Merge pull request #271 from kozistr/fix/kwargs

[Fix] Add missing kwargs

Author: kozistr

docs/changelogs/v3.1.2.md

@@ -71,7 +71,7 @@ lint.select = [
 ]
 lint.ignore = [
     "B905", "D100", "D102", "D104", "D105", "D107", "D203", "D213", "D413", "PIE790", "PLR0912", "PLR0913", "PLR0915",
-    "PLR2004", "RUF013", "Q003",
+    "PLR2004", "RUF013", "Q003", "ARG002",
 ]
 lint.fixable = ["ALL"]
 lint.unfixable = ["F401"]

pyproject.toml

@@ -52,7 +52,7 @@ def get_linear_lr(self) -> float:
 
         return self.min_lr + (self.max_lr - self.min_lr) * ((1.0 - progress) / (1.0 - progress / 2.0))
 
-    def step(self, epoch: Optional[int] = None) -> float:  # noqa: ARG002
+    def step(self, epoch: Optional[int] = None) -> float:
         value: float = self.get_linear_lr()
 
         self.step_t += 1

pytorch_optimizer/lr_scheduler/rex.py

@@ -27,6 +27,7 @@ def __init__(
         lips: float = 10.0,
         rho: float = 0.5,
         variant: str = 'uni',
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_non_negative(lips, 'lips')

pytorch_optimizer/optimizer/a2grad.py

@@ -42,6 +42,7 @@ def __init__(
         adanorm: bool = False,
         adam_debias: bool = False,
         eps: float = 1e-16,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_betas(betas)

pytorch_optimizer/optimizer/adabelief.py

@@ -37,6 +37,7 @@ def __init__(
         ams_bound: bool = False,
         adam_debias: bool = False,
         eps: float = 1e-8,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_betas(betas)

pytorch_optimizer/optimizer/adabound.py

@@ -26,6 +26,7 @@ def __init__(
         weight_decouple: bool = False,
         fixed_decay: bool = False,
         eps: float = 1e-6,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_range(rho, 'rho', 0.0, 1.0)

pytorch_optimizer/optimizer/adadelta.py

@@ -49,6 +49,7 @@ def __init__(
         eps1: float = 1e-30,
         eps2: float = 1e-3,
         momentum_dtype: torch.dtype = torch.bfloat16,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_betas(betas)

pytorch_optimizer/optimizer/adafactor.py

@@ -40,6 +40,7 @@ def __init__(
         hessian_distribution: HUTCHINSON_G = 'rademacher',
         adam_debias: bool = False,
         eps: float = 1e-16,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_betas(betas)

pytorch_optimizer/optimizer/adahessian.py

@@ -35,6 +35,7 @@ def __init__(
         dampening: float = 1.0,
         use_gc: bool = False,
         eps: float = 1e-3,
+        **kwargs,
     ):
         self.validate_learning_rate(lr)
         self.validate_betas(betas)