+ &j^RIHt^RIHtHt^RIHtHtHtHtH t H t H t RR.t !RR]4t RR] R ] R ] R ] R ] R ] R 2 ,] nRR RlltR #))Tensor)Adamadam)_capturable_doc_differentiable_doc _foreach_doc _fused_doc _maximize_doc _params_docParamsTAdamWadamwc faa]tRt^toR RRRRRRRRRR/V3RlV3R lllltV3R ltR tVtV;t#) r FmaximizeforeachN capturabledifferentiablefusedc<V^8dQhRS[RS[S[,RS[S[S[,S[S[,3,RS[RS[RS[RS[RS[R ,R S[R S[R S[R ,R R / #)paramslrbetaseps weight_decayamsgradrrNrrrreturn)r floatrtuplebool)format __classdict__s"i/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/optim/adamw.py __annotate__AdamW.__annotate__s    FN UV^UV^34           d{   c><\S V`VVVVVVVVV V V RR7 R#)T)rrrrrdecoupled_weight_decayN)super__init__) selfrrrrrrrrrrr __class__s &&&&&&&$$$$$r#r*AdamW.__init__s;       !)#'  r&cV<\SV`V4VPFpRVR&K R#)Tr(N)r) __setstate__ param_groups)r+stategroupr,s&& r#r/AdamW.__setstate__6s+ U#&&E.2E* +'r&)gMbP?)g?g+?g:0yE>g{Gz?F) __name__ __module__ __qualname____firstlineno__r*r/__static_attributes____classdictcell__ __classcell__)r,r"s@@r#r r sL   $ !  % "  B33r&a Implements AdamW algorithm, where weight decay does not accumulate in the momentum nor variance. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \gamma \text{(lr)}, \: \beta_1, \beta_2 \text{(betas)}, \: \theta_0 \text{(params)}, \: f(\theta) \text{(objective)}, \: \epsilon \text{ (epsilon)} \\ &\hspace{13mm} \lambda \text{(weight decay)}, \: \textit{amsgrad}, \: \textit{maximize} \\ &\textbf{initialize} : m_0 \leftarrow 0 \text{ (first moment)}, v_0 \leftarrow 0 \text{ ( second moment)}, \: v_0^{max}\leftarrow 0 \\[-1.ex] &\rule{110mm}{0.4pt} \\ &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do} \\ &\hspace{5mm}\textbf{if} \: \textit{maximize}: \\ &\hspace{10mm}g_t \leftarrow -\nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm}\textbf{else} \\ &\hspace{10mm}g_t \leftarrow \nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm} \theta_t \leftarrow \theta_{t-1} - \gamma \lambda \theta_{t-1} \\ &\hspace{5mm}m_t \leftarrow \beta_1 m_{t-1} + (1 - \beta_1) g_t \\ &\hspace{5mm}v_t \leftarrow \beta_2 v_{t-1} + (1-\beta_2) g^2_t \\ &\hspace{5mm}\widehat{m_t} \leftarrow m_t/\big(1-\beta_1^t \big) \\ &\hspace{5mm}\textbf{if} \: amsgrad \\ &\hspace{10mm} v_t^{max} \leftarrow \mathrm{max}(v_{t-1}^{max},v_t) \\ &\hspace{10mm}\widehat{v_t} \leftarrow v_t^{max}/\big(1-\beta_2^t \big) \\ &\hspace{5mm}\textbf{else} \\ &\hspace{10mm}\widehat{v_t} \leftarrow v_t/\big(1-\beta_2^t \big) \\ &\hspace{5mm}\theta_t \leftarrow \theta_t - \gamma \widehat{m_t}/ \big(\sqrt{\widehat{v_t}} + \epsilon \big) \\ &\rule{110mm}{0.4pt} \\[-1.ex] &\bf{return} \: \theta_t \\[-1.ex] &\rule{110mm}{0.4pt} \\[-1.ex] \end{aligned} For further details regarding the algorithm we refer to `Decoupled Weight Decay Regularization`_. z Args: ac lr (float, Tensor, optional): learning rate (default: 1e-3). A tensor LR is not yet supported for all our implementations. Please use a float LR if you are not also specifying fused=True or capturable=True. betas (tuple[float | Tensor, float | Tensor], optional): coefficients used for computing running averages of gradient and its square. If a tensor is provided, must be 1-element. (default: (0.9, 0.999)) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8) weight_decay (float, optional): weight decay coefficient (default: 1e-2) amsgrad (bool, optional): whether to use the AMSGrad variant of this algorithm from the paper `On the Convergence of Adam and Beyond`_ (default: False) z a8 .. Note:: A prototype implementation of Adam and AdamW for MPS supports `torch.float32` and `torch.float16`. .. _Decoupled Weight Decay Regularization: https://arxiv.org/abs/1711.05101 .. _On the Convergence of Adam and Beyond: https://openreview.net/forum?id=ryQu7f-RZ Nc* V^8dQhR\\,R\\,R\\,R\\,R\\,R\\,R\R,R \R \R \R,R \R,R \R,R\R\R\\,R\\,R\\,R\R\R\RR/#)rrgradsexp_avgs exp_avg_sqsmax_exp_avg_sqs state_stepsrNrrr grad_scale found_inf has_complexrbeta1beta2rrrrr)listrr r)r!s"r#r$r$s33 L3 <36l3f 3 &\ 3 f 3D[333 $;3 3}33"#3$ 6>%3& 6>'3( )3*+3, -3./30 13r&c !`\VVVVVV3RVRVRVRV RV RV RV RV R VR VR VR VR VRVRR/R#)zhFunctional API that performs AdamW algorithm computation. See :class:`~torch.optim.AdamW` for details. rrrrrBrCrDrrErFrrrrr(TN)r)rr=r>r?r@rArrrrrBrCrDrrErFrrrrs&&&&&&&&&&&&&$$$$$$$r#rrs:   &  !" #$"%& '()* $+r&)NFFNNNF)torchrrr optimizerrrrr r r r __all__r __doc__rr4r&r#rMs G %3D%3R$J         'K@ L33r&