Commit 17f4ae11 authored by Vishnu Banna's avatar Vishnu Banna
Browse files

optimization package pr comments

parent d1988e3e
...@@ -54,10 +54,10 @@ class SGDTorchConfig(BaseOptimizerConfig): ...@@ -54,10 +54,10 @@ class SGDTorchConfig(BaseOptimizerConfig):
nesterov: bool = False nesterov: bool = False
momentum_start: float = 0.0 momentum_start: float = 0.0
momentum: float = 0.9 momentum: float = 0.9
warmup_steps: int = 1000 warmup_steps: int = 0
weight_decay: float = 0.0 weight_decay: float = 0.0
sim_torch: bool = False sim_torch: bool = False
weight_keys: List[str] = dataclasses.field( weight_keys: Optional[List[str]] = dataclasses.field(
default_factory=lambda:["kernel", "weight"]) default_factory=lambda:["kernel", "weight"])
bias_keys: List[str] = dataclasses.field( bias_keys: Optional[List[str]] = dataclasses.field(
default_factory=lambda:["bias", "beta"]) default_factory=lambda:["bias", "beta"])
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment