Llama Factory微调报错

[mkygogo]

参考readme中微调的方法，微调报错：
Setting num_proc from 16 back to 1 for the train split to disable multiprocessing as it only contains one shard.
Generating train split: 6 examples [00:00, 644.04 examples/s]
num_proc must be <= 6. Reducing num_proc to 6 for dataset of size 6.
Converting format of dataset (num_proc=6): 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 44.81 examples/s]
num_proc must be <= 6. Reducing num_proc to 6 for dataset of size 6.
Running tokenizer on dataset (num_proc=6): 0%| | 0/6 [00:01<?, ? examples/s]
multiprocess.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.10/site-packages/multiprocess/pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "/root/miniconda3/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 678, in _write_generator_to_queue
for i, result in enumerate(func(**kwargs)):
File "/root/miniconda3/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3476, in _map_single
batch = apply_function_on_filtered_inputs(
File "/root/miniconda3/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3338, in apply_function_on_filtered_inputs
processed_inputs = function(*fn_args, *additional_args, **fn_kwargs)
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/data/processors/supervised.py", line 107, in preprocess_supervised_dataset
input_ids, labels = _encode_supervised_example(
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/data/processors/supervised.py", line 48, in _encode_supervised_example
messages = template.mm_plugin.process_messages(prompt + response, images, videos, processor)
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/data/mm_plugin.py", line 433, in process_messages
image_processor: "BaseImageProcessor" = getattr(processor, "image_processor")
AttributeError: 'NoneType' object has no attribute 'image_processor'
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/root/miniconda3/bin/llamafactory-cli", line 8, in
sys.exit(main())
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/cli.py", line 112, in main
run_exp()
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/train/tuner.py", line 92, in run_exp
_training_function(config={"args": args, "callbacks": callbacks})
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/train/tuner.py", line 66, in _training_function
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/train/sft/workflow.py", line 51, in run_sft
dataset_module = get_dataset(template, model_args, data_args, training_args, stage="sft", **tokenizer_module)
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/data/loader.py", line 269, in get_dataset
dataset = _get_preprocessed_dataset(
File "/root/autodl-tmp/llamafactory/LLaMA-Factory-main/src/llamafactory/data/loader.py", line 204, in _get_preprocessed_dataset
dataset = dataset.map(
File "/root/miniconda3/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 560, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3165, in map
for rank, done, content in iflatmap_unordered(
File "/root/miniconda3/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 718, in iflatmap_unordered
[async_result.get(timeout=0.05) for async_result in async_results]
File "/root/miniconda3/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 718, in
[async_result.get(timeout=0.05) for async_result in async_results]
File "/root/miniconda3/lib/python3.10/site-packages/multiprocess/pool.py", line 774, in get
raise self._value
AttributeError: 'NoneType' object has no attribute 'image_processor'

[BUAADreamer]

应该是有些库没有装上，暂时推荐使用transformers==4.45.0，可以稳定跑通微调和推理

【重要】使用以下方式安装最新的llamafactory以及相应的库

git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics,deepspeed,minicpm_v]"
pip3 install transformers==4.45.0
pip3 install huggingface_hub==0.25.0

[mkygogo]

transformers和hugginfface_hud都安装了你说的版本，运行还是报一样的错误哦

[BUAADreamer]

transformers和hugginfface_hud都安装了你说的版本，运行还是报一样的错误哦

pip list 结果发一下

[mkygogo]

pip-list.txt

[BUAADreamer]

拉取最新代码后执行一下这一行，有一些语音依赖没装上

pip install -e ".[torch,metrics,deepspeed,minicpm_v]"

[BUAADreamer]

@mkygogo 能跑起来了吗？

[mkygogo]

不行哦，我是拉的llamafactory最新的代码，问题一样的，之前安装就是按照你们文档里的pip install -e ".[torch,metrics,deepspeed,minicpm_v]"，全部重新来一遍还是不行，貌似安装的时候有个warning，意思不支持minicpm-v。可能要等llamafactory更新吧

[BUAADreamer]

已经有很多人都微调成功了哟，你的pip list里没有torchaudio，说明没安装成功，有可能是环境嵌套，你试一下python -m pip install以下这些库，pip show torchaudio 确认安装好再试试 @mkygogo

soundfile
torchvision
torchaudio
vector_quantize_pytorch
vocos
msgpack
referencing
jsonschema_specifications
librosa