Add dpo

[wtmlon]

PR types

PR changes

Description

新增 dpo 训练框架及单测

[paddle-bot[bot]]

Thanks for your contribution!

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 78.43137% with 22 lines in your changes missing coverage. Please review.

Project coverage is 55.28%. Comparing base (09a0ce7) to head (4c24566). Report is 163 commits behind head on develop.

:exclamation: Current head 4c24566 differs from pull request most recent head 1572b27

Please upload reports for the commit 1572b27 to get more accurate results.

Files	Patch %	Lines
paddlenlp/transformers/tokenizer_utils.py	87.20%	11 Missing :warning:
paddlenlp/datasets/intokens_dataset.py	16.66%	10 Missing :warning:
paddlenlp/transformers/tokenizer_utils_base.py	66.66%	1 Missing :warning:

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #8285      +/-   ##
===========================================
- Coverage    55.36%   55.28%   -0.09%     
===========================================
  Files          614      613       -1     
  Lines        96016    95712     -304     
===========================================
- Hits         53164    52912     -252     
+ Misses       42852    42800      -52     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[github-actions[bot]]

This Pull Request is stale because it has been open for 60 days with no activity. 当前Pull Request 60天内无活动，被标记为stale。