Open dignfei opened 3 months ago
数据的格式,和 dataset_info.json 中设置的格式不一样
你的代码没有更新到最新
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
[rank4]: ValueError: Some specified arguments are not used by the HfArgumentParser: ['--pref_loss:', 'orpo', '--orpo_beta', '0.05']
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" } },