in bitsandbytes/optim/adagrad.py [0:0]
def __init__(self, params, lr=1e-2, lr_decay=0, weight_decay=0, initial_accumulator_value=0, eps=1e-10,
optim_bits=8, args=None, min_8bit_size=4096, percentile_clipping=100, block_wise=True):
if not 0.0 <= lr:
raise ValueError("Invalid learning rate: {}".format(lr))
if not 0.0 <= weight_decay:
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
if initial_accumulator_value != 0.0:
raise ValueError('Initial accumulator value != 0.0 not supported!')
if lr_decay != 0.0:
raise ValueError('Lr Decay != 0.0 not supported!')
assert block_wise
super(Adagrad8bit, self).__init__('adagrad', params, lr, (0.0, 0.0), eps,
weight_decay, 8, args, min_8bit_size, percentile_clipping, block_wise)