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: 127034622 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=3e-05, 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-5' 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 05:21:54 - 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 05:21:59 - 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-5. 2023/06/06 05:23:13 - mmengine - INFO - Epoch(train) [1][ 100/3907] lr: 3.0000e-05 eta: 7:44:55 time: 0.6327 data_time: 0.0017 memory: 44139 loss: 0.5821 2023/06/06 05:24:17 - mmengine - INFO - Epoch(train) [1][ 200/3907] lr: 2.9999e-05 eta: 7:17:41 time: 0.6465 data_time: 0.0017 memory: 44139 loss: 0.5244 2023/06/06 05:25:20 - mmengine - INFO - Epoch(train) [1][ 300/3907] lr: 2.9997e-05 eta: 7:07:48 time: 0.6347 data_time: 0.0015 memory: 44139 loss: 0.5025 2023/06/06 05:26:24 - mmengine - INFO - Epoch(train) [1][ 400/3907] lr: 2.9995e-05 eta: 7:02:32 time: 0.6352 data_time: 0.0016 memory: 44139 loss: 0.5020 2023/06/06 05:27:27 - mmengine - INFO - Epoch(train) [1][ 500/3907] lr: 2.9992e-05 eta: 6:58:51 time: 0.6358 data_time: 0.0015 memory: 44139 loss: 0.4893 2023/06/06 05:28:31 - mmengine - INFO - Epoch(train) [1][ 600/3907] lr: 2.9988e-05 eta: 6:56:11 time: 0.6359 data_time: 0.0015 memory: 44139 loss: 0.4940 2023/06/06 05:29:35 - mmengine - INFO - Epoch(train) [1][ 700/3907] lr: 2.9984e-05 eta: 6:53:59 time: 0.6356 data_time: 0.0015 memory: 44139 loss: 0.4516 2023/06/06 05:30:38 - mmengine - INFO - Epoch(train) [1][ 800/3907] lr: 2.9979e-05 eta: 6:51:58 time: 0.6353 data_time: 0.0016 memory: 44139 loss: 0.4653 2023/06/06 05:31:42 - mmengine - INFO - Epoch(train) [1][ 900/3907] lr: 2.9974e-05 eta: 6:50:15 time: 0.6363 data_time: 0.0016 memory: 44139 loss: 0.4562 2023/06/06 05:32:46 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 05:32:46 - mmengine - INFO - Epoch(train) [1][1000/3907] lr: 2.9968e-05 eta: 6:48:41 time: 0.6352 data_time: 0.0015 memory: 44139 loss: 0.4434 2023/06/06 05:33:49 - mmengine - INFO - Epoch(train) [1][1100/3907] lr: 2.9961e-05 eta: 6:47:07 time: 0.6362 data_time: 0.0014 memory: 44139 loss: 0.4577 2023/06/06 05:36:13 - mmengine - INFO - Epoch(train) [1][1200/3907] lr: 2.9954e-05 eta: 7:27:56 time: 0.6349 data_time: 0.0017 memory: 44139 loss: 0.4558 2023/06/06 05:37:17 - mmengine - INFO - Epoch(train) [1][1300/3907] lr: 2.9945e-05 eta: 7:23:10 time: 0.6344 data_time: 0.0015 memory: 44139 loss: 0.4663 2023/06/06 05:38:20 - mmengine - INFO - Epoch(train) [1][1400/3907] lr: 2.9937e-05 eta: 7:18:57 time: 0.6346 data_time: 0.0016 memory: 44139 loss: 0.4483 2023/06/06 05:39:24 - mmengine - INFO - Epoch(train) [1][1500/3907] lr: 2.9927e-05 eta: 7:15:07 time: 0.6364 data_time: 0.0015 memory: 44139 loss: 0.4409 2023/06/06 05:40:27 - mmengine - INFO - Epoch(train) [1][1600/3907] lr: 2.9917e-05 eta: 7:11:39 time: 0.6369 data_time: 0.0015 memory: 44139 loss: 0.4377 2023/06/06 05:41:31 - mmengine - INFO - Epoch(train) [1][1700/3907] lr: 2.9907e-05 eta: 7:08:29 time: 0.6341 data_time: 0.0014 memory: 44139 loss: 0.4680 2023/06/06 05:42:35 - mmengine - INFO - Epoch(train) [1][1800/3907] lr: 2.9896e-05 eta: 7:05:32 time: 0.6356 data_time: 0.0015 memory: 44139 loss: 0.4360 2023/06/06 05:43:38 - mmengine - INFO - Epoch(train) [1][1900/3907] lr: 2.9884e-05 eta: 7:02:46 time: 0.6354 data_time: 0.0016 memory: 44139 loss: 0.4360 2023/06/06 05:44:42 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 05:44:42 - mmengine - INFO - Epoch(train) [1][2000/3907] lr: 2.9871e-05 eta: 7:00:11 time: 0.6347 data_time: 0.0015 memory: 44139 loss: 0.4763 2023/06/06 05:45:45 - mmengine - INFO - Epoch(train) [1][2100/3907] lr: 2.9858e-05 eta: 6:57:45 time: 0.6356 data_time: 0.0014 memory: 44139 loss: 0.4316 2023/06/06 05:46:49 - mmengine - INFO - Epoch(train) [1][2200/3907] lr: 2.9844e-05 eta: 6:55:29 time: 0.6371 data_time: 0.0015 memory: 44139 loss: 0.4738 2023/06/06 05:47:53 - mmengine - INFO - Epoch(train) [1][2300/3907] lr: 2.9830e-05 eta: 6:53:18 time: 0.6363 data_time: 0.0016 memory: 44139 loss: 0.4565 2023/06/06 05:48:56 - mmengine - INFO - Epoch(train) [1][2400/3907] lr: 2.9815e-05 eta: 6:51:13 time: 0.6416 data_time: 0.0015 memory: 44139 loss: 0.4229 2023/06/06 05:50:00 - mmengine - INFO - Epoch(train) [1][2500/3907] lr: 2.9799e-05 eta: 6:49:12 time: 0.6352 data_time: 0.0014 memory: 44139 loss: 0.4524 2023/06/06 05:51:04 - mmengine - INFO - Epoch(train) [1][2600/3907] lr: 2.9782e-05 eta: 6:47:16 time: 0.6344 data_time: 0.0015 memory: 44139 loss: 0.4300 2023/06/06 05:52:07 - mmengine - INFO - Epoch(train) [1][2700/3907] lr: 2.9765e-05 eta: 6:45:22 time: 0.6349 data_time: 0.0015 memory: 44139 loss: 0.4235 2023/06/06 05:53:11 - mmengine - INFO - Epoch(train) [1][2800/3907] lr: 2.9748e-05 eta: 6:43:32 time: 0.6348 data_time: 0.0014 memory: 44139 loss: 0.4433 2023/06/06 05:54:14 - mmengine - INFO - Epoch(train) [1][2900/3907] lr: 2.9730e-05 eta: 6:41:45 time: 0.6349 data_time: 0.0014 memory: 44139 loss: 0.4557 2023/06/06 05:55:21 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 05:55:21 - mmengine - INFO - Epoch(train) [1][3000/3907] lr: 2.9711e-05 eta: 6:40:41 time: 0.6355 data_time: 0.0015 memory: 44139 loss: 0.4246 2023/06/06 05:56:25 - mmengine - INFO - Epoch(train) [1][3100/3907] lr: 2.9691e-05 eta: 6:38:59 time: 0.6353 data_time: 0.0015 memory: 44139 loss: 0.4596 2023/06/06 05:57:28 - mmengine - INFO - Epoch(train) [1][3200/3907] lr: 2.9671e-05 eta: 6:37:19 time: 0.6355 data_time: 0.0016 memory: 44139 loss: 0.4564 2023/06/06 05:58:32 - mmengine - INFO - Epoch(train) [1][3300/3907] lr: 2.9650e-05 eta: 6:35:42 time: 0.6347 data_time: 0.0015 memory: 44139 loss: 0.4362 2023/06/06 05:59:35 - mmengine - INFO - Epoch(train) [1][3400/3907] lr: 2.9629e-05 eta: 6:34:06 time: 0.6359 data_time: 0.0017 memory: 44139 loss: 0.4211 2023/06/06 06:00:39 - mmengine - INFO - Epoch(train) [1][3500/3907] lr: 2.9607e-05 eta: 6:32:32 time: 0.6354 data_time: 0.0015 memory: 44139 loss: 0.4355 2023/06/06 06:01:43 - mmengine - INFO - Epoch(train) [1][3600/3907] lr: 2.9584e-05 eta: 6:31:00 time: 0.6348 data_time: 0.0016 memory: 44139 loss: 0.4473 2023/06/06 06:02:46 - mmengine - INFO - Epoch(train) [1][3700/3907] lr: 2.9561e-05 eta: 6:29:29 time: 0.6365 data_time: 0.0014 memory: 44139 loss: 0.4363 2023/06/06 06:03:50 - mmengine - INFO - Epoch(train) [1][3800/3907] lr: 2.9537e-05 eta: 6:28:00 time: 0.6355 data_time: 0.0016 memory: 44139 loss: 0.4333 2023/06/06 06:04:53 - mmengine - INFO - Epoch(train) [1][3900/3907] lr: 2.9513e-05 eta: 6:26:32 time: 0.6347 data_time: 0.0012 memory: 44139 loss: 0.4194 2023/06/06 06:04:57 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:04:57 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/06/06 06:06:40 - mmengine - INFO - Epoch(val) [1][57/57] accuracy/top1: 80.0738 single-label/precision_classwise: [78.82466888427734, 82.03089904785156] single-label/recall_classwise: [87.29878234863281, 71.20155334472656] single-label/f1-score_classwise: [82.84559631347656, 76.23355865478516] data_time: 0.0479 time: 1.3421 2023/06/06 06:07:42 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:07:47 - mmengine - INFO - Epoch(train) [2][ 100/3907] lr: 2.9486e-05 eta: 6:25:22 time: 0.6368 data_time: 0.0016 memory: 44139 loss: 0.4614 2023/06/06 06:08:50 - mmengine - INFO - Epoch(train) [2][ 200/3907] lr: 2.9460e-05 eta: 6:23:57 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.4183 2023/06/06 06:09:54 - mmengine - INFO - Epoch(train) [2][ 300/3907] lr: 2.9434e-05 eta: 6:22:32 time: 0.6383 data_time: 0.0014 memory: 44138 loss: 0.4502 2023/06/06 06:10:58 - mmengine - INFO - Epoch(train) [2][ 400/3907] lr: 2.9407e-05 eta: 6:21:09 time: 0.6352 data_time: 0.0014 memory: 44138 loss: 0.4530 2023/06/06 06:12:01 - mmengine - INFO - Epoch(train) [2][ 500/3907] lr: 2.9379e-05 eta: 6:19:46 time: 0.6358 data_time: 0.0015 memory: 44138 loss: 0.4171 2023/06/06 06:13:05 - mmengine - INFO - Epoch(train) [2][ 600/3907] lr: 2.9351e-05 eta: 6:18:24 time: 0.6353 data_time: 0.0014 memory: 44138 loss: 0.4244 2023/06/06 06:14:09 - mmengine - INFO - Epoch(train) [2][ 700/3907] lr: 2.9322e-05 eta: 6:17:02 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.4053 2023/06/06 06:15:12 - mmengine - INFO - Epoch(train) [2][ 800/3907] lr: 2.9293e-05 eta: 6:15:41 time: 0.6364 data_time: 0.0014 memory: 44138 loss: 0.4170 2023/06/06 06:16:16 - mmengine - INFO - Epoch(train) [2][ 900/3907] lr: 2.9263e-05 eta: 6:14:23 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.4180 2023/06/06 06:17:20 - mmengine - INFO - Epoch(train) [2][1000/3907] lr: 2.9232e-05 eta: 6:13:05 time: 0.6371 data_time: 0.0016 memory: 44138 loss: 0.4058 2023/06/06 06:18:19 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:18:23 - mmengine - INFO - Epoch(train) [2][1100/3907] lr: 2.9201e-05 eta: 6:11:47 time: 0.6362 data_time: 0.0017 memory: 44138 loss: 0.4151 2023/06/06 06:19:27 - mmengine - INFO - Epoch(train) [2][1200/3907] lr: 2.9169e-05 eta: 6:10:30 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.4330 2023/06/06 06:20:31 - mmengine - INFO - Epoch(train) [2][1300/3907] lr: 2.9137e-05 eta: 6:09:14 time: 0.6362 data_time: 0.0014 memory: 44138 loss: 0.4559 2023/06/06 06:21:35 - mmengine - INFO - Epoch(train) [2][1400/3907] lr: 2.9104e-05 eta: 6:07:58 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.4159 2023/06/06 06:22:38 - mmengine - INFO - Epoch(train) [2][1500/3907] lr: 2.9070e-05 eta: 6:06:41 time: 0.6374 data_time: 0.0014 memory: 44138 loss: 0.4259 2023/06/06 06:23:42 - mmengine - INFO - Epoch(train) [2][1600/3907] lr: 2.9036e-05 eta: 6:05:25 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.4157 2023/06/06 06:24:46 - mmengine - INFO - Epoch(train) [2][1700/3907] lr: 2.9001e-05 eta: 6:04:10 time: 0.6379 data_time: 0.0015 memory: 44138 loss: 0.4216 2023/06/06 06:25:49 - mmengine - INFO - Epoch(train) [2][1800/3907] lr: 2.8966e-05 eta: 6:02:55 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.4137 2023/06/06 06:26:53 - mmengine - INFO - Epoch(train) [2][1900/3907] lr: 2.8930e-05 eta: 6:01:40 time: 0.6360 data_time: 0.0014 memory: 44138 loss: 0.4191 2023/06/06 06:27:56 - mmengine - INFO - Epoch(train) [2][2000/3907] lr: 2.8893e-05 eta: 6:00:26 time: 0.6363 data_time: 0.0016 memory: 44138 loss: 0.4243 2023/06/06 06:28:56 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:29:00 - mmengine - INFO - Epoch(train) [2][2100/3907] lr: 2.8856e-05 eta: 5:59:13 time: 0.6360 data_time: 0.0016 memory: 44138 loss: 0.4397 2023/06/06 06:30:04 - mmengine - INFO - Epoch(train) [2][2200/3907] lr: 2.8819e-05 eta: 5:57:59 time: 0.6349 data_time: 0.0014 memory: 44138 loss: 0.3885 2023/06/06 06:31:08 - mmengine - INFO - Epoch(train) [2][2300/3907] lr: 2.8781e-05 eta: 5:56:47 time: 0.6370 data_time: 0.0014 memory: 44138 loss: 0.4367 2023/06/06 06:32:11 - mmengine - INFO - Epoch(train) [2][2400/3907] lr: 2.8742e-05 eta: 5:55:34 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.4364 2023/06/06 06:33:15 - mmengine - INFO - Epoch(train) [2][2500/3907] lr: 2.8702e-05 eta: 5:54:21 time: 0.6351 data_time: 0.0015 memory: 44138 loss: 0.4202 2023/06/06 06:34:19 - mmengine - INFO - Epoch(train) [2][2600/3907] lr: 2.8663e-05 eta: 5:53:08 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.4343 2023/06/06 06:35:22 - mmengine - INFO - Epoch(train) [2][2700/3907] lr: 2.8622e-05 eta: 5:51:56 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.4557 2023/06/06 06:36:26 - mmengine - INFO - Epoch(train) [2][2800/3907] lr: 2.8581e-05 eta: 5:50:45 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.4101 2023/06/06 06:37:30 - mmengine - INFO - Epoch(train) [2][2900/3907] lr: 2.8540e-05 eta: 5:49:33 time: 0.6367 data_time: 0.0014 memory: 44138 loss: 0.4268 2023/06/06 06:38:33 - mmengine - INFO - Epoch(train) [2][3000/3907] lr: 2.8497e-05 eta: 5:48:22 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.4199 2023/06/06 06:39:32 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:39:37 - mmengine - INFO - Epoch(train) [2][3100/3907] lr: 2.8455e-05 eta: 5:47:11 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.4295 2023/06/06 06:40:41 - mmengine - INFO - Epoch(train) [2][3200/3907] lr: 2.8412e-05 eta: 5:46:00 time: 0.6358 data_time: 0.0016 memory: 44138 loss: 0.4226 2023/06/06 06:41:44 - mmengine - INFO - Epoch(train) [2][3300/3907] lr: 2.8368e-05 eta: 5:44:50 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.4122 2023/06/06 06:42:48 - mmengine - INFO - Epoch(train) [2][3400/3907] lr: 2.8323e-05 eta: 5:43:40 time: 0.6351 data_time: 0.0015 memory: 44138 loss: 0.4387 2023/06/06 06:43:52 - mmengine - INFO - Epoch(train) [2][3500/3907] lr: 2.8279e-05 eta: 5:42:29 time: 0.6363 data_time: 0.0014 memory: 44138 loss: 0.4387 2023/06/06 06:44:55 - mmengine - INFO - Epoch(train) [2][3600/3907] lr: 2.8233e-05 eta: 5:41:19 time: 0.6362 data_time: 0.0016 memory: 44138 loss: 0.4182 2023/06/06 06:45:59 - mmengine - INFO - Epoch(train) [2][3700/3907] lr: 2.8187e-05 eta: 5:40:09 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.4316 2023/06/06 06:47:03 - mmengine - INFO - Epoch(train) [2][3800/3907] lr: 2.8141e-05 eta: 5:38:59 time: 0.6385 data_time: 0.0015 memory: 44138 loss: 0.3920 2023/06/06 06:48:06 - mmengine - INFO - Epoch(train) [2][3900/3907] lr: 2.8094e-05 eta: 5:37:49 time: 0.6353 data_time: 0.0013 memory: 44138 loss: 0.3885 2023/06/06 06:48:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:48:10 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/06/06 06:49:52 - mmengine - INFO - Epoch(val) [2][57/57] accuracy/top1: 81.8169 single-label/precision_classwise: [77.02530670166016, 92.15557098388672] single-label/recall_classwise: [95.49270629882812, 65.02325439453125] single-label/f1-score_classwise: [85.27057647705078, 76.24761199951172] data_time: 0.0349 time: 1.2780 2023/06/06 06:50:59 - mmengine - INFO - Epoch(train) [3][ 100/3907] lr: 2.8043e-05 eta: 5:36:46 time: 0.6348 data_time: 0.0024 memory: 44138 loss: 0.4136 2023/06/06 06:51:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 06:52:02 - mmengine - INFO - Epoch(train) [3][ 200/3907] lr: 2.7995e-05 eta: 5:35:36 time: 0.6361 data_time: 0.0018 memory: 44138 loss: 0.3959 2023/06/06 06:53:06 - mmengine - INFO - Epoch(train) [3][ 300/3907] lr: 2.7947e-05 eta: 5:34:27 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.3940 2023/06/06 06:54:10 - mmengine - INFO - Epoch(train) [3][ 400/3907] lr: 2.7897e-05 eta: 5:33:18 time: 0.6364 data_time: 0.0017 memory: 44138 loss: 0.4299 2023/06/06 06:55:13 - mmengine - INFO - Epoch(train) [3][ 500/3907] lr: 2.7848e-05 eta: 5:32:09 time: 0.6382 data_time: 0.0015 memory: 44138 loss: 0.4141 2023/06/06 06:56:17 - mmengine - INFO - Epoch(train) [3][ 600/3907] lr: 2.7798e-05 eta: 5:31:00 time: 0.6369 data_time: 0.0017 memory: 44138 loss: 0.4177 2023/06/06 06:57:21 - mmengine - INFO - Epoch(train) [3][ 700/3907] lr: 2.7747e-05 eta: 5:29:51 time: 0.6355 data_time: 0.0016 memory: 44138 loss: 0.4205 2023/06/06 06:58:25 - mmengine - INFO - Epoch(train) [3][ 800/3907] lr: 2.7696e-05 eta: 5:28:43 time: 0.6354 data_time: 0.0017 memory: 44138 loss: 0.4021 2023/06/06 06:59:28 - mmengine - INFO - Epoch(train) [3][ 900/3907] lr: 2.7645e-05 eta: 5:27:34 time: 0.6379 data_time: 0.0017 memory: 44138 loss: 0.3941 2023/06/06 07:00:32 - mmengine - INFO - Epoch(train) [3][1000/3907] lr: 2.7592e-05 eta: 5:26:26 time: 0.6357 data_time: 0.0017 memory: 44138 loss: 0.3778 2023/06/06 07:01:36 - mmengine - INFO - Epoch(train) [3][1100/3907] lr: 2.7540e-05 eta: 5:25:18 time: 0.6357 data_time: 0.0016 memory: 44138 loss: 0.4226 2023/06/06 07:02:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:02:40 - mmengine - INFO - Epoch(train) [3][1200/3907] lr: 2.7487e-05 eta: 5:24:10 time: 0.6348 data_time: 0.0015 memory: 44138 loss: 0.4193 2023/06/06 07:03:43 - mmengine - INFO - Epoch(train) [3][1300/3907] lr: 2.7433e-05 eta: 5:23:02 time: 0.6383 data_time: 0.0014 memory: 44138 loss: 0.3944 2023/06/06 07:04:47 - mmengine - INFO - Epoch(train) [3][1400/3907] lr: 2.7379e-05 eta: 5:21:54 time: 0.6354 data_time: 0.0015 memory: 44138 loss: 0.4156 2023/06/06 07:05:51 - mmengine - INFO - Epoch(train) [3][1500/3907] lr: 2.7325e-05 eta: 5:20:46 time: 0.6366 data_time: 0.0014 memory: 44138 loss: 0.3944 2023/06/06 07:06:54 - mmengine - INFO - Epoch(train) [3][1600/3907] lr: 2.7270e-05 eta: 5:19:38 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3986 2023/06/06 07:07:58 - mmengine - INFO - Epoch(train) [3][1700/3907] lr: 2.7214e-05 eta: 5:18:30 time: 0.6352 data_time: 0.0015 memory: 44138 loss: 0.3906 2023/06/06 07:09:02 - mmengine - INFO - Epoch(train) [3][1800/3907] lr: 2.7158e-05 eta: 5:17:23 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3704 2023/06/06 07:10:05 - mmengine - INFO - Epoch(train) [3][1900/3907] lr: 2.7102e-05 eta: 5:16:15 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.3927 2023/06/06 07:11:09 - mmengine - INFO - Epoch(train) [3][2000/3907] lr: 2.7045e-05 eta: 5:15:07 time: 0.6356 data_time: 0.0014 memory: 44138 loss: 0.4295 2023/06/06 07:12:13 - mmengine - INFO - Epoch(train) [3][2100/3907] lr: 2.6988e-05 eta: 5:14:00 time: 0.6366 data_time: 0.0014 memory: 44138 loss: 0.3927 2023/06/06 07:13:07 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:13:16 - mmengine - INFO - Epoch(train) [3][2200/3907] lr: 2.6930e-05 eta: 5:12:52 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3868 2023/06/06 07:14:20 - mmengine - INFO - Epoch(train) [3][2300/3907] lr: 2.6872e-05 eta: 5:11:45 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.4050 2023/06/06 07:15:23 - mmengine - INFO - Epoch(train) [3][2400/3907] lr: 2.6813e-05 eta: 5:10:38 time: 0.6353 data_time: 0.0015 memory: 44138 loss: 0.4070 2023/06/06 07:16:27 - mmengine - INFO - Epoch(train) [3][2500/3907] lr: 2.6754e-05 eta: 5:09:31 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.4014 2023/06/06 07:17:31 - mmengine - INFO - Epoch(train) [3][2600/3907] lr: 2.6695e-05 eta: 5:08:23 time: 0.6354 data_time: 0.0015 memory: 44138 loss: 0.4043 2023/06/06 07:18:35 - mmengine - INFO - Epoch(train) [3][2700/3907] lr: 2.6635e-05 eta: 5:07:16 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3955 2023/06/06 07:19:38 - mmengine - INFO - Epoch(train) [3][2800/3907] lr: 2.6574e-05 eta: 5:06:09 time: 0.6354 data_time: 0.0016 memory: 44138 loss: 0.3969 2023/06/06 07:20:42 - mmengine - INFO - Epoch(train) [3][2900/3907] lr: 2.6514e-05 eta: 5:05:03 time: 0.6440 data_time: 0.0015 memory: 44138 loss: 0.3879 2023/06/06 07:21:45 - mmengine - INFO - Epoch(train) [3][3000/3907] lr: 2.6452e-05 eta: 5:03:55 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.4132 2023/06/06 07:22:49 - mmengine - INFO - Epoch(train) [3][3100/3907] lr: 2.6391e-05 eta: 5:02:49 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.3975 2023/06/06 07:23:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:23:53 - mmengine - INFO - Epoch(train) [3][3200/3907] lr: 2.6329e-05 eta: 5:01:42 time: 0.6355 data_time: 0.0017 memory: 44138 loss: 0.4156 2023/06/06 07:24:56 - mmengine - INFO - Epoch(train) [3][3300/3907] lr: 2.6266e-05 eta: 5:00:35 time: 0.6360 data_time: 0.0015 memory: 44138 loss: 0.4108 2023/06/06 07:26:00 - mmengine - INFO - Epoch(train) [3][3400/3907] lr: 2.6203e-05 eta: 4:59:28 time: 0.6377 data_time: 0.0017 memory: 44138 loss: 0.3996 2023/06/06 07:27:04 - mmengine - INFO - Epoch(train) [3][3500/3907] lr: 2.6140e-05 eta: 4:58:22 time: 0.6386 data_time: 0.0015 memory: 44138 loss: 0.4072 2023/06/06 07:28:07 - mmengine - INFO - Epoch(train) [3][3600/3907] lr: 2.6076e-05 eta: 4:57:15 time: 0.6379 data_time: 0.0015 memory: 44138 loss: 0.3959 2023/06/06 07:29:11 - mmengine - INFO - Epoch(train) [3][3700/3907] lr: 2.6012e-05 eta: 4:56:09 time: 0.6354 data_time: 0.0015 memory: 44138 loss: 0.4010 2023/06/06 07:30:15 - mmengine - INFO - Epoch(train) [3][3800/3907] lr: 2.5948e-05 eta: 4:55:02 time: 0.6385 data_time: 0.0015 memory: 44138 loss: 0.3996 2023/06/06 07:31:18 - mmengine - INFO - Epoch(train) [3][3900/3907] lr: 2.5883e-05 eta: 4:53:56 time: 0.6359 data_time: 0.0013 memory: 44138 loss: 0.3793 2023/06/06 07:31:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:31:22 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/06/06 07:33:03 - mmengine - INFO - Epoch(val) [3][57/57] accuracy/top1: 81.4655 single-label/precision_classwise: [76.04796600341797, 94.23998260498047] single-label/recall_classwise: [96.8878173828125, 62.527130126953125] single-label/f1-score_classwise: [85.21221923828125, 75.17591094970703] data_time: 0.0318 time: 1.2766 2023/06/06 07:34:10 - mmengine - INFO - Epoch(train) [4][ 100/3907] lr: 2.5813e-05 eta: 4:52:51 time: 0.6359 data_time: 0.0015 memory: 44138 loss: 0.4052 2023/06/06 07:35:13 - mmengine - INFO - Epoch(train) [4][ 200/3907] lr: 2.5748e-05 eta: 4:51:45 time: 0.6373 data_time: 0.0019 memory: 44138 loss: 0.4041 2023/06/06 07:36:04 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:36:17 - mmengine - INFO - Epoch(train) [4][ 300/3907] lr: 2.5682e-05 eta: 4:50:39 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.3934 2023/06/06 07:37:21 - mmengine - INFO - Epoch(train) [4][ 400/3907] lr: 2.5615e-05 eta: 4:49:32 time: 0.6355 data_time: 0.0016 memory: 44138 loss: 0.4020 2023/06/06 07:38:24 - mmengine - INFO - Epoch(train) [4][ 500/3907] lr: 2.5549e-05 eta: 4:48:26 time: 0.6374 data_time: 0.0014 memory: 44138 loss: 0.4026 2023/06/06 07:39:28 - mmengine - INFO - Epoch(train) [4][ 600/3907] lr: 2.5482e-05 eta: 4:47:20 time: 0.6376 data_time: 0.0014 memory: 44138 loss: 0.3912 2023/06/06 07:40:32 - mmengine - INFO - Epoch(train) [4][ 700/3907] lr: 2.5414e-05 eta: 4:46:14 time: 0.6359 data_time: 0.0015 memory: 44138 loss: 0.4097 2023/06/06 07:41:35 - mmengine - INFO - Epoch(train) [4][ 800/3907] lr: 2.5346e-05 eta: 4:45:08 time: 0.6381 data_time: 0.0015 memory: 44138 loss: 0.3840 2023/06/06 07:42:39 - mmengine - INFO - Epoch(train) [4][ 900/3907] lr: 2.5278e-05 eta: 4:44:02 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.4085 2023/06/06 07:43:43 - mmengine - INFO - Epoch(train) [4][1000/3907] lr: 2.5210e-05 eta: 4:42:56 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.3875 2023/06/06 07:44:46 - mmengine - INFO - Epoch(train) [4][1100/3907] lr: 2.5141e-05 eta: 4:41:50 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.4015 2023/06/06 07:45:50 - mmengine - INFO - Epoch(train) [4][1200/3907] lr: 2.5072e-05 eta: 4:40:44 time: 0.6364 data_time: 0.0014 memory: 44138 loss: 0.3919 2023/06/06 07:46:41 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:46:54 - mmengine - INFO - Epoch(train) [4][1300/3907] lr: 2.5002e-05 eta: 4:39:39 time: 0.6352 data_time: 0.0014 memory: 44138 loss: 0.3964 2023/06/06 07:47:58 - mmengine - INFO - Epoch(train) [4][1400/3907] lr: 2.4933e-05 eta: 4:38:33 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.3731 2023/06/06 07:49:01 - mmengine - INFO - Epoch(train) [4][1500/3907] lr: 2.4862e-05 eta: 4:37:27 time: 0.6367 data_time: 0.0018 memory: 44138 loss: 0.3996 2023/06/06 07:50:05 - mmengine - INFO - Epoch(train) [4][1600/3907] lr: 2.4792e-05 eta: 4:36:21 time: 0.6357 data_time: 0.0015 memory: 44138 loss: 0.4016 2023/06/06 07:51:09 - mmengine - INFO - Epoch(train) [4][1700/3907] lr: 2.4721e-05 eta: 4:35:16 time: 0.6371 data_time: 0.0017 memory: 44138 loss: 0.3861 2023/06/06 07:52:13 - mmengine - INFO - Epoch(train) [4][1800/3907] lr: 2.4650e-05 eta: 4:34:10 time: 0.6360 data_time: 0.0015 memory: 44138 loss: 0.3891 2023/06/06 07:53:16 - mmengine - INFO - Epoch(train) [4][1900/3907] lr: 2.4579e-05 eta: 4:33:04 time: 0.6397 data_time: 0.0015 memory: 44138 loss: 0.3740 2023/06/06 07:54:20 - mmengine - INFO - Epoch(train) [4][2000/3907] lr: 2.4507e-05 eta: 4:31:59 time: 0.6453 data_time: 0.0016 memory: 44138 loss: 0.3678 2023/06/06 07:55:24 - mmengine - INFO - Epoch(train) [4][2100/3907] lr: 2.4435e-05 eta: 4:30:53 time: 0.6363 data_time: 0.0014 memory: 44138 loss: 0.4099 2023/06/06 07:56:27 - mmengine - INFO - Epoch(train) [4][2200/3907] lr: 2.4363e-05 eta: 4:29:47 time: 0.6355 data_time: 0.0014 memory: 44138 loss: 0.3971 2023/06/06 07:57:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 07:57:31 - mmengine - INFO - Epoch(train) [4][2300/3907] lr: 2.4291e-05 eta: 4:28:42 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3685 2023/06/06 07:58:35 - mmengine - INFO - Epoch(train) [4][2400/3907] lr: 2.4218e-05 eta: 4:27:36 time: 0.6435 data_time: 0.0015 memory: 44138 loss: 0.3989 2023/06/06 07:59:38 - mmengine - INFO - Epoch(train) [4][2500/3907] lr: 2.4145e-05 eta: 4:26:31 time: 0.6382 data_time: 0.0015 memory: 44138 loss: 0.3914 2023/06/06 08:00:42 - mmengine - INFO - Epoch(train) [4][2600/3907] lr: 2.4072e-05 eta: 4:25:26 time: 0.6387 data_time: 0.0015 memory: 44138 loss: 0.3884 2023/06/06 08:01:46 - mmengine - INFO - Epoch(train) [4][2700/3907] lr: 2.3998e-05 eta: 4:24:20 time: 0.6356 data_time: 0.0016 memory: 44138 loss: 0.3905 2023/06/06 08:02:50 - mmengine - INFO - Epoch(train) [4][2800/3907] lr: 2.3924e-05 eta: 4:23:14 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.4043 2023/06/06 08:03:53 - mmengine - INFO - Epoch(train) [4][2900/3907] lr: 2.3850e-05 eta: 4:22:09 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.3877 2023/06/06 08:04:57 - mmengine - INFO - Epoch(train) [4][3000/3907] lr: 2.3776e-05 eta: 4:21:04 time: 0.6356 data_time: 0.0016 memory: 44138 loss: 0.3915 2023/06/06 08:06:01 - mmengine - INFO - Epoch(train) [4][3100/3907] lr: 2.3701e-05 eta: 4:19:58 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.3847 2023/06/06 08:07:04 - mmengine - INFO - Epoch(train) [4][3200/3907] lr: 2.3626e-05 eta: 4:18:53 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.3819 2023/06/06 08:07:55 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:08:08 - mmengine - INFO - Epoch(train) [4][3300/3907] lr: 2.3551e-05 eta: 4:17:47 time: 0.6354 data_time: 0.0015 memory: 44138 loss: 0.3837 2023/06/06 08:09:12 - mmengine - INFO - Epoch(train) [4][3400/3907] lr: 2.3476e-05 eta: 4:16:42 time: 0.6390 data_time: 0.0015 memory: 44138 loss: 0.4051 2023/06/06 08:10:16 - mmengine - INFO - Epoch(train) [4][3500/3907] lr: 2.3400e-05 eta: 4:15:37 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.3862 2023/06/06 08:11:19 - mmengine - INFO - Epoch(train) [4][3600/3907] lr: 2.3325e-05 eta: 4:14:32 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3678 2023/06/06 08:12:23 - mmengine - INFO - Epoch(train) [4][3700/3907] lr: 2.3249e-05 eta: 4:13:27 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3959 2023/06/06 08:13:27 - mmengine - INFO - Epoch(train) [4][3800/3907] lr: 2.3173e-05 eta: 4:12:21 time: 0.6355 data_time: 0.0014 memory: 44138 loss: 0.3997 2023/06/06 08:14:30 - mmengine - INFO - Epoch(train) [4][3900/3907] lr: 2.3096e-05 eta: 4:11:16 time: 0.6355 data_time: 0.0013 memory: 44138 loss: 0.3931 2023/06/06 08:14:34 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:14:34 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/06/06 08:16:16 - mmengine - INFO - Epoch(val) [4][57/57] accuracy/top1: 80.3138 single-label/precision_classwise: [74.58592987060547, 95.08216857910156] single-label/recall_classwise: [97.5064697265625, 59.2015495300293] single-label/f1-score_classwise: [84.51983642578125, 72.96961212158203] data_time: 0.0321 time: 1.2764 2023/06/06 08:17:23 - mmengine - INFO - Epoch(train) [5][ 100/3907] lr: 2.3014e-05 eta: 4:10:11 time: 0.6359 data_time: 0.0015 memory: 44138 loss: 0.3916 2023/06/06 08:18:27 - mmengine - INFO - Epoch(train) [5][ 200/3907] lr: 2.2938e-05 eta: 4:09:05 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3880 2023/06/06 08:19:31 - mmengine - INFO - Epoch(train) [5][ 300/3907] lr: 2.2861e-05 eta: 4:08:00 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.4007 2023/06/06 08:20:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:20:34 - mmengine - INFO - Epoch(train) [5][ 400/3907] lr: 2.2784e-05 eta: 4:06:55 time: 0.6363 data_time: 0.0016 memory: 44138 loss: 0.4241 2023/06/06 08:21:38 - mmengine - INFO - Epoch(train) [5][ 500/3907] lr: 2.2706e-05 eta: 4:05:50 time: 0.6356 data_time: 0.0016 memory: 44138 loss: 0.3774 2023/06/06 08:22:42 - mmengine - INFO - Epoch(train) [5][ 600/3907] lr: 2.2629e-05 eta: 4:04:44 time: 0.6361 data_time: 0.0016 memory: 44138 loss: 0.3699 2023/06/06 08:23:45 - mmengine - INFO - Epoch(train) [5][ 700/3907] lr: 2.2551e-05 eta: 4:03:39 time: 0.6366 data_time: 0.0016 memory: 44138 loss: 0.4149 2023/06/06 08:24:49 - mmengine - INFO - Epoch(train) [5][ 800/3907] lr: 2.2473e-05 eta: 4:02:34 time: 0.6381 data_time: 0.0015 memory: 44138 loss: 0.3635 2023/06/06 08:25:53 - mmengine - INFO - Epoch(train) [5][ 900/3907] lr: 2.2395e-05 eta: 4:01:29 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3736 2023/06/06 08:26:56 - mmengine - INFO - Epoch(train) [5][1000/3907] lr: 2.2317e-05 eta: 4:00:24 time: 0.6360 data_time: 0.0015 memory: 44138 loss: 0.3605 2023/06/06 08:28:00 - mmengine - INFO - Epoch(train) [5][1100/3907] lr: 2.2239e-05 eta: 3:59:19 time: 0.6375 data_time: 0.0015 memory: 44138 loss: 0.3709 2023/06/06 08:29:04 - mmengine - INFO - Epoch(train) [5][1200/3907] lr: 2.2160e-05 eta: 3:58:14 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.3899 2023/06/06 08:30:08 - mmengine - INFO - Epoch(train) [5][1300/3907] lr: 2.2082e-05 eta: 3:57:09 time: 0.6384 data_time: 0.0015 memory: 44138 loss: 0.3937 2023/06/06 08:30:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:31:12 - mmengine - INFO - Epoch(train) [5][1400/3907] lr: 2.2003e-05 eta: 3:56:04 time: 0.6391 data_time: 0.0014 memory: 44138 loss: 0.3768 2023/06/06 08:32:15 - mmengine - INFO - Epoch(train) [5][1500/3907] lr: 2.1924e-05 eta: 3:54:59 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.4080 2023/06/06 08:33:19 - mmengine - INFO - Epoch(train) [5][1600/3907] lr: 2.1845e-05 eta: 3:53:55 time: 0.6375 data_time: 0.0016 memory: 44138 loss: 0.3828 2023/06/06 08:34:23 - mmengine - INFO - Epoch(train) [5][1700/3907] lr: 2.1766e-05 eta: 3:52:50 time: 0.6384 data_time: 0.0014 memory: 44138 loss: 0.3655 2023/06/06 08:35:27 - mmengine - INFO - Epoch(train) [5][1800/3907] lr: 2.1687e-05 eta: 3:51:45 time: 0.6359 data_time: 0.0017 memory: 44138 loss: 0.3966 2023/06/06 08:36:30 - mmengine - INFO - Epoch(train) [5][1900/3907] lr: 2.1608e-05 eta: 3:50:40 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.3885 2023/06/06 08:37:34 - mmengine - INFO - Epoch(train) [5][2000/3907] lr: 2.1528e-05 eta: 3:49:35 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.3777 2023/06/06 08:38:38 - mmengine - INFO - Epoch(train) [5][2100/3907] lr: 2.1449e-05 eta: 3:48:30 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3829 2023/06/06 08:39:41 - mmengine - INFO - Epoch(train) [5][2200/3907] lr: 2.1369e-05 eta: 3:47:25 time: 0.6396 data_time: 0.0016 memory: 44138 loss: 0.3939 2023/06/06 08:40:45 - mmengine - INFO - Epoch(train) [5][2300/3907] lr: 2.1289e-05 eta: 3:46:20 time: 0.6377 data_time: 0.0014 memory: 44138 loss: 0.3830 2023/06/06 08:41:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:41:49 - mmengine - INFO - Epoch(train) [5][2400/3907] lr: 2.1210e-05 eta: 3:45:15 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.4075 2023/06/06 08:42:53 - mmengine - INFO - Epoch(train) [5][2500/3907] lr: 2.1130e-05 eta: 3:44:11 time: 0.6363 data_time: 0.0014 memory: 44138 loss: 0.3941 2023/06/06 08:43:56 - mmengine - INFO - Epoch(train) [5][2600/3907] lr: 2.1050e-05 eta: 3:43:06 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3669 2023/06/06 08:45:00 - mmengine - INFO - Epoch(train) [5][2700/3907] lr: 2.0970e-05 eta: 3:42:01 time: 0.6359 data_time: 0.0016 memory: 44138 loss: 0.3765 2023/06/06 08:46:04 - mmengine - INFO - Epoch(train) [5][2800/3907] lr: 2.0890e-05 eta: 3:40:56 time: 0.6384 data_time: 0.0015 memory: 44138 loss: 0.3842 2023/06/06 08:47:07 - mmengine - INFO - Epoch(train) [5][2900/3907] lr: 2.0810e-05 eta: 3:39:51 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.4083 2023/06/06 08:48:11 - mmengine - INFO - Epoch(train) [5][3000/3907] lr: 2.0729e-05 eta: 3:38:47 time: 0.6359 data_time: 0.0016 memory: 44138 loss: 0.4011 2023/06/06 08:49:15 - mmengine - INFO - Epoch(train) [5][3100/3907] lr: 2.0649e-05 eta: 3:37:42 time: 0.6411 data_time: 0.0015 memory: 44138 loss: 0.3510 2023/06/06 08:50:19 - mmengine - INFO - Epoch(train) [5][3200/3907] lr: 2.0569e-05 eta: 3:36:37 time: 0.6372 data_time: 0.0016 memory: 44138 loss: 0.3843 2023/06/06 08:51:23 - mmengine - INFO - Epoch(train) [5][3300/3907] lr: 2.0489e-05 eta: 3:35:33 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3697 2023/06/06 08:52:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:52:27 - mmengine - INFO - Epoch(train) [5][3400/3907] lr: 2.0408e-05 eta: 3:34:28 time: 0.6382 data_time: 0.0014 memory: 44138 loss: 0.3669 2023/06/06 08:53:30 - mmengine - INFO - Epoch(train) [5][3500/3907] lr: 2.0328e-05 eta: 3:33:23 time: 0.6376 data_time: 0.0015 memory: 44138 loss: 0.3740 2023/06/06 08:54:34 - mmengine - INFO - Epoch(train) [5][3600/3907] lr: 2.0248e-05 eta: 3:32:19 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3798 2023/06/06 08:55:38 - mmengine - INFO - Epoch(train) [5][3700/3907] lr: 2.0167e-05 eta: 3:31:14 time: 0.6385 data_time: 0.0014 memory: 44138 loss: 0.3770 2023/06/06 08:56:41 - mmengine - INFO - Epoch(train) [5][3800/3907] lr: 2.0087e-05 eta: 3:30:09 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3950 2023/06/06 08:57:45 - mmengine - INFO - Epoch(train) [5][3900/3907] lr: 2.0006e-05 eta: 3:29:05 time: 0.6378 data_time: 0.0012 memory: 44138 loss: 0.3776 2023/06/06 08:57:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 08:57:49 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/06/06 08:59:30 - mmengine - INFO - Epoch(val) [5][57/57] accuracy/top1: 79.6736 single-label/precision_classwise: [73.83551788330078, 95.44166564941406] single-label/recall_classwise: [97.76528930664062, 57.45736312866211] single-label/f1-score_classwise: [84.13190460205078, 71.7313461303711] data_time: 0.0310 time: 1.2739 2023/06/06 09:00:37 - mmengine - INFO - Epoch(train) [6][ 100/3907] lr: 1.9920e-05 eta: 3:27:59 time: 0.6389 data_time: 0.0013 memory: 44138 loss: 0.3793 2023/06/06 09:01:41 - mmengine - INFO - Epoch(train) [6][ 200/3907] lr: 1.9840e-05 eta: 3:26:54 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.3913 2023/06/06 09:02:45 - mmengine - INFO - Epoch(train) [6][ 300/3907] lr: 1.9760e-05 eta: 3:25:49 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.4005 2023/06/06 09:03:48 - mmengine - INFO - Epoch(train) [6][ 400/3907] lr: 1.9679e-05 eta: 3:24:44 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3783 2023/06/06 09:04:30 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:04:52 - mmengine - INFO - Epoch(train) [6][ 500/3907] lr: 1.9599e-05 eta: 3:23:40 time: 0.6455 data_time: 0.0015 memory: 44138 loss: 0.3835 2023/06/06 09:05:56 - mmengine - INFO - Epoch(train) [6][ 600/3907] lr: 1.9519e-05 eta: 3:22:35 time: 0.6390 data_time: 0.0015 memory: 44138 loss: 0.3652 2023/06/06 09:07:00 - mmengine - INFO - Epoch(train) [6][ 700/3907] lr: 1.9438e-05 eta: 3:21:31 time: 0.6370 data_time: 0.0014 memory: 44138 loss: 0.3933 2023/06/06 09:08:03 - mmengine - INFO - Epoch(train) [6][ 800/3907] lr: 1.9358e-05 eta: 3:20:26 time: 0.6359 data_time: 0.0014 memory: 44138 loss: 0.3975 2023/06/06 09:09:07 - mmengine - INFO - Epoch(train) [6][ 900/3907] lr: 1.9278e-05 eta: 3:19:21 time: 0.6433 data_time: 0.0016 memory: 44138 loss: 0.4032 2023/06/06 09:10:11 - mmengine - INFO - Epoch(train) [6][1000/3907] lr: 1.9198e-05 eta: 3:18:17 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.3704 2023/06/06 09:11:15 - mmengine - INFO - Epoch(train) [6][1100/3907] lr: 1.9117e-05 eta: 3:17:12 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.3754 2023/06/06 09:12:18 - mmengine - INFO - Epoch(train) [6][1200/3907] lr: 1.9037e-05 eta: 3:16:08 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.3556 2023/06/06 09:13:22 - mmengine - INFO - Epoch(train) [6][1300/3907] lr: 1.8957e-05 eta: 3:15:03 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3643 2023/06/06 09:14:26 - mmengine - INFO - Epoch(train) [6][1400/3907] lr: 1.8877e-05 eta: 3:13:58 time: 0.6382 data_time: 0.0015 memory: 44138 loss: 0.3651 2023/06/06 09:15:07 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:15:29 - mmengine - INFO - Epoch(train) [6][1500/3907] lr: 1.8798e-05 eta: 3:12:54 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.3655 2023/06/06 09:16:33 - mmengine - INFO - Epoch(train) [6][1600/3907] lr: 1.8718e-05 eta: 3:11:49 time: 0.6353 data_time: 0.0016 memory: 44138 loss: 0.3602 2023/06/06 09:17:37 - mmengine - INFO - Epoch(train) [6][1700/3907] lr: 1.8638e-05 eta: 3:10:44 time: 0.6357 data_time: 0.0015 memory: 44138 loss: 0.3669 2023/06/06 09:18:40 - mmengine - INFO - Epoch(train) [6][1800/3907] lr: 1.8558e-05 eta: 3:09:40 time: 0.6385 data_time: 0.0016 memory: 44138 loss: 0.3765 2023/06/06 09:19:44 - mmengine - INFO - Epoch(train) [6][1900/3907] lr: 1.8479e-05 eta: 3:08:36 time: 0.6383 data_time: 0.0015 memory: 44138 loss: 0.3942 2023/06/06 09:20:48 - mmengine - INFO - Epoch(train) [6][2000/3907] lr: 1.8400e-05 eta: 3:07:31 time: 0.6389 data_time: 0.0014 memory: 44138 loss: 0.3796 2023/06/06 09:21:52 - mmengine - INFO - Epoch(train) [6][2100/3907] lr: 1.8320e-05 eta: 3:06:27 time: 0.6366 data_time: 0.0017 memory: 44138 loss: 0.3982 2023/06/06 09:22:56 - mmengine - INFO - Epoch(train) [6][2200/3907] lr: 1.8241e-05 eta: 3:05:22 time: 0.6386 data_time: 0.0015 memory: 44138 loss: 0.3645 2023/06/06 09:23:59 - mmengine - INFO - Epoch(train) [6][2300/3907] lr: 1.8162e-05 eta: 3:04:18 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3877 2023/06/06 09:25:03 - mmengine - INFO - Epoch(train) [6][2400/3907] lr: 1.8083e-05 eta: 3:03:13 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.3965 2023/06/06 09:25:45 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:26:07 - mmengine - INFO - Epoch(train) [6][2500/3907] lr: 1.8004e-05 eta: 3:02:09 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.3838 2023/06/06 09:27:10 - mmengine - INFO - Epoch(train) [6][2600/3907] lr: 1.7925e-05 eta: 3:01:04 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.4102 2023/06/06 09:28:14 - mmengine - INFO - Epoch(train) [6][2700/3907] lr: 1.7847e-05 eta: 3:00:00 time: 0.6381 data_time: 0.0015 memory: 44138 loss: 0.3947 2023/06/06 09:29:18 - mmengine - INFO - Epoch(train) [6][2800/3907] lr: 1.7768e-05 eta: 2:58:55 time: 0.6350 data_time: 0.0015 memory: 44138 loss: 0.3717 2023/06/06 09:30:22 - mmengine - INFO - Epoch(train) [6][2900/3907] lr: 1.7690e-05 eta: 2:57:51 time: 0.6372 data_time: 0.0014 memory: 44138 loss: 0.3782 2023/06/06 09:31:25 - mmengine - INFO - Epoch(train) [6][3000/3907] lr: 1.7612e-05 eta: 2:56:46 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3384 2023/06/06 09:32:29 - mmengine - INFO - Epoch(train) [6][3100/3907] lr: 1.7534e-05 eta: 2:55:42 time: 0.6378 data_time: 0.0015 memory: 44138 loss: 0.3631 2023/06/06 09:33:33 - mmengine - INFO - Epoch(train) [6][3200/3907] lr: 1.7456e-05 eta: 2:54:37 time: 0.6370 data_time: 0.0017 memory: 44138 loss: 0.3875 2023/06/06 09:34:37 - mmengine - INFO - Epoch(train) [6][3300/3907] lr: 1.7378e-05 eta: 2:53:33 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3765 2023/06/06 09:35:40 - mmengine - INFO - Epoch(train) [6][3400/3907] lr: 1.7301e-05 eta: 2:52:29 time: 0.6382 data_time: 0.0014 memory: 44138 loss: 0.3879 2023/06/06 09:36:22 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:36:44 - mmengine - INFO - Epoch(train) [6][3500/3907] lr: 1.7223e-05 eta: 2:51:24 time: 0.6376 data_time: 0.0014 memory: 44138 loss: 0.3694 2023/06/06 09:37:48 - mmengine - INFO - Epoch(train) [6][3600/3907] lr: 1.7146e-05 eta: 2:50:20 time: 0.6368 data_time: 0.0014 memory: 44138 loss: 0.3771 2023/06/06 09:38:52 - mmengine - INFO - Epoch(train) [6][3700/3907] lr: 1.7069e-05 eta: 2:49:15 time: 0.6374 data_time: 0.0015 memory: 44138 loss: 0.3630 2023/06/06 09:39:55 - mmengine - INFO - Epoch(train) [6][3800/3907] lr: 1.6993e-05 eta: 2:48:11 time: 0.6366 data_time: 0.0014 memory: 44138 loss: 0.3609 2023/06/06 09:40:59 - mmengine - INFO - Epoch(train) [6][3900/3907] lr: 1.6916e-05 eta: 2:47:06 time: 0.6344 data_time: 0.0014 memory: 44138 loss: 0.3965 2023/06/06 09:41:03 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:41:03 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/06/06 09:42:45 - mmengine - INFO - Epoch(val) [6][57/57] accuracy/top1: 79.6632 single-label/precision_classwise: [73.68944549560547, 96.1533432006836] single-label/recall_classwise: [98.14405822753906, 56.968994140625] single-label/f1-score_classwise: [84.1766128540039, 71.5474853515625] data_time: 0.0322 time: 1.2768 2023/06/06 09:43:52 - mmengine - INFO - Epoch(train) [7][ 100/3907] lr: 1.6834e-05 eta: 2:45:59 time: 0.6352 data_time: 0.0016 memory: 44138 loss: 0.3702 2023/06/06 09:44:56 - mmengine - INFO - Epoch(train) [7][ 200/3907] lr: 1.6758e-05 eta: 2:44:55 time: 0.6352 data_time: 0.0015 memory: 44138 loss: 0.3628 2023/06/06 09:45:59 - mmengine - INFO - Epoch(train) [7][ 300/3907] lr: 1.6682e-05 eta: 2:43:50 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3686 2023/06/06 09:47:03 - mmengine - INFO - Epoch(train) [7][ 400/3907] lr: 1.6606e-05 eta: 2:42:46 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3560 2023/06/06 09:48:07 - mmengine - INFO - Epoch(train) [7][ 500/3907] lr: 1.6531e-05 eta: 2:41:41 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3811 2023/06/06 09:48:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:49:10 - mmengine - INFO - Epoch(train) [7][ 600/3907] lr: 1.6456e-05 eta: 2:40:37 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.4050 2023/06/06 09:50:14 - mmengine - INFO - Epoch(train) [7][ 700/3907] lr: 1.6380e-05 eta: 2:39:32 time: 0.6383 data_time: 0.0015 memory: 44138 loss: 0.3550 2023/06/06 09:51:18 - mmengine - INFO - Epoch(train) [7][ 800/3907] lr: 1.6306e-05 eta: 2:38:28 time: 0.6361 data_time: 0.0016 memory: 44138 loss: 0.3617 2023/06/06 09:52:21 - mmengine - INFO - Epoch(train) [7][ 900/3907] lr: 1.6231e-05 eta: 2:37:24 time: 0.6377 data_time: 0.0014 memory: 44138 loss: 0.3531 2023/06/06 09:53:25 - mmengine - INFO - Epoch(train) [7][1000/3907] lr: 1.6157e-05 eta: 2:36:19 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3748 2023/06/06 09:54:29 - mmengine - INFO - Epoch(train) [7][1100/3907] lr: 1.6083e-05 eta: 2:35:15 time: 0.6350 data_time: 0.0015 memory: 44138 loss: 0.3918 2023/06/06 09:55:33 - mmengine - INFO - Epoch(train) [7][1200/3907] lr: 1.6009e-05 eta: 2:34:11 time: 0.6369 data_time: 0.0014 memory: 44138 loss: 0.3528 2023/06/06 09:56:36 - mmengine - INFO - Epoch(train) [7][1300/3907] lr: 1.5935e-05 eta: 2:33:06 time: 0.6396 data_time: 0.0016 memory: 44138 loss: 0.3765 2023/06/06 09:57:40 - mmengine - INFO - Epoch(train) [7][1400/3907] lr: 1.5862e-05 eta: 2:32:02 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3666 2023/06/06 09:58:44 - mmengine - INFO - Epoch(train) [7][1500/3907] lr: 1.5789e-05 eta: 2:30:58 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3824 2023/06/06 09:59:21 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 09:59:48 - mmengine - INFO - Epoch(train) [7][1600/3907] lr: 1.5716e-05 eta: 2:29:53 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3892 2023/06/06 10:00:51 - mmengine - INFO - Epoch(train) [7][1700/3907] lr: 1.5643e-05 eta: 2:28:49 time: 0.6357 data_time: 0.0015 memory: 44138 loss: 0.3589 2023/06/06 10:01:55 - mmengine - INFO - Epoch(train) [7][1800/3907] lr: 1.5571e-05 eta: 2:27:45 time: 0.6357 data_time: 0.0014 memory: 44138 loss: 0.3735 2023/06/06 10:02:59 - mmengine - INFO - Epoch(train) [7][1900/3907] lr: 1.5499e-05 eta: 2:26:40 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.3890 2023/06/06 10:04:02 - mmengine - INFO - Epoch(train) [7][2000/3907] lr: 1.5428e-05 eta: 2:25:36 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3634 2023/06/06 10:05:06 - mmengine - INFO - Epoch(train) [7][2100/3907] lr: 1.5356e-05 eta: 2:24:32 time: 0.6360 data_time: 0.0016 memory: 44138 loss: 0.3768 2023/06/06 10:06:10 - mmengine - INFO - Epoch(train) [7][2200/3907] lr: 1.5285e-05 eta: 2:23:27 time: 0.6351 data_time: 0.0015 memory: 44138 loss: 0.3859 2023/06/06 10:07:13 - mmengine - INFO - Epoch(train) [7][2300/3907] lr: 1.5214e-05 eta: 2:22:23 time: 0.6403 data_time: 0.0014 memory: 44138 loss: 0.3875 2023/06/06 10:08:17 - mmengine - INFO - Epoch(train) [7][2400/3907] lr: 1.5144e-05 eta: 2:21:19 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.3642 2023/06/06 10:09:21 - mmengine - INFO - Epoch(train) [7][2500/3907] lr: 1.5074e-05 eta: 2:20:14 time: 0.6364 data_time: 0.0020 memory: 44138 loss: 0.3523 2023/06/06 10:09:58 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:10:25 - mmengine - INFO - Epoch(train) [7][2600/3907] lr: 1.5004e-05 eta: 2:19:10 time: 0.6363 data_time: 0.0015 memory: 44138 loss: 0.3742 2023/06/06 10:11:28 - mmengine - INFO - Epoch(train) [7][2700/3907] lr: 1.4934e-05 eta: 2:18:06 time: 0.6378 data_time: 0.0014 memory: 44138 loss: 0.3535 2023/06/06 10:12:32 - mmengine - INFO - Epoch(train) [7][2800/3907] lr: 1.4865e-05 eta: 2:17:01 time: 0.6352 data_time: 0.0014 memory: 44138 loss: 0.3805 2023/06/06 10:13:36 - mmengine - INFO - Epoch(train) [7][2900/3907] lr: 1.4796e-05 eta: 2:15:57 time: 0.6355 data_time: 0.0015 memory: 44138 loss: 0.3934 2023/06/06 10:14:39 - mmengine - INFO - Epoch(train) [7][3000/3907] lr: 1.4728e-05 eta: 2:14:53 time: 0.6362 data_time: 0.0017 memory: 44138 loss: 0.3819 2023/06/06 10:15:43 - mmengine - INFO - Epoch(train) [7][3100/3907] lr: 1.4660e-05 eta: 2:13:49 time: 0.6362 data_time: 0.0016 memory: 44138 loss: 0.3392 2023/06/06 10:16:47 - mmengine - INFO - Epoch(train) [7][3200/3907] lr: 1.4592e-05 eta: 2:12:44 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3761 2023/06/06 10:17:50 - mmengine - INFO - Epoch(train) [7][3300/3907] lr: 1.4525e-05 eta: 2:11:40 time: 0.6365 data_time: 0.0017 memory: 44138 loss: 0.3643 2023/06/06 10:18:54 - mmengine - INFO - Epoch(train) [7][3400/3907] lr: 1.4457e-05 eta: 2:10:36 time: 0.6364 data_time: 0.0014 memory: 44138 loss: 0.3812 2023/06/06 10:19:58 - mmengine - INFO - Epoch(train) [7][3500/3907] lr: 1.4391e-05 eta: 2:09:32 time: 0.6356 data_time: 0.0015 memory: 44138 loss: 0.3685 2023/06/06 10:20:35 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:21:02 - mmengine - INFO - Epoch(train) [7][3600/3907] lr: 1.4324e-05 eta: 2:08:27 time: 0.6396 data_time: 0.0015 memory: 44138 loss: 0.3588 2023/06/06 10:22:06 - mmengine - INFO - Epoch(train) [7][3700/3907] lr: 1.4258e-05 eta: 2:07:23 time: 0.6377 data_time: 0.0015 memory: 44138 loss: 0.3918 2023/06/06 10:23:09 - mmengine - INFO - Epoch(train) [7][3800/3907] lr: 1.4193e-05 eta: 2:06:19 time: 0.6497 data_time: 0.0016 memory: 44138 loss: 0.3637 2023/06/06 10:24:13 - mmengine - INFO - Epoch(train) [7][3900/3907] lr: 1.4127e-05 eta: 2:05:15 time: 0.6345 data_time: 0.0013 memory: 44138 loss: 0.3829 2023/06/06 10:24:17 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:24:17 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/06/06 10:25:55 - mmengine - INFO - Epoch(val) [7][57/57] accuracy/top1: 79.1065 single-label/precision_classwise: [73.08920288085938, 96.33113861083984] single-label/recall_classwise: [98.27661895751953, 55.565895080566406] single-label/f1-score_classwise: [83.8318862915039, 70.47834777832031] data_time: 0.0338 time: 1.2759 2023/06/06 10:27:02 - mmengine - INFO - Epoch(train) [8][ 100/3907] lr: 1.4058e-05 eta: 2:04:07 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.4042 2023/06/06 10:28:06 - mmengine - INFO - Epoch(train) [8][ 200/3907] lr: 1.3993e-05 eta: 2:03:03 time: 0.6392 data_time: 0.0014 memory: 44138 loss: 0.3983 2023/06/06 10:29:10 - mmengine - INFO - Epoch(train) [8][ 300/3907] lr: 1.3929e-05 eta: 2:01:59 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3864 2023/06/06 10:30:13 - mmengine - INFO - Epoch(train) [8][ 400/3907] lr: 1.3866e-05 eta: 2:00:55 time: 0.6354 data_time: 0.0014 memory: 44138 loss: 0.3792 2023/06/06 10:31:17 - mmengine - INFO - Epoch(train) [8][ 500/3907] lr: 1.3802e-05 eta: 1:59:50 time: 0.6385 data_time: 0.0014 memory: 44138 loss: 0.3679 2023/06/06 10:32:21 - mmengine - INFO - Epoch(train) [8][ 600/3907] lr: 1.3739e-05 eta: 1:58:46 time: 0.6369 data_time: 0.0014 memory: 44138 loss: 0.3605 2023/06/06 10:32:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:33:25 - mmengine - INFO - Epoch(train) [8][ 700/3907] lr: 1.3677e-05 eta: 1:57:42 time: 0.6393 data_time: 0.0015 memory: 44138 loss: 0.3706 2023/06/06 10:34:29 - mmengine - INFO - Epoch(train) [8][ 800/3907] lr: 1.3615e-05 eta: 1:56:38 time: 0.6377 data_time: 0.0014 memory: 44138 loss: 0.3896 2023/06/06 10:35:32 - mmengine - INFO - Epoch(train) [8][ 900/3907] lr: 1.3553e-05 eta: 1:55:34 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3782 2023/06/06 10:36:36 - mmengine - INFO - Epoch(train) [8][1000/3907] lr: 1.3492e-05 eta: 1:54:29 time: 0.6376 data_time: 0.0016 memory: 44138 loss: 0.3768 2023/06/06 10:37:40 - mmengine - INFO - Epoch(train) [8][1100/3907] lr: 1.3431e-05 eta: 1:53:25 time: 0.6351 data_time: 0.0015 memory: 44138 loss: 0.3737 2023/06/06 10:38:44 - mmengine - INFO - Epoch(train) [8][1200/3907] lr: 1.3371e-05 eta: 1:52:21 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3834 2023/06/06 10:39:47 - mmengine - INFO - Epoch(train) [8][1300/3907] lr: 1.3311e-05 eta: 1:51:17 time: 0.6374 data_time: 0.0015 memory: 44138 loss: 0.3759 2023/06/06 10:40:51 - mmengine - INFO - Epoch(train) [8][1400/3907] lr: 1.3251e-05 eta: 1:50:13 time: 0.6370 data_time: 0.0014 memory: 44138 loss: 0.3792 2023/06/06 10:41:55 - mmengine - INFO - Epoch(train) [8][1500/3907] lr: 1.3192e-05 eta: 1:49:08 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3774 2023/06/06 10:42:59 - mmengine - INFO - Epoch(train) [8][1600/3907] lr: 1.3133e-05 eta: 1:48:04 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3626 2023/06/06 10:43:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:44:03 - mmengine - INFO - Epoch(train) [8][1700/3907] lr: 1.3075e-05 eta: 1:47:00 time: 0.6357 data_time: 0.0015 memory: 44138 loss: 0.3762 2023/06/06 10:45:06 - mmengine - INFO - Epoch(train) [8][1800/3907] lr: 1.3017e-05 eta: 1:45:56 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3778 2023/06/06 10:46:10 - mmengine - INFO - Epoch(train) [8][1900/3907] lr: 1.2960e-05 eta: 1:44:52 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3494 2023/06/06 10:47:14 - mmengine - INFO - Epoch(train) [8][2000/3907] lr: 1.2903e-05 eta: 1:43:48 time: 0.6380 data_time: 0.0016 memory: 44138 loss: 0.3399 2023/06/06 10:48:18 - mmengine - INFO - Epoch(train) [8][2100/3907] lr: 1.2847e-05 eta: 1:42:43 time: 0.6388 data_time: 0.0015 memory: 44138 loss: 0.3769 2023/06/06 10:49:21 - mmengine - INFO - Epoch(train) [8][2200/3907] lr: 1.2791e-05 eta: 1:41:39 time: 0.6378 data_time: 0.0016 memory: 44138 loss: 0.3620 2023/06/06 10:50:25 - mmengine - INFO - Epoch(train) [8][2300/3907] lr: 1.2735e-05 eta: 1:40:35 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3535 2023/06/06 10:51:29 - mmengine - INFO - Epoch(train) [8][2400/3907] lr: 1.2680e-05 eta: 1:39:31 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3676 2023/06/06 10:52:33 - mmengine - INFO - Epoch(train) [8][2500/3907] lr: 1.2626e-05 eta: 1:38:27 time: 0.6375 data_time: 0.0015 memory: 44138 loss: 0.3606 2023/06/06 10:53:37 - mmengine - INFO - Epoch(train) [8][2600/3907] lr: 1.2572e-05 eta: 1:37:23 time: 0.6419 data_time: 0.0015 memory: 44138 loss: 0.3713 2023/06/06 10:54:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 10:54:41 - mmengine - INFO - Epoch(train) [8][2700/3907] lr: 1.2518e-05 eta: 1:36:19 time: 0.6390 data_time: 0.0015 memory: 44138 loss: 0.3760 2023/06/06 10:55:44 - mmengine - INFO - Epoch(train) [8][2800/3907] lr: 1.2465e-05 eta: 1:35:14 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3636 2023/06/06 10:56:48 - mmengine - INFO - Epoch(train) [8][2900/3907] lr: 1.2412e-05 eta: 1:34:10 time: 0.6375 data_time: 0.0017 memory: 44138 loss: 0.3955 2023/06/06 10:57:52 - mmengine - INFO - Epoch(train) [8][3000/3907] lr: 1.2360e-05 eta: 1:33:06 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.3832 2023/06/06 10:58:55 - mmengine - INFO - Epoch(train) [8][3100/3907] lr: 1.2309e-05 eta: 1:32:02 time: 0.6378 data_time: 0.0018 memory: 44138 loss: 0.3842 2023/06/06 10:59:59 - mmengine - INFO - Epoch(train) [8][3200/3907] lr: 1.2257e-05 eta: 1:30:58 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3535 2023/06/06 11:01:03 - mmengine - INFO - Epoch(train) [8][3300/3907] lr: 1.2207e-05 eta: 1:29:54 time: 0.6396 data_time: 0.0016 memory: 44138 loss: 0.3575 2023/06/06 11:02:07 - mmengine - INFO - Epoch(train) [8][3400/3907] lr: 1.2157e-05 eta: 1:28:50 time: 0.6398 data_time: 0.0016 memory: 44138 loss: 0.3667 2023/06/06 11:03:11 - mmengine - INFO - Epoch(train) [8][3500/3907] lr: 1.2107e-05 eta: 1:27:45 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.3717 2023/06/06 11:04:15 - mmengine - INFO - Epoch(train) [8][3600/3907] lr: 1.2058e-05 eta: 1:26:41 time: 0.6374 data_time: 0.0016 memory: 44138 loss: 0.3639 2023/06/06 11:04:47 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:05:18 - mmengine - INFO - Epoch(train) [8][3700/3907] lr: 1.2009e-05 eta: 1:25:37 time: 0.6376 data_time: 0.0018 memory: 44138 loss: 0.3591 2023/06/06 11:06:22 - mmengine - INFO - Epoch(train) [8][3800/3907] lr: 1.1961e-05 eta: 1:24:33 time: 0.6374 data_time: 0.0014 memory: 44138 loss: 0.3854 2023/06/06 11:07:26 - mmengine - INFO - Epoch(train) [8][3900/3907] lr: 1.1914e-05 eta: 1:23:29 time: 0.6368 data_time: 0.0013 memory: 44138 loss: 0.3818 2023/06/06 11:07:30 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:07:30 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/06/06 11:09:11 - mmengine - INFO - Epoch(val) [8][57/57] accuracy/top1: 79.1831 single-label/precision_classwise: [73.12781524658203, 96.55404663085938] single-label/recall_classwise: [98.38394165039062, 55.60464859008789] single-label/f1-score_classwise: [83.89632415771484, 70.56913757324219] data_time: 0.0314 time: 1.2761 2023/06/06 11:10:19 - mmengine - INFO - Epoch(train) [9][ 100/3907] lr: 1.1863e-05 eta: 1:22:21 time: 0.6391 data_time: 0.0017 memory: 44138 loss: 0.3623 2023/06/06 11:11:22 - mmengine - INFO - Epoch(train) [9][ 200/3907] lr: 1.1817e-05 eta: 1:21:17 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3555 2023/06/06 11:12:26 - mmengine - INFO - Epoch(train) [9][ 300/3907] lr: 1.1771e-05 eta: 1:20:13 time: 0.6372 data_time: 0.0017 memory: 44138 loss: 0.3709 2023/06/06 11:13:30 - mmengine - INFO - Epoch(train) [9][ 400/3907] lr: 1.1725e-05 eta: 1:19:09 time: 0.6406 data_time: 0.0014 memory: 44138 loss: 0.3729 2023/06/06 11:14:34 - mmengine - INFO - Epoch(train) [9][ 500/3907] lr: 1.1681e-05 eta: 1:18:05 time: 0.6392 data_time: 0.0015 memory: 44138 loss: 0.3687 2023/06/06 11:15:38 - mmengine - INFO - Epoch(train) [9][ 600/3907] lr: 1.1636e-05 eta: 1:17:01 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.3786 2023/06/06 11:16:42 - mmengine - INFO - Epoch(train) [9][ 700/3907] lr: 1.1592e-05 eta: 1:15:56 time: 0.6362 data_time: 0.0014 memory: 44138 loss: 0.3668 2023/06/06 11:17:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:17:46 - mmengine - INFO - Epoch(train) [9][ 800/3907] lr: 1.1549e-05 eta: 1:14:52 time: 0.6402 data_time: 0.0014 memory: 44138 loss: 0.3583 2023/06/06 11:18:49 - mmengine - INFO - Epoch(train) [9][ 900/3907] lr: 1.1506e-05 eta: 1:13:48 time: 0.6367 data_time: 0.0014 memory: 44138 loss: 0.3795 2023/06/06 11:19:53 - mmengine - INFO - Epoch(train) [9][1000/3907] lr: 1.1464e-05 eta: 1:12:44 time: 0.6377 data_time: 0.0015 memory: 44138 loss: 0.3826 2023/06/06 11:20:57 - mmengine - INFO - Epoch(train) [9][1100/3907] lr: 1.1423e-05 eta: 1:11:40 time: 0.6372 data_time: 0.0014 memory: 44138 loss: 0.3926 2023/06/06 11:22:01 - mmengine - INFO - Epoch(train) [9][1200/3907] lr: 1.1382e-05 eta: 1:10:36 time: 0.6379 data_time: 0.0015 memory: 44138 loss: 0.3772 2023/06/06 11:23:05 - mmengine - INFO - Epoch(train) [9][1300/3907] lr: 1.1341e-05 eta: 1:09:32 time: 0.6378 data_time: 0.0018 memory: 44138 loss: 0.3500 2023/06/06 11:24:09 - mmengine - INFO - Epoch(train) [9][1400/3907] lr: 1.1301e-05 eta: 1:08:28 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3698 2023/06/06 11:25:13 - mmengine - INFO - Epoch(train) [9][1500/3907] lr: 1.1262e-05 eta: 1:07:24 time: 0.6398 data_time: 0.0015 memory: 44138 loss: 0.3839 2023/06/06 11:26:17 - mmengine - INFO - Epoch(train) [9][1600/3907] lr: 1.1223e-05 eta: 1:06:20 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3808 2023/06/06 11:27:20 - mmengine - INFO - Epoch(train) [9][1700/3907] lr: 1.1185e-05 eta: 1:05:15 time: 0.6371 data_time: 0.0014 memory: 44138 loss: 0.3679 2023/06/06 11:27:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:28:24 - mmengine - INFO - Epoch(train) [9][1800/3907] lr: 1.1147e-05 eta: 1:04:11 time: 0.6390 data_time: 0.0015 memory: 44138 loss: 0.3671 2023/06/06 11:29:28 - mmengine - INFO - Epoch(train) [9][1900/3907] lr: 1.1110e-05 eta: 1:03:07 time: 0.6382 data_time: 0.0015 memory: 44138 loss: 0.3607 2023/06/06 11:30:32 - mmengine - INFO - Epoch(train) [9][2000/3907] lr: 1.1073e-05 eta: 1:02:03 time: 0.6375 data_time: 0.0015 memory: 44138 loss: 0.3539 2023/06/06 11:31:36 - mmengine - INFO - Epoch(train) [9][2100/3907] lr: 1.1037e-05 eta: 1:00:59 time: 0.6386 data_time: 0.0014 memory: 44138 loss: 0.3990 2023/06/06 11:32:40 - mmengine - INFO - Epoch(train) [9][2200/3907] lr: 1.1002e-05 eta: 0:59:55 time: 0.6386 data_time: 0.0015 memory: 44138 loss: 0.3768 2023/06/06 11:33:44 - mmengine - INFO - Epoch(train) [9][2300/3907] lr: 1.0967e-05 eta: 0:58:51 time: 0.6383 data_time: 0.0014 memory: 44138 loss: 0.3703 2023/06/06 11:34:47 - mmengine - INFO - Epoch(train) [9][2400/3907] lr: 1.0933e-05 eta: 0:57:47 time: 0.6401 data_time: 0.0014 memory: 44138 loss: 0.3780 2023/06/06 11:35:51 - mmengine - INFO - Epoch(train) [9][2500/3907] lr: 1.0899e-05 eta: 0:56:43 time: 0.6357 data_time: 0.0016 memory: 44138 loss: 0.3759 2023/06/06 11:36:55 - mmengine - INFO - Epoch(train) [9][2600/3907] lr: 1.0866e-05 eta: 0:55:39 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3702 2023/06/06 11:37:59 - mmengine - INFO - Epoch(train) [9][2700/3907] lr: 1.0834e-05 eta: 0:54:35 time: 0.6379 data_time: 0.0014 memory: 44138 loss: 0.3471 2023/06/06 11:38:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:39:03 - mmengine - INFO - Epoch(train) [9][2800/3907] lr: 1.0802e-05 eta: 0:53:31 time: 0.6378 data_time: 0.0015 memory: 44138 loss: 0.4077 2023/06/06 11:40:07 - mmengine - INFO - Epoch(train) [9][2900/3907] lr: 1.0771e-05 eta: 0:52:27 time: 0.6378 data_time: 0.0017 memory: 44138 loss: 0.3521 2023/06/06 11:41:10 - mmengine - INFO - Epoch(train) [9][3000/3907] lr: 1.0740e-05 eta: 0:51:22 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.4087 2023/06/06 11:42:14 - mmengine - INFO - Epoch(train) [9][3100/3907] lr: 1.0710e-05 eta: 0:50:18 time: 0.6535 data_time: 0.0015 memory: 44138 loss: 0.3581 2023/06/06 11:43:18 - mmengine - INFO - Epoch(train) [9][3200/3907] lr: 1.0681e-05 eta: 0:49:14 time: 0.6393 data_time: 0.0014 memory: 44138 loss: 0.3922 2023/06/06 11:44:22 - mmengine - INFO - Epoch(train) [9][3300/3907] lr: 1.0652e-05 eta: 0:48:10 time: 0.6416 data_time: 0.0016 memory: 44138 loss: 0.3732 2023/06/06 11:45:26 - mmengine - INFO - Epoch(train) [9][3400/3907] lr: 1.0624e-05 eta: 0:47:06 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3640 2023/06/06 11:46:29 - mmengine - INFO - Epoch(train) [9][3500/3907] lr: 1.0596e-05 eta: 0:46:02 time: 0.6364 data_time: 0.0016 memory: 44138 loss: 0.3692 2023/06/06 11:47:33 - mmengine - INFO - Epoch(train) [9][3600/3907] lr: 1.0569e-05 eta: 0:44:58 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.3812 2023/06/06 11:48:37 - mmengine - INFO - Epoch(train) [9][3700/3907] lr: 1.0542e-05 eta: 0:43:54 time: 0.6377 data_time: 0.0014 memory: 44138 loss: 0.3598 2023/06/06 11:49:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:49:41 - mmengine - INFO - Epoch(train) [9][3800/3907] lr: 1.0517e-05 eta: 0:42:50 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3529 2023/06/06 11:50:44 - mmengine - INFO - Epoch(train) [9][3900/3907] lr: 1.0491e-05 eta: 0:41:46 time: 0.6387 data_time: 0.0014 memory: 44138 loss: 0.3287 2023/06/06 11:50:48 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 11:50:48 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/06/06 11:52:32 - mmengine - INFO - Epoch(val) [9][57/57] accuracy/top1: 79.1622 single-label/precision_classwise: [73.08341217041016, 96.68963623046875] single-label/recall_classwise: [98.45337677001953, 55.472869873046875] single-label/f1-score_classwise: [83.8923110961914, 70.49898529052734] data_time: 0.0324 time: 1.2746 2023/06/06 11:53:39 - mmengine - INFO - Epoch(train) [10][ 100/3907] lr: 1.0465e-05 eta: 0:40:38 time: 0.6357 data_time: 0.0015 memory: 44138 loss: 0.3764 2023/06/06 11:54:43 - mmengine - INFO - Epoch(train) [10][ 200/3907] lr: 1.0441e-05 eta: 0:39:34 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3857 2023/06/06 11:55:47 - mmengine - INFO - Epoch(train) [10][ 300/3907] lr: 1.0418e-05 eta: 0:38:29 time: 0.6388 data_time: 0.0015 memory: 44138 loss: 0.3529 2023/06/06 11:56:50 - mmengine - INFO - Epoch(train) [10][ 400/3907] lr: 1.0395e-05 eta: 0:37:25 time: 0.6385 data_time: 0.0014 memory: 44138 loss: 0.3618 2023/06/06 11:57:54 - mmengine - INFO - Epoch(train) [10][ 500/3907] lr: 1.0373e-05 eta: 0:36:21 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.3934 2023/06/06 11:58:58 - mmengine - INFO - Epoch(train) [10][ 600/3907] lr: 1.0352e-05 eta: 0:35:17 time: 0.6389 data_time: 0.0015 memory: 44138 loss: 0.3513 2023/06/06 12:00:02 - mmengine - INFO - Epoch(train) [10][ 700/3907] lr: 1.0331e-05 eta: 0:34:13 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3731 2023/06/06 12:01:06 - mmengine - INFO - Epoch(train) [10][ 800/3907] lr: 1.0311e-05 eta: 0:33:09 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3761 2023/06/06 12:01:29 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 12:02:10 - mmengine - INFO - Epoch(train) [10][ 900/3907] lr: 1.0291e-05 eta: 0:32:05 time: 0.6375 data_time: 0.0016 memory: 44138 loss: 0.3635 2023/06/06 12:03:13 - mmengine - INFO - Epoch(train) [10][1000/3907] lr: 1.0272e-05 eta: 0:31:01 time: 0.6390 data_time: 0.0014 memory: 44138 loss: 0.3746 2023/06/06 12:04:17 - mmengine - INFO - Epoch(train) [10][1100/3907] lr: 1.0254e-05 eta: 0:29:57 time: 0.6390 data_time: 0.0016 memory: 44138 loss: 0.3888 2023/06/06 12:05:21 - mmengine - INFO - Epoch(train) [10][1200/3907] lr: 1.0236e-05 eta: 0:28:53 time: 0.6389 data_time: 0.0014 memory: 44138 loss: 0.3702 2023/06/06 12:06:25 - mmengine - INFO - Epoch(train) [10][1300/3907] lr: 1.0219e-05 eta: 0:27:49 time: 0.6363 data_time: 0.0014 memory: 44138 loss: 0.3894 2023/06/06 12:07:29 - mmengine - INFO - Epoch(train) [10][1400/3907] lr: 1.0203e-05 eta: 0:26:45 time: 0.6375 data_time: 0.0016 memory: 44138 loss: 0.3747 2023/06/06 12:08:33 - mmengine - INFO - Epoch(train) [10][1500/3907] lr: 1.0187e-05 eta: 0:25:41 time: 0.6372 data_time: 0.0014 memory: 44138 loss: 0.3911 2023/06/06 12:09:37 - mmengine - INFO - Epoch(train) [10][1600/3907] lr: 1.0172e-05 eta: 0:24:37 time: 0.6711 data_time: 0.0367 memory: 44138 loss: 0.3456 2023/06/06 12:10:45 - mmengine - INFO - Epoch(train) [10][1700/3907] lr: 1.0157e-05 eta: 0:23:33 time: 0.6376 data_time: 0.0014 memory: 44138 loss: 0.3497 2023/06/06 12:12:01 - mmengine - INFO - Epoch(train) [10][1800/3907] lr: 1.0143e-05 eta: 0:22:30 time: 0.6383 data_time: 0.0014 memory: 44138 loss: 0.3668 2023/06/06 12:12:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 12:13:08 - mmengine - INFO - Epoch(train) [10][1900/3907] lr: 1.0130e-05 eta: 0:21:26 time: 0.6493 data_time: 0.0014 memory: 44138 loss: 0.3871 2023/06/06 12:14:13 - mmengine - INFO - Epoch(train) [10][2000/3907] lr: 1.0117e-05 eta: 0:20:22 time: 0.6374 data_time: 0.0014 memory: 44138 loss: 0.3554 2023/06/06 12:15:17 - mmengine - INFO - Epoch(train) [10][2100/3907] lr: 1.0105e-05 eta: 0:19:18 time: 0.6393 data_time: 0.0014 memory: 44138 loss: 0.3578 2023/06/06 12:16:21 - mmengine - INFO - Epoch(train) [10][2200/3907] lr: 1.0094e-05 eta: 0:18:13 time: 0.6389 data_time: 0.0016 memory: 44138 loss: 0.3811 2023/06/06 12:17:25 - mmengine - INFO - Epoch(train) [10][2300/3907] lr: 1.0083e-05 eta: 0:17:09 time: 0.6388 data_time: 0.0015 memory: 44138 loss: 0.3741 2023/06/06 12:18:29 - mmengine - INFO - Epoch(train) [10][2400/3907] lr: 1.0073e-05 eta: 0:16:05 time: 0.6386 data_time: 0.0016 memory: 44138 loss: 0.3670 2023/06/06 12:19:33 - mmengine - INFO - Epoch(train) [10][2500/3907] lr: 1.0064e-05 eta: 0:15:01 time: 0.6420 data_time: 0.0015 memory: 44138 loss: 0.3903 2023/06/06 12:20:37 - mmengine - INFO - Epoch(train) [10][2600/3907] lr: 1.0055e-05 eta: 0:13:57 time: 0.6424 data_time: 0.0017 memory: 44138 loss: 0.3787 2023/06/06 12:21:41 - mmengine - INFO - Epoch(train) [10][2700/3907] lr: 1.0047e-05 eta: 0:12:53 time: 0.6391 data_time: 0.0015 memory: 44138 loss: 0.3845 2023/06/06 12:22:45 - mmengine - INFO - Epoch(train) [10][2800/3907] lr: 1.0040e-05 eta: 0:11:49 time: 0.6374 data_time: 0.0015 memory: 44138 loss: 0.3589 2023/06/06 12:23:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 12:23:49 - mmengine - INFO - Epoch(train) [10][2900/3907] lr: 1.0033e-05 eta: 0:10:45 time: 0.6393 data_time: 0.0015 memory: 44138 loss: 0.3925 2023/06/06 12:24:53 - mmengine - INFO - Epoch(train) [10][3000/3907] lr: 1.0027e-05 eta: 0:09:41 time: 0.6386 data_time: 0.0016 memory: 44138 loss: 0.3934 2023/06/06 12:25:56 - mmengine - INFO - Epoch(train) [10][3100/3907] lr: 1.0021e-05 eta: 0:08:37 time: 0.6383 data_time: 0.0014 memory: 44138 loss: 0.3612 2023/06/06 12:27:00 - mmengine - INFO - Epoch(train) [10][3200/3907] lr: 1.0016e-05 eta: 0:07:33 time: 0.6386 data_time: 0.0015 memory: 44138 loss: 0.3312 2023/06/06 12:28:04 - mmengine - INFO - Epoch(train) [10][3300/3907] lr: 1.0012e-05 eta: 0:06:28 time: 0.6370 data_time: 0.0014 memory: 44138 loss: 0.3677 2023/06/06 12:29:08 - mmengine - INFO - Epoch(train) [10][3400/3907] lr: 1.0008e-05 eta: 0:05:24 time: 0.6383 data_time: 0.0015 memory: 44138 loss: 0.3790 2023/06/06 12:30:12 - mmengine - INFO - Epoch(train) [10][3500/3907] lr: 1.0005e-05 eta: 0:04:20 time: 0.6404 data_time: 0.0017 memory: 44138 loss: 0.3797 2023/06/06 12:31:16 - mmengine - INFO - Epoch(train) [10][3600/3907] lr: 1.0003e-05 eta: 0:03:16 time: 0.6484 data_time: 0.0019 memory: 44138 loss: 0.3576 2023/06/06 12:32:20 - mmengine - INFO - Epoch(train) [10][3700/3907] lr: 1.0001e-05 eta: 0:02:12 time: 0.6407 data_time: 0.0016 memory: 44138 loss: 0.3869 2023/06/06 12:33:24 - mmengine - INFO - Epoch(train) [10][3800/3907] lr: 1.0000e-05 eta: 0:01:08 time: 0.6391 data_time: 0.0015 memory: 44138 loss: 0.3512 2023/06/06 12:33:48 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 12:34:28 - mmengine - INFO - Epoch(train) [10][3900/3907] lr: 1.0000e-05 eta: 0:00:04 time: 0.6382 data_time: 0.0013 memory: 44138 loss: 0.3589 2023/06/06 12:34:32 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_sdv2_lr3e-5_20230606_052112 2023/06/06 12:34:32 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/06/06 12:36:13 - mmengine - INFO - Epoch(val) [10][57/57] accuracy/top1: 78.6646 single-label/precision_classwise: [72.5381851196289, 96.98694610595703] single-label/recall_classwise: [98.63013458251953, 54.14728546142578] single-label/f1-score_classwise: [83.59550476074219, 69.49557495117188] data_time: 0.0317 time: 1.2740