Spaces:
Running
Running
File size: 1,279 Bytes
6a62ffb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import torch.optim
from . import LegacyFairseqOptimizer, register_optimizer
@register_optimizer("adagrad")
class Adagrad(LegacyFairseqOptimizer):
def __init__(self, args, params):
super().__init__(args)
self._optimizer = torch.optim.Adagrad(params, **self.optimizer_config)
@staticmethod
def add_args(parser):
"""Add optimizer-specific arguments to the parser."""
# fmt: off
parser.add_argument('--weight-decay', '--wd', default=0.0, type=float, metavar='WD',
help='weight decay')
# fmt: on
@property
def optimizer_config(self):
"""
Return a kwarg dictionary that will be used to override optimizer
args stored in checkpoints. This allows us to load a checkpoint and
resume training using a different set of optimizer args, e.g., with a
different learning rate.
"""
return {
"lr": self.args.lr[0],
"weight_decay": self.args.weight_decay,
}
@property
def supports_flat_params(self):
return False
|