Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations. Parent comment
In section 4.8 they compare accuracy at the same amount of training time for the biggest of each model and show that ALBERT is substantially better.
There are no comments on this comment yet.
In section 4.8 they compare accuracy at the same amount of training time for the biggest of each model and show that ALBERT is substantially better.