We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent d6b8fa6 commit b724bb7Copy full SHA for b724bb7
emerging_optimizers/orthogonalized_optimizers/muon.py
@@ -64,7 +64,7 @@ def __init__(
64
params: ParamsT,
65
lr: float = 3e-4,
66
momentum_beta: float = 0.95,
67
- use_nesterov: bool = True,
+ use_nesterov: bool = False,
68
weight_decay: float = 0.01,
69
use_decoupled_weight_decay: bool = True,
70
fp32_matmul_prec: str = "medium",
0 commit comments