pytorch-optimizer 3.3.2__tar.gz → 3.3.4__tar.gz

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/PKG-INFO

@@ -1,10 +1,9 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: pytorch_optimizer
-Version: 3.3.2
+Version: 3.3.4
 Summary: optimizer & lr scheduler & objective function collections in PyTorch
-Home-page: https://github.com/kozistr/pytorch_optimizer
 License: Apache-2.0
-Keywords: pytorch,deep-learning,optimizer,lr scheduler,A2Grad,ASGD,AccSGD,AdaBelief,AdaBound,AdaDelta,AdaFactor,AdaMax,AdamG,AdaMod,AdaNorm,AdaPNM,AdaSmooth,AdEMAMix,ADOPT,AdaHessian,Adai,Adalite,AdaLomo,AdamMini,AdamP,AdamS,Adan,AggMo,Aida,AliG,Amos,Apollo,APOLLO,AvaGrad,bSAM,CAME,DAdaptAdaGrad,DAdaptAdam,DAdaptAdan,DAdaptSGD,DAdaptLion,DeMo,DiffGrad,FAdam,Fromage,FTRL,GaLore,Gravity,GrokFast,GSAM,Kate,Lamb,LaProp,LARS,Lion,LOMO,Lookahead,MADGRAD,MARS,MSVAG,Muno,Nero,NovoGrad,PAdam,PCGrad,PID,PNM,Prodigy,QHAdam,QHM,RAdam,Ranger,Ranger21,RotoGrad,SAM,ScheduleFreeSGD,ScheduleFreeAdamW,ScheduleFreeRAdam,SGDP,Shampoo,ScalableShampoo,SGDW,SignSGD,SM3,SOAP,SopihaH,SRMM,StableAdamW,SWATS,Tiger,TRAC,WSAM,Yogi,BCE,BCEFocal,Focal,FocalCosine,SoftF1,Dice,LDAM,Jaccard,Bi-Tempered,Tversky,FocalTversky,LovaszHinge,bitsandbytes,WSD,QGaLore
+Keywords: pytorch,deep-learning,optimizer,lr scheduler,A2Grad,ASGD,AccSGD,AdaBelief,AdaBound,AdaDelta,AdaFactor,AdaMax,AdamG,AdaMod,AdaNorm,AdaPNM,AdaSmooth,AdEMAMix,ADOPT,AdaHessian,Adai,Adalite,AdaLomo,AdamMini,AdamP,AdamS,Adan,AggMo,Aida,AliG,Amos,Apollo,APOLLO,AvaGrad,bSAM,CAME,DAdaptAdaGrad,DAdaptAdam,DAdaptAdan,DAdaptSGD,DAdaptLion,DeMo,DiffGrad,FAdam,Fromage,FTRL,GaLore,Grams,Gravity,GrokFast,GSAM,Kate,Lamb,LaProp,LARS,Lion,LOMO,Lookahead,MADGRAD,MARS,MSVAG,Muno,Nero,NovoGrad,OrthoGrad,PAdam,PCGrad,PID,PNM,Prodigy,QHAdam,QHM,RAdam,Ranger,Ranger21,RotoGrad,SAM,ScheduleFreeSGD,ScheduleFreeAdamW,ScheduleFreeRAdam,SGDP,Shampoo,ScalableShampoo,SGDW,SignSGD,SM3,SOAP,SopihaH,SPAM,SRMM,StableAdamW,SWATS,TAM,Tiger,TRAC,WSAM,Yogi,BCE,BCEFocal,Focal,FocalCosine,SoftF1,Dice,LDAM,Jaccard,Bi-Tempered,Tversky,FocalTversky,LovaszHinge,bitsandbytes,WSD,QGaLore
 Author: kozistr
 Author-email: kozistr@gmail.com
 Maintainer: kozistr
@@ -36,6 +35,7 @@ Requires-Dist: numpy (<=1.24.4) ; python_version < "3.9"
 Requires-Dist: numpy (>1.24.4) ; python_version >= "3.9"
 Requires-Dist: torch (>=1.10) ; python_version >= "3.8"
 Project-URL: Documentation, https://pytorch-optimizers.readthedocs.io/en/latest
+Project-URL: Homepage, https://github.com/kozistr/pytorch_optimizer
 Project-URL: Repository, https://github.com/kozistr/pytorch_optimizer
 Description-Content-Type: text/markdown
 
@@ -51,8 +51,8 @@ Description-Content-Type: text/markdown
 
 ## The reasons why you use `pytorch-optimizer`.
 
-* Wide range of supported optimizers. Currently, **86 optimizers (+ `bitsandbytes`, `qgalore`, `torchao`)**, **16 lr schedulers**, and **13 loss functions** are supported!
-* Including many variants such as `Cautious`, `AdamD`, `Gradient Centrailiaztion`
+* Wide range of supported optimizers. Currently, **92 optimizers (+ `bitsandbytes`, `qgalore`, `torchao`)**, **16 lr schedulers**, and **13 loss functions** are supported!
+* Including many variants such as `ADOPT`, `Cautious`, `AdamD`, `StableAdamW`, and `Gradient Centrailiaztion`
 * Easy to use, clean, and tested codes
 * Active maintenance
 * Somewhat a bit more optimized compared to the original implementation
@@ -236,6 +236,11 @@ get_supported_optimizers(['adam*', 'ranger*'])
 | APOLLO        | *SGD-like Memory, AdamW-level Performance*                                                        | [github](https://github.com/zhuhanqing/APOLLO)                                                                 | <https://arxiv.org/abs/2412.05270>                                                          | [cite](https://github.com/zhuhanqing/APOLLO?tab=readme-ov-file#-citation)                                                           |
 | MARS          | *Unleashing the Power of Variance Reduction for Training Large Models*                            | [github](https://github.com/AGI-Arena/MARS)                                                                    | <https://arxiv.org/abs/2411.10438>                                                          | [cite](https://github.com/AGI-Arena/MARS/tree/main?tab=readme-ov-file#citation)                                                     |
 | SGDSaI        | *No More Adam: Learning Rate Scaling at Initialization is All You Need*                           | [github](https://github.com/AnonymousAlethiometer/SGD_SaI)                                                     | <https://arxiv.org/abs/2411.10438>                                                          | [cite](https://github.com/AnonymousAlethiometer/SGD_SaI?tab=readme-ov-file#citation)                                                |
+| Grams         | *Gradient Descent with Adaptive Momentum Scaling*                                                 |                                                                                                                | <https://arxiv.org/abs/2412.17107>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv241217107C/exportcitation)                                                        |
+| OrthoGrad     | *Grokking at the Edge of Numerical Stability*                                                     | [github](https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability)                         | <https://arxiv.org/abs/2501.04697>                                                          | [cite](https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability?tab=readme-ov-file#citation)                    |
+| Adam-ATAN2    | *Scaling Exponents Across Parameterizations and Optimizers*                                       |                                                                                                                | <https://arxiv.org/abs/2407.05872>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv240705872E/exportcitation)                                                        |
+| SPAM          | *Spike-Aware Adam with Momentum Reset for Stable LLM Training*                                    | [github](https://github.com/TianjinYellow/SPAM-Optimizer)                                                      | <https://arxiv.org/abs/2501.06842>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2025arXiv250106842H/exportcitation)                                                        |
+| TAM           | *Torque-Aware Momentum*                                                                           |                                                                                                                | <https://arxiv.org/abs/2412.18790>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv241218790M/exportcitation)                                                        |
 
 ## Supported LR Scheduler
 
@@ -411,6 +416,10 @@ Correcting the norm of a gradient in each iteration based on the adaptive traini
 
 Updates only occur when the proposed update direction aligns with the current gradient.
 
+### Adam-ATAN2
+
+Adam-atan2 is a new numerically stable, scale-invariant version of Adam that eliminates the epsilon hyperparameter.
+
 ## Frequently asked questions
 
 [here](docs/qa.md)

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/README.md

@@ -10,8 +10,8 @@
 
 ## The reasons why you use `pytorch-optimizer`.
 
-* Wide range of supported optimizers. Currently, **86 optimizers (+ `bitsandbytes`, `qgalore`, `torchao`)**, **16 lr schedulers**, and **13 loss functions** are supported!
-* Including many variants such as `Cautious`, `AdamD`, `Gradient Centrailiaztion`
+* Wide range of supported optimizers. Currently, **92 optimizers (+ `bitsandbytes`, `qgalore`, `torchao`)**, **16 lr schedulers**, and **13 loss functions** are supported!
+* Including many variants such as `ADOPT`, `Cautious`, `AdamD`, `StableAdamW`, and `Gradient Centrailiaztion`
 * Easy to use, clean, and tested codes
 * Active maintenance
 * Somewhat a bit more optimized compared to the original implementation
@@ -195,6 +195,11 @@ get_supported_optimizers(['adam*', 'ranger*'])
 | APOLLO        | *SGD-like Memory, AdamW-level Performance*                                                        | [github](https://github.com/zhuhanqing/APOLLO)                                                                 | <https://arxiv.org/abs/2412.05270>                                                          | [cite](https://github.com/zhuhanqing/APOLLO?tab=readme-ov-file#-citation)                                                           |
 | MARS          | *Unleashing the Power of Variance Reduction for Training Large Models*                            | [github](https://github.com/AGI-Arena/MARS)                                                                    | <https://arxiv.org/abs/2411.10438>                                                          | [cite](https://github.com/AGI-Arena/MARS/tree/main?tab=readme-ov-file#citation)                                                     |
 | SGDSaI        | *No More Adam: Learning Rate Scaling at Initialization is All You Need*                           | [github](https://github.com/AnonymousAlethiometer/SGD_SaI)                                                     | <https://arxiv.org/abs/2411.10438>                                                          | [cite](https://github.com/AnonymousAlethiometer/SGD_SaI?tab=readme-ov-file#citation)                                                |
+| Grams         | *Gradient Descent with Adaptive Momentum Scaling*                                                 |                                                                                                                | <https://arxiv.org/abs/2412.17107>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv241217107C/exportcitation)                                                        |
+| OrthoGrad     | *Grokking at the Edge of Numerical Stability*                                                     | [github](https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability)                         | <https://arxiv.org/abs/2501.04697>                                                          | [cite](https://github.com/LucasPrietoAl/grokking-at-the-edge-of-numerical-stability?tab=readme-ov-file#citation)                    |
+| Adam-ATAN2    | *Scaling Exponents Across Parameterizations and Optimizers*                                       |                                                                                                                | <https://arxiv.org/abs/2407.05872>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv240705872E/exportcitation)                                                        |
+| SPAM          | *Spike-Aware Adam with Momentum Reset for Stable LLM Training*                                    | [github](https://github.com/TianjinYellow/SPAM-Optimizer)                                                      | <https://arxiv.org/abs/2501.06842>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2025arXiv250106842H/exportcitation)                                                        |
+| TAM           | *Torque-Aware Momentum*                                                                           |                                                                                                                | <https://arxiv.org/abs/2412.18790>                                                          | [cite](https://ui.adsabs.harvard.edu/abs/2024arXiv241218790M/exportcitation)                                                        |
 
 ## Supported LR Scheduler
 
@@ -370,6 +375,10 @@ Correcting the norm of a gradient in each iteration based on the adaptive traini
 
 Updates only occur when the proposed update direction aligns with the current gradient.
 
+### Adam-ATAN2
+
+Adam-atan2 is a new numerically stable, scale-invariant version of Adam that eliminates the epsilon hyperparameter.
+
 ## Frequently asked questions
 
 [here](docs/qa.md)

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pytorch_optimizer"
-version = "3.3.2"
+version = "3.3.4"
 description = "optimizer & lr scheduler & objective function collections in PyTorch"
 license = "Apache-2.0"
 authors = ["kozistr <kozistr@gmail.com>"]
@@ -14,13 +14,13 @@ keywords = [
     "AdaDelta", "AdaFactor", "AdaMax", "AdamG", "AdaMod", "AdaNorm", "AdaPNM", "AdaSmooth", "AdEMAMix", "ADOPT",
     "AdaHessian", "Adai", "Adalite", "AdaLomo", "AdamMini", "AdamP", "AdamS", "Adan", "AggMo", "Aida", "AliG", "Amos",
     "Apollo", "APOLLO", "AvaGrad", "bSAM", "CAME", "DAdaptAdaGrad", "DAdaptAdam", "DAdaptAdan", "DAdaptSGD",
-    "DAdaptLion", "DeMo", "DiffGrad", "FAdam", "Fromage", "FTRL", "GaLore", "Gravity", "GrokFast", "GSAM", "Kate",
-    "Lamb", "LaProp", "LARS", "Lion", "LOMO", "Lookahead", "MADGRAD", "MARS", "MSVAG", "Muno", "Nero", "NovoGrad",
-    "PAdam", "PCGrad", "PID", "PNM", "Prodigy", "QHAdam", "QHM", "RAdam", "Ranger", "Ranger21", "RotoGrad", "SAM",
-    "ScheduleFreeSGD", "ScheduleFreeAdamW", "ScheduleFreeRAdam", "SGDP", "Shampoo", "ScalableShampoo", "SGDW",
-    "SignSGD", "SM3", "SOAP", "SopihaH", "SRMM", "StableAdamW", "SWATS", "Tiger", "TRAC", "WSAM", "Yogi", "BCE",
-    "BCEFocal", "Focal", "FocalCosine", "SoftF1", "Dice", "LDAM", "Jaccard", "Bi-Tempered", "Tversky", "FocalTversky",
-    "LovaszHinge", "bitsandbytes", "WSD", "QGaLore",
+    "DAdaptLion", "DeMo", "DiffGrad", "FAdam", "Fromage", "FTRL", "GaLore", "Grams", "Gravity", "GrokFast", "GSAM",
+    "Kate", "Lamb", "LaProp", "LARS", "Lion", "LOMO", "Lookahead", "MADGRAD", "MARS", "MSVAG", "Muno", "Nero",
+    "NovoGrad", "OrthoGrad", "PAdam", "PCGrad", "PID", "PNM", "Prodigy", "QHAdam", "QHM", "RAdam", "Ranger",
+    "Ranger21", "RotoGrad", "SAM", "ScheduleFreeSGD", "ScheduleFreeAdamW", "ScheduleFreeRAdam", "SGDP", "Shampoo",
+    "ScalableShampoo", "SGDW", "SignSGD", "SM3", "SOAP", "SopihaH", "SPAM", "SRMM", "StableAdamW", "SWATS", "TAM",
+    "Tiger", "TRAC", "WSAM", "Yogi", "BCE", "BCEFocal", "Focal", "FocalCosine", "SoftF1", "Dice", "LDAM", "Jaccard",
+    "Bi-Tempered", "Tversky", "FocalTversky", "LovaszHinge", "bitsandbytes", "WSD", "QGaLore",
 ]
 classifiers = [
     "License :: OSI Approved :: Apache Software License",
@@ -97,8 +97,8 @@ select = [
     "TID", "ARG", "ERA", "RUF", "YTT", "PL", "Q"
 ]
 ignore = [
-    "B905", "D100", "D102", "D104", "D105", "D107", "D203", "D213", "D413", "PIE790", "PLR0912", "PLR0913", "PLR0915",
-    "PLR2004", "RUF013", "Q003", "ARG002",
+    "A005", "B905", "D100", "D102", "D104", "D105", "D107", "D203", "D213", "D413", "PIE790", "PLR0912", "PLR0913",
+    "PLR0915", "PLR2004", "RUF013", "Q003", "ARG002",
 ]
 fixable = ["ALL"]
 unfixable = ["F401"]

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/__init__.py

@@ -61,8 +61,10 @@ from pytorch_optimizer.optimizer import (
     SGDW,
     SM3,
     SOAP,
+    SPAM,
     SRMM,
     SWATS,
+    TAM,
     TRAC,
     WSAM,
     A2Grad,
@@ -87,6 +89,7 @@ from pytorch_optimizer.optimizer import (
     AdaPNM,
     AdaShift,
     AdaSmooth,
+    AdaTAM,
     AdEMAMix,
     AggMo,
     Aida,
@@ -105,6 +108,7 @@ from pytorch_optimizer.optimizer import (
     FAdam,
     Fromage,
     GaLore,
+    Grams,
     Gravity,
     GrokFastAdamW,
     Kate,
@@ -115,6 +119,7 @@ from pytorch_optimizer.optimizer import (
     Muon,
     Nero,
     NovoGrad,
+    OrthoGrad,
     PAdam,
     PCGrad,
     Prodigy,
@@ -122,6 +127,7 @@ from pytorch_optimizer.optimizer import (
     RAdam,
     Ranger,
     Ranger21,
+    Ranger25,
     RotoGrad,
     SafeFP16Optimizer,
     ScalableShampoo,

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/base/optimizer.py

@@ -266,6 +266,16 @@ class BaseOptimizer(ABC, Optimizer):
         mask.mul_(mask.numel() / (mask.sum() + 1))
         update.mul_(mask)
 
+    @staticmethod
+    def get_stable_adamw_rms(grad: torch.Tensor, exp_avg_sq: torch.Tensor, eps: float = 1e-16) -> float:
+        r"""Get StableAdamW RMS.
+
+        :param grad: torch.Tensor. gradient.
+        :param exp_avg_sq: torch.Tensor. exp_avg_sq.
+        :param eps: float. epsilon.
+        """
+        return grad.pow(2).div_(exp_avg_sq.clip(min=eps)).mean().sqrt_().clip_(min=1.0).item()
+
     @staticmethod
     def validate_range(x: float, name: str, low: float, high: float, range_type: str = '[)') -> None:
         if range_type == '[)' and not low <= x < high:

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/base/scheduler.py

@@ -1,8 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import List
 
+from torch.optim import Optimizer
+
 from pytorch_optimizer.base.exception import NegativeLRError, NegativeStepError
-from pytorch_optimizer.base.types import OPTIMIZER
 
 
 class BaseLinearWarmupScheduler(ABC):
@@ -10,7 +11,7 @@ class BaseLinearWarmupScheduler(ABC):
 
         The LR Scheduler class based on this class has linear warmup strategy.
 
-    :param optimizer: Optimizer. OPTIMIZER. It will set learning rate to all trainable parameters in optimizer.
+    :param optimizer: Optimizer. It will set learning rate to all trainable parameters in optimizer.
     :param t_max: int. total steps to train.
     :param max_lr: float. maximum lr.
     :param min_lr: float. minimum lr.
@@ -20,7 +21,7 @@ class BaseLinearWarmupScheduler(ABC):
 
     def __init__(
         self,
-        optimizer: OPTIMIZER,
+        optimizer: Optimizer,
         t_max: int,
         max_lr: float,
         min_lr: float = 0.0,

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/base/types.py

@@ -11,6 +11,7 @@ DEFAULTS = Dict
 PARAMETERS = Optional[Union[Iterable[Dict], Iterable[torch.Tensor]]]
 STATE = Dict
 OPTIMIZER = Type[Optimizer]
+OPTIMIZER_INSTANCE_OR_CLASS = Union[OPTIMIZER, Optimizer]
 SCHEDULER = Type[LRScheduler]
 
 HUTCHINSON_G = Literal['gaussian', 'rademacher']

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/lr_scheduler/cosine_anealing.py

@@ -1,10 +1,9 @@
 import math
 from typing import List, Optional
 
+from torch.optim import Optimizer
 from torch.optim.lr_scheduler import LRScheduler
 
-from pytorch_optimizer.base.types import OPTIMIZER
-
 
 class CosineAnnealingWarmupRestarts(LRScheduler):
     r"""CosineAnnealingWarmupRestarts.
@@ -21,7 +20,7 @@ class CosineAnnealingWarmupRestarts(LRScheduler):
 
     def __init__(
         self,
-        optimizer: OPTIMIZER,
+        optimizer: Optimizer,
         first_cycle_steps: int,
         cycle_mult: float = 1.0,
         max_lr: float = 1e-4,
@@ -53,7 +52,7 @@ class CosineAnnealingWarmupRestarts(LRScheduler):
 
         self.init_lr()
 
-    def init_lr(self):
+    def init_lr(self) -> None:
         self.base_lrs = []
         for param_group in self.optimizer.param_groups:
             param_group['lr'] = self.min_lr

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/lr_scheduler/rex.py

@@ -1,9 +1,8 @@
 from typing import List, Optional
 
+from torch.optim import Optimizer
 from torch.optim.lr_scheduler import LRScheduler
 
-from pytorch_optimizer.base.types import OPTIMIZER
-
 
 class REXScheduler(LRScheduler):
     r"""Revisiting Budgeted Training with an Improved Schedule.
@@ -16,7 +15,7 @@ class REXScheduler(LRScheduler):
 
     def __init__(
         self,
-        optimizer: OPTIMIZER,
+        optimizer: Optimizer,
         total_steps: int,
         max_lr: float = 1.0,
         min_lr: float = 0.0,
@@ -35,7 +34,7 @@ class REXScheduler(LRScheduler):
 
         self.init_lr()
 
-    def init_lr(self):
+    def init_lr(self) -> None:
         self.base_lrs = []
         for param_group in self.optimizer.param_groups:
             param_group['lr'] = self.min_lr

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/__init__.py

@@ -1,10 +1,10 @@
 import fnmatch
 from importlib.util import find_spec
-from typing import Dict, List, Optional, Sequence, Set, Union
+from typing import Dict, List, Optional, Sequence, Set, Type, Union
 
 import torch
 from torch import nn
-from torch.optim import AdamW
+from torch.optim import AdamW, Optimizer
 
 from pytorch_optimizer.base.types import OPTIMIZER, PARAMETERS
 from pytorch_optimizer.optimizer.a2grad import A2Grad
@@ -40,12 +40,14 @@ from pytorch_optimizer.optimizer.came import CAME
 from pytorch_optimizer.optimizer.dadapt import DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptLion, DAdaptSGD
 from pytorch_optimizer.optimizer.demo import DeMo
 from pytorch_optimizer.optimizer.diffgrad import DiffGrad
+from pytorch_optimizer.optimizer.experimental.ranger25 import Ranger25
 from pytorch_optimizer.optimizer.fadam import FAdam
 from pytorch_optimizer.optimizer.fp16 import DynamicLossScaler, SafeFP16Optimizer
 from pytorch_optimizer.optimizer.fromage import Fromage
 from pytorch_optimizer.optimizer.ftrl import FTRL
 from pytorch_optimizer.optimizer.galore import GaLore
 from pytorch_optimizer.optimizer.gc import centralize_gradient
+from pytorch_optimizer.optimizer.grams import Grams
 from pytorch_optimizer.optimizer.gravity import Gravity
 from pytorch_optimizer.optimizer.grokfast import GrokFastAdamW
 from pytorch_optimizer.optimizer.kate import Kate
@@ -61,6 +63,7 @@ from pytorch_optimizer.optimizer.msvag import MSVAG
 from pytorch_optimizer.optimizer.muon import Muon
 from pytorch_optimizer.optimizer.nero import Nero
 from pytorch_optimizer.optimizer.novograd import NovoGrad
+from pytorch_optimizer.optimizer.orthograd import OrthoGrad
 from pytorch_optimizer.optimizer.padam import PAdam
 from pytorch_optimizer.optimizer.pcgrad import PCGrad
 from pytorch_optimizer.optimizer.pid import PID
@@ -80,8 +83,10 @@ from pytorch_optimizer.optimizer.shampoo import ScalableShampoo, Shampoo
 from pytorch_optimizer.optimizer.sm3 import SM3
 from pytorch_optimizer.optimizer.soap import SOAP
 from pytorch_optimizer.optimizer.sophia import SophiaH
+from pytorch_optimizer.optimizer.spam import SPAM
 from pytorch_optimizer.optimizer.srmm import SRMM
 from pytorch_optimizer.optimizer.swats import SWATS
+from pytorch_optimizer.optimizer.tam import TAM, AdaTAM
 from pytorch_optimizer.optimizer.tiger import Tiger
 from pytorch_optimizer.optimizer.trac import TRAC
 from pytorch_optimizer.optimizer.yogi import Yogi
@@ -248,6 +253,8 @@ OPTIMIZER_LIST: List[OPTIMIZER] = [
     SRMM,
     AvaGrad,
     AdaShift,
+    TAM,
+    AdaTAM,
     AdaDelta,
     Amos,
     AdaHessian,
@@ -282,6 +289,9 @@ OPTIMIZER_LIST: List[OPTIMIZER] = [
     LaProp,
     MARS,
     SGDSaI,
+    Grams,
+    SPAM,
+    Ranger25,
 ]
 OPTIMIZERS: Dict[str, OPTIMIZER] = {str(optimizer.__name__).lower(): optimizer for optimizer in OPTIMIZER_LIST}
 
@@ -293,8 +303,9 @@ def create_optimizer(
     weight_decay: float = 0.0,
     wd_ban_list: List[str] = ('bias', 'LayerNorm.bias', 'LayerNorm.weight'),
     use_lookahead: bool = False,
+    use_orthograd: bool = False,
     **kwargs,
-):
+) -> Optimizer:
     r"""Build optimizer.
 
     :param model: nn.Module. model.
@@ -302,7 +313,8 @@ def create_optimizer(
     :param lr: float. learning rate.
     :param weight_decay: float. weight decay.
     :param wd_ban_list: List[str]. weight decay ban list by layer.
-    :param use_lookahead: bool. use lookahead.
+    :param use_lookahead: bool. use Lookahead.
+    :param use_orthograd: bool. use OrthoGrad.
     """
     optimizer_name = optimizer_name.lower()
 
@@ -310,14 +322,17 @@ def create_optimizer(
         get_optimizer_parameters(model, weight_decay, wd_ban_list) if weight_decay > 0.0 else model.parameters()
     )
 
-    optimizer = load_optimizer(optimizer_name)
+    optimizer_class: OPTIMIZER = load_optimizer(optimizer_name)
 
     if optimizer_name == 'alig':
-        optimizer = optimizer(parameters, max_lr=lr, **kwargs)
+        optimizer = optimizer_class(parameters, max_lr=lr, **kwargs)
     elif optimizer_name in {'lomo', 'adalomo', 'adammini'}:
-        optimizer = optimizer(model, lr=lr, **kwargs)
+        optimizer = optimizer_class(model, lr=lr, **kwargs)
     else:
-        optimizer = optimizer(parameters, lr=lr, **kwargs)
+        optimizer = optimizer_class(parameters, lr=lr, **kwargs)
+
+    if use_orthograd:
+        optimizer = OrthoGrad(optimizer, **kwargs)
 
     if use_lookahead:
         optimizer = Lookahead(

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/adafactor.py

@@ -13,8 +13,8 @@ class AdaFactor(BaseOptimizer):
 
     :param params: PARAMETERS. iterable of parameters to optimize or dicts defining parameter groups.
     :param lr: float. learning rate.
-    :param betas: BETAS. coefficients used for computing running averages of gradient and the squared
-        hessian trace. if beta1 is None, first momentum will be skipped.
+    :param betas: BETAS. coefficients used for computing running averages of gradient and the squared hessian trace.
+        if beta1 is None, first momentum will be skipped.
     :param decay_rate: float. coefficient used to compute running averages of square gradient.
     :param weight_decay: float. weight decay (L2 penalty).
     :param weight_decouple: bool. the optimizer uses decoupled weight decay as in AdamW.

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/adamp.py

@@ -141,6 +141,10 @@ class AdamP(BaseOptimizer):
                 inv_de_nom = exp_avg_sq.rsqrt().add_(group['eps']).mul_(bias_correction2_sq)
 
                 perturb = exp_avg.clone()
+
+                if self.cautious:
+                    self.apply_cautious(perturb, grad)
+
                 if group['nesterov']:
                     perturb.mul_(beta1).addcmul_(grad, inv_de_nom, value=1.0 - beta1)
                 else:
@@ -173,9 +177,6 @@ class AdamP(BaseOptimizer):
                     bias_correction1=bias_correction1,
                 )
 
-                if self.cautious:
-                    self.apply_cautious(perturb, grad)
-
                 p.add_(perturb, alpha=-step_size)
 
         return loss

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/adamw.py

@@ -107,13 +107,11 @@ class StableAdamW(BaseOptimizer):
                 exp_avg.lerp_(grad, weight=beta1_comp)
                 exp_avg_sq.mul_(beta2_hat).addcmul_(grad, grad, value=1.0 - beta2_hat)
 
-                rms = grad.pow(2).div_(exp_avg_sq.clip(min=eps_p2)).mean().sqrt_()
-
-                lr = group['lr'] / rms.clip(min=1.0)
+                lr: float = group['lr'] / self.get_stable_adamw_rms(grad, exp_avg_sq, eps=eps_p2)
 
                 self.apply_weight_decay(
                     p,
-                    p.grad,
+                    grad,
                     lr=lr,
                     weight_decay=group['weight_decay'],
                     weight_decouple=group['weight_decouple'],

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/ademamix.py

@@ -19,7 +19,8 @@ class AdEMAMix(BaseOptimizer):
     :param fixed_decay: bool. fix weight decay.
     :param alpha: float. usually between 4 and 10 would work well.
     :param t_alpha_beta3: Optional[float]. total number of iterations is preferred when needed.
-    :param cautious: bool. whether to use cautious feature.
+    :param cautious: bool. whether to use the Cautious variant.
+    :param stable_adamw: bool. whether to use stable AdamW variant.
     :param eps: float. term added to the denominator to improve numerical stability.
     """
 
@@ -34,6 +35,7 @@ class AdEMAMix(BaseOptimizer):
         alpha: float = 5.0,
         t_alpha_beta3: Optional[float] = None,
         cautious: bool = False,
+        stable_adamw: bool = False,
         eps: float = 1e-8,
         **kwargs,
     ):
@@ -45,6 +47,7 @@ class AdEMAMix(BaseOptimizer):
         self.validate_non_negative(eps, 'eps')
 
         self.cautious = cautious
+        self.stable_adamw = stable_adamw
 
         defaults: DEFAULTS = {
             'lr': lr,
@@ -150,6 +153,9 @@ class AdEMAMix(BaseOptimizer):
                 if self.cautious:
                     self.apply_cautious(update, grad)
 
+                if self.stable_adamw:
+                    step_size /= self.get_stable_adamw_rms(grad, exp_avg_sq)
+
                 update.add_(exp_avg_slow, alpha=alpha_t).div_(de_nom)
 
                 p.add_(update, alpha=-step_size)

{pytorch_optimizer-3.3.2 → pytorch_optimizer-3.3.4}/pytorch_optimizer/optimizer/adopt.py

@@ -18,6 +18,7 @@ class ADOPT(BaseOptimizer):
     :param weight_decouple: bool. the optimizer uses decoupled weight decay as in AdamW.
     :param fixed_decay: bool. fix weight decay.
     :param cautious: bool. whether to use the Cautious variant.
+    :param stable_adamw: bool. whether to use stable AdamW variant.
     :param eps: float. term added to the denominator to improve numerical stability.
     """
 
@@ -31,6 +32,7 @@ class ADOPT(BaseOptimizer):
         weight_decouple: bool = False,
         fixed_decay: bool = False,
         cautious: bool = False,
+        stable_adamw: bool = False,
         eps: float = 1e-6,
         **kwargs,
     ):
@@ -41,6 +43,7 @@ class ADOPT(BaseOptimizer):
 
         self.clip_lambda = clip_lambda
         self.cautious = cautious
+        self.stable_adamw = stable_adamw
 
         defaults: DEFAULTS = {
             'lr': lr,
@@ -80,6 +83,7 @@ class ADOPT(BaseOptimizer):
                 group['step'] = 1
 
             beta1, beta2 = group['betas']
+            lr: float = group['lr']
 
             for p in group['params']:
                 if p.grad is None:
@@ -98,7 +102,7 @@ class ADOPT(BaseOptimizer):
                 self.apply_weight_decay(
                     p=p,
                     grad=grad,
-                    lr=group['lr'],
+                    lr=lr,
                     weight_decay=group['weight_decay'],
                     weight_decouple=group['weight_decouple'],
                     fixed_decay=group['fixed_decay'],
@@ -127,6 +131,9 @@ class ADOPT(BaseOptimizer):
                 else:
                     update = exp_avg
 
-                p.add_(update, alpha=-group['lr'])
+                if self.stable_adamw:
+                    lr /= self.get_stable_adamw_rms(grad, exp_avg_sq)
+
+                p.add_(update, alpha=-lr)
 
         return loss