diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index 443c8b267f..bcfe4d7774 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -177,6 +177,7 @@ def grpo_trainer__get_per_token_logps(function_name, function): if function_name != "_get_per_token_logps": return function def _get_per_token_logps(self, model, input_ids, attention_mask, logits_to_keep): + print(self.args.unsloth_num_chunks) if self.args.unsloth_num_chunks != 1: return None if not hasattr(self, '_autocast_dtype'): self._autocast_dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16