in bitsandbytes/optim/lars.py [0:0]
def __init__(self, params, lr=0.01, momentum=0, dampening=0,
weight_decay=0, nesterov=False, max_unorm=0.02):
if lr < 0.0:
raise ValueError("Invalid learning rate: {}".format(lr))
if momentum < 0.0:
raise ValueError("Invalid momentum value: {}".format(momentum))
if weight_decay < 0.0:
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
defaults = dict(lr=lr, momentum=momentum, dampening=dampening,
weight_decay=weight_decay, nesterov=nesterov, max_unorm=max_unorm)
if nesterov and (momentum <= 0 or dampening != 0):
raise ValueError("Nesterov momentum requires a momentum and zero dampening")
super(PytorchLARS, self).__init__(params, defaults)