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
There's no related config that gives the batch size of performing gradient on minibatchs as introduced in the D4FT paper, how can I reproduce the experiment in section 6.2 that tests the convergence speed on different batch size?
The text was updated successfully, but these errors were encountered:
There's no related config that gives the batch size of performing gradient on minibatchs as introduced in the D4FT paper, how can I reproduce the experiment in section 6.2 that tests the convergence speed on different batch size?
The text was updated successfully, but these errors were encountered: