control learning rate in train_text_cyc_ptb.py example

[d1024choi]

Could you explain why you control learning rate in optimizer in the example?

tmp = float((epoch-1)%args.cycle)/args.cycle cur_lr = args.lr*0.5*(1+np.cos(tmp*np.pi)) for param_group in optimizer.param_groups: param_group['lr'] = cur_lr