KJGithub2021
KJGithub2021
> @KJGithub2021 All experiments were running on a single NVIDIA GeForce 1080 (12G) GPU card. The default training parameters is 10 epochs and 96 batch_size with evaluation every 1000 steps....
> @KJGithub2021 It took about 90h (including evaluation on the dev set every 1000 steps) under the default setting, i.e., 10 epochs and 96 batch_size on a single NVIDIA GeForce...
> @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > 1. Enlarge batch_size with more advanced GPU cards > 2. Evaluate with less frequent steps, e.g....
> > @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > > > 1. Enlarge batch_size with more advanced GPU cards > > 2. Evaluate with...
> > > @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > > > > > 1. Enlarge batch_size with more advanced GPU cards > >...
> > > @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > > > > > 1. Enlarge batch_size with more advanced GPU cards > >...
> @KJGithub2021 Sorry, we do not have any experience of resuming model training from a saved checkpoint using google colab. No suggestion can be provided. Okay...but what was the purpose...
> @KJGithub2021 Sorry, we do not have any experience of resuming model training from a saved checkpoint using google colab. No suggestion can be provided. @JasonForJoy Understood. But how did...
> > @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > > > 1. Enlarge batch_size with more advanced GPU cards > > 2. Evaluate with...
> @KJGithub2021 About 50h on the Ubuntu V2 dataset. You might try: > > 1. Enlarge batch_size with more advanced GPU cards > 2. Evaluate with less frequent steps, e.g....