报错。同样的代码（run_clm_pt_with_peft.py）和配置参数，在windows能正常在chinese-llama-2-1.3b-hf继续预训练，搬到linux就报错

[yinggaohai]

Traceback (most recent call last):
File "/home/yinggaohai/Mycodes/LLM/Chinese-LLaMA-Alpaca/Chinese-LLaMA-Alpaca-2/scripts/training/run_clm_pt_with_peft.py", line 726, in
main()
File "/home/yinggaohai/Mycodes/LLM/Chinese-LLaMA-Alpaca/Chinese-LLaMA-Alpaca-2/scripts/training/run_clm_pt_with_peft.py", line 694, in main
train_result = trainer.train(resume_from_checkpoint=checkpoint)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/trainer.py", line 1555, in train
return inner_training_loop(
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/trainer.py", line 1860, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/trainer.py", line 2725, in training_step
loss = self.compute_loss(model, inputs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/trainer.py", line 2748, in compute_loss
outputs = model(**inputs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/parallel/data_parallel.py", line 171, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/parallel/data_parallel.py", line 181, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/parallel/parallel_apply.py", line 89, in parallel_apply
output.reraise()
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/_utils.py", line 644, in reraise
raise exception
RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/parallel/parallel_apply.py", line 64, in _worker
output = module(*input, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/Mycodes/LLM/Chinese-LLaMA-Alpaca/Chinese-LLaMA-Alpaca-2/scripts/training/peft/peft_model.py", line 529, in forward
return self.base_model(
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 1034, in forward
outputs = self.model(
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 912, in forward
layer_outputs = self._gradient_checkpointing_func(
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/utils/checkpoint.py", line 249, in checkpoint
return CheckpointFunction.apply(function, preserve, *args)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/autograd/function.py", line 506, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/utils/checkpoint.py", line 107, in forward
outputs = run_function(*args)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 672, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 366, in forward
query_states = self.q_proj(hidden_states)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/Mycodes/LLM/Chinese-LLaMA-Alpaca/Chinese-LLaMA-Alpaca-2/scripts/training/peft/tuners/lora.py", line 375, in forward
result += self.lora_B(self.lora_A(self.lora_dropout(x))) * self.scaling
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/yinggaohai/anaconda3/envs/Chinese-LLaMA-Alpaca/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: expected scalar type Half but found Float

[yinggaohai]

把fp16改成false也继续报同样的错误