You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
During some of my trainings I noticed, that the memory consumption differs greatly as the sentence size increases within an epoch. For short sentences in the beginning, TTS only consumed about 3GB, but then later for the long example sentences over 7,4GB. I guess a fixed batch size comes from tasks that deal with fixed size tensors, like in image classification. Given that batch size seems important for learning attention, it might be worth experimenting with dynamic batch sizes. That can probably double the batch size for medium sized sentences.
Any thoughts?
The text was updated successfully, but these errors were encountered:
@twerkmeister makes sense. My only concern is the learning rate. If the initial batch size vs the last batch size in an epoch is too different, it might turbulence the training. Anyhow, it is worth to try.
During some of my trainings I noticed, that the memory consumption differs greatly as the sentence size increases within an epoch. For short sentences in the beginning, TTS only consumed about 3GB, but then later for the long example sentences over 7,4GB. I guess a fixed batch size comes from tasks that deal with fixed size tensors, like in image classification. Given that batch size seems important for learning attention, it might be worth experimenting with dynamic batch sizes. That can probably double the batch size for medium sized sentences.
Any thoughts?
The text was updated successfully, but these errors were encountered: