* fix model name

* fix: bug when distillation

* modify some default hyperparams to adapt to fine-tune downstream tasks

1. unset EMA because of the relatively small size of most downstream dataset;
2. use mean and std of IMN.

modified batch_size per gpu and update_freq in MobileViTv3_S.yaml for training with 4 gpus

add cooldown config

update optimizer

fix ParamAttr & update  test_tipc

fix tipc

update tipc config

remove docs of `_make_divisible`

refactor the implementation of "no weight decay"

fix model name

remove cooldown config