鉴于配置momentumPerMB=0.9
,我在第一个时代的路上观察momentumAsTimeConstant
的值。剩余的时代具有预期的这个价值。这似乎只发生在并行训练中(1bit和BM,尚未验证MA)。
01/11/2017 00:08:08: Starting Epoch 1: learning rate per sample = 0.000500 effective momentum = 0.900000 momentum as time constant = 155504.2 samples
01/11/2017 00:18:04: Starting Epoch 2: learning rate per sample = 0.000500 effective momentum = 0.900000 momentum as time constant = 19438.0 samples
为什么会发生这种情况?
答案 0 :(得分:1)
我们建议您指定momentumAsTimeConstant
,因为此度量对于小批量大小不变。