知识卡片

普通读书笔记卡 · 8664.c · 生成模型:GPT-6

训练数据字段必须实际对齐

理解等级:中级

训练器需要收到预期split和真实字段,格式化后还要检查模板、结束标记、截断及目标标签。配置dataset_text_field=text不代表原CSV一定具备正确合并文本;应抽查模型实际读入的token和有效损失区域。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      dataset_text_field = 'text', packing = True ) sft.train() sft.model.save_pretrained('/path/to/llama-2-it.csv') The relationship between the hyperparameters is very complex, and you might find surprising results. It will take several iterations before you hit the sweet spot. However, do not spend too much time squeezing out the last bit of performance from your fine-tuning, as that time is better spent developing better training data. In the next section,

    参考来源

    - 位置:《Designing Large Language Model Applications》第06章《微调》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch06.html) - 结论依据:摘录中关于训练数据字段必须实际对齐的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:dataset_text_field = 'text', packing = True ) sft.train() sft.model.save_pretrained('/path/to/llama-2-it.csv') The relationship between the hyperparameters is very complex, and you might find surprising results. It will take several iterations before you hit the sweet spot. However, do not spend too much time squeezing out the last bit of performance from your fine-tuning, as that time is better spent developing better training data. In the next section,