diff --git "a/clip_large_pretrain_4x256_all2_lr1e-4/20230606_005614/20230606_005614.log" "b/clip_large_pretrain_4x256_all2_lr1e-4/20230606_005614/20230606_005614.log" new file mode 100644--- /dev/null +++ "b/clip_large_pretrain_4x256_all2_lr1e-4/20230606_005614/20230606_005614.log" @@ -0,0 +1,1853 @@ +2023/06/06 00:56:18 - 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: 2026736370 + 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 00:56:22 - mmengine - INFO - Config: +optim_wrapper = dict( + optimizer=dict( + type='AdamW', lr=0.0001, weight_decay=0.3, _scope_='mmpretrain'), + paramwise_cfg=dict( + custom_keys=dict({ + '.cls_token': dict(decay_mult=0.0), + '.pos_embed': dict(decay_mult=0.0) + })), + type='AmpOptimWrapper', + dtype='bfloat16', + clip_grad=None) +param_scheduler = [ + dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=False, begin=0) +] +train_cfg = dict(by_epoch=True, max_epochs=10, val_interval=1) +val_cfg = dict() +test_cfg = dict() +auto_scale_lr = dict(base_batch_size=4096) +model = dict( + type='ImageClassifier', + backbone=dict( + frozen_stages=24, + type='VisionTransformer', + arch='l', + img_size=224, + patch_size=14, + drop_rate=0.1, + pre_norm=True, + 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/all_0.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') + ]), + dict( + type='CustomDataset', + data_root='', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/all_1.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') + ]), + dict( + type='CustomDataset', + data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3fake8w.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') + ]), + 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') + ]), + dict( + type='CustomDataset', + data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3real8w.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='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV1-5R2-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='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/if-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='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV1-5R2-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='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/if-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_all2_lr1e-4' + +2023/06/06 00:56:34 - 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 00:56:54 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth +2023/06/06 00:56:56 - 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 00:56:56 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth +2023/06/06 00:56:57 - 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 00:56:57 - 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 00:56:57 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. +2023/06/06 00:56:57 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/luzeyu/workspace/fakebench/mmpretrain/workdir/clip_large_pretrain_4x256_all2_lr1e-4. +2023/06/06 00:58:07 - mmengine - INFO - Epoch(train) [1][ 100/4092] lr: 9.9999e-05 eta: 7:55:06 time: 0.6306 data_time: 0.0018 memory: 44139 loss: 0.5742 +2023/06/06 00:59:11 - mmengine - INFO - Epoch(train) [1][ 200/4092] lr: 9.9995e-05 eta: 7:32:09 time: 0.6331 data_time: 0.0018 memory: 44139 loss: 0.5510 +2023/06/06 01:00:14 - mmengine - INFO - Epoch(train) [1][ 300/4092] lr: 9.9988e-05 eta: 7:23:36 time: 0.6333 data_time: 0.0023 memory: 44139 loss: 0.5507 +2023/06/06 01:01:17 - mmengine - INFO - Epoch(train) [1][ 400/4092] lr: 9.9979e-05 eta: 7:18:35 time: 0.6325 data_time: 0.0017 memory: 44139 loss: 0.5323 +2023/06/06 01:02:21 - mmengine - INFO - Epoch(train) [1][ 500/4092] lr: 9.9967e-05 eta: 7:15:20 time: 0.6465 data_time: 0.0016 memory: 44139 loss: 0.5343 +2023/06/06 01:03:24 - mmengine - INFO - Epoch(train) [1][ 600/4092] lr: 9.9952e-05 eta: 7:13:00 time: 0.6330 data_time: 0.0014 memory: 44139 loss: 0.4938 +2023/06/06 01:04:28 - mmengine - INFO - Epoch(train) [1][ 700/4092] lr: 9.9935e-05 eta: 7:11:00 time: 0.6354 data_time: 0.0016 memory: 44139 loss: 0.5040 +2023/06/06 01:05:31 - mmengine - INFO - Epoch(train) [1][ 800/4092] lr: 9.9915e-05 eta: 7:09:08 time: 0.6346 data_time: 0.0016 memory: 44139 loss: 0.5007 +2023/06/06 01:06:34 - mmengine - INFO - Epoch(train) [1][ 900/4092] lr: 9.9893e-05 eta: 7:07:26 time: 0.6326 data_time: 0.0015 memory: 44139 loss: 0.4955 +2023/06/06 01:07:38 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:07:38 - mmengine - INFO - Epoch(train) [1][1000/4092] lr: 9.9868e-05 eta: 7:05:51 time: 0.6321 data_time: 0.0015 memory: 44139 loss: 0.4976 +2023/06/06 01:08:41 - mmengine - INFO - Epoch(train) [1][1100/4092] lr: 9.9840e-05 eta: 7:04:24 time: 0.6333 data_time: 0.0014 memory: 44139 loss: 0.5405 +2023/06/06 01:09:44 - mmengine - INFO - Epoch(train) [1][1200/4092] lr: 9.9809e-05 eta: 7:03:03 time: 0.6363 data_time: 0.0015 memory: 44139 loss: 0.4754 +2023/06/06 01:10:48 - mmengine - INFO - Epoch(train) [1][1300/4092] lr: 9.9776e-05 eta: 7:01:44 time: 0.6345 data_time: 0.0014 memory: 44139 loss: 0.5028 +2023/06/06 01:11:51 - mmengine - INFO - Epoch(train) [1][1400/4092] lr: 9.9741e-05 eta: 7:00:27 time: 0.6315 data_time: 0.0016 memory: 44139 loss: 0.4924 +2023/06/06 01:12:55 - mmengine - INFO - Epoch(train) [1][1500/4092] lr: 9.9702e-05 eta: 6:59:10 time: 0.6319 data_time: 0.0016 memory: 44139 loss: 0.4951 +2023/06/06 01:13:58 - mmengine - INFO - Epoch(train) [1][1600/4092] lr: 9.9661e-05 eta: 6:57:53 time: 0.6314 data_time: 0.0014 memory: 44139 loss: 0.5086 +2023/06/06 01:15:01 - mmengine - INFO - Epoch(train) [1][1700/4092] lr: 9.9618e-05 eta: 6:56:38 time: 0.6313 data_time: 0.0013 memory: 44139 loss: 0.4961 +2023/06/06 01:16:04 - mmengine - INFO - Epoch(train) [1][1800/4092] lr: 9.9571e-05 eta: 6:55:23 time: 0.6315 data_time: 0.0015 memory: 44139 loss: 0.4864 +2023/06/06 01:17:07 - mmengine - INFO - Epoch(train) [1][1900/4092] lr: 9.9523e-05 eta: 6:54:08 time: 0.6309 data_time: 0.0014 memory: 44139 loss: 0.4863 +2023/06/06 01:18:11 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:18:11 - mmengine - INFO - Epoch(train) [1][2000/4092] lr: 9.9471e-05 eta: 6:52:55 time: 0.6314 data_time: 0.0016 memory: 44139 loss: 0.4824 +2023/06/06 01:19:14 - mmengine - INFO - Epoch(train) [1][2100/4092] lr: 9.9417e-05 eta: 6:51:41 time: 0.6311 data_time: 0.0015 memory: 44139 loss: 0.5120 +2023/06/06 01:20:17 - mmengine - INFO - Epoch(train) [1][2200/4092] lr: 9.9360e-05 eta: 6:50:28 time: 0.6317 data_time: 0.0017 memory: 44139 loss: 0.4707 +2023/06/06 01:21:20 - mmengine - INFO - Epoch(train) [1][2300/4092] lr: 9.9301e-05 eta: 6:49:17 time: 0.6315 data_time: 0.0014 memory: 44139 loss: 0.4904 +2023/06/06 01:22:23 - mmengine - INFO - Epoch(train) [1][2400/4092] lr: 9.9239e-05 eta: 6:48:06 time: 0.6319 data_time: 0.0014 memory: 44139 loss: 0.4934 +2023/06/06 01:23:26 - mmengine - INFO - Epoch(train) [1][2500/4092] lr: 9.9174e-05 eta: 6:46:57 time: 0.6312 data_time: 0.0014 memory: 44139 loss: 0.5018 +2023/06/06 01:24:30 - mmengine - INFO - Epoch(train) [1][2600/4092] lr: 9.9107e-05 eta: 6:45:49 time: 0.6314 data_time: 0.0014 memory: 44139 loss: 0.4846 +2023/06/06 01:25:33 - mmengine - INFO - Epoch(train) [1][2700/4092] lr: 9.9037e-05 eta: 6:44:40 time: 0.6321 data_time: 0.0015 memory: 44139 loss: 0.4840 +2023/06/06 01:27:59 - mmengine - INFO - Epoch(train) [1][2800/4092] lr: 9.8965e-05 eta: 7:02:29 time: 0.6289 data_time: 0.0015 memory: 44139 loss: 0.4953 +2023/06/06 01:29:03 - mmengine - INFO - Epoch(train) [1][2900/4092] lr: 9.8890e-05 eta: 7:00:38 time: 0.6311 data_time: 0.0013 memory: 44139 loss: 0.5100 +2023/06/06 01:30:06 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:30:06 - mmengine - INFO - Epoch(train) [1][3000/4092] lr: 9.8812e-05 eta: 6:58:52 time: 0.6315 data_time: 0.0014 memory: 44139 loss: 0.4527 +2023/06/06 01:31:09 - mmengine - INFO - Epoch(train) [1][3100/4092] lr: 9.8732e-05 eta: 6:57:07 time: 0.6318 data_time: 0.0014 memory: 44139 loss: 0.4773 +2023/06/06 01:32:12 - mmengine - INFO - Epoch(train) [1][3200/4092] lr: 9.8650e-05 eta: 6:55:26 time: 0.6315 data_time: 0.0014 memory: 44139 loss: 0.4770 +2023/06/06 01:33:15 - mmengine - INFO - Epoch(train) [1][3300/4092] lr: 9.8564e-05 eta: 6:53:47 time: 0.6312 data_time: 0.0016 memory: 44139 loss: 0.4589 +2023/06/06 01:34:19 - mmengine - INFO - Epoch(train) [1][3400/4092] lr: 9.8476e-05 eta: 6:52:10 time: 0.6317 data_time: 0.0015 memory: 44139 loss: 0.4754 +2023/06/06 01:35:22 - mmengine - INFO - Epoch(train) [1][3500/4092] lr: 9.8386e-05 eta: 6:50:35 time: 0.6314 data_time: 0.0015 memory: 44139 loss: 0.4615 +2023/06/06 01:36:25 - mmengine - INFO - Epoch(train) [1][3600/4092] lr: 9.8293e-05 eta: 6:49:02 time: 0.6320 data_time: 0.0014 memory: 44139 loss: 0.4558 +2023/06/06 01:37:28 - mmengine - INFO - Epoch(train) [1][3700/4092] lr: 9.8198e-05 eta: 6:47:30 time: 0.6316 data_time: 0.0014 memory: 44139 loss: 0.4740 +2023/06/06 01:38:31 - mmengine - INFO - Epoch(train) [1][3800/4092] lr: 9.8099e-05 eta: 6:46:00 time: 0.6321 data_time: 0.0014 memory: 44139 loss: 0.4786 +2023/06/06 01:39:35 - mmengine - INFO - Epoch(train) [1][3900/4092] lr: 9.7999e-05 eta: 6:44:31 time: 0.6321 data_time: 0.0014 memory: 44139 loss: 0.4451 +2023/06/06 01:40:38 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:40:38 - mmengine - INFO - Epoch(train) [1][4000/4092] lr: 9.7896e-05 eta: 6:43:04 time: 0.6311 data_time: 0.0013 memory: 44139 loss: 0.4625 +2023/06/06 01:41:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:41:36 - mmengine - INFO - Saving checkpoint at 1 epochs +2023/06/06 01:43:59 - mmengine - INFO - Epoch(val) [1][100/119] eta: 0:00:25 time: 1.2878 data_time: 0.0007 memory: 44139 +2023/06/06 01:44:42 - mmengine - INFO - Epoch(val) [1][119/119] accuracy/top1: 71.7806 single-label/precision_classwise: [93.49911499023438, 41.82777404785156] single-label/recall_classwise: [68.91189575195312, 82.34883880615234] single-label/f1-score_classwise: [79.34439086914062, 55.4769287109375] data_time: 0.0222 time: 1.3161 +2023/06/06 01:45:49 - mmengine - INFO - Epoch(train) [2][ 100/4092] lr: 9.7691e-05 eta: 6:40:48 time: 0.6318 data_time: 0.0019 memory: 44140 loss: 0.4436 +2023/06/06 01:46:53 - mmengine - INFO - Epoch(train) [2][ 200/4092] lr: 9.7580e-05 eta: 6:39:23 time: 0.6318 data_time: 0.0014 memory: 44140 loss: 0.4713 +2023/06/06 01:47:56 - mmengine - INFO - Epoch(train) [2][ 300/4092] lr: 9.7467e-05 eta: 6:38:00 time: 0.6340 data_time: 0.0014 memory: 44140 loss: 0.4740 +2023/06/06 01:48:59 - mmengine - INFO - Epoch(train) [2][ 400/4092] lr: 9.7352e-05 eta: 6:36:38 time: 0.6323 data_time: 0.0014 memory: 44140 loss: 0.4599 +2023/06/06 01:50:03 - mmengine - INFO - Epoch(train) [2][ 500/4092] lr: 9.7234e-05 eta: 6:35:18 time: 0.6346 data_time: 0.0014 memory: 44140 loss: 0.4425 +2023/06/06 01:51:06 - mmengine - INFO - Epoch(train) [2][ 600/4092] lr: 9.7113e-05 eta: 6:33:57 time: 0.6318 data_time: 0.0014 memory: 44140 loss: 0.4755 +2023/06/06 01:52:09 - mmengine - INFO - Epoch(train) [2][ 700/4092] lr: 9.6990e-05 eta: 6:32:36 time: 0.6312 data_time: 0.0014 memory: 44140 loss: 0.4483 +2023/06/06 01:53:12 - mmengine - INFO - Epoch(train) [2][ 800/4092] lr: 9.6865e-05 eta: 6:31:16 time: 0.6319 data_time: 0.0014 memory: 44140 loss: 0.4435 +2023/06/06 01:54:15 - mmengine - INFO - Epoch(train) [2][ 900/4092] lr: 9.6737e-05 eta: 6:29:57 time: 0.6316 data_time: 0.0013 memory: 44140 loss: 0.4590 +2023/06/06 01:54:20 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 01:55:19 - mmengine - INFO - Epoch(train) [2][1000/4092] lr: 9.6606e-05 eta: 6:28:39 time: 0.6326 data_time: 0.0013 memory: 44140 loss: 0.4541 +2023/06/06 01:56:22 - mmengine - INFO - Epoch(train) [2][1100/4092] lr: 9.6473e-05 eta: 6:27:21 time: 0.6318 data_time: 0.0015 memory: 44140 loss: 0.4619 +2023/06/06 01:57:25 - mmengine - INFO - Epoch(train) [2][1200/4092] lr: 9.6338e-05 eta: 6:26:03 time: 0.6313 data_time: 0.0013 memory: 44140 loss: 0.4453 +2023/06/06 01:58:28 - mmengine - INFO - Epoch(train) [2][1300/4092] lr: 9.6200e-05 eta: 6:24:46 time: 0.6314 data_time: 0.0016 memory: 44140 loss: 0.4572 +2023/06/06 01:59:31 - mmengine - INFO - Epoch(train) [2][1400/4092] lr: 9.6060e-05 eta: 6:23:29 time: 0.6333 data_time: 0.0015 memory: 44140 loss: 0.4921 +2023/06/06 02:00:35 - mmengine - INFO - Epoch(train) [2][1500/4092] lr: 9.5918e-05 eta: 6:22:13 time: 0.6329 data_time: 0.0017 memory: 44140 loss: 0.4525 +2023/06/06 02:01:38 - mmengine - INFO - Epoch(train) [2][1600/4092] lr: 9.5773e-05 eta: 6:20:58 time: 0.6310 data_time: 0.0015 memory: 44140 loss: 0.4643 +2023/06/06 02:02:41 - mmengine - INFO - Epoch(train) [2][1700/4092] lr: 9.5625e-05 eta: 6:19:43 time: 0.6319 data_time: 0.0015 memory: 44140 loss: 0.4222 +2023/06/06 02:03:44 - mmengine - INFO - Epoch(train) [2][1800/4092] lr: 9.5475e-05 eta: 6:18:28 time: 0.6319 data_time: 0.0014 memory: 44140 loss: 0.4527 +2023/06/06 02:04:47 - mmengine - INFO - Epoch(train) [2][1900/4092] lr: 9.5323e-05 eta: 6:17:14 time: 0.6303 data_time: 0.0016 memory: 44140 loss: 0.4463 +2023/06/06 02:04:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:05:51 - mmengine - INFO - Epoch(train) [2][2000/4092] lr: 9.5169e-05 eta: 6:16:00 time: 0.6329 data_time: 0.0015 memory: 44140 loss: 0.4297 +2023/06/06 02:06:54 - mmengine - INFO - Epoch(train) [2][2100/4092] lr: 9.5012e-05 eta: 6:14:46 time: 0.6331 data_time: 0.0016 memory: 44140 loss: 0.4281 +2023/06/06 02:07:57 - mmengine - INFO - Epoch(train) [2][2200/4092] lr: 9.4853e-05 eta: 6:13:33 time: 0.6313 data_time: 0.0014 memory: 44140 loss: 0.4476 +2023/06/06 02:09:00 - mmengine - INFO - Epoch(train) [2][2300/4092] lr: 9.4691e-05 eta: 6:12:20 time: 0.6314 data_time: 0.0014 memory: 44140 loss: 0.4375 +2023/06/06 02:10:04 - mmengine - INFO - Epoch(train) [2][2400/4092] lr: 9.4527e-05 eta: 6:11:07 time: 0.6311 data_time: 0.0015 memory: 44140 loss: 0.4416 +2023/06/06 02:11:07 - mmengine - INFO - Epoch(train) [2][2500/4092] lr: 9.4361e-05 eta: 6:09:55 time: 0.6314 data_time: 0.0014 memory: 44140 loss: 0.4352 +2023/06/06 02:12:10 - mmengine - INFO - Epoch(train) [2][2600/4092] lr: 9.4192e-05 eta: 6:08:43 time: 0.6314 data_time: 0.0014 memory: 44140 loss: 0.4278 +2023/06/06 02:13:13 - mmengine - INFO - Epoch(train) [2][2700/4092] lr: 9.4021e-05 eta: 6:07:31 time: 0.6318 data_time: 0.0014 memory: 44140 loss: 0.4350 +2023/06/06 02:14:16 - mmengine - INFO - Epoch(train) [2][2800/4092] lr: 9.3848e-05 eta: 6:06:20 time: 0.6315 data_time: 0.0014 memory: 44140 loss: 0.4279 +2023/06/06 02:15:20 - mmengine - INFO - Epoch(train) [2][2900/4092] lr: 9.3672e-05 eta: 6:05:08 time: 0.6311 data_time: 0.0014 memory: 44140 loss: 0.4438 +2023/06/06 02:15:25 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:16:23 - mmengine - INFO - Epoch(train) [2][3000/4092] lr: 9.3495e-05 eta: 6:03:58 time: 0.6320 data_time: 0.0014 memory: 44140 loss: 0.4462 +2023/06/06 02:17:26 - mmengine - INFO - Epoch(train) [2][3100/4092] lr: 9.3315e-05 eta: 6:02:47 time: 0.6315 data_time: 0.0014 memory: 44140 loss: 0.4394 +2023/06/06 02:18:29 - mmengine - INFO - Epoch(train) [2][3200/4092] lr: 9.3132e-05 eta: 6:01:36 time: 0.6344 data_time: 0.0014 memory: 44140 loss: 0.4422 +2023/06/06 02:19:33 - mmengine - INFO - Epoch(train) [2][3300/4092] lr: 9.2948e-05 eta: 6:00:26 time: 0.6315 data_time: 0.0014 memory: 44140 loss: 0.4563 +2023/06/06 02:20:36 - mmengine - INFO - Epoch(train) [2][3400/4092] lr: 9.2761e-05 eta: 5:59:16 time: 0.6312 data_time: 0.0014 memory: 44140 loss: 0.4429 +2023/06/06 02:21:39 - mmengine - INFO - Epoch(train) [2][3500/4092] lr: 9.2572e-05 eta: 5:58:06 time: 0.6410 data_time: 0.0016 memory: 44140 loss: 0.4485 +2023/06/06 02:22:42 - mmengine - INFO - Epoch(train) [2][3600/4092] lr: 9.2381e-05 eta: 5:56:56 time: 0.6309 data_time: 0.0015 memory: 44140 loss: 0.4140 +2023/06/06 02:23:45 - mmengine - INFO - Epoch(train) [2][3700/4092] lr: 9.2187e-05 eta: 5:55:46 time: 0.6325 data_time: 0.0015 memory: 44140 loss: 0.4222 +2023/06/06 02:24:49 - mmengine - INFO - Epoch(train) [2][3800/4092] lr: 9.1991e-05 eta: 5:54:36 time: 0.6321 data_time: 0.0014 memory: 44140 loss: 0.4607 +2023/06/06 02:25:52 - mmengine - INFO - Epoch(train) [2][3900/4092] lr: 9.1794e-05 eta: 5:53:27 time: 0.6330 data_time: 0.0014 memory: 44140 loss: 0.4672 +2023/06/06 02:25:57 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:26:55 - mmengine - INFO - Epoch(train) [2][4000/4092] lr: 9.1594e-05 eta: 5:52:18 time: 0.6318 data_time: 0.0015 memory: 44140 loss: 0.4245 +2023/06/06 02:27:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:27:53 - mmengine - INFO - Saving checkpoint at 2 epochs +2023/06/06 02:30:13 - mmengine - INFO - Epoch(val) [2][100/119] eta: 0:00:24 time: 1.2874 data_time: 0.0007 memory: 44140 +2023/06/06 02:30:56 - mmengine - INFO - Epoch(val) [2][119/119] accuracy/top1: 72.9457 single-label/precision_classwise: [96.08561706542969, 43.52043151855469] single-label/recall_classwise: [68.387939453125, 89.73643493652344] single-label/f1-score_classwise: [79.90460205078125, 58.614139556884766] data_time: 0.0177 time: 1.2847 +2023/06/06 02:32:03 - mmengine - INFO - Epoch(train) [3][ 100/4092] lr: 9.1204e-05 eta: 5:50:17 time: 0.6333 data_time: 0.0015 memory: 44140 loss: 0.4474 +2023/06/06 02:33:06 - mmengine - INFO - Epoch(train) [3][ 200/4092] lr: 9.0997e-05 eta: 5:49:09 time: 0.6336 data_time: 0.0016 memory: 44140 loss: 0.4212 +2023/06/06 02:34:09 - mmengine - INFO - Epoch(train) [3][ 300/4092] lr: 9.0789e-05 eta: 5:48:00 time: 0.6341 data_time: 0.0014 memory: 44140 loss: 0.4284 +2023/06/06 02:35:13 - mmengine - INFO - Epoch(train) [3][ 400/4092] lr: 9.0579e-05 eta: 5:46:52 time: 0.6312 data_time: 0.0014 memory: 44140 loss: 0.4249 +2023/06/06 02:36:16 - mmengine - INFO - Epoch(train) [3][ 500/4092] lr: 9.0366e-05 eta: 5:45:44 time: 0.6338 data_time: 0.0014 memory: 44140 loss: 0.4253 +2023/06/06 02:37:19 - mmengine - INFO - Epoch(train) [3][ 600/4092] lr: 9.0151e-05 eta: 5:44:36 time: 0.6319 data_time: 0.0014 memory: 44140 loss: 0.4409 +2023/06/06 02:38:23 - mmengine - INFO - Epoch(train) [3][ 700/4092] lr: 8.9935e-05 eta: 5:43:28 time: 0.6324 data_time: 0.0014 memory: 44140 loss: 0.4236 +2023/06/06 02:39:26 - mmengine - INFO - Epoch(train) [3][ 800/4092] lr: 8.9716e-05 eta: 5:42:20 time: 0.6361 data_time: 0.0014 memory: 44140 loss: 0.4090 +2023/06/06 02:39:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:40:29 - mmengine - INFO - Epoch(train) [3][ 900/4092] lr: 8.9495e-05 eta: 5:41:13 time: 0.6332 data_time: 0.0016 memory: 44140 loss: 0.4282 +2023/06/06 02:41:33 - mmengine - INFO - Epoch(train) [3][1000/4092] lr: 8.9272e-05 eta: 5:40:05 time: 0.6346 data_time: 0.0016 memory: 44140 loss: 0.4246 +2023/06/06 02:42:36 - mmengine - INFO - Epoch(train) [3][1100/4092] lr: 8.9047e-05 eta: 5:38:58 time: 0.6333 data_time: 0.0014 memory: 44140 loss: 0.4437 +2023/06/06 02:43:40 - mmengine - INFO - Epoch(train) [3][1200/4092] lr: 8.8820e-05 eta: 5:37:51 time: 0.6322 data_time: 0.0013 memory: 44140 loss: 0.4244 +2023/06/06 02:44:43 - mmengine - INFO - Epoch(train) [3][1300/4092] lr: 8.8591e-05 eta: 5:36:44 time: 0.6338 data_time: 0.0014 memory: 44140 loss: 0.4091 +2023/06/06 02:45:46 - mmengine - INFO - Epoch(train) [3][1400/4092] lr: 8.8360e-05 eta: 5:35:36 time: 0.6321 data_time: 0.0014 memory: 44140 loss: 0.4393 +2023/06/06 02:46:50 - mmengine - INFO - Epoch(train) [3][1500/4092] lr: 8.8128e-05 eta: 5:34:29 time: 0.6322 data_time: 0.0013 memory: 44140 loss: 0.4247 +2023/06/06 02:47:53 - mmengine - INFO - Epoch(train) [3][1600/4092] lr: 8.7893e-05 eta: 5:33:22 time: 0.6324 data_time: 0.0016 memory: 44140 loss: 0.4355 +2023/06/06 02:48:57 - mmengine - INFO - Epoch(train) [3][1700/4092] lr: 8.7656e-05 eta: 5:32:15 time: 0.6409 data_time: 0.0016 memory: 44140 loss: 0.4343 +2023/06/06 02:50:00 - mmengine - INFO - Epoch(train) [3][1800/4092] lr: 8.7417e-05 eta: 5:31:08 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4275 +2023/06/06 02:50:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 02:51:03 - mmengine - INFO - Epoch(train) [3][1900/4092] lr: 8.7177e-05 eta: 5:30:01 time: 0.6326 data_time: 0.0017 memory: 44140 loss: 0.4183 +2023/06/06 02:52:06 - mmengine - INFO - Epoch(train) [3][2000/4092] lr: 8.6934e-05 eta: 5:28:53 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4195 +2023/06/06 02:53:10 - mmengine - INFO - Epoch(train) [3][2100/4092] lr: 8.6690e-05 eta: 5:27:46 time: 0.6316 data_time: 0.0015 memory: 44140 loss: 0.4253 +2023/06/06 02:54:13 - mmengine - INFO - Epoch(train) [3][2200/4092] lr: 8.6444e-05 eta: 5:26:39 time: 0.6323 data_time: 0.0016 memory: 44140 loss: 0.4027 +2023/06/06 02:55:16 - mmengine - INFO - Epoch(train) [3][2300/4092] lr: 8.6196e-05 eta: 5:25:33 time: 0.6324 data_time: 0.0014 memory: 44140 loss: 0.4506 +2023/06/06 02:56:20 - mmengine - INFO - Epoch(train) [3][2400/4092] lr: 8.5946e-05 eta: 5:24:26 time: 0.6322 data_time: 0.0014 memory: 44140 loss: 0.4363 +2023/06/06 02:57:23 - mmengine - INFO - Epoch(train) [3][2500/4092] lr: 8.5694e-05 eta: 5:23:20 time: 0.6337 data_time: 0.0016 memory: 44140 loss: 0.4133 +2023/06/06 02:58:26 - mmengine - INFO - Epoch(train) [3][2600/4092] lr: 8.5441e-05 eta: 5:22:13 time: 0.6330 data_time: 0.0015 memory: 44140 loss: 0.4413 +2023/06/06 02:59:30 - mmengine - INFO - Epoch(train) [3][2700/4092] lr: 8.5185e-05 eta: 5:21:07 time: 0.6332 data_time: 0.0014 memory: 44140 loss: 0.4279 +2023/06/06 03:00:33 - mmengine - INFO - Epoch(train) [3][2800/4092] lr: 8.4928e-05 eta: 5:20:00 time: 0.6331 data_time: 0.0014 memory: 44140 loss: 0.4370 +2023/06/06 03:00:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:01:36 - mmengine - INFO - Epoch(train) [3][2900/4092] lr: 8.4669e-05 eta: 5:18:55 time: 0.6357 data_time: 0.0013 memory: 44140 loss: 0.4369 +2023/06/06 03:02:40 - mmengine - INFO - Epoch(train) [3][3000/4092] lr: 8.4409e-05 eta: 5:17:48 time: 0.6355 data_time: 0.0017 memory: 44140 loss: 0.4133 +2023/06/06 03:03:43 - mmengine - INFO - Epoch(train) [3][3100/4092] lr: 8.4146e-05 eta: 5:16:42 time: 0.6321 data_time: 0.0016 memory: 44140 loss: 0.4270 +2023/06/06 03:04:46 - mmengine - INFO - Epoch(train) [3][3200/4092] lr: 8.3882e-05 eta: 5:15:35 time: 0.6318 data_time: 0.0014 memory: 44140 loss: 0.4333 +2023/06/06 03:05:49 - mmengine - INFO - Epoch(train) [3][3300/4092] lr: 8.3616e-05 eta: 5:14:29 time: 0.6341 data_time: 0.0018 memory: 44140 loss: 0.4250 +2023/06/06 03:06:53 - mmengine - INFO - Epoch(train) [3][3400/4092] lr: 8.3349e-05 eta: 5:13:23 time: 0.6464 data_time: 0.0022 memory: 44140 loss: 0.4533 +2023/06/06 03:07:56 - mmengine - INFO - Epoch(train) [3][3500/4092] lr: 8.3080e-05 eta: 5:12:17 time: 0.6343 data_time: 0.0023 memory: 44140 loss: 0.4503 +2023/06/06 03:09:00 - mmengine - INFO - Epoch(train) [3][3600/4092] lr: 8.2809e-05 eta: 5:11:11 time: 0.6343 data_time: 0.0025 memory: 44140 loss: 0.4467 +2023/06/06 03:10:03 - mmengine - INFO - Epoch(train) [3][3700/4092] lr: 8.2537e-05 eta: 5:10:05 time: 0.6328 data_time: 0.0017 memory: 44140 loss: 0.4151 +2023/06/06 03:11:06 - mmengine - INFO - Epoch(train) [3][3800/4092] lr: 8.2263e-05 eta: 5:08:59 time: 0.6329 data_time: 0.0020 memory: 44140 loss: 0.4179 +2023/06/06 03:11:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:12:10 - mmengine - INFO - Epoch(train) [3][3900/4092] lr: 8.1987e-05 eta: 5:07:54 time: 0.6335 data_time: 0.0024 memory: 44140 loss: 0.4292 +2023/06/06 03:13:13 - mmengine - INFO - Epoch(train) [3][4000/4092] lr: 8.1710e-05 eta: 5:06:48 time: 0.6408 data_time: 0.0023 memory: 44140 loss: 0.4231 +2023/06/06 03:14:11 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:14:11 - mmengine - INFO - Saving checkpoint at 3 epochs +2023/06/06 03:16:33 - mmengine - INFO - Epoch(val) [3][100/119] eta: 0:00:24 time: 1.2880 data_time: 0.0010 memory: 44140 +2023/06/06 03:17:16 - mmengine - INFO - Epoch(val) [3][119/119] accuracy/top1: 75.0476 single-label/precision_classwise: [96.72523498535156, 45.76508712768555] single-label/recall_classwise: [70.66683959960938, 91.18605041503906] single-label/f1-score_classwise: [81.6677474975586, 60.943450927734375] data_time: 0.0200 time: 1.2880 +2023/06/06 03:18:23 - mmengine - INFO - Epoch(train) [4][ 100/4092] lr: 8.1173e-05 eta: 5:04:49 time: 0.6323 data_time: 0.0025 memory: 44140 loss: 0.4168 +2023/06/06 03:19:26 - mmengine - INFO - Epoch(train) [4][ 200/4092] lr: 8.0891e-05 eta: 5:03:44 time: 0.6332 data_time: 0.0021 memory: 44140 loss: 0.4294 +2023/06/06 03:20:29 - mmengine - INFO - Epoch(train) [4][ 300/4092] lr: 8.0608e-05 eta: 5:02:38 time: 0.6329 data_time: 0.0024 memory: 44140 loss: 0.4202 +2023/06/06 03:21:32 - mmengine - INFO - Epoch(train) [4][ 400/4092] lr: 8.0323e-05 eta: 5:01:32 time: 0.6330 data_time: 0.0025 memory: 44140 loss: 0.3883 +2023/06/06 03:22:36 - mmengine - INFO - Epoch(train) [4][ 500/4092] lr: 8.0037e-05 eta: 5:00:27 time: 0.6332 data_time: 0.0024 memory: 44140 loss: 0.4146 +2023/06/06 03:23:39 - mmengine - INFO - Epoch(train) [4][ 600/4092] lr: 7.9749e-05 eta: 4:59:21 time: 0.6315 data_time: 0.0022 memory: 44140 loss: 0.4219 +2023/06/06 03:24:43 - mmengine - INFO - Epoch(train) [4][ 700/4092] lr: 7.9459e-05 eta: 4:58:16 time: 0.6348 data_time: 0.0021 memory: 44140 loss: 0.4341 +2023/06/06 03:24:58 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:25:46 - mmengine - INFO - Epoch(train) [4][ 800/4092] lr: 7.9169e-05 eta: 4:57:10 time: 0.6324 data_time: 0.0020 memory: 44140 loss: 0.4551 +2023/06/06 03:26:49 - mmengine - INFO - Epoch(train) [4][ 900/4092] lr: 7.8877e-05 eta: 4:56:04 time: 0.6329 data_time: 0.0018 memory: 44140 loss: 0.4364 +2023/06/06 03:27:53 - mmengine - INFO - Epoch(train) [4][1000/4092] lr: 7.8583e-05 eta: 4:54:59 time: 0.6334 data_time: 0.0019 memory: 44140 loss: 0.4265 +2023/06/06 03:28:56 - mmengine - INFO - Epoch(train) [4][1100/4092] lr: 7.8288e-05 eta: 4:53:53 time: 0.6325 data_time: 0.0022 memory: 44140 loss: 0.4444 +2023/06/06 03:29:59 - mmengine - INFO - Epoch(train) [4][1200/4092] lr: 7.7992e-05 eta: 4:52:48 time: 0.6307 data_time: 0.0021 memory: 44140 loss: 0.4278 +2023/06/06 03:31:03 - mmengine - INFO - Epoch(train) [4][1300/4092] lr: 7.7694e-05 eta: 4:51:43 time: 0.6340 data_time: 0.0019 memory: 44140 loss: 0.4094 +2023/06/06 03:32:06 - mmengine - INFO - Epoch(train) [4][1400/4092] lr: 7.7395e-05 eta: 4:50:38 time: 0.6329 data_time: 0.0024 memory: 44140 loss: 0.4303 +2023/06/06 03:33:10 - mmengine - INFO - Epoch(train) [4][1500/4092] lr: 7.7095e-05 eta: 4:49:32 time: 0.6322 data_time: 0.0020 memory: 44140 loss: 0.4366 +2023/06/06 03:34:13 - mmengine - INFO - Epoch(train) [4][1600/4092] lr: 7.6793e-05 eta: 4:48:27 time: 0.6337 data_time: 0.0027 memory: 44140 loss: 0.4132 +2023/06/06 03:35:16 - mmengine - INFO - Epoch(train) [4][1700/4092] lr: 7.6490e-05 eta: 4:47:22 time: 0.6324 data_time: 0.0019 memory: 44140 loss: 0.4383 +2023/06/06 03:35:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:36:20 - mmengine - INFO - Epoch(train) [4][1800/4092] lr: 7.6186e-05 eta: 4:46:17 time: 0.6326 data_time: 0.0023 memory: 44140 loss: 0.4211 +2023/06/06 03:37:23 - mmengine - INFO - Epoch(train) [4][1900/4092] lr: 7.5881e-05 eta: 4:45:12 time: 0.6322 data_time: 0.0024 memory: 44140 loss: 0.4364 +2023/06/06 03:38:27 - mmengine - INFO - Epoch(train) [4][2000/4092] lr: 7.5574e-05 eta: 4:44:07 time: 0.6362 data_time: 0.0024 memory: 44140 loss: 0.4302 +2023/06/06 03:39:30 - mmengine - INFO - Epoch(train) [4][2100/4092] lr: 7.5266e-05 eta: 4:43:01 time: 0.6330 data_time: 0.0019 memory: 44140 loss: 0.4075 +2023/06/06 03:40:33 - mmengine - INFO - Epoch(train) [4][2200/4092] lr: 7.4957e-05 eta: 4:41:56 time: 0.6322 data_time: 0.0024 memory: 44140 loss: 0.4017 +2023/06/06 03:41:36 - mmengine - INFO - Epoch(train) [4][2300/4092] lr: 7.4647e-05 eta: 4:40:51 time: 0.6337 data_time: 0.0032 memory: 44140 loss: 0.4278 +2023/06/06 03:42:40 - mmengine - INFO - Epoch(train) [4][2400/4092] lr: 7.4336e-05 eta: 4:39:46 time: 0.6332 data_time: 0.0020 memory: 44140 loss: 0.4448 +2023/06/06 03:43:43 - mmengine - INFO - Epoch(train) [4][2500/4092] lr: 7.4023e-05 eta: 4:38:40 time: 0.6318 data_time: 0.0019 memory: 44140 loss: 0.4192 +2023/06/06 03:44:46 - mmengine - INFO - Epoch(train) [4][2600/4092] lr: 7.3709e-05 eta: 4:37:35 time: 0.6316 data_time: 0.0019 memory: 44140 loss: 0.4232 +2023/06/06 03:45:50 - mmengine - INFO - Epoch(train) [4][2700/4092] lr: 7.3395e-05 eta: 4:36:30 time: 0.6323 data_time: 0.0023 memory: 44140 loss: 0.4666 +2023/06/06 03:46:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:46:53 - mmengine - INFO - Epoch(train) [4][2800/4092] lr: 7.3079e-05 eta: 4:35:25 time: 0.6315 data_time: 0.0021 memory: 44140 loss: 0.4382 +2023/06/06 03:47:56 - mmengine - INFO - Epoch(train) [4][2900/4092] lr: 7.2762e-05 eta: 4:34:21 time: 0.6321 data_time: 0.0024 memory: 44140 loss: 0.3834 +2023/06/06 03:49:00 - mmengine - INFO - Epoch(train) [4][3000/4092] lr: 7.2444e-05 eta: 4:33:16 time: 0.6340 data_time: 0.0031 memory: 44140 loss: 0.4198 +2023/06/06 03:50:03 - mmengine - INFO - Epoch(train) [4][3100/4092] lr: 7.2125e-05 eta: 4:32:11 time: 0.6334 data_time: 0.0026 memory: 44140 loss: 0.4397 +2023/06/06 03:51:07 - mmengine - INFO - Epoch(train) [4][3200/4092] lr: 7.1805e-05 eta: 4:31:06 time: 0.6322 data_time: 0.0020 memory: 44140 loss: 0.4347 +2023/06/06 03:52:10 - mmengine - INFO - Epoch(train) [4][3300/4092] lr: 7.1484e-05 eta: 4:30:01 time: 0.6348 data_time: 0.0026 memory: 44140 loss: 0.4178 +2023/06/06 03:53:13 - mmengine - INFO - Epoch(train) [4][3400/4092] lr: 7.1162e-05 eta: 4:28:56 time: 0.6323 data_time: 0.0019 memory: 44140 loss: 0.4433 +2023/06/06 03:54:17 - mmengine - INFO - Epoch(train) [4][3500/4092] lr: 7.0839e-05 eta: 4:27:51 time: 0.6344 data_time: 0.0024 memory: 44140 loss: 0.4336 +2023/06/06 03:55:20 - mmengine - INFO - Epoch(train) [4][3600/4092] lr: 7.0515e-05 eta: 4:26:46 time: 0.6330 data_time: 0.0022 memory: 44140 loss: 0.4535 +2023/06/06 03:56:23 - mmengine - INFO - Epoch(train) [4][3700/4092] lr: 7.0191e-05 eta: 4:25:42 time: 0.6319 data_time: 0.0023 memory: 44140 loss: 0.4276 +2023/06/06 03:56:39 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 03:57:27 - mmengine - INFO - Epoch(train) [4][3800/4092] lr: 6.9865e-05 eta: 4:24:37 time: 0.6330 data_time: 0.0022 memory: 44140 loss: 0.4230 +2023/06/06 03:58:30 - mmengine - INFO - Epoch(train) [4][3900/4092] lr: 6.9538e-05 eta: 4:23:32 time: 0.6325 data_time: 0.0019 memory: 44140 loss: 0.4415 +2023/06/06 03:59:33 - mmengine - INFO - Epoch(train) [4][4000/4092] lr: 6.9211e-05 eta: 4:22:27 time: 0.6328 data_time: 0.0024 memory: 44140 loss: 0.4170 +2023/06/06 04:00:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:00:31 - mmengine - INFO - Saving checkpoint at 4 epochs +2023/06/06 04:02:53 - mmengine - INFO - Epoch(val) [4][100/119] eta: 0:00:24 time: 1.2892 data_time: 0.0009 memory: 44140 +2023/06/06 04:03:36 - mmengine - INFO - Epoch(val) [4][119/119] accuracy/top1: 77.1925 single-label/precision_classwise: [96.76256561279297, 48.19059371948242] single-label/recall_classwise: [73.45916748046875, 90.94573974609375] single-label/f1-score_classwise: [83.5157470703125, 62.99905776977539] data_time: 0.0182 time: 1.2875 +2023/06/06 04:04:43 - mmengine - INFO - Epoch(train) [5][ 100/4092] lr: 6.8580e-05 eta: 4:20:27 time: 0.6321 data_time: 0.0017 memory: 44140 loss: 0.4497 +2023/06/06 04:05:46 - mmengine - INFO - Epoch(train) [5][ 200/4092] lr: 6.8250e-05 eta: 4:19:22 time: 0.6332 data_time: 0.0017 memory: 44140 loss: 0.4209 +2023/06/06 04:06:49 - mmengine - INFO - Epoch(train) [5][ 300/4092] lr: 6.7920e-05 eta: 4:18:18 time: 0.6322 data_time: 0.0021 memory: 44140 loss: 0.4413 +2023/06/06 04:07:53 - mmengine - INFO - Epoch(train) [5][ 400/4092] lr: 6.7588e-05 eta: 4:17:13 time: 0.6328 data_time: 0.0022 memory: 44140 loss: 0.4384 +2023/06/06 04:08:56 - mmengine - INFO - Epoch(train) [5][ 500/4092] lr: 6.7256e-05 eta: 4:16:08 time: 0.6331 data_time: 0.0025 memory: 44140 loss: 0.4339 +2023/06/06 04:09:59 - mmengine - INFO - Epoch(train) [5][ 600/4092] lr: 6.6924e-05 eta: 4:15:04 time: 0.6321 data_time: 0.0015 memory: 44140 loss: 0.4453 +2023/06/06 04:10:19 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:11:02 - mmengine - INFO - Epoch(train) [5][ 700/4092] lr: 6.6590e-05 eta: 4:13:59 time: 0.6323 data_time: 0.0017 memory: 44140 loss: 0.4455 +2023/06/06 04:12:06 - mmengine - INFO - Epoch(train) [5][ 800/4092] lr: 6.6256e-05 eta: 4:12:54 time: 0.6320 data_time: 0.0015 memory: 44140 loss: 0.4187 +2023/06/06 04:13:09 - mmengine - INFO - Epoch(train) [5][ 900/4092] lr: 6.5921e-05 eta: 4:11:49 time: 0.6345 data_time: 0.0015 memory: 44140 loss: 0.4166 +2023/06/06 04:14:12 - mmengine - INFO - Epoch(train) [5][1000/4092] lr: 6.5586e-05 eta: 4:10:45 time: 0.6343 data_time: 0.0024 memory: 44140 loss: 0.4171 +2023/06/06 04:15:16 - mmengine - INFO - Epoch(train) [5][1100/4092] lr: 6.5250e-05 eta: 4:09:40 time: 0.6327 data_time: 0.0015 memory: 44140 loss: 0.4422 +2023/06/06 04:16:19 - mmengine - INFO - Epoch(train) [5][1200/4092] lr: 6.4913e-05 eta: 4:08:36 time: 0.6323 data_time: 0.0014 memory: 44140 loss: 0.4665 +2023/06/06 04:17:23 - mmengine - INFO - Epoch(train) [5][1300/4092] lr: 6.4576e-05 eta: 4:07:31 time: 0.6342 data_time: 0.0018 memory: 44140 loss: 0.4295 +2023/06/06 04:18:26 - mmengine - INFO - Epoch(train) [5][1400/4092] lr: 6.4238e-05 eta: 4:06:27 time: 0.6336 data_time: 0.0015 memory: 44140 loss: 0.4353 +2023/06/06 04:19:29 - mmengine - INFO - Epoch(train) [5][1500/4092] lr: 6.3899e-05 eta: 4:05:22 time: 0.6321 data_time: 0.0017 memory: 44140 loss: 0.4146 +2023/06/06 04:20:33 - mmengine - INFO - Epoch(train) [5][1600/4092] lr: 6.3560e-05 eta: 4:04:17 time: 0.6318 data_time: 0.0015 memory: 44140 loss: 0.4556 +2023/06/06 04:20:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:21:36 - mmengine - INFO - Epoch(train) [5][1700/4092] lr: 6.3221e-05 eta: 4:03:13 time: 0.6337 data_time: 0.0015 memory: 44140 loss: 0.4441 +2023/06/06 04:22:39 - mmengine - INFO - Epoch(train) [5][1800/4092] lr: 6.2881e-05 eta: 4:02:08 time: 0.6334 data_time: 0.0015 memory: 44140 loss: 0.4030 +2023/06/06 04:23:43 - mmengine - INFO - Epoch(train) [5][1900/4092] lr: 6.2541e-05 eta: 4:01:04 time: 0.6325 data_time: 0.0015 memory: 44140 loss: 0.4508 +2023/06/06 04:24:46 - mmengine - INFO - Epoch(train) [5][2000/4092] lr: 6.2200e-05 eta: 4:00:00 time: 0.6371 data_time: 0.0016 memory: 44140 loss: 0.4132 +2023/06/06 04:25:50 - mmengine - INFO - Epoch(train) [5][2100/4092] lr: 6.1859e-05 eta: 3:58:56 time: 0.6336 data_time: 0.0017 memory: 44140 loss: 0.4684 +2023/06/06 04:26:53 - mmengine - INFO - Epoch(train) [5][2200/4092] lr: 6.1517e-05 eta: 3:57:51 time: 0.6357 data_time: 0.0020 memory: 44140 loss: 0.4058 +2023/06/06 04:27:57 - mmengine - INFO - Epoch(train) [5][2300/4092] lr: 6.1175e-05 eta: 3:56:47 time: 0.6328 data_time: 0.0016 memory: 44140 loss: 0.4473 +2023/06/06 04:29:00 - mmengine - INFO - Epoch(train) [5][2400/4092] lr: 6.0833e-05 eta: 3:55:43 time: 0.6336 data_time: 0.0016 memory: 44140 loss: 0.4328 +2023/06/06 04:30:04 - mmengine - INFO - Epoch(train) [5][2500/4092] lr: 6.0490e-05 eta: 3:54:38 time: 0.6354 data_time: 0.0015 memory: 44140 loss: 0.4395 +2023/06/06 04:31:07 - mmengine - INFO - Epoch(train) [5][2600/4092] lr: 6.0147e-05 eta: 3:53:34 time: 0.6356 data_time: 0.0015 memory: 44140 loss: 0.4286 +2023/06/06 04:31:28 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:32:11 - mmengine - INFO - Epoch(train) [5][2700/4092] lr: 5.9803e-05 eta: 3:52:30 time: 0.6328 data_time: 0.0013 memory: 44140 loss: 0.4076 +2023/06/06 04:33:14 - mmengine - INFO - Epoch(train) [5][2800/4092] lr: 5.9460e-05 eta: 3:51:26 time: 0.6349 data_time: 0.0015 memory: 44140 loss: 0.4158 +2023/06/06 04:34:18 - mmengine - INFO - Epoch(train) [5][2900/4092] lr: 5.9116e-05 eta: 3:50:21 time: 0.6347 data_time: 0.0014 memory: 44140 loss: 0.4413 +2023/06/06 04:35:21 - mmengine - INFO - Epoch(train) [5][3000/4092] lr: 5.8772e-05 eta: 3:49:17 time: 0.6336 data_time: 0.0014 memory: 44140 loss: 0.4374 +2023/06/06 04:36:25 - mmengine - INFO - Epoch(train) [5][3100/4092] lr: 5.8427e-05 eta: 3:48:13 time: 0.6353 data_time: 0.0015 memory: 44140 loss: 0.4362 +2023/06/06 04:37:28 - mmengine - INFO - Epoch(train) [5][3200/4092] lr: 5.8083e-05 eta: 3:47:09 time: 0.6328 data_time: 0.0018 memory: 44140 loss: 0.4268 +2023/06/06 04:38:31 - mmengine - INFO - Epoch(train) [5][3300/4092] lr: 5.7738e-05 eta: 3:46:04 time: 0.6329 data_time: 0.0015 memory: 44140 loss: 0.4766 +2023/06/06 04:39:35 - mmengine - INFO - Epoch(train) [5][3400/4092] lr: 5.7393e-05 eta: 3:45:00 time: 0.6352 data_time: 0.0024 memory: 44140 loss: 0.4457 +2023/06/06 04:40:38 - mmengine - INFO - Epoch(train) [5][3500/4092] lr: 5.7048e-05 eta: 3:43:56 time: 0.6324 data_time: 0.0018 memory: 44140 loss: 0.4370 +2023/06/06 04:41:42 - mmengine - INFO - Epoch(train) [5][3600/4092] lr: 5.6703e-05 eta: 3:42:51 time: 0.6327 data_time: 0.0023 memory: 44140 loss: 0.4330 +2023/06/06 04:42:02 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:42:45 - mmengine - INFO - Epoch(train) [5][3700/4092] lr: 5.6358e-05 eta: 3:41:47 time: 0.6361 data_time: 0.0019 memory: 44140 loss: 0.4219 +2023/06/06 04:43:49 - mmengine - INFO - Epoch(train) [5][3800/4092] lr: 5.6012e-05 eta: 3:40:43 time: 0.6338 data_time: 0.0017 memory: 44140 loss: 0.4352 +2023/06/06 04:44:52 - mmengine - INFO - Epoch(train) [5][3900/4092] lr: 5.5667e-05 eta: 3:39:39 time: 0.6346 data_time: 0.0023 memory: 44140 loss: 0.4157 +2023/06/06 04:45:55 - mmengine - INFO - Epoch(train) [5][4000/4092] lr: 5.5321e-05 eta: 3:38:35 time: 0.6326 data_time: 0.0014 memory: 44140 loss: 0.4114 +2023/06/06 04:46:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:46:53 - mmengine - INFO - Saving checkpoint at 5 epochs +2023/06/06 04:49:14 - mmengine - INFO - Epoch(val) [5][100/119] eta: 0:00:24 time: 1.2875 data_time: 0.0007 memory: 44140 +2023/06/06 04:49:57 - mmengine - INFO - Epoch(val) [5][119/119] accuracy/top1: 79.0411 single-label/precision_classwise: [96.61665344238281, 50.51228332519531] single-label/recall_classwise: [76.01371765136719, 90.19379425048828] single-label/f1-score_classwise: [85.08573150634766, 64.75760650634766] data_time: 0.0182 time: 1.2853 +2023/06/06 04:51:04 - mmengine - INFO - Epoch(train) [6][ 100/4092] lr: 5.4658e-05 eta: 3:36:35 time: 0.6321 data_time: 0.0014 memory: 44140 loss: 0.3863 +2023/06/06 04:52:08 - mmengine - INFO - Epoch(train) [6][ 200/4092] lr: 5.4313e-05 eta: 3:35:30 time: 0.6337 data_time: 0.0015 memory: 44140 loss: 0.4308 +2023/06/06 04:53:11 - mmengine - INFO - Epoch(train) [6][ 300/4092] lr: 5.3967e-05 eta: 3:34:26 time: 0.6327 data_time: 0.0016 memory: 44140 loss: 0.4431 +2023/06/06 04:54:14 - mmengine - INFO - Epoch(train) [6][ 400/4092] lr: 5.3622e-05 eta: 3:33:22 time: 0.6327 data_time: 0.0014 memory: 44140 loss: 0.4252 +2023/06/06 04:55:18 - mmengine - INFO - Epoch(train) [6][ 500/4092] lr: 5.3276e-05 eta: 3:32:17 time: 0.6334 data_time: 0.0014 memory: 44140 loss: 0.4332 +2023/06/06 04:55:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 04:56:21 - mmengine - INFO - Epoch(train) [6][ 600/4092] lr: 5.2931e-05 eta: 3:31:13 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4298 +2023/06/06 04:57:24 - mmengine - INFO - Epoch(train) [6][ 700/4092] lr: 5.2586e-05 eta: 3:30:09 time: 0.6339 data_time: 0.0015 memory: 44140 loss: 0.4453 +2023/06/06 04:58:28 - mmengine - INFO - Epoch(train) [6][ 800/4092] lr: 5.2241e-05 eta: 3:29:05 time: 0.6310 data_time: 0.0014 memory: 44140 loss: 0.4186 +2023/06/06 04:59:31 - mmengine - INFO - Epoch(train) [6][ 900/4092] lr: 5.1897e-05 eta: 3:28:00 time: 0.6324 data_time: 0.0015 memory: 44140 loss: 0.4301 +2023/06/06 05:00:34 - mmengine - INFO - Epoch(train) [6][1000/4092] lr: 5.1552e-05 eta: 3:26:56 time: 0.6323 data_time: 0.0018 memory: 44140 loss: 0.4261 +2023/06/06 05:01:37 - mmengine - INFO - Epoch(train) [6][1100/4092] lr: 5.1208e-05 eta: 3:25:52 time: 0.6319 data_time: 0.0023 memory: 44140 loss: 0.4062 +2023/06/06 05:02:41 - mmengine - INFO - Epoch(train) [6][1200/4092] lr: 5.0864e-05 eta: 3:24:48 time: 0.6329 data_time: 0.0017 memory: 44140 loss: 0.4500 +2023/06/06 05:03:44 - mmengine - INFO - Epoch(train) [6][1300/4092] lr: 5.0520e-05 eta: 3:23:43 time: 0.6339 data_time: 0.0015 memory: 44140 loss: 0.4262 +2023/06/06 05:04:47 - mmengine - INFO - Epoch(train) [6][1400/4092] lr: 5.0176e-05 eta: 3:22:39 time: 0.6331 data_time: 0.0017 memory: 44140 loss: 0.3823 +2023/06/06 05:05:51 - mmengine - INFO - Epoch(train) [6][1500/4092] lr: 4.9833e-05 eta: 3:21:35 time: 0.6337 data_time: 0.0016 memory: 44140 loss: 0.4539 +2023/06/06 05:06:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:06:54 - mmengine - INFO - Epoch(train) [6][1600/4092] lr: 4.9490e-05 eta: 3:20:31 time: 0.6321 data_time: 0.0018 memory: 44140 loss: 0.4357 +2023/06/06 05:07:57 - mmengine - INFO - Epoch(train) [6][1700/4092] lr: 4.9147e-05 eta: 3:19:26 time: 0.6327 data_time: 0.0015 memory: 44140 loss: 0.4344 +2023/06/06 05:09:01 - mmengine - INFO - Epoch(train) [6][1800/4092] lr: 4.8805e-05 eta: 3:18:22 time: 0.6333 data_time: 0.0014 memory: 44140 loss: 0.4336 +2023/06/06 05:10:04 - mmengine - INFO - Epoch(train) [6][1900/4092] lr: 4.8462e-05 eta: 3:17:18 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4356 +2023/06/06 05:11:07 - mmengine - INFO - Epoch(train) [6][2000/4092] lr: 4.8121e-05 eta: 3:16:14 time: 0.6333 data_time: 0.0014 memory: 44140 loss: 0.4078 +2023/06/06 05:12:11 - mmengine - INFO - Epoch(train) [6][2100/4092] lr: 4.7780e-05 eta: 3:15:10 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4258 +2023/06/06 05:13:14 - mmengine - INFO - Epoch(train) [6][2200/4092] lr: 4.7439e-05 eta: 3:14:06 time: 0.6323 data_time: 0.0016 memory: 44140 loss: 0.4239 +2023/06/06 05:14:17 - mmengine - INFO - Epoch(train) [6][2300/4092] lr: 4.7099e-05 eta: 3:13:02 time: 0.6332 data_time: 0.0015 memory: 44140 loss: 0.4572 +2023/06/06 05:15:21 - mmengine - INFO - Epoch(train) [6][2400/4092] lr: 4.6759e-05 eta: 3:11:57 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4410 +2023/06/06 05:16:24 - mmengine - INFO - Epoch(train) [6][2500/4092] lr: 4.6419e-05 eta: 3:10:53 time: 0.6344 data_time: 0.0017 memory: 44140 loss: 0.4452 +2023/06/06 05:16:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:17:27 - mmengine - INFO - Epoch(train) [6][2600/4092] lr: 4.6080e-05 eta: 3:09:49 time: 0.6324 data_time: 0.0024 memory: 44140 loss: 0.4552 +2023/06/06 05:18:31 - mmengine - INFO - Epoch(train) [6][2700/4092] lr: 4.5742e-05 eta: 3:08:45 time: 0.6334 data_time: 0.0014 memory: 44140 loss: 0.4126 +2023/06/06 05:19:34 - mmengine - INFO - Epoch(train) [6][2800/4092] lr: 4.5404e-05 eta: 3:07:41 time: 0.6323 data_time: 0.0014 memory: 44140 loss: 0.3934 +2023/06/06 05:20:37 - mmengine - INFO - Epoch(train) [6][2900/4092] lr: 4.5067e-05 eta: 3:06:37 time: 0.6365 data_time: 0.0015 memory: 44140 loss: 0.4579 +2023/06/06 05:21:41 - mmengine - INFO - Epoch(train) [6][3000/4092] lr: 4.4730e-05 eta: 3:05:33 time: 0.6339 data_time: 0.0016 memory: 44140 loss: 0.4238 +2023/06/06 05:22:44 - mmengine - INFO - Epoch(train) [6][3100/4092] lr: 4.4394e-05 eta: 3:04:29 time: 0.6327 data_time: 0.0016 memory: 44140 loss: 0.4227 +2023/06/06 05:23:47 - mmengine - INFO - Epoch(train) [6][3200/4092] lr: 4.4059e-05 eta: 3:03:25 time: 0.6359 data_time: 0.0020 memory: 44140 loss: 0.4336 +2023/06/06 05:24:51 - mmengine - INFO - Epoch(train) [6][3300/4092] lr: 4.3724e-05 eta: 3:02:21 time: 0.6328 data_time: 0.0015 memory: 44140 loss: 0.4338 +2023/06/06 05:25:54 - mmengine - INFO - Epoch(train) [6][3400/4092] lr: 4.3390e-05 eta: 3:01:16 time: 0.6324 data_time: 0.0019 memory: 44140 loss: 0.4539 +2023/06/06 05:26:57 - mmengine - INFO - Epoch(train) [6][3500/4092] lr: 4.3056e-05 eta: 3:00:12 time: 0.6344 data_time: 0.0016 memory: 44140 loss: 0.4467 +2023/06/06 05:27:23 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:28:01 - mmengine - INFO - Epoch(train) [6][3600/4092] lr: 4.2724e-05 eta: 2:59:08 time: 0.6322 data_time: 0.0018 memory: 44140 loss: 0.4293 +2023/06/06 05:29:04 - mmengine - INFO - Epoch(train) [6][3700/4092] lr: 4.2392e-05 eta: 2:58:04 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4475 +2023/06/06 05:30:08 - mmengine - INFO - Epoch(train) [6][3800/4092] lr: 4.2060e-05 eta: 2:57:00 time: 0.6326 data_time: 0.0017 memory: 44140 loss: 0.4637 +2023/06/06 05:31:11 - mmengine - INFO - Epoch(train) [6][3900/4092] lr: 4.1730e-05 eta: 2:55:56 time: 0.6341 data_time: 0.0018 memory: 44140 loss: 0.4521 +2023/06/06 05:32:14 - mmengine - INFO - Epoch(train) [6][4000/4092] lr: 4.1400e-05 eta: 2:54:52 time: 0.6329 data_time: 0.0015 memory: 44140 loss: 0.4264 +2023/06/06 05:33:12 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:33:12 - mmengine - INFO - Saving checkpoint at 6 epochs +2023/06/06 05:35:33 - mmengine - INFO - Epoch(val) [6][100/119] eta: 0:00:24 time: 1.2877 data_time: 0.0007 memory: 44140 +2023/06/06 05:36:16 - mmengine - INFO - Epoch(val) [6][119/119] accuracy/top1: 80.9394 single-label/precision_classwise: [96.39708709716797, 53.19827651977539] single-label/recall_classwise: [78.7071533203125, 89.16278839111328] single-label/f1-score_classwise: [86.6585464477539, 66.6376953125] data_time: 0.0175 time: 1.2862 +2023/06/06 05:37:22 - mmengine - INFO - Epoch(train) [7][ 100/4092] lr: 4.0769e-05 eta: 2:52:51 time: 0.6331 data_time: 0.0016 memory: 44140 loss: 0.4452 +2023/06/06 05:38:26 - mmengine - INFO - Epoch(train) [7][ 200/4092] lr: 4.0442e-05 eta: 2:51:47 time: 0.6327 data_time: 0.0015 memory: 44140 loss: 0.4411 +2023/06/06 05:39:29 - mmengine - INFO - Epoch(train) [7][ 300/4092] lr: 4.0116e-05 eta: 2:50:43 time: 0.6337 data_time: 0.0015 memory: 44140 loss: 0.4431 +2023/06/06 05:40:32 - mmengine - INFO - Epoch(train) [7][ 400/4092] lr: 3.9790e-05 eta: 2:49:39 time: 0.6330 data_time: 0.0014 memory: 44140 loss: 0.4064 +2023/06/06 05:41:03 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:41:36 - mmengine - INFO - Epoch(train) [7][ 500/4092] lr: 3.9465e-05 eta: 2:48:35 time: 0.6327 data_time: 0.0021 memory: 44140 loss: 0.4140 +2023/06/06 05:42:39 - mmengine - INFO - Epoch(train) [7][ 600/4092] lr: 3.9141e-05 eta: 2:47:31 time: 0.6324 data_time: 0.0015 memory: 44140 loss: 0.4600 +2023/06/06 05:43:43 - mmengine - INFO - Epoch(train) [7][ 700/4092] lr: 3.8819e-05 eta: 2:46:27 time: 0.6326 data_time: 0.0014 memory: 44140 loss: 0.4257 +2023/06/06 05:44:46 - mmengine - INFO - Epoch(train) [7][ 800/4092] lr: 3.8497e-05 eta: 2:45:23 time: 0.6328 data_time: 0.0015 memory: 44140 loss: 0.4564 +2023/06/06 05:45:49 - mmengine - INFO - Epoch(train) [7][ 900/4092] lr: 3.8176e-05 eta: 2:44:19 time: 0.6324 data_time: 0.0014 memory: 44140 loss: 0.4589 +2023/06/06 05:46:52 - mmengine - INFO - Epoch(train) [7][1000/4092] lr: 3.7856e-05 eta: 2:43:15 time: 0.6321 data_time: 0.0024 memory: 44140 loss: 0.4382 +2023/06/06 05:47:56 - mmengine - INFO - Epoch(train) [7][1100/4092] lr: 3.7537e-05 eta: 2:42:11 time: 0.6317 data_time: 0.0019 memory: 44140 loss: 0.4153 +2023/06/06 05:48:59 - mmengine - INFO - Epoch(train) [7][1200/4092] lr: 3.7219e-05 eta: 2:41:07 time: 0.6321 data_time: 0.0022 memory: 44140 loss: 0.4278 +2023/06/06 05:50:02 - mmengine - INFO - Epoch(train) [7][1300/4092] lr: 3.6902e-05 eta: 2:40:03 time: 0.6340 data_time: 0.0020 memory: 44140 loss: 0.4140 +2023/06/06 05:51:06 - mmengine - INFO - Epoch(train) [7][1400/4092] lr: 3.6586e-05 eta: 2:39:00 time: 0.6349 data_time: 0.0018 memory: 44140 loss: 0.4359 +2023/06/06 05:51:37 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 05:52:10 - mmengine - INFO - Epoch(train) [7][1500/4092] lr: 3.6272e-05 eta: 2:37:56 time: 0.6340 data_time: 0.0019 memory: 44140 loss: 0.4346 +2023/06/06 05:53:13 - mmengine - INFO - Epoch(train) [7][1600/4092] lr: 3.5958e-05 eta: 2:36:52 time: 0.6338 data_time: 0.0020 memory: 44140 loss: 0.4228 +2023/06/06 05:54:20 - mmengine - INFO - Epoch(train) [7][1700/4092] lr: 3.5646e-05 eta: 2:35:50 time: 1.0242 data_time: 0.0273 memory: 44140 loss: 0.4392 +2023/06/06 05:55:24 - mmengine - INFO - Epoch(train) [7][1800/4092] lr: 3.5334e-05 eta: 2:34:46 time: 0.6342 data_time: 0.0025 memory: 44140 loss: 0.4330 +2023/06/06 05:56:27 - mmengine - INFO - Epoch(train) [7][1900/4092] lr: 3.5024e-05 eta: 2:33:42 time: 0.6351 data_time: 0.0027 memory: 44140 loss: 0.4355 +2023/06/06 05:57:31 - mmengine - INFO - Epoch(train) [7][2000/4092] lr: 3.4715e-05 eta: 2:32:38 time: 0.6419 data_time: 0.0017 memory: 44140 loss: 0.4206 +2023/06/06 05:58:35 - mmengine - INFO - Epoch(train) [7][2100/4092] lr: 3.4407e-05 eta: 2:31:35 time: 0.6338 data_time: 0.0016 memory: 44140 loss: 0.4379 +2023/06/06 05:59:38 - mmengine - INFO - Epoch(train) [7][2200/4092] lr: 3.4101e-05 eta: 2:30:31 time: 0.6320 data_time: 0.0015 memory: 44140 loss: 0.4500 +2023/06/06 06:00:41 - mmengine - INFO - Epoch(train) [7][2300/4092] lr: 3.3796e-05 eta: 2:29:27 time: 0.6355 data_time: 0.0015 memory: 44140 loss: 0.4528 +2023/06/06 06:01:45 - mmengine - INFO - Epoch(train) [7][2400/4092] lr: 3.3491e-05 eta: 2:28:23 time: 0.6341 data_time: 0.0021 memory: 44140 loss: 0.4518 +2023/06/06 06:02:15 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:02:48 - mmengine - INFO - Epoch(train) [7][2500/4092] lr: 3.3189e-05 eta: 2:27:19 time: 0.6331 data_time: 0.0018 memory: 44140 loss: 0.4160 +2023/06/06 06:03:51 - mmengine - INFO - Epoch(train) [7][2600/4092] lr: 3.2887e-05 eta: 2:26:15 time: 0.6332 data_time: 0.0023 memory: 44140 loss: 0.4469 +2023/06/06 06:04:55 - mmengine - INFO - Epoch(train) [7][2700/4092] lr: 3.2587e-05 eta: 2:25:11 time: 0.6332 data_time: 0.0025 memory: 44140 loss: 0.4390 +2023/06/06 06:05:58 - mmengine - INFO - Epoch(train) [7][2800/4092] lr: 3.2288e-05 eta: 2:24:07 time: 0.6329 data_time: 0.0015 memory: 44140 loss: 0.4331 +2023/06/06 06:07:02 - mmengine - INFO - Epoch(train) [7][2900/4092] lr: 3.1990e-05 eta: 2:23:03 time: 0.6331 data_time: 0.0023 memory: 44140 loss: 0.4151 +2023/06/06 06:08:05 - mmengine - INFO - Epoch(train) [7][3000/4092] lr: 3.1694e-05 eta: 2:21:59 time: 0.6323 data_time: 0.0019 memory: 44140 loss: 0.4372 +2023/06/06 06:09:08 - mmengine - INFO - Epoch(train) [7][3100/4092] lr: 3.1399e-05 eta: 2:20:55 time: 0.6338 data_time: 0.0020 memory: 44140 loss: 0.4525 +2023/06/06 06:10:12 - mmengine - INFO - Epoch(train) [7][3200/4092] lr: 3.1106e-05 eta: 2:19:51 time: 0.6332 data_time: 0.0018 memory: 44140 loss: 0.4206 +2023/06/06 06:11:15 - mmengine - INFO - Epoch(train) [7][3300/4092] lr: 3.0814e-05 eta: 2:18:48 time: 0.6336 data_time: 0.0018 memory: 44140 loss: 0.4574 +2023/06/06 06:12:18 - mmengine - INFO - Epoch(train) [7][3400/4092] lr: 3.0523e-05 eta: 2:17:44 time: 0.6330 data_time: 0.0020 memory: 44140 loss: 0.4343 +2023/06/06 06:12:49 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:13:22 - mmengine - INFO - Epoch(train) [7][3500/4092] lr: 3.0234e-05 eta: 2:16:40 time: 0.6341 data_time: 0.0018 memory: 44140 loss: 0.4280 +2023/06/06 06:14:25 - mmengine - INFO - Epoch(train) [7][3600/4092] lr: 2.9946e-05 eta: 2:15:36 time: 0.6324 data_time: 0.0021 memory: 44140 loss: 0.4194 +2023/06/06 06:15:28 - mmengine - INFO - Epoch(train) [7][3700/4092] lr: 2.9660e-05 eta: 2:14:32 time: 0.6323 data_time: 0.0018 memory: 44140 loss: 0.4519 +2023/06/06 06:16:32 - mmengine - INFO - Epoch(train) [7][3800/4092] lr: 2.9375e-05 eta: 2:13:28 time: 0.6333 data_time: 0.0024 memory: 44140 loss: 0.4330 +2023/06/06 06:17:35 - mmengine - INFO - Epoch(train) [7][3900/4092] lr: 2.9092e-05 eta: 2:12:24 time: 0.6322 data_time: 0.0021 memory: 44140 loss: 0.4570 +2023/06/06 06:18:38 - mmengine - INFO - Epoch(train) [7][4000/4092] lr: 2.8810e-05 eta: 2:11:20 time: 0.6325 data_time: 0.0017 memory: 44140 loss: 0.4274 +2023/06/06 06:19:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:19:36 - mmengine - INFO - Saving checkpoint at 7 epochs +2023/06/06 06:21:58 - mmengine - INFO - Epoch(val) [7][100/119] eta: 0:00:24 time: 1.2877 data_time: 0.0006 memory: 44140 +2023/06/06 06:22:40 - mmengine - INFO - Epoch(val) [7][119/119] accuracy/top1: 82.5083 single-label/precision_classwise: [96.11871337890625, 55.72473907470703] single-label/recall_classwise: [81.03234100341797, 87.94573211669922] single-label/f1-score_classwise: [87.93313598632812, 68.22212982177734] data_time: 0.0170 time: 1.2840 +2023/06/06 06:23:47 - mmengine - INFO - Epoch(train) [8][ 100/4092] lr: 2.8274e-05 eta: 2:09:19 time: 0.6333 data_time: 0.0020 memory: 44140 loss: 0.4547 +2023/06/06 06:24:51 - mmengine - INFO - Epoch(train) [8][ 200/4092] lr: 2.7997e-05 eta: 2:08:15 time: 0.6333 data_time: 0.0015 memory: 44140 loss: 0.4534 +2023/06/06 06:25:54 - mmengine - INFO - Epoch(train) [8][ 300/4092] lr: 2.7721e-05 eta: 2:07:11 time: 0.6471 data_time: 0.0019 memory: 44140 loss: 0.4233 +2023/06/06 06:26:29 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:26:57 - mmengine - INFO - Epoch(train) [8][ 400/4092] lr: 2.7447e-05 eta: 2:06:07 time: 0.6344 data_time: 0.0021 memory: 44140 loss: 0.4301 +2023/06/06 06:28:01 - mmengine - INFO - Epoch(train) [8][ 500/4092] lr: 2.7175e-05 eta: 2:05:03 time: 0.6328 data_time: 0.0018 memory: 44140 loss: 0.4388 +2023/06/06 06:29:04 - mmengine - INFO - Epoch(train) [8][ 600/4092] lr: 2.6904e-05 eta: 2:03:59 time: 0.6319 data_time: 0.0017 memory: 44140 loss: 0.4352 +2023/06/06 06:30:07 - mmengine - INFO - Epoch(train) [8][ 700/4092] lr: 2.6635e-05 eta: 2:02:56 time: 0.6606 data_time: 0.0016 memory: 44140 loss: 0.3998 +2023/06/06 06:31:11 - mmengine - INFO - Epoch(train) [8][ 800/4092] lr: 2.6368e-05 eta: 2:01:52 time: 0.6344 data_time: 0.0016 memory: 44140 loss: 0.4316 +2023/06/06 06:32:14 - mmengine - INFO - Epoch(train) [8][ 900/4092] lr: 2.6102e-05 eta: 2:00:48 time: 0.6356 data_time: 0.0014 memory: 44140 loss: 0.4166 +2023/06/06 06:33:17 - mmengine - INFO - Epoch(train) [8][1000/4092] lr: 2.5838e-05 eta: 1:59:44 time: 0.6324 data_time: 0.0014 memory: 44140 loss: 0.4451 +2023/06/06 06:34:21 - mmengine - INFO - Epoch(train) [8][1100/4092] lr: 2.5576e-05 eta: 1:58:40 time: 0.6329 data_time: 0.0014 memory: 44140 loss: 0.4389 +2023/06/06 06:35:24 - mmengine - INFO - Epoch(train) [8][1200/4092] lr: 2.5315e-05 eta: 1:57:36 time: 0.6327 data_time: 0.0015 memory: 44140 loss: 0.4256 +2023/06/06 06:36:27 - mmengine - INFO - Epoch(train) [8][1300/4092] lr: 2.5056e-05 eta: 1:56:32 time: 0.6322 data_time: 0.0014 memory: 44140 loss: 0.4029 +2023/06/06 06:37:02 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:37:30 - mmengine - INFO - Epoch(train) [8][1400/4092] lr: 2.4799e-05 eta: 1:55:28 time: 0.6318 data_time: 0.0014 memory: 44140 loss: 0.4328 +2023/06/06 06:38:34 - mmengine - INFO - Epoch(train) [8][1500/4092] lr: 2.4544e-05 eta: 1:54:25 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4334 +2023/06/06 06:39:37 - mmengine - INFO - Epoch(train) [8][1600/4092] lr: 2.4291e-05 eta: 1:53:21 time: 0.6311 data_time: 0.0023 memory: 44140 loss: 0.4030 +2023/06/06 06:40:40 - mmengine - INFO - Epoch(train) [8][1700/4092] lr: 2.4039e-05 eta: 1:52:17 time: 0.6329 data_time: 0.0014 memory: 44140 loss: 0.4400 +2023/06/06 06:41:43 - mmengine - INFO - Epoch(train) [8][1800/4092] lr: 2.3789e-05 eta: 1:51:13 time: 0.6322 data_time: 0.0015 memory: 44140 loss: 0.4242 +2023/06/06 06:42:47 - mmengine - INFO - Epoch(train) [8][1900/4092] lr: 2.3541e-05 eta: 1:50:09 time: 0.6333 data_time: 0.0015 memory: 44140 loss: 0.4326 +2023/06/06 06:43:50 - mmengine - INFO - Epoch(train) [8][2000/4092] lr: 2.3295e-05 eta: 1:49:05 time: 0.6321 data_time: 0.0016 memory: 44140 loss: 0.4057 +2023/06/06 06:44:53 - mmengine - INFO - Epoch(train) [8][2100/4092] lr: 2.3051e-05 eta: 1:48:01 time: 0.6324 data_time: 0.0015 memory: 44140 loss: 0.4293 +2023/06/06 06:45:57 - mmengine - INFO - Epoch(train) [8][2200/4092] lr: 2.2809e-05 eta: 1:46:58 time: 0.6320 data_time: 0.0014 memory: 44140 loss: 0.4227 +2023/06/06 06:47:00 - mmengine - INFO - Epoch(train) [8][2300/4092] lr: 2.2568e-05 eta: 1:45:54 time: 0.6322 data_time: 0.0017 memory: 44140 loss: 0.4292 +2023/06/06 06:47:35 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:48:03 - mmengine - INFO - Epoch(train) [8][2400/4092] lr: 2.2330e-05 eta: 1:44:50 time: 0.6315 data_time: 0.0021 memory: 44140 loss: 0.4299 +2023/06/06 06:49:06 - mmengine - INFO - Epoch(train) [8][2500/4092] lr: 2.2093e-05 eta: 1:43:46 time: 0.6322 data_time: 0.0019 memory: 44140 loss: 0.4226 +2023/06/06 06:50:10 - mmengine - INFO - Epoch(train) [8][2600/4092] lr: 2.1858e-05 eta: 1:42:42 time: 0.6334 data_time: 0.0015 memory: 44140 loss: 0.4533 +2023/06/06 06:51:13 - mmengine - INFO - Epoch(train) [8][2700/4092] lr: 2.1626e-05 eta: 1:41:38 time: 0.6318 data_time: 0.0016 memory: 44140 loss: 0.4104 +2023/06/06 06:52:16 - mmengine - INFO - Epoch(train) [8][2800/4092] lr: 2.1395e-05 eta: 1:40:35 time: 0.6330 data_time: 0.0016 memory: 44140 loss: 0.4277 +2023/06/06 06:53:20 - mmengine - INFO - Epoch(train) [8][2900/4092] lr: 2.1166e-05 eta: 1:39:31 time: 0.6349 data_time: 0.0033 memory: 44140 loss: 0.4660 +2023/06/06 06:54:23 - mmengine - INFO - Epoch(train) [8][3000/4092] lr: 2.0939e-05 eta: 1:38:27 time: 0.6327 data_time: 0.0015 memory: 44140 loss: 0.4146 +2023/06/06 06:55:26 - mmengine - INFO - Epoch(train) [8][3100/4092] lr: 2.0715e-05 eta: 1:37:23 time: 0.6330 data_time: 0.0015 memory: 44140 loss: 0.4298 +2023/06/06 06:56:30 - mmengine - INFO - Epoch(train) [8][3200/4092] lr: 2.0492e-05 eta: 1:36:20 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4238 +2023/06/06 06:57:33 - mmengine - INFO - Epoch(train) [8][3300/4092] lr: 2.0271e-05 eta: 1:35:16 time: 0.6332 data_time: 0.0016 memory: 44140 loss: 0.4399 +2023/06/06 06:58:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 06:58:36 - mmengine - INFO - Epoch(train) [8][3400/4092] lr: 2.0052e-05 eta: 1:34:12 time: 0.6324 data_time: 0.0018 memory: 44140 loss: 0.4230 +2023/06/06 06:59:40 - mmengine - INFO - Epoch(train) [8][3500/4092] lr: 1.9836e-05 eta: 1:33:08 time: 0.6349 data_time: 0.0018 memory: 44140 loss: 0.4160 +2023/06/06 07:00:43 - mmengine - INFO - Epoch(train) [8][3600/4092] lr: 1.9621e-05 eta: 1:32:04 time: 0.6338 data_time: 0.0017 memory: 44140 loss: 0.4029 +2023/06/06 07:01:47 - mmengine - INFO - Epoch(train) [8][3700/4092] lr: 1.9409e-05 eta: 1:31:01 time: 0.6326 data_time: 0.0015 memory: 44140 loss: 0.4238 +2023/06/06 07:02:50 - mmengine - INFO - Epoch(train) [8][3800/4092] lr: 1.9198e-05 eta: 1:29:57 time: 0.6321 data_time: 0.0022 memory: 44140 loss: 0.4153 +2023/06/06 07:03:53 - mmengine - INFO - Epoch(train) [8][3900/4092] lr: 1.8990e-05 eta: 1:28:53 time: 0.6325 data_time: 0.0015 memory: 44140 loss: 0.4483 +2023/06/06 07:04:57 - mmengine - INFO - Epoch(train) [8][4000/4092] lr: 1.8784e-05 eta: 1:27:49 time: 0.6318 data_time: 0.0022 memory: 44140 loss: 0.4293 +2023/06/06 07:05:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:05:54 - mmengine - INFO - Saving checkpoint at 8 epochs +2023/06/06 07:08:15 - mmengine - INFO - Epoch(val) [8][100/119] eta: 0:00:24 time: 1.2877 data_time: 0.0006 memory: 44140 +2023/06/06 07:08:57 - mmengine - INFO - Epoch(val) [8][119/119] accuracy/top1: 83.3822 single-label/precision_classwise: [95.77450561523438, 57.337921142578125] single-label/recall_classwise: [82.51162719726562, 86.58914184570312] single-label/f1-score_classwise: [88.64974975585938, 68.99107360839844] data_time: 0.0176 time: 1.2849 +2023/06/06 07:10:04 - mmengine - INFO - Epoch(train) [9][ 100/4092] lr: 1.8394e-05 eta: 1:25:48 time: 0.6331 data_time: 0.0015 memory: 44140 loss: 0.4192 +2023/06/06 07:11:08 - mmengine - INFO - Epoch(train) [9][ 200/4092] lr: 1.8194e-05 eta: 1:24:44 time: 0.6337 data_time: 0.0018 memory: 44140 loss: 0.4159 +2023/06/06 07:11:48 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:12:11 - mmengine - INFO - Epoch(train) [9][ 300/4092] lr: 1.7997e-05 eta: 1:23:40 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4478 +2023/06/06 07:13:14 - mmengine - INFO - Epoch(train) [9][ 400/4092] lr: 1.7801e-05 eta: 1:22:36 time: 0.6328 data_time: 0.0016 memory: 44140 loss: 0.4213 +2023/06/06 07:14:18 - mmengine - INFO - Epoch(train) [9][ 500/4092] lr: 1.7608e-05 eta: 1:21:33 time: 0.6325 data_time: 0.0022 memory: 44140 loss: 0.4436 +2023/06/06 07:15:21 - mmengine - INFO - Epoch(train) [9][ 600/4092] lr: 1.7417e-05 eta: 1:20:29 time: 0.6316 data_time: 0.0018 memory: 44140 loss: 0.4177 +2023/06/06 07:16:24 - mmengine - INFO - Epoch(train) [9][ 700/4092] lr: 1.7228e-05 eta: 1:19:25 time: 0.6318 data_time: 0.0017 memory: 44140 loss: 0.4439 +2023/06/06 07:17:27 - mmengine - INFO - Epoch(train) [9][ 800/4092] lr: 1.7041e-05 eta: 1:18:21 time: 0.6323 data_time: 0.0016 memory: 44140 loss: 0.4294 +2023/06/06 07:18:31 - mmengine - INFO - Epoch(train) [9][ 900/4092] lr: 1.6857e-05 eta: 1:17:18 time: 0.6332 data_time: 0.0021 memory: 44140 loss: 0.4280 +2023/06/06 07:19:34 - mmengine - INFO - Epoch(train) [9][1000/4092] lr: 1.6675e-05 eta: 1:16:14 time: 0.6328 data_time: 0.0024 memory: 44140 loss: 0.4527 +2023/06/06 07:20:37 - mmengine - INFO - Epoch(train) [9][1100/4092] lr: 1.6495e-05 eta: 1:15:10 time: 0.6425 data_time: 0.0015 memory: 44140 loss: 0.4159 +2023/06/06 07:21:41 - mmengine - INFO - Epoch(train) [9][1200/4092] lr: 1.6317e-05 eta: 1:14:06 time: 0.6325 data_time: 0.0017 memory: 44140 loss: 0.4096 +2023/06/06 07:22:21 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:22:44 - mmengine - INFO - Epoch(train) [9][1300/4092] lr: 1.6142e-05 eta: 1:13:03 time: 0.6315 data_time: 0.0026 memory: 44140 loss: 0.4171 +2023/06/06 07:23:47 - mmengine - INFO - Epoch(train) [9][1400/4092] lr: 1.5969e-05 eta: 1:11:59 time: 0.6314 data_time: 0.0016 memory: 44140 loss: 0.4286 +2023/06/06 07:24:50 - mmengine - INFO - Epoch(train) [9][1500/4092] lr: 1.5798e-05 eta: 1:10:55 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4414 +2023/06/06 07:25:54 - mmengine - INFO - Epoch(train) [9][1600/4092] lr: 1.5629e-05 eta: 1:09:51 time: 0.6321 data_time: 0.0017 memory: 44140 loss: 0.4408 +2023/06/06 07:26:57 - mmengine - INFO - Epoch(train) [9][1700/4092] lr: 1.5463e-05 eta: 1:08:48 time: 0.6321 data_time: 0.0015 memory: 44140 loss: 0.4242 +2023/06/06 07:28:00 - mmengine - INFO - Epoch(train) [9][1800/4092] lr: 1.5299e-05 eta: 1:07:44 time: 0.6316 data_time: 0.0017 memory: 44140 loss: 0.4343 +2023/06/06 07:29:03 - mmengine - INFO - Epoch(train) [9][1900/4092] lr: 1.5138e-05 eta: 1:06:40 time: 0.6328 data_time: 0.0016 memory: 44140 loss: 0.4663 +2023/06/06 07:30:07 - mmengine - INFO - Epoch(train) [9][2000/4092] lr: 1.4979e-05 eta: 1:05:36 time: 0.6314 data_time: 0.0015 memory: 44140 loss: 0.4332 +2023/06/06 07:31:10 - mmengine - INFO - Epoch(train) [9][2100/4092] lr: 1.4822e-05 eta: 1:04:33 time: 0.6326 data_time: 0.0022 memory: 44140 loss: 0.4290 +2023/06/06 07:32:13 - mmengine - INFO - Epoch(train) [9][2200/4092] lr: 1.4668e-05 eta: 1:03:29 time: 0.6312 data_time: 0.0017 memory: 44140 loss: 0.4446 +2023/06/06 07:32:54 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:33:17 - mmengine - INFO - Epoch(train) [9][2300/4092] lr: 1.4515e-05 eta: 1:02:25 time: 0.6336 data_time: 0.0015 memory: 44140 loss: 0.3901 +2023/06/06 07:34:20 - mmengine - INFO - Epoch(train) [9][2400/4092] lr: 1.4366e-05 eta: 1:01:21 time: 0.6338 data_time: 0.0016 memory: 44140 loss: 0.4295 +2023/06/06 07:35:24 - mmengine - INFO - Epoch(train) [9][2500/4092] lr: 1.4219e-05 eta: 1:00:18 time: 0.6336 data_time: 0.0020 memory: 44140 loss: 0.4015 +2023/06/06 07:36:27 - mmengine - INFO - Epoch(train) [9][2600/4092] lr: 1.4074e-05 eta: 0:59:14 time: 0.6346 data_time: 0.0016 memory: 44140 loss: 0.4517 +2023/06/06 07:37:31 - mmengine - INFO - Epoch(train) [9][2700/4092] lr: 1.3931e-05 eta: 0:58:10 time: 0.6338 data_time: 0.0017 memory: 44140 loss: 0.4484 +2023/06/06 07:38:34 - mmengine - INFO - Epoch(train) [9][2800/4092] lr: 1.3791e-05 eta: 0:57:07 time: 0.6338 data_time: 0.0016 memory: 44140 loss: 0.4113 +2023/06/06 07:39:38 - mmengine - INFO - Epoch(train) [9][2900/4092] lr: 1.3654e-05 eta: 0:56:03 time: 0.6355 data_time: 0.0022 memory: 44140 loss: 0.4379 +2023/06/06 07:40:41 - mmengine - INFO - Epoch(train) [9][3000/4092] lr: 1.3519e-05 eta: 0:54:59 time: 0.6333 data_time: 0.0015 memory: 44140 loss: 0.4329 +2023/06/06 07:41:45 - mmengine - INFO - Epoch(train) [9][3100/4092] lr: 1.3386e-05 eta: 0:53:56 time: 0.6344 data_time: 0.0020 memory: 44140 loss: 0.4024 +2023/06/06 07:42:48 - mmengine - INFO - Epoch(train) [9][3200/4092] lr: 1.3256e-05 eta: 0:52:52 time: 0.6335 data_time: 0.0019 memory: 44140 loss: 0.4243 +2023/06/06 07:43:29 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:43:52 - mmengine - INFO - Epoch(train) [9][3300/4092] lr: 1.3128e-05 eta: 0:51:48 time: 0.6335 data_time: 0.0017 memory: 44140 loss: 0.4423 +2023/06/06 07:44:55 - mmengine - INFO - Epoch(train) [9][3400/4092] lr: 1.3003e-05 eta: 0:50:45 time: 0.6337 data_time: 0.0019 memory: 44140 loss: 0.4114 +2023/06/06 07:45:59 - mmengine - INFO - Epoch(train) [9][3500/4092] lr: 1.2880e-05 eta: 0:49:41 time: 0.6368 data_time: 0.0015 memory: 44140 loss: 0.4362 +2023/06/06 07:47:02 - mmengine - INFO - Epoch(train) [9][3600/4092] lr: 1.2759e-05 eta: 0:48:37 time: 0.6355 data_time: 0.0017 memory: 44140 loss: 0.4443 +2023/06/06 07:48:06 - mmengine - INFO - Epoch(train) [9][3700/4092] lr: 1.2641e-05 eta: 0:47:34 time: 0.6332 data_time: 0.0016 memory: 44140 loss: 0.4355 +2023/06/06 07:49:09 - mmengine - INFO - Epoch(train) [9][3800/4092] lr: 1.2526e-05 eta: 0:46:30 time: 0.6356 data_time: 0.0019 memory: 44140 loss: 0.4494 +2023/06/06 07:50:12 - mmengine - INFO - Epoch(train) [9][3900/4092] lr: 1.2413e-05 eta: 0:45:26 time: 0.6345 data_time: 0.0019 memory: 44140 loss: 0.4139 +2023/06/06 07:51:16 - mmengine - INFO - Epoch(train) [9][4000/4092] lr: 1.2303e-05 eta: 0:44:23 time: 0.6347 data_time: 0.0016 memory: 44140 loss: 0.4212 +2023/06/06 07:52:14 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:52:14 - mmengine - INFO - Saving checkpoint at 9 epochs +2023/06/06 07:54:35 - mmengine - INFO - Epoch(val) [9][100/119] eta: 0:00:24 time: 1.2877 data_time: 0.0007 memory: 44140 +2023/06/06 07:55:17 - mmengine - INFO - Epoch(val) [9][119/119] accuracy/top1: 84.1517 single-label/precision_classwise: [95.78436279296875, 58.75566482543945] single-label/recall_classwise: [83.52587127685547, 86.45736694335938] single-label/f1-score_classwise: [89.236083984375, 69.96424102783203] data_time: 0.0184 time: 1.2860 +2023/06/06 07:56:24 - mmengine - INFO - Epoch(train) [10][ 100/4092] lr: 1.2098e-05 eta: 0:42:21 time: 0.6331 data_time: 0.0018 memory: 44140 loss: 0.4379 +2023/06/06 07:57:10 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 07:57:28 - mmengine - INFO - Epoch(train) [10][ 200/4092] lr: 1.1995e-05 eta: 0:41:17 time: 0.6329 data_time: 0.0016 memory: 44140 loss: 0.4197 +2023/06/06 07:58:31 - mmengine - INFO - Epoch(train) [10][ 300/4092] lr: 1.1895e-05 eta: 0:40:13 time: 0.6335 data_time: 0.0018 memory: 44140 loss: 0.4558 +2023/06/06 07:59:34 - mmengine - INFO - Epoch(train) [10][ 400/4092] lr: 1.1797e-05 eta: 0:39:10 time: 0.6324 data_time: 0.0020 memory: 44140 loss: 0.4206 +2023/06/06 08:00:38 - mmengine - INFO - Epoch(train) [10][ 500/4092] lr: 1.1701e-05 eta: 0:38:06 time: 0.6353 data_time: 0.0016 memory: 44140 loss: 0.4137 +2023/06/06 08:01:41 - mmengine - INFO - Epoch(train) [10][ 600/4092] lr: 1.1608e-05 eta: 0:37:02 time: 0.6342 data_time: 0.0017 memory: 44140 loss: 0.4046 +2023/06/06 08:02:44 - mmengine - INFO - Epoch(train) [10][ 700/4092] lr: 1.1518e-05 eta: 0:35:59 time: 0.6338 data_time: 0.0021 memory: 44140 loss: 0.4356 +2023/06/06 08:03:48 - mmengine - INFO - Epoch(train) [10][ 800/4092] lr: 1.1430e-05 eta: 0:34:55 time: 0.6319 data_time: 0.0022 memory: 44140 loss: 0.4533 +2023/06/06 08:04:51 - mmengine - INFO - Epoch(train) [10][ 900/4092] lr: 1.1345e-05 eta: 0:33:51 time: 0.6314 data_time: 0.0023 memory: 44140 loss: 0.4262 +2023/06/06 08:05:54 - mmengine - INFO - Epoch(train) [10][1000/4092] lr: 1.1263e-05 eta: 0:32:48 time: 0.6451 data_time: 0.0017 memory: 44140 loss: 0.4054 +2023/06/06 08:06:58 - mmengine - INFO - Epoch(train) [10][1100/4092] lr: 1.1183e-05 eta: 0:31:44 time: 0.6340 data_time: 0.0026 memory: 44140 loss: 0.4339 +2023/06/06 08:07:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 08:08:01 - mmengine - INFO - Epoch(train) [10][1200/4092] lr: 1.1105e-05 eta: 0:30:40 time: 0.6330 data_time: 0.0028 memory: 44140 loss: 0.4344 +2023/06/06 08:09:05 - mmengine - INFO - Epoch(train) [10][1300/4092] lr: 1.1031e-05 eta: 0:29:37 time: 0.6334 data_time: 0.0016 memory: 44140 loss: 0.4391 +2023/06/06 08:10:08 - mmengine - INFO - Epoch(train) [10][1400/4092] lr: 1.0958e-05 eta: 0:28:33 time: 0.6321 data_time: 0.0017 memory: 44140 loss: 0.4351 +2023/06/06 08:11:11 - mmengine - INFO - Epoch(train) [10][1500/4092] lr: 1.0889e-05 eta: 0:27:29 time: 0.6337 data_time: 0.0015 memory: 44140 loss: 0.4341 +2023/06/06 08:12:15 - mmengine - INFO - Epoch(train) [10][1600/4092] lr: 1.0822e-05 eta: 0:26:26 time: 0.6337 data_time: 0.0031 memory: 44140 loss: 0.4434 +2023/06/06 08:13:18 - mmengine - INFO - Epoch(train) [10][1700/4092] lr: 1.0757e-05 eta: 0:25:22 time: 0.6330 data_time: 0.0022 memory: 44140 loss: 0.4389 +2023/06/06 08:14:22 - mmengine - INFO - Epoch(train) [10][1800/4092] lr: 1.0696e-05 eta: 0:24:18 time: 0.6371 data_time: 0.0025 memory: 44140 loss: 0.4290 +2023/06/06 08:15:25 - mmengine - INFO - Epoch(train) [10][1900/4092] lr: 1.0636e-05 eta: 0:23:15 time: 0.6350 data_time: 0.0017 memory: 44140 loss: 0.4352 +2023/06/06 08:16:29 - mmengine - INFO - Epoch(train) [10][2000/4092] lr: 1.0580e-05 eta: 0:22:11 time: 0.6348 data_time: 0.0016 memory: 44140 loss: 0.4078 +2023/06/06 08:17:32 - mmengine - INFO - Epoch(train) [10][2100/4092] lr: 1.0526e-05 eta: 0:21:07 time: 0.6331 data_time: 0.0023 memory: 44140 loss: 0.4292 +2023/06/06 08:18:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 08:18:35 - mmengine - INFO - Epoch(train) [10][2200/4092] lr: 1.0474e-05 eta: 0:20:04 time: 0.6333 data_time: 0.0014 memory: 44140 loss: 0.4246 +2023/06/06 08:19:39 - mmengine - INFO - Epoch(train) [10][2300/4092] lr: 1.0426e-05 eta: 0:19:00 time: 0.6339 data_time: 0.0019 memory: 44140 loss: 0.4188 +2023/06/06 08:20:42 - mmengine - INFO - Epoch(train) [10][2400/4092] lr: 1.0380e-05 eta: 0:17:56 time: 0.6328 data_time: 0.0021 memory: 44140 loss: 0.4077 +2023/06/06 08:21:45 - mmengine - INFO - Epoch(train) [10][2500/4092] lr: 1.0336e-05 eta: 0:16:53 time: 0.6336 data_time: 0.0017 memory: 44140 loss: 0.4142 +2023/06/06 08:22:49 - mmengine - INFO - Epoch(train) [10][2600/4092] lr: 1.0295e-05 eta: 0:15:49 time: 0.6315 data_time: 0.0023 memory: 44140 loss: 0.4428 +2023/06/06 08:23:53 - mmengine - INFO - Epoch(train) [10][2700/4092] lr: 1.0257e-05 eta: 0:14:45 time: 0.6380 data_time: 0.0024 memory: 44140 loss: 0.4394 +2023/06/06 08:24:56 - mmengine - INFO - Epoch(train) [10][2800/4092] lr: 1.0222e-05 eta: 0:13:42 time: 0.6329 data_time: 0.0027 memory: 44140 loss: 0.4387 +2023/06/06 08:26:00 - mmengine - INFO - Epoch(train) [10][2900/4092] lr: 1.0189e-05 eta: 0:12:38 time: 0.6328 data_time: 0.0022 memory: 44140 loss: 0.4340 +2023/06/06 08:27:03 - mmengine - INFO - Epoch(train) [10][3000/4092] lr: 1.0158e-05 eta: 0:11:34 time: 0.6348 data_time: 0.0015 memory: 44140 loss: 0.4061 +2023/06/06 08:28:06 - mmengine - INFO - Epoch(train) [10][3100/4092] lr: 1.0131e-05 eta: 0:10:31 time: 0.6341 data_time: 0.0016 memory: 44140 loss: 0.4352 +2023/06/06 08:28:52 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 08:29:10 - mmengine - INFO - Epoch(train) [10][3200/4092] lr: 1.0106e-05 eta: 0:09:27 time: 0.6323 data_time: 0.0015 memory: 44140 loss: 0.4138 +2023/06/06 08:30:13 - mmengine - INFO - Epoch(train) [10][3300/4092] lr: 1.0083e-05 eta: 0:08:24 time: 0.6353 data_time: 0.0024 memory: 44140 loss: 0.4161 +2023/06/06 08:31:17 - mmengine - INFO - Epoch(train) [10][3400/4092] lr: 1.0064e-05 eta: 0:07:20 time: 0.6348 data_time: 0.0019 memory: 44140 loss: 0.4420 +2023/06/06 08:32:20 - mmengine - INFO - Epoch(train) [10][3500/4092] lr: 1.0047e-05 eta: 0:06:16 time: 0.6341 data_time: 0.0018 memory: 44140 loss: 0.4455 +2023/06/06 08:33:24 - mmengine - INFO - Epoch(train) [10][3600/4092] lr: 1.0032e-05 eta: 0:05:13 time: 0.6340 data_time: 0.0017 memory: 44140 loss: 0.4343 +2023/06/06 08:34:27 - mmengine - INFO - Epoch(train) [10][3700/4092] lr: 1.0020e-05 eta: 0:04:09 time: 0.6342 data_time: 0.0015 memory: 44140 loss: 0.4428 +2023/06/06 08:35:31 - mmengine - INFO - Epoch(train) [10][3800/4092] lr: 1.0011e-05 eta: 0:03:05 time: 0.6335 data_time: 0.0018 memory: 44140 loss: 0.4355 +2023/06/06 08:36:34 - mmengine - INFO - Epoch(train) [10][3900/4092] lr: 1.0005e-05 eta: 0:02:02 time: 0.6345 data_time: 0.0017 memory: 44140 loss: 0.4310 +2023/06/06 08:37:37 - mmengine - INFO - Epoch(train) [10][4000/4092] lr: 1.0001e-05 eta: 0:00:58 time: 0.6344 data_time: 0.0014 memory: 44140 loss: 0.4473 +2023/06/06 08:38:35 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_all2_lr1e-4_20230606_005614 +2023/06/06 08:38:35 - mmengine - INFO - Saving checkpoint at 10 epochs +2023/06/06 08:40:59 - mmengine - INFO - Epoch(val) [10][100/119] eta: 0:00:24 time: 1.2877 data_time: 0.0007 memory: 44140 +2023/06/06 08:41:41 - mmengine - INFO - Epoch(val) [10][119/119] accuracy/top1: 84.3503 single-label/precision_classwise: [95.57939910888672, 59.226314544677734] single-label/recall_classwise: [83.98670196533203, 85.6899185180664] single-label/f1-score_classwise: [89.40884399414062, 70.04181671142578] data_time: 0.0170 time: 1.2857