原书出处
Natural Language Processing in Action, Second Edition
Recall that in your first fine-tuning run, the model trained for exactly one epoch. Your hunch that the model could have trained longer to achieve better results is likely correct. You want to find the sweet spot in terms of the amount of training to do before the model overfits on the training samples. Configure options to enable evaluation during training, so you can also
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-9.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36