o Zh+@sjUddlmZddlZddlmmZddlmZddlm Z gZ e e e d<ejjGdddZdS))OptionalN)Tensor)2_scripted_functional_optimizer_deprecation_warning__all__c@sheZdZ       ddeededeeefd ed ed ed ed efddZdee efddZ dS)_FunctionalAdamaxMbP?g?g+?:0yE>Fparamslrbetaseps weight_decayforeachmaximize_allow_empty_param_listc Cstddd|kstd|d|kstd|d|dkr'dks1ntd|dd|d kr=dksGntd |d d|ksRtd ||||d|d |d |_||_||_tjttj tt tj ffi|_ t |dkr|std d|i|_ dS)N) stacklevelr zInvalid learning rate: zInvalid epsilon value: rg?z#Invalid beta parameter at index 0: z#Invalid beta parameter at index 1: zInvalid weight_decay value: )r rbeta1beta2rz%optimizer got an empty parameter listr )r ValueErrordefaultsrrtorchjitZannotatedictrstrstatelen param_group) selfr r r rrrrrr"X/var/www/auris/lib/python3.10/site-packages/torch/distributed/optim/functional_adamax.py__init__s. $z_FunctionalAdamax.__init__ gradientsc Cs|jd}g}g}g}g}g}t|t|kr*tddt|ddt|d}t|jd|D]]\} } | dur|t| O}|| || | |jvrwi|j| <|j| } td| d<tj | tj d | d <tj | tj d | d <|j| } || d || d || dq4t ,t j ||||||jd |jd |jd|jd|jd|j|j|d WddS1swYdS)Nr zEthe gradients passed in does not equal to the size of the parameters!zParams length: z. zGradients length: Fr step)Z memory_formatZexp_avgZexp_infrrrr r)rrrr rrr has_complex)r rrziprZ is_complexappendrZtensorZ zeros_likeZpreserve_formatZno_gradFZadamaxrrr) r!r%r Zparams_with_gradZgradsZexp_avgsZexp_infsZ state_stepsr'paramZgradientrr"r"r#r&Csh          "z_FunctionalAdamax.stepN)rrr r FFF) __name__ __module__ __qualname__listrfloattupleboolr$rr&r"r"r"r#rs4  )r)typingrrZtorch.optim._functionalZoptimZ _functionalr*rZ,torch.distributed.optim._deprecation_warningrrr/r__annotations__rscriptrr"r"r"r#s