diff --git "a/clip_large_pretrain_4x256_IF_lr1e-4/20230606_050006/20230606_050006.log" "b/clip_large_pretrain_4x256_IF_lr1e-4/20230606_050006/20230606_050006.log" new file mode 100644--- /dev/null +++ "b/clip_large_pretrain_4x256_IF_lr1e-4/20230606_050006/20230606_050006.log" @@ -0,0 +1,1742 @@ +2023/06/06 05:00:11 - 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: 1053694385 + GPU 0,1,2,3: NVIDIA A100-SXM4-80GB + CUDA_HOME: /mnt/petrelfs/share/cuda-11.6 + NVCC: Cuda compilation tools, release 11.6, V11.6.124 + GCC: gcc (GCC) 7.5.0 + PyTorch: 1.13.1 + PyTorch compiling details: PyTorch built with: + - GCC 9.3 + - C++ Version: 201402 + - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications + - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) + - OpenMP 201511 (a.k.a. OpenMP 4.5) + - LAPACK is enabled (usually provided by MKL) + - NNPACK is enabled + - CPU capability usage: AVX2 + - CUDA Runtime 11.6 + - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 + - CuDNN 8.3.2 (built against CUDA 11.5) + - Magma 2.6.1 + - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, + + TorchVision: 0.14.1 + OpenCV: 4.7.0 + MMEngine: 0.7.3 + +Runtime environment: + cudnn_benchmark: True + mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} + dist_cfg: {'backend': 'nccl'} + seed: None + deterministic: False + Distributed launcher: slurm + Distributed training: True + GPU number: 4 +------------------------------------------------------------ + +2023/06/06 05:00:14 - 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/IF80w.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/if-dpmsolver++-50-20w.tsv', + pipeline=[ + dict(type='LoadImageFromFile'), + dict( + type='RandomResizedCrop', + scale=224, + backend='pillow', + interpolation='bicubic'), + dict(type='RandomFlip', prob=0.5, direction='horizontal'), + dict(type='PackInputs') + ]), + dict( + type='CustomDataset', + data_root='', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/cc1m.csv', + pipeline=[ + dict(type='LoadImageFromFile'), + dict( + type='RandomResizedCrop', + scale=224, + backend='pillow', + interpolation='bicubic'), + dict(type='RandomFlip', prob=0.5, direction='horizontal'), + dict(type='PackInputs') + ]) + ]), + sampler=dict(type='DefaultSampler', shuffle=True)) +val_dataloader = dict( + pin_memory=True, + persistent_workers=True, + collate_fn=dict(type='default_collate'), + batch_size=128, + num_workers=10, + dataset=dict( + type='ConcatDataset', + datasets=[ + dict( + type='CustomDataset', + data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', + ann_file= + '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/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/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_IF_lr1e-4' + +2023/06/06 05:00:26 - mmengine - INFO - Hooks will be executed in the following order: +before_run: +(VERY_HIGH ) RuntimeInfoHook +(ABOVE_NORMAL) EMAHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_load_checkpoint: +(ABOVE_NORMAL) EMAHook + -------------------- +before_train: +(VERY_HIGH ) RuntimeInfoHook +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook +(VERY_LOW ) CheckpointHook + -------------------- +before_train_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(NORMAL ) DistSamplerSeedHook + -------------------- +before_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook + -------------------- +after_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +after_train_epoch: +(NORMAL ) IterTimerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +before_val_epoch: +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook + -------------------- +before_val_iter: +(NORMAL ) IterTimerHook + -------------------- +after_val_iter: +(NORMAL ) IterTimerHook +(NORMAL ) VisualizationHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_val_epoch: +(VERY_HIGH ) RuntimeInfoHook +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +before_save_checkpoint: +(ABOVE_NORMAL) EMAHook + -------------------- +after_train: +(VERY_LOW ) CheckpointHook + -------------------- +before_test_epoch: +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook + -------------------- +before_test_iter: +(NORMAL ) IterTimerHook + -------------------- +after_test_iter: +(NORMAL ) IterTimerHook +(NORMAL ) VisualizationHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_test_epoch: +(VERY_HIGH ) RuntimeInfoHook +(ABOVE_NORMAL) EMAHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_run: +(BELOW_NORMAL) LoggerHook + -------------------- +2023/06/06 05:00:42 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth +2023/06/06 05:00:44 - mmengine - WARNING - The model and loaded state dict do not match exactly + +unexpected key in source state_dict: ln1.weight, ln1.bias + +2023/06/06 05:00:44 - mmengine - INFO - load backbone in model from: ckpt/openclip-ViT-L-14.pth +2023/06/06 05:00:46 - mmengine - WARNING - The model and loaded state dict do not match exactly + +unexpected key in source state_dict: cls_token, pos_embed, patch_embed.projection.weight, pre_norm.weight, pre_norm.bias, layers.0.ln1.weight, layers.0.ln1.bias, layers.0.attn.qkv.weight, layers.0.attn.qkv.bias, layers.0.attn.proj.weight, layers.0.attn.proj.bias, layers.0.ln2.weight, layers.0.ln2.bias, layers.0.ffn.layers.0.0.weight, layers.0.ffn.layers.0.0.bias, layers.0.ffn.layers.1.weight, layers.0.ffn.layers.1.bias, layers.1.ln1.weight, layers.1.ln1.bias, layers.1.attn.qkv.weight, layers.1.attn.qkv.bias, layers.1.attn.proj.weight, layers.1.attn.proj.bias, layers.1.ln2.weight, layers.1.ln2.bias, layers.1.ffn.layers.0.0.weight, layers.1.ffn.layers.0.0.bias, layers.1.ffn.layers.1.weight, layers.1.ffn.layers.1.bias, layers.2.ln1.weight, layers.2.ln1.bias, layers.2.attn.qkv.weight, layers.2.attn.qkv.bias, layers.2.attn.proj.weight, layers.2.attn.proj.bias, layers.2.ln2.weight, layers.2.ln2.bias, layers.2.ffn.layers.0.0.weight, layers.2.ffn.layers.0.0.bias, layers.2.ffn.layers.1.weight, layers.2.ffn.layers.1.bias, layers.3.ln1.weight, layers.3.ln1.bias, layers.3.attn.qkv.weight, layers.3.attn.qkv.bias, layers.3.attn.proj.weight, layers.3.attn.proj.bias, layers.3.ln2.weight, layers.3.ln2.bias, layers.3.ffn.layers.0.0.weight, layers.3.ffn.layers.0.0.bias, layers.3.ffn.layers.1.weight, layers.3.ffn.layers.1.bias, layers.4.ln1.weight, layers.4.ln1.bias, layers.4.attn.qkv.weight, layers.4.attn.qkv.bias, layers.4.attn.proj.weight, layers.4.attn.proj.bias, layers.4.ln2.weight, layers.4.ln2.bias, layers.4.ffn.layers.0.0.weight, layers.4.ffn.layers.0.0.bias, layers.4.ffn.layers.1.weight, layers.4.ffn.layers.1.bias, layers.5.ln1.weight, layers.5.ln1.bias, layers.5.attn.qkv.weight, layers.5.attn.qkv.bias, layers.5.attn.proj.weight, layers.5.attn.proj.bias, layers.5.ln2.weight, layers.5.ln2.bias, layers.5.ffn.layers.0.0.weight, layers.5.ffn.layers.0.0.bias, layers.5.ffn.layers.1.weight, layers.5.ffn.layers.1.bias, layers.6.ln1.weight, layers.6.ln1.bias, layers.6.attn.qkv.weight, layers.6.attn.qkv.bias, layers.6.attn.proj.weight, layers.6.attn.proj.bias, layers.6.ln2.weight, layers.6.ln2.bias, layers.6.ffn.layers.0.0.weight, layers.6.ffn.layers.0.0.bias, layers.6.ffn.layers.1.weight, layers.6.ffn.layers.1.bias, layers.7.ln1.weight, layers.7.ln1.bias, layers.7.attn.qkv.weight, layers.7.attn.qkv.bias, layers.7.attn.proj.weight, layers.7.attn.proj.bias, layers.7.ln2.weight, layers.7.ln2.bias, layers.7.ffn.layers.0.0.weight, layers.7.ffn.layers.0.0.bias, layers.7.ffn.layers.1.weight, layers.7.ffn.layers.1.bias, layers.8.ln1.weight, layers.8.ln1.bias, layers.8.attn.qkv.weight, layers.8.attn.qkv.bias, layers.8.attn.proj.weight, layers.8.attn.proj.bias, layers.8.ln2.weight, layers.8.ln2.bias, layers.8.ffn.layers.0.0.weight, layers.8.ffn.layers.0.0.bias, layers.8.ffn.layers.1.weight, layers.8.ffn.layers.1.bias, layers.9.ln1.weight, layers.9.ln1.bias, layers.9.attn.qkv.weight, layers.9.attn.qkv.bias, layers.9.attn.proj.weight, layers.9.attn.proj.bias, layers.9.ln2.weight, layers.9.ln2.bias, layers.9.ffn.layers.0.0.weight, layers.9.ffn.layers.0.0.bias, layers.9.ffn.layers.1.weight, layers.9.ffn.layers.1.bias, layers.10.ln1.weight, layers.10.ln1.bias, layers.10.attn.qkv.weight, layers.10.attn.qkv.bias, layers.10.attn.proj.weight, layers.10.attn.proj.bias, layers.10.ln2.weight, layers.10.ln2.bias, layers.10.ffn.layers.0.0.weight, layers.10.ffn.layers.0.0.bias, layers.10.ffn.layers.1.weight, layers.10.ffn.layers.1.bias, layers.11.ln1.weight, layers.11.ln1.bias, layers.11.attn.qkv.weight, layers.11.attn.qkv.bias, layers.11.attn.proj.weight, layers.11.attn.proj.bias, layers.11.ln2.weight, layers.11.ln2.bias, layers.11.ffn.layers.0.0.weight, layers.11.ffn.layers.0.0.bias, layers.11.ffn.layers.1.weight, layers.11.ffn.layers.1.bias, layers.12.ln1.weight, layers.12.ln1.bias, layers.12.attn.qkv.weight, layers.12.attn.qkv.bias, layers.12.attn.proj.weight, layers.12.attn.proj.bias, layers.12.ln2.weight, layers.12.ln2.bias, layers.12.ffn.layers.0.0.weight, layers.12.ffn.layers.0.0.bias, layers.12.ffn.layers.1.weight, layers.12.ffn.layers.1.bias, layers.13.ln1.weight, layers.13.ln1.bias, layers.13.attn.qkv.weight, layers.13.attn.qkv.bias, layers.13.attn.proj.weight, layers.13.attn.proj.bias, layers.13.ln2.weight, layers.13.ln2.bias, layers.13.ffn.layers.0.0.weight, layers.13.ffn.layers.0.0.bias, layers.13.ffn.layers.1.weight, layers.13.ffn.layers.1.bias, layers.14.ln1.weight, layers.14.ln1.bias, layers.14.attn.qkv.weight, layers.14.attn.qkv.bias, layers.14.attn.proj.weight, layers.14.attn.proj.bias, layers.14.ln2.weight, layers.14.ln2.bias, layers.14.ffn.layers.0.0.weight, layers.14.ffn.layers.0.0.bias, layers.14.ffn.layers.1.weight, layers.14.ffn.layers.1.bias, layers.15.ln1.weight, layers.15.ln1.bias, layers.15.attn.qkv.weight, layers.15.attn.qkv.bias, layers.15.attn.proj.weight, layers.15.attn.proj.bias, layers.15.ln2.weight, layers.15.ln2.bias, layers.15.ffn.layers.0.0.weight, layers.15.ffn.layers.0.0.bias, layers.15.ffn.layers.1.weight, layers.15.ffn.layers.1.bias, layers.16.ln1.weight, layers.16.ln1.bias, layers.16.attn.qkv.weight, layers.16.attn.qkv.bias, layers.16.attn.proj.weight, layers.16.attn.proj.bias, layers.16.ln2.weight, layers.16.ln2.bias, layers.16.ffn.layers.0.0.weight, layers.16.ffn.layers.0.0.bias, layers.16.ffn.layers.1.weight, layers.16.ffn.layers.1.bias, layers.17.ln1.weight, layers.17.ln1.bias, layers.17.attn.qkv.weight, layers.17.attn.qkv.bias, layers.17.attn.proj.weight, layers.17.attn.proj.bias, layers.17.ln2.weight, layers.17.ln2.bias, layers.17.ffn.layers.0.0.weight, layers.17.ffn.layers.0.0.bias, layers.17.ffn.layers.1.weight, layers.17.ffn.layers.1.bias, layers.18.ln1.weight, layers.18.ln1.bias, layers.18.attn.qkv.weight, layers.18.attn.qkv.bias, layers.18.attn.proj.weight, layers.18.attn.proj.bias, layers.18.ln2.weight, layers.18.ln2.bias, layers.18.ffn.layers.0.0.weight, layers.18.ffn.layers.0.0.bias, layers.18.ffn.layers.1.weight, layers.18.ffn.layers.1.bias, layers.19.ln1.weight, layers.19.ln1.bias, layers.19.attn.qkv.weight, layers.19.attn.qkv.bias, layers.19.attn.proj.weight, layers.19.attn.proj.bias, layers.19.ln2.weight, layers.19.ln2.bias, layers.19.ffn.layers.0.0.weight, layers.19.ffn.layers.0.0.bias, layers.19.ffn.layers.1.weight, layers.19.ffn.layers.1.bias, layers.20.ln1.weight, layers.20.ln1.bias, layers.20.attn.qkv.weight, layers.20.attn.qkv.bias, layers.20.attn.proj.weight, layers.20.attn.proj.bias, layers.20.ln2.weight, layers.20.ln2.bias, layers.20.ffn.layers.0.0.weight, layers.20.ffn.layers.0.0.bias, layers.20.ffn.layers.1.weight, layers.20.ffn.layers.1.bias, layers.21.ln1.weight, layers.21.ln1.bias, layers.21.attn.qkv.weight, layers.21.attn.qkv.bias, layers.21.attn.proj.weight, layers.21.attn.proj.bias, layers.21.ln2.weight, layers.21.ln2.bias, layers.21.ffn.layers.0.0.weight, layers.21.ffn.layers.0.0.bias, layers.21.ffn.layers.1.weight, layers.21.ffn.layers.1.bias, layers.22.ln1.weight, layers.22.ln1.bias, layers.22.attn.qkv.weight, layers.22.attn.qkv.bias, layers.22.attn.proj.weight, layers.22.attn.proj.bias, layers.22.ln2.weight, layers.22.ln2.bias, layers.22.ffn.layers.0.0.weight, layers.22.ffn.layers.0.0.bias, layers.22.ffn.layers.1.weight, layers.22.ffn.layers.1.bias, layers.23.ln1.weight, layers.23.ln1.bias, layers.23.attn.qkv.weight, layers.23.attn.qkv.bias, layers.23.attn.proj.weight, layers.23.attn.proj.bias, layers.23.ln2.weight, layers.23.ln2.bias, layers.23.ffn.layers.0.0.weight, layers.23.ffn.layers.0.0.bias, layers.23.ffn.layers.1.weight, layers.23.ffn.layers.1.bias, ln1.weight, ln1.bias + +missing keys in source state_dict: proj + +Name of parameter - Initialization information + +backbone.cls_token - torch.Size([1, 1, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.pos_embed - torch.Size([1, 257, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.patch_embed.projection.weight - torch.Size([1024, 3, 14, 14]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.0.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.1.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.2.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.3.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.4.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.5.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.6.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.7.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.8.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.9.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.10.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.11.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.12.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.13.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.14.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.15.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.16.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.17.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.18.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.19.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.20.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.21.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.22.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ln1.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ln1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.attn.qkv.weight - torch.Size([3072, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.attn.qkv.bias - torch.Size([3072]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.attn.proj.weight - torch.Size([1024, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.attn.proj.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ln2.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ln2.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ffn.layers.0.0.weight - torch.Size([4096, 1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ffn.layers.0.0.bias - torch.Size([4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ffn.layers.1.weight - torch.Size([1024, 4096]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.layers.23.ffn.layers.1.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.pre_norm.weight - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +backbone.pre_norm.bias - torch.Size([1024]): +PretrainedInit: load from ckpt/openclip-ViT-L-14.pth + +neck.proj - torch.Size([1024, 768]): +The value is the same before and after calling `init_weights` of ImageClassifier + +head.fc.weight - torch.Size([2, 768]): +TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 + +head.fc.bias - torch.Size([2]): +TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 +2023/06/06 05:00:46 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io +2023/06/06 05:00:46 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. +2023/06/06 05:00:46 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/luzeyu/workspace/fakebench/mmpretrain/workdir/clip_large_pretrain_4x256_IF_lr1e-4. +2023/06/06 05:01:55 - mmengine - INFO - Epoch(train) [1][ 100/3937] lr: 9.9999e-05 eta: 7:29:53 time: 0.6355 data_time: 0.0017 memory: 44139 loss: 0.5122 +2023/06/06 05:02:58 - mmengine - INFO - Epoch(train) [1][ 200/3937] lr: 9.9994e-05 eta: 7:11:52 time: 0.6366 data_time: 0.0015 memory: 44139 loss: 0.4937 +2023/06/06 05:04:02 - mmengine - INFO - Epoch(train) [1][ 300/3937] lr: 9.9987e-05 eta: 7:05:16 time: 0.6359 data_time: 0.0015 memory: 44139 loss: 0.4727 +2023/06/06 05:05:05 - mmengine - INFO - Epoch(train) [1][ 400/3937] lr: 9.9977e-05 eta: 7:01:25 time: 0.6360 data_time: 0.0017 memory: 44139 loss: 0.4517 +2023/06/06 05:06:09 - mmengine - INFO - Epoch(train) [1][ 500/3937] lr: 9.9964e-05 eta: 6:58:43 time: 0.6357 data_time: 0.0015 memory: 44139 loss: 0.4451 +2023/06/06 05:07:13 - mmengine - INFO - Epoch(train) [1][ 600/3937] lr: 9.9949e-05 eta: 6:56:35 time: 0.6361 data_time: 0.0015 memory: 44139 loss: 0.4288 +2023/06/06 05:08:16 - mmengine - INFO - Epoch(train) [1][ 700/3937] lr: 9.9930e-05 eta: 6:54:44 time: 0.6368 data_time: 0.0014 memory: 44139 loss: 0.4537 +2023/06/06 05:09:20 - mmengine - INFO - Epoch(train) [1][ 800/3937] lr: 9.9909e-05 eta: 6:53:06 time: 0.6362 data_time: 0.0015 memory: 44139 loss: 0.4423 +2023/06/06 05:10:24 - mmengine - INFO - Epoch(train) [1][ 900/3937] lr: 9.9884e-05 eta: 6:51:36 time: 0.6361 data_time: 0.0017 memory: 44139 loss: 0.4625 +2023/06/06 05:11:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:11:27 - mmengine - INFO - Epoch(train) [1][1000/3937] lr: 9.9857e-05 eta: 6:50:13 time: 0.6368 data_time: 0.0016 memory: 44139 loss: 0.4689 +2023/06/06 05:12:31 - mmengine - INFO - Epoch(train) [1][1100/3937] lr: 9.9827e-05 eta: 6:49:09 time: 0.6370 data_time: 0.0016 memory: 44139 loss: 0.4332 +2023/06/06 05:13:35 - mmengine - INFO - Epoch(train) [1][1200/3937] lr: 9.9794e-05 eta: 6:47:51 time: 0.6362 data_time: 0.0014 memory: 44139 loss: 0.4505 +2023/06/06 05:14:40 - mmengine - INFO - Epoch(train) [1][1300/3937] lr: 9.9758e-05 eta: 6:47:02 time: 0.6367 data_time: 0.0015 memory: 44139 loss: 0.4287 +2023/06/06 05:15:43 - mmengine - INFO - Epoch(train) [1][1400/3937] lr: 9.9720e-05 eta: 6:45:46 time: 0.6370 data_time: 0.0014 memory: 44139 loss: 0.4348 +2023/06/06 05:16:47 - mmengine - INFO - Epoch(train) [1][1500/3937] lr: 9.9678e-05 eta: 6:44:31 time: 0.6361 data_time: 0.0014 memory: 44139 loss: 0.4104 +2023/06/06 05:17:51 - mmengine - INFO - Epoch(train) [1][1600/3937] lr: 9.9634e-05 eta: 6:43:18 time: 0.6372 data_time: 0.0015 memory: 44139 loss: 0.4315 +2023/06/06 05:18:55 - mmengine - INFO - Epoch(train) [1][1700/3937] lr: 9.9587e-05 eta: 6:42:10 time: 0.6372 data_time: 0.0015 memory: 44139 loss: 0.3877 +2023/06/06 05:19:59 - mmengine - INFO - Epoch(train) [1][1800/3937] lr: 9.9537e-05 eta: 6:41:00 time: 0.6368 data_time: 0.0015 memory: 44139 loss: 0.4208 +2023/06/06 05:21:02 - mmengine - INFO - Epoch(train) [1][1900/3937] lr: 9.9484e-05 eta: 6:39:48 time: 0.6369 data_time: 0.0016 memory: 44139 loss: 0.3864 +2023/06/06 05:22:06 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:22:06 - mmengine - INFO - Epoch(train) [1][2000/3937] lr: 9.9429e-05 eta: 6:38:41 time: 0.6362 data_time: 0.0018 memory: 44139 loss: 0.4355 +2023/06/06 05:23:10 - mmengine - INFO - Epoch(train) [1][2100/3937] lr: 9.9370e-05 eta: 6:37:31 time: 0.6362 data_time: 0.0015 memory: 44139 loss: 0.4060 +2023/06/06 05:24:13 - mmengine - INFO - Epoch(train) [1][2200/3937] lr: 9.9309e-05 eta: 6:36:21 time: 0.6362 data_time: 0.0015 memory: 44139 loss: 0.4165 +2023/06/06 05:25:17 - mmengine - INFO - Epoch(train) [1][2300/3937] lr: 9.9245e-05 eta: 6:35:13 time: 0.6361 data_time: 0.0017 memory: 44139 loss: 0.3778 +2023/06/06 05:26:22 - mmengine - INFO - Epoch(train) [1][2400/3937] lr: 9.9178e-05 eta: 6:34:23 time: 0.6380 data_time: 0.0021 memory: 44139 loss: 0.3887 +2023/06/06 05:27:26 - mmengine - INFO - Epoch(train) [1][2500/3937] lr: 9.9108e-05 eta: 6:33:13 time: 0.6361 data_time: 0.0015 memory: 44139 loss: 0.3986 +2023/06/06 05:28:29 - mmengine - INFO - Epoch(train) [1][2600/3937] lr: 9.9036e-05 eta: 6:32:05 time: 0.6398 data_time: 0.0017 memory: 44139 loss: 0.3802 +2023/06/06 05:29:33 - mmengine - INFO - Epoch(train) [1][2700/3937] lr: 9.8960e-05 eta: 6:30:56 time: 0.6364 data_time: 0.0015 memory: 44139 loss: 0.4019 +2023/06/06 05:30:37 - mmengine - INFO - Epoch(train) [1][2800/3937] lr: 9.8882e-05 eta: 6:29:48 time: 0.6359 data_time: 0.0014 memory: 44139 loss: 0.3907 +2023/06/06 05:31:40 - mmengine - INFO - Epoch(train) [1][2900/3937] lr: 9.8801e-05 eta: 6:28:39 time: 0.6360 data_time: 0.0015 memory: 44139 loss: 0.3792 +2023/06/06 05:32:44 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:32:44 - mmengine - INFO - Epoch(train) [1][3000/3937] lr: 9.8718e-05 eta: 6:27:32 time: 0.6364 data_time: 0.0014 memory: 44139 loss: 0.3677 +2023/06/06 05:33:48 - mmengine - INFO - Epoch(train) [1][3100/3937] lr: 9.8631e-05 eta: 6:26:25 time: 0.6362 data_time: 0.0017 memory: 44139 loss: 0.4087 +2023/06/06 05:36:14 - mmengine - INFO - Epoch(train) [1][3200/3937] lr: 9.8542e-05 eta: 6:40:52 time: 0.6348 data_time: 0.0015 memory: 44139 loss: 0.4124 +2023/06/06 05:37:17 - mmengine - INFO - Epoch(train) [1][3300/3937] lr: 9.8450e-05 eta: 6:39:14 time: 0.6361 data_time: 0.0015 memory: 44139 loss: 0.3805 +2023/06/06 05:38:21 - mmengine - INFO - Epoch(train) [1][3400/3937] lr: 9.8355e-05 eta: 6:37:39 time: 0.6366 data_time: 0.0015 memory: 44139 loss: 0.3824 +2023/06/06 05:39:25 - mmengine - INFO - Epoch(train) [1][3500/3937] lr: 9.8257e-05 eta: 6:36:11 time: 0.6371 data_time: 0.0014 memory: 44139 loss: 0.3761 +2023/06/06 05:40:29 - mmengine - INFO - Epoch(train) [1][3600/3937] lr: 9.8157e-05 eta: 6:34:39 time: 0.6378 data_time: 0.0015 memory: 44139 loss: 0.3861 +2023/06/06 05:41:33 - mmengine - INFO - Epoch(train) [1][3700/3937] lr: 9.8054e-05 eta: 6:33:09 time: 0.6381 data_time: 0.0016 memory: 44139 loss: 0.3839 +2023/06/06 05:42:36 - mmengine - INFO - Epoch(train) [1][3800/3937] lr: 9.7948e-05 eta: 6:31:40 time: 0.6371 data_time: 0.0015 memory: 44139 loss: 0.3808 +2023/06/06 05:43:40 - mmengine - INFO - Epoch(train) [1][3900/3937] lr: 9.7840e-05 eta: 6:30:14 time: 0.6362 data_time: 0.0014 memory: 44139 loss: 0.3776 +2023/06/06 05:44:04 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:44:04 - mmengine - INFO - Saving checkpoint at 1 epochs +2023/06/06 05:45:38 - mmengine - INFO - Epoch(val) [1][57/57] accuracy/top1: 80.4809 single-label/precision_classwise: [89.67041015625, 73.00264739990234] single-label/recall_classwise: [72.99413299560547, 89.6744155883789] single-label/f1-score_classwise: [80.47744750976562, 80.48423767089844] data_time: 0.0251 time: 1.3206 +2023/06/06 05:46:21 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:46:45 - mmengine - INFO - Epoch(train) [2][ 100/3937] lr: 9.7686e-05 eta: 6:28:47 time: 0.6394 data_time: 0.0016 memory: 44139 loss: 0.3625 +2023/06/06 05:47:49 - mmengine - INFO - Epoch(train) [2][ 200/3937] lr: 9.7571e-05 eta: 6:27:21 time: 0.6369 data_time: 0.0013 memory: 44138 loss: 0.3595 +2023/06/06 05:48:52 - mmengine - INFO - Epoch(train) [2][ 300/3937] lr: 9.7454e-05 eta: 6:25:56 time: 0.6368 data_time: 0.0014 memory: 44138 loss: 0.3616 +2023/06/06 05:49:56 - mmengine - INFO - Epoch(train) [2][ 400/3937] lr: 9.7333e-05 eta: 6:24:33 time: 0.6390 data_time: 0.0014 memory: 44138 loss: 0.3791 +2023/06/06 05:51:00 - mmengine - INFO - Epoch(train) [2][ 500/3937] lr: 9.7210e-05 eta: 6:23:11 time: 0.6482 data_time: 0.0015 memory: 44138 loss: 0.3935 +2023/06/06 05:52:04 - mmengine - INFO - Epoch(train) [2][ 600/3937] lr: 9.7084e-05 eta: 6:21:49 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3580 +2023/06/06 05:53:07 - mmengine - INFO - Epoch(train) [2][ 700/3937] lr: 9.6956e-05 eta: 6:20:27 time: 0.6371 data_time: 0.0016 memory: 44138 loss: 0.3991 +2023/06/06 05:54:11 - mmengine - INFO - Epoch(train) [2][ 800/3937] lr: 9.6825e-05 eta: 6:19:07 time: 0.6358 data_time: 0.0014 memory: 44138 loss: 0.3925 +2023/06/06 05:55:21 - mmengine - INFO - Epoch(train) [2][ 900/3937] lr: 9.6691e-05 eta: 6:18:30 time: 0.6383 data_time: 0.0015 memory: 44138 loss: 0.3729 +2023/06/06 05:56:24 - mmengine - INFO - Epoch(train) [2][1000/3937] lr: 9.6554e-05 eta: 6:17:10 time: 0.6391 data_time: 0.0016 memory: 44138 loss: 0.3283 +2023/06/06 05:57:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 05:57:28 - mmengine - INFO - Epoch(train) [2][1100/3937] lr: 9.6415e-05 eta: 6:15:51 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.3831 +2023/06/06 05:58:32 - mmengine - INFO - Epoch(train) [2][1200/3937] lr: 9.6273e-05 eta: 6:14:32 time: 0.6368 data_time: 0.0014 memory: 44138 loss: 0.3891 +2023/06/06 05:59:36 - mmengine - INFO - Epoch(train) [2][1300/3937] lr: 9.6129e-05 eta: 6:13:13 time: 0.6361 data_time: 0.0014 memory: 44138 loss: 0.3717 +2023/06/06 06:00:39 - mmengine - INFO - Epoch(train) [2][1400/3937] lr: 9.5982e-05 eta: 6:11:56 time: 0.6363 data_time: 0.0014 memory: 44138 loss: 0.3645 +2023/06/06 06:01:43 - mmengine - INFO - Epoch(train) [2][1500/3937] lr: 9.5832e-05 eta: 6:10:39 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3516 +2023/06/06 06:02:47 - mmengine - INFO - Epoch(train) [2][1600/3937] lr: 9.5680e-05 eta: 6:09:23 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3908 +2023/06/06 06:03:51 - mmengine - INFO - Epoch(train) [2][1700/3937] lr: 9.5525e-05 eta: 6:08:07 time: 0.6374 data_time: 0.0017 memory: 44138 loss: 0.3329 +2023/06/06 06:04:54 - mmengine - INFO - Epoch(train) [2][1800/3937] lr: 9.5368e-05 eta: 6:06:51 time: 0.6382 data_time: 0.0016 memory: 44138 loss: 0.3408 +2023/06/06 06:05:58 - mmengine - INFO - Epoch(train) [2][1900/3937] lr: 9.5208e-05 eta: 6:05:36 time: 0.6384 data_time: 0.0018 memory: 44138 loss: 0.3576 +2023/06/06 06:07:02 - mmengine - INFO - Epoch(train) [2][2000/3937] lr: 9.5045e-05 eta: 6:04:20 time: 0.6363 data_time: 0.0017 memory: 44138 loss: 0.3598 +2023/06/06 06:07:42 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:08:05 - mmengine - INFO - Epoch(train) [2][2100/3937] lr: 9.4880e-05 eta: 6:03:06 time: 0.6373 data_time: 0.0017 memory: 44138 loss: 0.3374 +2023/06/06 06:09:09 - mmengine - INFO - Epoch(train) [2][2200/3937] lr: 9.4713e-05 eta: 6:01:51 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3715 +2023/06/06 06:10:13 - mmengine - INFO - Epoch(train) [2][2300/3937] lr: 9.4543e-05 eta: 6:00:37 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3563 +2023/06/06 06:11:17 - mmengine - INFO - Epoch(train) [2][2400/3937] lr: 9.4370e-05 eta: 5:59:24 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3385 +2023/06/06 06:12:20 - mmengine - INFO - Epoch(train) [2][2500/3937] lr: 9.4195e-05 eta: 5:58:11 time: 0.6366 data_time: 0.0017 memory: 44138 loss: 0.3685 +2023/06/06 06:13:24 - mmengine - INFO - Epoch(train) [2][2600/3937] lr: 9.4017e-05 eta: 5:56:57 time: 0.6367 data_time: 0.0014 memory: 44138 loss: 0.3705 +2023/06/06 06:14:28 - mmengine - INFO - Epoch(train) [2][2700/3937] lr: 9.3837e-05 eta: 5:55:45 time: 0.6373 data_time: 0.0025 memory: 44138 loss: 0.3419 +2023/06/06 06:15:32 - mmengine - INFO - Epoch(train) [2][2800/3937] lr: 9.3654e-05 eta: 5:54:34 time: 0.6380 data_time: 0.0016 memory: 44138 loss: 0.3687 +2023/06/06 06:16:35 - mmengine - INFO - Epoch(train) [2][2900/3937] lr: 9.3469e-05 eta: 5:53:22 time: 0.6378 data_time: 0.0015 memory: 44138 loss: 0.3347 +2023/06/06 06:17:39 - mmengine - INFO - Epoch(train) [2][3000/3937] lr: 9.3282e-05 eta: 5:52:10 time: 0.6371 data_time: 0.0016 memory: 44138 loss: 0.3643 +2023/06/06 06:18:19 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:18:43 - mmengine - INFO - Epoch(train) [2][3100/3937] lr: 9.3092e-05 eta: 5:50:58 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.3295 +2023/06/06 06:19:47 - mmengine - INFO - Epoch(train) [2][3200/3937] lr: 9.2899e-05 eta: 5:49:46 time: 0.6371 data_time: 0.0017 memory: 44138 loss: 0.3336 +2023/06/06 06:20:50 - mmengine - INFO - Epoch(train) [2][3300/3937] lr: 9.2705e-05 eta: 5:48:35 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3379 +2023/06/06 06:21:54 - mmengine - INFO - Epoch(train) [2][3400/3937] lr: 9.2507e-05 eta: 5:47:24 time: 0.6369 data_time: 0.0014 memory: 44138 loss: 0.3514 +2023/06/06 06:22:58 - mmengine - INFO - Epoch(train) [2][3500/3937] lr: 9.2308e-05 eta: 5:46:13 time: 0.6377 data_time: 0.0015 memory: 44138 loss: 0.3443 +2023/06/06 06:24:01 - mmengine - INFO - Epoch(train) [2][3600/3937] lr: 9.2106e-05 eta: 5:45:02 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3348 +2023/06/06 06:25:05 - mmengine - INFO - Epoch(train) [2][3700/3937] lr: 9.1902e-05 eta: 5:43:51 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3649 +2023/06/06 06:26:09 - mmengine - INFO - Epoch(train) [2][3800/3937] lr: 9.1695e-05 eta: 5:42:41 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3500 +2023/06/06 06:27:13 - mmengine - INFO - Epoch(train) [2][3900/3937] lr: 9.1486e-05 eta: 5:41:31 time: 0.6375 data_time: 0.0016 memory: 44138 loss: 0.3576 +2023/06/06 06:27:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:27:36 - mmengine - INFO - Saving checkpoint at 2 epochs +2023/06/06 06:29:08 - mmengine - INFO - Epoch(val) [2][57/57] accuracy/top1: 78.8316 single-label/precision_classwise: [96.29875183105469, 68.72116088867188] single-label/recall_classwise: [64.0552978515625, 96.97674560546875] single-label/f1-score_classwise: [76.9353256225586, 80.43981170654297] data_time: 0.0165 time: 1.2614 +2023/06/06 06:30:15 - mmengine - INFO - Epoch(train) [3][ 100/3937] lr: 9.1196e-05 eta: 5:40:07 time: 0.6431 data_time: 0.0015 memory: 44138 loss: 0.3411 +2023/06/06 06:30:31 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:31:18 - mmengine - INFO - Epoch(train) [3][ 200/3937] lr: 9.0981e-05 eta: 5:38:57 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.3388 +2023/06/06 06:32:22 - mmengine - INFO - Epoch(train) [3][ 300/3937] lr: 9.0764e-05 eta: 5:37:47 time: 0.6391 data_time: 0.0016 memory: 44138 loss: 0.3596 +2023/06/06 06:33:26 - mmengine - INFO - Epoch(train) [3][ 400/3937] lr: 9.0545e-05 eta: 5:36:38 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3803 +2023/06/06 06:34:30 - mmengine - INFO - Epoch(train) [3][ 500/3937] lr: 9.0324e-05 eta: 5:35:28 time: 0.6369 data_time: 0.0015 memory: 44138 loss: 0.3338 +2023/06/06 06:35:33 - mmengine - INFO - Epoch(train) [3][ 600/3937] lr: 9.0100e-05 eta: 5:34:19 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3524 +2023/06/06 06:36:37 - mmengine - INFO - Epoch(train) [3][ 700/3937] lr: 8.9875e-05 eta: 5:33:10 time: 0.6372 data_time: 0.0018 memory: 44138 loss: 0.3310 +2023/06/06 06:37:41 - mmengine - INFO - Epoch(train) [3][ 800/3937] lr: 8.9647e-05 eta: 5:32:01 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3386 +2023/06/06 06:38:45 - mmengine - INFO - Epoch(train) [3][ 900/3937] lr: 8.9416e-05 eta: 5:30:52 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3177 +2023/06/06 06:39:48 - mmengine - INFO - Epoch(train) [3][1000/3937] lr: 8.9184e-05 eta: 5:29:43 time: 0.6374 data_time: 0.0015 memory: 44138 loss: 0.3489 +2023/06/06 06:40:52 - mmengine - INFO - Epoch(train) [3][1100/3937] lr: 8.8949e-05 eta: 5:28:35 time: 0.6476 data_time: 0.0017 memory: 44138 loss: 0.3389 +2023/06/06 06:41:09 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:41:56 - mmengine - INFO - Epoch(train) [3][1200/3937] lr: 8.8712e-05 eta: 5:27:26 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.3414 +2023/06/06 06:43:00 - mmengine - INFO - Epoch(train) [3][1300/3937] lr: 8.8474e-05 eta: 5:26:18 time: 0.6401 data_time: 0.0015 memory: 44138 loss: 0.3254 +2023/06/06 06:44:04 - mmengine - INFO - Epoch(train) [3][1400/3937] lr: 8.8232e-05 eta: 5:25:09 time: 0.6372 data_time: 0.0014 memory: 44138 loss: 0.3486 +2023/06/06 06:45:07 - mmengine - INFO - Epoch(train) [3][1500/3937] lr: 8.7989e-05 eta: 5:24:01 time: 0.6373 data_time: 0.0014 memory: 44138 loss: 0.3306 +2023/06/06 06:46:11 - mmengine - INFO - Epoch(train) [3][1600/3937] lr: 8.7744e-05 eta: 5:22:53 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3267 +2023/06/06 06:47:15 - mmengine - INFO - Epoch(train) [3][1700/3937] lr: 8.7497e-05 eta: 5:21:45 time: 0.6383 data_time: 0.0017 memory: 44138 loss: 0.3426 +2023/06/06 06:48:18 - mmengine - INFO - Epoch(train) [3][1800/3937] lr: 8.7247e-05 eta: 5:20:36 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3574 +2023/06/06 06:49:22 - mmengine - INFO - Epoch(train) [3][1900/3937] lr: 8.6996e-05 eta: 5:19:28 time: 0.6387 data_time: 0.0019 memory: 44138 loss: 0.3522 +2023/06/06 06:50:26 - mmengine - INFO - Epoch(train) [3][2000/3937] lr: 8.6742e-05 eta: 5:18:21 time: 0.6389 data_time: 0.0016 memory: 44138 loss: 0.3137 +2023/06/06 06:51:30 - mmengine - INFO - Epoch(train) [3][2100/3937] lr: 8.6487e-05 eta: 5:17:13 time: 0.6372 data_time: 0.0017 memory: 44138 loss: 0.3321 +2023/06/06 06:51:46 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 06:52:34 - mmengine - INFO - Epoch(train) [3][2200/3937] lr: 8.6229e-05 eta: 5:16:06 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3593 +2023/06/06 06:53:37 - mmengine - INFO - Epoch(train) [3][2300/3937] lr: 8.5970e-05 eta: 5:14:58 time: 0.6370 data_time: 0.0017 memory: 44138 loss: 0.3654 +2023/06/06 06:54:41 - mmengine - INFO - Epoch(train) [3][2400/3937] lr: 8.5708e-05 eta: 5:13:50 time: 0.6361 data_time: 0.0016 memory: 44138 loss: 0.3468 +2023/06/06 06:55:45 - mmengine - INFO - Epoch(train) [3][2500/3937] lr: 8.5445e-05 eta: 5:12:43 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3359 +2023/06/06 06:56:48 - mmengine - INFO - Epoch(train) [3][2600/3937] lr: 8.5179e-05 eta: 5:11:35 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3342 +2023/06/06 06:57:52 - mmengine - INFO - Epoch(train) [3][2700/3937] lr: 8.4912e-05 eta: 5:10:28 time: 0.6385 data_time: 0.0015 memory: 44138 loss: 0.3113 +2023/06/06 06:58:56 - mmengine - INFO - Epoch(train) [3][2800/3937] lr: 8.4643e-05 eta: 5:09:21 time: 0.6391 data_time: 0.0017 memory: 44138 loss: 0.3383 +2023/06/06 07:00:00 - mmengine - INFO - Epoch(train) [3][2900/3937] lr: 8.4372e-05 eta: 5:08:14 time: 0.6382 data_time: 0.0014 memory: 44138 loss: 0.3224 +2023/06/06 07:01:04 - mmengine - INFO - Epoch(train) [3][3000/3937] lr: 8.4099e-05 eta: 5:07:07 time: 0.6373 data_time: 0.0016 memory: 44138 loss: 0.3374 +2023/06/06 07:02:07 - mmengine - INFO - Epoch(train) [3][3100/3937] lr: 8.3824e-05 eta: 5:06:00 time: 0.6373 data_time: 0.0017 memory: 44138 loss: 0.3260 +2023/06/06 07:02:24 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:03:11 - mmengine - INFO - Epoch(train) [3][3200/3937] lr: 8.3547e-05 eta: 5:04:53 time: 0.6373 data_time: 0.0015 memory: 44138 loss: 0.3232 +2023/06/06 07:04:15 - mmengine - INFO - Epoch(train) [3][3300/3937] lr: 8.3269e-05 eta: 5:03:46 time: 0.6367 data_time: 0.0017 memory: 44138 loss: 0.3508 +2023/06/06 07:05:19 - mmengine - INFO - Epoch(train) [3][3400/3937] lr: 8.2988e-05 eta: 5:02:39 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3453 +2023/06/06 07:06:22 - mmengine - INFO - Epoch(train) [3][3500/3937] lr: 8.2706e-05 eta: 5:01:32 time: 0.6367 data_time: 0.0016 memory: 44138 loss: 0.3596 +2023/06/06 07:07:26 - mmengine - INFO - Epoch(train) [3][3600/3937] lr: 8.2423e-05 eta: 5:00:26 time: 0.6418 data_time: 0.0022 memory: 44138 loss: 0.3164 +2023/06/06 07:08:30 - mmengine - INFO - Epoch(train) [3][3700/3937] lr: 8.2137e-05 eta: 4:59:20 time: 0.6377 data_time: 0.0017 memory: 44138 loss: 0.3380 +2023/06/06 07:09:34 - mmengine - INFO - Epoch(train) [3][3800/3937] lr: 8.1850e-05 eta: 4:58:13 time: 0.6373 data_time: 0.0016 memory: 44138 loss: 0.3182 +2023/06/06 07:10:38 - mmengine - INFO - Epoch(train) [3][3900/3937] lr: 8.1561e-05 eta: 4:57:06 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3442 +2023/06/06 07:11:01 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:11:01 - mmengine - INFO - Saving checkpoint at 3 epochs +2023/06/06 07:12:32 - mmengine - INFO - Epoch(val) [3][57/57] accuracy/top1: 82.1649 single-label/precision_classwise: [97.1237564086914, 72.37509155273438] single-label/recall_classwise: [69.70519256591797, 97.46511840820312] single-label/f1-score_classwise: [81.16133880615234, 83.06686401367188] data_time: 0.0157 time: 1.2586 +2023/06/06 07:13:39 - mmengine - INFO - Epoch(train) [4][ 100/3937] lr: 8.1162e-05 eta: 4:55:43 time: 0.6382 data_time: 0.0031 memory: 44138 loss: 0.3380 +2023/06/06 07:14:36 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:14:43 - mmengine - INFO - Epoch(train) [4][ 200/3937] lr: 8.0869e-05 eta: 4:54:36 time: 0.6364 data_time: 0.0016 memory: 44138 loss: 0.3376 +2023/06/06 07:15:47 - mmengine - INFO - Epoch(train) [4][ 300/3937] lr: 8.0574e-05 eta: 4:53:29 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3617 +2023/06/06 07:16:51 - mmengine - INFO - Epoch(train) [4][ 400/3937] lr: 8.0278e-05 eta: 4:52:23 time: 0.6372 data_time: 0.0016 memory: 44138 loss: 0.3121 +2023/06/06 07:17:54 - mmengine - INFO - Epoch(train) [4][ 500/3937] lr: 7.9980e-05 eta: 4:51:16 time: 0.6371 data_time: 0.0018 memory: 44138 loss: 0.3400 +2023/06/06 07:18:58 - mmengine - INFO - Epoch(train) [4][ 600/3937] lr: 7.9681e-05 eta: 4:50:10 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3378 +2023/06/06 07:20:02 - mmengine - INFO - Epoch(train) [4][ 700/3937] lr: 7.9380e-05 eta: 4:49:04 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3383 +2023/06/06 07:21:06 - mmengine - INFO - Epoch(train) [4][ 800/3937] lr: 7.9077e-05 eta: 4:47:57 time: 0.6374 data_time: 0.0022 memory: 44138 loss: 0.3340 +2023/06/06 07:22:09 - mmengine - INFO - Epoch(train) [4][ 900/3937] lr: 7.8773e-05 eta: 4:46:51 time: 0.6368 data_time: 0.0015 memory: 44138 loss: 0.3364 +2023/06/06 07:23:13 - mmengine - INFO - Epoch(train) [4][1000/3937] lr: 7.8467e-05 eta: 4:45:45 time: 0.6369 data_time: 0.0014 memory: 44138 loss: 0.3190 +2023/06/06 07:24:17 - mmengine - INFO - Epoch(train) [4][1100/3937] lr: 7.8160e-05 eta: 4:44:38 time: 0.6368 data_time: 0.0018 memory: 44138 loss: 0.3354 +2023/06/06 07:25:14 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:25:21 - mmengine - INFO - Epoch(train) [4][1200/3937] lr: 7.7852e-05 eta: 4:43:32 time: 0.6379 data_time: 0.0015 memory: 44138 loss: 0.3120 +2023/06/06 07:26:24 - mmengine - INFO - Epoch(train) [4][1300/3937] lr: 7.7541e-05 eta: 4:42:26 time: 0.6379 data_time: 0.0016 memory: 44138 loss: 0.3525 +2023/06/06 07:27:28 - mmengine - INFO - Epoch(train) [4][1400/3937] lr: 7.7230e-05 eta: 4:41:20 time: 0.6378 data_time: 0.0014 memory: 44138 loss: 0.3322 +2023/06/06 07:28:32 - mmengine - INFO - Epoch(train) [4][1500/3937] lr: 7.6917e-05 eta: 4:40:14 time: 0.6376 data_time: 0.0016 memory: 44138 loss: 0.3502 +2023/06/06 07:29:36 - mmengine - INFO - Epoch(train) [4][1600/3937] lr: 7.6603e-05 eta: 4:39:08 time: 0.6373 data_time: 0.0016 memory: 44138 loss: 0.3586 +2023/06/06 07:30:40 - mmengine - INFO - Epoch(train) [4][1700/3937] lr: 7.6287e-05 eta: 4:38:02 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3289 +2023/06/06 07:31:43 - mmengine - INFO - Epoch(train) [4][1800/3937] lr: 7.5970e-05 eta: 4:36:56 time: 0.6379 data_time: 0.0018 memory: 44138 loss: 0.3384 +2023/06/06 07:32:47 - mmengine - INFO - Epoch(train) [4][1900/3937] lr: 7.5652e-05 eta: 4:35:51 time: 0.6375 data_time: 0.0015 memory: 44138 loss: 0.3200 +2023/06/06 07:33:51 - mmengine - INFO - Epoch(train) [4][2000/3937] lr: 7.5332e-05 eta: 4:34:45 time: 0.6369 data_time: 0.0017 memory: 44138 loss: 0.3320 +2023/06/06 07:34:55 - mmengine - INFO - Epoch(train) [4][2100/3937] lr: 7.5011e-05 eta: 4:33:39 time: 0.6373 data_time: 0.0020 memory: 44138 loss: 0.3438 +2023/06/06 07:35:51 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:35:58 - mmengine - INFO - Epoch(train) [4][2200/3937] lr: 7.4689e-05 eta: 4:32:33 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3016 +2023/06/06 07:37:02 - mmengine - INFO - Epoch(train) [4][2300/3937] lr: 7.4365e-05 eta: 4:31:27 time: 0.6376 data_time: 0.0023 memory: 44138 loss: 0.3412 +2023/06/06 07:38:06 - mmengine - INFO - Epoch(train) [4][2400/3937] lr: 7.4040e-05 eta: 4:30:21 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3275 +2023/06/06 07:39:10 - mmengine - INFO - Epoch(train) [4][2500/3937] lr: 7.3714e-05 eta: 4:29:16 time: 0.6370 data_time: 0.0014 memory: 44138 loss: 0.3261 +2023/06/06 07:40:13 - mmengine - INFO - Epoch(train) [4][2600/3937] lr: 7.3387e-05 eta: 4:28:10 time: 0.6382 data_time: 0.0014 memory: 44138 loss: 0.3429 +2023/06/06 07:41:17 - mmengine - INFO - Epoch(train) [4][2700/3937] lr: 7.3059e-05 eta: 4:27:04 time: 0.6380 data_time: 0.0018 memory: 44138 loss: 0.3348 +2023/06/06 07:42:21 - mmengine - INFO - Epoch(train) [4][2800/3937] lr: 7.2730e-05 eta: 4:25:58 time: 0.6372 data_time: 0.0018 memory: 44138 loss: 0.3406 +2023/06/06 07:43:25 - mmengine - INFO - Epoch(train) [4][2900/3937] lr: 7.2399e-05 eta: 4:24:53 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3422 +2023/06/06 07:44:28 - mmengine - INFO - Epoch(train) [4][3000/3937] lr: 7.2067e-05 eta: 4:23:47 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3132 +2023/06/06 07:45:32 - mmengine - INFO - Epoch(train) [4][3100/3937] lr: 7.1734e-05 eta: 4:22:42 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3458 +2023/06/06 07:46:29 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:46:36 - mmengine - INFO - Epoch(train) [4][3200/3937] lr: 7.1401e-05 eta: 4:21:36 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3669 +2023/06/06 07:47:40 - mmengine - INFO - Epoch(train) [4][3300/3937] lr: 7.1066e-05 eta: 4:20:31 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3488 +2023/06/06 07:48:44 - mmengine - INFO - Epoch(train) [4][3400/3937] lr: 7.0730e-05 eta: 4:19:25 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3177 +2023/06/06 07:49:47 - mmengine - INFO - Epoch(train) [4][3500/3937] lr: 7.0393e-05 eta: 4:18:20 time: 0.6365 data_time: 0.0015 memory: 44138 loss: 0.3466 +2023/06/06 07:50:51 - mmengine - INFO - Epoch(train) [4][3600/3937] lr: 7.0055e-05 eta: 4:17:14 time: 0.6370 data_time: 0.0015 memory: 44138 loss: 0.3368 +2023/06/06 07:51:55 - mmengine - INFO - Epoch(train) [4][3700/3937] lr: 6.9716e-05 eta: 4:16:09 time: 0.6362 data_time: 0.0015 memory: 44138 loss: 0.3190 +2023/06/06 07:52:59 - mmengine - INFO - Epoch(train) [4][3800/3937] lr: 6.9376e-05 eta: 4:15:03 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3387 +2023/06/06 07:54:02 - mmengine - INFO - Epoch(train) [4][3900/3937] lr: 6.9035e-05 eta: 4:13:58 time: 0.6374 data_time: 0.0018 memory: 44138 loss: 0.3340 +2023/06/06 07:54:26 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:54:26 - mmengine - INFO - Saving checkpoint at 4 epochs +2023/06/06 07:55:57 - mmengine - INFO - Epoch(val) [4][57/57] accuracy/top1: 86.2566 single-label/precision_classwise: [97.55258178710938, 77.5588150024414] single-label/recall_classwise: [76.99640655517578, 97.6279067993164] single-label/f1-score_classwise: [86.06407165527344, 86.44381713867188] data_time: 0.0159 time: 1.2590 +2023/06/06 07:57:04 - mmengine - INFO - Epoch(train) [5][ 100/3937] lr: 6.8567e-05 eta: 4:12:33 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3264 +2023/06/06 07:58:08 - mmengine - INFO - Epoch(train) [5][ 200/3937] lr: 6.8224e-05 eta: 4:11:28 time: 0.6375 data_time: 0.0015 memory: 44138 loss: 0.3349 +2023/06/06 07:58:41 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 07:59:12 - mmengine - INFO - Epoch(train) [5][ 300/3937] lr: 6.7881e-05 eta: 4:10:23 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3428 +2023/06/06 08:00:15 - mmengine - INFO - Epoch(train) [5][ 400/3937] lr: 6.7536e-05 eta: 4:09:17 time: 0.6381 data_time: 0.0026 memory: 44138 loss: 0.3338 +2023/06/06 08:01:19 - mmengine - INFO - Epoch(train) [5][ 500/3937] lr: 6.7191e-05 eta: 4:08:12 time: 0.6389 data_time: 0.0021 memory: 44138 loss: 0.3222 +2023/06/06 08:02:23 - mmengine - INFO - Epoch(train) [5][ 600/3937] lr: 6.6845e-05 eta: 4:07:07 time: 0.6428 data_time: 0.0021 memory: 44138 loss: 0.3249 +2023/06/06 08:03:28 - mmengine - INFO - Epoch(train) [5][ 700/3937] lr: 6.6498e-05 eta: 4:06:02 time: 0.6384 data_time: 0.0018 memory: 44138 loss: 0.3563 +2023/06/06 08:04:32 - mmengine - INFO - Epoch(train) [5][ 800/3937] lr: 6.6151e-05 eta: 4:04:58 time: 0.6386 data_time: 0.0026 memory: 44138 loss: 0.3415 +2023/06/06 08:05:35 - mmengine - INFO - Epoch(train) [5][ 900/3937] lr: 6.5802e-05 eta: 4:03:52 time: 0.6362 data_time: 0.0020 memory: 44138 loss: 0.3410 +2023/06/06 08:06:39 - mmengine - INFO - Epoch(train) [5][1000/3937] lr: 6.5454e-05 eta: 4:02:47 time: 0.6389 data_time: 0.0020 memory: 44138 loss: 0.3617 +2023/06/06 08:07:43 - mmengine - INFO - Epoch(train) [5][1100/3937] lr: 6.5104e-05 eta: 4:01:42 time: 0.6379 data_time: 0.0020 memory: 44138 loss: 0.3619 +2023/06/06 08:08:47 - mmengine - INFO - Epoch(train) [5][1200/3937] lr: 6.4754e-05 eta: 4:00:37 time: 0.6412 data_time: 0.0019 memory: 44138 loss: 0.3187 +2023/06/06 08:09:20 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:09:51 - mmengine - INFO - Epoch(train) [5][1300/3937] lr: 6.4403e-05 eta: 3:59:32 time: 0.6368 data_time: 0.0019 memory: 44138 loss: 0.3272 +2023/06/06 08:10:55 - mmengine - INFO - Epoch(train) [5][1400/3937] lr: 6.4051e-05 eta: 3:58:27 time: 0.6371 data_time: 0.0020 memory: 44138 loss: 0.3496 +2023/06/06 08:11:58 - mmengine - INFO - Epoch(train) [5][1500/3937] lr: 6.3699e-05 eta: 3:57:22 time: 0.6372 data_time: 0.0024 memory: 44138 loss: 0.3175 +2023/06/06 08:13:02 - mmengine - INFO - Epoch(train) [5][1600/3937] lr: 6.3347e-05 eta: 3:56:16 time: 0.6371 data_time: 0.0023 memory: 44138 loss: 0.3220 +2023/06/06 08:14:06 - mmengine - INFO - Epoch(train) [5][1700/3937] lr: 6.2994e-05 eta: 3:55:11 time: 0.6377 data_time: 0.0022 memory: 44138 loss: 0.3163 +2023/06/06 08:15:10 - mmengine - INFO - Epoch(train) [5][1800/3937] lr: 6.2640e-05 eta: 3:54:06 time: 0.6382 data_time: 0.0017 memory: 44138 loss: 0.3425 +2023/06/06 08:16:14 - mmengine - INFO - Epoch(train) [5][1900/3937] lr: 6.2286e-05 eta: 3:53:02 time: 0.6394 data_time: 0.0018 memory: 44138 loss: 0.3069 +2023/06/06 08:17:18 - mmengine - INFO - Epoch(train) [5][2000/3937] lr: 6.1931e-05 eta: 3:51:57 time: 0.6384 data_time: 0.0027 memory: 44138 loss: 0.3705 +2023/06/06 08:18:22 - mmengine - INFO - Epoch(train) [5][2100/3937] lr: 6.1576e-05 eta: 3:50:52 time: 0.6364 data_time: 0.0020 memory: 44138 loss: 0.3499 +2023/06/06 08:19:26 - mmengine - INFO - Epoch(train) [5][2200/3937] lr: 6.1221e-05 eta: 3:49:47 time: 0.6382 data_time: 0.0024 memory: 44138 loss: 0.3240 +2023/06/06 08:19:59 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:20:29 - mmengine - INFO - Epoch(train) [5][2300/3937] lr: 6.0865e-05 eta: 3:48:42 time: 0.6373 data_time: 0.0018 memory: 44138 loss: 0.3075 +2023/06/06 08:21:33 - mmengine - INFO - Epoch(train) [5][2400/3937] lr: 6.0509e-05 eta: 3:47:37 time: 0.6380 data_time: 0.0018 memory: 44138 loss: 0.3451 +2023/06/06 08:22:37 - mmengine - INFO - Epoch(train) [5][2500/3937] lr: 6.0152e-05 eta: 3:46:32 time: 0.6389 data_time: 0.0018 memory: 44138 loss: 0.3387 +2023/06/06 08:23:41 - mmengine - INFO - Epoch(train) [5][2600/3937] lr: 5.9795e-05 eta: 3:45:27 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.3282 +2023/06/06 08:24:45 - mmengine - INFO - Epoch(train) [5][2700/3937] lr: 5.9438e-05 eta: 3:44:22 time: 0.6377 data_time: 0.0017 memory: 44138 loss: 0.3411 +2023/06/06 08:25:49 - mmengine - INFO - Epoch(train) [5][2800/3937] lr: 5.9081e-05 eta: 3:43:17 time: 0.6385 data_time: 0.0027 memory: 44138 loss: 0.3036 +2023/06/06 08:26:52 - mmengine - INFO - Epoch(train) [5][2900/3937] lr: 5.8723e-05 eta: 3:42:12 time: 0.6391 data_time: 0.0015 memory: 44138 loss: 0.3333 +2023/06/06 08:27:56 - mmengine - INFO - Epoch(train) [5][3000/3937] lr: 5.8365e-05 eta: 3:41:07 time: 0.6406 data_time: 0.0018 memory: 44138 loss: 0.3187 +2023/06/06 08:29:00 - mmengine - INFO - Epoch(train) [5][3100/3937] lr: 5.8007e-05 eta: 3:40:03 time: 0.6411 data_time: 0.0016 memory: 44138 loss: 0.2957 +2023/06/06 08:30:05 - mmengine - INFO - Epoch(train) [5][3200/3937] lr: 5.7649e-05 eta: 3:38:58 time: 0.6422 data_time: 0.0015 memory: 44138 loss: 0.3227 +2023/06/06 08:30:38 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:31:09 - mmengine - INFO - Epoch(train) [5][3300/3937] lr: 5.7290e-05 eta: 3:37:54 time: 0.6410 data_time: 0.0016 memory: 44138 loss: 0.3376 +2023/06/06 08:32:13 - mmengine - INFO - Epoch(train) [5][3400/3937] lr: 5.6931e-05 eta: 3:36:49 time: 0.6420 data_time: 0.0016 memory: 44138 loss: 0.3269 +2023/06/06 08:33:17 - mmengine - INFO - Epoch(train) [5][3500/3937] lr: 5.6572e-05 eta: 3:35:45 time: 0.6469 data_time: 0.0018 memory: 44138 loss: 0.3279 +2023/06/06 08:34:21 - mmengine - INFO - Epoch(train) [5][3600/3937] lr: 5.6214e-05 eta: 3:34:40 time: 0.6398 data_time: 0.0018 memory: 44138 loss: 0.3242 +2023/06/06 08:35:25 - mmengine - INFO - Epoch(train) [5][3700/3937] lr: 5.5855e-05 eta: 3:33:35 time: 0.6397 data_time: 0.0018 memory: 44138 loss: 0.3336 +2023/06/06 08:36:29 - mmengine - INFO - Epoch(train) [5][3800/3937] lr: 5.5496e-05 eta: 3:32:31 time: 0.6414 data_time: 0.0017 memory: 44138 loss: 0.3647 +2023/06/06 08:37:33 - mmengine - INFO - Epoch(train) [5][3900/3937] lr: 5.5136e-05 eta: 3:31:26 time: 0.6419 data_time: 0.0015 memory: 44138 loss: 0.3502 +2023/06/06 08:37:57 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:37:57 - mmengine - INFO - Saving checkpoint at 5 epochs +2023/06/06 08:39:29 - mmengine - INFO - Epoch(val) [5][57/57] accuracy/top1: 90.2439 single-label/precision_classwise: [97.54212188720703, 83.5861587524414] single-label/recall_classwise: [84.42648315429688, 97.3875961303711] single-label/f1-score_classwise: [90.51165008544922, 89.96060943603516] data_time: 0.0146 time: 1.2585 +2023/06/06 08:40:35 - mmengine - INFO - Epoch(train) [6][ 100/3937] lr: 5.4645e-05 eta: 3:30:00 time: 0.6386 data_time: 0.0016 memory: 44138 loss: 0.3622 +2023/06/06 08:41:39 - mmengine - INFO - Epoch(train) [6][ 200/3937] lr: 5.4285e-05 eta: 3:28:55 time: 0.6384 data_time: 0.0018 memory: 44138 loss: 0.2929 +2023/06/06 08:42:43 - mmengine - INFO - Epoch(train) [6][ 300/3937] lr: 5.3926e-05 eta: 3:27:51 time: 0.6405 data_time: 0.0017 memory: 44138 loss: 0.3145 +2023/06/06 08:42:53 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:43:47 - mmengine - INFO - Epoch(train) [6][ 400/3937] lr: 5.3567e-05 eta: 3:26:46 time: 0.6401 data_time: 0.0029 memory: 44138 loss: 0.3452 +2023/06/06 08:44:51 - mmengine - INFO - Epoch(train) [6][ 500/3937] lr: 5.3209e-05 eta: 3:25:41 time: 0.6493 data_time: 0.0016 memory: 44138 loss: 0.3426 +2023/06/06 08:45:55 - mmengine - INFO - Epoch(train) [6][ 600/3937] lr: 5.2850e-05 eta: 3:24:36 time: 0.6393 data_time: 0.0015 memory: 44138 loss: 0.3071 +2023/06/06 08:46:59 - mmengine - INFO - Epoch(train) [6][ 700/3937] lr: 5.2491e-05 eta: 3:23:31 time: 0.6379 data_time: 0.0017 memory: 44138 loss: 0.3507 +2023/06/06 08:48:03 - mmengine - INFO - Epoch(train) [6][ 800/3937] lr: 5.2133e-05 eta: 3:22:27 time: 0.6376 data_time: 0.0024 memory: 44138 loss: 0.3170 +2023/06/06 08:49:06 - mmengine - INFO - Epoch(train) [6][ 900/3937] lr: 5.1775e-05 eta: 3:21:22 time: 0.6387 data_time: 0.0017 memory: 44138 loss: 0.3608 +2023/06/06 08:50:10 - mmengine - INFO - Epoch(train) [6][1000/3937] lr: 5.1417e-05 eta: 3:20:17 time: 0.6372 data_time: 0.0016 memory: 44138 loss: 0.3422 +2023/06/06 08:51:14 - mmengine - INFO - Epoch(train) [6][1100/3937] lr: 5.1059e-05 eta: 3:19:13 time: 0.6403 data_time: 0.0017 memory: 44138 loss: 0.3411 +2023/06/06 08:52:18 - mmengine - INFO - Epoch(train) [6][1200/3937] lr: 5.0701e-05 eta: 3:18:08 time: 0.6392 data_time: 0.0017 memory: 44138 loss: 0.3372 +2023/06/06 08:53:22 - mmengine - INFO - Epoch(train) [6][1300/3937] lr: 5.0344e-05 eta: 3:17:03 time: 0.6388 data_time: 0.0019 memory: 44138 loss: 0.3402 +2023/06/06 08:53:32 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 08:54:26 - mmengine - INFO - Epoch(train) [6][1400/3937] lr: 4.9987e-05 eta: 3:15:59 time: 0.6395 data_time: 0.0020 memory: 44138 loss: 0.3344 +2023/06/06 08:55:30 - mmengine - INFO - Epoch(train) [6][1500/3937] lr: 4.9630e-05 eta: 3:14:54 time: 0.6405 data_time: 0.0020 memory: 44138 loss: 0.3596 +2023/06/06 08:56:34 - mmengine - INFO - Epoch(train) [6][1600/3937] lr: 4.9274e-05 eta: 3:13:49 time: 0.6406 data_time: 0.0017 memory: 44138 loss: 0.3008 +2023/06/06 08:57:38 - mmengine - INFO - Epoch(train) [6][1700/3937] lr: 4.8918e-05 eta: 3:12:45 time: 0.6387 data_time: 0.0018 memory: 44138 loss: 0.3156 +2023/06/06 08:58:41 - mmengine - INFO - Epoch(train) [6][1800/3937] lr: 4.8562e-05 eta: 3:11:40 time: 0.6380 data_time: 0.0017 memory: 44138 loss: 0.3158 +2023/06/06 08:59:45 - mmengine - INFO - Epoch(train) [6][1900/3937] lr: 4.8207e-05 eta: 3:10:35 time: 0.6385 data_time: 0.0019 memory: 44138 loss: 0.3264 +2023/06/06 09:00:49 - mmengine - INFO - Epoch(train) [6][2000/3937] lr: 4.7852e-05 eta: 3:09:31 time: 0.6381 data_time: 0.0019 memory: 44138 loss: 0.3240 +2023/06/06 09:01:53 - mmengine - INFO - Epoch(train) [6][2100/3937] lr: 4.7498e-05 eta: 3:08:26 time: 0.6385 data_time: 0.0016 memory: 44138 loss: 0.3161 +2023/06/06 09:02:57 - mmengine - INFO - Epoch(train) [6][2200/3937] lr: 4.7144e-05 eta: 3:07:21 time: 0.6386 data_time: 0.0018 memory: 44138 loss: 0.3347 +2023/06/06 09:04:01 - mmengine - INFO - Epoch(train) [6][2300/3937] lr: 4.6791e-05 eta: 3:06:17 time: 0.6387 data_time: 0.0017 memory: 44138 loss: 0.3308 +2023/06/06 09:04:11 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:05:05 - mmengine - INFO - Epoch(train) [6][2400/3937] lr: 4.6438e-05 eta: 3:05:12 time: 0.6387 data_time: 0.0017 memory: 44138 loss: 0.3387 +2023/06/06 09:06:09 - mmengine - INFO - Epoch(train) [6][2500/3937] lr: 4.6086e-05 eta: 3:04:08 time: 0.6381 data_time: 0.0017 memory: 44138 loss: 0.3311 +2023/06/06 09:07:13 - mmengine - INFO - Epoch(train) [6][2600/3937] lr: 4.5734e-05 eta: 3:03:03 time: 0.6406 data_time: 0.0016 memory: 44138 loss: 0.3468 +2023/06/06 09:08:17 - mmengine - INFO - Epoch(train) [6][2700/3937] lr: 4.5383e-05 eta: 3:01:59 time: 0.6401 data_time: 0.0016 memory: 44138 loss: 0.3607 +2023/06/06 09:09:21 - mmengine - INFO - Epoch(train) [6][2800/3937] lr: 4.5033e-05 eta: 3:00:54 time: 0.6379 data_time: 0.0018 memory: 44138 loss: 0.3262 +2023/06/06 09:10:25 - mmengine - INFO - Epoch(train) [6][2900/3937] lr: 4.4683e-05 eta: 2:59:50 time: 0.6442 data_time: 0.0021 memory: 44138 loss: 0.3510 +2023/06/06 09:11:29 - mmengine - INFO - Epoch(train) [6][3000/3937] lr: 4.4334e-05 eta: 2:58:45 time: 0.6387 data_time: 0.0018 memory: 44138 loss: 0.3286 +2023/06/06 09:12:33 - mmengine - INFO - Epoch(train) [6][3100/3937] lr: 4.3985e-05 eta: 2:57:40 time: 0.6387 data_time: 0.0016 memory: 44138 loss: 0.3489 +2023/06/06 09:13:36 - mmengine - INFO - Epoch(train) [6][3200/3937] lr: 4.3637e-05 eta: 2:56:36 time: 0.6383 data_time: 0.0022 memory: 44138 loss: 0.3292 +2023/06/06 09:14:40 - mmengine - INFO - Epoch(train) [6][3300/3937] lr: 4.3290e-05 eta: 2:55:31 time: 0.6419 data_time: 0.0017 memory: 44138 loss: 0.3328 +2023/06/06 09:14:50 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:15:44 - mmengine - INFO - Epoch(train) [6][3400/3937] lr: 4.2944e-05 eta: 2:54:27 time: 0.6391 data_time: 0.0016 memory: 44138 loss: 0.3286 +2023/06/06 09:16:48 - mmengine - INFO - Epoch(train) [6][3500/3937] lr: 4.2598e-05 eta: 2:53:22 time: 0.6381 data_time: 0.0016 memory: 44138 loss: 0.3221 +2023/06/06 09:17:52 - mmengine - INFO - Epoch(train) [6][3600/3937] lr: 4.2253e-05 eta: 2:52:18 time: 0.6395 data_time: 0.0031 memory: 44138 loss: 0.3422 +2023/06/06 09:18:56 - mmengine - INFO - Epoch(train) [6][3700/3937] lr: 4.1909e-05 eta: 2:51:13 time: 0.6373 data_time: 0.0016 memory: 44138 loss: 0.3500 +2023/06/06 09:20:00 - mmengine - INFO - Epoch(train) [6][3800/3937] lr: 4.1566e-05 eta: 2:50:09 time: 0.6380 data_time: 0.0015 memory: 44138 loss: 0.3381 +2023/06/06 09:21:04 - mmengine - INFO - Epoch(train) [6][3900/3937] lr: 4.1224e-05 eta: 2:49:04 time: 0.6394 data_time: 0.0015 memory: 44138 loss: 0.3400 +2023/06/06 09:21:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:21:27 - mmengine - INFO - Saving checkpoint at 6 epochs +2023/06/06 09:22:59 - mmengine - INFO - Epoch(val) [6][57/57] accuracy/top1: 92.4568 single-label/precision_classwise: [97.46580505371094, 87.4250259399414] single-label/recall_classwise: [88.6181411743164, 97.17054748535156] single-label/f1-score_classwise: [92.83162689208984, 92.04053497314453] data_time: 0.0161 time: 1.2590 +2023/06/06 09:24:06 - mmengine - INFO - Epoch(train) [7][ 100/3937] lr: 4.0757e-05 eta: 2:47:38 time: 0.6380 data_time: 0.0016 memory: 44138 loss: 0.3351 +2023/06/06 09:25:10 - mmengine - INFO - Epoch(train) [7][ 200/3937] lr: 4.0416e-05 eta: 2:46:33 time: 0.6393 data_time: 0.0019 memory: 44138 loss: 0.3270 +2023/06/06 09:26:13 - mmengine - INFO - Epoch(train) [7][ 300/3937] lr: 4.0077e-05 eta: 2:45:29 time: 0.6402 data_time: 0.0016 memory: 44138 loss: 0.3321 +2023/06/06 09:27:03 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:27:17 - mmengine - INFO - Epoch(train) [7][ 400/3937] lr: 3.9739e-05 eta: 2:44:24 time: 0.6381 data_time: 0.0017 memory: 44138 loss: 0.3327 +2023/06/06 09:28:21 - mmengine - INFO - Epoch(train) [7][ 500/3937] lr: 3.9402e-05 eta: 2:43:20 time: 0.6379 data_time: 0.0015 memory: 44138 loss: 0.3382 +2023/06/06 09:29:25 - mmengine - INFO - Epoch(train) [7][ 600/3937] lr: 3.9065e-05 eta: 2:42:15 time: 0.6395 data_time: 0.0019 memory: 44138 loss: 0.3125 +2023/06/06 09:30:29 - mmengine - INFO - Epoch(train) [7][ 700/3937] lr: 3.8730e-05 eta: 2:41:11 time: 0.6399 data_time: 0.0016 memory: 44138 loss: 0.3509 +2023/06/06 09:31:33 - mmengine - INFO - Epoch(train) [7][ 800/3937] lr: 3.8396e-05 eta: 2:40:06 time: 0.6391 data_time: 0.0016 memory: 44138 loss: 0.3387 +2023/06/06 09:32:37 - mmengine - INFO - Epoch(train) [7][ 900/3937] lr: 3.8062e-05 eta: 2:39:02 time: 0.6412 data_time: 0.0016 memory: 44138 loss: 0.3242 +2023/06/06 09:33:41 - mmengine - INFO - Epoch(train) [7][1000/3937] lr: 3.7730e-05 eta: 2:37:57 time: 0.6378 data_time: 0.0017 memory: 44138 loss: 0.3211 +2023/06/06 09:34:45 - mmengine - INFO - Epoch(train) [7][1100/3937] lr: 3.7399e-05 eta: 2:36:53 time: 0.6385 data_time: 0.0016 memory: 44138 loss: 0.3298 +2023/06/06 09:35:49 - mmengine - INFO - Epoch(train) [7][1200/3937] lr: 3.7069e-05 eta: 2:35:48 time: 0.6386 data_time: 0.0017 memory: 44138 loss: 0.3449 +2023/06/06 09:36:53 - mmengine - INFO - Epoch(train) [7][1300/3937] lr: 3.6741e-05 eta: 2:34:44 time: 0.6386 data_time: 0.0016 memory: 44138 loss: 0.3130 +2023/06/06 09:37:43 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:37:57 - mmengine - INFO - Epoch(train) [7][1400/3937] lr: 3.6413e-05 eta: 2:33:40 time: 0.6414 data_time: 0.0021 memory: 44138 loss: 0.3471 +2023/06/06 09:39:01 - mmengine - INFO - Epoch(train) [7][1500/3937] lr: 3.6087e-05 eta: 2:32:35 time: 0.6397 data_time: 0.0021 memory: 44138 loss: 0.3027 +2023/06/06 09:40:05 - mmengine - INFO - Epoch(train) [7][1600/3937] lr: 3.5761e-05 eta: 2:31:31 time: 0.6403 data_time: 0.0015 memory: 44138 loss: 0.3238 +2023/06/06 09:41:09 - mmengine - INFO - Epoch(train) [7][1700/3937] lr: 3.5437e-05 eta: 2:30:26 time: 0.6394 data_time: 0.0018 memory: 44138 loss: 0.3504 +2023/06/06 09:42:13 - mmengine - INFO - Epoch(train) [7][1800/3937] lr: 3.5115e-05 eta: 2:29:22 time: 0.6392 data_time: 0.0015 memory: 44138 loss: 0.3467 +2023/06/06 09:43:17 - mmengine - INFO - Epoch(train) [7][1900/3937] lr: 3.4793e-05 eta: 2:28:18 time: 0.6376 data_time: 0.0018 memory: 44138 loss: 0.3153 +2023/06/06 09:44:21 - mmengine - INFO - Epoch(train) [7][2000/3937] lr: 3.4473e-05 eta: 2:27:13 time: 0.6395 data_time: 0.0016 memory: 44138 loss: 0.3325 +2023/06/06 09:45:25 - mmengine - INFO - Epoch(train) [7][2100/3937] lr: 3.4154e-05 eta: 2:26:09 time: 0.6396 data_time: 0.0020 memory: 44138 loss: 0.3500 +2023/06/06 09:46:29 - mmengine - INFO - Epoch(train) [7][2200/3937] lr: 3.3836e-05 eta: 2:25:04 time: 0.6414 data_time: 0.0018 memory: 44138 loss: 0.3323 +2023/06/06 09:47:33 - mmengine - INFO - Epoch(train) [7][2300/3937] lr: 3.3520e-05 eta: 2:24:00 time: 0.6374 data_time: 0.0016 memory: 44138 loss: 0.3465 +2023/06/06 09:48:23 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:48:37 - mmengine - INFO - Epoch(train) [7][2400/3937] lr: 3.3205e-05 eta: 2:22:56 time: 0.6386 data_time: 0.0015 memory: 44138 loss: 0.3382 +2023/06/06 09:49:41 - mmengine - INFO - Epoch(train) [7][2500/3937] lr: 3.2892e-05 eta: 2:21:51 time: 0.6405 data_time: 0.0018 memory: 44138 loss: 0.3324 +2023/06/06 09:50:45 - mmengine - INFO - Epoch(train) [7][2600/3937] lr: 3.2580e-05 eta: 2:20:47 time: 0.6402 data_time: 0.0017 memory: 44138 loss: 0.3484 +2023/06/06 09:51:49 - mmengine - INFO - Epoch(train) [7][2700/3937] lr: 3.2269e-05 eta: 2:19:43 time: 0.6393 data_time: 0.0014 memory: 44138 loss: 0.3480 +2023/06/06 09:52:53 - mmengine - INFO - Epoch(train) [7][2800/3937] lr: 3.1960e-05 eta: 2:18:38 time: 0.6389 data_time: 0.0020 memory: 44138 loss: 0.3267 +2023/06/06 09:53:57 - mmengine - INFO - Epoch(train) [7][2900/3937] lr: 3.1652e-05 eta: 2:17:34 time: 0.6416 data_time: 0.0020 memory: 44138 loss: 0.3208 +2023/06/06 09:55:01 - mmengine - INFO - Epoch(train) [7][3000/3937] lr: 3.1346e-05 eta: 2:16:30 time: 0.6430 data_time: 0.0022 memory: 44138 loss: 0.3511 +2023/06/06 09:56:05 - mmengine - INFO - Epoch(train) [7][3100/3937] lr: 3.1041e-05 eta: 2:15:25 time: 0.6418 data_time: 0.0019 memory: 44138 loss: 0.3995 +2023/06/06 09:57:09 - mmengine - INFO - Epoch(train) [7][3200/3937] lr: 3.0738e-05 eta: 2:14:21 time: 0.6405 data_time: 0.0017 memory: 44138 loss: 0.3602 +2023/06/06 09:58:13 - mmengine - INFO - Epoch(train) [7][3300/3937] lr: 3.0437e-05 eta: 2:13:17 time: 0.6395 data_time: 0.0016 memory: 44138 loss: 0.3430 +2023/06/06 09:59:03 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 09:59:18 - mmengine - INFO - Epoch(train) [7][3400/3937] lr: 3.0136e-05 eta: 2:12:12 time: 0.6418 data_time: 0.0016 memory: 44138 loss: 0.3421 +2023/06/06 10:00:22 - mmengine - INFO - Epoch(train) [7][3500/3937] lr: 2.9838e-05 eta: 2:11:08 time: 0.6427 data_time: 0.0015 memory: 44138 loss: 0.3353 +2023/06/06 10:01:26 - mmengine - INFO - Epoch(train) [7][3600/3937] lr: 2.9541e-05 eta: 2:10:04 time: 0.6429 data_time: 0.0015 memory: 44138 loss: 0.3391 +2023/06/06 10:02:30 - mmengine - INFO - Epoch(train) [7][3700/3937] lr: 2.9246e-05 eta: 2:08:59 time: 0.6408 data_time: 0.0017 memory: 44138 loss: 0.3578 +2023/06/06 10:03:34 - mmengine - INFO - Epoch(train) [7][3800/3937] lr: 2.8952e-05 eta: 2:07:55 time: 0.6400 data_time: 0.0016 memory: 44138 loss: 0.3137 +2023/06/06 10:04:38 - mmengine - INFO - Epoch(train) [7][3900/3937] lr: 2.8660e-05 eta: 2:06:51 time: 0.6452 data_time: 0.0016 memory: 44138 loss: 0.3143 +2023/06/06 10:05:02 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:05:02 - mmengine - INFO - Saving checkpoint at 7 epochs +2023/06/06 10:06:33 - mmengine - INFO - Epoch(val) [7][57/57] accuracy/top1: 93.6293 single-label/precision_classwise: [97.43363952636719, 89.60853576660156] single-label/recall_classwise: [90.83391571044922, 97.06201171875] single-label/f1-score_classwise: [94.01810455322266, 93.18647003173828] data_time: 0.0161 time: 1.2589 +2023/06/06 10:07:40 - mmengine - INFO - Epoch(train) [8][ 100/3937] lr: 2.8263e-05 eta: 2:05:24 time: 0.6414 data_time: 0.0018 memory: 44138 loss: 0.3279 +2023/06/06 10:08:44 - mmengine - INFO - Epoch(train) [8][ 200/3937] lr: 2.7975e-05 eta: 2:04:19 time: 0.6421 data_time: 0.0024 memory: 44138 loss: 0.3484 +2023/06/06 10:09:48 - mmengine - INFO - Epoch(train) [8][ 300/3937] lr: 2.7689e-05 eta: 2:03:15 time: 0.6495 data_time: 0.0018 memory: 44138 loss: 0.3356 +2023/06/06 10:10:52 - mmengine - INFO - Epoch(train) [8][ 400/3937] lr: 2.7404e-05 eta: 2:02:11 time: 0.6396 data_time: 0.0016 memory: 44138 loss: 0.3365 +2023/06/06 10:11:18 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:11:56 - mmengine - INFO - Epoch(train) [8][ 500/3937] lr: 2.7121e-05 eta: 2:01:07 time: 0.6401 data_time: 0.0017 memory: 44138 loss: 0.3527 +2023/06/06 10:13:00 - mmengine - INFO - Epoch(train) [8][ 600/3937] lr: 2.6840e-05 eta: 2:00:02 time: 0.6407 data_time: 0.0015 memory: 44138 loss: 0.3274 +2023/06/06 10:14:04 - mmengine - INFO - Epoch(train) [8][ 700/3937] lr: 2.6561e-05 eta: 1:58:58 time: 0.6378 data_time: 0.0016 memory: 44138 loss: 0.3499 +2023/06/06 10:15:08 - mmengine - INFO - Epoch(train) [8][ 800/3937] lr: 2.6284e-05 eta: 1:57:53 time: 0.6381 data_time: 0.0015 memory: 44138 loss: 0.3353 +2023/06/06 10:16:12 - mmengine - INFO - Epoch(train) [8][ 900/3937] lr: 2.6008e-05 eta: 1:56:49 time: 0.6378 data_time: 0.0030 memory: 44138 loss: 0.3310 +2023/06/06 10:17:16 - mmengine - INFO - Epoch(train) [8][1000/3937] lr: 2.5735e-05 eta: 1:55:45 time: 0.6385 data_time: 0.0026 memory: 44138 loss: 0.3441 +2023/06/06 10:18:19 - mmengine - INFO - Epoch(train) [8][1100/3937] lr: 2.5463e-05 eta: 1:54:40 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3304 +2023/06/06 10:19:23 - mmengine - INFO - Epoch(train) [8][1200/3937] lr: 2.5193e-05 eta: 1:53:36 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3501 +2023/06/06 10:20:27 - mmengine - INFO - Epoch(train) [8][1300/3937] lr: 2.4925e-05 eta: 1:52:31 time: 0.6371 data_time: 0.0017 memory: 44138 loss: 0.3493 +2023/06/06 10:21:31 - mmengine - INFO - Epoch(train) [8][1400/3937] lr: 2.4659e-05 eta: 1:51:27 time: 0.6362 data_time: 0.0017 memory: 44138 loss: 0.3444 +2023/06/06 10:21:57 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:22:34 - mmengine - INFO - Epoch(train) [8][1500/3937] lr: 2.4394e-05 eta: 1:50:23 time: 0.6368 data_time: 0.0018 memory: 44138 loss: 0.3415 +2023/06/06 10:23:38 - mmengine - INFO - Epoch(train) [8][1600/3937] lr: 2.4132e-05 eta: 1:49:18 time: 0.6387 data_time: 0.0030 memory: 44138 loss: 0.3317 +2023/06/06 10:24:42 - mmengine - INFO - Epoch(train) [8][1700/3937] lr: 2.3872e-05 eta: 1:48:14 time: 0.6383 data_time: 0.0018 memory: 44138 loss: 0.3175 +2023/06/06 10:25:46 - mmengine - INFO - Epoch(train) [8][1800/3937] lr: 2.3613e-05 eta: 1:47:09 time: 0.6373 data_time: 0.0016 memory: 44138 loss: 0.3351 +2023/06/06 10:26:50 - mmengine - INFO - Epoch(train) [8][1900/3937] lr: 2.3357e-05 eta: 1:46:05 time: 0.6380 data_time: 0.0016 memory: 44138 loss: 0.3334 +2023/06/06 10:27:54 - mmengine - INFO - Epoch(train) [8][2000/3937] lr: 2.3103e-05 eta: 1:45:01 time: 0.6373 data_time: 0.0021 memory: 44138 loss: 0.3357 +2023/06/06 10:28:57 - mmengine - INFO - Epoch(train) [8][2100/3937] lr: 2.2851e-05 eta: 1:43:56 time: 0.6381 data_time: 0.0026 memory: 44138 loss: 0.3277 +2023/06/06 10:30:01 - mmengine - INFO - Epoch(train) [8][2200/3937] lr: 2.2600e-05 eta: 1:42:52 time: 0.6372 data_time: 0.0017 memory: 44138 loss: 0.3512 +2023/06/06 10:31:05 - mmengine - INFO - Epoch(train) [8][2300/3937] lr: 2.2352e-05 eta: 1:41:48 time: 0.6360 data_time: 0.0021 memory: 44138 loss: 0.3321 +2023/06/06 10:32:09 - mmengine - INFO - Epoch(train) [8][2400/3937] lr: 2.2106e-05 eta: 1:40:43 time: 0.6363 data_time: 0.0018 memory: 44138 loss: 0.3401 +2023/06/06 10:32:35 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:33:12 - mmengine - INFO - Epoch(train) [8][2500/3937] lr: 2.1862e-05 eta: 1:39:39 time: 0.6382 data_time: 0.0018 memory: 44138 loss: 0.3393 +2023/06/06 10:34:16 - mmengine - INFO - Epoch(train) [8][2600/3937] lr: 2.1620e-05 eta: 1:38:34 time: 0.6372 data_time: 0.0018 memory: 44138 loss: 0.3494 +2023/06/06 10:35:20 - mmengine - INFO - Epoch(train) [8][2700/3937] lr: 2.1380e-05 eta: 1:37:30 time: 0.6456 data_time: 0.0018 memory: 44138 loss: 0.3472 +2023/06/06 10:36:24 - mmengine - INFO - Epoch(train) [8][2800/3937] lr: 2.1143e-05 eta: 1:36:26 time: 0.6369 data_time: 0.0017 memory: 44138 loss: 0.3159 +2023/06/06 10:37:27 - mmengine - INFO - Epoch(train) [8][2900/3937] lr: 2.0907e-05 eta: 1:35:21 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3737 +2023/06/06 10:38:31 - mmengine - INFO - Epoch(train) [8][3000/3937] lr: 2.0674e-05 eta: 1:34:17 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3234 +2023/06/06 10:39:35 - mmengine - INFO - Epoch(train) [8][3100/3937] lr: 2.0443e-05 eta: 1:33:13 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3398 +2023/06/06 10:40:39 - mmengine - INFO - Epoch(train) [8][3200/3937] lr: 2.0214e-05 eta: 1:32:08 time: 0.6368 data_time: 0.0021 memory: 44138 loss: 0.3354 +2023/06/06 10:41:42 - mmengine - INFO - Epoch(train) [8][3300/3937] lr: 1.9987e-05 eta: 1:31:04 time: 0.6389 data_time: 0.0026 memory: 44138 loss: 0.3449 +2023/06/06 10:42:46 - mmengine - INFO - Epoch(train) [8][3400/3937] lr: 1.9763e-05 eta: 1:30:00 time: 0.6366 data_time: 0.0019 memory: 44138 loss: 0.3225 +2023/06/06 10:43:12 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:43:50 - mmengine - INFO - Epoch(train) [8][3500/3937] lr: 1.9541e-05 eta: 1:28:55 time: 0.6378 data_time: 0.0015 memory: 44138 loss: 0.3325 +2023/06/06 10:44:54 - mmengine - INFO - Epoch(train) [8][3600/3937] lr: 1.9321e-05 eta: 1:27:51 time: 0.6369 data_time: 0.0017 memory: 44138 loss: 0.3004 +2023/06/06 10:45:57 - mmengine - INFO - Epoch(train) [8][3700/3937] lr: 1.9103e-05 eta: 1:26:47 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3464 +2023/06/06 10:47:01 - mmengine - INFO - Epoch(train) [8][3800/3937] lr: 1.8888e-05 eta: 1:25:42 time: 0.6450 data_time: 0.0020 memory: 44138 loss: 0.3485 +2023/06/06 10:48:05 - mmengine - INFO - Epoch(train) [8][3900/3937] lr: 1.8675e-05 eta: 1:24:38 time: 0.6373 data_time: 0.0021 memory: 44138 loss: 0.3407 +2023/06/06 10:48:29 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:48:29 - mmengine - INFO - Saving checkpoint at 8 epochs +2023/06/06 10:49:59 - mmengine - INFO - Epoch(val) [8][57/57] accuracy/top1: 94.4400 single-label/precision_classwise: [96.95391082763672, 91.63105773925781] single-label/recall_classwise: [92.8287353515625, 96.41860961914062] single-label/f1-score_classwise: [94.84648895263672, 93.9638900756836] data_time: 0.0144 time: 1.2575 +2023/06/06 10:51:06 - mmengine - INFO - Epoch(train) [9][ 100/3937] lr: 1.8386e-05 eta: 1:23:11 time: 0.6380 data_time: 0.0019 memory: 44138 loss: 0.3471 +2023/06/06 10:52:10 - mmengine - INFO - Epoch(train) [9][ 200/3937] lr: 1.8179e-05 eta: 1:22:06 time: 0.6379 data_time: 0.0024 memory: 44138 loss: 0.3632 +2023/06/06 10:53:13 - mmengine - INFO - Epoch(train) [9][ 300/3937] lr: 1.7974e-05 eta: 1:21:02 time: 0.6378 data_time: 0.0017 memory: 44138 loss: 0.3465 +2023/06/06 10:54:17 - mmengine - INFO - Epoch(train) [9][ 400/3937] lr: 1.7771e-05 eta: 1:19:58 time: 0.6380 data_time: 0.0018 memory: 44138 loss: 0.3592 +2023/06/06 10:55:21 - mmengine - INFO - Epoch(train) [9][ 500/3937] lr: 1.7570e-05 eta: 1:18:53 time: 0.6379 data_time: 0.0017 memory: 44138 loss: 0.3359 +2023/06/06 10:55:24 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 10:56:25 - mmengine - INFO - Epoch(train) [9][ 600/3937] lr: 1.7372e-05 eta: 1:17:49 time: 0.6384 data_time: 0.0018 memory: 44138 loss: 0.3351 +2023/06/06 10:57:29 - mmengine - INFO - Epoch(train) [9][ 700/3937] lr: 1.7176e-05 eta: 1:16:45 time: 0.6380 data_time: 0.0019 memory: 44138 loss: 0.3564 +2023/06/06 10:58:32 - mmengine - INFO - Epoch(train) [9][ 800/3937] lr: 1.6983e-05 eta: 1:15:41 time: 0.6378 data_time: 0.0016 memory: 44138 loss: 0.3528 +2023/06/06 10:59:36 - mmengine - INFO - Epoch(train) [9][ 900/3937] lr: 1.6792e-05 eta: 1:14:36 time: 0.6371 data_time: 0.0020 memory: 44138 loss: 0.3167 +2023/06/06 11:00:40 - mmengine - INFO - Epoch(train) [9][1000/3937] lr: 1.6604e-05 eta: 1:13:32 time: 0.6367 data_time: 0.0025 memory: 44138 loss: 0.3180 +2023/06/06 11:01:44 - mmengine - INFO - Epoch(train) [9][1100/3937] lr: 1.6418e-05 eta: 1:12:28 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3418 +2023/06/06 11:02:47 - mmengine - INFO - Epoch(train) [9][1200/3937] lr: 1.6234e-05 eta: 1:11:23 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3467 +2023/06/06 11:03:51 - mmengine - INFO - Epoch(train) [9][1300/3937] lr: 1.6053e-05 eta: 1:10:19 time: 0.6372 data_time: 0.0016 memory: 44138 loss: 0.3446 +2023/06/06 11:04:55 - mmengine - INFO - Epoch(train) [9][1400/3937] lr: 1.5874e-05 eta: 1:09:15 time: 0.6367 data_time: 0.0015 memory: 44138 loss: 0.3337 +2023/06/06 11:05:58 - mmengine - INFO - Epoch(train) [9][1500/3937] lr: 1.5698e-05 eta: 1:08:11 time: 0.6364 data_time: 0.0016 memory: 44138 loss: 0.3353 +2023/06/06 11:06:01 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:07:02 - mmengine - INFO - Epoch(train) [9][1600/3937] lr: 1.5524e-05 eta: 1:07:06 time: 0.6365 data_time: 0.0017 memory: 44138 loss: 0.3292 +2023/06/06 11:08:06 - mmengine - INFO - Epoch(train) [9][1700/3937] lr: 1.5353e-05 eta: 1:06:02 time: 0.6375 data_time: 0.0019 memory: 44138 loss: 0.3220 +2023/06/06 11:09:10 - mmengine - INFO - Epoch(train) [9][1800/3937] lr: 1.5185e-05 eta: 1:04:58 time: 0.6366 data_time: 0.0019 memory: 44138 loss: 0.3659 +2023/06/06 11:10:13 - mmengine - INFO - Epoch(train) [9][1900/3937] lr: 1.5019e-05 eta: 1:03:54 time: 0.6365 data_time: 0.0017 memory: 44138 loss: 0.3399 +2023/06/06 11:11:17 - mmengine - INFO - Epoch(train) [9][2000/3937] lr: 1.4855e-05 eta: 1:02:49 time: 0.6376 data_time: 0.0018 memory: 44138 loss: 0.3403 +2023/06/06 11:12:21 - mmengine - INFO - Epoch(train) [9][2100/3937] lr: 1.4694e-05 eta: 1:01:45 time: 0.6372 data_time: 0.0019 memory: 44138 loss: 0.3265 +2023/06/06 11:13:25 - mmengine - INFO - Epoch(train) [9][2200/3937] lr: 1.4536e-05 eta: 1:00:41 time: 0.6368 data_time: 0.0017 memory: 44138 loss: 0.3236 +2023/06/06 11:14:29 - mmengine - INFO - Epoch(train) [9][2300/3937] lr: 1.4380e-05 eta: 0:59:37 time: 0.6374 data_time: 0.0018 memory: 44138 loss: 0.3228 +2023/06/06 11:15:32 - mmengine - INFO - Epoch(train) [9][2400/3937] lr: 1.4227e-05 eta: 0:58:32 time: 0.6372 data_time: 0.0018 memory: 44138 loss: 0.3449 +2023/06/06 11:16:36 - mmengine - INFO - Epoch(train) [9][2500/3937] lr: 1.4076e-05 eta: 0:57:28 time: 0.6375 data_time: 0.0014 memory: 44138 loss: 0.3215 +2023/06/06 11:16:39 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:17:40 - mmengine - INFO - Epoch(train) [9][2600/3937] lr: 1.3928e-05 eta: 0:56:24 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3619 +2023/06/06 11:18:44 - mmengine - INFO - Epoch(train) [9][2700/3937] lr: 1.3783e-05 eta: 0:55:20 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3587 +2023/06/06 11:19:47 - mmengine - INFO - Epoch(train) [9][2800/3937] lr: 1.3640e-05 eta: 0:54:15 time: 0.6373 data_time: 0.0020 memory: 44138 loss: 0.3619 +2023/06/06 11:20:51 - mmengine - INFO - Epoch(train) [9][2900/3937] lr: 1.3500e-05 eta: 0:53:11 time: 0.6366 data_time: 0.0015 memory: 44138 loss: 0.3353 +2023/06/06 11:21:55 - mmengine - INFO - Epoch(train) [9][3000/3937] lr: 1.3362e-05 eta: 0:52:07 time: 0.6360 data_time: 0.0017 memory: 44138 loss: 0.3545 +2023/06/06 11:22:58 - mmengine - INFO - Epoch(train) [9][3100/3937] lr: 1.3227e-05 eta: 0:51:03 time: 0.6367 data_time: 0.0017 memory: 44138 loss: 0.3315 +2023/06/06 11:24:02 - mmengine - INFO - Epoch(train) [9][3200/3937] lr: 1.3095e-05 eta: 0:49:58 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3482 +2023/06/06 11:25:06 - mmengine - INFO - Epoch(train) [9][3300/3937] lr: 1.2966e-05 eta: 0:48:54 time: 0.6360 data_time: 0.0016 memory: 44138 loss: 0.3190 +2023/06/06 11:26:09 - mmengine - INFO - Epoch(train) [9][3400/3937] lr: 1.2839e-05 eta: 0:47:50 time: 0.6377 data_time: 0.0015 memory: 44138 loss: 0.3432 +2023/06/06 11:27:13 - mmengine - INFO - Epoch(train) [9][3500/3937] lr: 1.2715e-05 eta: 0:46:46 time: 0.6384 data_time: 0.0015 memory: 44138 loss: 0.3670 +2023/06/06 11:27:16 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:28:17 - mmengine - INFO - Epoch(train) [9][3600/3937] lr: 1.2593e-05 eta: 0:45:42 time: 0.6370 data_time: 0.0023 memory: 44138 loss: 0.3338 +2023/06/06 11:29:21 - mmengine - INFO - Epoch(train) [9][3700/3937] lr: 1.2474e-05 eta: 0:44:37 time: 0.6370 data_time: 0.0016 memory: 44138 loss: 0.3443 +2023/06/06 11:30:24 - mmengine - INFO - Epoch(train) [9][3800/3937] lr: 1.2358e-05 eta: 0:43:33 time: 0.6361 data_time: 0.0015 memory: 44138 loss: 0.3388 +2023/06/06 11:31:28 - mmengine - INFO - Epoch(train) [9][3900/3937] lr: 1.2245e-05 eta: 0:42:29 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3283 +2023/06/06 11:31:52 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:31:52 - mmengine - INFO - Saving checkpoint at 9 epochs +2023/06/06 11:33:23 - mmengine - INFO - Epoch(val) [9][57/57] accuracy/top1: 94.7497 single-label/precision_classwise: [96.73274993896484, 92.4815444946289] single-label/recall_classwise: [93.63676452636719, 96.11627960205078] single-label/f1-score_classwise: [95.15959167480469, 94.2638931274414] data_time: 0.0181 time: 1.2612 +2023/06/06 11:34:29 - mmengine - INFO - Epoch(train) [10][ 100/3937] lr: 1.2094e-05 eta: 0:41:01 time: 0.6379 data_time: 0.0018 memory: 44138 loss: 0.3731 +2023/06/06 11:35:33 - mmengine - INFO - Epoch(train) [10][ 200/3937] lr: 1.1987e-05 eta: 0:39:57 time: 0.6375 data_time: 0.0018 memory: 44138 loss: 0.3633 +2023/06/06 11:36:37 - mmengine - INFO - Epoch(train) [10][ 300/3937] lr: 1.1883e-05 eta: 0:38:53 time: 0.6378 data_time: 0.0018 memory: 44138 loss: 0.3484 +2023/06/06 11:37:41 - mmengine - INFO - Epoch(train) [10][ 400/3937] lr: 1.1781e-05 eta: 0:37:49 time: 0.6419 data_time: 0.0014 memory: 44138 loss: 0.3425 +2023/06/06 11:38:44 - mmengine - INFO - Epoch(train) [10][ 500/3937] lr: 1.1683e-05 eta: 0:36:45 time: 0.6377 data_time: 0.0021 memory: 44138 loss: 0.3399 +2023/06/06 11:39:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:39:48 - mmengine - INFO - Epoch(train) [10][ 600/3937] lr: 1.1587e-05 eta: 0:35:40 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.3612 +2023/06/06 11:40:52 - mmengine - INFO - Epoch(train) [10][ 700/3937] lr: 1.1494e-05 eta: 0:34:36 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3209 +2023/06/06 11:41:56 - mmengine - INFO - Epoch(train) [10][ 800/3937] lr: 1.1403e-05 eta: 0:33:32 time: 0.6371 data_time: 0.0015 memory: 44138 loss: 0.3721 +2023/06/06 11:42:59 - mmengine - INFO - Epoch(train) [10][ 900/3937] lr: 1.1316e-05 eta: 0:32:28 time: 0.6368 data_time: 0.0016 memory: 44138 loss: 0.3169 +2023/06/06 11:44:03 - mmengine - INFO - Epoch(train) [10][1000/3937] lr: 1.1231e-05 eta: 0:31:24 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3270 +2023/06/06 11:45:07 - mmengine - INFO - Epoch(train) [10][1100/3937] lr: 1.1149e-05 eta: 0:30:19 time: 0.6380 data_time: 0.0015 memory: 44138 loss: 0.3336 +2023/06/06 11:46:11 - mmengine - INFO - Epoch(train) [10][1200/3937] lr: 1.1070e-05 eta: 0:29:15 time: 0.6376 data_time: 0.0016 memory: 44138 loss: 0.3387 +2023/06/06 11:47:15 - mmengine - INFO - Epoch(train) [10][1300/3937] lr: 1.0993e-05 eta: 0:28:11 time: 0.6385 data_time: 0.0018 memory: 44138 loss: 0.3431 +2023/06/06 11:48:18 - mmengine - INFO - Epoch(train) [10][1400/3937] lr: 1.0920e-05 eta: 0:27:07 time: 0.6373 data_time: 0.0019 memory: 44138 loss: 0.3487 +2023/06/06 11:49:22 - mmengine - INFO - Epoch(train) [10][1500/3937] lr: 1.0849e-05 eta: 0:26:03 time: 0.6379 data_time: 0.0016 memory: 44138 loss: 0.3504 +2023/06/06 11:50:05 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 11:50:26 - mmengine - INFO - Epoch(train) [10][1600/3937] lr: 1.0781e-05 eta: 0:24:59 time: 0.6369 data_time: 0.0016 memory: 44138 loss: 0.3206 +2023/06/06 11:51:30 - mmengine - INFO - Epoch(train) [10][1700/3937] lr: 1.0716e-05 eta: 0:23:54 time: 0.6376 data_time: 0.0015 memory: 44138 loss: 0.3239 +2023/06/06 11:52:33 - mmengine - INFO - Epoch(train) [10][1800/3937] lr: 1.0653e-05 eta: 0:22:50 time: 0.6372 data_time: 0.0015 memory: 44138 loss: 0.3422 +2023/06/06 11:53:37 - mmengine - INFO - Epoch(train) [10][1900/3937] lr: 1.0594e-05 eta: 0:21:46 time: 0.6374 data_time: 0.0017 memory: 44138 loss: 0.3440 +2023/06/06 11:54:41 - mmengine - INFO - Epoch(train) [10][2000/3937] lr: 1.0537e-05 eta: 0:20:42 time: 0.6368 data_time: 0.0023 memory: 44138 loss: 0.3332 +2023/06/06 11:55:45 - mmengine - INFO - Epoch(train) [10][2100/3937] lr: 1.0483e-05 eta: 0:19:38 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3279 +2023/06/06 11:56:48 - mmengine - INFO - Epoch(train) [10][2200/3937] lr: 1.0432e-05 eta: 0:18:34 time: 0.6364 data_time: 0.0015 memory: 44138 loss: 0.3528 +2023/06/06 11:57:52 - mmengine - INFO - Epoch(train) [10][2300/3937] lr: 1.0384e-05 eta: 0:17:29 time: 0.6370 data_time: 0.0017 memory: 44138 loss: 0.3226 +2023/06/06 11:58:56 - mmengine - INFO - Epoch(train) [10][2400/3937] lr: 1.0338e-05 eta: 0:16:25 time: 0.6369 data_time: 0.0017 memory: 44138 loss: 0.3160 +2023/06/06 12:00:00 - mmengine - INFO - Epoch(train) [10][2500/3937] lr: 1.0296e-05 eta: 0:15:21 time: 0.6380 data_time: 0.0016 memory: 44138 loss: 0.3655 +2023/06/06 12:00:42 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 12:01:03 - mmengine - INFO - Epoch(train) [10][2600/3937] lr: 1.0256e-05 eta: 0:14:17 time: 0.6383 data_time: 0.0017 memory: 44138 loss: 0.3382 +2023/06/06 12:02:07 - mmengine - INFO - Epoch(train) [10][2700/3937] lr: 1.0219e-05 eta: 0:13:13 time: 0.6372 data_time: 0.0013 memory: 44138 loss: 0.3508 +2023/06/06 12:03:11 - mmengine - INFO - Epoch(train) [10][2800/3937] lr: 1.0185e-05 eta: 0:12:09 time: 0.6375 data_time: 0.0014 memory: 44138 loss: 0.3306 +2023/06/06 12:04:15 - mmengine - INFO - Epoch(train) [10][2900/3937] lr: 1.0154e-05 eta: 0:11:05 time: 0.6382 data_time: 0.0016 memory: 44138 loss: 0.3464 +2023/06/06 12:05:19 - mmengine - INFO - Epoch(train) [10][3000/3937] lr: 1.0126e-05 eta: 0:10:00 time: 0.6375 data_time: 0.0016 memory: 44138 loss: 0.3515 +2023/06/06 12:06:22 - mmengine - INFO - Epoch(train) [10][3100/3937] lr: 1.0101e-05 eta: 0:08:56 time: 0.6369 data_time: 0.0018 memory: 44138 loss: 0.3582 +2023/06/06 12:07:26 - mmengine - INFO - Epoch(train) [10][3200/3937] lr: 1.0078e-05 eta: 0:07:52 time: 0.6378 data_time: 0.0019 memory: 44138 loss: 0.3580 +2023/06/06 12:08:30 - mmengine - INFO - Epoch(train) [10][3300/3937] lr: 1.0058e-05 eta: 0:06:48 time: 0.6377 data_time: 0.0016 memory: 44138 loss: 0.3149 +2023/06/06 12:09:34 - mmengine - INFO - Epoch(train) [10][3400/3937] lr: 1.0041e-05 eta: 0:05:44 time: 0.6372 data_time: 0.0022 memory: 44138 loss: 0.3470 +2023/06/06 12:10:37 - mmengine - INFO - Epoch(train) [10][3500/3937] lr: 1.0027e-05 eta: 0:04:40 time: 0.6371 data_time: 0.0019 memory: 44138 loss: 0.3348 +2023/06/06 12:11:27 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 12:11:52 - mmengine - INFO - Epoch(train) [10][3600/3937] lr: 1.0016e-05 eta: 0:03:36 time: 0.6461 data_time: 0.0021 memory: 44138 loss: 0.3517 +2023/06/06 12:12:57 - mmengine - INFO - Epoch(train) [10][3700/3937] lr: 1.0008e-05 eta: 0:02:32 time: 0.6565 data_time: 0.0018 memory: 44138 loss: 0.3443 +2023/06/06 12:14:03 - mmengine - INFO - Epoch(train) [10][3800/3937] lr: 1.0003e-05 eta: 0:01:27 time: 0.6375 data_time: 0.0017 memory: 44138 loss: 0.3186 +2023/06/06 12:15:07 - mmengine - INFO - Epoch(train) [10][3900/3937] lr: 1.0000e-05 eta: 0:00:23 time: 0.6365 data_time: 0.0016 memory: 44138 loss: 0.3328 +2023/06/06 12:15:30 - mmengine - INFO - Exp name: clip_large_pretrain_4x256_IF_lr1e-4_20230606_050006 +2023/06/06 12:15:30 - mmengine - INFO - Saving checkpoint at 10 epochs +2023/06/06 12:17:01 - mmengine - INFO - Epoch(val) [10][57/57] accuracy/top1: 94.7705 single-label/precision_classwise: [96.6064224243164, 92.6566390991211] single-label/recall_classwise: [93.80720520019531, 95.9534912109375] single-label/f1-score_classwise: [95.18624114990234, 94.2762451171875] data_time: 0.0153 time: 1.2585