mmpretrain/configs/_base_/schedules/imagenet_bs4096_AdamW.py

# specific to vit pretrain
paramwise_cfg = dict(custom_keys={
    '.cls_token': dict(decay_mult=0.0),
    '.pos_embed': dict(decay_mult=0.0)
})

# optimizer
optimizer = dict(
    type='AdamW',
    lr=0.003,
    weight_decay=0.3,
    paramwise_cfg=paramwise_cfg,
)

# learning policy
param_scheduler = [
    # warm up learning rate schedule
    dict(
        type='LinearLR',
        start_factor=1e-4,
        by_epoch=True,
        begin=0,
        end=30,
        # update by iter
        convert_to_iter_based=True),
    # main learning rate scheduler
    dict(
        type='CosineAnnealingLR',
        T_max=270,
        by_epoch=True,
        begin=30,
        end=300,
    )
]

# train, val, test setting
train_cfg = dict(by_epoch=True, max_epochs=300)
val_cfg = dict(interval=1)  # validate every epoch
test_cfg = dict()