Simplify and update trl examples (#38772)
* Simplify and update trl examples
* Remove optim_args from SFTConfig in Trainer documentation
* Update docs/source/en/trainer.md
* Apply suggestions from code review
* Update docs/source/en/trainer.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
---------
Co-authored-by: Quentin Gallouédec <qgallouedec@Quentins-MacBook-Pro.local>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
