about ending automatically after training

MCG-NJU / MMN

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

MIT License

89 stars 8 forks source link

about ending automatically after training #3

Closed menghuaa closed 2 years ago

menghuaa commented 2 years ago

Hi, when the model is finished training it cannot stop itself, I have to terminaterminate the taste the task, what causes this? How can I modify it so that it ends automatically after training?

zhenzhiwang commented 2 years ago

You could set the maximum training epoch in the configuration file. For example, https://github.com/MCG-NJU/MMN/blob/ac1cb74ca9b9e818d61a25eca39343ee40e3221a/configs/pool_activitynet_64x64_k9l4.yaml#L41 shows the maximum training epoch for ActivityNet-Captions dataset.