运行复现代码，为什么报错？

[dignfei]

数据格式明显是错的

"dpo_mix_en": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "en",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},
"dpo_mix_zh": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "zh",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
},

[dignfei]

数据的格式，和 dataset_info.json 中设置的格式不一样

[hiyouga]

你的代码没有更新到最新

[dignfei]

你的代码没有更新到最新

我更新到了复现代码中指定的版本
git clone https://github.com/hiyouga/LLaMA-Factory.git
git reset --hard 25aeaae51b6d08a747e222bbcb27e75c4d56a856
没有用最新版，因为最新版不支持orpo参数

[dignfei]

[dignfei]

[rank4]: ValueError: Some specified arguments are not used by the HfArgumentParser: ['--pref_loss:', 'orpo', '--orpo_beta', '0.05']