U ʹj@sjUddlmZmZmZmZddlZddlmmZ ddlm Z gZ ee e d<ejjGdddZdS))DictListOptionalTupleN)Tensor__all__c @sdeZdZdeeeeeefeeeeeeed ddZee ed d d Z ee ed d dZ dS)_FunctionalAdamWMbP?g?g+?:0yE>{Gz?F) paramslrbetaseps weight_decayamsgradmaximizeforeachfused_allow_empty_param_listc Csd|kstd|d|ks,td|d|dkrDdksXntd|dd|dkrpdksntd|dd|kstd ||||d|d|d |_||_||_||_| |_tjt tj t t tj ffi|_ t |dkr | s td d |i|_dS) NzInvalid learning rate: zInvalid epsilon value: rg?z#Invalid beta parameter at index 0: z#Invalid beta parameter at index 1: zInvalid weight_decay value: )rrbeta1beta2rz%optimizer got an empty parameter listr ) ValueErrordefaultsrrrrtorchjitZannotaterrstrstatelen param_group) selfr rrrrrrrrrr$g/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torch/distributed/optim/functional_adamw.py__init__s0 $z_FunctionalAdamW.__init__)paramgradc CsTg}g}g}g}g}g}|dk r4||||||jkri|j|<|j|} td| d<tj|tjd| d<tj|tjd| d<|jrtj|tjd| d<|j|} || d|| d|jr|| d|| dtXtj |||||||j|j |j d|j d|j d |j d |j d |j |j ddd W5QRXdS) NrstepZ memory_formatexp_avg exp_avg_sqmax_exp_avg_sqrrrrr rrrrrrrrrZ grad_scaleZ found_inf)appendr rtensor zeros_likepreserve_formatrno_gradFadamwrrrr) r#r'r(params_with_gradgradsexp_avgs exp_avg_sqsmax_exp_avg_sqs state_stepsr r$r$r% step_paramAsh          z_FunctionalAdamW.step_param) gradientsc Cs|jd}g}g}g}g}g}g}t|t|krXtddt|ddt|t|jd|D]\} } | dk rh|| || | |jkri|j| <|j| } td| d<tj| tj d| d <tj| tj d| d <|j rtj| tj d| d <|j| } || d || d |j r6|| d || dqht Xt j |||||||j |j|jd |jd |jd|jd|jd|j|jdddW5QRXdS)Nr zEthe gradients passed in does not equal to the size of the parameters!zParams length: z. zGradients length: rr)r*r+r,r-rrrrrr.)r"r!rzipr/r rr0r1r2rr3r4r5rrrr) r#r=r r6r7r8r9r:r;r'Zgradientr r$r$r%r)|s|            z_FunctionalAdamW.stepN) r r r r FFFFF) __name__ __module__ __qualname__rrfloatrboolr&rr<r)r$r$r$r%rs.  ,;r)typingrrrrrZtorch.optim._functionalZoptimZ _functionalr4rrr__annotations__rscriptrr$r$r$r%s