2023/06/06 05:21:18 - 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: 1258785886 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 ------------------------------------------------------------ 2023/06/06 05:21:22 - mmengine - INFO - Config: optim_wrapper = dict( optimizer=dict( type='AdamW', lr=0.0003, 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, final_norm=False, init_cfg=dict( type='Pretrained', checkpoint='ckpt/openclip-ViT-L-14.pth', prefix='backbone')), neck=dict( type='CLIPProjection', in_channels=1024, out_channels=768, init_cfg=dict( type='Pretrained', checkpoint='ckpt/openclip-ViT-L-14.pth', prefix='backbone')), head=dict( type='LinearClsHead', num_classes=2, in_channels=768, 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_lr3e-4' 2023/06/06 05:21:36 - 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 -------------------- 2023/06/06 05:21:55 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth 2023/06/06 05:21:59 - mmengine - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: ln1.weight, ln1.bias 2023/06/06 05:22:00 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth 2023/06/06 05:22:01 - mmengine - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: cls_token, pos_embed, patch_embed.projection.weight, pre_norm.weight, pre_norm.bias, layers.0.ln1.weight, layers.0.ln1.bias, layers.0.attn.qkv.weight, layers.0.attn.qkv.bias, layers.0.attn.proj.weight, layers.0.attn.proj.bias, layers.0.ln2.weight, layers.0.ln2.bias, layers.0.ffn.layers.0.0.weight, layers.0.ffn.layers.0.0.bias, layers.0.ffn.layers.1.weight, layers.0.ffn.layers.1.bias, layers.1.ln1.weight, layers.1.ln1.bias, layers.1.attn.qkv.weight, layers.1.attn.qkv.bias, layers.1.attn.proj.weight, layers.1.attn.proj.bias, layers.1.ln2.weight, layers.1.ln2.bias, layers.1.ffn.layers.0.0.weight, layers.1.ffn.layers.0.0.bias, layers.1.ffn.layers.1.weight, layers.1.ffn.layers.1.bias, layers.2.ln1.weight, layers.2.ln1.bias, layers.2.attn.qkv.weight, layers.2.attn.qkv.bias, layers.2.attn.proj.weight, layers.2.attn.proj.bias, layers.2.ln2.weight, layers.2.ln2.bias, layers.2.ffn.layers.0.0.weight, layers.2.ffn.layers.0.0.bias, layers.2.ffn.layers.1.weight, layers.2.ffn.layers.1.bias, layers.3.ln1.weight, layers.3.ln1.bias, layers.3.attn.qkv.weight, layers.3.attn.qkv.bias, layers.3.attn.proj.weight, layers.3.attn.proj.bias, layers.3.ln2.weight, layers.3.ln2.bias, layers.3.ffn.layers.0.0.weight, layers.3.ffn.layers.0.0.bias, layers.3.ffn.layers.1.weight, layers.3.ffn.layers.1.bias, layers.4.ln1.weight, layers.4.ln1.bias, layers.4.attn.qkv.weight, layers.4.attn.qkv.bias, layers.4.attn.proj.weight, layers.4.attn.proj.bias, layers.4.ln2.weight, layers.4.ln2.bias, layers.4.ffn.layers.0.0.weight, layers.4.ffn.layers.0.0.bias, layers.4.ffn.layers.1.weight, layers.4.ffn.layers.1.bias, layers.5.ln1.weight, layers.5.ln1.bias, layers.5.attn.qkv.weight, layers.5.attn.qkv.bias, layers.5.attn.proj.weight, layers.5.attn.proj.bias, layers.5.ln2.weight, layers.5.ln2.bias, layers.5.ffn.layers.0.0.weight, layers.5.ffn.layers.0.0.bias, layers.5.ffn.layers.1.weight, layers.5.ffn.layers.1.bias, layers.6.ln1.weight, layers.6.ln1.bias, layers.6.attn.qkv.weight, layers.6.attn.qkv.bias, layers.6.attn.proj.weight, layers.6.attn.proj.bias, layers.6.ln2.weight, layers.6.ln2.bias, layers.6.ffn.layers.0.0.weight, layers.6.ffn.layers.0.0.bias, layers.6.ffn.layers.1.weight, layers.6.ffn.layers.1.bias, layers.7.ln1.weight, layers.7.ln1.bias, layers.7.attn.qkv.weight, layers.7.attn.qkv.bias, layers.7.attn.proj.weight, layers.7.attn.proj.bias, layers.7.ln2.weight, layers.7.ln2.bias, layers.7.ffn.layers.0.0.weight, layers.7.ffn.layers.0.0.bias, layers.7.ffn.layers.1.weight, layers.7.ffn.layers.1.bias, layers.8.ln1.weight, layers.8.ln1.bias, layers.8.attn.qkv.weight, layers.8.attn.qkv.bias, layers.8.attn.proj.weight, layers.8.attn.proj.bias, layers.8.ln2.weight, layers.8.ln2.bias, layers.8.ffn.layers.0.0.weight, layers.8.ffn.layers.0.0.bias, layers.8.ffn.layers.1.weight, layers.8.ffn.layers.1.bias, layers.9.ln1.weight, layers.9.ln1.bias, layers.9.attn.qkv.weight, layers.9.attn.qkv.bias, layers.9.attn.proj.weight, layers.9.attn.proj.bias, layers.9.ln2.weight, layers.9.ln2.bias, layers.9.ffn.layers.0.0.weight, layers.9.ffn.layers.0.0.bias, layers.9.ffn.layers.1.weight, layers.9.ffn.layers.1.bias, layers.10.ln1.weight, layers.10.ln1.bias, layers.10.attn.qkv.weight, layers.10.attn.qkv.bias, layers.10.attn.proj.weight, layers.10.attn.proj.bias, layers.10.ln2.weight, layers.10.ln2.bias, layers.10.ffn.layers.0.0.weight, layers.10.ffn.layers.0.0.bias, layers.10.ffn.layers.1.weight, layers.10.ffn.layers.1.bias, layers.11.ln1.weight, layers.11.ln1.bias, layers.11.attn.qkv.weight, layers.11.attn.qkv.bias, layers.11.attn.proj.weight, layers.11.attn.proj.bias, layers.11.ln2.weight, layers.11.ln2.bias, layers.11.ffn.layers.0.0.weight, layers.11.ffn.layers.0.0.bias, layers.11.ffn.layers.1.weight, layers.11.ffn.layers.1.bias, layers.12.ln1.weight, layers.12.ln1.bias, layers.12.attn.qkv.weight, layers.12.attn.qkv.bias, layers.12.attn.proj.weight, layers.12.attn.proj.bias, layers.12.ln2.weight, layers.12.ln2.bias, layers.12.ffn.layers.0.0.weight, layers.12.ffn.layers.0.0.bias, layers.12.ffn.layers.1.weight, layers.12.ffn.layers.1.bias, layers.13.ln1.weight, layers.13.ln1.bias, layers.13.attn.qkv.weight, layers.13.attn.qkv.bias, layers.13.attn.proj.weight, layers.13.attn.proj.bias, layers.13.ln2.weight, layers.13.ln2.bias, layers.13.ffn.layers.0.0.weight, layers.13.ffn.layers.0.0.bias, layers.13.ffn.layers.1.weight, layers.13.ffn.layers.1.bias, layers.14.ln1.weight, layers.14.ln1.bias, layers.14.attn.qkv.weight, layers.14.attn.qkv.bias, layers.14.attn.proj.weight, layers.14.attn.proj.bias, layers.14.ln2.weight, layers.14.ln2.bias, layers.14.ffn.layers.0.0.weight, layers.14.ffn.layers.0.0.bias, layers.14.ffn.layers.1.weight, layers.14.ffn.layers.1.bias, layers.15.ln1.weight, layers.15.ln1.bias, layers.15.attn.qkv.weight, layers.15.attn.qkv.bias, layers.15.attn.proj.weight, layers.15.attn.proj.bias, layers.15.ln2.weight, layers.15.ln2.bias, layers.15.ffn.layers.0.0.weight, layers.15.ffn.layers.0.0.bias, layers.15.ffn.layers.1.weight, layers.15.ffn.layers.1.bias, layers.16.ln1.weight, layers.16.ln1.bias, layers.16.attn.qkv.weight, layers.16.attn.qkv.bias, layers.16.attn.proj.weight, layers.16.attn.proj.bias, layers.16.ln2.weight, layers.16.ln2.bias, layers.16.ffn.layers.0.0.weight, layers.16.ffn.layers.0.0.bias, layers.16.ffn.layers.1.weight, layers.16.ffn.layers.1.bias, layers.17.ln1.weight, layers.17.ln1.bias, layers.17.attn.qkv.weight, layers.17.attn.qkv.bias, layers.17.attn.proj.weight, layers.17.attn.proj.bias, layers.17.ln2.weight, layers.17.ln2.bias, layers.17.ffn.layers.0.0.weight, layers.17.ffn.layers.0.0.bias, layers.17.ffn.layers.1.weight, layers.17.ffn.layers.1.bias, layers.18.ln1.weight, layers.18.ln1.bias, layers.18.attn.qkv.weight, layers.18.attn.qkv.bias, layers.18.attn.proj.weight, layers.18.attn.proj.bias, layers.18.ln2.weight, layers.18.ln2.bias, layers.18.ffn.layers.0.0.weight, layers.18.ffn.layers.0.0.bias, layers.18.ffn.layers.1.weight, layers.18.ffn.layers.1.bias, layers.19.ln1.weight, layers.19.ln1.bias, layers.19.attn.qkv.weight, layers.19.attn.qkv.bias, layers.19.attn.proj.weight, layers.19.attn.proj.bias, layers.19.ln2.weight, layers.19.ln2.bias, layers.19.ffn.layers.0.0.weight, layers.19.ffn.layers.0.0.bias, layers.19.ffn.layers.1.weight, layers.19.ffn.layers.1.bias, layers.20.ln1.weight, layers.20.ln1.bias, layers.20.attn.qkv.weight, layers.20.attn.qkv.bias, layers.20.attn.proj.weight, layers.20.attn.proj.bias, layers.20.ln2.weight, layers.20.ln2.bias, layers.20.ffn.layers.0.0.weight, layers.20.ffn.layers.0.0.bias, layers.20.ffn.layers.1.weight, layers.20.ffn.layers.1.bias, layers.21.ln1.weight, layers.21.ln1.bias, layers.21.attn.qkv.weight, layers.21.attn.qkv.bias, layers.21.attn.proj.weight, layers.21.attn.proj.bias, layers.21.ln2.weight, layers.21.ln2.bias, layers.21.ffn.layers.0.0.weight, layers.21.ffn.layers.0.0.bias, layers.21.ffn.layers.1.weight, layers.21.ffn.layers.1.bias, layers.22.ln1.weight, layers.22.ln1.bias, layers.22.attn.qkv.weight, layers.22.attn.qkv.bias, layers.22.attn.proj.weight, layers.22.attn.proj.bias, layers.22.ln2.weight, layers.22.ln2.bias, layers.22.ffn.layers.0.0.weight, layers.22.ffn.layers.0.0.bias, layers.22.ffn.layers.1.weight, layers.22.ffn.layers.1.bias, layers.23.ln1.weight, layers.23.ln1.bias, layers.23.attn.qkv.weight, layers.23.attn.qkv.bias, layers.23.attn.proj.weight, layers.23.attn.proj.bias, layers.23.ln2.weight, layers.23.ln2.bias, layers.23.ffn.layers.0.0.weight, layers.23.ffn.layers.0.0.bias, layers.23.ffn.layers.1.weight, layers.23.ffn.layers.1.bias, ln1.weight, ln1.bias missing keys in source state_dict: proj 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 neck.proj - torch.Size([1024, 768]): The value is the same before and after calling `init_weights` of ImageClassifier head.fc.weight - torch.Size([2, 768]): 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 2023/06/06 05:22:01 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/06/06 05:22:01 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/06/06 05:22:01 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/luzeyu/workspace/fakebench/mmpretrain/workdir/clip_large_pretrain_4x256_sdv2_lr3e-4. 2023/06/06 05:23:13 - mmengine - INFO - Epoch(train) [1][ 100/3907] lr: 3.0000e-04 eta: 7:43:35 time: 0.6310 data_time: 0.0017 memory: 44138 loss: 0.4902 2023/06/06 05:24:16 - mmengine - INFO - Epoch(train) [1][ 200/3907] lr: 2.9998e-04 eta: 7:15:47 time: 0.6329 data_time: 0.0016 memory: 44138 loss: 0.4914 2023/06/06 05:25:19 - mmengine - INFO - Epoch(train) [1][ 300/3907] lr: 2.9996e-04 eta: 7:06:28 time: 0.6324 data_time: 0.0015 memory: 44138 loss: 0.4494 2023/06/06 05:26:23 - mmengine - INFO - Epoch(train) [1][ 400/3907] lr: 2.9993e-04 eta: 7:00:59 time: 0.6327 data_time: 0.0017 memory: 44138 loss: 0.4426 2023/06/06 05:27:26 - mmengine - INFO - Epoch(train) [1][ 500/3907] lr: 2.9988e-04 eta: 6:57:17 time: 0.6334 data_time: 0.0015 memory: 44138 loss: 0.4519 2023/06/06 05:28:29 - mmengine - INFO - Epoch(train) [1][ 600/3907] lr: 2.9983e-04 eta: 6:54:31 time: 0.6340 data_time: 0.0015 memory: 44138 loss: 0.4173 2023/06/06 05:29:33 - mmengine - INFO - Epoch(train) [1][ 700/3907] lr: 2.9977e-04 eta: 6:52:16 time: 0.6324 data_time: 0.0016 memory: 44138 loss: 0.4038 2023/06/06 05:30:36 - mmengine - INFO - Epoch(train) [1][ 800/3907] lr: 2.9970e-04 eta: 6:50:15 time: 0.6337 data_time: 0.0015 memory: 44138 loss: 0.4298 2023/06/06 05:31:39 - mmengine - INFO - Epoch(train) [1][ 900/3907] lr: 2.9962e-04 eta: 6:48:27 time: 0.6332 data_time: 0.0015 memory: 44138 loss: 0.4194 2023/06/06 05:32:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 05:32:43 - mmengine - INFO - Epoch(train) [1][1000/3907] lr: 2.9953e-04 eta: 6:46:49 time: 0.6328 data_time: 0.0015 memory: 44138 loss: 0.4238 2023/06/06 05:33:46 - mmengine - INFO - Epoch(train) [1][1100/3907] lr: 2.9943e-04 eta: 6:45:18 time: 0.6326 data_time: 0.0015 memory: 44138 loss: 0.4083 2023/06/06 05:36:10 - mmengine - INFO - Epoch(train) [1][1200/3907] lr: 2.9933e-04 eta: 7:26:02 time: 0.6305 data_time: 0.0014 memory: 44138 loss: 0.4097 2023/06/06 05:37:13 - mmengine - INFO - Epoch(train) [1][1300/3907] lr: 2.9921e-04 eta: 7:21:17 time: 0.6327 data_time: 0.0014 memory: 44138 loss: 0.3748 2023/06/06 05:38:16 - mmengine - INFO - Epoch(train) [1][1400/3907] lr: 2.9908e-04 eta: 7:17:07 time: 0.6336 data_time: 0.0015 memory: 44138 loss: 0.3998 2023/06/06 05:39:20 - mmengine - INFO - Epoch(train) [1][1500/3907] lr: 2.9895e-04 eta: 7:13:20 time: 0.6327 data_time: 0.0016 memory: 44138 loss: 0.3972 2023/06/06 05:40:23 - mmengine - INFO - Epoch(train) [1][1600/3907] lr: 2.9880e-04 eta: 7:09:52 time: 0.6335 data_time: 0.0016 memory: 44138 loss: 0.4123 2023/06/06 05:41:26 - mmengine - INFO - Epoch(train) [1][1700/3907] lr: 2.9865e-04 eta: 7:06:42 time: 0.6330 data_time: 0.0016 memory: 44138 loss: 0.4265 2023/06/06 05:42:30 - mmengine - INFO - Epoch(train) [1][1800/3907] lr: 2.9849e-04 eta: 7:03:51 time: 0.6333 data_time: 0.0017 memory: 44138 loss: 0.3921 2023/06/06 05:43:33 - mmengine - INFO - Epoch(train) [1][1900/3907] lr: 2.9831e-04 eta: 7:01:10 time: 0.6330 data_time: 0.0014 memory: 44138 loss: 0.3964 2023/06/06 05:44:37 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 05:44:37 - mmengine - INFO - Epoch(train) [1][2000/3907] lr: 2.9813e-04 eta: 6:58:36 time: 0.6349 data_time: 0.0014 memory: 44138 loss: 0.3734 2023/06/06 05:45:40 - mmengine - INFO - Epoch(train) [1][2100/3907] lr: 2.9794e-04 eta: 6:56:10 time: 0.6333 data_time: 0.0014 memory: 44138 loss: 0.3939 2023/06/06 05:46:43 - mmengine - INFO - Epoch(train) [1][2200/3907] lr: 2.9774e-04 eta: 6:53:53 time: 0.6339 data_time: 0.0015 memory: 44138 loss: 0.3556 2023/06/06 05:47:47 - mmengine - INFO - Epoch(train) [1][2300/3907] lr: 2.9753e-04 eta: 6:51:40 time: 0.6328 data_time: 0.0015 memory: 44138 loss: 0.3780 2023/06/06 05:48:50 - mmengine - INFO - Epoch(train) [1][2400/3907] lr: 2.9731e-04 eta: 6:49:34 time: 0.6330 data_time: 0.0014 memory: 44138 loss: 0.3937 2023/06/06 05:49:53 - mmengine - INFO - Epoch(train) [1][2500/3907] lr: 2.9708e-04 eta: 6:47:33 time: 0.6332 data_time: 0.0014 memory: 44138 loss: 0.3939 2023/06/06 05:50:57 - mmengine - INFO - Epoch(train) [1][2600/3907] lr: 2.9685e-04 eta: 6:45:36 time: 0.6337 data_time: 0.0014 memory: 44138 loss: 0.3750 2023/06/06 05:52:00 - mmengine - INFO - Epoch(train) [1][2700/3907] lr: 2.9660e-04 eta: 6:43:44 time: 0.6326 data_time: 0.0015 memory: 44138 loss: 0.3766 2023/06/06 05:53:03 - mmengine - INFO - Epoch(train) [1][2800/3907] lr: 2.9634e-04 eta: 6:41:55 time: 0.6333 data_time: 0.0015 memory: 44138 loss: 0.3962 2023/06/06 05:54:07 - mmengine - INFO - Epoch(train) [1][2900/3907] lr: 2.9608e-04 eta: 6:40:09 time: 0.6331 data_time: 0.0015 memory: 44138 loss: 0.3758 2023/06/06 05:55:13 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 05:55:13 - mmengine - INFO - Epoch(train) [1][3000/3907] lr: 2.9580e-04 eta: 6:39:08 time: 0.6327 data_time: 0.0016 memory: 44138 loss: 0.3716 2023/06/06 05:56:17 - mmengine - INFO - Epoch(train) [1][3100/3907] lr: 2.9552e-04 eta: 6:37:25 time: 0.6324 data_time: 0.0015 memory: 44138 loss: 0.3768 2023/06/06 05:57:20 - mmengine - INFO - Epoch(train) [1][3200/3907] lr: 2.9523e-04 eta: 6:35:45 time: 0.6326 data_time: 0.0016 memory: 44138 loss: 0.3876 2023/06/06 05:58:23 - mmengine - INFO - Epoch(train) [1][3300/3907] lr: 2.9493e-04 eta: 6:34:07 time: 0.6327 data_time: 0.0015 memory: 44138 loss: 0.3849 2023/06/06 05:59:26 - mmengine - INFO - Epoch(train) [1][3400/3907] lr: 2.9462e-04 eta: 6:32:31 time: 0.6326 data_time: 0.0015 memory: 44138 loss: 0.3955 2023/06/06 06:00:30 - mmengine - INFO - Epoch(train) [1][3500/3907] lr: 2.9430e-04 eta: 6:30:57 time: 0.6329 data_time: 0.0015 memory: 44138 loss: 0.3836 2023/06/06 06:01:33 - mmengine - INFO - Epoch(train) [1][3600/3907] lr: 2.9397e-04 eta: 6:29:26 time: 0.6334 data_time: 0.0016 memory: 44138 loss: 0.3765 2023/06/06 06:02:36 - mmengine - INFO - Epoch(train) [1][3700/3907] lr: 2.9363e-04 eta: 6:27:55 time: 0.6333 data_time: 0.0016 memory: 44138 loss: 0.3621 2023/06/06 06:03:40 - mmengine - INFO - Epoch(train) [1][3800/3907] lr: 2.9329e-04 eta: 6:26:26 time: 0.6321 data_time: 0.0016 memory: 44138 loss: 0.3587 2023/06/06 06:04:43 - mmengine - INFO - Epoch(train) [1][3900/3907] lr: 2.9293e-04 eta: 6:24:58 time: 0.6322 data_time: 0.0012 memory: 44138 loss: 0.3765 2023/06/06 06:04:47 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:04:47 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/06/06 06:06:34 - mmengine - INFO - Epoch(val) [1][57/57] accuracy/top1: 65.9059 single-label/precision_classwise: [61.83221435546875, 98.3172378540039] single-label/recall_classwise: [99.65911865234375, 24.45736312866211] single-label/f1-score_classwise: [76.31547546386719, 39.170650482177734] data_time: 0.0454 time: 1.3536 2023/06/06 06:07:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:07:41 - mmengine - INFO - Epoch(train) [2][ 100/3907] lr: 2.9254e-04 eta: 6:23:50 time: 0.6337 data_time: 0.0017 memory: 44138 loss: 0.3807 2023/06/06 06:08:44 - mmengine - INFO - Epoch(train) [2][ 200/3907] lr: 2.9217e-04 eta: 6:22:25 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.3625 2023/06/06 06:09:48 - mmengine - INFO - Epoch(train) [2][ 300/3907] lr: 2.9179e-04 eta: 6:21:01 time: 0.6334 data_time: 0.0015 memory: 44137 loss: 0.3828 2023/06/06 06:10:51 - mmengine - INFO - Epoch(train) [2][ 400/3907] lr: 2.9139e-04 eta: 6:19:38 time: 0.6332 data_time: 0.0015 memory: 44137 loss: 0.3831 2023/06/06 06:11:54 - mmengine - INFO - Epoch(train) [2][ 500/3907] lr: 2.9099e-04 eta: 6:18:16 time: 0.6360 data_time: 0.0014 memory: 44137 loss: 0.3692 2023/06/06 06:12:58 - mmengine - INFO - Epoch(train) [2][ 600/3907] lr: 2.9059e-04 eta: 6:16:55 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.3525 2023/06/06 06:14:01 - mmengine - INFO - Epoch(train) [2][ 700/3907] lr: 2.9017e-04 eta: 6:15:34 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3589 2023/06/06 06:15:05 - mmengine - INFO - Epoch(train) [2][ 800/3907] lr: 2.8974e-04 eta: 6:14:13 time: 0.6326 data_time: 0.0014 memory: 44137 loss: 0.3609 2023/06/06 06:16:08 - mmengine - INFO - Epoch(train) [2][ 900/3907] lr: 2.8931e-04 eta: 6:12:54 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3747 2023/06/06 06:17:11 - mmengine - INFO - Epoch(train) [2][1000/3907] lr: 2.8886e-04 eta: 6:11:35 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.3882 2023/06/06 06:18:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:18:15 - mmengine - INFO - Epoch(train) [2][1100/3907] lr: 2.8841e-04 eta: 6:10:17 time: 0.6332 data_time: 0.0019 memory: 44137 loss: 0.3529 2023/06/06 06:19:18 - mmengine - INFO - Epoch(train) [2][1200/3907] lr: 2.8795e-04 eta: 6:08:59 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.3874 2023/06/06 06:20:21 - mmengine - INFO - Epoch(train) [2][1300/3907] lr: 2.8748e-04 eta: 6:07:42 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3844 2023/06/06 06:21:25 - mmengine - INFO - Epoch(train) [2][1400/3907] lr: 2.8700e-04 eta: 6:06:26 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.3736 2023/06/06 06:22:28 - mmengine - INFO - Epoch(train) [2][1500/3907] lr: 2.8651e-04 eta: 6:05:10 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.3806 2023/06/06 06:23:31 - mmengine - INFO - Epoch(train) [2][1600/3907] lr: 2.8602e-04 eta: 6:03:54 time: 0.6350 data_time: 0.0013 memory: 44137 loss: 0.3710 2023/06/06 06:24:35 - mmengine - INFO - Epoch(train) [2][1700/3907] lr: 2.8552e-04 eta: 6:02:40 time: 0.6440 data_time: 0.0015 memory: 44137 loss: 0.3771 2023/06/06 06:25:38 - mmengine - INFO - Epoch(train) [2][1800/3907] lr: 2.8500e-04 eta: 6:01:25 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.3843 2023/06/06 06:26:42 - mmengine - INFO - Epoch(train) [2][1900/3907] lr: 2.8448e-04 eta: 6:00:11 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.4046 2023/06/06 06:27:45 - mmengine - INFO - Epoch(train) [2][2000/3907] lr: 2.8395e-04 eta: 5:58:57 time: 0.6342 data_time: 0.0014 memory: 44137 loss: 0.3640 2023/06/06 06:28:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:28:48 - mmengine - INFO - Epoch(train) [2][2100/3907] lr: 2.8342e-04 eta: 5:57:43 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.3548 2023/06/06 06:29:52 - mmengine - INFO - Epoch(train) [2][2200/3907] lr: 2.8287e-04 eta: 5:56:30 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.3748 2023/06/06 06:30:55 - mmengine - INFO - Epoch(train) [2][2300/3907] lr: 2.8232e-04 eta: 5:55:17 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3613 2023/06/06 06:31:59 - mmengine - INFO - Epoch(train) [2][2400/3907] lr: 2.8176e-04 eta: 5:54:05 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.3847 2023/06/06 06:33:02 - mmengine - INFO - Epoch(train) [2][2500/3907] lr: 2.8119e-04 eta: 5:52:53 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.3942 2023/06/06 06:34:06 - mmengine - INFO - Epoch(train) [2][2600/3907] lr: 2.8061e-04 eta: 5:51:41 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.3432 2023/06/06 06:35:09 - mmengine - INFO - Epoch(train) [2][2700/3907] lr: 2.8002e-04 eta: 5:50:30 time: 0.6329 data_time: 0.0013 memory: 44137 loss: 0.4181 2023/06/06 06:36:12 - mmengine - INFO - Epoch(train) [2][2800/3907] lr: 2.7943e-04 eta: 5:49:18 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.3541 2023/06/06 06:37:16 - mmengine - INFO - Epoch(train) [2][2900/3907] lr: 2.7882e-04 eta: 5:48:06 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.3673 2023/06/06 06:38:19 - mmengine - INFO - Epoch(train) [2][3000/3907] lr: 2.7821e-04 eta: 5:46:55 time: 0.6329 data_time: 0.0015 memory: 44137 loss: 0.3860 2023/06/06 06:39:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:39:22 - mmengine - INFO - Epoch(train) [2][3100/3907] lr: 2.7759e-04 eta: 5:45:44 time: 0.6331 data_time: 0.0016 memory: 44137 loss: 0.3611 2023/06/06 06:40:26 - mmengine - INFO - Epoch(train) [2][3200/3907] lr: 2.7697e-04 eta: 5:44:33 time: 0.6328 data_time: 0.0014 memory: 44137 loss: 0.3986 2023/06/06 06:41:29 - mmengine - INFO - Epoch(train) [2][3300/3907] lr: 2.7633e-04 eta: 5:43:23 time: 0.6332 data_time: 0.0013 memory: 44137 loss: 0.3689 2023/06/06 06:42:33 - mmengine - INFO - Epoch(train) [2][3400/3907] lr: 2.7569e-04 eta: 5:42:13 time: 0.6328 data_time: 0.0014 memory: 44137 loss: 0.3703 2023/06/06 06:43:36 - mmengine - INFO - Epoch(train) [2][3500/3907] lr: 2.7504e-04 eta: 5:41:03 time: 0.6328 data_time: 0.0014 memory: 44137 loss: 0.4029 2023/06/06 06:44:39 - mmengine - INFO - Epoch(train) [2][3600/3907] lr: 2.7438e-04 eta: 5:39:53 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.3923 2023/06/06 06:45:43 - mmengine - INFO - Epoch(train) [2][3700/3907] lr: 2.7372e-04 eta: 5:38:43 time: 0.6332 data_time: 0.0015 memory: 44137 loss: 0.3727 2023/06/06 06:46:46 - mmengine - INFO - Epoch(train) [2][3800/3907] lr: 2.7304e-04 eta: 5:37:34 time: 0.6326 data_time: 0.0014 memory: 44137 loss: 0.3905 2023/06/06 06:47:49 - mmengine - INFO - Epoch(train) [2][3900/3907] lr: 2.7236e-04 eta: 5:36:24 time: 0.6329 data_time: 0.0014 memory: 44137 loss: 0.3634 2023/06/06 06:47:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:47:53 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/06/06 06:49:35 - mmengine - INFO - Epoch(val) [2][57/57] accuracy/top1: 73.0350 single-label/precision_classwise: [67.38280487060547, 97.09217834472656] single-label/recall_classwise: [98.99627685546875, 41.15503692626953] single-label/f1-score_classwise: [80.18611907958984, 57.80705261230469] data_time: 0.0413 time: 1.2851 2023/06/06 06:50:41 - mmengine - INFO - Epoch(train) [3][ 100/3907] lr: 2.7163e-04 eta: 5:35:21 time: 0.6344 data_time: 0.0015 memory: 44137 loss: 0.3904 2023/06/06 06:51:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 06:51:45 - mmengine - INFO - Epoch(train) [3][ 200/3907] lr: 2.7093e-04 eta: 5:34:12 time: 0.6343 data_time: 0.0016 memory: 44137 loss: 0.3502 2023/06/06 06:52:48 - mmengine - INFO - Epoch(train) [3][ 300/3907] lr: 2.7022e-04 eta: 5:33:03 time: 0.6333 data_time: 0.0015 memory: 44137 loss: 0.3972 2023/06/06 06:53:52 - mmengine - INFO - Epoch(train) [3][ 400/3907] lr: 2.6951e-04 eta: 5:31:55 time: 0.6353 data_time: 0.0016 memory: 44137 loss: 0.3641 2023/06/06 06:54:55 - mmengine - INFO - Epoch(train) [3][ 500/3907] lr: 2.6879e-04 eta: 5:30:46 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.4046 2023/06/06 06:55:59 - mmengine - INFO - Epoch(train) [3][ 600/3907] lr: 2.6807e-04 eta: 5:29:38 time: 0.6367 data_time: 0.0014 memory: 44137 loss: 0.3757 2023/06/06 06:57:02 - mmengine - INFO - Epoch(train) [3][ 700/3907] lr: 2.6733e-04 eta: 5:28:30 time: 0.6332 data_time: 0.0015 memory: 44137 loss: 0.3754 2023/06/06 06:58:06 - mmengine - INFO - Epoch(train) [3][ 800/3907] lr: 2.6659e-04 eta: 5:27:22 time: 0.6426 data_time: 0.0015 memory: 44137 loss: 0.3896 2023/06/06 06:59:09 - mmengine - INFO - Epoch(train) [3][ 900/3907] lr: 2.6585e-04 eta: 5:26:14 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.3795 2023/06/06 07:00:12 - mmengine - INFO - Epoch(train) [3][1000/3907] lr: 2.6509e-04 eta: 5:25:05 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.3862 2023/06/06 07:01:16 - mmengine - INFO - Epoch(train) [3][1100/3907] lr: 2.6433e-04 eta: 5:23:57 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4060 2023/06/06 07:02:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:02:19 - mmengine - INFO - Epoch(train) [3][1200/3907] lr: 2.6356e-04 eta: 5:22:49 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3851 2023/06/06 07:03:23 - mmengine - INFO - Epoch(train) [3][1300/3907] lr: 2.6278e-04 eta: 5:21:41 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.3818 2023/06/06 07:04:26 - mmengine - INFO - Epoch(train) [3][1400/3907] lr: 2.6200e-04 eta: 5:20:34 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.3861 2023/06/06 07:05:29 - mmengine - INFO - Epoch(train) [3][1500/3907] lr: 2.6121e-04 eta: 5:19:26 time: 0.6337 data_time: 0.0016 memory: 44137 loss: 0.4049 2023/06/06 07:06:33 - mmengine - INFO - Epoch(train) [3][1600/3907] lr: 2.6041e-04 eta: 5:18:18 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3932 2023/06/06 07:07:36 - mmengine - INFO - Epoch(train) [3][1700/3907] lr: 2.5961e-04 eta: 5:17:11 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.3619 2023/06/06 07:08:40 - mmengine - INFO - Epoch(train) [3][1800/3907] lr: 2.5880e-04 eta: 5:16:03 time: 0.6326 data_time: 0.0015 memory: 44137 loss: 0.3690 2023/06/06 07:09:43 - mmengine - INFO - Epoch(train) [3][1900/3907] lr: 2.5798e-04 eta: 5:14:56 time: 0.6339 data_time: 0.0013 memory: 44137 loss: 0.3662 2023/06/06 07:10:46 - mmengine - INFO - Epoch(train) [3][2000/3907] lr: 2.5715e-04 eta: 5:13:49 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.4190 2023/06/06 07:11:50 - mmengine - INFO - Epoch(train) [3][2100/3907] lr: 2.5632e-04 eta: 5:12:41 time: 0.6336 data_time: 0.0014 memory: 44137 loss: 0.4015 2023/06/06 07:12:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:12:53 - mmengine - INFO - Epoch(train) [3][2200/3907] lr: 2.5549e-04 eta: 5:11:35 time: 0.6363 data_time: 0.0014 memory: 44137 loss: 0.3521 2023/06/06 07:13:57 - mmengine - INFO - Epoch(train) [3][2300/3907] lr: 2.5464e-04 eta: 5:10:27 time: 0.6344 data_time: 0.0014 memory: 44137 loss: 0.3942 2023/06/06 07:15:00 - mmengine - INFO - Epoch(train) [3][2400/3907] lr: 2.5379e-04 eta: 5:09:20 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.3686 2023/06/06 07:16:03 - mmengine - INFO - Epoch(train) [3][2500/3907] lr: 2.5294e-04 eta: 5:08:13 time: 0.6346 data_time: 0.0014 memory: 44137 loss: 0.3932 2023/06/06 07:17:07 - mmengine - INFO - Epoch(train) [3][2600/3907] lr: 2.5207e-04 eta: 5:07:07 time: 0.6329 data_time: 0.0014 memory: 44137 loss: 0.3807 2023/06/06 07:18:10 - mmengine - INFO - Epoch(train) [3][2700/3907] lr: 2.5120e-04 eta: 5:06:00 time: 0.6345 data_time: 0.0015 memory: 44137 loss: 0.3918 2023/06/06 07:19:14 - mmengine - INFO - Epoch(train) [3][2800/3907] lr: 2.5033e-04 eta: 5:04:53 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.4117 2023/06/06 07:20:17 - mmengine - INFO - Epoch(train) [3][2900/3907] lr: 2.4945e-04 eta: 5:03:47 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.3975 2023/06/06 07:21:20 - mmengine - INFO - Epoch(train) [3][3000/3907] lr: 2.4856e-04 eta: 5:02:40 time: 0.6353 data_time: 0.0014 memory: 44137 loss: 0.3954 2023/06/06 07:22:24 - mmengine - INFO - Epoch(train) [3][3100/3907] lr: 2.4767e-04 eta: 5:01:33 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3588 2023/06/06 07:23:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:23:27 - mmengine - INFO - Epoch(train) [3][3200/3907] lr: 2.4677e-04 eta: 5:00:27 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.4098 2023/06/06 07:24:30 - mmengine - INFO - Epoch(train) [3][3300/3907] lr: 2.4586e-04 eta: 4:59:20 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.4026 2023/06/06 07:25:34 - mmengine - INFO - Epoch(train) [3][3400/3907] lr: 2.4495e-04 eta: 4:58:14 time: 0.6329 data_time: 0.0016 memory: 44137 loss: 0.3887 2023/06/06 07:26:37 - mmengine - INFO - Epoch(train) [3][3500/3907] lr: 2.4403e-04 eta: 4:57:07 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3891 2023/06/06 07:27:41 - mmengine - INFO - Epoch(train) [3][3600/3907] lr: 2.4311e-04 eta: 4:56:01 time: 0.6328 data_time: 0.0015 memory: 44137 loss: 0.4167 2023/06/06 07:28:44 - mmengine - INFO - Epoch(train) [3][3700/3907] lr: 2.4218e-04 eta: 4:54:55 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3952 2023/06/06 07:29:48 - mmengine - INFO - Epoch(train) [3][3800/3907] lr: 2.4124e-04 eta: 4:53:49 time: 0.6332 data_time: 0.0016 memory: 44137 loss: 0.3703 2023/06/06 07:30:51 - mmengine - INFO - Epoch(train) [3][3900/3907] lr: 2.4030e-04 eta: 4:52:43 time: 0.6336 data_time: 0.0011 memory: 44137 loss: 0.4004 2023/06/06 07:30:55 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:30:55 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/06/06 07:32:37 - mmengine - INFO - Epoch(val) [3][57/57] accuracy/top1: 73.6474 single-label/precision_classwise: [67.92108917236328, 96.91683959960938] single-label/recall_classwise: [98.89527130126953, 42.643409729003906] single-label/f1-score_classwise: [80.53256225585938, 59.226959228515625] data_time: 0.0359 time: 1.2846 2023/06/06 07:33:43 - mmengine - INFO - Epoch(train) [4][ 100/3907] lr: 2.3929e-04 eta: 4:51:39 time: 0.6335 data_time: 0.0016 memory: 44137 loss: 0.3860 2023/06/06 07:34:47 - mmengine - INFO - Epoch(train) [4][ 200/3907] lr: 2.3834e-04 eta: 4:50:33 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.3928 2023/06/06 07:35:37 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:35:50 - mmengine - INFO - Epoch(train) [4][ 300/3907] lr: 2.3738e-04 eta: 4:49:27 time: 0.6350 data_time: 0.0015 memory: 44137 loss: 0.4065 2023/06/06 07:36:54 - mmengine - INFO - Epoch(train) [4][ 400/3907] lr: 2.3642e-04 eta: 4:48:21 time: 0.6337 data_time: 0.0015 memory: 44137 loss: 0.3975 2023/06/06 07:37:57 - mmengine - INFO - Epoch(train) [4][ 500/3907] lr: 2.3545e-04 eta: 4:47:15 time: 0.6337 data_time: 0.0016 memory: 44137 loss: 0.3993 2023/06/06 07:39:01 - mmengine - INFO - Epoch(train) [4][ 600/3907] lr: 2.3448e-04 eta: 4:46:09 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.3807 2023/06/06 07:40:04 - mmengine - INFO - Epoch(train) [4][ 700/3907] lr: 2.3350e-04 eta: 4:45:03 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.3722 2023/06/06 07:41:07 - mmengine - INFO - Epoch(train) [4][ 800/3907] lr: 2.3252e-04 eta: 4:43:57 time: 0.6342 data_time: 0.0017 memory: 44137 loss: 0.4032 2023/06/06 07:42:11 - mmengine - INFO - Epoch(train) [4][ 900/3907] lr: 2.3153e-04 eta: 4:42:52 time: 0.6331 data_time: 0.0016 memory: 44137 loss: 0.4019 2023/06/06 07:43:14 - mmengine - INFO - Epoch(train) [4][1000/3907] lr: 2.3054e-04 eta: 4:41:46 time: 0.6352 data_time: 0.0014 memory: 44137 loss: 0.4120 2023/06/06 07:44:18 - mmengine - INFO - Epoch(train) [4][1100/3907] lr: 2.2954e-04 eta: 4:40:40 time: 0.6339 data_time: 0.0016 memory: 44137 loss: 0.3979 2023/06/06 07:45:21 - mmengine - INFO - Epoch(train) [4][1200/3907] lr: 2.2854e-04 eta: 4:39:34 time: 0.6344 data_time: 0.0016 memory: 44137 loss: 0.4025 2023/06/06 07:46:11 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:46:24 - mmengine - INFO - Epoch(train) [4][1300/3907] lr: 2.2753e-04 eta: 4:38:29 time: 0.6327 data_time: 0.0017 memory: 44137 loss: 0.3891 2023/06/06 07:47:28 - mmengine - INFO - Epoch(train) [4][1400/3907] lr: 2.2652e-04 eta: 4:37:23 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.3711 2023/06/06 07:48:31 - mmengine - INFO - Epoch(train) [4][1500/3907] lr: 2.2551e-04 eta: 4:36:17 time: 0.6345 data_time: 0.0015 memory: 44137 loss: 0.3801 2023/06/06 07:49:35 - mmengine - INFO - Epoch(train) [4][1600/3907] lr: 2.2448e-04 eta: 4:35:12 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.3855 2023/06/06 07:50:38 - mmengine - INFO - Epoch(train) [4][1700/3907] lr: 2.2346e-04 eta: 4:34:07 time: 0.6346 data_time: 0.0014 memory: 44137 loss: 0.3935 2023/06/06 07:51:42 - mmengine - INFO - Epoch(train) [4][1800/3907] lr: 2.2243e-04 eta: 4:33:01 time: 0.6364 data_time: 0.0014 memory: 44137 loss: 0.3960 2023/06/06 07:52:45 - mmengine - INFO - Epoch(train) [4][1900/3907] lr: 2.2139e-04 eta: 4:31:56 time: 0.6374 data_time: 0.0015 memory: 44137 loss: 0.4126 2023/06/06 07:53:49 - mmengine - INFO - Epoch(train) [4][2000/3907] lr: 2.2036e-04 eta: 4:30:51 time: 0.6339 data_time: 0.0014 memory: 44137 loss: 0.4013 2023/06/06 07:54:52 - mmengine - INFO - Epoch(train) [4][2100/3907] lr: 2.1931e-04 eta: 4:29:45 time: 0.6343 data_time: 0.0014 memory: 44137 loss: 0.4048 2023/06/06 07:55:56 - mmengine - INFO - Epoch(train) [4][2200/3907] lr: 2.1827e-04 eta: 4:28:40 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.4055 2023/06/06 07:56:46 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 07:56:59 - mmengine - INFO - Epoch(train) [4][2300/3907] lr: 2.1721e-04 eta: 4:27:35 time: 0.6355 data_time: 0.0015 memory: 44137 loss: 0.4077 2023/06/06 07:58:03 - mmengine - INFO - Epoch(train) [4][2400/3907] lr: 2.1616e-04 eta: 4:26:30 time: 0.6345 data_time: 0.0015 memory: 44137 loss: 0.4163 2023/06/06 07:59:06 - mmengine - INFO - Epoch(train) [4][2500/3907] lr: 2.1510e-04 eta: 4:25:24 time: 0.6341 data_time: 0.0016 memory: 44137 loss: 0.3776 2023/06/06 08:00:09 - mmengine - INFO - Epoch(train) [4][2600/3907] lr: 2.1404e-04 eta: 4:24:19 time: 0.6339 data_time: 0.0014 memory: 44137 loss: 0.4263 2023/06/06 08:01:13 - mmengine - INFO - Epoch(train) [4][2700/3907] lr: 2.1297e-04 eta: 4:23:14 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.3801 2023/06/06 08:02:16 - mmengine - INFO - Epoch(train) [4][2800/3907] lr: 2.1190e-04 eta: 4:22:09 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.3921 2023/06/06 08:03:20 - mmengine - INFO - Epoch(train) [4][2900/3907] lr: 2.1083e-04 eta: 4:21:04 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.3812 2023/06/06 08:04:23 - mmengine - INFO - Epoch(train) [4][3000/3907] lr: 2.0975e-04 eta: 4:19:59 time: 0.6346 data_time: 0.0014 memory: 44137 loss: 0.3905 2023/06/06 08:05:26 - mmengine - INFO - Epoch(train) [4][3100/3907] lr: 2.0867e-04 eta: 4:18:53 time: 0.6332 data_time: 0.0017 memory: 44137 loss: 0.4121 2023/06/06 08:06:30 - mmengine - INFO - Epoch(train) [4][3200/3907] lr: 2.0758e-04 eta: 4:17:48 time: 0.6328 data_time: 0.0015 memory: 44137 loss: 0.3613 2023/06/06 08:07:20 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:07:33 - mmengine - INFO - Epoch(train) [4][3300/3907] lr: 2.0649e-04 eta: 4:16:43 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.3770 2023/06/06 08:08:37 - mmengine - INFO - Epoch(train) [4][3400/3907] lr: 2.0540e-04 eta: 4:15:38 time: 0.6348 data_time: 0.0015 memory: 44137 loss: 0.3904 2023/06/06 08:09:40 - mmengine - INFO - Epoch(train) [4][3500/3907] lr: 2.0431e-04 eta: 4:14:33 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.3929 2023/06/06 08:10:43 - mmengine - INFO - Epoch(train) [4][3600/3907] lr: 2.0321e-04 eta: 4:13:28 time: 0.6337 data_time: 0.0015 memory: 44137 loss: 0.4146 2023/06/06 08:11:47 - mmengine - INFO - Epoch(train) [4][3700/3907] lr: 2.0211e-04 eta: 4:12:23 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.3817 2023/06/06 08:12:50 - mmengine - INFO - Epoch(train) [4][3800/3907] lr: 2.0100e-04 eta: 4:11:18 time: 0.6344 data_time: 0.0016 memory: 44137 loss: 0.3898 2023/06/06 08:13:54 - mmengine - INFO - Epoch(train) [4][3900/3907] lr: 1.9990e-04 eta: 4:10:13 time: 0.6353 data_time: 0.0012 memory: 44137 loss: 0.4089 2023/06/06 08:13:58 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:13:58 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/06/06 08:15:43 - mmengine - INFO - Epoch(val) [4][57/57] accuracy/top1: 74.1032 single-label/precision_classwise: [68.3282470703125, 96.79299926757812] single-label/recall_classwise: [98.81951904296875, 43.75193786621094] single-label/f1-score_classwise: [80.79275512695312, 60.26373291015625] data_time: 0.0387 time: 1.2833 2023/06/06 08:16:49 - mmengine - INFO - Epoch(train) [5][ 100/3907] lr: 1.9871e-04 eta: 4:09:08 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.3896 2023/06/06 08:17:53 - mmengine - INFO - Epoch(train) [5][ 200/3907] lr: 1.9760e-04 eta: 4:08:03 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.4006 2023/06/06 08:18:56 - mmengine - INFO - Epoch(train) [5][ 300/3907] lr: 1.9648e-04 eta: 4:06:58 time: 0.6331 data_time: 0.0019 memory: 44137 loss: 0.3996 2023/06/06 08:19:42 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:20:00 - mmengine - INFO - Epoch(train) [5][ 400/3907] lr: 1.9536e-04 eta: 4:05:53 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4185 2023/06/06 08:21:03 - mmengine - INFO - Epoch(train) [5][ 500/3907] lr: 1.9424e-04 eta: 4:04:48 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.3988 2023/06/06 08:22:07 - mmengine - INFO - Epoch(train) [5][ 600/3907] lr: 1.9312e-04 eta: 4:03:43 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4062 2023/06/06 08:23:10 - mmengine - INFO - Epoch(train) [5][ 700/3907] lr: 1.9199e-04 eta: 4:02:38 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.3885 2023/06/06 08:24:13 - mmengine - INFO - Epoch(train) [5][ 800/3907] lr: 1.9086e-04 eta: 4:01:33 time: 0.6340 data_time: 0.0016 memory: 44137 loss: 0.4010 2023/06/06 08:25:17 - mmengine - INFO - Epoch(train) [5][ 900/3907] lr: 1.8973e-04 eta: 4:00:29 time: 0.6329 data_time: 0.0016 memory: 44137 loss: 0.3853 2023/06/06 08:26:20 - mmengine - INFO - Epoch(train) [5][1000/3907] lr: 1.8860e-04 eta: 3:59:24 time: 0.6334 data_time: 0.0017 memory: 44137 loss: 0.4026 2023/06/06 08:27:24 - mmengine - INFO - Epoch(train) [5][1100/3907] lr: 1.8746e-04 eta: 3:58:19 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.4035 2023/06/06 08:28:27 - mmengine - INFO - Epoch(train) [5][1200/3907] lr: 1.8632e-04 eta: 3:57:14 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.4132 2023/06/06 08:29:30 - mmengine - INFO - Epoch(train) [5][1300/3907] lr: 1.8519e-04 eta: 3:56:09 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3668 2023/06/06 08:30:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:30:34 - mmengine - INFO - Epoch(train) [5][1400/3907] lr: 1.8404e-04 eta: 3:55:04 time: 0.6333 data_time: 0.0015 memory: 44137 loss: 0.4048 2023/06/06 08:31:37 - mmengine - INFO - Epoch(train) [5][1500/3907] lr: 1.8290e-04 eta: 3:54:00 time: 0.6331 data_time: 0.0016 memory: 44137 loss: 0.3937 2023/06/06 08:32:40 - mmengine - INFO - Epoch(train) [5][1600/3907] lr: 1.8176e-04 eta: 3:52:55 time: 0.6332 data_time: 0.0015 memory: 44137 loss: 0.4019 2023/06/06 08:33:44 - mmengine - INFO - Epoch(train) [5][1700/3907] lr: 1.8061e-04 eta: 3:51:50 time: 0.6330 data_time: 0.0014 memory: 44137 loss: 0.3819 2023/06/06 08:34:47 - mmengine - INFO - Epoch(train) [5][1800/3907] lr: 1.7946e-04 eta: 3:50:45 time: 0.6336 data_time: 0.0014 memory: 44137 loss: 0.4042 2023/06/06 08:35:51 - mmengine - INFO - Epoch(train) [5][1900/3907] lr: 1.7831e-04 eta: 3:49:41 time: 0.6328 data_time: 0.0015 memory: 44137 loss: 0.3941 2023/06/06 08:36:54 - mmengine - INFO - Epoch(train) [5][2000/3907] lr: 1.7716e-04 eta: 3:48:36 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.3920 2023/06/06 08:37:57 - mmengine - INFO - Epoch(train) [5][2100/3907] lr: 1.7601e-04 eta: 3:47:31 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.4196 2023/06/06 08:39:00 - mmengine - INFO - Epoch(train) [5][2200/3907] lr: 1.7485e-04 eta: 3:46:26 time: 0.6330 data_time: 0.0017 memory: 44137 loss: 0.3883 2023/06/06 08:40:04 - mmengine - INFO - Epoch(train) [5][2300/3907] lr: 1.7370e-04 eta: 3:45:22 time: 0.6334 data_time: 0.0015 memory: 44137 loss: 0.4159 2023/06/06 08:40:50 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:41:07 - mmengine - INFO - Epoch(train) [5][2400/3907] lr: 1.7254e-04 eta: 3:44:17 time: 0.6331 data_time: 0.0013 memory: 44137 loss: 0.3879 2023/06/06 08:42:11 - mmengine - INFO - Epoch(train) [5][2500/3907] lr: 1.7138e-04 eta: 3:43:12 time: 0.6328 data_time: 0.0014 memory: 44137 loss: 0.4301 2023/06/06 08:43:14 - mmengine - INFO - Epoch(train) [5][2600/3907] lr: 1.7022e-04 eta: 3:42:08 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.4012 2023/06/06 08:44:17 - mmengine - INFO - Epoch(train) [5][2700/3907] lr: 1.6906e-04 eta: 3:41:03 time: 0.6366 data_time: 0.0015 memory: 44137 loss: 0.3898 2023/06/06 08:45:21 - mmengine - INFO - Epoch(train) [5][2800/3907] lr: 1.6790e-04 eta: 3:39:59 time: 0.6342 data_time: 0.0014 memory: 44137 loss: 0.4273 2023/06/06 08:46:24 - mmengine - INFO - Epoch(train) [5][2900/3907] lr: 1.6674e-04 eta: 3:38:54 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.3856 2023/06/06 08:47:28 - mmengine - INFO - Epoch(train) [5][3000/3907] lr: 1.6558e-04 eta: 3:37:50 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3669 2023/06/06 08:48:31 - mmengine - INFO - Epoch(train) [5][3100/3907] lr: 1.6441e-04 eta: 3:36:45 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4032 2023/06/06 08:49:35 - mmengine - INFO - Epoch(train) [5][3200/3907] lr: 1.6325e-04 eta: 3:35:41 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4009 2023/06/06 08:50:38 - mmengine - INFO - Epoch(train) [5][3300/3907] lr: 1.6209e-04 eta: 3:34:36 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3852 2023/06/06 08:51:24 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:51:41 - mmengine - INFO - Epoch(train) [5][3400/3907] lr: 1.6092e-04 eta: 3:33:32 time: 0.6344 data_time: 0.0014 memory: 44137 loss: 0.4015 2023/06/06 08:52:45 - mmengine - INFO - Epoch(train) [5][3500/3907] lr: 1.5976e-04 eta: 3:32:27 time: 0.6346 data_time: 0.0015 memory: 44137 loss: 0.3843 2023/06/06 08:53:48 - mmengine - INFO - Epoch(train) [5][3600/3907] lr: 1.5859e-04 eta: 3:31:23 time: 0.6335 data_time: 0.0016 memory: 44137 loss: 0.4046 2023/06/06 08:54:52 - mmengine - INFO - Epoch(train) [5][3700/3907] lr: 1.5743e-04 eta: 3:30:18 time: 0.6338 data_time: 0.0014 memory: 44137 loss: 0.4211 2023/06/06 08:55:55 - mmengine - INFO - Epoch(train) [5][3800/3907] lr: 1.5626e-04 eta: 3:29:14 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.4157 2023/06/06 08:56:59 - mmengine - INFO - Epoch(train) [5][3900/3907] lr: 1.5509e-04 eta: 3:28:09 time: 0.6333 data_time: 0.0013 memory: 44137 loss: 0.3958 2023/06/06 08:57:02 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 08:57:03 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/06/06 08:58:45 - mmengine - INFO - Epoch(val) [5][57/57] accuracy/top1: 74.8965 single-label/precision_classwise: [69.01339721679688, 96.9291763305664] single-label/recall_classwise: [98.8258285522461, 45.511627197265625] single-label/f1-score_classwise: [81.27189636230469, 61.940181732177734] data_time: 0.0357 time: 1.2823 2023/06/06 08:59:51 - mmengine - INFO - Epoch(train) [6][ 100/3907] lr: 1.5385e-04 eta: 3:27:03 time: 0.6339 data_time: 0.0016 memory: 44137 loss: 0.4108 2023/06/06 09:00:55 - mmengine - INFO - Epoch(train) [6][ 200/3907] lr: 1.5268e-04 eta: 3:25:59 time: 0.6333 data_time: 0.0015 memory: 44137 loss: 0.3964 2023/06/06 09:01:58 - mmengine - INFO - Epoch(train) [6][ 300/3907] lr: 1.5151e-04 eta: 3:24:54 time: 0.6329 data_time: 0.0015 memory: 44137 loss: 0.3975 2023/06/06 09:03:02 - mmengine - INFO - Epoch(train) [6][ 400/3907] lr: 1.5035e-04 eta: 3:23:50 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3966 2023/06/06 09:03:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:04:05 - mmengine - INFO - Epoch(train) [6][ 500/3907] lr: 1.4918e-04 eta: 3:22:45 time: 0.6330 data_time: 0.0015 memory: 44137 loss: 0.4015 2023/06/06 09:05:08 - mmengine - INFO - Epoch(train) [6][ 600/3907] lr: 1.4802e-04 eta: 3:21:41 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.4208 2023/06/06 09:06:12 - mmengine - INFO - Epoch(train) [6][ 700/3907] lr: 1.4685e-04 eta: 3:20:36 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3958 2023/06/06 09:07:15 - mmengine - INFO - Epoch(train) [6][ 800/3907] lr: 1.4569e-04 eta: 3:19:32 time: 0.6336 data_time: 0.0016 memory: 44137 loss: 0.4158 2023/06/06 09:08:18 - mmengine - INFO - Epoch(train) [6][ 900/3907] lr: 1.4453e-04 eta: 3:18:27 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.4056 2023/06/06 09:09:22 - mmengine - INFO - Epoch(train) [6][1000/3907] lr: 1.4336e-04 eta: 3:17:23 time: 0.6329 data_time: 0.0014 memory: 44137 loss: 0.4274 2023/06/06 09:10:25 - mmengine - INFO - Epoch(train) [6][1100/3907] lr: 1.4220e-04 eta: 3:16:19 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.4200 2023/06/06 09:11:29 - mmengine - INFO - Epoch(train) [6][1200/3907] lr: 1.4104e-04 eta: 3:15:15 time: 0.6343 data_time: 0.0015 memory: 44137 loss: 0.4036 2023/06/06 09:12:32 - mmengine - INFO - Epoch(train) [6][1300/3907] lr: 1.3988e-04 eta: 3:14:10 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.3884 2023/06/06 09:13:35 - mmengine - INFO - Epoch(train) [6][1400/3907] lr: 1.3872e-04 eta: 3:13:06 time: 0.6349 data_time: 0.0016 memory: 44137 loss: 0.4155 2023/06/06 09:14:17 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:14:39 - mmengine - INFO - Epoch(train) [6][1500/3907] lr: 1.3756e-04 eta: 3:12:02 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.4024 2023/06/06 09:15:42 - mmengine - INFO - Epoch(train) [6][1600/3907] lr: 1.3641e-04 eta: 3:10:57 time: 0.6332 data_time: 0.0016 memory: 44137 loss: 0.4068 2023/06/06 09:16:46 - mmengine - INFO - Epoch(train) [6][1700/3907] lr: 1.3525e-04 eta: 3:09:53 time: 0.6350 data_time: 0.0015 memory: 44137 loss: 0.3796 2023/06/06 09:17:49 - mmengine - INFO - Epoch(train) [6][1800/3907] lr: 1.3410e-04 eta: 3:08:49 time: 0.6359 data_time: 0.0014 memory: 44137 loss: 0.4033 2023/06/06 09:18:53 - mmengine - INFO - Epoch(train) [6][1900/3907] lr: 1.3294e-04 eta: 3:07:44 time: 0.6332 data_time: 0.0016 memory: 44137 loss: 0.3757 2023/06/06 09:19:56 - mmengine - INFO - Epoch(train) [6][2000/3907] lr: 1.3179e-04 eta: 3:06:40 time: 0.6364 data_time: 0.0014 memory: 44137 loss: 0.4129 2023/06/06 09:20:59 - mmengine - INFO - Epoch(train) [6][2100/3907] lr: 1.3064e-04 eta: 3:05:36 time: 0.6335 data_time: 0.0016 memory: 44137 loss: 0.4117 2023/06/06 09:22:03 - mmengine - INFO - Epoch(train) [6][2200/3907] lr: 1.2949e-04 eta: 3:04:32 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4058 2023/06/06 09:23:06 - mmengine - INFO - Epoch(train) [6][2300/3907] lr: 1.2835e-04 eta: 3:03:28 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3744 2023/06/06 09:24:10 - mmengine - INFO - Epoch(train) [6][2400/3907] lr: 1.2720e-04 eta: 3:02:23 time: 0.6359 data_time: 0.0015 memory: 44137 loss: 0.4227 2023/06/06 09:24:51 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:25:13 - mmengine - INFO - Epoch(train) [6][2500/3907] lr: 1.2606e-04 eta: 3:01:19 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3869 2023/06/06 09:26:17 - mmengine - INFO - Epoch(train) [6][2600/3907] lr: 1.2492e-04 eta: 3:00:15 time: 0.6350 data_time: 0.0014 memory: 44137 loss: 0.3986 2023/06/06 09:27:20 - mmengine - INFO - Epoch(train) [6][2700/3907] lr: 1.2378e-04 eta: 2:59:11 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.3789 2023/06/06 09:28:24 - mmengine - INFO - Epoch(train) [6][2800/3907] lr: 1.2264e-04 eta: 2:58:07 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.4107 2023/06/06 09:29:27 - mmengine - INFO - Epoch(train) [6][2900/3907] lr: 1.2150e-04 eta: 2:57:03 time: 0.6344 data_time: 0.0017 memory: 44137 loss: 0.3939 2023/06/06 09:30:31 - mmengine - INFO - Epoch(train) [6][3000/3907] lr: 1.2037e-04 eta: 2:55:59 time: 0.6367 data_time: 0.0015 memory: 44137 loss: 0.4375 2023/06/06 09:31:35 - mmengine - INFO - Epoch(train) [6][3100/3907] lr: 1.1924e-04 eta: 2:54:55 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.4152 2023/06/06 09:32:38 - mmengine - INFO - Epoch(train) [6][3200/3907] lr: 1.1811e-04 eta: 2:53:50 time: 0.6358 data_time: 0.0015 memory: 44137 loss: 0.3900 2023/06/06 09:33:42 - mmengine - INFO - Epoch(train) [6][3300/3907] lr: 1.1699e-04 eta: 2:52:46 time: 0.6346 data_time: 0.0014 memory: 44137 loss: 0.4125 2023/06/06 09:34:45 - mmengine - INFO - Epoch(train) [6][3400/3907] lr: 1.1586e-04 eta: 2:51:42 time: 0.6342 data_time: 0.0016 memory: 44137 loss: 0.4143 2023/06/06 09:35:26 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:35:49 - mmengine - INFO - Epoch(train) [6][3500/3907] lr: 1.1474e-04 eta: 2:50:38 time: 0.6443 data_time: 0.0015 memory: 44137 loss: 0.4068 2023/06/06 09:36:52 - mmengine - INFO - Epoch(train) [6][3600/3907] lr: 1.1362e-04 eta: 2:49:34 time: 0.6345 data_time: 0.0015 memory: 44137 loss: 0.4010 2023/06/06 09:37:56 - mmengine - INFO - Epoch(train) [6][3700/3907] lr: 1.1251e-04 eta: 2:48:30 time: 0.6348 data_time: 0.0014 memory: 44137 loss: 0.4028 2023/06/06 09:38:59 - mmengine - INFO - Epoch(train) [6][3800/3907] lr: 1.1139e-04 eta: 2:47:26 time: 0.6343 data_time: 0.0015 memory: 44137 loss: 0.4139 2023/06/06 09:40:03 - mmengine - INFO - Epoch(train) [6][3900/3907] lr: 1.1028e-04 eta: 2:46:22 time: 0.6343 data_time: 0.0013 memory: 44137 loss: 0.3883 2023/06/06 09:40:07 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:40:07 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/06/06 09:41:49 - mmengine - INFO - Epoch(val) [6][57/57] accuracy/top1: 74.7051 single-label/precision_classwise: [68.8315658569336, 97.0421142578125] single-label/recall_classwise: [98.88264465332031, 45.015506744384766] single-label/f1-score_classwise: [81.16482543945312, 61.50180435180664] data_time: 0.0362 time: 1.2833 2023/06/06 09:42:55 - mmengine - INFO - Epoch(train) [7][ 100/3907] lr: 1.0910e-04 eta: 2:45:15 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.4047 2023/06/06 09:43:59 - mmengine - INFO - Epoch(train) [7][ 200/3907] lr: 1.0799e-04 eta: 2:44:11 time: 0.6342 data_time: 0.0014 memory: 44137 loss: 0.4482 2023/06/06 09:45:02 - mmengine - INFO - Epoch(train) [7][ 300/3907] lr: 1.0689e-04 eta: 2:43:07 time: 0.6344 data_time: 0.0014 memory: 44137 loss: 0.4107 2023/06/06 09:46:06 - mmengine - INFO - Epoch(train) [7][ 400/3907] lr: 1.0579e-04 eta: 2:42:02 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.3960 2023/06/06 09:47:10 - mmengine - INFO - Epoch(train) [7][ 500/3907] lr: 1.0470e-04 eta: 2:40:59 time: 0.6344 data_time: 0.0016 memory: 44137 loss: 0.3927 2023/06/06 09:47:46 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:48:13 - mmengine - INFO - Epoch(train) [7][ 600/3907] lr: 1.0360e-04 eta: 2:39:54 time: 0.6349 data_time: 0.0014 memory: 44137 loss: 0.3906 2023/06/06 09:49:17 - mmengine - INFO - Epoch(train) [7][ 700/3907] lr: 1.0252e-04 eta: 2:38:50 time: 0.6344 data_time: 0.0013 memory: 44137 loss: 0.3974 2023/06/06 09:50:20 - mmengine - INFO - Epoch(train) [7][ 800/3907] lr: 1.0143e-04 eta: 2:37:46 time: 0.6349 data_time: 0.0015 memory: 44137 loss: 0.4009 2023/06/06 09:51:24 - mmengine - INFO - Epoch(train) [7][ 900/3907] lr: 1.0035e-04 eta: 2:36:42 time: 0.6343 data_time: 0.0014 memory: 44137 loss: 0.3946 2023/06/06 09:52:27 - mmengine - INFO - Epoch(train) [7][1000/3907] lr: 9.9271e-05 eta: 2:35:38 time: 0.6361 data_time: 0.0014 memory: 44137 loss: 0.3930 2023/06/06 09:53:31 - mmengine - INFO - Epoch(train) [7][1100/3907] lr: 9.8197e-05 eta: 2:34:34 time: 0.6358 data_time: 0.0015 memory: 44137 loss: 0.3951 2023/06/06 09:54:35 - mmengine - INFO - Epoch(train) [7][1200/3907] lr: 9.7126e-05 eta: 2:33:30 time: 0.6365 data_time: 0.0015 memory: 44137 loss: 0.4105 2023/06/06 09:55:38 - mmengine - INFO - Epoch(train) [7][1300/3907] lr: 9.6059e-05 eta: 2:32:26 time: 0.6357 data_time: 0.0014 memory: 44137 loss: 0.4261 2023/06/06 09:56:42 - mmengine - INFO - Epoch(train) [7][1400/3907] lr: 9.4995e-05 eta: 2:31:23 time: 0.6353 data_time: 0.0014 memory: 44137 loss: 0.4296 2023/06/06 09:57:46 - mmengine - INFO - Epoch(train) [7][1500/3907] lr: 9.3936e-05 eta: 2:30:19 time: 0.6354 data_time: 0.0014 memory: 44137 loss: 0.3760 2023/06/06 09:58:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 09:58:49 - mmengine - INFO - Epoch(train) [7][1600/3907] lr: 9.2880e-05 eta: 2:29:15 time: 0.6355 data_time: 0.0017 memory: 44137 loss: 0.4077 2023/06/06 09:59:53 - mmengine - INFO - Epoch(train) [7][1700/3907] lr: 9.1829e-05 eta: 2:28:11 time: 0.6375 data_time: 0.0015 memory: 44137 loss: 0.3991 2023/06/06 10:00:56 - mmengine - INFO - Epoch(train) [7][1800/3907] lr: 9.0781e-05 eta: 2:27:07 time: 0.6362 data_time: 0.0015 memory: 44137 loss: 0.3841 2023/06/06 10:02:00 - mmengine - INFO - Epoch(train) [7][1900/3907] lr: 8.9738e-05 eta: 2:26:03 time: 0.6354 data_time: 0.0016 memory: 44137 loss: 0.3982 2023/06/06 10:03:03 - mmengine - INFO - Epoch(train) [7][2000/3907] lr: 8.8699e-05 eta: 2:24:59 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4010 2023/06/06 10:04:07 - mmengine - INFO - Epoch(train) [7][2100/3907] lr: 8.7664e-05 eta: 2:23:55 time: 0.6347 data_time: 0.0014 memory: 44137 loss: 0.4164 2023/06/06 10:05:10 - mmengine - INFO - Epoch(train) [7][2200/3907] lr: 8.6634e-05 eta: 2:22:51 time: 0.6363 data_time: 0.0015 memory: 44137 loss: 0.4027 2023/06/06 10:06:14 - mmengine - INFO - Epoch(train) [7][2300/3907] lr: 8.5608e-05 eta: 2:21:47 time: 0.6344 data_time: 0.0015 memory: 44137 loss: 0.4354 2023/06/06 10:07:17 - mmengine - INFO - Epoch(train) [7][2400/3907] lr: 8.4586e-05 eta: 2:20:43 time: 0.6344 data_time: 0.0015 memory: 44137 loss: 0.3847 2023/06/06 10:08:21 - mmengine - INFO - Epoch(train) [7][2500/3907] lr: 8.3570e-05 eta: 2:19:39 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3799 2023/06/06 10:08:58 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:09:24 - mmengine - INFO - Epoch(train) [7][2600/3907] lr: 8.2557e-05 eta: 2:18:35 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.3941 2023/06/06 10:10:28 - mmengine - INFO - Epoch(train) [7][2700/3907] lr: 8.1550e-05 eta: 2:17:31 time: 0.6345 data_time: 0.0015 memory: 44137 loss: 0.4308 2023/06/06 10:11:31 - mmengine - INFO - Epoch(train) [7][2800/3907] lr: 8.0547e-05 eta: 2:16:27 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3985 2023/06/06 10:12:35 - mmengine - INFO - Epoch(train) [7][2900/3907] lr: 7.9549e-05 eta: 2:15:23 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3925 2023/06/06 10:13:39 - mmengine - INFO - Epoch(train) [7][3000/3907] lr: 7.8555e-05 eta: 2:14:19 time: 0.6360 data_time: 0.0015 memory: 44137 loss: 0.3960 2023/06/06 10:14:42 - mmengine - INFO - Epoch(train) [7][3100/3907] lr: 7.7567e-05 eta: 2:13:15 time: 0.6359 data_time: 0.0014 memory: 44137 loss: 0.4325 2023/06/06 10:15:46 - mmengine - INFO - Epoch(train) [7][3200/3907] lr: 7.6584e-05 eta: 2:12:11 time: 0.6353 data_time: 0.0015 memory: 44137 loss: 0.4226 2023/06/06 10:16:49 - mmengine - INFO - Epoch(train) [7][3300/3907] lr: 7.5606e-05 eta: 2:11:07 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.4033 2023/06/06 10:17:53 - mmengine - INFO - Epoch(train) [7][3400/3907] lr: 7.4633e-05 eta: 2:10:03 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3979 2023/06/06 10:18:56 - mmengine - INFO - Epoch(train) [7][3500/3907] lr: 7.3665e-05 eta: 2:08:59 time: 0.6358 data_time: 0.0015 memory: 44137 loss: 0.4090 2023/06/06 10:19:33 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:20:00 - mmengine - INFO - Epoch(train) [7][3600/3907] lr: 7.2702e-05 eta: 2:07:55 time: 0.6345 data_time: 0.0016 memory: 44137 loss: 0.3982 2023/06/06 10:21:03 - mmengine - INFO - Epoch(train) [7][3700/3907] lr: 7.1745e-05 eta: 2:06:51 time: 0.6357 data_time: 0.0016 memory: 44137 loss: 0.3984 2023/06/06 10:22:07 - mmengine - INFO - Epoch(train) [7][3800/3907] lr: 7.0793e-05 eta: 2:05:47 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3969 2023/06/06 10:23:10 - mmengine - INFO - Epoch(train) [7][3900/3907] lr: 6.9847e-05 eta: 2:04:43 time: 0.6357 data_time: 0.0012 memory: 44137 loss: 0.4011 2023/06/06 10:23:14 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:23:14 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/06/06 10:24:57 - mmengine - INFO - Epoch(val) [7][57/57] accuracy/top1: 74.8408 single-label/precision_classwise: [68.9764633178711, 96.81255340576172] single-label/recall_classwise: [98.78164672851562, 45.44186019897461] single-label/f1-score_classwise: [81.23133850097656, 61.85175323486328] data_time: 0.0357 time: 1.2791 2023/06/06 10:26:04 - mmengine - INFO - Epoch(train) [8][ 100/3907] lr: 6.8840e-05 eta: 2:03:36 time: 0.6349 data_time: 0.0016 memory: 44137 loss: 0.3970 2023/06/06 10:27:08 - mmengine - INFO - Epoch(train) [8][ 200/3907] lr: 6.7905e-05 eta: 2:02:32 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.4097 2023/06/06 10:28:11 - mmengine - INFO - Epoch(train) [8][ 300/3907] lr: 6.6976e-05 eta: 2:01:28 time: 0.6338 data_time: 0.0017 memory: 44137 loss: 0.4081 2023/06/06 10:29:14 - mmengine - INFO - Epoch(train) [8][ 400/3907] lr: 6.6052e-05 eta: 2:00:24 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.4042 2023/06/06 10:30:18 - mmengine - INFO - Epoch(train) [8][ 500/3907] lr: 6.5134e-05 eta: 1:59:20 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.4124 2023/06/06 10:31:21 - mmengine - INFO - Epoch(train) [8][ 600/3907] lr: 6.4222e-05 eta: 1:58:16 time: 0.6346 data_time: 0.0015 memory: 44137 loss: 0.4051 2023/06/06 10:31:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:32:25 - mmengine - INFO - Epoch(train) [8][ 700/3907] lr: 6.3316e-05 eta: 1:57:12 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.3989 2023/06/06 10:33:28 - mmengine - INFO - Epoch(train) [8][ 800/3907] lr: 6.2416e-05 eta: 1:56:08 time: 0.6330 data_time: 0.0016 memory: 44137 loss: 0.3962 2023/06/06 10:34:31 - mmengine - INFO - Epoch(train) [8][ 900/3907] lr: 6.1521e-05 eta: 1:55:04 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.4054 2023/06/06 10:35:35 - mmengine - INFO - Epoch(train) [8][1000/3907] lr: 6.0633e-05 eta: 1:54:00 time: 0.6334 data_time: 0.0015 memory: 44137 loss: 0.4100 2023/06/06 10:36:38 - mmengine - INFO - Epoch(train) [8][1100/3907] lr: 5.9751e-05 eta: 1:52:56 time: 0.6335 data_time: 0.0016 memory: 44137 loss: 0.3976 2023/06/06 10:37:42 - mmengine - INFO - Epoch(train) [8][1200/3907] lr: 5.8875e-05 eta: 1:51:52 time: 0.6329 data_time: 0.0015 memory: 44137 loss: 0.4064 2023/06/06 10:38:45 - mmengine - INFO - Epoch(train) [8][1300/3907] lr: 5.8005e-05 eta: 1:50:48 time: 0.6331 data_time: 0.0016 memory: 44137 loss: 0.4128 2023/06/06 10:39:48 - mmengine - INFO - Epoch(train) [8][1400/3907] lr: 5.7141e-05 eta: 1:49:44 time: 0.6349 data_time: 0.0014 memory: 44137 loss: 0.4046 2023/06/06 10:40:52 - mmengine - INFO - Epoch(train) [8][1500/3907] lr: 5.6284e-05 eta: 1:48:40 time: 0.6336 data_time: 0.0016 memory: 44137 loss: 0.3848 2023/06/06 10:41:55 - mmengine - INFO - Epoch(train) [8][1600/3907] lr: 5.5433e-05 eta: 1:47:36 time: 0.6359 data_time: 0.0016 memory: 44137 loss: 0.3775 2023/06/06 10:42:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:42:58 - mmengine - INFO - Epoch(train) [8][1700/3907] lr: 5.4589e-05 eta: 1:46:33 time: 0.6341 data_time: 0.0016 memory: 44137 loss: 0.4161 2023/06/06 10:44:02 - mmengine - INFO - Epoch(train) [8][1800/3907] lr: 5.3751e-05 eta: 1:45:29 time: 0.6332 data_time: 0.0015 memory: 44137 loss: 0.3929 2023/06/06 10:45:05 - mmengine - INFO - Epoch(train) [8][1900/3907] lr: 5.2920e-05 eta: 1:44:25 time: 0.6346 data_time: 0.0015 memory: 44137 loss: 0.4086 2023/06/06 10:46:09 - mmengine - INFO - Epoch(train) [8][2000/3907] lr: 5.2095e-05 eta: 1:43:21 time: 0.6334 data_time: 0.0015 memory: 44137 loss: 0.4202 2023/06/06 10:47:12 - mmengine - INFO - Epoch(train) [8][2100/3907] lr: 5.1277e-05 eta: 1:42:17 time: 0.6332 data_time: 0.0016 memory: 44137 loss: 0.4079 2023/06/06 10:48:15 - mmengine - INFO - Epoch(train) [8][2200/3907] lr: 5.0466e-05 eta: 1:41:13 time: 0.6331 data_time: 0.0015 memory: 44137 loss: 0.3835 2023/06/06 10:49:19 - mmengine - INFO - Epoch(train) [8][2300/3907] lr: 4.9661e-05 eta: 1:40:09 time: 0.6331 data_time: 0.0014 memory: 44137 loss: 0.3971 2023/06/06 10:50:22 - mmengine - INFO - Epoch(train) [8][2400/3907] lr: 4.8863e-05 eta: 1:39:05 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.4183 2023/06/06 10:51:26 - mmengine - INFO - Epoch(train) [8][2500/3907] lr: 4.8072e-05 eta: 1:38:01 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.4206 2023/06/06 10:52:29 - mmengine - INFO - Epoch(train) [8][2600/3907] lr: 4.7288e-05 eta: 1:36:57 time: 0.6330 data_time: 0.0015 memory: 44137 loss: 0.4409 2023/06/06 10:53:02 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 10:53:33 - mmengine - INFO - Epoch(train) [8][2700/3907] lr: 4.6511e-05 eta: 1:35:53 time: 0.6337 data_time: 0.0015 memory: 44137 loss: 0.4135 2023/06/06 10:54:36 - mmengine - INFO - Epoch(train) [8][2800/3907] lr: 4.5741e-05 eta: 1:34:50 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.3945 2023/06/06 10:55:39 - mmengine - INFO - Epoch(train) [8][2900/3907] lr: 4.4978e-05 eta: 1:33:46 time: 0.6331 data_time: 0.0016 memory: 44137 loss: 0.4152 2023/06/06 10:56:43 - mmengine - INFO - Epoch(train) [8][3000/3907] lr: 4.4222e-05 eta: 1:32:42 time: 0.6346 data_time: 0.0016 memory: 44137 loss: 0.4000 2023/06/06 10:57:46 - mmengine - INFO - Epoch(train) [8][3100/3907] lr: 4.3474e-05 eta: 1:31:38 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4009 2023/06/06 10:58:50 - mmengine - INFO - Epoch(train) [8][3200/3907] lr: 4.2732e-05 eta: 1:30:34 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.4309 2023/06/06 10:59:53 - mmengine - INFO - Epoch(train) [8][3300/3907] lr: 4.1998e-05 eta: 1:29:30 time: 0.6334 data_time: 0.0015 memory: 44137 loss: 0.4027 2023/06/06 11:00:56 - mmengine - INFO - Epoch(train) [8][3400/3907] lr: 4.1271e-05 eta: 1:28:26 time: 0.6337 data_time: 0.0015 memory: 44137 loss: 0.4031 2023/06/06 11:02:00 - mmengine - INFO - Epoch(train) [8][3500/3907] lr: 4.0551e-05 eta: 1:27:22 time: 0.6335 data_time: 0.0016 memory: 44137 loss: 0.4453 2023/06/06 11:03:03 - mmengine - INFO - Epoch(train) [8][3600/3907] lr: 3.9839e-05 eta: 1:26:18 time: 0.6356 data_time: 0.0015 memory: 44137 loss: 0.3786 2023/06/06 11:03:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:04:07 - mmengine - INFO - Epoch(train) [8][3700/3907] lr: 3.9134e-05 eta: 1:25:15 time: 0.6338 data_time: 0.0016 memory: 44137 loss: 0.3968 2023/06/06 11:05:10 - mmengine - INFO - Epoch(train) [8][3800/3907] lr: 3.8437e-05 eta: 1:24:11 time: 0.6350 data_time: 0.0014 memory: 44137 loss: 0.4266 2023/06/06 11:06:14 - mmengine - INFO - Epoch(train) [8][3900/3907] lr: 3.7747e-05 eta: 1:23:07 time: 0.6341 data_time: 0.0013 memory: 44137 loss: 0.3991 2023/06/06 11:06:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:06:18 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/06/06 11:08:00 - mmengine - INFO - Epoch(val) [8][57/57] accuracy/top1: 74.3781 single-label/precision_classwise: [68.55816650390625, 96.89935302734375] single-label/recall_classwise: [98.84477233886719, 44.33333206176758] single-label/f1-score_classwise: [80.96173858642578, 60.833953857421875] data_time: 0.0374 time: 1.2846 2023/06/06 11:09:07 - mmengine - INFO - Epoch(train) [9][ 100/3907] lr: 3.7018e-05 eta: 1:21:59 time: 0.6333 data_time: 0.0017 memory: 44137 loss: 0.4049 2023/06/06 11:10:10 - mmengine - INFO - Epoch(train) [9][ 200/3907] lr: 3.6344e-05 eta: 1:20:55 time: 0.6341 data_time: 0.0017 memory: 44137 loss: 0.3990 2023/06/06 11:11:14 - mmengine - INFO - Epoch(train) [9][ 300/3907] lr: 3.5678e-05 eta: 1:19:52 time: 0.6422 data_time: 0.0016 memory: 44137 loss: 0.3981 2023/06/06 11:12:17 - mmengine - INFO - Epoch(train) [9][ 400/3907] lr: 3.5019e-05 eta: 1:18:48 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.3904 2023/06/06 11:13:21 - mmengine - INFO - Epoch(train) [9][ 500/3907] lr: 3.4368e-05 eta: 1:17:44 time: 0.6337 data_time: 0.0016 memory: 44137 loss: 0.4220 2023/06/06 11:14:24 - mmengine - INFO - Epoch(train) [9][ 600/3907] lr: 3.3725e-05 eta: 1:16:40 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.3847 2023/06/06 11:15:27 - mmengine - INFO - Epoch(train) [9][ 700/3907] lr: 3.3090e-05 eta: 1:15:36 time: 0.6343 data_time: 0.0014 memory: 44137 loss: 0.3820 2023/06/06 11:15:55 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:16:31 - mmengine - INFO - Epoch(train) [9][ 800/3907] lr: 3.2463e-05 eta: 1:14:32 time: 0.6348 data_time: 0.0014 memory: 44137 loss: 0.3988 2023/06/06 11:17:34 - mmengine - INFO - Epoch(train) [9][ 900/3907] lr: 3.1843e-05 eta: 1:13:28 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4339 2023/06/06 11:18:38 - mmengine - INFO - Epoch(train) [9][1000/3907] lr: 3.1232e-05 eta: 1:12:25 time: 0.6342 data_time: 0.0017 memory: 44137 loss: 0.4047 2023/06/06 11:19:41 - mmengine - INFO - Epoch(train) [9][1100/3907] lr: 3.0628e-05 eta: 1:11:21 time: 0.6336 data_time: 0.0016 memory: 44137 loss: 0.3994 2023/06/06 11:20:45 - mmengine - INFO - Epoch(train) [9][1200/3907] lr: 3.0033e-05 eta: 1:10:17 time: 0.6332 data_time: 0.0014 memory: 44137 loss: 0.3938 2023/06/06 11:21:48 - mmengine - INFO - Epoch(train) [9][1300/3907] lr: 2.9446e-05 eta: 1:09:13 time: 0.6330 data_time: 0.0015 memory: 44137 loss: 0.4070 2023/06/06 11:22:51 - mmengine - INFO - Epoch(train) [9][1400/3907] lr: 2.8867e-05 eta: 1:08:09 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.4066 2023/06/06 11:23:55 - mmengine - INFO - Epoch(train) [9][1500/3907] lr: 2.8296e-05 eta: 1:07:05 time: 0.6341 data_time: 0.0015 memory: 44137 loss: 0.4111 2023/06/06 11:24:58 - mmengine - INFO - Epoch(train) [9][1600/3907] lr: 2.7733e-05 eta: 1:06:02 time: 0.6417 data_time: 0.0017 memory: 44137 loss: 0.4075 2023/06/06 11:26:02 - mmengine - INFO - Epoch(train) [9][1700/3907] lr: 2.7178e-05 eta: 1:04:58 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.4007 2023/06/06 11:26:30 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:27:05 - mmengine - INFO - Epoch(train) [9][1800/3907] lr: 2.6632e-05 eta: 1:03:54 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.3754 2023/06/06 11:28:08 - mmengine - INFO - Epoch(train) [9][1900/3907] lr: 2.6094e-05 eta: 1:02:50 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.3654 2023/06/06 11:29:12 - mmengine - INFO - Epoch(train) [9][2000/3907] lr: 2.5564e-05 eta: 1:01:46 time: 0.6350 data_time: 0.0016 memory: 44137 loss: 0.4076 2023/06/06 11:30:15 - mmengine - INFO - Epoch(train) [9][2100/3907] lr: 2.5043e-05 eta: 1:00:42 time: 0.6345 data_time: 0.0014 memory: 44137 loss: 0.4009 2023/06/06 11:31:19 - mmengine - INFO - Epoch(train) [9][2200/3907] lr: 2.4530e-05 eta: 0:59:39 time: 0.6335 data_time: 0.0014 memory: 44137 loss: 0.4067 2023/06/06 11:32:22 - mmengine - INFO - Epoch(train) [9][2300/3907] lr: 2.4025e-05 eta: 0:58:35 time: 0.6336 data_time: 0.0016 memory: 44137 loss: 0.4030 2023/06/06 11:33:26 - mmengine - INFO - Epoch(train) [9][2400/3907] lr: 2.3529e-05 eta: 0:57:31 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.3882 2023/06/06 11:34:29 - mmengine - INFO - Epoch(train) [9][2500/3907] lr: 2.3042e-05 eta: 0:56:27 time: 0.6340 data_time: 0.0016 memory: 44137 loss: 0.3934 2023/06/06 11:35:33 - mmengine - INFO - Epoch(train) [9][2600/3907] lr: 2.2563e-05 eta: 0:55:23 time: 0.6359 data_time: 0.0015 memory: 44137 loss: 0.4072 2023/06/06 11:36:36 - mmengine - INFO - Epoch(train) [9][2700/3907] lr: 2.2092e-05 eta: 0:54:20 time: 0.6342 data_time: 0.0016 memory: 44137 loss: 0.4105 2023/06/06 11:37:04 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:37:40 - mmengine - INFO - Epoch(train) [9][2800/3907] lr: 2.1631e-05 eta: 0:53:16 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.4228 2023/06/06 11:38:43 - mmengine - INFO - Epoch(train) [9][2900/3907] lr: 2.1177e-05 eta: 0:52:12 time: 0.6349 data_time: 0.0015 memory: 44137 loss: 0.4199 2023/06/06 11:39:47 - mmengine - INFO - Epoch(train) [9][3000/3907] lr: 2.0733e-05 eta: 0:51:08 time: 0.6355 data_time: 0.0015 memory: 44137 loss: 0.3760 2023/06/06 11:40:50 - mmengine - INFO - Epoch(train) [9][3100/3907] lr: 2.0297e-05 eta: 0:50:05 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3991 2023/06/06 11:41:54 - mmengine - INFO - Epoch(train) [9][3200/3907] lr: 1.9870e-05 eta: 0:49:01 time: 0.6351 data_time: 0.0014 memory: 44137 loss: 0.4381 2023/06/06 11:42:57 - mmengine - INFO - Epoch(train) [9][3300/3907] lr: 1.9451e-05 eta: 0:47:57 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4118 2023/06/06 11:44:00 - mmengine - INFO - Epoch(train) [9][3400/3907] lr: 1.9042e-05 eta: 0:46:53 time: 0.6348 data_time: 0.0016 memory: 44137 loss: 0.4093 2023/06/06 11:45:04 - mmengine - INFO - Epoch(train) [9][3500/3907] lr: 1.8641e-05 eta: 0:45:49 time: 0.6350 data_time: 0.0017 memory: 44137 loss: 0.3998 2023/06/06 11:46:07 - mmengine - INFO - Epoch(train) [9][3600/3907] lr: 1.8249e-05 eta: 0:44:46 time: 0.6339 data_time: 0.0014 memory: 44137 loss: 0.3997 2023/06/06 11:47:11 - mmengine - INFO - Epoch(train) [9][3700/3907] lr: 1.7865e-05 eta: 0:43:42 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.4115 2023/06/06 11:47:39 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:48:14 - mmengine - INFO - Epoch(train) [9][3800/3907] lr: 1.7491e-05 eta: 0:42:38 time: 0.6342 data_time: 0.0016 memory: 44137 loss: 0.4288 2023/06/06 11:49:18 - mmengine - INFO - Epoch(train) [9][3900/3907] lr: 1.7126e-05 eta: 0:41:34 time: 0.6356 data_time: 0.0013 memory: 44137 loss: 0.4301 2023/06/06 11:49:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 11:49:22 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/06/06 11:51:05 - mmengine - INFO - Epoch(val) [9][57/57] accuracy/top1: 74.2876 single-label/precision_classwise: [68.5012435913086, 96.67909240722656] single-label/recall_classwise: [98.76270294189453, 44.23255920410156] single-label/f1-score_classwise: [80.89451599121094, 60.695674896240234] data_time: 0.0376 time: 1.2835 2023/06/06 11:52:11 - mmengine - INFO - Epoch(train) [10][ 100/3907] lr: 1.6744e-05 eta: 0:40:26 time: 0.6339 data_time: 0.0019 memory: 44137 loss: 0.3890 2023/06/06 11:53:15 - mmengine - INFO - Epoch(train) [10][ 200/3907] lr: 1.6398e-05 eta: 0:39:23 time: 0.6344 data_time: 0.0015 memory: 44137 loss: 0.4330 2023/06/06 11:54:18 - mmengine - INFO - Epoch(train) [10][ 300/3907] lr: 1.6059e-05 eta: 0:38:19 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.4041 2023/06/06 11:55:21 - mmengine - INFO - Epoch(train) [10][ 400/3907] lr: 1.5730e-05 eta: 0:37:15 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.4127 2023/06/06 11:56:25 - mmengine - INFO - Epoch(train) [10][ 500/3907] lr: 1.5410e-05 eta: 0:36:11 time: 0.6352 data_time: 0.0015 memory: 44137 loss: 0.4082 2023/06/06 11:57:28 - mmengine - INFO - Epoch(train) [10][ 600/3907] lr: 1.5099e-05 eta: 0:35:07 time: 0.6344 data_time: 0.0016 memory: 44137 loss: 0.4406 2023/06/06 11:58:32 - mmengine - INFO - Epoch(train) [10][ 700/3907] lr: 1.4797e-05 eta: 0:34:04 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4013 2023/06/06 11:59:35 - mmengine - INFO - Epoch(train) [10][ 800/3907] lr: 1.4505e-05 eta: 0:33:00 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.4200 2023/06/06 11:59:59 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 12:00:39 - mmengine - INFO - Epoch(train) [10][ 900/3907] lr: 1.4221e-05 eta: 0:31:56 time: 0.6334 data_time: 0.0017 memory: 44137 loss: 0.4198 2023/06/06 12:01:42 - mmengine - INFO - Epoch(train) [10][1000/3907] lr: 1.3946e-05 eta: 0:30:52 time: 0.6342 data_time: 0.0014 memory: 44137 loss: 0.3851 2023/06/06 12:02:46 - mmengine - INFO - Epoch(train) [10][1100/3907] lr: 1.3680e-05 eta: 0:29:49 time: 0.6339 data_time: 0.0015 memory: 44137 loss: 0.4090 2023/06/06 12:03:49 - mmengine - INFO - Epoch(train) [10][1200/3907] lr: 1.3424e-05 eta: 0:28:45 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.4391 2023/06/06 12:04:53 - mmengine - INFO - Epoch(train) [10][1300/3907] lr: 1.3177e-05 eta: 0:27:41 time: 0.6361 data_time: 0.0018 memory: 44137 loss: 0.4089 2023/06/06 12:05:56 - mmengine - INFO - Epoch(train) [10][1400/3907] lr: 1.2939e-05 eta: 0:26:37 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.4454 2023/06/06 12:07:00 - mmengine - INFO - Epoch(train) [10][1500/3907] lr: 1.2710e-05 eta: 0:25:34 time: 0.6346 data_time: 0.0016 memory: 44137 loss: 0.4100 2023/06/06 12:08:03 - mmengine - INFO - Epoch(train) [10][1600/3907] lr: 1.2490e-05 eta: 0:24:30 time: 0.6340 data_time: 0.0015 memory: 44137 loss: 0.3992 2023/06/06 12:09:07 - mmengine - INFO - Epoch(train) [10][1700/3907] lr: 1.2279e-05 eta: 0:23:26 time: 0.6437 data_time: 0.0015 memory: 44137 loss: 0.4182 2023/06/06 12:10:12 - mmengine - INFO - Epoch(train) [10][1800/3907] lr: 1.2078e-05 eta: 0:22:22 time: 0.6347 data_time: 0.0016 memory: 44137 loss: 0.3996 2023/06/06 12:10:38 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 12:11:21 - mmengine - INFO - Epoch(train) [10][1900/3907] lr: 1.1886e-05 eta: 0:21:19 time: 0.6784 data_time: 0.0018 memory: 44137 loss: 0.4041 2023/06/06 12:12:35 - mmengine - INFO - Epoch(train) [10][2000/3907] lr: 1.1703e-05 eta: 0:20:16 time: 0.6348 data_time: 0.0014 memory: 44137 loss: 0.3840 2023/06/06 12:13:46 - mmengine - INFO - Epoch(train) [10][2100/3907] lr: 1.1530e-05 eta: 0:19:12 time: 0.6342 data_time: 0.0015 memory: 44137 loss: 0.3895 2023/06/06 12:14:50 - mmengine - INFO - Epoch(train) [10][2200/3907] lr: 1.1365e-05 eta: 0:18:09 time: 0.6371 data_time: 0.0014 memory: 44137 loss: 0.3979 2023/06/06 12:15:54 - mmengine - INFO - Epoch(train) [10][2300/3907] lr: 1.1210e-05 eta: 0:17:05 time: 0.6374 data_time: 0.0015 memory: 44137 loss: 0.4039 2023/06/06 12:16:57 - mmengine - INFO - Epoch(train) [10][2400/3907] lr: 1.1065e-05 eta: 0:16:01 time: 0.6344 data_time: 0.0016 memory: 44137 loss: 0.3965 2023/06/06 12:18:01 - mmengine - INFO - Epoch(train) [10][2500/3907] lr: 1.0928e-05 eta: 0:14:57 time: 0.6339 data_time: 0.0019 memory: 44137 loss: 0.4068 2023/06/06 12:19:04 - mmengine - INFO - Epoch(train) [10][2600/3907] lr: 1.0801e-05 eta: 0:13:53 time: 0.6338 data_time: 0.0015 memory: 44137 loss: 0.4245 2023/06/06 12:20:08 - mmengine - INFO - Epoch(train) [10][2700/3907] lr: 1.0684e-05 eta: 0:12:50 time: 0.6342 data_time: 0.0016 memory: 44137 loss: 0.4159 2023/06/06 12:21:11 - mmengine - INFO - Epoch(train) [10][2800/3907] lr: 1.0575e-05 eta: 0:11:46 time: 0.6337 data_time: 0.0014 memory: 44137 loss: 0.4106 2023/06/06 12:21:34 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 12:22:14 - mmengine - INFO - Epoch(train) [10][2900/3907] lr: 1.0476e-05 eta: 0:10:42 time: 0.6342 data_time: 0.0016 memory: 44137 loss: 0.4262 2023/06/06 12:23:18 - mmengine - INFO - Epoch(train) [10][3000/3907] lr: 1.0386e-05 eta: 0:09:38 time: 0.6350 data_time: 0.0015 memory: 44137 loss: 0.3968 2023/06/06 12:24:21 - mmengine - INFO - Epoch(train) [10][3100/3907] lr: 1.0306e-05 eta: 0:08:34 time: 0.6333 data_time: 0.0020 memory: 44137 loss: 0.4200 2023/06/06 12:25:25 - mmengine - INFO - Epoch(train) [10][3200/3907] lr: 1.0235e-05 eta: 0:07:31 time: 0.6336 data_time: 0.0015 memory: 44137 loss: 0.4236 2023/06/06 12:26:28 - mmengine - INFO - Epoch(train) [10][3300/3907] lr: 1.0173e-05 eta: 0:06:27 time: 0.6347 data_time: 0.0015 memory: 44137 loss: 0.4105 2023/06/06 12:27:32 - mmengine - INFO - Epoch(train) [10][3400/3907] lr: 1.0121e-05 eta: 0:05:23 time: 0.6334 data_time: 0.0014 memory: 44137 loss: 0.4174 2023/06/06 12:28:35 - mmengine - INFO - Epoch(train) [10][3500/3907] lr: 1.0078e-05 eta: 0:04:19 time: 0.6333 data_time: 0.0014 memory: 44137 loss: 0.3993 2023/06/06 12:29:38 - mmengine - INFO - Epoch(train) [10][3600/3907] lr: 1.0044e-05 eta: 0:03:15 time: 0.6335 data_time: 0.0015 memory: 44137 loss: 0.3893 2023/06/06 12:30:42 - mmengine - INFO - Epoch(train) [10][3700/3907] lr: 1.0020e-05 eta: 0:02:12 time: 0.6342 data_time: 0.0014 memory: 44137 loss: 0.4125 2023/06/06 12:31:45 - mmengine - INFO - Epoch(train) [10][3800/3907] lr: 1.0005e-05 eta: 0:01:08 time: 0.6334 data_time: 0.0016 memory: 44137 loss: 0.4115 2023/06/06 12:32:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 12:32:49 - mmengine - INFO - Epoch(train) [10][3900/3907] lr: 1.0000e-05 eta: 0:00:04 time: 0.6340 data_time: 0.0013 memory: 44137 loss: 0.4028 2023/06/06 12:32:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-4_20230606_052113 2023/06/06 12:32:53 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/06/06 12:34:35 - mmengine - INFO - Epoch(val) [10][57/57] accuracy/top1: 74.2911 single-label/precision_classwise: [68.50100708007812, 96.71131134033203] single-label/recall_classwise: [98.77532958984375, 44.22480773925781] single-label/f1-score_classwise: [80.8985824584961, 60.69471740722656] data_time: 0.0361 time: 1.2821