RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

[vpegasus]

I used peft to fine tune baichuan llm via lora way. I ran the same fine-tuning code as 7B for 13B, but something went wrong:

/opt/conda/envs/trl/lib/python3.10/site-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
  warnings.warn(
/opt/conda/envs/trl/lib/python3.10/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
  warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
Cell In[21], line 1
----> 1 trainer.train()
      2 model.save_pretrained("baichuan13b/baichuan13b/")

File /opt/conda/envs/trl/lib/python3.10/site-packages/transformers/trainer.py:1537, in Trainer.train(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)
   1532     self.model_wrapped = self.model
   1534 inner_training_loop = find_executable_batch_size(
   1535     self._inner_training_loop, self._train_batch_size, args.auto_find_batch_size
   1536 )
-> 1537 return inner_training_loop(
   1538     args=args,
   1539     resume_from_checkpoint=resume_from_checkpoint,
   1540     trial=trial,
   1541     ignore_keys_for_eval=ignore_keys_for_eval,
   1542 )

File /opt/conda/envs/trl/lib/python3.10/site-packages/transformers/trainer.py:1802, in Trainer._inner_training_loop(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)
   1799     self.control = self.callback_handler.on_step_begin(args, self.state, self.control)
   1801 with self.accelerator.accumulate(model):
-> 1802     tr_loss_step = self.training_step(model, inputs)
   1804 if (
   1805     args.logging_nan_inf_filter
   1806     and not is_torch_tpu_available()
   1807     and (torch.isnan(tr_loss_step) or torch.isinf(tr_loss_step))
   1808 ):
   1809     # if loss is nan or inf simply add the average of previous logged losses
   1810     tr_loss += tr_loss / (1 + self.state.global_step - self._globalstep_last_logged)

File /opt/conda/envs/trl/lib/python3.10/site-packages/transformers/trainer.py:2658, in Trainer.training_step(self, model, inputs)
   2656         scaled_loss.backward()
   2657 else:
-> 2658     self.accelerator.backward(loss)
   2660 return loss.detach() / self.args.gradient_accumulation_steps

File /opt/conda/envs/trl/lib/python3.10/site-packages/accelerate/accelerator.py:1842, in Accelerator.backward(self, loss, **kwargs)
   1840     return
   1841 elif self.scaler is not None:
-> 1842     self.scaler.scale(loss).backward(**kwargs)
   1843 else:
   1844     loss.backward(**kwargs)

File /opt/conda/envs/trl/lib/python3.10/site-packages/torch/_tensor.py:487, in Tensor.backward(self, gradient, retain_graph, create_graph, inputs)
    477 if has_torch_function_unary(self):
    478     return handle_torch_function(
    479         Tensor.backward,
    480         (self,),
   (...)
    485         inputs=inputs,
    486     )
--> 487 torch.autograd.backward(
    488     self, gradient, retain_graph, create_graph, inputs=inputs
    489 )

File /opt/conda/envs/trl/lib/python3.10/site-packages/torch/autograd/__init__.py:200, in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)
    195     retain_graph = create_graph
    197 # The reason we repeat same the comment below is that
    198 # some Python versions print out the first line of a multi-line function
    199 # calls in the traceback and some print out the last line
--> 200 Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
    201     tensors, grad_tensors_, retain_graph, create_graph, inputs,
    202     allow_unreachable=True, accumulate_grad=True)

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

could you please help me to fix this, thx