Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

RLHF & Preference Optimization1 / 7

Chapter 121 / 7

RLHF & Preference Optimization

Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

Target interface

bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor)

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.

solution.pyPython

Local draft

import torch
import torch.nn.functional as F

def bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor) -> torch.Tensor:
    raise NotImplementedError

⌘/Ctrl↵to submit

AI review

No review yet

Submit your solution for a verdict, a score out of 100 and concrete feedback. Any correct approach passes.

Chapter 121 / 7

RLHF & Preference Optimization

Implement the Bradley–Terry pairwise reward-model loss in PyTorch

Easy

Target interface

bt_loss(reward_chosen: torch.Tensor, reward_rejected: torch.Tensor)

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints0 / 2

Reference solution

Your own code stays in the editor.