search

neulab / awesome-align

A neural word aligner based on multilingual BERT
https://arxiv.org/abs/2101.08231
BSD 3-Clause "New" or "Revised" License
321 stars 46 forks source link

How can I resume training from a checkpoint? #42

Closed MusfiqDehan closed 2 years ago

MusfiqDehan commented 2 years ago

Hi, First of all thanks for these amazing tools and amazing documentation. I am training awesome_align using a parallel corpus. My dataset is quite large. Is there any way to resume training from checkpoint? During training, many checkpoints are being created in the Output directory (checkpoint-4000, checkpoint-8000 etc). How can I use those checkpoints?

Thanks in advance.

zdou0830 commented 2 years ago

Hi, this issue https://github.com/neulab/awesome-align/issues/39 may be helpful.