Dataset[0] → {"input_ids": [101, 2003], "labels": 1}
Dataset[1] → {"input_ids": [101, 2003, 1996], "labels": 0}
Dataset[2] → {"input_ids": [101, 7592], "labels": 1}
         ↓  collator
{
  "input_ids": tensor([[101, 2003,    0],   # padded to longest
                        [101, 2003, 1996],
                        [101, 7592,    0]]),
  "labels":    tensor([1, 0, 1])
}

import torch
from dataclasses import dataclass
from transformers import DataCollatorWithPadding, PreTrainedTokenizerBase

@dataclass
class DataCollatorWithScore(DataCollatorWithPadding):
    tokenizer: PreTrainedTokenizerBase

    def __call__(self, features):
        scores = [f.pop("score") for f in features]

        batch = super().__call__(features)
        batch["score"] = torch.tensor(scores, dtype=torch.float)

        return batch

trainer = Trainer(
    ...,
    data_collator=DataCollatorWithScore(tokenizer=tokenizer),
)

import torch
from dataclasses import dataclass
from transformers.data.data_collator import DataCollatorMixin
from trl.trainer.utils import pad

@dataclass
class DataCollatorForPreference(DataCollatorMixin):
    pad_token_id: int
    pad_to_multiple_of: int | None = None

    def __call__(self, examples: list[dict]) -> dict:
        chosen_input_ids   = [torch.tensor(ex["chosen_ids"])   for ex in examples]
        rejected_input_ids = [torch.tensor(ex["rejected_ids"]) for ex in examples]

        input_ids      = chosen_input_ids + rejected_input_ids
        attention_mask = [torch.ones_like(ids) for ids in input_ids]

        output = {
            "input_ids": pad(
                input_ids,
                padding_value=self.pad_token_id,
                padding_side="right",
                pad_to_multiple_of=self.pad_to_multiple_of,
            ),
            "attention_mask": pad(
                attention_mask,
                padding_value=0,
                padding_side="right",
                pad_to_multiple_of=self.pad_to_multiple_of,
            ),
        }

        ...

        return output