fix(pu): fix last_linear_layer_weight_bias_init_zero in MLP and add its unittest

[puyuan1996]

Description

fix last_linear_layer_weight_bias_init_zero in MLP and add its unittest

Related Issue

TODO

Check List

• merge the latest version source branch/repo, and resolve all the conflicts
• pass style check
• pass all the tests

[codecov]

Codecov Report

Merging #650 (dd238a2) into main (93e4fa5) will increase coverage by 0.01%.
The diff coverage is 92.68%.

❗ Current head dd238a2 differs from pull request most recent head 5a514fd. Consider uploading reports for the commit 5a514fd to get more accurate results

@@            Coverage Diff             @@
##             main     #650      +/-   ##
==========================================
+ Coverage   82.73%   82.74%   +0.01%     
==========================================
  Files         581      581              
  Lines       47587    47604      +17     
==========================================
+ Hits        39370    39390      +20     
+ Misses       8217     8214       -3     

Flag	Coverage Δ
unittests	82.74% <92.68%> (+0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
ding/torch_utils/network/nn_module.py	95.74% <78.57%> (+0.76%)	⬆️
ding/torch_utils/network/tests/test_nn_module.py	100.00% <100.00%> (ø)

... and 6 files with indirect coverage changes

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.