Add ORPO Trainer + support HF metrics directly from chunked loss functions + fixes to avoid torch compile recompilations

[shivam15s]

Summary

This PR adds support for the following:

1. LigerORPOTrainer: a wrapper on top of HuggingFace ORPO Trainer to use LigerORPOLoss module.
2. We also provide an example for using LigerORPOTrainer in examples/alignment/run_orpo.py
3. Change FusedLinearPreference base class' forward function to return additional metrics to align our implementation with HF ORPO Trainer
4. Additional refactor to avoid torch compile recompilations -- accumulate_chunk function now calls accumulate_helper which is torch compiled solely and input_chunk/target_chunk/target dimension 1 (seq len) is explicitly marked as dynamic to avoid recompilations

Testing Done

• Hardware Type:
• run make test to ensure correctness
• run make checkstyle to ensure code style
• run make test-convergence to ensure convergence

[ByronHsu]

awesome work!!