h : S SK r S\\\\\4 S\\ 4S jrg) N completionsreturnc SnU Vs/ s H
o3S S PM nnU Vs/ s H9 n[ R " X%[ R [ R - 5 PM; nnU Vs/ s H
ow( a SOSPM sn$ s snf s snf s snf )aF
Reward function that checks if the reasoning process is enclosed within `""` and `""` tags. The
function returns a reward of 1.0 if the format is correct, otherwise 0.0.
Args:
completions (`list[list[dict[str, str]]]`):
List of completions to be evaluated. Each completion must be a list of one message, i.e. a dictionary
containing the key `"content"` with the value being the text of the completion.
**kwargs:
Additional keyword arguments. This function does not use them, but they are required in the function
signature to ensure compatibility with trainers like [`GRPOTrainer`].
Returns:
`list[float]`:
A list of rewards, where each reward is 1.0 if the completion matches the expected format, otherwise 0.0.
Example:
```python
>>> from trl.rewards import think_format_reward
>>> completions = [
... [{"content": "\nThis is my reasoning.\n\nThis is my answer."}],
... [{"content": "\nThis is my reasoning.\nThis is my answer."}],
... ]
>>> think_format_reward(completions)
[1.0, 0.0]
```
z%^(?!.*)(.*?).*$r contentg ?g )rematchDOTALL MULTILINE)r kwargspattern
completioncompletion_contentsr matchesr s T/home/james-whalen/.local/lib/python3.13/site-packages/trl/rewards/format_rewards.pythink_format_rewardr s{ : 7GFQRk
a=3kRSfgSfrxx"))bll*BCSfGg/6 7we5Cc !w 77 Sg 7s A;A B $B)r listdictstrfloatr r r s4
8T$tCH~*>%? 8dSXk 8r