missing pad_token error when using GPT2Chinese

### 🐛 Describe the bug

When i run the code in summarization-rlhf using GPT2Chinese, the following error occurs . I have checked the "specail_tokens_map.json", it does have the "[PAD]" token. Any and all help is appreciated.

Errno 2] No such file or directory: '/tmp/ipykernel_31/1112272871.py' │
│ │
│ /kaggle/working/trlx/trlx/trlx.py:105 in train │
│ │
│ 102 │ │ if eval_prompts is None: │
│ 103 │ │ │ eval_prompts = prompts[:batch_size] │
│ 104 │ │ │
│ ❱ 105 │ │ trainer.make_experience(config.method.num_rollouts) │
│ 106 │ │
│ 107 │ # Offline training from the collected samples (e.g. SFT, ILQL) │
│ 108 │ elif samples: │
│ │
│ /kaggle/working/trlx/trlx/trainer/accelerate_ppo_trainer.py:281 in make_experience │
│ │
│ 278 │ │ while len(ppo_rl_elements) < num_rollouts: │
│ 279 │ │ │ stats = {} │
│ 280 │ │ │ # Get next batch in prompt dataset │
│ ❱ 281 │ │ │ batch: PromptBatch = next(self.prompt_iterator) │
│ 282 │ │ │ │
│ 283 │ │ │ rollout_generate_time = time() │
│ 284 │
│ │
│ /kaggle/working/trlx/trlx/utils/__init__.py:240 in infinite_dataloader │
│ │
│ 237 │ Returns a cyclic infinite dataloader from a finite dataloader │
│ 238 │ """ │
│ 239 │ for _ in repeat(dataloader): │
│ ❱ 240 │ │ yield from dataloader │
│ 241 │
│ │
│ /opt/conda/lib/python3.10/site-packages/accelerate/data_loader.py:378 in __iter__ │
│ │
│ 375 │ │ dataloader_iter = super().__iter__() │
│ 376 │ │ # We iterate one batch ahead to check when we are at the end │
│ 377 │ │ try: │
│ ❱ 378 │ │ │ current_batch = next(dataloader_iter) │
│ 379 │ │ except StopIteration: │
│ 380 │ │ │ yield │
│ 381 │
│ │
│ /opt/conda/lib/python3.10/site-packages/torch/utils/data/dataloader.py:634 in __next__ │
│ │
│ 631 │ │ │ if self._sampler_iter is None: │
│ 632 │ │ │ │ # TODO(https://github.com/pytorch/pytorch/issues/76750) │
│ 633 │ │ │ │ self._reset() # type: ignore[call-arg] │
│ ❱ 634 │ │ │ data = self._next_data() │
│ 635 │ │ │ self._num_yielded += 1 │
│ 636 │ │ │ if self._dataset_kind == _DatasetKind.Iterable and \ │
│ 637 │ │ │ │ │ self._IterableDataset_len_called is not None and \ │
│ │
│ /opt/conda/lib/python3.10/site-packages/torch/utils/data/dataloader.py:678 in _next_data │
│ │
│ 675 │ │
│ 676 │ def _next_data(self): │
│ 677 │ │ index = self._next_index() # may raise StopIteration │
│ ❱ 678 │ │ data = self._dataset_fetcher.fetch(index) # may raise StopIteration │
│ 679 │ │ if self._pin_memory: │
│ 680 │ │ │ data = _utils.pin_memory.pin_memory(data, self._pin_memory_device) │
│ 681 │ │ return data │
│ │
│ /opt/conda/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py:54 in fetch │
│ │
│ 51 │ │ │ │ data = [self.dataset[idx] for idx in possibly_batched_index] │
│ 52 │ │ else: │
│ 53 │ │ │ data = self.dataset[possibly_batched_index] │
│ ❱ 54 │ │ return self.collate_fn(data) │
│ 55 │
│ │
│ /kaggle/working/trlx/trlx/pipeline/offline_pipeline.py:160 in collate_fn │
│ │
│ 157 │ │
│ 158 │ def create_loader(self, batch_size: int, shuffle=False) -> DataLoader: │
│ 159 │ │ def collate_fn(xs): │
│ ❱ 160 │ │ │ out = self.tokenizer.pad([{"input_ids": x["input_ids"]} for x in xs], return │
│ 161 │ │ │ │
│ 162 │ │ │ for key in xs[0]: │
│ 163 │ │ │ │ if key != "input_ids" and key != "attention_mask": │
│ │
│ /opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:2995 in pad │
│ │
│ 2992 │ │ │ │ encoded_inputs[key] = to_py_obj(value) │
│ 2993 │ │ │
│ 2994 │ │ # Convert padding_strategy in PaddingStrategy │
│ ❱ 2995 │ │ padding_strategy, _, max_length, _ = self._get_padding_truncation_strategies( │
│ 2996 │ │ │ padding=padding, max_length=max_length, verbose=verbose │
│ 2997 │ │ ) │
│ 2998 │
│ │
│ /opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:2443 in │
│ _get_padding_truncation_strategies │
│ │
│ 2440 │ │ │
│ 2441 │ │ # Test if we have a padding token │
│ 2442 │ │ if padding_strategy != PaddingStrategy.DO_NOT_PAD and (not self.pad_token or sel │
│ ❱ 2443 │ │ │ raise ValueError( │
│ 2444 │ │ │ │ "Asking to pad but the tokenizer does not have a padding token. " │
│ 2445 │ │ │ │ "Please select a token to use as `pad_token` `(tokenizer.pad_token = tok │
│ 2446 │ │ │ │ "or add a new pad token via `tokenizer.add_special_tokens({'pad_token': │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as
`pad_token` `(tokenizer.pad_token = tokenizer.eos_token e.g.)` or add a new pad token via
`tokenizer.add_special_tokens({'pad_token': '[PAD]'})`.

### Which trlX version are you using?

_No response_

### Additional system and package information

_No response_