107 2023/06/04 02:30:53 - mmengine - INFO - Epoch(train) [1][3300/3907] lr: 9.8426e-05 eta: 6:17:20 time: 0.6324 data_time: 0.0016 memory: 44120 loss: 0.3919 2023/06/04 02:31:56 - mmengine - INFO - Epoch(train) [1][3400/3907] lr: 9.8330e-05 eta: 6:16:16 time: 0.6319 data_time: 0.0022 memory: 44120 loss: 0.3944 2023/06/04 02:32:59 - mmengine - INFO - Epoch(train) [1][3500/3907] lr: 9.8231e-05 eta: 6:15:12 time: 0.6310 data_time: 0.0018 memory: 44120 loss: 0.4241 2023/06/04 02:34:03 - mmengine - INFO - Epoch(train) [1][3600/3907] lr: 9.8129e-05 eta: 6:14:08 time: 0.6322 data_time: 0.0017 memory: 44120 loss: 0.4126 2023/06/04 02:35:06 - mmengine - INFO - Epoch(train) [1][3700/3907] lr: 9.8024e-05 eta: 6:13:05 time: 0.6301 data_time: 0.0018 memory: 44120 loss: 0.3861 2023/06/04 02:36:09 - mmengine - INFO - Epoch(train) [1][3800/3907] lr: 9.7917e-05 eta: 6:11:59 time: 0.6288 data_time: 0.0016 memory: 44120 loss: 0.4106 2023/06/04 02:37:12 - mmengine - INFO - Epoch(train) [1][3900/3907] lr: 9.7806e-05 eta: 6:10:53 time: 0.6306 data_time: 0.0017 memory: 44120 loss: 0.3786 2023/06/04 02:37:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:37:16 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/06/04 02:38:53 - mmengine - INFO - Epoch(val) [1][57/57] accuracy/top1: 60.2032 single-label/precision_classwise: [58.161865234375, 91.34615325927734] single-label/recall_classwise: [99.0341567993164, 12.519380569458008] single-label/f1-score_classwise: [73.2844467163086, 22.020727157592773] data_time: 0.0458 time: 1.3493 2023/06/04 02:39:55 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:39:59 - mmengine - INFO - Epoch(train) [2][ 100/3907] lr: 9.7685e-05 eta: 6:10:07 time: 0.6312 data_time: 0.0024 memory: 44120 loss: 0.4061 2023/06/04 02:41:02 - mmengine - INFO - Epoch(train) [2][ 200/3907] lr: 9.7570e-05 eta: 6:09:02 time: 0.6301 data_time: 0.0015 memory: 44120 loss: 0.4036 2023/06/04 02:42:05 - mmengine - INFO - Epoch(train) [2][ 300/3907] lr: 9.7451e-05 eta: 6:07:56 time: 0.6305 data_time: 0.0014 memory: 44120 loss: 0.3966 2023/06/04 02:43:08 - mmengine - INFO - Epoch(train) [2][ 400/3907] lr: 9.7329e-05 eta: 6:06:50 time: 0.6293 data_time: 0.0015 memory: 44120 loss: 0.4431 2023/06/04 02:44:11 - mmengine - INFO - Epoch(train) [2][ 500/3907] lr: 9.7205e-05 eta: 6:05:45 time: 0.6296 data_time: 0.0018 memory: 44120 loss: 0.3746 2023/06/04 02:45:14 - mmengine - INFO - Epoch(train) [2][ 600/3907] lr: 9.7078e-05 eta: 6:04:39 time: 0.6294 data_time: 0.0014 memory: 44120 loss: 0.4080 2023/06/04 02:46:17 - mmengine - INFO - Epoch(train) [2][ 700/3907] lr: 9.6949e-05 eta: 6:03:33 time: 0.6291 data_time: 0.0014 memory: 44120 loss: 0.3937 2023/06/04 02:47:20 - mmengine - INFO - Epoch(train) [2][ 800/3907] lr: 9.6816e-05 eta: 6:02:28 time: 0.6295 data_time: 0.0015 memory: 44120 loss: 0.3627 2023/06/04 02:48:23 - mmengine - INFO - Epoch(train) [2][ 900/3907] lr: 9.6681e-05 eta: 6:01:23 time: 0.6384 data_time: 0.0015 memory: 44120 loss: 0.3746 2023/06/04 02:49:26 - mmengine - INFO - Epoch(train) [2][1000/3907] lr: 9.6544e-05 eta: 6:00:18 time: 0.6301 data_time: 0.0016 memory: 44120 loss: 0.3812 2023/06/04 02:50:25 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 02:50:29 - mmengine - INFO - Epoch(train) [2][1100/3907] lr: 9.6403e-05 eta: 5:59:13 time: 0.6311 data_time: 0.0020 memory: 44120 loss: 0.4129 2023/06/04 02:51:32 - mmengine - INFO - Epoch(train) [2][1200/3907] lr: 9.6260e-05 eta: 5:58:09 time: 0.6310 data_time: 0.0017 memory: 44120 loss: 0.4010 2023/06/04 02:52:35 - mmengine - INFO - Epoch(train) [2][1300/3907] lr: 9.6114e-05 eta: 5:57:04 time: 0.6297 data_time: 0.0016 memory: 44120 loss: 0.3777 2023/06/04 02:53:39 - mmengine - INFO - Epoch(train) [2][1400/3907] lr: 9.5966e-05 eta: 5:56:00 time: 0.6302 data_time: 0.0015 memory: 44120 loss: 0.3880 2023/06/04 02:54:42 - mmengine - INFO - Epoch(train) [2][1500/3907] lr: 9.5815e-05 eta: 5:54:55 time: 0.6317 data_time: 0.0014 memory: 44120 loss: 0.3734 2023/06/04 02:55:45 - mmengine - INFO - Epoch(train) [2][1600/3907] lr: 9.5661e-05 eta: 5:53:52 time: 0.6300 data_time: 0.0016 memory: 44120 loss: 0.3854 2023/06/04 02:56:48 - mmengine - INFO - Epoch(train) [2][1700/3907] lr: 9.5505e-05 eta: 5:52:47 time: 0.6295 data_time: 0.0015 memory: 44120 loss: 0.3805 2023/06/04 02:57:51 - mmengine - INFO - Epoch(train) [2][1800/3907] lr: 9.5346e-05 eta: 5:51:42 time: 0.6297 data_time: 0.0016 memory: 44120 loss: 0.3834 2023/06/04 02:58:54 - mmengine - INFO - Epoch(train) [2][1900/3907] lr: 9.5184e-05 eta: 5:50:38 time: 0.6304 data_time: 0.0016 memory: 44120 loss: 0.3680 2023/06/04 02:59:57 - mmengine - INFO - Epoch(train) [2][2000/3907] lr: 9.5020e-05 eta: 5:49:34 time: 0.6302 data_time: 0.0013 memory: 44120 loss: 0.3973 2023/06/04 03:00:56 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:01:00 - mmengine - INFO - Epoch(train) [2][2100/3907] lr: 9.4854e-05 eta: 5:48:29 time: 0.6311 data_time: 0.0015 memory: 44120 loss: 0.3713 2023/06/04 03:02:03 - mmengine - INFO - Epoch(train) [2][2200/3907] lr: 9.4684e-05 eta: 5:47:25 time: 0.6302 data_time: 0.0014 memory: 44120 loss: 0.3753 2023/06/04 03:03:06 - mmengine - INFO - Epoch(train) [2][2300/3907] lr: 9.4512e-05 eta: 5:46:21 time: 0.6300 data_time: 0.0014 memory: 44120 loss: 0.3761 2023/06/04 03:04:09 - mmengine - INFO - Epoch(train) [2][2400/3907] lr: 9.4338e-05 eta: 5:45:16 time: 0.6299 data_time: 0.0018 memory: 44120 loss: 0.3866 2023/06/04 03:05:12 - mmengine - INFO - Epoch(train) [2][2500/3907] lr: 9.4161e-05 eta: 5:44:12 time: 0.6304 data_time: 0.0017 memory: 44120 loss: 0.3936 2023/06/04 03:06:15 - mmengine - INFO - Epoch(train) [2][2600/3907] lr: 9.3981e-05 eta: 5:43:08 time: 0.6299 data_time: 0.0016 memory: 44120 loss: 0.4170 2023/06/04 03:07:18 - mmengine - INFO - Epoch(train) [2][2700/3907] lr: 9.3799e-05 eta: 5:42:04 time: 0.6305 data_time: 0.0016 memory: 44120 loss: 0.3835 2023/06/04 03:08:21 - mmengine - INFO - Epoch(train) [2][2800/3907] lr: 9.3615e-05 eta: 5:40:59 time: 0.6302 data_time: 0.0015 memory: 44120 loss: 0.3864 2023/06/04 03:09:24 - mmengine - INFO - Epoch(train) [2][2900/3907] lr: 9.3428e-05 eta: 5:39:56 time: 0.6305 data_time: 0.0016 memory: 44120 loss: 0.3615 2023/06/04 03:10:28 - mmengine - INFO - Epoch(train) [2][3000/3907] lr: 9.3238e-05 eta: 5:38:52 time: 0.6301 data_time: 0.0014 memory: 44120 loss: 0.3628 2023/06/04 03:11:26 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:11:31 - mmengine - INFO - Epoch(train) [2][3100/3907] lr: 9.3046e-05 eta: 5:37:49 time: 0.6336 data_time: 0.0017 memory: 44120 loss: 0.3922 2023/06/04 03:12:34 - mmengine - INFO - Epoch(train) [2][3200/3907] lr: 9.2852e-05 eta: 5:36:45 time: 0.6307 data_time: 0.0017 memory: 44120 loss: 0.3859 2023/06/04 03:13:37 - mmengine - INFO - Epoch(train) [2][3300/3907] lr: 9.2655e-05 eta: 5:35:41 time: 0.6305 data_time: 0.0015 memory: 44120 loss: 0.3957 2023/06/04 03:14:40 - mmengine - INFO - Epoch(train) [2][3400/3907] lr: 9.2456e-05 eta: 5:34:37 time: 0.6318 data_time: 0.0016 memory: 44120 loss: 0.3874 2023/06/04 03:15:43 - mmengine - INFO - Epoch(train) [2][3500/3907] lr: 9.2254e-05 eta: 5:33:33 time: 0.6298 data_time: 0.0016 memory: 44120 loss: 0.3795 2023/06/04 03:16:46 - mmengine - INFO - Epoch(train) [2][3600/3907] lr: 9.2050e-05 eta: 5:32:30 time: 0.6309 data_time: 0.0015 memory: 44120 loss: 0.3857 2023/06/04 03:17:49 - mmengine - INFO - Epoch(train) [2][3700/3907] lr: 9.1843e-05 eta: 5:31:27 time: 0.6300 data_time: 0.0015 memory: 44120 loss: 0.3903 2023/06/04 03:18:52 - mmengine - INFO - Epoch(train) [2][3800/3907] lr: 9.1634e-05 eta: 5:30:23 time: 0.6334 data_time: 0.0015 memory: 44120 loss: 0.3988 2023/06/04 03:19:56 - mmengine - INFO - Epoch(train) [2][3900/3907] lr: 9.1423e-05 eta: 5:29:19 time: 0.6290 data_time: 0.0014 memory: 44120 loss: 0.3804 2023/06/04 03:19:59 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:19:59 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/06/04 03:21:33 - mmengine - INFO - Epoch(val) [2][57/57] accuracy/top1: 66.7653 single-label/precision_classwise: [62.49751281738281, 96.75978088378906] single-label/recall_classwise: [99.2677230834961, 26.852712631225586] single-label/f1-score_classwise: [76.70357513427734, 42.03883743286133] data_time: 0.0366 time: 1.2851 2023/06/04 03:22:39 - mmengine - INFO - Epoch(train) [3][ 100/3907] lr: 9.1194e-05 eta: 5:28:21 time: 0.6291 data_time: 0.0013 memory: 44120 loss: 0.3677 2023/06/04 03:23:33 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:23:42 - mmengine - INFO - Epoch(train) [3][ 200/3907] lr: 9.0978e-05 eta: 5:27:17 time: 0.6294 data_time: 0.0016 memory: 44120 loss: 0.3831 2023/06/04 03:24:45 - mmengine - INFO - Epoch(train) [3][ 300/3907] lr: 9.0759e-05 eta: 5:26:13 time: 0.6312 data_time: 0.0020 memory: 44120 loss: 0.3798 2023/06/04 03:25:48 - mmengine - INFO - Epoch(train) [3][ 400/3907] lr: 9.0539e-05 eta: 5:25:09 time: 0.6300 data_time: 0.0019 memory: 44120 loss: 0.3775 2023/06/04 03:26:51 - mmengine - INFO - Epoch(train) [3][ 500/3907] lr: 9.0315e-05 eta: 5:24:05 time: 0.6303 data_time: 0.0014 memory: 44120 loss: 0.3702 2023/06/04 03:27:54 - mmengine - INFO - Epoch(train) [3][ 600/3907] lr: 9.0090e-05 eta: 5:23:01 time: 0.6302 data_time: 0.0017 memory: 44120 loss: 0.3814 2023/06/04 03:28:57 - mmengine - INFO - Epoch(train) [3][ 700/3907] lr: 8.9862e-05 eta: 5:21:58 time: 0.6302 data_time: 0.0017 memory: 44120 loss: 0.3968 2023/06/04 03:30:00 - mmengine - INFO - Epoch(train) [3][ 800/3907] lr: 8.9632e-05 eta: 5:20:54 time: 0.6328 data_time: 0.0019 memory: 44120 loss: 0.4027 2023/06/04 03:31:04 - mmengine - INFO - Epoch(train) [3][ 900/3907] lr: 8.9400e-05 eta: 5:19:51 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3704 2023/06/04 03:32:07 - mmengine - INFO - Epoch(train) [3][1000/3907] lr: 8.9166e-05 eta: 5:18:47 time: 0.6318 data_time: 0.0019 memory: 44120 loss: 0.4036 2023/06/04 03:33:10 - mmengine - INFO - Epoch(train) [3][1100/3907] lr: 8.8929e-05 eta: 5:17:45 time: 0.6323 data_time: 0.0024 memory: 44120 loss: 0.3695 2023/06/04 03:34:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:34:13 - mmengine - INFO - Epoch(train) [3][1200/3907] lr: 8.8691e-05 eta: 5:16:42 time: 0.6331 data_time: 0.0022 memory: 44120 loss: 0.3578 2023/06/04 03:35:17 - mmengine - INFO - Epoch(train) [3][1300/3907] lr: 8.8450e-05 eta: 5:15:38 time: 0.6310 data_time: 0.0018 memory: 44120 loss: 0.3782 2023/06/04 03:36:20 - mmengine - INFO - Epoch(train) [3][1400/3907] lr: 8.8206e-05 eta: 5:14:35 time: 0.6302 data_time: 0.0017 memory: 44120 loss: 0.3636 2023/06/04 03:37:23 - mmengine - INFO - Epoch(train) [3][1500/3907] lr: 8.7961e-05 eta: 5:13:32 time: 0.6302 data_time: 0.0015 memory: 44120 loss: 0.3884 2023/06/04 03:38:26 - mmengine - INFO - Epoch(train) [3][1600/3907] lr: 8.7714e-05 eta: 5:12:28 time: 0.6319 data_time: 0.0018 memory: 44120 loss: 0.3720 2023/06/04 03:39:29 - mmengine - INFO - Epoch(train) [3][1700/3907] lr: 8.7464e-05 eta: 5:11:25 time: 0.6308 data_time: 0.0015 memory: 44120 loss: 0.3773 2023/06/04 03:40:32 - mmengine - INFO - Epoch(train) [3][1800/3907] lr: 8.7213e-05 eta: 5:10:21 time: 0.6303 data_time: 0.0016 memory: 44120 loss: 0.3679 2023/06/04 03:41:36 - mmengine - INFO - Epoch(train) [3][1900/3907] lr: 8.6959e-05 eta: 5:09:18 time: 0.6314 data_time: 0.0024 memory: 44120 loss: 0.3706 2023/06/04 03:42:39 - mmengine - INFO - Epoch(train) [3][2000/3907] lr: 8.6703e-05 eta: 5:08:14 time: 0.6301 data_time: 0.0017 memory: 44120 loss: 0.3868 2023/06/04 03:43:42 - mmengine - INFO - Epoch(train) [3][2100/3907] lr: 8.6445e-05 eta: 5:07:11 time: 0.6304 data_time: 0.0016 memory: 44120 loss: 0.3731 2023/06/04 03:44:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:44:45 - mmengine - INFO - Epoch(train) [3][2200/3907] lr: 8.6186e-05 eta: 5:06:07 time: 0.6303 data_time: 0.0017 memory: 44120 loss: 0.3727 2023/06/04 03:45:48 - mmengine - INFO - Epoch(train) [3][2300/3907] lr: 8.5924e-05 eta: 5:05:03 time: 0.6306 data_time: 0.0015 memory: 44120 loss: 0.3646 2023/06/04 03:46:51 - mmengine - INFO - Epoch(train) [3][2400/3907] lr: 8.5660e-05 eta: 5:04:00 time: 0.6310 data_time: 0.0015 memory: 44120 loss: 0.3594 2023/06/04 03:47:54 - mmengine - INFO - Epoch(train) [3][2500/3907] lr: 8.5394e-05 eta: 5:02:57 time: 0.6309 data_time: 0.0018 memory: 44120 loss: 0.3431 2023/06/04 03:48:57 - mmengine - INFO - Epoch(train) [3][2600/3907] lr: 8.5126e-05 eta: 5:01:53 time: 0.6306 data_time: 0.0018 memory: 44120 loss: 0.3686 2023/06/04 03:50:01 - mmengine - INFO - Epoch(train) [3][2700/3907] lr: 8.4856e-05 eta: 5:00:50 time: 0.6308 data_time: 0.0016 memory: 44120 loss: 0.3896 2023/06/04 03:51:04 - mmengine - INFO - Epoch(train) [3][2800/3907] lr: 8.4585e-05 eta: 4:59:46 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3783 2023/06/04 03:52:07 - mmengine - INFO - Epoch(train) [3][2900/3907] lr: 8.4311e-05 eta: 4:58:43 time: 0.6306 data_time: 0.0017 memory: 44120 loss: 0.3652 2023/06/04 03:53:10 - mmengine - INFO - Epoch(train) [3][3000/3907] lr: 8.4036e-05 eta: 4:57:40 time: 0.6325 data_time: 0.0025 memory: 44120 loss: 0.3763 2023/06/04 03:54:14 - mmengine - INFO - Epoch(train) [3][3100/3907] lr: 8.3758e-05 eta: 4:56:37 time: 0.6315 data_time: 0.0019 memory: 44120 loss: 0.3439 2023/06/04 03:55:08 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 03:55:17 - mmengine - INFO - Epoch(train) [3][3200/3907] lr: 8.3479e-05 eta: 4:55:34 time: 0.6343 data_time: 0.0018 memory: 44120 loss: 0.3857 2023/06/04 03:56:20 - mmengine - INFO - Epoch(train) [3][3300/3907] lr: 8.3198e-05 eta: 4:54:31 time: 0.6319 data_time: 0.0018 memory: 44120 loss: 0.3935 2023/06/04 03:57:23 - mmengine - INFO - Epoch(train) [3][3400/3907] lr: 8.2915e-05 eta: 4:53:27 time: 0.6364 data_time: 0.0029 memory: 44120 loss: 0.3598 2023/06/04 03:58:26 - mmengine - INFO - Epoch(train) [3][3500/3907] lr: 8.2630e-05 eta: 4:52:24 time: 0.6318 data_time: 0.0018 memory: 44120 loss: 0.3610 2023/06/04 03:59:30 - mmengine - INFO - Epoch(train) [3][3600/3907] lr: 8.2344e-05 eta: 4:51:21 time: 0.6315 data_time: 0.0016 memory: 44120 loss: 0.3520 2023/06/04 04:00:33 - mmengine - INFO - Epoch(train) [3][3700/3907] lr: 8.2056e-05 eta: 4:50:18 time: 0.6312 data_time: 0.0016 memory: 44120 loss: 0.4015 2023/06/04 04:01:36 - mmengine - INFO - Epoch(train) [3][3800/3907] lr: 8.1765e-05 eta: 4:49:14 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3792 2023/06/04 04:02:39 - mmengine - INFO - Epoch(train) [3][3900/3907] lr: 8.1474e-05 eta: 4:48:11 time: 0.6305 data_time: 0.0013 memory: 44120 loss: 0.3917 2023/06/04 04:02:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:02:43 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/06/04 04:04:18 - mmengine - INFO - Epoch(val) [3][57/57] accuracy/top1: 70.7561 single-label/precision_classwise: [65.50458526611328, 97.20646667480469] single-label/recall_classwise: [99.16040802001953, 35.87596893310547] single-label/f1-score_classwise: [78.8930435180664, 52.40926742553711] data_time: 0.0345 time: 1.2825 2023/06/04 04:05:25 - mmengine - INFO - Epoch(train) [4][ 100/3907] lr: 8.1160e-05 eta: 4:47:09 time: 0.6294 data_time: 0.0014 memory: 44120 loss: 0.3568 2023/06/04 04:06:28 - mmengine - INFO - Epoch(train) [4][ 200/3907] lr: 8.0864e-05 eta: 4:46:05 time: 0.6308 data_time: 0.0014 memory: 44120 loss: 0.3732 2023/06/04 04:07:17 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:07:31 - mmengine - INFO - Epoch(train) [4][ 300/3907] lr: 8.0567e-05 eta: 4:45:02 time: 0.6319 data_time: 0.0015 memory: 44120 loss: 0.3886 2023/06/04 04:08:34 - mmengine - INFO - Epoch(train) [4][ 400/3907] lr: 8.0269e-05 eta: 4:43:58 time: 0.6312 data_time: 0.0015 memory: 44120 loss: 0.3713 2023/06/04 04:09:37 - mmengine - INFO - Epoch(train) [4][ 500/3907] lr: 7.9969e-05 eta: 4:42:55 time: 0.6296 data_time: 0.0015 memory: 44120 loss: 0.3773 2023/06/04 04:10:40 - mmengine - INFO - Epoch(train) [4][ 600/3907] lr: 7.9667e-05 eta: 4:41:51 time: 0.6305 data_time: 0.0014 memory: 44120 loss: 0.3723 2023/06/04 04:11:43 - mmengine - INFO - Epoch(train) [4][ 700/3907] lr: 7.9363e-05 eta: 4:40:48 time: 0.6314 data_time: 0.0015 memory: 44120 loss: 0.3403 2023/06/04 04:12:46 - mmengine - INFO - Epoch(train) [4][ 800/3907] lr: 7.9058e-05 eta: 4:39:44 time: 0.6303 data_time: 0.0015 memory: 44120 loss: 0.3501 2023/06/04 04:13:49 - mmengine - INFO - Epoch(train) [4][ 900/3907] lr: 7.8752e-05 eta: 4:38:41 time: 0.6402 data_time: 0.0018 memory: 44120 loss: 0.3872 2023/06/04 04:14:52 - mmengine - INFO - Epoch(train) [4][1000/3907] lr: 7.8444e-05 eta: 4:37:37 time: 0.6307 data_time: 0.0019 memory: 44120 loss: 0.3647 2023/06/04 04:15:55 - mmengine - INFO - Epoch(train) [4][1100/3907] lr: 7.8134e-05 eta: 4:36:34 time: 0.6318 data_time: 0.0023 memory: 44120 loss: 0.3562 2023/06/04 04:16:59 - mmengine - INFO - Epoch(train) [4][1200/3907] lr: 7.7823e-05 eta: 4:35:31 time: 0.6318 data_time: 0.0021 memory: 44120 loss: 0.3545 2023/06/04 04:17:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:18:02 - mmengine - INFO - Epoch(train) [4][1300/3907] lr: 7.7510e-05 eta: 4:34:28 time: 0.6354 data_time: 0.0024 memory: 44120 loss: 0.3912 2023/06/04 04:19:05 - mmengine - INFO - Epoch(train) [4][1400/3907] lr: 7.7196e-05 eta: 4:33:25 time: 0.6315 data_time: 0.0022 memory: 44120 loss: 0.3548 2023/06/04 04:20:09 - mmengine - INFO - Epoch(train) [4][1500/3907] lr: 7.6881e-05 eta: 4:32:22 time: 0.6356 data_time: 0.0025 memory: 44120 loss: 0.3395 2023/06/04 04:21:12 - mmengine - INFO - Epoch(train) [4][1600/3907] lr: 7.6564e-05 eta: 4:31:19 time: 0.6345 data_time: 0.0024 memory: 44120 loss: 0.3590 2023/06/04 04:22:15 - mmengine - INFO - Epoch(train) [4][1700/3907] lr: 7.6246e-05 eta: 4:30:16 time: 0.6330 data_time: 0.0026 memory: 44120 loss: 0.3762 2023/06/04 04:23:19 - mmengine - INFO - Epoch(train) [4][1800/3907] lr: 7.5926e-05 eta: 4:29:13 time: 0.6348 data_time: 0.0026 memory: 44120 loss: 0.3627 2023/06/04 04:24:22 - mmengine - INFO - Epoch(train) [4][1900/3907] lr: 7.5605e-05 eta: 4:28:10 time: 0.6332 data_time: 0.0026 memory: 44120 loss: 0.3569 2023/06/04 04:25:26 - mmengine - INFO - Epoch(train) [4][2000/3907] lr: 7.5283e-05 eta: 4:27:07 time: 0.6345 data_time: 0.0024 memory: 44120 loss: 0.3352 2023/06/04 04:26:29 - mmengine - INFO - Epoch(train) [4][2100/3907] lr: 7.4959e-05 eta: 4:26:04 time: 0.6311 data_time: 0.0021 memory: 44120 loss: 0.3555 2023/06/04 04:27:32 - mmengine - INFO - Epoch(train) [4][2200/3907] lr: 7.4634e-05 eta: 4:25:01 time: 0.6349 data_time: 0.0021 memory: 44120 loss: 0.3551 2023/06/04 04:28:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:28:36 - mmengine - INFO - Epoch(train) [4][2300/3907] lr: 7.4308e-05 eta: 4:23:58 time: 0.6317 data_time: 0.0022 memory: 44120 loss: 0.3711 2023/06/04 04:29:39 - mmengine - INFO - Epoch(train) [4][2400/3907] lr: 7.3980e-05 eta: 4:22:54 time: 0.6320 data_time: 0.0022 memory: 44120 loss: 0.3771 2023/06/04 04:30:42 - mmengine - INFO - Epoch(train) [4][2500/3907] lr: 7.3652e-05 eta: 4:21:51 time: 0.6326 data_time: 0.0020 memory: 44120 loss: 0.3532 2023/06/04 04:31:45 - mmengine - INFO - Epoch(train) [4][2600/3907] lr: 7.3322e-05 eta: 4:20:48 time: 0.6314 data_time: 0.0019 memory: 44120 loss: 0.4026 2023/06/04 04:32:49 - mmengine - INFO - Epoch(train) [4][2700/3907] lr: 7.2991e-05 eta: 4:19:46 time: 0.6362 data_time: 0.0023 memory: 44120 loss: 0.3727 2023/06/04 04:33:52 - mmengine - INFO - Epoch(train) [4][2800/3907] lr: 7.2659e-05 eta: 4:18:43 time: 0.6323 data_time: 0.0021 memory: 44120 loss: 0.3621 2023/06/04 04:34:56 - mmengine - INFO - Epoch(train) [4][2900/3907] lr: 7.2325e-05 eta: 4:17:40 time: 0.6318 data_time: 0.0018 memory: 44120 loss: 0.3518 2023/06/04 04:35:59 - mmengine - INFO - Epoch(train) [4][3000/3907] lr: 7.1991e-05 eta: 4:16:36 time: 0.6316 data_time: 0.0019 memory: 44120 loss: 0.3624 2023/06/04 04:37:02 - mmengine - INFO - Epoch(train) [4][3100/3907] lr: 7.1655e-05 eta: 4:15:33 time: 0.6343 data_time: 0.0021 memory: 44120 loss: 0.3663 2023/06/04 04:38:06 - mmengine - INFO - Epoch(train) [4][3200/3907] lr: 7.1318e-05 eta: 4:14:30 time: 0.6327 data_time: 0.0022 memory: 44120 loss: 0.3525 2023/06/04 04:38:55 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:39:09 - mmengine - INFO - Epoch(train) [4][3300/3907] lr: 7.0981e-05 eta: 4:13:27 time: 0.6304 data_time: 0.0018 memory: 44120 loss: 0.3712 2023/06/04 04:40:12 - mmengine - INFO - Epoch(train) [4][3400/3907] lr: 7.0642e-05 eta: 4:12:23 time: 0.6301 data_time: 0.0016 memory: 44120 loss: 0.3629 2023/06/04 04:41:15 - mmengine - INFO - Epoch(train) [4][3500/3907] lr: 7.0302e-05 eta: 4:11:20 time: 0.6292 data_time: 0.0014 memory: 44120 loss: 0.4025 2023/06/04 04:42:18 - mmengine - INFO - Epoch(train) [4][3600/3907] lr: 6.9961e-05 eta: 4:10:17 time: 0.6315 data_time: 0.0015 memory: 44120 loss: 0.3519 2023/06/04 04:43:21 - mmengine - INFO - Epoch(train) [4][3700/3907] lr: 6.9620e-05 eta: 4:09:13 time: 0.6317 data_time: 0.0015 memory: 44120 loss: 0.3676 2023/06/04 04:44:25 - mmengine - INFO - Epoch(train) [4][3800/3907] lr: 6.9277e-05 eta: 4:08:10 time: 0.6306 data_time: 0.0016 memory: 44120 loss: 0.3885 2023/06/04 04:45:28 - mmengine - INFO - Epoch(train) [4][3900/3907] lr: 6.8933e-05 eta: 4:07:07 time: 0.6299 data_time: 0.0012 memory: 44120 loss: 0.3632 2023/06/04 04:45:32 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:45:32 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/06/04 04:47:05 - mmengine - INFO - Epoch(val) [4][57/57] accuracy/top1: 72.9237 single-label/precision_classwise: [67.2444076538086, 97.6181640625] single-label/recall_classwise: [99.19197082519531, 40.66666793823242] single-label/f1-score_classwise: [80.15201568603516, 57.4149055480957] data_time: 0.0339 time: 1.2814 2023/06/04 04:48:12 - mmengine - INFO - Epoch(train) [5][ 100/3907] lr: 6.8565e-05 eta: 4:06:03 time: 0.6298 data_time: 0.0015 memory: 44120 loss: 0.3604 2023/06/04 04:49:15 - mmengine - INFO - Epoch(train) [5][ 200/3907] lr: 6.8219e-05 eta: 4:05:00 time: 0.6306 data_time: 0.0015 memory: 44120 loss: 0.3726 2023/06/04 04:50:18 - mmengine - INFO - Epoch(train) [5][ 300/3907] lr: 6.7873e-05 eta: 4:03:56 time: 0.6314 data_time: 0.0022 memory: 44120 loss: 0.3698 2023/06/04 04:51:03 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 04:51:21 - mmengine - INFO - Epoch(train) [5][ 400/3907] lr: 6.7526e-05 eta: 4:02:53 time: 0.6309 data_time: 0.0016 memory: 44120 loss: 0.3606 2023/06/04 04:52:24 - mmengine - INFO - Epoch(train) [5][ 500/3907] lr: 6.7178e-05 eta: 4:01:49 time: 0.6309 data_time: 0.0014 memory: 44120 loss: 0.3740 2023/06/04 04:53:27 - mmengine - INFO - Epoch(train) [5][ 600/3907] lr: 6.6829e-05 eta: 4:00:46 time: 0.6325 data_time: 0.0016 memory: 44120 loss: 0.3751 2023/06/04 04:54:31 - mmengine - INFO - Epoch(train) [5][ 700/3907] lr: 6.6480e-05 eta: 3:59:43 time: 0.6315 data_time: 0.0014 memory: 44120 loss: 0.3717 2023/06/04 04:55:34 - mmengine - INFO - Epoch(train) [5][ 800/3907] lr: 6.6129e-05 eta: 3:58:40 time: 0.6328 data_time: 0.0015 memory: 44120 loss: 0.3558 2023/06/04 04:56:37 - mmengine - INFO - Epoch(train) [5][ 900/3907] lr: 6.5778e-05 eta: 3:57:37 time: 0.6312 data_time: 0.0018 memory: 44120 loss: 0.3636 2023/06/04 04:57:41 - mmengine - INFO - Epoch(train) [5][1000/3907] lr: 6.5427e-05 eta: 3:56:34 time: 0.6371 data_time: 0.0020 memory: 44120 loss: 0.3688 2023/06/04 04:58:44 - mmengine - INFO - Epoch(train) [5][1100/3907] lr: 6.5074e-05 eta: 3:55:30 time: 0.6312 data_time: 0.0016 memory: 44120 loss: 0.3715 2023/06/04 04:59:47 - mmengine - INFO - Epoch(train) [5][1200/3907] lr: 6.4721e-05 eta: 3:54:27 time: 0.6323 data_time: 0.0017 memory: 44120 loss: 0.3440 2023/06/04 05:00:50 - mmengine - INFO - Epoch(train) [5][1300/3907] lr: 6.4368e-05 eta: 3:53:24 time: 0.6310 data_time: 0.0016 memory: 44120 loss: 0.3613 2023/06/04 05:01:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:01:53 - mmengine - INFO - Epoch(train) [5][1400/3907] lr: 6.4014e-05 eta: 3:52:20 time: 0.6305 data_time: 0.0019 memory: 44120 loss: 0.3369 2023/06/04 05:02:57 - mmengine - INFO - Epoch(train) [5][1500/3907] lr: 6.3659e-05 eta: 3:51:17 time: 0.6301 data_time: 0.0016 memory: 44120 loss: 0.3567 2023/06/04 05:04:00 - mmengine - INFO - Epoch(train) [5][1600/3907] lr: 6.3303e-05 eta: 3:50:13 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3875 2023/06/04 05:05:03 - mmengine - INFO - Epoch(train) [5][1700/3907] lr: 6.2948e-05 eta: 3:49:10 time: 0.6324 data_time: 0.0016 memory: 44120 loss: 0.3812 2023/06/04 05:06:06 - mmengine - INFO - Epoch(train) [5][1800/3907] lr: 6.2591e-05 eta: 3:48:07 time: 0.6315 data_time: 0.0016 memory: 44120 loss: 0.3553 2023/06/04 05:07:09 - mmengine - INFO - Epoch(train) [5][1900/3907] lr: 6.2234e-05 eta: 3:47:03 time: 0.6326 data_time: 0.0022 memory: 44120 loss: 0.3960 2023/06/04 05:08:12 - mmengine - INFO - Epoch(train) [5][2000/3907] lr: 6.1877e-05 eta: 3:46:00 time: 0.6313 data_time: 0.0015 memory: 44120 loss: 0.3601 2023/06/04 05:09:16 - mmengine - INFO - Epoch(train) [5][2100/3907] lr: 6.1519e-05 eta: 3:44:57 time: 0.6310 data_time: 0.0016 memory: 44120 loss: 0.3430 2023/06/04 05:10:19 - mmengine - INFO - Epoch(train) [5][2200/3907] lr: 6.1161e-05 eta: 3:43:53 time: 0.6306 data_time: 0.0018 memory: 44120 loss: 0.3600 2023/06/04 05:11:22 - mmengine - INFO - Epoch(train) [5][2300/3907] lr: 6.0802e-05 eta: 3:42:50 time: 0.6309 data_time: 0.0017 memory: 44120 loss: 0.3507 2023/06/04 05:12:07 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:12:25 - mmengine - INFO - Epoch(train) [5][2400/3907] lr: 6.0443e-05 eta: 3:41:47 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3818 2023/06/04 05:13:28 - mmengine - INFO - Epoch(train) [5][2500/3907] lr: 6.0084e-05 eta: 3:40:43 time: 0.6308 data_time: 0.0016 memory: 44120 loss: 0.3692 2023/06/04 05:14:31 - mmengine - INFO - Epoch(train) [5][2600/3907] lr: 5.9724e-05 eta: 3:39:40 time: 0.6305 data_time: 0.0015 memory: 44120 loss: 0.3737 2023/06/04 05:15:35 - mmengine - INFO - Epoch(train) [5][2700/3907] lr: 5.9364e-05 eta: 3:38:37 time: 0.6305 data_time: 0.0014 memory: 44120 loss: 0.3773 2023/06/04 05:16:38 - mmengine - INFO - Epoch(train) [5][2800/3907] lr: 5.9004e-05 eta: 3:37:33 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3454 2023/06/04 05:17:41 - mmengine - INFO - Epoch(train) [5][2900/3907] lr: 5.8643e-05 eta: 3:36:30 time: 0.6328 data_time: 0.0020 memory: 44120 loss: 0.3517 2023/06/04 05:18:44 - mmengine - INFO - Epoch(train) [5][3000/3907] lr: 5.8283e-05 eta: 3:35:27 time: 0.6313 data_time: 0.0017 memory: 44120 loss: 0.3615 2023/06/04 05:19:48 - mmengine - INFO - Epoch(train) [5][3100/3907] lr: 5.7922e-05 eta: 3:34:24 time: 0.6343 data_time: 0.0029 memory: 44120 loss: 0.3724 2023/06/04 05:20:51 - mmengine - INFO - Epoch(train) [5][3200/3907] lr: 5.7560e-05 eta: 3:33:21 time: 0.6325 data_time: 0.0019 memory: 44120 loss: 0.3680 2023/06/04 05:21:54 - mmengine - INFO - Epoch(train) [5][3300/3907] lr: 5.7199e-05 eta: 3:32:18 time: 0.6394 data_time: 0.0016 memory: 44120 loss: 0.3743 2023/06/04 05:22:40 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:22:58 - mmengine - INFO - Epoch(train) [5][3400/3907] lr: 5.6838e-05 eta: 3:31:14 time: 0.6325 data_time: 0.0020 memory: 44120 loss: 0.3637 2023/06/04 05:24:01 - mmengine - INFO - Epoch(train) [5][3500/3907] lr: 5.6476e-05 eta: 3:30:11 time: 0.6316 data_time: 0.0017 memory: 44120 loss: 0.3521 2023/06/04 05:25:04 - mmengine - INFO - Epoch(train) [5][3600/3907] lr: 5.6114e-05 eta: 3:29:08 time: 0.6313 data_time: 0.0016 memory: 44120 loss: 0.3706 2023/06/04 05:26:07 - mmengine - INFO - Epoch(train) [5][3700/3907] lr: 5.5753e-05 eta: 3:28:05 time: 0.6312 data_time: 0.0016 memory: 44120 loss: 0.3684 2023/06/04 05:27:11 - mmengine - INFO - Epoch(train) [5][3800/3907] lr: 5.5391e-05 eta: 3:27:01 time: 0.6324 data_time: 0.0017 memory: 44120 loss: 0.3916 2023/06/04 05:28:14 - mmengine - INFO - Epoch(train) [5][3900/3907] lr: 5.5029e-05 eta: 3:25:58 time: 0.6315 data_time: 0.0014 memory: 44120 loss: 0.3690 2023/06/04 05:28:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:28:18 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/06/04 05:29:52 - mmengine - INFO - Epoch(val) [5][57/57] accuracy/top1: 74.1867 single-label/precision_classwise: [68.33740234375, 97.43811798095703] single-label/recall_classwise: [99.06571197509766, 43.635658264160156] single-label/f1-score_classwise: [80.88134002685547, 60.27734375] data_time: 0.0338 time: 1.2835 2023/06/04 05:30:59 - mmengine - INFO - Epoch(train) [6][ 100/3907] lr: 5.4642e-05 eta: 3:24:53 time: 0.6312 data_time: 0.0014 memory: 44120 loss: 0.3427 2023/06/04 05:32:02 - mmengine - INFO - Epoch(train) [6][ 200/3907] lr: 5.4280e-05 eta: 3:23:50 time: 0.6307 data_time: 0.0014 memory: 44120 loss: 0.3660 2023/06/04 05:33:05 - mmengine - INFO - Epoch(train) [6][ 300/3907] lr: 5.3918e-05 eta: 3:22:47 time: 0.6346 data_time: 0.0016 memory: 44120 loss: 0.3612 2023/06/04 05:34:08 - mmengine - INFO - Epoch(train) [6][ 400/3907] lr: 5.3556e-05 eta: 3:21:43 time: 0.6309 data_time: 0.0014 memory: 44120 loss: 0.3365 2023/06/04 05:34:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:35:11 - mmengine - INFO - Epoch(train) [6][ 500/3907] lr: 5.3195e-05 eta: 3:20:40 time: 0.6317 data_time: 0.0014 memory: 44120 loss: 0.3765 2023/06/04 05:36:15 - mmengine - INFO - Epoch(train) [6][ 600/3907] lr: 5.2833e-05 eta: 3:19:37 time: 0.6314 data_time: 0.0016 memory: 44120 loss: 0.3631 2023/06/04 05:37:18 - mmengine - INFO - Epoch(train) [6][ 700/3907] lr: 5.2472e-05 eta: 3:18:34 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3929 2023/06/04 05:38:21 - mmengine - INFO - Epoch(train) [6][ 800/3907] lr: 5.2111e-05 eta: 3:17:30 time: 0.6329 data_time: 0.0016 memory: 44120 loss: 0.3521 2023/06/04 05:39:24 - mmengine - INFO - Epoch(train) [6][ 900/3907] lr: 5.1750e-05 eta: 3:16:27 time: 0.6312 data_time: 0.0018 memory: 44120 loss: 0.3688 2023/06/04 05:40:28 - mmengine - INFO - Epoch(train) [6][1000/3907] lr: 5.1389e-05 eta: 3:15:24 time: 0.6309 data_time: 0.0018 memory: 44120 loss: 0.3505 2023/06/04 05:41:31 - mmengine - INFO - Epoch(train) [6][1100/3907] lr: 5.1029e-05 eta: 3:14:20 time: 0.6307 data_time: 0.0017 memory: 44120 loss: 0.3884 2023/06/04 05:42:34 - mmengine - INFO - Epoch(train) [6][1200/3907] lr: 5.0668e-05 eta: 3:13:17 time: 0.6327 data_time: 0.0018 memory: 44120 loss: 0.3525 2023/06/04 05:43:37 - mmengine - INFO - Epoch(train) [6][1300/3907] lr: 5.0308e-05 eta: 3:12:14 time: 0.6351 data_time: 0.0016 memory: 44120 loss: 0.3769 2023/06/04 05:44:41 - mmengine - INFO - Epoch(train) [6][1400/3907] lr: 4.9949e-05 eta: 3:11:11 time: 0.6432 data_time: 0.0016 memory: 44120 loss: 0.3827 2023/06/04 05:45:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:45:44 - mmengine - INFO - Epoch(train) [6][1500/3907] lr: 4.9589e-05 eta: 3:10:08 time: 0.6320 data_time: 0.0017 memory: 44120 loss: 0.3490 2023/06/04 05:46:47 - mmengine - INFO - Epoch(train) [6][1600/3907] lr: 4.9230e-05 eta: 3:09:04 time: 0.6321 data_time: 0.0017 memory: 44120 loss: 0.3568 2023/06/04 05:47:51 - mmengine - INFO - Epoch(train) [6][1700/3907] lr: 4.8871e-05 eta: 3:08:01 time: 0.6317 data_time: 0.0018 memory: 44120 loss: 0.3654 2023/06/04 05:48:54 - mmengine - INFO - Epoch(train) [6][1800/3907] lr: 4.8513e-05 eta: 3:06:58 time: 0.6306 data_time: 0.0017 memory: 44120 loss: 0.3845 2023/06/04 05:49:57 - mmengine - INFO - Epoch(train) [6][1900/3907] lr: 4.8155e-05 eta: 3:05:54 time: 0.6317 data_time: 0.0015 memory: 44120 loss: 0.3605 2023/06/04 05:51:00 - mmengine - INFO - Epoch(train) [6][2000/3907] lr: 4.7798e-05 eta: 3:04:51 time: 0.6315 data_time: 0.0015 memory: 44120 loss: 0.3793 2023/06/04 05:52:03 - mmengine - INFO - Epoch(train) [6][2100/3907] lr: 4.7441e-05 eta: 3:03:48 time: 0.6309 data_time: 0.0015 memory: 44120 loss: 0.3866 2023/06/04 05:53:06 - mmengine - INFO - Epoch(train) [6][2200/3907] lr: 4.7084e-05 eta: 3:02:44 time: 0.6312 data_time: 0.0015 memory: 44120 loss: 0.3695 2023/06/04 05:54:09 - mmengine - INFO - Epoch(train) [6][2300/3907] lr: 4.6729e-05 eta: 3:01:41 time: 0.6308 data_time: 0.0016 memory: 44120 loss: 0.3582 2023/06/04 05:55:13 - mmengine - INFO - Epoch(train) [6][2400/3907] lr: 4.6373e-05 eta: 3:00:38 time: 0.6326 data_time: 0.0019 memory: 44120 loss: 0.3662 2023/06/04 05:55:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 05:56:16 - mmengine - INFO - Epoch(train) [6][2500/3907] lr: 4.6018e-05 eta: 2:59:34 time: 0.6340 data_time: 0.0015 memory: 44120 loss: 0.3825 2023/06/04 05:57:19 - mmengine - INFO - Epoch(train) [6][2600/3907] lr: 4.5664e-05 eta: 2:58:31 time: 0.6347 data_time: 0.0019 memory: 44120 loss: 0.3929 2023/06/04 05:58:22 - mmengine - INFO - Epoch(train) [6][2700/3907] lr: 4.5310e-05 eta: 2:57:28 time: 0.6304 data_time: 0.0017 memory: 44120 loss: 0.3461 2023/06/04 05:59:26 - mmengine - INFO - Epoch(train) [6][2800/3907] lr: 4.4957e-05 eta: 2:56:25 time: 0.6325 data_time: 0.0017 memory: 44120 loss: 0.3413 2023/06/04 06:00:29 - mmengine - INFO - Epoch(train) [6][2900/3907] lr: 4.4605e-05 eta: 2:55:21 time: 0.6322 data_time: 0.0015 memory: 44120 loss: 0.3636 2023/06/04 06:01:32 - mmengine - INFO - Epoch(train) [6][3000/3907] lr: 4.4253e-05 eta: 2:54:18 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3834 2023/06/04 06:02:35 - mmengine - INFO - Epoch(train) [6][3100/3907] lr: 4.3902e-05 eta: 2:53:15 time: 0.6302 data_time: 0.0016 memory: 44120 loss: 0.3630 2023/06/04 06:03:38 - mmengine - INFO - Epoch(train) [6][3200/3907] lr: 4.3552e-05 eta: 2:52:11 time: 0.6307 data_time: 0.0015 memory: 44120 loss: 0.3936 2023/06/04 06:04:41 - mmengine - INFO - Epoch(train) [6][3300/3907] lr: 4.3202e-05 eta: 2:51:08 time: 0.6331 data_time: 0.0015 memory: 44120 loss: 0.3545 2023/06/04 06:05:44 - mmengine - INFO - Epoch(train) [6][3400/3907] lr: 4.2854e-05 eta: 2:50:05 time: 0.6330 data_time: 0.0015 memory: 44120 loss: 0.3753 2023/06/04 06:06:26 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:06:48 - mmengine - INFO - Epoch(train) [6][3500/3907] lr: 4.2506e-05 eta: 2:49:01 time: 0.6303 data_time: 0.0017 memory: 44120 loss: 0.3990 2023/06/04 06:07:51 - mmengine - INFO - Epoch(train) [6][3600/3907] lr: 4.2158e-05 eta: 2:47:58 time: 0.6320 data_time: 0.0019 memory: 44120 loss: 0.3641 2023/06/04 06:08:54 - mmengine - INFO - Epoch(train) [6][3700/3907] lr: 4.1812e-05 eta: 2:46:55 time: 0.6305 data_time: 0.0018 memory: 44120 loss: 0.3594 2023/06/04 06:09:57 - mmengine - INFO - Epoch(train) [6][3800/3907] lr: 4.1466e-05 eta: 2:45:51 time: 0.6327 data_time: 0.0014 memory: 44120 loss: 0.3692 2023/06/04 06:11:00 - mmengine - INFO - Epoch(train) [6][3900/3907] lr: 4.1122e-05 eta: 2:44:48 time: 0.6310 data_time: 0.0015 memory: 44120 loss: 0.3825 2023/06/04 06:11:04 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:11:04 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/06/04 06:12:38 - mmengine - INFO - Epoch(val) [6][57/57] accuracy/top1: 74.7608 single-label/precision_classwise: [68.8204116821289, 97.6214599609375] single-label/recall_classwise: [99.10990905761719, 44.86046600341797] single-label/f1-score_classwise: [81.23350524902344, 61.47227478027344] data_time: 0.0361 time: 1.2847 2023/06/04 06:13:44 - mmengine - INFO - Epoch(train) [7][ 100/3907] lr: 4.0754e-05 eta: 2:43:42 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3907 2023/06/04 06:14:48 - mmengine - INFO - Epoch(train) [7][ 200/3907] lr: 4.0411e-05 eta: 2:42:39 time: 0.6326 data_time: 0.0020 memory: 44120 loss: 0.3554 2023/06/04 06:15:51 - mmengine - INFO - Epoch(train) [7][ 300/3907] lr: 4.0069e-05 eta: 2:41:36 time: 0.6350 data_time: 0.0030 memory: 44120 loss: 0.3805 2023/06/04 06:16:54 - mmengine - INFO - Epoch(train) [7][ 400/3907] lr: 3.9729e-05 eta: 2:40:32 time: 0.6355 data_time: 0.0032 memory: 44120 loss: 0.3926 2023/06/04 06:17:58 - mmengine - INFO - Epoch(train) [7][ 500/3907] lr: 3.9389e-05 eta: 2:39:29 time: 0.6364 data_time: 0.0028 memory: 44120 loss: 0.3541 2023/06/04 06:18:34 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:19:01 - mmengine - INFO - Epoch(train) [7][ 600/3907] lr: 3.9050e-05 eta: 2:38:26 time: 0.6305 data_time: 0.0019 memory: 44120 loss: 0.3664 2023/06/04 06:20:04 - mmengine - INFO - Epoch(train) [7][ 700/3907] lr: 3.8712e-05 eta: 2:37:23 time: 0.6317 data_time: 0.0014 memory: 44120 loss: 0.3534 2023/06/04 06:21:07 - mmengine - INFO - Epoch(train) [7][ 800/3907] lr: 3.8375e-05 eta: 2:36:19 time: 0.6323 data_time: 0.0018 memory: 44120 loss: 0.3657 2023/06/04 06:22:11 - mmengine - INFO - Epoch(train) [7][ 900/3907] lr: 3.8039e-05 eta: 2:35:16 time: 0.6302 data_time: 0.0019 memory: 44120 loss: 0.3790 2023/06/04 06:23:14 - mmengine - INFO - Epoch(train) [7][1000/3907] lr: 3.7705e-05 eta: 2:34:13 time: 0.6311 data_time: 0.0015 memory: 44120 loss: 0.3830 2023/06/04 06:24:17 - mmengine - INFO - Epoch(train) [7][1100/3907] lr: 3.7371e-05 eta: 2:33:10 time: 0.6312 data_time: 0.0018 memory: 44120 loss: 0.3756 2023/06/04 06:25:20 - mmengine - INFO - Epoch(train) [7][1200/3907] lr: 3.7039e-05 eta: 2:32:06 time: 0.6304 data_time: 0.0016 memory: 44120 loss: 0.3716 2023/06/04 06:26:23 - mmengine - INFO - Epoch(train) [7][1300/3907] lr: 3.6708e-05 eta: 2:31:03 time: 0.6307 data_time: 0.0014 memory: 44120 loss: 0.3579 2023/06/04 06:27:26 - mmengine - INFO - Epoch(train) [7][1400/3907] lr: 3.6378e-05 eta: 2:30:00 time: 0.6336 data_time: 0.0019 memory: 44120 loss: 0.4021 2023/06/04 06:28:30 - mmengine - INFO - Epoch(train) [7][1500/3907] lr: 3.6049e-05 eta: 2:28:56 time: 0.6413 data_time: 0.0021 memory: 44120 loss: 0.3833 2023/06/04 06:29:07 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:29:33 - mmengine - INFO - Epoch(train) [7][1600/3907] lr: 3.5721e-05 eta: 2:27:53 time: 0.6323 data_time: 0.0022 memory: 44120 loss: 0.3706 2023/06/04 06:30:36 - mmengine - INFO - Epoch(train) [7][1700/3907] lr: 3.5395e-05 eta: 2:26:50 time: 0.6330 data_time: 0.0016 memory: 44120 loss: 0.3531 2023/06/04 06:31:40 - mmengine - INFO - Epoch(train) [7][1800/3907] lr: 3.5070e-05 eta: 2:25:47 time: 0.6315 data_time: 0.0016 memory: 44120 loss: 0.3761 2023/06/04 06:32:43 - mmengine - INFO - Epoch(train) [7][1900/3907] lr: 3.4746e-05 eta: 2:24:43 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3810 2023/06/04 06:33:46 - mmengine - INFO - Epoch(train) [7][2000/3907] lr: 3.4424e-05 eta: 2:23:40 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.4143 2023/06/04 06:34:49 - mmengine - INFO - Epoch(train) [7][2100/3907] lr: 3.4103e-05 eta: 2:22:37 time: 0.6315 data_time: 0.0017 memory: 44120 loss: 0.3733 2023/06/04 06:35:52 - mmengine - INFO - Epoch(train) [7][2200/3907] lr: 3.3783e-05 eta: 2:21:33 time: 0.6352 data_time: 0.0023 memory: 44120 loss: 0.3778 2023/06/04 06:36:56 - mmengine - INFO - Epoch(train) [7][2300/3907] lr: 3.3465e-05 eta: 2:20:30 time: 0.6337 data_time: 0.0019 memory: 44120 loss: 0.3983 2023/06/04 06:37:59 - mmengine - INFO - Epoch(train) [7][2400/3907] lr: 3.3148e-05 eta: 2:19:27 time: 0.6315 data_time: 0.0019 memory: 44120 loss: 0.3413 2023/06/04 06:39:02 - mmengine - INFO - Epoch(train) [7][2500/3907] lr: 3.2832e-05 eta: 2:18:24 time: 0.6326 data_time: 0.0016 memory: 44120 loss: 0.3760 2023/06/04 06:39:39 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:40:06 - mmengine - INFO - Epoch(train) [7][2600/3907] lr: 3.2518e-05 eta: 2:17:21 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3815 2023/06/04 06:41:09 - mmengine - INFO - Epoch(train) [7][2700/3907] lr: 3.2205e-05 eta: 2:16:17 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3696 2023/06/04 06:42:12 - mmengine - INFO - Epoch(train) [7][2800/3907] lr: 3.1894e-05 eta: 2:15:14 time: 0.6324 data_time: 0.0018 memory: 44120 loss: 0.3680 2023/06/04 06:43:15 - mmengine - INFO - Epoch(train) [7][2900/3907] lr: 3.1584e-05 eta: 2:14:11 time: 0.6307 data_time: 0.0015 memory: 44120 loss: 0.3825 2023/06/04 06:44:19 - mmengine - INFO - Epoch(train) [7][3000/3907] lr: 3.1276e-05 eta: 2:13:07 time: 0.6309 data_time: 0.0016 memory: 44120 loss: 0.3610 2023/06/04 06:45:22 - mmengine - INFO - Epoch(train) [7][3100/3907] lr: 3.0969e-05 eta: 2:12:04 time: 0.6306 data_time: 0.0016 memory: 44120 loss: 0.3675 2023/06/04 06:46:25 - mmengine - INFO - Epoch(train) [7][3200/3907] lr: 3.0664e-05 eta: 2:11:01 time: 0.6312 data_time: 0.0015 memory: 44120 loss: 0.3705 2023/06/04 06:47:28 - mmengine - INFO - Epoch(train) [7][3300/3907] lr: 3.0360e-05 eta: 2:09:58 time: 0.6323 data_time: 0.0020 memory: 44120 loss: 0.3740 2023/06/04 06:48:31 - mmengine - INFO - Epoch(train) [7][3400/3907] lr: 3.0058e-05 eta: 2:08:54 time: 0.6343 data_time: 0.0016 memory: 44120 loss: 0.3671 2023/06/04 06:49:35 - mmengine - INFO - Epoch(train) [7][3500/3907] lr: 2.9758e-05 eta: 2:07:51 time: 0.6317 data_time: 0.0019 memory: 44120 loss: 0.3717 2023/06/04 06:50:11 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:50:38 - mmengine - INFO - Epoch(train) [7][3600/3907] lr: 2.9459e-05 eta: 2:06:48 time: 0.6339 data_time: 0.0016 memory: 44120 loss: 0.3721 2023/06/04 06:51:41 - mmengine - INFO - Epoch(train) [7][3700/3907] lr: 2.9162e-05 eta: 2:05:45 time: 0.6303 data_time: 0.0016 memory: 44120 loss: 0.3967 2023/06/04 06:52:44 - mmengine - INFO - Epoch(train) [7][3800/3907] lr: 2.8867e-05 eta: 2:04:41 time: 0.6320 data_time: 0.0018 memory: 44120 loss: 0.3844 2023/06/04 06:53:47 - mmengine - INFO - Epoch(train) [7][3900/3907] lr: 2.8573e-05 eta: 2:03:38 time: 0.6294 data_time: 0.0015 memory: 44120 loss: 0.3524 2023/06/04 06:53:51 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 06:53:51 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/06/04 06:55:25 - mmengine - INFO - Epoch(val) [7][57/57] accuracy/top1: 75.0357 single-label/precision_classwise: [69.0578842163086, 97.66860961914062] single-label/recall_classwise: [99.11621856689453, 45.465118408203125] single-label/f1-score_classwise: [81.40083312988281, 62.047080993652344] data_time: 0.0318 time: 1.2814 2023/06/04 06:56:31 - mmengine - INFO - Epoch(train) [8][ 100/3907] lr: 2.8261e-05 eta: 2:02:31 time: 0.6305 data_time: 0.0018 memory: 44120 loss: 0.3888 2023/06/04 06:57:35 - mmengine - INFO - Epoch(train) [8][ 200/3907] lr: 2.7971e-05 eta: 2:01:28 time: 0.6301 data_time: 0.0014 memory: 44120 loss: 0.3569 2023/06/04 06:58:38 - mmengine - INFO - Epoch(train) [8][ 300/3907] lr: 2.7682e-05 eta: 2:00:25 time: 0.6309 data_time: 0.0015 memory: 44120 loss: 0.3666 2023/06/04 06:59:41 - mmengine - INFO - Epoch(train) [8][ 400/3907] lr: 2.7395e-05 eta: 1:59:21 time: 0.6302 data_time: 0.0019 memory: 44120 loss: 0.3775 2023/06/04 07:00:44 - mmengine - INFO - Epoch(train) [8][ 500/3907] lr: 2.7111e-05 eta: 1:58:18 time: 0.6320 data_time: 0.0017 memory: 44120 loss: 0.3902 2023/06/04 07:01:47 - mmengine - INFO - Epoch(train) [8][ 600/3907] lr: 2.6828e-05 eta: 1:57:15 time: 0.6325 data_time: 0.0020 memory: 44120 loss: 0.3546 2023/06/04 07:02:19 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:02:50 - mmengine - INFO - Epoch(train) [8][ 700/3907] lr: 2.6546e-05 eta: 1:56:11 time: 0.6310 data_time: 0.0015 memory: 44120 loss: 0.3699 2023/06/04 07:03:54 - mmengine - INFO - Epoch(train) [8][ 800/3907] lr: 2.6267e-05 eta: 1:55:08 time: 0.6330 data_time: 0.0023 memory: 44120 loss: 0.3367 2023/06/04 07:04:57 - mmengine - INFO - Epoch(train) [8][ 900/3907] lr: 2.5989e-05 eta: 1:54:05 time: 0.6312 data_time: 0.0017 memory: 44120 loss: 0.3577 2023/06/04 07:06:00 - mmengine - INFO - Epoch(train) [8][1000/3907] lr: 2.5714e-05 eta: 1:53:02 time: 0.6319 data_time: 0.0017 memory: 44120 loss: 0.3707 2023/06/04 07:07:03 - mmengine - INFO - Epoch(train) [8][1100/3907] lr: 2.5440e-05 eta: 1:51:58 time: 0.6332 data_time: 0.0019 memory: 44120 loss: 0.3652 2023/06/04 07:08:07 - mmengine - INFO - Epoch(train) [8][1200/3907] lr: 2.5168e-05 eta: 1:50:55 time: 0.6309 data_time: 0.0016 memory: 44120 loss: 0.3963 2023/06/04 07:09:10 - mmengine - INFO - Epoch(train) [8][1300/3907] lr: 2.4898e-05 eta: 1:49:52 time: 0.6313 data_time: 0.0017 memory: 44120 loss: 0.3455 2023/06/04 07:10:13 - mmengine - INFO - Epoch(train) [8][1400/3907] lr: 2.4630e-05 eta: 1:48:48 time: 0.6302 data_time: 0.0015 memory: 44120 loss: 0.3566 2023/06/04 07:11:16 - mmengine - INFO - Epoch(train) [8][1500/3907] lr: 2.4364e-05 eta: 1:47:45 time: 0.6316 data_time: 0.0017 memory: 44120 loss: 0.3558 2023/06/04 07:12:19 - mmengine - INFO - Epoch(train) [8][1600/3907] lr: 2.4100e-05 eta: 1:46:42 time: 0.6453 data_time: 0.0017 memory: 44120 loss: 0.4059 2023/06/04 07:12:52 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:13:23 - mmengine - INFO - Epoch(train) [8][1700/3907] lr: 2.3838e-05 eta: 1:45:39 time: 0.6318 data_time: 0.0020 memory: 44120 loss: 0.3632 2023/06/04 07:14:26 - mmengine - INFO - Epoch(train) [8][1800/3907] lr: 2.3578e-05 eta: 1:44:35 time: 0.6327 data_time: 0.0017 memory: 44120 loss: 0.3727 2023/06/04 07:15:29 - mmengine - INFO - Epoch(train) [8][1900/3907] lr: 2.3320e-05 eta: 1:43:32 time: 0.6314 data_time: 0.0016 memory: 44120 loss: 0.3891 2023/06/04 07:16:32 - mmengine - INFO - Epoch(train) [8][2000/3907] lr: 2.3064e-05 eta: 1:42:29 time: 0.6343 data_time: 0.0015 memory: 44120 loss: 0.3707 2023/06/04 07:17:35 - mmengine - INFO - Epoch(train) [8][2100/3907] lr: 2.2810e-05 eta: 1:41:26 time: 0.6312 data_time: 0.0015 memory: 44120 loss: 0.3851 2023/06/04 07:18:38 - mmengine - INFO - Epoch(train) [8][2200/3907] lr: 2.2558e-05 eta: 1:40:22 time: 0.6336 data_time: 0.0016 memory: 44120 loss: 0.3780 2023/06/04 07:19:42 - mmengine - INFO - Epoch(train) [8][2300/3907] lr: 2.2309e-05 eta: 1:39:19 time: 0.6311 data_time: 0.0020 memory: 44120 loss: 0.3452 2023/06/04 07:20:45 - mmengine - INFO - Epoch(train) [8][2400/3907] lr: 2.2061e-05 eta: 1:38:16 time: 0.6307 data_time: 0.0016 memory: 44120 loss: 0.3977 2023/06/04 07:21:48 - mmengine - INFO - Epoch(train) [8][2500/3907] lr: 2.1816e-05 eta: 1:37:12 time: 0.6324 data_time: 0.0015 memory: 44120 loss: 0.3869 2023/06/04 07:22:51 - mmengine - INFO - Epoch(train) [8][2600/3907] lr: 2.1572e-05 eta: 1:36:09 time: 0.6331 data_time: 0.0016 memory: 44120 loss: 0.3647 2023/06/04 07:23:23 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:23:54 - mmengine - INFO - Epoch(train) [8][2700/3907] lr: 2.1331e-05 eta: 1:35:06 time: 0.6307 data_time: 0.0014 memory: 44120 loss: 0.3893 2023/06/04 07:24:58 - mmengine - INFO - Epoch(train) [8][2800/3907] lr: 2.1092e-05 eta: 1:34:03 time: 0.6316 data_time: 0.0016 memory: 44120 loss: 0.3776 2023/06/04 07:26:01 - mmengine - INFO - Epoch(train) [8][2900/3907] lr: 2.0855e-05 eta: 1:32:59 time: 0.6313 data_time: 0.0014 memory: 44120 loss: 0.3686 2023/06/04 07:27:04 - mmengine - INFO - Epoch(train) [8][3000/3907] lr: 2.0621e-05 eta: 1:31:56 time: 0.6353 data_time: 0.0014 memory: 44120 loss: 0.3694 2023/06/04 07:28:08 - mmengine - INFO - Epoch(train) [8][3100/3907] lr: 2.0388e-05 eta: 1:30:53 time: 0.6312 data_time: 0.0014 memory: 44120 loss: 0.4033 2023/06/04 07:29:11 - mmengine - INFO - Epoch(train) [8][3200/3907] lr: 2.0158e-05 eta: 1:29:50 time: 0.6298 data_time: 0.0016 memory: 44120 loss: 0.3626 2023/06/04 07:30:14 - mmengine - INFO - Epoch(train) [8][3300/3907] lr: 1.9930e-05 eta: 1:28:46 time: 0.6325 data_time: 0.0015 memory: 44120 loss: 0.3532 2023/06/04 07:31:17 - mmengine - INFO - Epoch(train) [8][3400/3907] lr: 1.9705e-05 eta: 1:27:43 time: 0.6316 data_time: 0.0016 memory: 44120 loss: 0.3608 2023/06/04 07:32:20 - mmengine - INFO - Epoch(train) [8][3500/3907] lr: 1.9481e-05 eta: 1:26:40 time: 0.6312 data_time: 0.0014 memory: 44120 loss: 0.3749 2023/06/04 07:33:23 - mmengine - INFO - Epoch(train) [8][3600/3907] lr: 1.9260e-05 eta: 1:25:36 time: 0.6321 data_time: 0.0019 memory: 44120 loss: 0.3705 2023/06/04 07:33:56 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:34:27 - mmengine - INFO - Epoch(train) [8][3700/3907] lr: 1.9042e-05 eta: 1:24:33 time: 0.6339 data_time: 0.0018 memory: 44120 loss: 0.3659 2023/06/04 07:35:30 - mmengine - INFO - Epoch(train) [8][3800/3907] lr: 1.8825e-05 eta: 1:23:30 time: 0.6306 data_time: 0.0015 memory: 44120 loss: 0.3681 2023/06/04 07:36:33 - mmengine - INFO - Epoch(train) [8][3900/3907] lr: 1.8611e-05 eta: 1:22:27 time: 0.6309 data_time: 0.0013 memory: 44120 loss: 0.3498 2023/06/04 07:36:37 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:36:37 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/06/04 07:38:11 - mmengine - INFO - Epoch(val) [8][57/57] accuracy/top1: 75.3175 single-label/precision_classwise: [69.3047866821289, 97.69963836669922] single-label/recall_classwise: [99.11621856689453, 46.093021392822266] single-label/f1-score_classwise: [81.57211303710938, 62.635623931884766] data_time: 0.0382 time: 1.2858 2023/06/04 07:39:18 - mmengine - INFO - Epoch(train) [9][ 100/3907] lr: 1.8385e-05 eta: 1:21:20 time: 0.6300 data_time: 0.0015 memory: 44120 loss: 0.3670 2023/06/04 07:40:21 - mmengine - INFO - Epoch(train) [9][ 200/3907] lr: 1.8176e-05 eta: 1:20:16 time: 0.6300 data_time: 0.0016 memory: 44120 loss: 0.3762 2023/06/04 07:41:24 - mmengine - INFO - Epoch(train) [9][ 300/3907] lr: 1.7969e-05 eta: 1:19:13 time: 0.6309 data_time: 0.0017 memory: 44120 loss: 0.3762 2023/06/04 07:42:27 - mmengine - INFO - Epoch(train) [9][ 400/3907] lr: 1.7765e-05 eta: 1:18:10 time: 0.6331 data_time: 0.0024 memory: 44120 loss: 0.3647 2023/06/04 07:43:31 - mmengine - INFO - Epoch(train) [9][ 500/3907] lr: 1.7563e-05 eta: 1:17:07 time: 0.6323 data_time: 0.0018 memory: 44120 loss: 0.3522 2023/06/04 07:44:34 - mmengine - INFO - Epoch(train) [9][ 600/3907] lr: 1.7363e-05 eta: 1:16:03 time: 0.6366 data_time: 0.0020 memory: 44120 loss: 0.3591 2023/06/04 07:45:37 - mmengine - INFO - Epoch(train) [9][ 700/3907] lr: 1.7166e-05 eta: 1:15:00 time: 0.6315 data_time: 0.0016 memory: 44120 loss: 0.3492 2023/06/04 07:46:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:46:40 - mmengine - INFO - Epoch(train) [9][ 800/3907] lr: 1.6971e-05 eta: 1:13:57 time: 0.6314 data_time: 0.0019 memory: 44120 loss: 0.3773 2023/06/04 07:47:44 - mmengine - INFO - Epoch(train) [9][ 900/3907] lr: 1.6779e-05 eta: 1:12:53 time: 0.6309 data_time: 0.0015 memory: 44120 loss: 0.3667 2023/06/04 07:48:47 - mmengine - INFO - Epoch(train) [9][1000/3907] lr: 1.6589e-05 eta: 1:11:50 time: 0.6315 data_time: 0.0017 memory: 44120 loss: 0.3766 2023/06/04 07:49:50 - mmengine - INFO - Epoch(train) [9][1100/3907] lr: 1.6402e-05 eta: 1:10:47 time: 0.6338 data_time: 0.0017 memory: 44120 loss: 0.3595 2023/06/04 07:50:53 - mmengine - INFO - Epoch(train) [9][1200/3907] lr: 1.6217e-05 eta: 1:09:44 time: 0.6327 data_time: 0.0016 memory: 44120 loss: 0.3981 2023/06/04 07:51:57 - mmengine - INFO - Epoch(train) [9][1300/3907] lr: 1.6035e-05 eta: 1:08:40 time: 0.6316 data_time: 0.0019 memory: 44120 loss: 0.3540 2023/06/04 07:53:00 - mmengine - INFO - Epoch(train) [9][1400/3907] lr: 1.5855e-05 eta: 1:07:37 time: 0.6316 data_time: 0.0015 memory: 44120 loss: 0.3799 2023/06/04 07:54:03 - mmengine - INFO - Epoch(train) [9][1500/3907] lr: 1.5678e-05 eta: 1:06:34 time: 0.6313 data_time: 0.0015 memory: 44120 loss: 0.3942 2023/06/04 07:55:06 - mmengine - INFO - Epoch(train) [9][1600/3907] lr: 1.5503e-05 eta: 1:05:31 time: 0.6313 data_time: 0.0018 memory: 44120 loss: 0.3615 2023/06/04 07:56:09 - mmengine - INFO - Epoch(train) [9][1700/3907] lr: 1.5331e-05 eta: 1:04:27 time: 0.6343 data_time: 0.0014 memory: 44120 loss: 0.3896 2023/06/04 07:56:37 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 07:57:13 - mmengine - INFO - Epoch(train) [9][1800/3907] lr: 1.5162e-05 eta: 1:03:24 time: 0.6307 data_time: 0.0016 memory: 44120 loss: 0.3814 2023/06/04 07:58:16 - mmengine - INFO - Epoch(train) [9][1900/3907] lr: 1.4995e-05 eta: 1:02:21 time: 0.6312 data_time: 0.0015 memory: 44120 loss: 0.3929 2023/06/04 07:59:19 - mmengine - INFO - Epoch(train) [9][2000/3907] lr: 1.4830e-05 eta: 1:01:17 time: 0.6309 data_time: 0.0018 memory: 44120 loss: 0.3716 2023/06/04 08:00:22 - mmengine - INFO - Epoch(train) [9][2100/3907] lr: 1.4668e-05 eta: 1:00:14 time: 0.6308 data_time: 0.0017 memory: 44120 loss: 0.3421 2023/06/04 08:01:25 - mmengine - INFO - Epoch(train) [9][2200/3907] lr: 1.4509e-05 eta: 0:59:11 time: 0.6317 data_time: 0.0016 memory: 44120 loss: 0.3499 2023/06/04 08:02:29 - mmengine - INFO - Epoch(train) [9][2300/3907] lr: 1.4353e-05 eta: 0:58:08 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3561 2023/06/04 08:03:32 - mmengine - INFO - Epoch(train) [9][2400/3907] lr: 1.4199e-05 eta: 0:57:04 time: 0.6342 data_time: 0.0017 memory: 44120 loss: 0.4037 2023/06/04 08:04:35 - mmengine - INFO - Epoch(train) [9][2500/3907] lr: 1.4047e-05 eta: 0:56:01 time: 0.6315 data_time: 0.0017 memory: 44120 loss: 0.3733 2023/06/04 08:05:38 - mmengine - INFO - Epoch(train) [9][2600/3907] lr: 1.3899e-05 eta: 0:54:58 time: 0.6326 data_time: 0.0019 memory: 44120 loss: 0.3626 2023/06/04 08:06:41 - mmengine - INFO - Epoch(train) [9][2700/3907] lr: 1.3753e-05 eta: 0:53:55 time: 0.6308 data_time: 0.0015 memory: 44120 loss: 0.3699 2023/06/04 08:07:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:07:44 - mmengine - INFO - Epoch(train) [9][2800/3907] lr: 1.3609e-05 eta: 0:52:51 time: 0.6303 data_time: 0.0018 memory: 44120 loss: 0.3656 2023/06/04 08:08:47 - mmengine - INFO - Epoch(train) [9][2900/3907] lr: 1.3469e-05 eta: 0:51:48 time: 0.6306 data_time: 0.0017 memory: 44120 loss: 0.3944 2023/06/04 08:09:51 - mmengine - INFO - Epoch(train) [9][3000/3907] lr: 1.3331e-05 eta: 0:50:45 time: 0.6309 data_time: 0.0016 memory: 44120 loss: 0.3797 2023/06/04 08:10:54 - mmengine - INFO - Epoch(train) [9][3100/3907] lr: 1.3196e-05 eta: 0:49:41 time: 0.6310 data_time: 0.0016 memory: 44120 loss: 0.3287 2023/06/04 08:11:57 - mmengine - INFO - Epoch(train) [9][3200/3907] lr: 1.3063e-05 eta: 0:48:38 time: 0.6328 data_time: 0.0018 memory: 44120 loss: 0.3583 2023/06/04 08:13:00 - mmengine - INFO - Epoch(train) [9][3300/3907] lr: 1.2933e-05 eta: 0:47:35 time: 0.6322 data_time: 0.0017 memory: 44120 loss: 0.3624 2023/06/04 08:14:03 - mmengine - INFO - Epoch(train) [9][3400/3907] lr: 1.2806e-05 eta: 0:46:32 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3890 2023/06/04 08:15:07 - mmengine - INFO - Epoch(train) [9][3500/3907] lr: 1.2682e-05 eta: 0:45:28 time: 0.6311 data_time: 0.0016 memory: 44120 loss: 0.3814 2023/06/04 08:16:10 - mmengine - INFO - Epoch(train) [9][3600/3907] lr: 1.2560e-05 eta: 0:44:25 time: 0.6319 data_time: 0.0017 memory: 44120 loss: 0.3663 2023/06/04 08:17:13 - mmengine - INFO - Epoch(train) [9][3700/3907] lr: 1.2441e-05 eta: 0:43:22 time: 0.6319 data_time: 0.0023 memory: 44120 loss: 0.3615 2023/06/04 08:17:41 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:18:16 - mmengine - INFO - Epoch(train) [9][3800/3907] lr: 1.2325e-05 eta: 0:42:19 time: 0.6342 data_time: 0.0016 memory: 44120 loss: 0.3735 2023/06/04 08:19:19 - mmengine - INFO - Epoch(train) [9][3900/3907] lr: 1.2211e-05 eta: 0:41:15 time: 0.6308 data_time: 0.0012 memory: 44120 loss: 0.4132 2023/06/04 08:19:23 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:19:23 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/06/04 08:20:57 - mmengine - INFO - Epoch(val) [9][57/57] accuracy/top1: 75.6376 single-label/precision_classwise: [69.57523345947266, 97.84231567382812] single-label/recall_classwise: [99.16040802001953, 46.75193786621094] single-label/f1-score_classwise: [81.774169921875, 63.271087646484375] data_time: 0.0317 time: 1.2791 2023/06/04 08:22:04 - mmengine - INFO - Epoch(train) [10][ 100/3907] lr: 1.2093e-05 eta: 0:40:08 time: 0.6304 data_time: 0.0017 memory: 44120 loss: 0.3572 2023/06/04 08:23:07 - mmengine - INFO - Epoch(train) [10][ 200/3907] lr: 1.1985e-05 eta: 0:39:05 time: 0.6307 data_time: 0.0016 memory: 44120 loss: 0.3765 2023/06/04 08:24:10 - mmengine - INFO - Epoch(train) [10][ 300/3907] lr: 1.1881e-05 eta: 0:38:01 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3687 2023/06/04 08:25:14 - mmengine - INFO - Epoch(train) [10][ 400/3907] lr: 1.1778e-05 eta: 0:36:58 time: 0.6301 data_time: 0.0016 memory: 44120 loss: 0.3558 2023/06/04 08:26:17 - mmengine - INFO - Epoch(train) [10][ 500/3907] lr: 1.1679e-05 eta: 0:35:55 time: 0.6314 data_time: 0.0015 memory: 44120 loss: 0.3804 2023/06/04 08:27:20 - mmengine - INFO - Epoch(train) [10][ 600/3907] lr: 1.1583e-05 eta: 0:34:52 time: 0.6309 data_time: 0.0017 memory: 44120 loss: 0.3518 2023/06/04 08:28:23 - mmengine - INFO - Epoch(train) [10][ 700/3907] lr: 1.1489e-05 eta: 0:33:48 time: 0.6328 data_time: 0.0021 memory: 44120 loss: 0.3624 2023/06/04 08:29:26 - mmengine - INFO - Epoch(train) [10][ 800/3907] lr: 1.1398e-05 eta: 0:32:45 time: 0.6307 data_time: 0.0016 memory: 44120 loss: 0.3868 2023/06/04 08:29:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:30:29 - mmengine - INFO - Epoch(train) [10][ 900/3907] lr: 1.1310e-05 eta: 0:31:42 time: 0.6328 data_time: 0.0017 memory: 44120 loss: 0.3741 2023/06/04 08:31:32 - mmengine - INFO - Epoch(train) [10][1000/3907] lr: 1.1225e-05 eta: 0:30:39 time: 0.6305 data_time: 0.0016 memory: 44120 loss: 0.3466 2023/06/04 08:32:36 - mmengine - INFO - Epoch(train) [10][1100/3907] lr: 1.1142e-05 eta: 0:29:35 time: 0.6306 data_time: 0.0018 memory: 44120 loss: 0.3633 2023/06/04 08:33:39 - mmengine - INFO - Epoch(train) [10][1200/3907] lr: 1.1063e-05 eta: 0:28:32 time: 0.6305 data_time: 0.0016 memory: 44120 loss: 0.3635 2023/06/04 08:34:42 - mmengine - INFO - Epoch(train) [10][1300/3907] lr: 1.0986e-05 eta: 0:27:29 time: 0.6311 data_time: 0.0017 memory: 44120 loss: 0.3559 2023/06/04 08:35:45 - mmengine - INFO - Epoch(train) [10][1400/3907] lr: 1.0912e-05 eta: 0:26:25 time: 0.6342 data_time: 0.0016 memory: 44120 loss: 0.3782 2023/06/04 08:36:48 - mmengine - INFO - Epoch(train) [10][1500/3907] lr: 1.0841e-05 eta: 0:25:22 time: 0.6316 data_time: 0.0022 memory: 44120 loss: 0.3685 2023/06/04 08:37:52 - mmengine - INFO - Epoch(train) [10][1600/3907] lr: 1.0773e-05 eta: 0:24:19 time: 0.6310 data_time: 0.0016 memory: 44120 loss: 0.3689 2023/06/04 08:38:55 - mmengine - INFO - Epoch(train) [10][1700/3907] lr: 1.0707e-05 eta: 0:23:16 time: 0.6304 data_time: 0.0015 memory: 44120 loss: 0.3840 2023/06/04 08:39:58 - mmengine - INFO - Epoch(train) [10][1800/3907] lr: 1.0645e-05 eta: 0:22:12 time: 0.6308 data_time: 0.0016 memory: 44120 loss: 0.3538 2023/06/04 08:40:21 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:41:01 - mmengine - INFO - Epoch(train) [10][1900/3907] lr: 1.0585e-05 eta: 0:21:09 time: 0.6312 data_time: 0.0016 memory: 44120 loss: 0.3882 2023/06/04 08:42:04 - mmengine - INFO - Epoch(train) [10][2000/3907] lr: 1.0529e-05 eta: 0:20:06 time: 0.6356 data_time: 0.0018 memory: 44120 loss: 0.3650 2023/06/04 08:43:07 - mmengine - INFO - Epoch(train) [10][2100/3907] lr: 1.0475e-05 eta: 0:19:03 time: 0.6305 data_time: 0.0017 memory: 44120 loss: 0.3672 2023/06/04 08:44:11 - mmengine - INFO - Epoch(train) [10][2200/3907] lr: 1.0424e-05 eta: 0:17:59 time: 0.6327 data_time: 0.0015 memory: 44120 loss: 0.3779 2023/06/04 08:45:14 - mmengine - INFO - Epoch(train) [10][2300/3907] lr: 1.0376e-05 eta: 0:16:56 time: 0.6307 data_time: 0.0016 memory: 44120 loss: 0.3571 2023/06/04 08:46:17 - mmengine - INFO - Epoch(train) [10][2400/3907] lr: 1.0330e-05 eta: 0:15:53 time: 0.6325 data_time: 0.0018 memory: 44120 loss: 0.3923 2023/06/04 08:47:20 - mmengine - INFO - Epoch(train) [10][2500/3907] lr: 1.0288e-05 eta: 0:14:50 time: 0.6336 data_time: 0.0018 memory: 44120 loss: 0.3453 2023/06/04 08:48:23 - mmengine - INFO - Epoch(train) [10][2600/3907] lr: 1.0249e-05 eta: 0:13:46 time: 0.6309 data_time: 0.0016 memory: 44120 loss: 0.3701 2023/06/04 08:49:27 - mmengine - INFO - Epoch(train) [10][2700/3907] lr: 1.0212e-05 eta: 0:12:43 time: 0.6314 data_time: 0.0018 memory: 44120 loss: 0.3581 2023/06/04 08:50:30 - mmengine - INFO - Epoch(train) [10][2800/3907] lr: 1.0178e-05 eta: 0:11:40 time: 0.6306 data_time: 0.0016 memory: 44120 loss: 0.3813 2023/06/04 08:50:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 08:51:33 - mmengine - INFO - Epoch(train) [10][2900/3907] lr: 1.0148e-05 eta: 0:10:37 time: 0.6367 data_time: 0.0017 memory: 44120 loss: 0.3749 2023/06/04 08:52:36 - mmengine - INFO - Epoch(train) [10][3000/3907] lr: 1.0120e-05 eta: 0:09:33 time: 0.6316 data_time: 0.0017 memory: 44120 loss: 0.3817 2023/06/04 08:53:39 - mmengine - INFO - Epoch(train) [10][3100/3907] lr: 1.0095e-05 eta: 0:08:30 time: 0.6315 data_time: 0.0017 memory: 44120 loss: 0.3391 2023/06/04 08:54:43 - mmengine - INFO - Epoch(train) [10][3200/3907] lr: 1.0073e-05 eta: 0:07:27 time: 0.6409 data_time: 0.0017 memory: 44120 loss: 0.3735 2023/06/04 08:55:46 - mmengine - INFO - Epoch(train) [10][3300/3907] lr: 1.0054e-05 eta: 0:06:23 time: 0.6356 data_time: 0.0024 memory: 44120 loss: 0.3694 2023/06/04 08:56:49 - mmengine - INFO - Epoch(train) [10][3400/3907] lr: 1.0038e-05 eta: 0:05:20 time: 0.6434 data_time: 0.0017 memory: 44120 loss: 0.3701 2023/06/04 08:57:53 - mmengine - INFO - Epoch(train) [10][3500/3907] lr: 1.0024e-05 eta: 0:04:17 time: 0.6300 data_time: 0.0016 memory: 44120 loss: 0.3660 2023/06/04 08:58:56 - mmengine - INFO - Epoch(train) [10][3600/3907] lr: 1.0014e-05 eta: 0:03:14 time: 0.6342 data_time: 0.0029 memory: 44120 loss: 0.3813 2023/06/04 08:59:59 - mmengine - INFO - Epoch(train) [10][3700/3907] lr: 1.0006e-05 eta: 0:02:10 time: 0.6326 data_time: 0.0022 memory: 44120 loss: 0.3606 2023/06/04 09:01:02 - mmengine - INFO - Epoch(train) [10][3800/3907] lr: 1.0002e-05 eta: 0:01:07 time: 0.6331 data_time: 0.0016 memory: 44120 loss: 0.3612 2023/06/04 09:01:26 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 09:02:05 - mmengine - INFO - Epoch(train) [10][3900/3907] lr: 1.0000e-05 eta: 0:00:04 time: 0.6311 data_time: 0.0012 memory: 44120 loss: 0.3667 2023/06/04 09:02:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr1e-4_20230604_015520 2023/06/04 09:02:09 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/06/04 09:03:43 - mmengine - INFO - Epoch(val) [10][57/57] accuracy/top1: 75.4254 single-label/precision_classwise: [69.43756103515625, 97.37055969238281] single-label/recall_classwise: [98.97734069824219, 46.503875732421875] single-label/f1-score_classwise: [81.61682891845703, 62.945281982421875] data_time: 0.0323 time: 1.2791