🧸 Fix unset tokenizer pad_token (#3290)

Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>

Author: LeonEricsson

trl/trainer/grpo_trainer.py

@@ -330,7 +330,9 @@ def reward_func(completions, **kwargs):
             Dataset to use for evaluation. It must meet the same requirements as `train_dataset`.
         processing_class ([`~transformers.PreTrainedTokenizerBase`], *optional*, defaults to `None`):
             Processing class used to process the data. The padding side must be set to "left". If `None`, the
-            processing class is loaded from the model's name with [`~transformers.AutoTokenizer.from_pretrained`].
+            processing class is loaded from the model's name with [`~transformers.AutoTokenizer.from_pretrained`]. A
+            padding token, `processing_class.pad_token`, must be set. If the processing class has not set a padding
+            token, `processing_class.eos_token` will be used as the default.
         reward_processing_classes (`Union[PreTrainedTokenizerBase, list[PreTrainedTokenizerBase]]`, *optional*, defaults to `None`):
             Processing classes corresponding to the reward functions specified in `reward_funcs`. Can be either:
 
@@ -436,6 +438,8 @@ def __init__(
         # Processing class
         if processing_class is None:
             processing_class = AutoTokenizer.from_pretrained(model.config._name_or_path, padding_side="left")
+        if processing_class.pad_token is None:
+            processing_class.pad_token = processing_class.eos_token
 
         # Reward functions
         if not isinstance(reward_funcs, list):