2023/06/06 05:00:15 - 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: 424435667 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 05:00:19 - mmengine - INFO - Config: optim_wrapper = dict( optimizer=dict( type='AdamW', lr=0.0003, weight_decay=0.3, _scope_='mmpretrain'), paramwise_cfg=dict( custom_keys=dict({ '.cls_token': dict(decay_mult=0.0), '.pos_embed': dict(decay_mult=0.0) })), type='AmpOptimWrapper', dtype='bfloat16', clip_grad=None) param_scheduler = [ dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=False, begin=0) ] train_cfg = dict(by_epoch=True, max_epochs=10, val_interval=1) val_cfg = dict() test_cfg = dict() auto_scale_lr = dict(base_batch_size=4096) model = dict( type='ImageClassifier', backbone=dict( frozen_stages=24, type='VisionTransformer', arch='l', img_size=224, patch_size=14, drop_rate=0.1, pre_norm=True, final_norm=False, init_cfg=dict( type='Pretrained', checkpoint='ckpt/openclip-ViT-L-14.pth', prefix='backbone')), neck=dict( type='CLIPProjection', in_channels=1024, out_channels=768, init_cfg=dict( type='Pretrained', checkpoint='ckpt/openclip-ViT-L-14.pth', prefix='backbone')), head=dict( type='LinearClsHead', num_classes=2, in_channels=768, loss=dict(type='CrossEntropyLoss', loss_weight=1.0), init_cfg=None), init_cfg=dict( type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0), train_cfg=None) dataset_type = 'CustomDataset' data_preprocessor = dict( num_classes=2, mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) bgr_mean = [103.53, 116.28, 123.675] bgr_std = [57.375, 57.12, 58.395] train_pipeline = [ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='ResizeEdge', scale=256, edge='short', backend='pillow', interpolation='bicubic'), dict(type='CenterCrop', crop_size=224), dict(type='PackInputs') ] train_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stablediffusionV2-1-dpmsolver-25-1m.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/cc1m.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=True)) val_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV2-1-dpmsolver-25-1w.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=False)) val_evaluator = [ dict(type='Accuracy', topk=1), dict(type='SingleLabelMetric', average=None) ] test_dataloader = dict( pin_memory=True, persistent_workers=True, collate_fn=dict(type='default_collate'), batch_size=128, num_workers=10, dataset=dict( type='ConcatDataset', datasets=[ dict( type='CustomDataset', data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/stablediffusionV2-1-dpmsolver-25-1w.tsv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]), dict( type='CustomDataset', data_root='', ann_file= '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/val/cc1w.csv', pipeline=[ dict(type='LoadImageFromFile'), dict( type='RandomResizedCrop', scale=224, backend='pillow', interpolation='bicubic'), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackInputs') ]) ]), sampler=dict(type='DefaultSampler', shuffle=False)) test_evaluator = [ dict(type='Accuracy', topk=1), dict(type='SingleLabelMetric', average=None) ] custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')] default_scope = 'mmpretrain' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='VisualizationHook', enable=True)) env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='UniversalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), dict(type='TensorboardVisBackend') ]) log_level = 'INFO' load_from = None resume = False randomness = dict(seed=None, deterministic=False) launcher = 'slurm' work_dir = 'workdir/clip_large_pretrain_4x256_sdv2_lr3e-4'