Integration testing for DPO

[SalmanMohammadi]

We have a gap in our CI for the DPO recipes which we should address. To do this, we should:

1. Verify correctness of the algorithm against some reference implementation (maybe this is overkill, but it's been a while since it was originally contributed). This may also be an opportunity to ensure it works OK on other datasets. cc @RdoubleA RE Anthropic HH
2. Run the model with some mock inputs/models to obtain reference loss values.
3. Write a test which ensures that when the recipe is launched with the above inputs/models it obtains expected loss values. This should sufficiently guard the recipe against future changes which may trigger re-verifying the correctness.

See similar recipe tests for PPO, LoRA fine-tune, etc.

[andrewldesousa]

Hey @SalmanMohammadi - is this ticket still up for grabs? I can start taking a look at it this weekend if still available.

[SalmanMohammadi]

Hey @andrewldesousa, yes please!