Table 3.

Hyper-parameters of BERTSUM, in the case of multiple candidate parameter values, the ultimately chosen parameter value is displayed in bold

Parameters	Values
encoder	(classifier/transformer/rnn)
batch size	(1000/2000/3000)
train steps	10,000
dropout	0.1
learning rate	$2e^{-3}·min\left(s,t,e,p^{-0.5},,,s,t,e,p,·,w,a,r,m,u,p^{-1.5}\right)$
warmup	(1000/10,000)
optimizer	adam