o hzp'@sddlmZmZmZmZddlZddlmZddlmZm Z m Z m Z m Z m Z mZmZmZmZmZmZddlmZddgZGd ddeZd d ed ed ed ed ed e_      d*deedeedeedeedeedeedeedededeedeedeededededeeefded ed!ef&d"dZdeedeedeedeedeedeedeedeededededeeefded ed!ededef"d#d$Zdeedeedeedeedeedeedeedeededededeeefded ed!ededef"d%d&Zdeedeedeedeedeedeedeedeededededeeefded ed!ededed'df$d(d)ZdS)+)ListOptionalUnionTupleN)Tensor) Optimizerparams_t_use_grad_for_differentiable _get_value_stack_if_compiling_dispatch_sqrt_default_to_fused_or_foreach_capturable_doc_differentiable_doc _foreach_doc _fused_doc _maximize_doc)$_get_fused_kernels_supported_devicesAdamadamcseZdZ     dddddddded eeefd eeefd ed ed ede edededede effddZ fddZ ddZ e dddZZS)rMbP?g?g+?:0yE>rFN)foreachmaximize capturabledifferentiablefusedparamslrbetaseps weight_decayamsgradrrrrrc s6d|ks td|t|tr|r| stdd|ks#td|d|dkr/dks9ntd|dd|dkrEdksOntd |dd|ksZtd |t|||||||| | | d } t|| | r| rwtd d |_tt fdd|j Dstdd|rtddSdS)NzInvalid learning rate: Elr as a Tensor is not supported for capturable=False and foreach=TruezInvalid epsilon value: rg?z#Invalid beta parameter at index 0: rz#Invalid beta parameter at index 1: zInvalid weight_decay value: ) r r!r"r#r$rrrrrz)`fused` does not support `differentiable`Tc3s4|]}|dD]}|jjvot|VqqdS)rN)devicetypetorchis_floating_point).0pgpfused_supported_devicesF/var/www/html/ai/venv/lib/python3.10/site-packages/torch/optim/adam.py 8s  z Adam.__init__..zX`fused=True` requires all the params to be floating point Tensors of supported devices: .z0`fused` and `foreach` cannot be `True` together.) ValueError isinstancerdictsuper__init__ RuntimeError_step_supports_amp_scalingrall param_groups) selfrr r!r"r#r$rrrrrdefaults __class__r.r1r8sB   z Adam.__init__cst||jD]&}|dd|dd|dd|dd|dd|ddq t|j}t|dkoEt |dd }|sX|D]}t t |d |d <qJdSdS) Nr$Frrrrrrstep) r7 __setstate__r< setdefaultliststatevalueslenr) is_tensortensorfloat)r=rEgroup state_valuesstep_is_tensorsr?r0r1rBAs       zAdam.__setstate__c CsN|dD]}|jdur|||jjrtd||j|j|} t| dkrd|ds1|dr;tjdtj|j dnt d| d <tj |tj d | d <tj |tj d | d <|d rdtj |tj d | d<|| d || d |d r}|| d|dr| d j rtd|drt|dr|dstd|| d qdS)NrzJAdam does not support sparse gradients, please consider SparseAdam insteadrrrr0)dtyper'r%rA) memory_formatexp_avg exp_avg_sqr$max_exp_avg_sqrzB`requires_grad` is not supported for `step` in differentiable moderr r&)gradappend is_sparser9rErGr)zerosrJr'rI zeros_likepreserve_format requires_gradrH) r=rKparams_with_gradgradsexp_avgs exp_avg_sqsmax_exp_avg_sqs state_stepsr-rEr0r0r1 _init_groupPs:     zAdam._init_groupc Cs|d}|dur!t |}Wdn1swY|jD]R}g}g}g}g}g}g} |d\} } |||||||| t|||||| f|d| | |d|d|d|d|d|d |d |d t|d dt|d dd q$|S)zPerforms a single optimization step. Args: closure (Callable, optional): A closure that reevaluates the model and returns the loss. Nr!r$r r#r"rrrrr grad_scale found_inf) r$beta1beta2r r#r"rrrrrrbrc) _cuda_graph_capture_health_checkr) enable_gradr<rargetattr) r=closurelossrKr[r\r]r^r_r`rdrer0r0r1rAs\       z Adam.step)rrrrFN)__name__ __module__ __qualname__r rrJrrboolrr8rBrar rA __classcell__r0r0r?r1rsN       22a Implements Adam algorithm. .. 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)} \\ &\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)},\: \widehat{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}\textbf{if} \: \lambda \neq 0 \\ &\hspace{10mm} g_t \leftarrow g_t + \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}\widehat{v_t} \leftarrow v_t/\big(1-\beta_2^t \big) \\ &\hspace{5mm}\textbf{if} \: amsgrad \\ &\hspace{10mm}\widehat{v_t}^{max} \leftarrow \mathrm{max}(\widehat{v_t}^{max}, \widehat{v_t}) \\ &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t}/ \big(\sqrt{\widehat{v_t}^{max}} + \epsilon \big) \\ &\hspace{5mm}\textbf{else} \\ &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \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 `Adam: A Method for Stochastic Optimization`_. a Args: params (iterable): iterable of parameters to optimize or dicts defining parameter groups 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, float], optional): coefficients used for computing running averages of gradient and its square (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 (L2 penalty) (default: 0) 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 z .. _Adam\: A Method for Stochastic Optimization: https://arxiv.org/abs/1412.6980 .. _On the Convergence of Adam and Beyond: https://openreview.net/forum?id=ryQu7f-RZ Frr\r]r^r_r`rrrrrbrcr$rdrer r#r"rc Cs| dur|durt||dd\}}|rt|tr|sd}| dur"d} |dur(d}tjs:tdd|Ds:td|rEtj rEtd| rPtj rPtd| rZtj sZt }n |rdtj sdt }nt }|||||||| | |||||||| | d dS) zmFunctional API that performs Adam algorithm computation. See :class:`~torch.optim.Adam` for details. NF) use_fusedcss|] }t|tjVqdSrk)r5r)r)r+tr0r0r1r2(szadam..zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsz6torch.jit.script not supported with foreach optimizersz4torch.jit.script not supported with fused optimizers) r$rdrer r#r"rrrrbrc) rr5rr)_utils is_compilingr;r9jit is_scripting _fused_adam_multi_tensor_adam_single_tensor_adam)rr\r]r^r_r`rrrrrbrcr$rdrer r#r"r_funcr0r0r1rsJ c Cs|dur|dus Jtjrt| tsJt|D]1\}}|s%||n|| }||}||}||}tjsM|rM|jrC|jsM|j rI|j sMJd|d7}| dkr\|j || d}t |rt |}t |}t |}|r{t ||||<t |}| |d| || j||d| d|s|r|}d| |}d| |}| |}|}|}|r|r||}n||}||t||||||| |}n |||| |}|||nEt|}d| |}d| |}| |}t|}|r&tj|||||d|||| }n ||| }|j||| d|rLt ||rLt||||<qdS)NzGIf capturable=True, params and state_steps must be CUDA or XLA tensors.rralpha)value)out)r)rurvr5rJ enumeratersrtis_cudais_xlaadd is_complex view_as_reallerp_mul_addcmul_conjnegsqrtclonecopy_maximumadd_addcdiv_r r view_as_complex)rr\r]r^r_r`rbrcr$rdrer r#r"rrriparamrTrQrRstep_trAbias_correction1bias_correction2 step_size step_size_negbias_correction2_sqrtrSdenomr0r0r1ryJsx           ryc st|dkrdSttr|stdtjs*|r*tddt||Ds*Jd|dur2|dus4J|r:Jdt ||||||g}| D]\\}}}}}}}|r[t |}dd|D}d d|D}d d|D}d d|D}d d|D}t |d | dkr|rtj ||| dntj||| d}t||d t|t|||d ~|rt|}t|}t|d t|d t|t|t|t||}|}|rt||t|}nt|}t||t || t||t|||qIfdd|D}fdd|D}tfdd|D}dd|D}|rIt||t|}nt|}t||t || t||||qIdS)Nrr&css |] \}}|jo |jVqdSrk)r)r+r-rAr0r0r1r2sz%_multi_tensor_adam..z@If capturable=True, params and state_steps must be CUDA tensors.z#_foreach ops don't support autogradcS$g|]}t|rt|n|qSr0r)rrr+xr0r0r1 $z&_multi_tensor_adam..cSrr0rrr0r0r1rrcSrr0rrr0r0r1rrcSrr0rrr0r0r1rrcSrr0rrr0r0r1rrrr|cg|] }dt|qSrr r+rA)rdr0r1r'crrrr)rer0r1r(rcsg|]}|dqS)r0r+bc)r r0r1r*scSsg|]}t|qSr0)r rr0r0r1r,s)rGr5rr9r)rsrtr;zipr"_group_tensors_by_device_and_dtyperF _foreach_neg _foreach_add_ _foreach_add_foreach_lerp_ _foreach_mul__foreach_addcmul_ _foreach_pow _foreach_sub_ _foreach_neg_ _foreach_div__foreach_reciprocal__foreach_sqrt__foreach_maximum_ _foreach_sqrt_foreach_addcdiv_r )rr\r]r^r_r`rbrcr$rdrer r#r"rrrgrouped_tensors device_params device_gradsdevice_exp_avgsdevice_exp_avg_sqsdevice_max_exp_avg_sqsdevice_state_stepsrzrrrrexp_avg_sq_sqrtr0)rdrer r1rxs                         rxreturnc Cs~|sdS|r td|dur|j|ind}|dur|j|ind}t| tr1t| jdkr1| j| ind}t||||||g}|D]z\\}}\\}}}}}}}d\}}|duri||vre|j|dd||<||}|dur~||vrz|j|dd||<||}|dur||vr| j|dd||<||} t |dt j |||||||| | | | | |||d|durt ||gt |qBdS) Nz9Adam with fused=True does not support differentiable=Truecpu)NNT) non_blocking)r'rr) r$r rdrer#r"rrbrc)r9r'r5rstrrritemstor)r _fused_adam_rrG)rr\r]r^r_r`rbrcr$rdrer r#r"rrrgrad_scale_dictfound_inf_dictlr_dictrr'rzrrrrrrdevice_grad_scaledevice_found_infr0r0r1rw<sf& rw)NFFNNN)typingrrrrr)r optimizerrr r r r r rrrrrrtorch.utils._foreach_utilsr__all__r__doc__rorJrryrxrwr0r0r0r1sP 8 /&J        L      o