dynamic temperature

[shirinyamani]

What does this PR do?

This PR adds dynamic sampling temperature with cosine decay toward min_temp. The idea is we have warmup steps, during which the temp is linearly increased then in between warmup_step and max_steps we decay the temp by cosine.
The goal is to see the impact of if particularly in the generation quality!

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a GitHub issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.