3jY#SSKJr SSKrSSKJr SSKJrJrJrJrJ r J r J r J r J r JrJrJrJrJr SS/r"SS\5rS S \ S \S \ S \S 3 -\lS$S\\S\\S\\S\\S\S-S\S-S\S-S\S\S-S\S\S\S\S\S\S\SS4"SjjrS rS\\S\\S\\S\\S\S-S\S-S\S\S\S\S\S\S\S\SS4S!jrS\\S\\S\\S\\S\S-S\S-S\S\S\S\S\S\S\S\SS4S"jrS\\S\\S\\S\\S\S-S\S-S\\-S\S\S\S\S\S\S\SS4S#jrg)%)castN)Tensor)_default_to_fused_or_foreach_device_dtype_check_for_fused_differentiable_doc _foreach_doc_get_scalar_dtype _get_value _maximize_doc _params_doc _to_scalar_use_grad_for_differentiable _view_as_real DeviceDict OptimizerParamsTAdagradadagradc^\rSrSrSSSSS.S\S\\-S\S\S \S \S \S-S \S \S\S-SS4U4SjjjjrU4Sjr SSjr Sr \ SSj5r SrU=r$)rNF)maximizedifferentiablefusedparamslrlr_decay weight_decayinitial_accumulator_valueepsforeachrrrreturnc ~>[U[5(aUR5S:wa [S5eSU::d[SU35eSU::d[SU35eSU::d[SU35eSU::d[SU35eSU::d[SU35eUUUUUUUU U S . n [TU]X5 U (a2U (a [ S 5eU(a [ S 5eS UlS UlURHn U S Hn URU nU S(a*[R"S[U SS9U RS9O[R"S[5S9US'[R "U 5(a [#XU5OUn[R$"X[R&S9US'M M g)NrzTensor lr must be 1-elementzInvalid learning rate: zInvalid lr_decay value: zInvalid weight_decay value: z)Invalid initial_accumulator_value value: zInvalid epsilon value: ) rrr rrr!rrrz)`fused` does not support `differentiable`z0`fused` and `foreach` cannot be `True` together.Trris_fuseddtypedevicer)step memory_formatsum) isinstancernumel ValueErrorsuper__init__ RuntimeError"_need_device_dtype_check_for_fused_step_supports_amp_scaling param_groupsstatetorchzerosr r*tensor is_complexcomplex full_likepreserve_format)selfrrrrrr r!rrrdefaultsgrouppr9 init_value __class__s M/home/wildlama/miniconda3/lib/python3.13/site-packages/torch/optim/adagrad.pyr4Adagrad.__init__s b& ! !bhhjAo:; ;by6rd;< <h7zBC Cl";L>JK K//;[T U]U5 SnURGHnURSS5 URSS5 URSS5 URSS5nUSHnURR U/5n[ U5S:wdM0[R"US5(aMP[US5nUS(a'[R"U[US 9URS 9O[R"U[5S 9US'M GM [URR55n[ U5S:g=(a [R"USS5nU(d5UH.n [R"[U S5[US 9S 9U S'M0 gg) Nr!rFrrrrr,r&r(r+)r3 __setstate__r8 setdefaultr9getlenr: is_tensorfloatr<r r*listvalues) rAr9rrCrDp_statestep_val state_valuesstep_is_tensorsrFs rGrKAdagrad.__setstate__ds| U#&&E   Y -   Z /   -u 5$$Wd3E8_**..B/w<1$U__WV_-M-M$WV_5H!>  $"3U"C#$88 #\\(:K:MNFO % '(DJJ--/0 l+q0 eoo OF #7 !!LL!F)$,=u,M& "rIcURH1nUSH%nURUnUSR5 M' M3 g)z6Calls tensor.share_memory_() on the state sum tensors.rr/N)r8r9 share_memory_)rArCrDr9s rG share_memoryAdagrad.share_memorys=&&E8_ 1 e **,%'rIcxSupgUSGHnURcMUS(a$[USS5(a[U5 SUlXhRR-nU[ R "U5-nURU5 URUR5 URUn [U 5S:XaUS(a [U5 US(a*[ R"S[USS 9URS 9O[ R"S [5S 9U S 'URSn [ R "U5(a [X5OU n [ R "X[ R"S9U S'URU S5 URU S 5 GM Xg4$)N)FFrrr6TFrr%r&r(r$r+r,rr-r/)gradgetattrrr6 is_sparser:r=appendr9rNr;r r*r<rBr>r?r@) rArCparams_with_gradgrads state_sums state_stepshas_sparse_grad has_complexrDr9rrEs rG _init_groupAdagrad._init_groups'3$xAvv!>g8'' 2!4>CD;66#3#33u//22  ''* QVV$ 1 u:?W~5a8!>  "3U7^"L#$88 #\\#5F5HI&M15 31- !++A.. 9U6 $)??U5J5J$E%L!!%,/""5=1Q!T++rIchSnUb%[R"5 U"5nSSS5 URHfn/n/n/n/nURX4XVU5up[ UUUUUSUSUSUSUUSUSUSU US [ US S5[ US S5S 9 Mh U$!,(df  N=f) zPerform a single optimization step. Args: closure (Callable, optional): A closure that reevaluates the model and returns the loss. Nrrrr r!rrr grad_scale found_inf) rrrr rfr!rrrgrrkrl)r: enable_gradr8rhrr_) rAclosurelossrCrbrcrdrerfrgs rGr, Adagrad.steps  ""$y%&&E-/ "$E')J(*K+/+;+;K, (O  ;">2z*%L /i(z*$%56'Gn"4t<!$ T:! ': A%$s B## B1)r6r7)g{Gz?rrrg|=N)r"NN)__name__ __module__ __qualname____firstlineno__rrPrboolr4rKr[rhrr,__static_attributes__ __classcell__)rFs@rGrrs"+,#E$!EE FNE E  E $) EEEEEd{E EEN!F-,,\"*"*rIa[Implements Adagrad algorithm. .. math:: \begin{aligned} &\rule{110mm}{0.4pt} \\ &\textbf{input} : \gamma \text{ (lr)}, \: \theta_0 \text{ (params)}, \: f(\theta) \text{ (objective)}, \: \lambda \text{ (weight decay)}, \\ &\hspace{12mm} \tau \text{ (initial accumulator value)}, \: \eta\text{ (lr decay)}\\ &\textbf{initialize} : state\_sum_0 \leftarrow \tau \\[-1.ex] &\rule{110mm}{0.4pt} \\ &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do} \\ &\hspace{5mm}g_t \leftarrow \nabla_{\theta} f_t (\theta_{t-1}) \\ &\hspace{5mm} \tilde{\gamma} \leftarrow \gamma / (1 +(t-1) \eta) \\ &\hspace{5mm} \textbf{if} \: \lambda \neq 0 \\ &\hspace{10mm} g_t \leftarrow g_t + \lambda \theta_{t-1} \\ &\hspace{5mm}state\_sum_t \leftarrow state\_sum_{t-1} + g^2_t \\ &\hspace{5mm}\theta_t \leftarrow \theta_{t-1}- \tilde{\gamma} \frac{g_t}{\sqrt{state\_sum_t}+\epsilon} \\ &\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 `Adaptive Subgradient Methods for Online Learning and Stochastic Optimization`_. z Args: a lr (float, Tensor, optional): learning rate (default: 1e-2) lr_decay (float, optional): learning rate decay (default: 0) weight_decay (float, optional): weight decay (L2 penalty) (default: 0) initial_accumulator_value (float, optional): initial value of the sum of squares of gradients (default: 0) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-10) z a fused (bool, optional): whether the fused implementation (CPU and CUDA only) is used. Currently, `torch.float64`, `torch.float32`, `torch.float16`, and `torch.bfloat16` are supported. (default: None). Please note that the fused implementations does not support sparse or complex gradients. .. _Adaptive Subgradient Methods for Online Learning and Stochastic Optimization: http://jmlr.org/papers/v12/duchi11a.html rrcrdrerrkrlrfr!rrgrrrr rr"c L[SU55(d [S5eUcUc [X SS9unnUcSnUcSnU(a.[RR 5(a [S5eU(a.[RR 5(a [S5eU(a*[RR 5(d[ nO7U(a*[RR 5(d[nO[nU"UUUUU U U UUUU U UUS9 g) zlFunctional API that performs Adagrad algorithm computation. See :class:`~torch.optim.Adagrad` for details. c3V# UHn[U[R5v M! g7frq)r0r:r).0ts rG adagrad..6s@Kqz!U\\**Ks')zPAPI has changed, `state_steps` argument must contain a list of singleton tensorsNF) use_fusedz6torch.jit.script not supported with foreach optimizersz4torch.jit.script not supported with fused optimizers rrrr rfrrrgrkrl) allr5rr:jit is_scripting_fused_adagrad_multi_tensor_adagrad_single_tensor_adagrad)rrcrdrerrkrlrfr!rrgrrrr r_funcs rGrrs2 @K@ @ @ ^   }1 e 7 }599))++STT ''))QRR UYY++-- //11$%  ! '%rIcPUR5n[R"XU5$rq)sizer:sparse_coo_tensor)r^ grad_indicesrRrs rG _make_sparsergs 99;D  " "< >>rIc UcUb [S5e[RR5(d [ U5n[ XX#SS9GH upnnUS- n[ U5nU (dUOU*nUS:wa+UR(a [S5eURXS9nUSUS- U--- nUR(aUR5nUR5nUR5nUR[UUURS555 UR!U5nUR5R#5RU 5nUR[UUUU- 5U*S9 GM/[R$"U5nU(aB[R&"U5n[R&"U5n[R&"U5nUR)XSS 9 U (aUR+5U -nOUR+5RU 5nUR-UUU*S 9 U(dGM[R."U5n[R."U5nGM# g) N,Expected grad_scale and found_inf to be NoneT)strictrrz;weight_decay option is not compatible with sparse gradientsalphavalue)AssertionErrorr:rrrzipr r`r5addcoalesce_indices_valuesadd_rpow sparse_masksqrt_r= view_as_realaddcmul_sqrtaddcdiv_view_as_complex)rrcrdrerkrlrrrr rfrrrgparamr^ state_sumstep_tr,clrr grad_valuesstd std_valuesr=s rGrrls"!6KLL 99 ! ! # # ^*-zt+&Y ! &!#t$ 1 ~~"Q88E86DAX--. >>==?D==?L,,.K NN<lKOOAUSR (a*[R""U[R$"SSS 9SS 9 O[R""US 5 US:wa4U (a[R""UUUS 9 O[R&"UUUS 9nUVs/sHnU*S [)U5S - U--- PM nn[R*"UUUS S 9 [R,"U5n[R""UU 5 US:wdU (a[R."UU5 UnO[R0"UU5n[R2"UUU5 GMJ gs snf) Nz#_foreach ops don't support autogradrrc38# UHoRv M g7frq)r`)r{r^s rGr}(_multi_tensor_adagrad..s9 '3tNN|sTrg?cpu)r*rrr)rrNrr"_group_tensors_by_device_and_dtyperRrrQranyrrr: _foreach_negcompiler is_compilingis_cpu _foreach_add_r< _foreach_addr _foreach_addcmul_ _foreach_sqrt _foreach_mul_ _foreach_mul_foreach_addcdiv_)rrcrdrerkrlrrrr rfrrrggrouped_tensorlistsdevice_params_ device_grads_device_state_sums_device_state_steps_r device_params device_gradsdevice_state_sumsdevice_state_stepsdevice_has_sparse_gradr, minus_clrr numerators rGrrs"BCC!6KLL 6{a BB#FF  0 & & (   T&\>: DL-8  f/AB!$v,0CD!0" S9 '39 6  " "!")! $!-'%#    -7H I  --l;L ~~**,,1CA1F1M1M   "ELLU$C3     2A 6 1 ##L-|T$11 -|  GY FXdRC1 4(1,88 9FX    1<UVW!!"34 C% 1     i 8$I**<CI  y#>Q )p s0"J4cU(dgU (dU (a [S5eU (a [S5eUbURU0O0nUbURU0O0n[U[5(a'[ UR5S:waURU0OSn[ R "XX#/5nUR5GH9uunnuunnnnn[[[U5n[[[U5n[[[U5n[[[U5nSunnUb URUURUSS95nUb URUURUSS95nUbUU;aURUSS9UU'UUn[R"US5 [R"UUUUUUUU U UUS 9 UcGM[R"UU/[!U5-5 GM< g) Nz5`fused` does not support sparse grad or complex paramz  9%B&b&11c"))n6MBSW  BB  0O           T&\>: DL-8  f/AB!$v,0CD.8++  ! / : : f4 @!   -88 V$ ?    6#8 ee6eEGFOB .2     %(&   '   "%5$6=O9P$P C !rI)NNNFNFF)typingrr:r optimizerrrrr r r r r rrrrrr__all__r__doc__rQrvrPrrrrrr%rIrGrs $ i KiK^4      5.p $#" G LG <GV Gf G $; G  G}GGD[GGG G !G"#G$ %G&'G( )GT? A= LA= <A=V A=f A=  A= } A= A=A=A= A=A=A=A=A=  !A=Hl? Ll? <l?V l?f l?  l? } l? l?l?l? l?l?l?l?l?  !l?^S LS <SV Sf S  S } S SSS SSSSS  !SrI