Fix typo in GRPO quickstart

[dwisdom0]

What does this PR do?

This PR updates the GRPO example in the quickstart to make it work. Before this PR, the example referenced a keyword argument reward_function that doesn't exist on the GRPOTrainer. After this PR, a user can copy/paste the example and have it run correctly.

The example in the GRPOTrainer reference documentation has the correct keyword argument reward_funcs.
https://huggingface.co/docs/trl/en/grpo_trainer#trl.GRPOTrainer.example

trainer = GRPOTrainer(
    model="Qwen/Qwen2-0.5B-Instruct",
    reward_funcs=reward_func,
    train_dataset=dataset,
)

Before (erroring out)

Traceback (most recent call last):
  File "/Users/freebie/code/python/llm_chess_rlvr/grpo_hello_world.py", line 9, in <module>
    trainer = GRPOTrainer(
              ^^^^^^^^^^^^
TypeError: GRPOTrainer.__init__() got an unexpected keyword argument 'reward_function'

After (running successfully)

config.json: 100%|██████████████████████████████████████████████████████████████████████████████████| 659/659 [00:00<00:00, 8.35MB/s]
model.safetensors: 100%|██████████████████████████████████████████████████████████████████████████| 988M/988M [00:12<00:00, 81.9MB/s]
generation_config.json: 100%|███████████████████████████████████████████████████████████████████████| 242/242 [00:00<00:00, 3.79MB/s]
tokenizer_config.json: 7.30kB [00:00, 22.6MB/s]
vocab.json: 2.78MB [00:00, 52.5MB/s]
merges.txt: 1.67MB [00:00, 159MB/s]
tokenizer.json: 7.03MB [00:00, 194MB/s]
The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.
  0%|                                                                                                     | 0/350166 [00:00<?, ?it/s]

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.

[qgallouedec]

Thanks!