模型训练无法收敛

THUNLP-MT / THUMT

An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group

BSD 3-Clause "New" or "Revised" License

701 stars 197 forks source link

Closed baoyu-yuan closed 3 years ago

baoyu-yuan commented 3 years ago

hello，我按照workthrough的教程训练模型，使用的默认参数，steps设置为100000，loss降到2-3之间后一直处于震荡，没有明显下降趋势。请问可以具体对哪些参数进行调整吗？