微调基于 InternLM2-7B 的模型时错误：TypeError: Linear4bit.forward() takes 2 positional arguments but 3 were given

微调基于 InternLM2-7B 的模型 `Mar2Ding/songcomposer_sft` 时出错。

版本：
python==3.10.9
transformers==4.45.1
torch==2.4.1
xtuner==0.1.23

错误信息：
```
10/05 22:39:41 - mmengine - INFO - before_train in EvaluateChatHook.
You are using an old version of the checkpointing format that is deprecated (We will also silently ignore `gradient_checkpointing_kwargs` in case you passed it).Please update to the new format on your modeling file. To use the new format, you need to completely remove the definition of the method `_set_gradient_checkpointing` in your model.
The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
[rank0]: Traceback (most recent call last):
[rank0]: File "/root/miniconda3/lib/python3.10/site-packages/xtuner/tools/train.py", line 360, in
[rank0]: main()
[rank0]: File "/root/miniconda3/lib/python3.10/site-packages/xtuner/tools/train.py", line 356, in main
[rank0]: runner.train()
[rank0]: File "/root/miniconda3/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1777, in train
[rank0]: model = self.train_loop.run() # type: ignore
[rank0]: File "/root/miniconda3/lib/python3.10/site-packages/mmengine/runner/loops.py", line 273, in run
[rank0]: self.runner.call_hook('before_train')
[rank0]: File "/root/miniconda3/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1841, in call_hook
[rank0]: raise TypeError(f'{e} in {hook}') from None
[rank0]: TypeError: Linear4bit.forward() takes 2 positional arguments but 3 were given in
[rank0]:[W1005 22:39:42.025200903 ProcessGroupNCCL.cpp:1168] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())
W1005 22:39:44.037000 140169750185792 torch/distributed/elastic/multiprocessing/api.py:858] Sending process 6539 closing signal SIGTERM
E1005 22:39:44.353000 140169750185792 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 1 (pid: 6540) of binary: /root/miniconda3/bin/python
Traceback (most recent call last):
File "/root/miniconda3/bin/torchrun", line 8, in
sys.exit(main())
File "/root/miniconda3/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper
return f(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main
run(args)
File "/root/miniconda3/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run
elastic_launch(
File "/root/miniconda3/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/root/miniconda3/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
/root/miniconda3/lib/python3.10/site-packages/xtuner/tools/train.py FAILED
------------------------------------------------------------
Failures:

------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2024-10-05_22:39:44
host : autodl-container-24364abc14-f76f21bf
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 6540)
error_file:
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
```

代码（修改自 `internlm2_7b_qlora_oasst1_e3`，只改了数据集格式的部分）：
```python
# Copyright (c) OpenMMLab. All rights reserved.
import torch
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
from peft import LoraConfig
from torch.optim import AdamW
from transformers import (AutoModelForCausalLM, AutoTokenizer,
BitsAndBytesConfig)

from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import oasst1_map_fn, template_map_fn_factory, openai_map_fn
from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook,
VarlenAttnArgsToMessageHubHook)
from xtuner.engine.runner import TrainLoop
from xtuner.model import SupervisedFinetune
from xtuner.parallel.sequence import SequenceParallelSampler
from xtuner.utils import PROMPT_TEMPLATE

#######################################################################
# PART 1 Settings #
#######################################################################
# Model
# pretrained_model_name_or_path = 'internlm/internlm2-7b'
pretrained_model_name_or_path = 'Mar2Ding/songcomposer_sft'
use_varlen_attn = False

# Data
# data_path = 'timdettmers/openassistant-guanaco'
data_path = './train_data2.json'
prompt_template = PROMPT_TEMPLATE.default
max_length = 2048
pack_to_max_length = True

# parallel
sequence_parallel_size = 1

# Scheduler & Optimizer
batch_size = 1 # per_device
accumulative_counts = 16
accumulative_counts *= sequence_parallel_size
dataloader_num_workers = 0
max_epochs = 3
optim_type = AdamW
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1 # grad clip
warmup_ratio = 0.03

# Save
save_steps = 500
save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 500
SYSTEM = ''
evaluation_inputs = [
"""According to the emotion, given the following lyrics, create a suitable melody. Total 6 lines.The first line:暖|日|融|融|照|画|堂
The second line:柳|丝|轻|舞|燕|成|双
The third line:桃|花|含|笑|映|红|妆
The fourth line:一|曲|清|歌|传|四|野
The fifth line:满|园|春|色|醉|心|房
The sixth line:人|生|何|处|不|芬|芳

"""
]

#######################################################################
# PART 2 Model & Tokenizer #
#######################################################################
tokenizer = dict(
type=AutoTokenizer.from_pretrained,
pretrained_model_name_or_path=pretrained_model_name_or_path,
trust_remote_code=True,
padding_side='right')

model = dict(
type=SupervisedFinetune,
use_varlen_attn=use_varlen_attn,
llm=dict(
type=AutoModelForCausalLM.from_pretrained,
pretrained_model_name_or_path=pretrained_model_name_or_path,
trust_remote_code=True,
torch_dtype=torch.float16,
quantization_config=dict(
type=BitsAndBytesConfig,
load_in_4bit=True,
load_in_8bit=False,
llm_int8_threshold=6.0,
llm_int8_has_fp16_weight=False,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type='nf4')),
lora=dict(
type=LoraConfig,
r=64,
lora_alpha=16,
lora_dropout=0.1,
bias='none',
task_type='CAUSAL_LM'))

#######################################################################
# PART 3 Dataset & Dataloader #
#######################################################################
train_dataset = dict(
type=process_hf_dataset,
# dataset=dict(type=load_dataset, path=alpaca_en_path),
dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),

tokenizer=tokenizer,
max_length=max_length,
# dataset_map_fn=oasst1_map_fn,
dataset_map_fn=openai_map_fn,
template_map_fn=dict(
type=template_map_fn_factory, template=prompt_template),
remove_unused_columns=True,
shuffle_before_pack=True,
pack_to_max_length=pack_to_max_length,
use_varlen_attn=use_varlen_attn)

sampler = SequenceParallelSampler \
if sequence_parallel_size > 1 else DefaultSampler
train_dataloader = dict(
batch_size=batch_size,
num_workers=dataloader_num_workers,
dataset=train_dataset,
sampler=dict(type=sampler, shuffle=True),
collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn))

#######################################################################
# PART 4 Scheduler & Optimizer #
#######################################################################
# optimizer
optim_wrapper = dict(
type=AmpOptimWrapper,
optimizer=dict(
type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
accumulative_counts=accumulative_counts,
loss_scale='dynamic',
dtype='float16')

# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501
param_scheduler = [
dict(
type=LinearLR,
start_factor=1e-5,
by_epoch=True,
begin=0,
end=warmup_ratio * max_epochs,
convert_to_iter_based=True),
dict(
type=CosineAnnealingLR,
eta_min=0.0,
by_epoch=True,
begin=warmup_ratio * max_epochs,
end=max_epochs,
convert_to_iter_based=True)
]

# train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)

#######################################################################
# PART 5 Runtime #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [
dict(type=DatasetInfoHook, tokenizer=tokenizer),
dict(
type=EvaluateChatHook,
tokenizer=tokenizer,
every_n_iters=evaluation_freq,
evaluation_inputs=evaluation_inputs,
system=SYSTEM,
prompt_template=prompt_template)
]

if use_varlen_attn:
custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]

# configure default hooks
default_hooks = dict(
# record the time of every iteration.
timer=dict(type=IterTimerHook),
# print log every 10 iterations.
logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
# enable the parameter scheduler.
param_scheduler=dict(type=ParamSchedulerHook),
# save checkpoint per `save_steps`.
checkpoint=dict(
type=CheckpointHook,
by_epoch=False,
interval=save_steps,
max_keep_ckpts=save_total_limit),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type=DistSamplerSeedHook),
)

# configure environment
env_cfg = dict(
# whether to enable cudnn benchmark
cudnn_benchmark=False,
# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
# set distributed parameters
dist_cfg=dict(backend='nccl'),
)

# set visualizer
visualizer = None

# set log level
log_level = 'INFO'

# load from which checkpoint
load_from = None

# whether to resume training from the loaded checkpoint
resume = False

# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)

# set log processor
log_processor = dict(by_epoch=False)
```